notenergydrinks/eden
1
0
Fork 0
forked from eden-emu/eden
Code Pull requests Activity

shader: Remove old shader management

Browse source
This commit is contained in:
ReinUsesLisp 2021-02-16 20:52:12 -03:00 • committed by ameerj
parent 58914796c0
commit c67d64365a
83 changed files with 57 additions and 19625 deletions
Download patch file Download diff file Expand all files Collapse all files

56
CMakeModules/GenerateSCMRev.cmake
View file

@ -51,61 +51,7 @@ endif()
# The variable SRC_DIR must be passed into the script (since it uses the current build directory for all values of CMAKE_*_DIR)
set(VIDEO_CORE "${SRC_DIR}/src/video_core")
set(HASH_FILES
"${VIDEO_CORE}/renderer_opengl/gl_arb_decompiler.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_arb_decompiler.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_cache.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_cache.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_decompiler.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_decompiler.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_disk_cache.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_disk_cache.h"
"${VIDEO_CORE}/shader/decode/arithmetic.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_half.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_half_immediate.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_immediate.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_integer.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_integer_immediate.cpp"
"${VIDEO_CORE}/shader/decode/bfe.cpp"
"${VIDEO_CORE}/shader/decode/bfi.cpp"
"${VIDEO_CORE}/shader/decode/conversion.cpp"
"${VIDEO_CORE}/shader/decode/ffma.cpp"
"${VIDEO_CORE}/shader/decode/float_set.cpp"
"${VIDEO_CORE}/shader/decode/float_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/half_set.cpp"
"${VIDEO_CORE}/shader/decode/half_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/hfma2.cpp"
"${VIDEO_CORE}/shader/decode/image.cpp"
"${VIDEO_CORE}/shader/decode/integer_set.cpp"
"${VIDEO_CORE}/shader/decode/integer_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/memory.cpp"
"${VIDEO_CORE}/shader/decode/texture.cpp"
"${VIDEO_CORE}/shader/decode/other.cpp"
"${VIDEO_CORE}/shader/decode/predicate_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/predicate_set_register.cpp"
"${VIDEO_CORE}/shader/decode/register_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/shift.cpp"
"${VIDEO_CORE}/shader/decode/video.cpp"
"${VIDEO_CORE}/shader/decode/warp.cpp"
"${VIDEO_CORE}/shader/decode/xmad.cpp"
"${VIDEO_CORE}/shader/ast.cpp"
"${VIDEO_CORE}/shader/ast.h"
"${VIDEO_CORE}/shader/compiler_settings.cpp"
"${VIDEO_CORE}/shader/compiler_settings.h"
"${VIDEO_CORE}/shader/control_flow.cpp"
"${VIDEO_CORE}/shader/control_flow.h"
"${VIDEO_CORE}/shader/decode.cpp"
"${VIDEO_CORE}/shader/expr.cpp"
"${VIDEO_CORE}/shader/expr.h"
"${VIDEO_CORE}/shader/node.h"
"${VIDEO_CORE}/shader/node_helper.cpp"
"${VIDEO_CORE}/shader/node_helper.h"
"${VIDEO_CORE}/shader/registry.cpp"
"${VIDEO_CORE}/shader/registry.h"
"${VIDEO_CORE}/shader/shader_ir.cpp"
"${VIDEO_CORE}/shader/shader_ir.h"
"${VIDEO_CORE}/shader/track.cpp"
"${VIDEO_CORE}/shader/transform_feedback.cpp"
"${VIDEO_CORE}/shader/transform_feedback.h"
# ...
)
set(COMBINED "")
foreach (F IN LISTS HASH_FILES)

2
externals/Vulkan-Headers vendored

@ -1 +1 @@
Subproject commit 8188e3fbbc105591064093440f88081fb957d4f0
Subproject commit 07c4a37bcf41ea50aef6e98236abdfe8089fb4c6

2
externals/sirit vendored

@ -1 +1 @@
Subproject commit 200310e8faa756b9869dd6dfc902c255246ac74a
Subproject commit a39596358a3a5488c06554c0c15184a6af71e433

56
src/common/CMakeLists.txt
View file

@ -32,61 +32,7 @@ add_custom_command(OUTPUT scm_rev.cpp
DEPENDS
# WARNING! It was too much work to try and make a common location for this list,
# so if you need to change it, please update CMakeModules/GenerateSCMRev.cmake as well
"${VIDEO_CORE}/renderer_opengl/gl_arb_decompiler.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_arb_decompiler.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_cache.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_cache.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_decompiler.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_decompiler.h"
"${VIDEO_CORE}/renderer_opengl/gl_shader_disk_cache.cpp"
"${VIDEO_CORE}/renderer_opengl/gl_shader_disk_cache.h"
"${VIDEO_CORE}/shader/decode/arithmetic.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_half.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_half_immediate.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_immediate.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_integer.cpp"
"${VIDEO_CORE}/shader/decode/arithmetic_integer_immediate.cpp"
"${VIDEO_CORE}/shader/decode/bfe.cpp"
"${VIDEO_CORE}/shader/decode/bfi.cpp"
"${VIDEO_CORE}/shader/decode/conversion.cpp"
"${VIDEO_CORE}/shader/decode/ffma.cpp"
"${VIDEO_CORE}/shader/decode/float_set.cpp"
"${VIDEO_CORE}/shader/decode/float_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/half_set.cpp"
"${VIDEO_CORE}/shader/decode/half_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/hfma2.cpp"
"${VIDEO_CORE}/shader/decode/image.cpp"
"${VIDEO_CORE}/shader/decode/integer_set.cpp"
"${VIDEO_CORE}/shader/decode/integer_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/memory.cpp"
"${VIDEO_CORE}/shader/decode/texture.cpp"
"${VIDEO_CORE}/shader/decode/other.cpp"
"${VIDEO_CORE}/shader/decode/predicate_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/predicate_set_register.cpp"
"${VIDEO_CORE}/shader/decode/register_set_predicate.cpp"
"${VIDEO_CORE}/shader/decode/shift.cpp"
"${VIDEO_CORE}/shader/decode/video.cpp"
"${VIDEO_CORE}/shader/decode/warp.cpp"
"${VIDEO_CORE}/shader/decode/xmad.cpp"
"${VIDEO_CORE}/shader/ast.cpp"
"${VIDEO_CORE}/shader/ast.h"
"${VIDEO_CORE}/shader/compiler_settings.cpp"
"${VIDEO_CORE}/shader/compiler_settings.h"
"${VIDEO_CORE}/shader/control_flow.cpp"
"${VIDEO_CORE}/shader/control_flow.h"
"${VIDEO_CORE}/shader/decode.cpp"
"${VIDEO_CORE}/shader/expr.cpp"
"${VIDEO_CORE}/shader/expr.h"
"${VIDEO_CORE}/shader/node.h"
"${VIDEO_CORE}/shader/node_helper.cpp"
"${VIDEO_CORE}/shader/node_helper.h"
"${VIDEO_CORE}/shader/registry.cpp"
"${VIDEO_CORE}/shader/registry.h"
"${VIDEO_CORE}/shader/shader_ir.cpp"
"${VIDEO_CORE}/shader/shader_ir.h"
"${VIDEO_CORE}/shader/track.cpp"
"${VIDEO_CORE}/shader/transform_feedback.cpp"
"${VIDEO_CORE}/shader/transform_feedback.h"
# ...
# and also check that the scm_rev files haven't changed
"${CMAKE_CURRENT_SOURCE_DIR}/scm_rev.cpp.in"
"${CMAKE_CURRENT_SOURCE_DIR}/scm_rev.h"

64
src/video_core/CMakeLists.txt
View file

@ -29,7 +29,6 @@ add_library(video_core STATIC
dirty_flags.h
dma_pusher.cpp
dma_pusher.h
engines/const_buffer_engine_interface.h
engines/const_buffer_info.h
engines/engine_interface.h
engines/engine_upload.cpp
@ -61,8 +60,6 @@ add_library(video_core STATIC
gpu.h
gpu_thread.cpp
gpu_thread.h
guest_driver.cpp
guest_driver.h
memory_manager.cpp
memory_manager.h
query_cache.h
@ -71,8 +68,6 @@ add_library(video_core STATIC
rasterizer_interface.h
renderer_base.cpp
renderer_base.h
renderer_opengl/gl_arb_decompiler.cpp
renderer_opengl/gl_arb_decompiler.h
renderer_opengl/gl_buffer_cache.cpp
renderer_opengl/gl_buffer_cache.h
renderer_opengl/gl_device.cpp
@ -85,10 +80,6 @@ add_library(video_core STATIC
renderer_opengl/gl_resource_manager.h
renderer_opengl/gl_shader_cache.cpp
renderer_opengl/gl_shader_cache.h
renderer_opengl/gl_shader_decompiler.cpp
renderer_opengl/gl_shader_decompiler.h
renderer_opengl/gl_shader_disk_cache.cpp
renderer_opengl/gl_shader_disk_cache.h
renderer_opengl/gl_shader_manager.cpp
renderer_opengl/gl_shader_manager.h
renderer_opengl/gl_shader_util.cpp
@ -128,8 +119,6 @@ add_library(video_core STATIC
renderer_vulkan/vk_descriptor_pool.h
renderer_vulkan/vk_fence_manager.cpp
renderer_vulkan/vk_fence_manager.h
renderer_vulkan/vk_graphics_pipeline.cpp
renderer_vulkan/vk_graphics_pipeline.h
renderer_vulkan/vk_master_semaphore.cpp
renderer_vulkan/vk_master_semaphore.h
renderer_vulkan/vk_pipeline_cache.cpp
@ -142,8 +131,6 @@ add_library(video_core STATIC
renderer_vulkan/vk_resource_pool.h
renderer_vulkan/vk_scheduler.cpp
renderer_vulkan/vk_scheduler.h
renderer_vulkan/vk_shader_decompiler.cpp
renderer_vulkan/vk_shader_decompiler.h
renderer_vulkan/vk_shader_util.cpp
renderer_vulkan/vk_shader_util.h
renderer_vulkan/vk_staging_buffer_pool.cpp
@ -159,57 +146,6 @@ add_library(video_core STATIC
shader_cache.h
shader_notify.cpp
shader_notify.h
shader/decode/arithmetic.cpp
shader/decode/arithmetic_immediate.cpp
shader/decode/bfe.cpp
shader/decode/bfi.cpp
shader/decode/shift.cpp
shader/decode/arithmetic_integer.cpp
shader/decode/arithmetic_integer_immediate.cpp
shader/decode/arithmetic_half.cpp
shader/decode/arithmetic_half_immediate.cpp
shader/decode/ffma.cpp
shader/decode/hfma2.cpp
shader/decode/conversion.cpp
shader/decode/memory.cpp
shader/decode/texture.cpp
shader/decode/image.cpp
shader/decode/float_set_predicate.cpp
shader/decode/integer_set_predicate.cpp
shader/decode/half_set_predicate.cpp
shader/decode/predicate_set_register.cpp
shader/decode/predicate_set_predicate.cpp
shader/decode/register_set_predicate.cpp
shader/decode/float_set.cpp
shader/decode/integer_set.cpp
shader/decode/half_set.cpp
shader/decode/video.cpp
shader/decode/warp.cpp
shader/decode/xmad.cpp
shader/decode/other.cpp
shader/ast.cpp
shader/ast.h
shader/async_shaders.cpp
shader/async_shaders.h
shader/compiler_settings.cpp
shader/compiler_settings.h
shader/control_flow.cpp
shader/control_flow.h
shader/decode.cpp
shader/expr.cpp
shader/expr.h
shader/memory_util.cpp
shader/memory_util.h
shader/node_helper.cpp
shader/node_helper.h
shader/node.h
shader/registry.cpp
shader/registry.h
shader/shader_ir.cpp
shader/shader_ir.h
shader/track.cpp
shader/transform_feedback.cpp
shader/transform_feedback.h
surface.cpp
surface.h
texture_cache/accelerated_swizzle.cpp

103
src/video_core/engines/const_buffer_engine_interface.h
View file

@ -1,103 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <type_traits>
#include "common/bit_field.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/engines/shader_type.h"
#include "video_core/guest_driver.h"
#include "video_core/textures/texture.h"
namespace Tegra::Engines {
struct SamplerDescriptor {
union {
u32 raw = 0;
BitField<0, 2, Tegra::Shader::TextureType> texture_type;
BitField<2, 3, Tegra::Texture::ComponentType> r_type;
BitField<5, 1, u32> is_array;
BitField<6, 1, u32> is_buffer;
BitField<7, 1, u32> is_shadow;
BitField<8, 3, Tegra::Texture::ComponentType> g_type;
BitField<11, 3, Tegra::Texture::ComponentType> b_type;
BitField<14, 3, Tegra::Texture::ComponentType> a_type;
BitField<17, 7, Tegra::Texture::TextureFormat> format;
};
bool operator==(const SamplerDescriptor& rhs) const noexcept {
return raw == rhs.raw;
}
bool operator!=(const SamplerDescriptor& rhs) const noexcept {
return !operator==(rhs);
}
static SamplerDescriptor FromTIC(const Tegra::Texture::TICEntry& tic) {
using Tegra::Shader::TextureType;
SamplerDescriptor result;
result.format.Assign(tic.format.Value());
result.r_type.Assign(tic.r_type.Value());
result.g_type.Assign(tic.g_type.Value());
result.b_type.Assign(tic.b_type.Value());
result.a_type.Assign(tic.a_type.Value());
switch (tic.texture_type.Value()) {
case Tegra::Texture::TextureType::Texture1D:
result.texture_type.Assign(TextureType::Texture1D);
return result;
case Tegra::Texture::TextureType::Texture2D:
result.texture_type.Assign(TextureType::Texture2D);
return result;
case Tegra::Texture::TextureType::Texture3D:
result.texture_type.Assign(TextureType::Texture3D);
return result;
case Tegra::Texture::TextureType::TextureCubemap:
result.texture_type.Assign(TextureType::TextureCube);
return result;
case Tegra::Texture::TextureType::Texture1DArray:
result.texture_type.Assign(TextureType::Texture1D);
result.is_array.Assign(1);
return result;
case Tegra::Texture::TextureType::Texture2DArray:
result.texture_type.Assign(TextureType::Texture2D);
result.is_array.Assign(1);
return result;
case Tegra::Texture::TextureType::Texture1DBuffer:
result.texture_type.Assign(TextureType::Texture1D);
result.is_buffer.Assign(1);
return result;
case Tegra::Texture::TextureType::Texture2DNoMipmap:
result.texture_type.Assign(TextureType::Texture2D);
return result;
case Tegra::Texture::TextureType::TextureCubeArray:
result.texture_type.Assign(TextureType::TextureCube);
result.is_array.Assign(1);
return result;
default:
result.texture_type.Assign(TextureType::Texture2D);
return result;
}
}
};
static_assert(std::is_trivially_copyable_v<SamplerDescriptor>);
class ConstBufferEngineInterface {
public:
virtual ~ConstBufferEngineInterface() = default;
virtual u32 AccessConstBuffer32(ShaderType stage, u64 const_buffer, u64 offset) const = 0;
virtual SamplerDescriptor AccessBoundSampler(ShaderType stage, u64 offset) const = 0;
virtual SamplerDescriptor AccessBindlessSampler(ShaderType stage, u64 const_buffer,
u64 offset) const = 0;
virtual SamplerDescriptor AccessSampler(u32 handle) const = 0;
virtual u32 GetBoundBuffer() const = 0;
virtual VideoCore::GuestDriverProfile& AccessGuestDriverProfile() = 0;
virtual const VideoCore::GuestDriverProfile& AccessGuestDriverProfile() const = 0;
};
} // namespace Tegra::Engines

44
src/video_core/engines/kepler_compute.cpp
View file

@ -57,53 +57,11 @@ void KeplerCompute::CallMultiMethod(u32 method, const u32* base_start, u32 amoun
}
}
u32 KeplerCompute::AccessConstBuffer32(ShaderType stage, u64 const_buffer, u64 offset) const {
ASSERT(stage == ShaderType::Compute);
const auto& buffer = launch_description.const_buffer_config[const_buffer];
u32 result;
std::memcpy(&result, memory_manager.GetPointer(buffer.Address() + offset), sizeof(u32));
return result;
}
SamplerDescriptor KeplerCompute::AccessBoundSampler(ShaderType stage, u64 offset) const {
return AccessBindlessSampler(stage, regs.tex_cb_index, offset * sizeof(Texture::TextureHandle));
}
SamplerDescriptor KeplerCompute::AccessBindlessSampler(ShaderType stage, u64 const_buffer,
u64 offset) const {
ASSERT(stage == ShaderType::Compute);
const auto& tex_info_buffer = launch_description.const_buffer_config[const_buffer];
const GPUVAddr tex_info_address = tex_info_buffer.Address() + offset;
return AccessSampler(memory_manager.Read<u32>(tex_info_address));
}
SamplerDescriptor KeplerCompute::AccessSampler(u32 handle) const {
const Texture::TextureHandle tex_handle{handle};
const Texture::TICEntry tic = GetTICEntry(tex_handle.tic_id);
const Texture::TSCEntry tsc = GetTSCEntry(tex_handle.tsc_id);
SamplerDescriptor result = SamplerDescriptor::FromTIC(tic);
result.is_shadow.Assign(tsc.depth_compare_enabled.Value());
return result;
}
VideoCore::GuestDriverProfile& KeplerCompute::AccessGuestDriverProfile() {
return rasterizer->AccessGuestDriverProfile();
}
const VideoCore::GuestDriverProfile& KeplerCompute::AccessGuestDriverProfile() const {
return rasterizer->AccessGuestDriverProfile();
}
void KeplerCompute::ProcessLaunch() {
const GPUVAddr launch_desc_loc = regs.launch_desc_loc.Address();
memory_manager.ReadBlockUnsafe(launch_desc_loc, &launch_description,
LaunchParams::NUM_LAUNCH_PARAMETERS * sizeof(u32));
const GPUVAddr code_addr = regs.code_loc.Address() + launch_description.program_start;
LOG_TRACE(HW_GPU, "Compute invocation launched at address 0x{:016x}", code_addr);
rasterizer->DispatchCompute(code_addr);
rasterizer->DispatchCompute();
}
Texture::TICEntry KeplerCompute::GetTICEntry(u32 tic_index) const {

20
src/video_core/engines/kepler_compute.h
View file

@ -10,7 +10,6 @@
#include "common/bit_field.h"
#include "common/common_funcs.h"
#include "common/common_types.h"
#include "video_core/engines/const_buffer_engine_interface.h"
#include "video_core/engines/engine_interface.h"
#include "video_core/engines/engine_upload.h"
#include "video_core/engines/shader_type.h"
@ -40,7 +39,7 @@ namespace Tegra::Engines {
#define KEPLER_COMPUTE_REG_INDEX(field_name) \
(offsetof(Tegra::Engines::KeplerCompute::Regs, field_name) / sizeof(u32))
class KeplerCompute final : public ConstBufferEngineInterface, public EngineInterface {
class KeplerCompute final : public EngineInterface {
public:
explicit KeplerCompute(Core::System& system, MemoryManager& memory_manager);
~KeplerCompute();
@ -209,23 +208,6 @@ public:
void CallMultiMethod(u32 method, const u32* base_start, u32 amount,
u32 methods_pending) override;
u32 AccessConstBuffer32(ShaderType stage, u64 const_buffer, u64 offset) const override;
SamplerDescriptor AccessBoundSampler(ShaderType stage, u64 offset) const override;
SamplerDescriptor AccessBindlessSampler(ShaderType stage, u64 const_buffer,
u64 offset) const override;
SamplerDescriptor AccessSampler(u32 handle) const override;
u32 GetBoundBuffer() const override {
return regs.tex_cb_index;
}
VideoCore::GuestDriverProfile& AccessGuestDriverProfile() override;
const VideoCore::GuestDriverProfile& AccessGuestDriverProfile() const override;
private:
void ProcessLaunch();

38
src/video_core/engines/maxwell_3d.cpp
View file

@ -670,42 +670,4 @@ void Maxwell3D::ProcessClearBuffers() {
rasterizer->Clear();
}
u32 Maxwell3D::AccessConstBuffer32(ShaderType stage, u64 const_buffer, u64 offset) const {
ASSERT(stage != ShaderType::Compute);
const auto& shader_stage = state.shader_stages[static_cast<std::size_t>(stage)];
const auto& buffer = shader_stage.const_buffers[const_buffer];
return memory_manager.Read<u32>(buffer.address + offset);
}
SamplerDescriptor Maxwell3D::AccessBoundSampler(ShaderType stage, u64 offset) const {
return AccessBindlessSampler(stage, regs.tex_cb_index, offset * sizeof(Texture::TextureHandle));
}
SamplerDescriptor Maxwell3D::AccessBindlessSampler(ShaderType stage, u64 const_buffer,
u64 offset) const {
ASSERT(stage != ShaderType::Compute);
const auto& shader = state.shader_stages[static_cast<std::size_t>(stage)];
const auto& tex_info_buffer = shader.const_buffers[const_buffer];
const GPUVAddr tex_info_address = tex_info_buffer.address + offset;
return AccessSampler(memory_manager.Read<u32>(tex_info_address));
}
SamplerDescriptor Maxwell3D::AccessSampler(u32 handle) const {
const Texture::TextureHandle tex_handle{handle};
const Texture::TICEntry tic = GetTICEntry(tex_handle.tic_id);
const Texture::TSCEntry tsc = GetTSCEntry(tex_handle.tsc_id);
SamplerDescriptor result = SamplerDescriptor::FromTIC(tic);
result.is_shadow.Assign(tsc.depth_compare_enabled.Value());
return result;
}
VideoCore::GuestDriverProfile& Maxwell3D::AccessGuestDriverProfile() {
return rasterizer->AccessGuestDriverProfile();
}
const VideoCore::GuestDriverProfile& Maxwell3D::AccessGuestDriverProfile() const {
return rasterizer->AccessGuestDriverProfile();
}
} // namespace Tegra::Engines

20
src/video_core/engines/maxwell_3d.h
View file

@ -17,7 +17,6 @@
#include "common/common_funcs.h"
#include "common/common_types.h"
#include "common/math_util.h"
#include "video_core/engines/const_buffer_engine_interface.h"
#include "video_core/engines/const_buffer_info.h"
#include "video_core/engines/engine_interface.h"
#include "video_core/engines/engine_upload.h"
@ -49,7 +48,7 @@ namespace Tegra::Engines {
#define MAXWELL3D_REG_INDEX(field_name) \
(offsetof(Tegra::Engines::Maxwell3D::Regs, field_name) / sizeof(u32))
class Maxwell3D final : public ConstBufferEngineInterface, public EngineInterface {
class Maxwell3D final : public EngineInterface {
public:
explicit Maxwell3D(Core::System& system, MemoryManager& memory_manager);
~Maxwell3D();
@ -1424,23 +1423,6 @@ public:
void FlushMMEInlineDraw();
u32 AccessConstBuffer32(ShaderType stage, u64 const_buffer, u64 offset) const override;
SamplerDescriptor AccessBoundSampler(ShaderType stage, u64 offset) const override;
SamplerDescriptor AccessBindlessSampler(ShaderType stage, u64 const_buffer,
u64 offset) const override;
SamplerDescriptor AccessSampler(u32 handle) const override;
u32 GetBoundBuffer() const override {
return regs.tex_cb_index;
}
VideoCore::GuestDriverProfile& AccessGuestDriverProfile() override;
const VideoCore::GuestDriverProfile& AccessGuestDriverProfile() const override;
bool ShouldExecute() const {
return execute_on;
}

37
src/video_core/guest_driver.cpp
View file

@ -1,37 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <limits>
#include <vector>
#include "common/common_types.h"
#include "video_core/guest_driver.h"
namespace VideoCore {
void GuestDriverProfile::DeduceTextureHandlerSize(std::vector<u32> bound_offsets) {
if (texture_handler_size) {
return;
}
const std::size_t size = bound_offsets.size();
if (size < 2) {
return;
}
std::sort(bound_offsets.begin(), bound_offsets.end(), std::less{});
u32 min_val = std::numeric_limits<u32>::max();
for (std::size_t i = 1; i < size; ++i) {
if (bound_offsets[i] == bound_offsets[i - 1]) {
continue;
}
const u32 new_min = bound_offsets[i] - bound_offsets[i - 1];
min_val = std::min(min_val, new_min);
}
if (min_val > 2) {
return;
}
texture_handler_size = min_texture_handler_size * min_val;
}
} // namespace VideoCore

46
src/video_core/guest_driver.h
View file

@ -1,46 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <optional>
#include <vector>
#include "common/common_types.h"
namespace VideoCore {
/**
* The GuestDriverProfile class is used to learn about the GPU drivers behavior and collect
* information necessary for impossible to avoid HLE methods like shader tracks as they are
* Entscheidungsproblems.
*/
class GuestDriverProfile {
public:
explicit GuestDriverProfile() = default;
explicit GuestDriverProfile(std::optional<u32> texture_handler_size_)
: texture_handler_size{texture_handler_size_} {}
void DeduceTextureHandlerSize(std::vector<u32> bound_offsets);
u32 GetTextureHandlerSize() const {
return texture_handler_size.value_or(default_texture_handler_size);
}
bool IsTextureHandlerSizeKnown() const {
return texture_handler_size.has_value();
}
private:
// Minimum size of texture handler any driver can use.
static constexpr u32 min_texture_handler_size = 4;
// This goes with Vulkan and OpenGL standards but Nvidia GPUs can easily use 4 bytes instead.
// Thus, certain drivers may squish the size.
static constexpr u32 default_texture_handler_size = 8;
std::optional<u32> texture_handler_size = default_texture_handler_size;
};
} // namespace VideoCore

16
src/video_core/rasterizer_interface.h
View file

@ -11,7 +11,6 @@
#include "common/common_types.h"
#include "video_core/engines/fermi_2d.h"
#include "video_core/gpu.h"
#include "video_core/guest_driver.h"
namespace Tegra {
class MemoryManager;
@ -45,7 +44,7 @@ public:
virtual void Clear() = 0;
/// Dispatches a compute shader invocation
virtual void DispatchCompute(GPUVAddr code_addr) = 0;
virtual void DispatchCompute() = 0;
/// Resets the counter of a query
virtual void ResetCounter(QueryType type) = 0;
@ -136,18 +135,5 @@ public:
/// Initialize disk cached resources for the game being emulated
virtual void LoadDiskResources(u64 title_id, std::stop_token stop_loading,
const DiskResourceLoadCallback& callback) {}
/// Grant access to the Guest Driver Profile for recording/obtaining info on the guest driver.
[[nodiscard]] GuestDriverProfile& AccessGuestDriverProfile() {
return guest_driver_profile;
}
/// Grant access to the Guest Driver Profile for recording/obtaining info on the guest driver.
[[nodiscard]] const GuestDriverProfile& AccessGuestDriverProfile() const {
return guest_driver_profile;
}
private:
GuestDriverProfile guest_driver_profile{};
};
} // namespace VideoCore

2124
src/video_core/renderer_opengl/gl_arb_decompiler.cpp
View file

File diff suppressed because it is too large Load diff

29
src/video_core/renderer_opengl/gl_arb_decompiler.h
View file

@ -1,29 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <string>
#include <string_view>
#include "common/common_types.h"
namespace Tegra::Engines {
enum class ShaderType : u32;
}
namespace VideoCommon::Shader {
class ShaderIR;
class Registry;
} // namespace VideoCommon::Shader
namespace OpenGL {
class Device;
std::string DecompileAssemblyShader(const Device& device, const VideoCommon::Shader::ShaderIR& ir,
const VideoCommon::Shader::Registry& registry,
Tegra::Engines::ShaderType stage, std::string_view identifier);
} // namespace OpenGL

314
src/video_core/renderer_opengl/gl_rasterizer.cpp
View file

@ -54,40 +54,6 @@ namespace {
constexpr size_t NUM_SUPPORTED_VERTEX_ATTRIBUTES = 16;
struct TextureHandle {
constexpr TextureHandle(u32 data, bool via_header_index) {
const Tegra::Texture::TextureHandle handle{data};
image = handle.tic_id;
sampler = via_header_index ? image : handle.tsc_id.Value();
}
u32 image;
u32 sampler;
};
template <typename Engine, typename Entry>
TextureHandle GetTextureInfo(const Engine& engine, bool via_header_index, const Entry& entry,
ShaderType shader_type, size_t index = 0) {
if constexpr (std::is_same_v<Entry, SamplerEntry>) {
if (entry.is_separated) {
const u32 buffer_1 = entry.buffer;
const u32 buffer_2 = entry.secondary_buffer;
const u32 offset_1 = entry.offset;
const u32 offset_2 = entry.secondary_offset;
const u32 handle_1 = engine.AccessConstBuffer32(shader_type, buffer_1, offset_1);
const u32 handle_2 = engine.AccessConstBuffer32(shader_type, buffer_2, offset_2);
return TextureHandle(handle_1 | handle_2, via_header_index);
}
}
if (entry.is_bindless) {
const u32 raw = engine.AccessConstBuffer32(shader_type, entry.buffer, entry.offset);
return TextureHandle(raw, via_header_index);
}
const u32 buffer = engine.GetBoundBuffer();
const u64 offset = (entry.offset + index) * sizeof(u32);
return TextureHandle(engine.AccessConstBuffer32(shader_type, buffer, offset), via_header_index);
}
/// Translates hardware transform feedback indices
/// @param location Hardware location
/// @return Pair of ARB_transform_feedback3 token stream first and third arguments
@ -119,44 +85,6 @@ std::pair<GLint, GLint> TransformFeedbackEnum(u8 location) {
void oglEnable(GLenum cap, bool state) {
(state ? glEnable : glDisable)(cap);
}
ImageViewType ImageViewTypeFromEntry(const SamplerEntry& entry) {
if (entry.is_buffer) {
return ImageViewType::Buffer;
}
switch (entry.type) {
case Tegra::Shader::TextureType::Texture1D:
return entry.is_array ? ImageViewType::e1DArray : ImageViewType::e1D;
case Tegra::Shader::TextureType::Texture2D:
return entry.is_array ? ImageViewType::e2DArray : ImageViewType::e2D;
case Tegra::Shader::TextureType::Texture3D:
return ImageViewType::e3D;
case Tegra::Shader::TextureType::TextureCube:
return entry.is_array ? ImageViewType::CubeArray : ImageViewType::Cube;
}
UNREACHABLE();
return ImageViewType::e2D;
}
ImageViewType ImageViewTypeFromEntry(const ImageEntry& entry) {
switch (entry.type) {
case Tegra::Shader::ImageType::Texture1D:
return ImageViewType::e1D;
case Tegra::Shader::ImageType::Texture1DArray:
return ImageViewType::e1DArray;
case Tegra::Shader::ImageType::Texture2D:
return ImageViewType::e2D;
case Tegra::Shader::ImageType::Texture2DArray:
return ImageViewType::e2DArray;
case Tegra::Shader::ImageType::Texture3D:
return ImageViewType::e3D;
case Tegra::Shader::ImageType::TextureBuffer:
return ImageViewType::Buffer;
}
UNREACHABLE();
return ImageViewType::e2D;
}
} // Anonymous namespace
RasterizerOpenGL::RasterizerOpenGL(Core::Frontend::EmuWindow& emu_window_, Tegra::GPU& gpu_,
@ -172,12 +100,7 @@ RasterizerOpenGL::RasterizerOpenGL(Core::Frontend::EmuWindow& emu_window_, Tegra
buffer_cache(*this, maxwell3d, kepler_compute, gpu_memory, cpu_memory_, buffer_cache_runtime),
shader_cache(*this, emu_window_, gpu, maxwell3d, kepler_compute, gpu_memory, device),
query_cache(*this, maxwell3d, gpu_memory), accelerate_dma(buffer_cache),
fence_manager(*this, gpu, texture_cache, buffer_cache, query_cache),
async_shaders(emu_window_) {
if (device.UseAsynchronousShaders()) {
async_shaders.AllocateWorkers();
}
}
fence_manager(*this, gpu, texture_cache, buffer_cache, query_cache) {}
RasterizerOpenGL::~RasterizerOpenGL() = default;
@ -244,117 +167,8 @@ void RasterizerOpenGL::SyncVertexInstances() {
}
}
void RasterizerOpenGL::SetupShaders(bool is_indexed) {
u32 clip_distances = 0;
std::array<Shader*, Maxwell::MaxShaderStage> shaders{};
image_view_indices.clear();
sampler_handles.clear();
texture_cache.SynchronizeGraphicsDescriptors();
for (std::size_t index = 0; index < Maxwell::MaxShaderProgram; ++index) {
const auto& shader_config = maxwell3d.regs.shader_config[index];
const auto program{static_cast<Maxwell::ShaderProgram>(index)};
// Skip stages that are not enabled
if (!maxwell3d.regs.IsShaderConfigEnabled(index)) {
switch (program) {
case Maxwell::ShaderProgram::Geometry:
program_manager.UseGeometryShader(0);
break;
case Maxwell::ShaderProgram::Fragment:
program_manager.UseFragmentShader(0);
break;
default:
break;
}
continue;
}
// Currently this stages are not supported in the OpenGL backend.
// TODO(Blinkhawk): Port tesselation shaders from Vulkan to OpenGL
if (program == Maxwell::ShaderProgram::TesselationControl ||
program == Maxwell::ShaderProgram::TesselationEval) {
continue;
}
Shader* const shader = shader_cache.GetStageProgram(program, async_shaders);
const GLuint program_handle = shader->IsBuilt() ? shader->GetHandle() : 0;
switch (program) {
case Maxwell::ShaderProgram::VertexA:
case Maxwell::ShaderProgram::VertexB:
program_manager.UseVertexShader(program_handle);
break;
case Maxwell::ShaderProgram::Geometry:
program_manager.UseGeometryShader(program_handle);
break;
case Maxwell::ShaderProgram::Fragment:
program_manager.UseFragmentShader(program_handle);
break;
default:
UNIMPLEMENTED_MSG("Unimplemented shader index={}, enable={}, offset=0x{:08X}", index,
shader_config.enable.Value(), shader_config.offset);
break;
}
// Stage indices are 0 - 5
const size_t stage = index == 0 ? 0 : index - 1;
shaders[stage] = shader;
SetupDrawTextures(shader, stage);
SetupDrawImages(shader, stage);
buffer_cache.SetEnabledUniformBuffers(stage, shader->GetEntries().enabled_uniform_buffers);
buffer_cache.UnbindGraphicsStorageBuffers(stage);
u32 ssbo_index = 0;
for (const auto& buffer : shader->GetEntries().global_memory_entries) {
buffer_cache.BindGraphicsStorageBuffer(stage, ssbo_index, buffer.cbuf_index,
buffer.cbuf_offset, buffer.is_written);
++ssbo_index;
}
// Workaround for Intel drivers.
// When a clip distance is enabled but not set in the shader it crops parts of the screen
// (sometimes it's half the screen, sometimes three quarters). To avoid this, enable the
// clip distances only when it's written by a shader stage.
clip_distances |= shader->GetEntries().clip_distances;
// When VertexA is enabled, we have dual vertex shaders
if (program == Maxwell::ShaderProgram::VertexA) {
// VertexB was combined with VertexA, so we skip the VertexB iteration
++index;
}
}
SyncClipEnabled(clip_distances);
maxwell3d.dirty.flags[Dirty::Shaders] = false;
buffer_cache.UpdateGraphicsBuffers(is_indexed);
const std::span indices_span(image_view_indices.data(), image_view_indices.size());
texture_cache.FillGraphicsImageViews(indices_span, image_view_ids);
buffer_cache.BindHostGeometryBuffers(is_indexed);
size_t image_view_index = 0;
size_t texture_index = 0;
size_t image_index = 0;
for (size_t stage = 0; stage < Maxwell::MaxShaderStage; ++stage) {
const Shader* const shader = shaders[stage];
if (!shader) {
continue;
}
buffer_cache.BindHostStageBuffers(stage);
const auto& base = device.GetBaseBindings(stage);
BindTextures(shader->GetEntries(), base.sampler, base.image, image_view_index,
texture_index, image_index);
}
}
void RasterizerOpenGL::LoadDiskResources(u64 title_id, std::stop_token stop_loading,
const VideoCore::DiskResourceLoadCallback& callback) {
shader_cache.LoadDiskCache(title_id, stop_loading, callback);
}
const VideoCore::DiskResourceLoadCallback& callback) {}
void RasterizerOpenGL::Clear() {
MICROPROFILE_SCOPE(OpenGL_Clears);
@ -434,7 +248,6 @@ void RasterizerOpenGL::Draw(bool is_indexed, bool is_instanced) {
// Setup shaders and their used resources.
std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
SetupShaders(is_indexed);
texture_cache.UpdateRenderTargets(false);
state_tracker.BindFramebuffer(texture_cache.GetFramebuffer()->Handle());
@ -488,27 +301,8 @@ void RasterizerOpenGL::Draw(bool is_indexed, bool is_instanced) {
gpu.TickWork();
}
void RasterizerOpenGL::DispatchCompute(GPUVAddr code_addr) {
Shader* const kernel = shader_cache.GetComputeKernel(code_addr);
std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
BindComputeTextures(kernel);
const auto& entries = kernel->GetEntries();
buffer_cache.SetEnabledComputeUniformBuffers(entries.enabled_uniform_buffers);
buffer_cache.UnbindComputeStorageBuffers();
u32 ssbo_index = 0;
for (const auto& buffer : entries.global_memory_entries) {
buffer_cache.BindComputeStorageBuffer(ssbo_index, buffer.cbuf_index, buffer.cbuf_offset,
buffer.is_written);
++ssbo_index;
}
buffer_cache.UpdateComputeBuffers();
buffer_cache.BindHostComputeBuffers();
const auto& launch_desc = kepler_compute.launch_description;
glDispatchCompute(launch_desc.grid_dim_x, launch_desc.grid_dim_y, launch_desc.grid_dim_z);
++num_queued_commands;
void RasterizerOpenGL::DispatchCompute() {
UNREACHABLE_MSG("Not implemented");
}
void RasterizerOpenGL::ResetCounter(VideoCore::QueryType type) {
@ -726,106 +520,6 @@ bool RasterizerOpenGL::AccelerateDisplay(const Tegra::FramebufferConfig& config,
return true;
}
void RasterizerOpenGL::BindComputeTextures(Shader* kernel) {
image_view_indices.clear();
sampler_handles.clear();
texture_cache.SynchronizeComputeDescriptors();
SetupComputeTextures(kernel);
SetupComputeImages(kernel);
const std::span indices_span(image_view_indices.data(), image_view_indices.size());
texture_cache.FillComputeImageViews(indices_span, image_view_ids);
program_manager.BindCompute(kernel->GetHandle());
size_t image_view_index = 0;
size_t texture_index = 0;
size_t image_index = 0;
BindTextures(kernel->GetEntries(), 0, 0, image_view_index, texture_index, image_index);
}
void RasterizerOpenGL::BindTextures(const ShaderEntries& entries, GLuint base_texture,
GLuint base_image, size_t& image_view_index,
size_t& texture_index, size_t& image_index) {
const GLuint* const samplers = sampler_handles.data() + texture_index;
const GLuint* const textures = texture_handles.data() + texture_index;
const GLuint* const images = image_handles.data() + image_index;
const size_t num_samplers = entries.samplers.size();
for (const auto& sampler : entries.samplers) {
for (size_t i = 0; i < sampler.size; ++i) {
const ImageViewId image_view_id = image_view_ids[image_view_index++];
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
const GLuint handle = image_view.Handle(ImageViewTypeFromEntry(sampler));
texture_handles[texture_index++] = handle;
}
}
const size_t num_images = entries.images.size();
for (size_t unit = 0; unit < num_images; ++unit) {
// TODO: Mark as modified
const ImageViewId image_view_id = image_view_ids[image_view_index++];
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
const GLuint handle = image_view.Handle(ImageViewTypeFromEntry(entries.images[unit]));
image_handles[image_index] = handle;
++image_index;
}
if (num_samplers > 0) {
glBindSamplers(base_texture, static_cast<GLsizei>(num_samplers), samplers);
glBindTextures(base_texture, static_cast<GLsizei>(num_samplers), textures);
}
if (num_images > 0) {
glBindImageTextures(base_image, static_cast<GLsizei>(num_images), images);
}
}
void RasterizerOpenGL::SetupDrawTextures(const Shader* shader, size_t stage_index) {
const bool via_header_index =
maxwell3d.regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : shader->GetEntries().samplers) {
const auto shader_type = static_cast<ShaderType>(stage_index);
for (size_t index = 0; index < entry.size; ++index) {
const auto handle =
GetTextureInfo(maxwell3d, via_header_index, entry, shader_type, index);
const Sampler* const sampler = texture_cache.GetGraphicsSampler(handle.sampler);
sampler_handles.push_back(sampler->Handle());
image_view_indices.push_back(handle.image);
}
}
}
void RasterizerOpenGL::SetupComputeTextures(const Shader* kernel) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : kernel->GetEntries().samplers) {
for (size_t i = 0; i < entry.size; ++i) {
const auto handle =
GetTextureInfo(kepler_compute, via_header_index, entry, ShaderType::Compute, i);
const Sampler* const sampler = texture_cache.GetComputeSampler(handle.sampler);
sampler_handles.push_back(sampler->Handle());
image_view_indices.push_back(handle.image);
}
}
}
void RasterizerOpenGL::SetupDrawImages(const Shader* shader, size_t stage_index) {
const bool via_header_index =
maxwell3d.regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : shader->GetEntries().images) {
const auto shader_type = static_cast<ShaderType>(stage_index);
const auto handle = GetTextureInfo(maxwell3d, via_header_index, entry, shader_type);
image_view_indices.push_back(handle.image);
}
}
void RasterizerOpenGL::SetupComputeImages(const Shader* shader) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : shader->GetEntries().images) {
const auto handle =
GetTextureInfo(kepler_compute, via_header_index, entry, ShaderType::Compute);
image_view_indices.push_back(handle.image);
}
}
void RasterizerOpenGL::SyncState() {
SyncViewport();
SyncRasterizeEnable();

33
src/video_core/renderer_opengl/gl_rasterizer.h
View file

@ -28,11 +28,9 @@
#include "video_core/renderer_opengl/gl_query_cache.h"
#include "video_core/renderer_opengl/gl_resource_manager.h"
#include "video_core/renderer_opengl/gl_shader_cache.h"
#include "video_core/renderer_opengl/gl_shader_decompiler.h"
#include "video_core/renderer_opengl/gl_shader_manager.h"
#include "video_core/renderer_opengl/gl_state_tracker.h"
#include "video_core/renderer_opengl/gl_texture_cache.h"
#include "video_core/shader/async_shaders.h"
#include "video_core/textures/texture.h"
namespace Core::Memory {
@ -81,7 +79,7 @@ public:
void Draw(bool is_indexed, bool is_instanced) override;
void Clear() override;
void DispatchCompute(GPUVAddr code_addr) override;
void DispatchCompute() override;
void ResetCounter(VideoCore::QueryType type) override;
void Query(GPUVAddr gpu_addr, VideoCore::QueryType type, std::optional<u64> timestamp) override;
void BindGraphicsUniformBuffer(size_t stage, u32 index, GPUVAddr gpu_addr, u32 size) override;
@ -118,36 +116,11 @@ public:
return num_queued_commands > 0;
}
VideoCommon::Shader::AsyncShaders& GetAsyncShaders() {
return async_shaders;
}
const VideoCommon::Shader::AsyncShaders& GetAsyncShaders() const {
return async_shaders;
}
private:
static constexpr size_t MAX_TEXTURES = 192;
static constexpr size_t MAX_IMAGES = 48;
static constexpr size_t MAX_IMAGE_VIEWS = MAX_TEXTURES + MAX_IMAGES;
void BindComputeTextures(Shader* kernel);
void BindTextures(const ShaderEntries& entries, GLuint base_texture, GLuint base_image,
size_t& image_view_index, size_t& texture_index, size_t& image_index);
/// Configures the current textures to use for the draw command.
void SetupDrawTextures(const Shader* shader, size_t stage_index);
/// Configures the textures used in a compute shader.
void SetupComputeTextures(const Shader* kernel);
/// Configures images in a graphics shader.
void SetupDrawImages(const Shader* shader, size_t stage_index);
/// Configures images in a compute shader.
void SetupComputeImages(const Shader* shader);
/// Syncs state to match guest's
void SyncState();
@ -230,8 +203,6 @@ private:
/// End a transform feedback
void EndTransformFeedback();
void SetupShaders(bool is_indexed);
Tegra::GPU& gpu;
Tegra::Engines::Maxwell3D& maxwell3d;
Tegra::Engines::KeplerCompute& kepler_compute;
@ -251,8 +222,6 @@ private:
AccelerateDMA accelerate_dma;
FenceManagerOpenGL fence_manager;
VideoCommon::Shader::AsyncShaders async_shaders;
boost::container::static_vector<u32, MAX_IMAGE_VIEWS> image_view_indices;
std::array<ImageViewId, MAX_IMAGE_VIEWS> image_view_ids;
boost::container::static_vector<GLuint, MAX_TEXTURES> sampler_handles;

564
src/video_core/renderer_opengl/gl_shader_cache.cpp
View file

@ -20,307 +20,19 @@
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_type.h"
#include "video_core/memory_manager.h"
#include "video_core/renderer_opengl/gl_arb_decompiler.h"
#include "video_core/renderer_opengl/gl_rasterizer.h"
#include "video_core/renderer_opengl/gl_resource_manager.h"
#include "video_core/renderer_opengl/gl_shader_cache.h"
#include "video_core/renderer_opengl/gl_shader_decompiler.h"
#include "video_core/renderer_opengl/gl_shader_disk_cache.h"
#include "video_core/renderer_opengl/gl_state_tracker.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
#include "video_core/shader_cache.h"
#include "video_core/shader_notify.h"
namespace OpenGL {
using Tegra::Engines::ShaderType;
using VideoCommon::Shader::GetShaderAddress;
using VideoCommon::Shader::GetShaderCode;
using VideoCommon::Shader::GetUniqueIdentifier;
using VideoCommon::Shader::KERNEL_MAIN_OFFSET;
using VideoCommon::Shader::ProgramCode;
using VideoCommon::Shader::Registry;
using VideoCommon::Shader::ShaderIR;
using VideoCommon::Shader::STAGE_MAIN_OFFSET;
namespace {
constexpr VideoCommon::Shader::CompilerSettings COMPILER_SETTINGS{};
/// Gets the shader type from a Maxwell program type
constexpr GLenum GetGLShaderType(ShaderType shader_type) {
switch (shader_type) {
case ShaderType::Vertex:
return GL_VERTEX_SHADER;
case ShaderType::Geometry:
return GL_GEOMETRY_SHADER;
case ShaderType::Fragment:
return GL_FRAGMENT_SHADER;
case ShaderType::Compute:
return GL_COMPUTE_SHADER;
default:
return GL_NONE;
}
}
constexpr const char* GetShaderTypeName(ShaderType shader_type) {
switch (shader_type) {
case ShaderType::Vertex:
return "VS";
case ShaderType::TesselationControl:
return "HS";
case ShaderType::TesselationEval:
return "DS";
case ShaderType::Geometry:
return "GS";
case ShaderType::Fragment:
return "FS";
case ShaderType::Compute:
return "CS";
}
return "UNK";
}
constexpr ShaderType GetShaderType(Maxwell::ShaderProgram program_type) {
switch (program_type) {
case Maxwell::ShaderProgram::VertexA:
case Maxwell::ShaderProgram::VertexB:
return ShaderType::Vertex;
case Maxwell::ShaderProgram::TesselationControl:
return ShaderType::TesselationControl;
case Maxwell::ShaderProgram::TesselationEval:
return ShaderType::TesselationEval;
case Maxwell::ShaderProgram::Geometry:
return ShaderType::Geometry;
case Maxwell::ShaderProgram::Fragment:
return ShaderType::Fragment;
}
return {};
}
constexpr GLenum AssemblyEnum(ShaderType shader_type) {
switch (shader_type) {
case ShaderType::Vertex:
return GL_VERTEX_PROGRAM_NV;
case ShaderType::TesselationControl:
return GL_TESS_CONTROL_PROGRAM_NV;
case ShaderType::TesselationEval:
return GL_TESS_EVALUATION_PROGRAM_NV;
case ShaderType::Geometry:
return GL_GEOMETRY_PROGRAM_NV;
case ShaderType::Fragment:
return GL_FRAGMENT_PROGRAM_NV;
case ShaderType::Compute:
return GL_COMPUTE_PROGRAM_NV;
}
return {};
}
std::string MakeShaderID(u64 unique_identifier, ShaderType shader_type) {
return fmt::format("{}{:016X}", GetShaderTypeName(shader_type), unique_identifier);
}
std::shared_ptr<Registry> MakeRegistry(const ShaderDiskCacheEntry& entry) {
const VideoCore::GuestDriverProfile guest_profile{entry.texture_handler_size};
const VideoCommon::Shader::SerializedRegistryInfo info{guest_profile, entry.bound_buffer,
entry.graphics_info, entry.compute_info};
auto registry = std::make_shared<Registry>(entry.type, info);
for (const auto& [address, value] : entry.keys) {
const auto [buffer, offset] = address;
registry->InsertKey(buffer, offset, value);
}
for (const auto& [offset, sampler] : entry.bound_samplers) {
registry->InsertBoundSampler(offset, sampler);
}
for (const auto& [key, sampler] : entry.bindless_samplers) {
const auto [buffer, offset] = key;
registry->InsertBindlessSampler(buffer, offset, sampler);
}
return registry;
}
std::unordered_set<GLenum> GetSupportedFormats() {
GLint num_formats;
glGetIntegerv(GL_NUM_PROGRAM_BINARY_FORMATS, &num_formats);
std::vector<GLint> formats(num_formats);
glGetIntegerv(GL_PROGRAM_BINARY_FORMATS, formats.data());
std::unordered_set<GLenum> supported_formats;
for (const GLint format : formats) {
supported_formats.insert(static_cast<GLenum>(format));
}
return supported_formats;
}
} // Anonymous namespace
ProgramSharedPtr BuildShader(const Device& device, ShaderType shader_type, u64 unique_identifier,
const ShaderIR& ir, const Registry& registry, bool hint_retrievable) {
if (device.UseDriverCache()) {
// Ignore hint retrievable if we are using the driver cache
hint_retrievable = false;
}
const std::string shader_id = MakeShaderID(unique_identifier, shader_type);
LOG_INFO(Render_OpenGL, "{}", shader_id);
auto program = std::make_shared<ProgramHandle>();
if (device.UseAssemblyShaders()) {
const std::string arb =
DecompileAssemblyShader(device, ir, registry, shader_type, shader_id);
GLuint& arb_prog = program->assembly_program.handle;
// Commented out functions signal OpenGL errors but are compatible with apitrace.
// Use them only to capture and replay on apitrace.
#if 0
glGenProgramsNV(1, &arb_prog);
glLoadProgramNV(AssemblyEnum(shader_type), arb_prog, static_cast<GLsizei>(arb.size()),
reinterpret_cast<const GLubyte*>(arb.data()));
#else
glGenProgramsARB(1, &arb_prog);
glNamedProgramStringEXT(arb_prog, AssemblyEnum(shader_type), GL_PROGRAM_FORMAT_ASCII_ARB,
static_cast<GLsizei>(arb.size()), arb.data());
#endif
const auto err = reinterpret_cast<const char*>(glGetString(GL_PROGRAM_ERROR_STRING_NV));
if (err && *err) {
LOG_CRITICAL(Render_OpenGL, "{}", err);
LOG_INFO(Render_OpenGL, "\n{}", arb);
}
} else {
const std::string glsl = DecompileShader(device, ir, registry, shader_type, shader_id);
OGLShader shader;
shader.Create(glsl.c_str(), GetGLShaderType(shader_type));
program->source_program.Create(true, hint_retrievable, shader.handle);
}
return program;
}
Shader::Shader(std::shared_ptr<Registry> registry_, ShaderEntries entries_,
ProgramSharedPtr program_, bool is_built_)
: registry{std::move(registry_)}, entries{std::move(entries_)}, program{std::move(program_)},
is_built{is_built_} {
handle = program->assembly_program.handle;
if (handle == 0) {
handle = program->source_program.handle;
}
if (is_built) {
ASSERT(handle != 0);
}
}
Shader::Shader() = default;
Shader::~Shader() = default;
GLuint Shader::GetHandle() const {
DEBUG_ASSERT(registry->IsConsistent());
return handle;
}
bool Shader::IsBuilt() const {
return is_built;
}
void Shader::AsyncOpenGLBuilt(OGLProgram new_program) {
program->source_program = std::move(new_program);
handle = program->source_program.handle;
is_built = true;
}
void Shader::AsyncGLASMBuilt(OGLAssemblyProgram new_program) {
program->assembly_program = std::move(new_program);
handle = program->assembly_program.handle;
is_built = true;
}
std::unique_ptr<Shader> Shader::CreateStageFromMemory(
const ShaderParameters& params, Maxwell::ShaderProgram program_type, ProgramCode code,
ProgramCode code_b, VideoCommon::Shader::AsyncShaders& async_shaders, VAddr cpu_addr) {
const auto shader_type = GetShaderType(program_type);
auto& gpu = params.gpu;
gpu.ShaderNotify().MarkSharderBuilding();
auto registry = std::make_shared<Registry>(shader_type, gpu.Maxwell3D());
if (!async_shaders.IsShaderAsync(gpu) || !params.device.UseAsynchronousShaders()) {
const ShaderIR ir(code, STAGE_MAIN_OFFSET, COMPILER_SETTINGS, *registry);
// TODO(Rodrigo): Handle VertexA shaders
// std::optional<ShaderIR> ir_b;
// if (!code_b.empty()) {
// ir_b.emplace(code_b, STAGE_MAIN_OFFSET);
// }
auto program =
BuildShader(params.device, shader_type, params.unique_identifier, ir, *registry);
ShaderDiskCacheEntry entry;
entry.type = shader_type;
entry.code = std::move(code);
entry.code_b = std::move(code_b);
entry.unique_identifier = params.unique_identifier;
entry.bound_buffer = registry->GetBoundBuffer();
entry.graphics_info = registry->GetGraphicsInfo();
entry.keys = registry->GetKeys();
entry.bound_samplers = registry->GetBoundSamplers();
entry.bindless_samplers = registry->GetBindlessSamplers();
params.disk_cache.SaveEntry(std::move(entry));
gpu.ShaderNotify().MarkShaderComplete();
return std::unique_ptr<Shader>(new Shader(std::move(registry),
MakeEntries(params.device, ir, shader_type),
std::move(program), true));
} else {
// Required for entries
const ShaderIR ir(code, STAGE_MAIN_OFFSET, COMPILER_SETTINGS, *registry);
auto entries = MakeEntries(params.device, ir, shader_type);
async_shaders.QueueOpenGLShader(params.device, shader_type, params.unique_identifier,
std::move(code), std::move(code_b), STAGE_MAIN_OFFSET,
COMPILER_SETTINGS, *registry, cpu_addr);
auto program = std::make_shared<ProgramHandle>();
return std::unique_ptr<Shader>(
new Shader(std::move(registry), std::move(entries), std::move(program), false));
}
}
std::unique_ptr<Shader> Shader::CreateKernelFromMemory(const ShaderParameters& params,
ProgramCode code) {
auto& gpu = params.gpu;
gpu.ShaderNotify().MarkSharderBuilding();
auto registry = std::make_shared<Registry>(ShaderType::Compute, params.engine);
const ShaderIR ir(code, KERNEL_MAIN_OFFSET, COMPILER_SETTINGS, *registry);
const u64 uid = params.unique_identifier;
auto program = BuildShader(params.device, ShaderType::Compute, uid, ir, *registry);
ShaderDiskCacheEntry entry;
entry.type = ShaderType::Compute;
entry.code = std::move(code);
entry.unique_identifier = uid;
entry.bound_buffer = registry->GetBoundBuffer();
entry.compute_info = registry->GetComputeInfo();
entry.keys = registry->GetKeys();
entry.bound_samplers = registry->GetBoundSamplers();
entry.bindless_samplers = registry->GetBindlessSamplers();
params.disk_cache.SaveEntry(std::move(entry));
gpu.ShaderNotify().MarkShaderComplete();
return std::unique_ptr<Shader>(new Shader(std::move(registry),
MakeEntries(params.device, ir, ShaderType::Compute),
std::move(program)));
}
std::unique_ptr<Shader> Shader::CreateFromCache(const ShaderParameters& params,
const PrecompiledShader& precompiled_shader) {
return std::unique_ptr<Shader>(new Shader(
precompiled_shader.registry, precompiled_shader.entries, precompiled_shader.program));
}
ShaderCacheOpenGL::ShaderCacheOpenGL(RasterizerOpenGL& rasterizer_,
Core::Frontend::EmuWindow& emu_window_, Tegra::GPU& gpu_,
Tegra::Engines::Maxwell3D& maxwell3d_,
@ -331,278 +43,4 @@ ShaderCacheOpenGL::ShaderCacheOpenGL(RasterizerOpenGL& rasterizer_,
ShaderCacheOpenGL::~ShaderCacheOpenGL() = default;
void ShaderCacheOpenGL::LoadDiskCache(u64 title_id, std::stop_token stop_loading,
const VideoCore::DiskResourceLoadCallback& callback) {
disk_cache.BindTitleID(title_id);
const std::optional transferable = disk_cache.LoadTransferable();
LOG_INFO(Render_OpenGL, "Total Shader Count: {}",
transferable.has_value() ? transferable->size() : 0);
if (!transferable) {
return;
}
std::vector<ShaderDiskCachePrecompiled> gl_cache;
if (!device.UseAssemblyShaders() && !device.UseDriverCache()) {
// Only load precompiled cache when we are not using assembly shaders
gl_cache = disk_cache.LoadPrecompiled();
}
const auto supported_formats = GetSupportedFormats();
// Track if precompiled cache was altered during loading to know if we have to
// serialize the virtual precompiled cache file back to the hard drive
bool precompiled_cache_altered = false;
// Inform the frontend about shader build initialization
if (callback) {
callback(VideoCore::LoadCallbackStage::Build, 0, transferable->size());
}
std::mutex mutex;
std::size_t built_shaders = 0; // It doesn't have be atomic since it's used behind a mutex
std::atomic_bool gl_cache_failed = false;
const auto find_precompiled = [&gl_cache](u64 id) {
return std::ranges::find(gl_cache, id, &ShaderDiskCachePrecompiled::unique_identifier);
};
const auto worker = [&](Core::Frontend::GraphicsContext* context, std::size_t begin,
std::size_t end) {
const auto scope = context->Acquire();
for (std::size_t i = begin; i < end; ++i) {
if (stop_loading.stop_requested()) {
return;
}
const auto& entry = (*transferable)[i];
const u64 uid = entry.unique_identifier;
const auto it = find_precompiled(uid);
const auto precompiled_entry = it != gl_cache.end() ? &*it : nullptr;
const bool is_compute = entry.type == ShaderType::Compute;
const u32 main_offset = is_compute ? KERNEL_MAIN_OFFSET : STAGE_MAIN_OFFSET;
auto registry = MakeRegistry(entry);
const ShaderIR ir(entry.code, main_offset, COMPILER_SETTINGS, *registry);
ProgramSharedPtr program;
if (precompiled_entry) {
// If the shader is precompiled, attempt to load it with
program = GeneratePrecompiledProgram(entry, *precompiled_entry, supported_formats);
if (!program) {
gl_cache_failed = true;
}
}
if (!program) {
// Otherwise compile it from GLSL
program = BuildShader(device, entry.type, uid, ir, *registry, true);
}
PrecompiledShader shader;
shader.program = std::move(program);
shader.registry = std::move(registry);
shader.entries = MakeEntries(device, ir, entry.type);
std::scoped_lock lock{mutex};
if (callback) {
callback(VideoCore::LoadCallbackStage::Build, ++built_shaders,
transferable->size());
}
runtime_cache.emplace(entry.unique_identifier, std::move(shader));
}
};
const std::size_t num_workers{std::max(1U, std::thread::hardware_concurrency())};
const std::size_t bucket_size{transferable->size() / num_workers};
std::vector<std::unique_ptr<Core::Frontend::GraphicsContext>> contexts(num_workers);
std::vector<std::thread> threads(num_workers);
for (std::size_t i = 0; i < num_workers; ++i) {
const bool is_last_worker = i + 1 == num_workers;
const std::size_t start{bucket_size * i};
const std::size_t end{is_last_worker ? transferable->size() : start + bucket_size};
// On some platforms the shared context has to be created from the GUI thread
contexts[i] = emu_window.CreateSharedContext();
threads[i] = std::thread(worker, contexts[i].get(), start, end);
}
for (auto& thread : threads) {
thread.join();
}
if (gl_cache_failed) {
// Invalidate the precompiled cache if a shader dumped shader was rejected
disk_cache.InvalidatePrecompiled();
precompiled_cache_altered = true;
return;
}
if (stop_loading.stop_requested()) {
return;
}
if (device.UseAssemblyShaders() || device.UseDriverCache()) {
// Don't store precompiled binaries for assembly shaders or when using the driver cache
return;
}
// TODO(Rodrigo): Do state tracking for transferable shaders and do a dummy draw
// before precompiling them
for (std::size_t i = 0; i < transferable->size(); ++i) {
const u64 id = (*transferable)[i].unique_identifier;
const auto it = find_precompiled(id);
if (it == gl_cache.end()) {
const GLuint program = runtime_cache.at(id).program->source_program.handle;
disk_cache.SavePrecompiled(id, program);
precompiled_cache_altered = true;
}
}
if (precompiled_cache_altered) {
disk_cache.SaveVirtualPrecompiledFile();
}
}
ProgramSharedPtr ShaderCacheOpenGL::GeneratePrecompiledProgram(
const ShaderDiskCacheEntry& entry, const ShaderDiskCachePrecompiled& precompiled_entry,
const std::unordered_set<GLenum>& supported_formats) {
if (!supported_formats.contains(precompiled_entry.binary_format)) {
LOG_INFO(Render_OpenGL, "Precompiled cache entry with unsupported format, removing");
return {};
}
auto program = std::make_shared<ProgramHandle>();
GLuint& handle = program->source_program.handle;
handle = glCreateProgram();
glProgramParameteri(handle, GL_PROGRAM_SEPARABLE, GL_TRUE);
glProgramBinary(handle, precompiled_entry.binary_format, precompiled_entry.binary.data(),
static_cast<GLsizei>(precompiled_entry.binary.size()));
GLint link_status;
glGetProgramiv(handle, GL_LINK_STATUS, &link_status);
if (link_status == GL_FALSE) {
LOG_INFO(Render_OpenGL, "Precompiled cache rejected by the driver, removing");
return {};
}
return program;
}
Shader* ShaderCacheOpenGL::GetStageProgram(Maxwell::ShaderProgram program,
VideoCommon::Shader::AsyncShaders& async_shaders) {
if (!maxwell3d.dirty.flags[Dirty::Shaders]) {
auto* last_shader = last_shaders[static_cast<std::size_t>(program)];
if (last_shader->IsBuilt()) {
return last_shader;
}
}
const GPUVAddr address{GetShaderAddress(maxwell3d, program)};
if (device.UseAsynchronousShaders() && async_shaders.HasCompletedWork()) {
auto completed_work = async_shaders.GetCompletedWork();
for (auto& work : completed_work) {
Shader* shader = TryGet(work.cpu_address);
gpu.ShaderNotify().MarkShaderComplete();
if (shader == nullptr) {
continue;
}
using namespace VideoCommon::Shader;
if (work.backend == AsyncShaders::Backend::OpenGL) {
shader->AsyncOpenGLBuilt(std::move(work.program.opengl));
} else if (work.backend == AsyncShaders::Backend::GLASM) {
shader->AsyncGLASMBuilt(std::move(work.program.glasm));
}
auto& registry = shader->GetRegistry();
ShaderDiskCacheEntry entry;
entry.type = work.shader_type;
entry.code = std::move(work.code);
entry.code_b = std::move(work.code_b);
entry.unique_identifier = work.uid;
entry.bound_buffer = registry.GetBoundBuffer();
entry.graphics_info = registry.GetGraphicsInfo();
entry.keys = registry.GetKeys();
entry.bound_samplers = registry.GetBoundSamplers();
entry.bindless_samplers = registry.GetBindlessSamplers();
disk_cache.SaveEntry(std::move(entry));
}
}
// Look up shader in the cache based on address
const std::optional<VAddr> cpu_addr{gpu_memory.GpuToCpuAddress(address)};
if (Shader* const shader{cpu_addr ? TryGet(*cpu_addr) : null_shader.get()}) {
return last_shaders[static_cast<std::size_t>(program)] = shader;
}
const u8* const host_ptr{gpu_memory.GetPointer(address)};
// No shader found - create a new one
ProgramCode code{GetShaderCode(gpu_memory, address, host_ptr, false)};
ProgramCode code_b;
if (program == Maxwell::ShaderProgram::VertexA) {
const GPUVAddr address_b{GetShaderAddress(maxwell3d, Maxwell::ShaderProgram::VertexB)};
const u8* host_ptr_b = gpu_memory.GetPointer(address_b);
code_b = GetShaderCode(gpu_memory, address_b, host_ptr_b, false);
}
const std::size_t code_size = code.size() * sizeof(u64);
const u64 unique_identifier = GetUniqueIdentifier(
GetShaderType(program), program == Maxwell::ShaderProgram::VertexA, code, code_b);
const ShaderParameters params{gpu, maxwell3d, disk_cache, device,
*cpu_addr, host_ptr, unique_identifier};
std::unique_ptr<Shader> shader;
const auto found = runtime_cache.find(unique_identifier);
if (found == runtime_cache.end()) {
shader = Shader::CreateStageFromMemory(params, program, std::move(code), std::move(code_b),
async_shaders, cpu_addr.value_or(0));
} else {
shader = Shader::CreateFromCache(params, found->second);
}
Shader* const result = shader.get();
if (cpu_addr) {
Register(std::move(shader), *cpu_addr, code_size);
} else {
null_shader = std::move(shader);
}
return last_shaders[static_cast<std::size_t>(program)] = result;
}
Shader* ShaderCacheOpenGL::GetComputeKernel(GPUVAddr code_addr) {
const std::optional<VAddr> cpu_addr{gpu_memory.GpuToCpuAddress(code_addr)};
if (Shader* const kernel = cpu_addr ? TryGet(*cpu_addr) : null_kernel.get()) {
return kernel;
}
// No kernel found, create a new one
const u8* host_ptr{gpu_memory.GetPointer(code_addr)};
ProgramCode code{GetShaderCode(gpu_memory, code_addr, host_ptr, true)};
const std::size_t code_size{code.size() * sizeof(u64)};
const u64 unique_identifier{GetUniqueIdentifier(ShaderType::Compute, false, code)};
const ShaderParameters params{gpu, kepler_compute, disk_cache, device,
*cpu_addr, host_ptr, unique_identifier};
std::unique_ptr<Shader> kernel;
const auto found = runtime_cache.find(unique_identifier);
if (found == runtime_cache.end()) {
kernel = Shader::CreateKernelFromMemory(params, std::move(code));
} else {
kernel = Shader::CreateFromCache(params, found->second);
}
Shader* const result = kernel.get();
if (cpu_addr) {
Register(std::move(kernel), *cpu_addr, code_size);
} else {
null_kernel = std::move(kernel);
}
return result;
}
} // namespace OpenGL

102
src/video_core/renderer_opengl/gl_shader_cache.h
View file

@ -19,10 +19,6 @@
#include "common/common_types.h"
#include "video_core/engines/shader_type.h"
#include "video_core/renderer_opengl/gl_resource_manager.h"
#include "video_core/renderer_opengl/gl_shader_decompiler.h"
#include "video_core/renderer_opengl/gl_shader_disk_cache.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
#include "video_core/shader_cache.h"
namespace Tegra {
@ -33,10 +29,6 @@ namespace Core::Frontend {
class EmuWindow;
}
namespace VideoCommon::Shader {
class AsyncShaders;
}
namespace OpenGL {
class Device;
@ -44,77 +36,10 @@ class RasterizerOpenGL;
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
struct ProgramHandle {
OGLProgram source_program;
OGLAssemblyProgram assembly_program;
};
using ProgramSharedPtr = std::shared_ptr<ProgramHandle>;
struct PrecompiledShader {
ProgramSharedPtr program;
std::shared_ptr<VideoCommon::Shader::Registry> registry;
ShaderEntries entries;
};
struct ShaderParameters {
Tegra::GPU& gpu;
Tegra::Engines::ConstBufferEngineInterface& engine;
ShaderDiskCacheOpenGL& disk_cache;
const Device& device;
VAddr cpu_addr;
const u8* host_ptr;
u64 unique_identifier;
};
ProgramSharedPtr BuildShader(const Device& device, Tegra::Engines::ShaderType shader_type,
u64 unique_identifier, const VideoCommon::Shader::ShaderIR& ir,
const VideoCommon::Shader::Registry& registry,
bool hint_retrievable = false);
class Shader final {
class Shader {
public:
explicit Shader();
~Shader();
/// Gets the GL program handle for the shader
GLuint GetHandle() const;
bool IsBuilt() const;
/// Gets the shader entries for the shader
const ShaderEntries& GetEntries() const {
return entries;
}
const VideoCommon::Shader::Registry& GetRegistry() const {
return *registry;
}
/// Mark a OpenGL shader as built
void AsyncOpenGLBuilt(OGLProgram new_program);
/// Mark a GLASM shader as built
void AsyncGLASMBuilt(OGLAssemblyProgram new_program);
static std::unique_ptr<Shader> CreateStageFromMemory(
const ShaderParameters& params, Maxwell::ShaderProgram program_type,
ProgramCode program_code, ProgramCode program_code_b,
VideoCommon::Shader::AsyncShaders& async_shaders, VAddr cpu_addr);
static std::unique_ptr<Shader> CreateKernelFromMemory(const ShaderParameters& params,
ProgramCode code);
static std::unique_ptr<Shader> CreateFromCache(const ShaderParameters& params,
const PrecompiledShader& precompiled_shader);
private:
explicit Shader(std::shared_ptr<VideoCommon::Shader::Registry> registry, ShaderEntries entries,
ProgramSharedPtr program, bool is_built_ = true);
std::shared_ptr<VideoCommon::Shader::Registry> registry;
ShaderEntries entries;
ProgramSharedPtr program;
GLuint handle = 0;
bool is_built{};
};
class ShaderCacheOpenGL final : public VideoCommon::ShaderCache<Shader> {
@ -126,36 +51,13 @@ public:
Tegra::MemoryManager& gpu_memory_, const Device& device_);
~ShaderCacheOpenGL() override;
/// Loads disk cache for the current game
void LoadDiskCache(u64 title_id, std::stop_token stop_loading,
const VideoCore::DiskResourceLoadCallback& callback);
/// Gets the current specified shader stage program
Shader* GetStageProgram(Maxwell::ShaderProgram program,
VideoCommon::Shader::AsyncShaders& async_shaders);
/// Gets a compute kernel in the passed address
Shader* GetComputeKernel(GPUVAddr code_addr);
private:
ProgramSharedPtr GeneratePrecompiledProgram(
const ShaderDiskCacheEntry& entry, const ShaderDiskCachePrecompiled& precompiled_entry,
const std::unordered_set<GLenum>& supported_formats);
Core::Frontend::EmuWindow& emu_window;
Tegra::GPU& gpu;
Tegra::MemoryManager& gpu_memory;
Tegra::Engines::Maxwell3D& maxwell3d;
Tegra::Engines::KeplerCompute& kepler_compute;
const Device& device;
ShaderDiskCacheOpenGL disk_cache;
std::unordered_map<u64, PrecompiledShader> runtime_cache;
std::unique_ptr<Shader> null_shader;
std::unique_ptr<Shader> null_kernel;
std::array<Shader*, Maxwell::MaxShaderProgram> last_shaders{};
};
} // namespace OpenGL

2986
src/video_core/renderer_opengl/gl_shader_decompiler.cpp
View file

File diff suppressed because it is too large Load diff

69
src/video_core/renderer_opengl/gl_shader_decompiler.h
View file

@ -1,69 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <array>
#include <string>
#include <string_view>
#include <utility>
#include <vector>
#include "common/common_types.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_type.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
namespace OpenGL {
class Device;
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
using SamplerEntry = VideoCommon::Shader::SamplerEntry;
using ImageEntry = VideoCommon::Shader::ImageEntry;
class ConstBufferEntry : public VideoCommon::Shader::ConstBuffer {
public:
explicit ConstBufferEntry(u32 max_offset_, bool is_indirect_, u32 index_)
: ConstBuffer{max_offset_, is_indirect_}, index{index_} {}
u32 GetIndex() const {
return index;
}
private:
u32 index = 0;
};
struct GlobalMemoryEntry {
constexpr explicit GlobalMemoryEntry(u32 cbuf_index_, u32 cbuf_offset_, bool is_read_,
bool is_written_)
: cbuf_index{cbuf_index_}, cbuf_offset{cbuf_offset_}, is_read{is_read_}, is_written{
is_written_} {}
u32 cbuf_index = 0;
u32 cbuf_offset = 0;
bool is_read = false;
bool is_written = false;
};
struct ShaderEntries {
std::vector<ConstBufferEntry> const_buffers;
std::vector<GlobalMemoryEntry> global_memory_entries;
std::vector<SamplerEntry> samplers;
std::vector<ImageEntry> images;
std::size_t shader_length{};
u32 clip_distances{};
u32 enabled_uniform_buffers{};
};
ShaderEntries MakeEntries(const Device& device, const VideoCommon::Shader::ShaderIR& ir,
Tegra::Engines::ShaderType stage);
std::string DecompileShader(const Device& device, const VideoCommon::Shader::ShaderIR& ir,
const VideoCommon::Shader::Registry& registry,
Tegra::Engines::ShaderType stage, std::string_view identifier,
std::string_view suffix = {});
} // namespace OpenGL

482
src/video_core/renderer_opengl/gl_shader_disk_cache.cpp
View file

@ -1,482 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <cstring>
#include <fmt/format.h>
#include "common/assert.h"
#include "common/common_types.h"
#include "common/fs/file.h"
#include "common/fs/fs.h"
#include "common/fs/path_util.h"
#include "common/logging/log.h"
#include "common/scm_rev.h"
#include "common/settings.h"
#include "common/zstd_compression.h"
#include "core/core.h"
#include "core/hle/kernel/k_process.h"
#include "video_core/engines/shader_type.h"
#include "video_core/renderer_opengl/gl_shader_cache.h"
#include "video_core/renderer_opengl/gl_shader_disk_cache.h"
namespace OpenGL {
using Tegra::Engines::ShaderType;
using VideoCommon::Shader::BindlessSamplerMap;
using VideoCommon::Shader::BoundSamplerMap;
using VideoCommon::Shader::KeyMap;
using VideoCommon::Shader::SeparateSamplerKey;
using ShaderCacheVersionHash = std::array<u8, 64>;
struct ConstBufferKey {
u32 cbuf = 0;
u32 offset = 0;
u32 value = 0;
};
struct BoundSamplerEntry {
u32 offset = 0;
Tegra::Engines::SamplerDescriptor sampler;
};
struct SeparateSamplerEntry {
u32 cbuf1 = 0;
u32 cbuf2 = 0;
u32 offset1 = 0;
u32 offset2 = 0;
Tegra::Engines::SamplerDescriptor sampler;
};
struct BindlessSamplerEntry {
u32 cbuf = 0;
u32 offset = 0;
Tegra::Engines::SamplerDescriptor sampler;
};
namespace {
constexpr u32 NativeVersion = 21;
ShaderCacheVersionHash GetShaderCacheVersionHash() {
ShaderCacheVersionHash hash{};
const std::size_t length = std::min(std::strlen(Common::g_shader_cache_version), hash.size());
std::memcpy(hash.data(), Common::g_shader_cache_version, length);
return hash;
}
} // Anonymous namespace
ShaderDiskCacheEntry::ShaderDiskCacheEntry() = default;
ShaderDiskCacheEntry::~ShaderDiskCacheEntry() = default;
bool ShaderDiskCacheEntry::Load(Common::FS::IOFile& file) {
if (!file.ReadObject(type)) {
return false;
}
u32 code_size;
u32 code_size_b;
if (!file.ReadObject(code_size) || !file.ReadObject(code_size_b)) {
return false;
}
code.resize(code_size);
code_b.resize(code_size_b);
if (file.Read(code) != code_size) {
return false;
}
if (HasProgramA() && file.Read(code_b) != code_size_b) {
return false;
}
u8 is_texture_handler_size_known;
u32 texture_handler_size_value;
u32 num_keys;
u32 num_bound_samplers;
u32 num_separate_samplers;
u32 num_bindless_samplers;
if (!file.ReadObject(unique_identifier) || !file.ReadObject(bound_buffer) ||
!file.ReadObject(is_texture_handler_size_known) ||
!file.ReadObject(texture_handler_size_value) || !file.ReadObject(graphics_info) ||
!file.ReadObject(compute_info) || !file.ReadObject(num_keys) ||
!file.ReadObject(num_bound_samplers) || !file.ReadObject(num_separate_samplers) ||
!file.ReadObject(num_bindless_samplers)) {
return false;
}
if (is_texture_handler_size_known) {
texture_handler_size = texture_handler_size_value;
}
std::vector<ConstBufferKey> flat_keys(num_keys);
std::vector<BoundSamplerEntry> flat_bound_samplers(num_bound_samplers);
std::vector<SeparateSamplerEntry> flat_separate_samplers(num_separate_samplers);
std::vector<BindlessSamplerEntry> flat_bindless_samplers(num_bindless_samplers);
if (file.Read(flat_keys) != flat_keys.size() ||
file.Read(flat_bound_samplers) != flat_bound_samplers.size() ||
file.Read(flat_separate_samplers) != flat_separate_samplers.size() ||
file.Read(flat_bindless_samplers) != flat_bindless_samplers.size()) {
return false;
}
for (const auto& entry : flat_keys) {
keys.insert({{entry.cbuf, entry.offset}, entry.value});
}
for (const auto& entry : flat_bound_samplers) {
bound_samplers.emplace(entry.offset, entry.sampler);
}
for (const auto& entry : flat_separate_samplers) {
SeparateSamplerKey key;
key.buffers = {entry.cbuf1, entry.cbuf2};
key.offsets = {entry.offset1, entry.offset2};
separate_samplers.emplace(key, entry.sampler);
}
for (const auto& entry : flat_bindless_samplers) {
bindless_samplers.insert({{entry.cbuf, entry.offset}, entry.sampler});
}
return true;
}
bool ShaderDiskCacheEntry::Save(Common::FS::IOFile& file) const {
if (!file.WriteObject(static_cast<u32>(type)) ||
!file.WriteObject(static_cast<u32>(code.size())) ||
!file.WriteObject(static_cast<u32>(code_b.size()))) {
return false;
}
if (file.Write(code) != code.size()) {
return false;
}
if (HasProgramA() && file.Write(code_b) != code_b.size()) {
return false;
}
if (!file.WriteObject(unique_identifier) || !file.WriteObject(bound_buffer) ||
!file.WriteObject(static_cast<u8>(texture_handler_size.has_value())) ||
!file.WriteObject(texture_handler_size.value_or(0)) || !file.WriteObject(graphics_info) ||
!file.WriteObject(compute_info) || !file.WriteObject(static_cast<u32>(keys.size())) ||
!file.WriteObject(static_cast<u32>(bound_samplers.size())) ||
!file.WriteObject(static_cast<u32>(separate_samplers.size())) ||
!file.WriteObject(static_cast<u32>(bindless_samplers.size()))) {
return false;
}
std::vector<ConstBufferKey> flat_keys;
flat_keys.reserve(keys.size());
for (const auto& [address, value] : keys) {
flat_keys.push_back(ConstBufferKey{address.first, address.second, value});
}
std::vector<BoundSamplerEntry> flat_bound_samplers;
flat_bound_samplers.reserve(bound_samplers.size());
for (const auto& [address, sampler] : bound_samplers) {
flat_bound_samplers.push_back(BoundSamplerEntry{address, sampler});
}
std::vector<SeparateSamplerEntry> flat_separate_samplers;
flat_separate_samplers.reserve(separate_samplers.size());
for (const auto& [key, sampler] : separate_samplers) {
SeparateSamplerEntry entry;
std::tie(entry.cbuf1, entry.cbuf2) = key.buffers;
std::tie(entry.offset1, entry.offset2) = key.offsets;
entry.sampler = sampler;
flat_separate_samplers.push_back(entry);
}
std::vector<BindlessSamplerEntry> flat_bindless_samplers;
flat_bindless_samplers.reserve(bindless_samplers.size());
for (const auto& [address, sampler] : bindless_samplers) {
flat_bindless_samplers.push_back(
BindlessSamplerEntry{address.first, address.second, sampler});
}
return file.Write(flat_keys) == flat_keys.size() &&
file.Write(flat_bound_samplers) == flat_bound_samplers.size() &&
file.Write(flat_separate_samplers) == flat_separate_samplers.size() &&
file.Write(flat_bindless_samplers) == flat_bindless_samplers.size();
}
ShaderDiskCacheOpenGL::ShaderDiskCacheOpenGL() = default;
ShaderDiskCacheOpenGL::~ShaderDiskCacheOpenGL() = default;
void ShaderDiskCacheOpenGL::BindTitleID(u64 title_id_) {
title_id = title_id_;
}
std::optional<std::vector<ShaderDiskCacheEntry>> ShaderDiskCacheOpenGL::LoadTransferable() {
// Skip games without title id
const bool has_title_id = title_id != 0;
if (!Settings::values.use_disk_shader_cache.GetValue() || !has_title_id) {
return std::nullopt;
}
Common::FS::IOFile file{GetTransferablePath(), Common::FS::FileAccessMode::Read,
Common::FS::FileType::BinaryFile};
if (!file.IsOpen()) {
LOG_INFO(Render_OpenGL, "No transferable shader cache found");
is_usable = true;
return std::nullopt;
}
u32 version{};
if (!file.ReadObject(version)) {
LOG_ERROR(Render_OpenGL, "Failed to get transferable cache version, skipping it");
return std::nullopt;
}
if (version < NativeVersion) {
LOG_INFO(Render_OpenGL, "Transferable shader cache is old, removing");
file.Close();
InvalidateTransferable();
is_usable = true;
return std::nullopt;
}
if (version > NativeVersion) {
LOG_WARNING(Render_OpenGL, "Transferable shader cache was generated with a newer version "
"of the emulator, skipping");
return std::nullopt;
}
// Version is valid, load the shaders
std::vector<ShaderDiskCacheEntry> entries;
while (static_cast<u64>(file.Tell()) < file.GetSize()) {
ShaderDiskCacheEntry& entry = entries.emplace_back();
if (!entry.Load(file)) {
LOG_ERROR(Render_OpenGL, "Failed to load transferable raw entry, skipping");
return std::nullopt;
}
}
is_usable = true;
return {std::move(entries)};
}
std::vector<ShaderDiskCachePrecompiled> ShaderDiskCacheOpenGL::LoadPrecompiled() {
if (!is_usable) {
return {};
}
Common::FS::IOFile file{GetPrecompiledPath(), Common::FS::FileAccessMode::Read,
Common::FS::FileType::BinaryFile};
if (!file.IsOpen()) {
LOG_INFO(Render_OpenGL, "No precompiled shader cache found");
return {};
}
if (const auto result = LoadPrecompiledFile(file)) {
return *result;
}
LOG_INFO(Render_OpenGL, "Failed to load precompiled cache");
file.Close();
InvalidatePrecompiled();
return {};
}
std::optional<std::vector<ShaderDiskCachePrecompiled>> ShaderDiskCacheOpenGL::LoadPrecompiledFile(
Common::FS::IOFile& file) {
// Read compressed file from disk and decompress to virtual precompiled cache file
std::vector<u8> compressed(file.GetSize());
if (file.Read(compressed) != file.GetSize()) {
return std::nullopt;
}
const std::vector<u8> decompressed = Common::Compression::DecompressDataZSTD(compressed);
SaveArrayToPrecompiled(decompressed.data(), decompressed.size());
precompiled_cache_virtual_file_offset = 0;
ShaderCacheVersionHash file_hash{};
if (!LoadArrayFromPrecompiled(file_hash.data(), file_hash.size())) {
precompiled_cache_virtual_file_offset = 0;
return std::nullopt;
}
if (GetShaderCacheVersionHash() != file_hash) {
LOG_INFO(Render_OpenGL, "Precompiled cache is from another version of the emulator");
precompiled_cache_virtual_file_offset = 0;
return std::nullopt;
}
std::vector<ShaderDiskCachePrecompiled> entries;
while (precompiled_cache_virtual_file_offset < precompiled_cache_virtual_file.GetSize()) {
u32 binary_size;
auto& entry = entries.emplace_back();
if (!LoadObjectFromPrecompiled(entry.unique_identifier) ||
!LoadObjectFromPrecompiled(entry.binary_format) ||
!LoadObjectFromPrecompiled(binary_size)) {
return std::nullopt;
}
entry.binary.resize(binary_size);
if (!LoadArrayFromPrecompiled(entry.binary.data(), entry.binary.size())) {
return std::nullopt;
}
}
return entries;
}
void ShaderDiskCacheOpenGL::InvalidateTransferable() {
if (!Common::FS::RemoveFile(GetTransferablePath())) {
LOG_ERROR(Render_OpenGL, "Failed to invalidate transferable file={}",
Common::FS::PathToUTF8String(GetTransferablePath()));
}
InvalidatePrecompiled();
}
void ShaderDiskCacheOpenGL::InvalidatePrecompiled() {
// Clear virtaul precompiled cache file
precompiled_cache_virtual_file.Resize(0);
if (!Common::FS::RemoveFile(GetPrecompiledPath())) {
LOG_ERROR(Render_OpenGL, "Failed to invalidate precompiled file={}",
Common::FS::PathToUTF8String(GetPrecompiledPath()));
}
}
void ShaderDiskCacheOpenGL::SaveEntry(const ShaderDiskCacheEntry& entry) {
if (!is_usable) {
return;
}
const u64 id = entry.unique_identifier;
if (stored_transferable.contains(id)) {
// The shader already exists
return;
}
Common::FS::IOFile file = AppendTransferableFile();
if (!file.IsOpen()) {
return;
}
if (!entry.Save(file)) {
LOG_ERROR(Render_OpenGL, "Failed to save raw transferable cache entry, removing");
file.Close();
InvalidateTransferable();
return;
}
stored_transferable.insert(id);
}
void ShaderDiskCacheOpenGL::SavePrecompiled(u64 unique_identifier, GLuint program) {
if (!is_usable) {
return;
}
// TODO(Rodrigo): This is a design smell. I shouldn't be having to manually write the header
// when writing the dump. This should be done the moment I get access to write to the virtual
// file.
if (precompiled_cache_virtual_file.GetSize() == 0) {
SavePrecompiledHeaderToVirtualPrecompiledCache();
}
GLint binary_length;
glGetProgramiv(program, GL_PROGRAM_BINARY_LENGTH, &binary_length);
GLenum binary_format;
std::vector<u8> binary(binary_length);
glGetProgramBinary(program, binary_length, nullptr, &binary_format, binary.data());
if (!SaveObjectToPrecompiled(unique_identifier) || !SaveObjectToPrecompiled(binary_format) ||
!SaveObjectToPrecompiled(static_cast<u32>(binary.size())) ||
!SaveArrayToPrecompiled(binary.data(), binary.size())) {
LOG_ERROR(Render_OpenGL, "Failed to save binary program file in shader={:016X}, removing",
unique_identifier);
InvalidatePrecompiled();
}
}
Common::FS::IOFile ShaderDiskCacheOpenGL::AppendTransferableFile() const {
if (!EnsureDirectories()) {
return {};
}
const auto transferable_path{GetTransferablePath()};
const bool existed = Common::FS::Exists(transferable_path);
Common::FS::IOFile file{transferable_path, Common::FS::FileAccessMode::Append,
Common::FS::FileType::BinaryFile};
if (!file.IsOpen()) {
LOG_ERROR(Render_OpenGL, "Failed to open transferable cache in path={}",
Common::FS::PathToUTF8String(transferable_path));
return {};
}
if (!existed || file.GetSize() == 0) {
// If the file didn't exist, write its version
if (!file.WriteObject(NativeVersion)) {
LOG_ERROR(Render_OpenGL, "Failed to write transferable cache version in path={}",
Common::FS::PathToUTF8String(transferable_path));
return {};
}
}
return file;
}
void ShaderDiskCacheOpenGL::SavePrecompiledHeaderToVirtualPrecompiledCache() {
const auto hash{GetShaderCacheVersionHash()};
if (!SaveArrayToPrecompiled(hash.data(), hash.size())) {
LOG_ERROR(
Render_OpenGL,
"Failed to write precompiled cache version hash to virtual precompiled cache file");
}
}
void ShaderDiskCacheOpenGL::SaveVirtualPrecompiledFile() {
precompiled_cache_virtual_file_offset = 0;
const std::vector<u8> uncompressed = precompiled_cache_virtual_file.ReadAllBytes();
const std::vector<u8> compressed =
Common::Compression::CompressDataZSTDDefault(uncompressed.data(), uncompressed.size());
const auto precompiled_path = GetPrecompiledPath();
Common::FS::IOFile file{precompiled_path, Common::FS::FileAccessMode::Write,
Common::FS::FileType::BinaryFile};
if (!file.IsOpen()) {
LOG_ERROR(Render_OpenGL, "Failed to open precompiled cache in path={}",
Common::FS::PathToUTF8String(precompiled_path));
return;
}
if (file.Write(compressed) != compressed.size()) {
LOG_ERROR(Render_OpenGL, "Failed to write precompiled cache version in path={}",
Common::FS::PathToUTF8String(precompiled_path));
}
}
bool ShaderDiskCacheOpenGL::EnsureDirectories() const {
const auto CreateDir = [](const std::filesystem::path& dir) {
if (!Common::FS::CreateDir(dir)) {
LOG_ERROR(Render_OpenGL, "Failed to create directory={}",
Common::FS::PathToUTF8String(dir));
return false;
}
return true;
};
return CreateDir(Common::FS::GetYuzuPath(Common::FS::YuzuPath::ShaderDir)) &&
CreateDir(GetBaseDir()) && CreateDir(GetTransferableDir()) &&
CreateDir(GetPrecompiledDir());
}
std::filesystem::path ShaderDiskCacheOpenGL::GetTransferablePath() const {
return GetTransferableDir() / fmt::format("{}.bin", GetTitleID());
}
std::filesystem::path ShaderDiskCacheOpenGL::GetPrecompiledPath() const {
return GetPrecompiledDir() / fmt::format("{}.bin", GetTitleID());
}
std::filesystem::path ShaderDiskCacheOpenGL::GetTransferableDir() const {
return GetBaseDir() / "transferable";
}
std::filesystem::path ShaderDiskCacheOpenGL::GetPrecompiledDir() const {
return GetBaseDir() / "precompiled";
}
std::filesystem::path ShaderDiskCacheOpenGL::GetBaseDir() const {
return Common::FS::GetYuzuPath(Common::FS::YuzuPath::ShaderDir) / "opengl";
}
std::string ShaderDiskCacheOpenGL::GetTitleID() const {
return fmt::format("{:016X}", title_id);
}
} // namespace OpenGL

176
src/video_core/renderer_opengl/gl_shader_disk_cache.h
View file

@ -1,176 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <filesystem>
#include <optional>
#include <string>
#include <tuple>
#include <type_traits>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
#include <glad/glad.h>
#include "common/assert.h"
#include "common/common_types.h"
#include "core/file_sys/vfs_vector.h"
#include "video_core/engines/shader_type.h"
#include "video_core/shader/registry.h"
namespace Common::FS {
class IOFile;
}
namespace OpenGL {
using ProgramCode = std::vector<u64>;
/// Describes a shader and how it's used by the guest GPU
struct ShaderDiskCacheEntry {
ShaderDiskCacheEntry();
~ShaderDiskCacheEntry();
bool Load(Common::FS::IOFile& file);
bool Save(Common::FS::IOFile& file) const;
bool HasProgramA() const {
return !code.empty() && !code_b.empty();
}
Tegra::Engines::ShaderType type{};
ProgramCode code;
ProgramCode code_b;
u64 unique_identifier = 0;
std::optional<u32> texture_handler_size;
u32 bound_buffer = 0;
VideoCommon::Shader::GraphicsInfo graphics_info;
VideoCommon::Shader::ComputeInfo compute_info;
VideoCommon::Shader::KeyMap keys;
VideoCommon::Shader::BoundSamplerMap bound_samplers;
VideoCommon::Shader::SeparateSamplerMap separate_samplers;
VideoCommon::Shader::BindlessSamplerMap bindless_samplers;
};
/// Contains an OpenGL dumped binary program
struct ShaderDiskCachePrecompiled {
u64 unique_identifier = 0;
GLenum binary_format = 0;
std::vector<u8> binary;
};
class ShaderDiskCacheOpenGL {
public:
explicit ShaderDiskCacheOpenGL();
~ShaderDiskCacheOpenGL();
/// Binds a title ID for all future operations.
void BindTitleID(u64 title_id);
/// Loads transferable cache. If file has a old version or on failure, it deletes the file.
std::optional<std::vector<ShaderDiskCacheEntry>> LoadTransferable();
/// Loads current game's precompiled cache. Invalidates on failure.
std::vector<ShaderDiskCachePrecompiled> LoadPrecompiled();
/// Removes the transferable (and precompiled) cache file.
void InvalidateTransferable();
/// Removes the precompiled cache file and clears virtual precompiled cache file.
void InvalidatePrecompiled();
/// Saves a raw dump to the transferable file. Checks for collisions.
void SaveEntry(const ShaderDiskCacheEntry& entry);
/// Saves a dump entry to the precompiled file. Does not check for collisions.
void SavePrecompiled(u64 unique_identifier, GLuint program);
/// Serializes virtual precompiled shader cache file to real file
void SaveVirtualPrecompiledFile();
private:
/// Loads the transferable cache. Returns empty on failure.
std::optional<std::vector<ShaderDiskCachePrecompiled>> LoadPrecompiledFile(
Common::FS::IOFile& file);
/// Opens current game's transferable file and write it's header if it doesn't exist
Common::FS::IOFile AppendTransferableFile() const;
/// Save precompiled header to precompiled_cache_in_memory
void SavePrecompiledHeaderToVirtualPrecompiledCache();
/// Create shader disk cache directories. Returns true on success.
bool EnsureDirectories() const;
/// Gets current game's transferable file path
std::filesystem::path GetTransferablePath() const;
/// Gets current game's precompiled file path
std::filesystem::path GetPrecompiledPath() const;
/// Get user's transferable directory path
std::filesystem::path GetTransferableDir() const;
/// Get user's precompiled directory path
std::filesystem::path GetPrecompiledDir() const;
/// Get user's shader directory path
std::filesystem::path GetBaseDir() const;
/// Get current game's title id
std::string GetTitleID() const;
template <typename T>
bool SaveArrayToPrecompiled(const T* data, std::size_t length) {
const std::size_t write_length = precompiled_cache_virtual_file.WriteArray(
data, length, precompiled_cache_virtual_file_offset);
precompiled_cache_virtual_file_offset += write_length;
return write_length == sizeof(T) * length;
}
template <typename T>
bool LoadArrayFromPrecompiled(T* data, std::size_t length) {
const std::size_t read_length = precompiled_cache_virtual_file.ReadArray(
data, length, precompiled_cache_virtual_file_offset);
precompiled_cache_virtual_file_offset += read_length;
return read_length == sizeof(T) * length;
}
template <typename T>
bool SaveObjectToPrecompiled(const T& object) {
return SaveArrayToPrecompiled(&object, 1);
}
bool SaveObjectToPrecompiled(bool object) {
const auto value = static_cast<u8>(object);
return SaveArrayToPrecompiled(&value, 1);
}
template <typename T>
bool LoadObjectFromPrecompiled(T& object) {
return LoadArrayFromPrecompiled(&object, 1);
}
// Stores whole precompiled cache which will be read from or saved to the precompiled chache
// file
FileSys::VectorVfsFile precompiled_cache_virtual_file;
// Stores the current offset of the precompiled cache file for IO purposes
std::size_t precompiled_cache_virtual_file_offset = 0;
// Stored transferable shaders
std::unordered_set<u64> stored_transferable;
/// Title ID to operate on
u64 title_id = 0;
// The cache has been loaded at boot
bool is_usable = false;
};
} // namespace OpenGL

1
src/video_core/renderer_vulkan/blit_image.cpp
View file

@ -323,7 +323,6 @@ void BindBlitState(vk::CommandBuffer cmdbuf, VkPipelineLayout layout, const Regi
cmdbuf.SetScissor(0, scissor);
cmdbuf.PushConstants(layout, VK_SHADER_STAGE_VERTEX_BIT, push_constants);
}
} // Anonymous namespace
BlitImageHelper::BlitImageHelper(const Device& device_, VKScheduler& scheduler_,

136
src/video_core/renderer_vulkan/vk_compute_pipeline.cpp
View file

@ -8,146 +8,14 @@
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_pipeline_cache.h"
#include "video_core/renderer_vulkan/vk_scheduler.h"
#include "video_core/renderer_vulkan/vk_shader_decompiler.h"
#include "video_core/renderer_vulkan/vk_update_descriptor.h"
#include "video_core/vulkan_common/vulkan_device.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
namespace Vulkan {
VKComputePipeline::VKComputePipeline(const Device& device_, VKScheduler& scheduler_,
VKDescriptorPool& descriptor_pool_,
VKUpdateDescriptorQueue& update_descriptor_queue_,
const SPIRVShader& shader_)
: device{device_}, scheduler{scheduler_}, entries{shader_.entries},
descriptor_set_layout{CreateDescriptorSetLayout()},
descriptor_allocator{descriptor_pool_, *descriptor_set_layout},
update_descriptor_queue{update_descriptor_queue_}, layout{CreatePipelineLayout()},
descriptor_template{CreateDescriptorUpdateTemplate()},
shader_module{CreateShaderModule(shader_.code)}, pipeline{CreatePipeline()} {}
ComputePipeline::ComputePipeline() = default;
VKComputePipeline::~VKComputePipeline() = default;
VkDescriptorSet VKComputePipeline::CommitDescriptorSet() {
if (!descriptor_template) {
return {};
}
const VkDescriptorSet set = descriptor_allocator.Commit();
update_descriptor_queue.Send(*descriptor_template, set);
return set;
}
vk::DescriptorSetLayout VKComputePipeline::CreateDescriptorSetLayout() const {
std::vector<VkDescriptorSetLayoutBinding> bindings;
u32 binding = 0;
const auto add_bindings = [&](VkDescriptorType descriptor_type, std::size_t num_entries) {
// TODO(Rodrigo): Maybe make individual bindings here?
for (u32 bindpoint = 0; bindpoint < static_cast<u32>(num_entries); ++bindpoint) {
bindings.push_back({
.binding = binding++,
.descriptorType = descriptor_type,
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
});
}
};
add_bindings(VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER, entries.const_buffers.size());
add_bindings(VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, entries.global_buffers.size());
add_bindings(VK_DESCRIPTOR_TYPE_UNIFORM_TEXEL_BUFFER, entries.uniform_texels.size());
add_bindings(VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, entries.samplers.size());
add_bindings(VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER, entries.storage_texels.size());
add_bindings(VK_DESCRIPTOR_TYPE_STORAGE_IMAGE, entries.images.size());
return device.GetLogical().CreateDescriptorSetLayout({
.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.bindingCount = static_cast<u32>(bindings.size()),
.pBindings = bindings.data(),
});
}
vk::PipelineLayout VKComputePipeline::CreatePipelineLayout() const {
return device.GetLogical().CreatePipelineLayout({
.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.setLayoutCount = 1,
.pSetLayouts = descriptor_set_layout.address(),
.pushConstantRangeCount = 0,
.pPushConstantRanges = nullptr,
});
}
vk::DescriptorUpdateTemplateKHR VKComputePipeline::CreateDescriptorUpdateTemplate() const {
std::vector<VkDescriptorUpdateTemplateEntryKHR> template_entries;
u32 binding = 0;
u32 offset = 0;
FillDescriptorUpdateTemplateEntries(entries, binding, offset, template_entries);
if (template_entries.empty()) {
// If the shader doesn't use descriptor sets, skip template creation.
return {};
}
return device.GetLogical().CreateDescriptorUpdateTemplateKHR({
.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_UPDATE_TEMPLATE_CREATE_INFO_KHR,
.pNext = nullptr,
.flags = 0,
.descriptorUpdateEntryCount = static_cast<u32>(template_entries.size()),
.pDescriptorUpdateEntries = template_entries.data(),
.templateType = VK_DESCRIPTOR_UPDATE_TEMPLATE_TYPE_DESCRIPTOR_SET_KHR,
.descriptorSetLayout = *descriptor_set_layout,
.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
.pipelineLayout = *layout,
.set = DESCRIPTOR_SET,
});
}
vk::ShaderModule VKComputePipeline::CreateShaderModule(const std::vector<u32>& code) const {
device.SaveShader(code);
return device.GetLogical().CreateShaderModule({
.sType = VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.codeSize = code.size() * sizeof(u32),
.pCode = code.data(),
});
}
vk::Pipeline VKComputePipeline::CreatePipeline() const {
VkComputePipelineCreateInfo ci{
.sType = VK_STRUCTURE_TYPE_COMPUTE_PIPELINE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.stage =
{
.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.stage = VK_SHADER_STAGE_COMPUTE_BIT,
.module = *shader_module,
.pName = "main",
.pSpecializationInfo = nullptr,
},
.layout = *layout,
.basePipelineHandle = nullptr,
.basePipelineIndex = 0,
};
const VkPipelineShaderStageRequiredSubgroupSizeCreateInfoEXT subgroup_size_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_REQUIRED_SUBGROUP_SIZE_CREATE_INFO_EXT,
.pNext = nullptr,
.requiredSubgroupSize = GuestWarpSize,
};
if (entries.uses_warps && device.IsGuestWarpSizeSupported(VK_SHADER_STAGE_COMPUTE_BIT)) {
ci.stage.pNext = &subgroup_size_ci;
}
return device.GetLogical().CreateComputePipeline(ci);
}
ComputePipeline::~ComputePipeline() = default;
} // namespace Vulkan

47
src/video_core/renderer_vulkan/vk_compute_pipeline.h
View file

@ -6,7 +6,6 @@
#include "common/common_types.h"
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_shader_decompiler.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
namespace Vulkan {
@ -15,50 +14,10 @@ class Device;
class VKScheduler;
class VKUpdateDescriptorQueue;
class VKComputePipeline final {
class ComputePipeline {
public:
explicit VKComputePipeline(const Device& device_, VKScheduler& scheduler_,
VKDescriptorPool& descriptor_pool_,
VKUpdateDescriptorQueue& update_descriptor_queue_,
const SPIRVShader& shader_);
~VKComputePipeline();
VkDescriptorSet CommitDescriptorSet();
VkPipeline GetHandle() const {
return *pipeline;
}
VkPipelineLayout GetLayout() const {
return *layout;
}
const ShaderEntries& GetEntries() const {
return entries;
}
private:
vk::DescriptorSetLayout CreateDescriptorSetLayout() const;
vk::PipelineLayout CreatePipelineLayout() const;
vk::DescriptorUpdateTemplateKHR CreateDescriptorUpdateTemplate() const;
vk::ShaderModule CreateShaderModule(const std::vector<u32>& code) const;
vk::Pipeline CreatePipeline() const;
const Device& device;
VKScheduler& scheduler;
ShaderEntries entries;
vk::DescriptorSetLayout descriptor_set_layout;
DescriptorAllocator descriptor_allocator;
VKUpdateDescriptorQueue& update_descriptor_queue;
vk::PipelineLayout layout;
vk::DescriptorUpdateTemplateKHR descriptor_template;
vk::ShaderModule shader_module;
vk::Pipeline pipeline;
explicit ComputePipeline();
~ComputePipeline();
};
} // namespace Vulkan

484
src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
View file

@ -1,484 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <array>
#include <cstring>
#include <vector>
#include "common/common_types.h"
#include "common/microprofile.h"
#include "video_core/renderer_vulkan/fixed_pipeline_state.h"
#include "video_core/renderer_vulkan/maxwell_to_vk.h"
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_graphics_pipeline.h"
#include "video_core/renderer_vulkan/vk_pipeline_cache.h"
#include "video_core/renderer_vulkan/vk_scheduler.h"
#include "video_core/renderer_vulkan/vk_update_descriptor.h"
#include "video_core/vulkan_common/vulkan_device.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
namespace Vulkan {
MICROPROFILE_DECLARE(Vulkan_PipelineCache);
namespace {
template <class StencilFace>
VkStencilOpState GetStencilFaceState(const StencilFace& face) {
return {
.failOp = MaxwellToVK::StencilOp(face.ActionStencilFail()),
.passOp = MaxwellToVK::StencilOp(face.ActionDepthPass()),
.depthFailOp = MaxwellToVK::StencilOp(face.ActionDepthFail()),
.compareOp = MaxwellToVK::ComparisonOp(face.TestFunc()),
.compareMask = 0,
.writeMask = 0,
.reference = 0,
};
}
bool SupportsPrimitiveRestart(VkPrimitiveTopology topology) {
static constexpr std::array unsupported_topologies = {
VK_PRIMITIVE_TOPOLOGY_POINT_LIST,
VK_PRIMITIVE_TOPOLOGY_LINE_LIST,
VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST,
VK_PRIMITIVE_TOPOLOGY_LINE_LIST_WITH_ADJACENCY,
VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST_WITH_ADJACENCY,
VK_PRIMITIVE_TOPOLOGY_PATCH_LIST};
return std::find(std::begin(unsupported_topologies), std::end(unsupported_topologies),
topology) == std::end(unsupported_topologies);
}
VkViewportSwizzleNV UnpackViewportSwizzle(u16 swizzle) {
union Swizzle {
u32 raw;
BitField<0, 3, Maxwell::ViewportSwizzle> x;
BitField<4, 3, Maxwell::ViewportSwizzle> y;
BitField<8, 3, Maxwell::ViewportSwizzle> z;
BitField<12, 3, Maxwell::ViewportSwizzle> w;
};
const Swizzle unpacked{swizzle};
return {
.x = MaxwellToVK::ViewportSwizzle(unpacked.x),
.y = MaxwellToVK::ViewportSwizzle(unpacked.y),
.z = MaxwellToVK::ViewportSwizzle(unpacked.z),
.w = MaxwellToVK::ViewportSwizzle(unpacked.w),
};
}
VkSampleCountFlagBits ConvertMsaaMode(Tegra::Texture::MsaaMode msaa_mode) {
switch (msaa_mode) {
case Tegra::Texture::MsaaMode::Msaa1x1:
return VK_SAMPLE_COUNT_1_BIT;
case Tegra::Texture::MsaaMode::Msaa2x1:
case Tegra::Texture::MsaaMode::Msaa2x1_D3D:
return VK_SAMPLE_COUNT_2_BIT;
case Tegra::Texture::MsaaMode::Msaa2x2:
case Tegra::Texture::MsaaMode::Msaa2x2_VC4:
case Tegra::Texture::MsaaMode::Msaa2x2_VC12:
return VK_SAMPLE_COUNT_4_BIT;
case Tegra::Texture::MsaaMode::Msaa4x2:
case Tegra::Texture::MsaaMode::Msaa4x2_D3D:
case Tegra::Texture::MsaaMode::Msaa4x2_VC8:
case Tegra::Texture::MsaaMode::Msaa4x2_VC24:
return VK_SAMPLE_COUNT_8_BIT;
case Tegra::Texture::MsaaMode::Msaa4x4:
return VK_SAMPLE_COUNT_16_BIT;
default:
UNREACHABLE_MSG("Invalid msaa_mode={}", static_cast<int>(msaa_mode));
return VK_SAMPLE_COUNT_1_BIT;
}
}
} // Anonymous namespace
VKGraphicsPipeline::VKGraphicsPipeline(const Device& device_, VKScheduler& scheduler_,
VKDescriptorPool& descriptor_pool_,
VKUpdateDescriptorQueue& update_descriptor_queue_,
const GraphicsPipelineCacheKey& key,
vk::Span<VkDescriptorSetLayoutBinding> bindings,
const SPIRVProgram& program, u32 num_color_buffers)
: device{device_}, scheduler{scheduler_}, cache_key{key}, hash{cache_key.Hash()},
descriptor_set_layout{CreateDescriptorSetLayout(bindings)},
descriptor_allocator{descriptor_pool_, *descriptor_set_layout},
update_descriptor_queue{update_descriptor_queue_}, layout{CreatePipelineLayout()},
descriptor_template{CreateDescriptorUpdateTemplate(program)},
modules(CreateShaderModules(program)),
pipeline(CreatePipeline(program, cache_key.renderpass, num_color_buffers)) {}
VKGraphicsPipeline::~VKGraphicsPipeline() = default;
VkDescriptorSet VKGraphicsPipeline::CommitDescriptorSet() {
if (!descriptor_template) {
return {};
}
const VkDescriptorSet set = descriptor_allocator.Commit();
update_descriptor_queue.Send(*descriptor_template, set);
return set;
}
vk::DescriptorSetLayout VKGraphicsPipeline::CreateDescriptorSetLayout(
vk::Span<VkDescriptorSetLayoutBinding> bindings) const {
const VkDescriptorSetLayoutCreateInfo ci{
.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.bindingCount = bindings.size(),
.pBindings = bindings.data(),
};
return device.GetLogical().CreateDescriptorSetLayout(ci);
}
vk::PipelineLayout VKGraphicsPipeline::CreatePipelineLayout() const {
const VkPipelineLayoutCreateInfo ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.setLayoutCount = 1,
.pSetLayouts = descriptor_set_layout.address(),
.pushConstantRangeCount = 0,
.pPushConstantRanges = nullptr,
};
return device.GetLogical().CreatePipelineLayout(ci);
}
vk::DescriptorUpdateTemplateKHR VKGraphicsPipeline::CreateDescriptorUpdateTemplate(
const SPIRVProgram& program) const {
std::vector<VkDescriptorUpdateTemplateEntry> template_entries;
u32 binding = 0;
u32 offset = 0;
for (const auto& stage : program) {
if (stage) {
FillDescriptorUpdateTemplateEntries(stage->entries, binding, offset, template_entries);
}
}
if (template_entries.empty()) {
// If the shader doesn't use descriptor sets, skip template creation.
return {};
}
const VkDescriptorUpdateTemplateCreateInfoKHR ci{
.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_UPDATE_TEMPLATE_CREATE_INFO_KHR,
.pNext = nullptr,
.flags = 0,
.descriptorUpdateEntryCount = static_cast<u32>(template_entries.size()),
.pDescriptorUpdateEntries = template_entries.data(),
.templateType = VK_DESCRIPTOR_UPDATE_TEMPLATE_TYPE_DESCRIPTOR_SET_KHR,
.descriptorSetLayout = *descriptor_set_layout,
.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
.pipelineLayout = *layout,
.set = DESCRIPTOR_SET,
};
return device.GetLogical().CreateDescriptorUpdateTemplateKHR(ci);
}
std::vector<vk::ShaderModule> VKGraphicsPipeline::CreateShaderModules(
const SPIRVProgram& program) const {
VkShaderModuleCreateInfo ci{
.sType = VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.codeSize = 0,
.pCode = nullptr,
};
std::vector<vk::ShaderModule> shader_modules;
shader_modules.reserve(Maxwell::MaxShaderStage);
for (std::size_t i = 0; i < Maxwell::MaxShaderStage; ++i) {
const auto& stage = program[i];
if (!stage) {
continue;
}
device.SaveShader(stage->code);
ci.codeSize = stage->code.size() * sizeof(u32);
ci.pCode = stage->code.data();
shader_modules.push_back(device.GetLogical().CreateShaderModule(ci));
}
return shader_modules;
}
vk::Pipeline VKGraphicsPipeline::CreatePipeline(const SPIRVProgram& program,
VkRenderPass renderpass,
u32 num_color_buffers) const {
const auto& state = cache_key.fixed_state;
const auto& viewport_swizzles = state.viewport_swizzles;
FixedPipelineState::DynamicState dynamic;
if (device.IsExtExtendedDynamicStateSupported()) {
// Insert dummy values, as long as they are valid they don't matter as extended dynamic
// state is ignored
dynamic.raw1 = 0;
dynamic.raw2 = 0;
dynamic.vertex_strides.fill(0);
} else {
dynamic = state.dynamic_state;
}
std::vector<VkVertexInputBindingDescription> vertex_bindings;
std::vector<VkVertexInputBindingDivisorDescriptionEXT> vertex_binding_divisors;
for (std::size_t index = 0; index < Maxwell::NumVertexArrays; ++index) {
const bool instanced = state.binding_divisors[index] != 0;
const auto rate = instanced ? VK_VERTEX_INPUT_RATE_INSTANCE : VK_VERTEX_INPUT_RATE_VERTEX;
vertex_bindings.push_back({
.binding = static_cast<u32>(index),
.stride = dynamic.vertex_strides[index],
.inputRate = rate,
});
if (instanced) {
vertex_binding_divisors.push_back({
.binding = static_cast<u32>(index),
.divisor = state.binding_divisors[index],
});
}
}
std::vector<VkVertexInputAttributeDescription> vertex_attributes;
const auto& input_attributes = program[0]->entries.attributes;
for (std::size_t index = 0; index < state.attributes.size(); ++index) {
const auto& attribute = state.attributes[index];
if (!attribute.enabled) {
continue;
}
if (!input_attributes.contains(static_cast<u32>(index))) {
// Skip attributes not used by the vertex shaders.
continue;
}
vertex_attributes.push_back({
.location = static_cast<u32>(index),
.binding = attribute.buffer,
.format = MaxwellToVK::VertexFormat(attribute.Type(), attribute.Size()),
.offset = attribute.offset,
});
}
VkPipelineVertexInputStateCreateInfo vertex_input_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.vertexBindingDescriptionCount = static_cast<u32>(vertex_bindings.size()),
.pVertexBindingDescriptions = vertex_bindings.data(),
.vertexAttributeDescriptionCount = static_cast<u32>(vertex_attributes.size()),
.pVertexAttributeDescriptions = vertex_attributes.data(),
};
const VkPipelineVertexInputDivisorStateCreateInfoEXT input_divisor_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_DIVISOR_STATE_CREATE_INFO_EXT,
.pNext = nullptr,
.vertexBindingDivisorCount = static_cast<u32>(vertex_binding_divisors.size()),
.pVertexBindingDivisors = vertex_binding_divisors.data(),
};
if (!vertex_binding_divisors.empty()) {
vertex_input_ci.pNext = &input_divisor_ci;
}
const auto input_assembly_topology = MaxwellToVK::PrimitiveTopology(device, state.topology);
const VkPipelineInputAssemblyStateCreateInfo input_assembly_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.topology = MaxwellToVK::PrimitiveTopology(device, state.topology),
.primitiveRestartEnable = state.primitive_restart_enable != 0 &&
SupportsPrimitiveRestart(input_assembly_topology),
};
const VkPipelineTessellationStateCreateInfo tessellation_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_TESSELLATION_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.patchControlPoints = state.patch_control_points_minus_one.Value() + 1,
};
VkPipelineViewportStateCreateInfo viewport_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.viewportCount = Maxwell::NumViewports,
.pViewports = nullptr,
.scissorCount = Maxwell::NumViewports,
.pScissors = nullptr,
};
std::array<VkViewportSwizzleNV, Maxwell::NumViewports> swizzles;
std::ranges::transform(viewport_swizzles, swizzles.begin(), UnpackViewportSwizzle);
VkPipelineViewportSwizzleStateCreateInfoNV swizzle_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_SWIZZLE_STATE_CREATE_INFO_NV,
.pNext = nullptr,
.flags = 0,
.viewportCount = Maxwell::NumViewports,
.pViewportSwizzles = swizzles.data(),
};
if (device.IsNvViewportSwizzleSupported()) {
viewport_ci.pNext = &swizzle_ci;
}
const VkPipelineRasterizationStateCreateInfo rasterization_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.depthClampEnable =
static_cast<VkBool32>(state.depth_clamp_disabled == 0 ? VK_TRUE : VK_FALSE),
.rasterizerDiscardEnable =
static_cast<VkBool32>(state.rasterize_enable == 0 ? VK_TRUE : VK_FALSE),
.polygonMode = VK_POLYGON_MODE_FILL,
.cullMode = static_cast<VkCullModeFlags>(
dynamic.cull_enable ? MaxwellToVK::CullFace(dynamic.CullFace()) : VK_CULL_MODE_NONE),
.frontFace = MaxwellToVK::FrontFace(dynamic.FrontFace()),
.depthBiasEnable = state.depth_bias_enable,
.depthBiasConstantFactor = 0.0f,
.depthBiasClamp = 0.0f,
.depthBiasSlopeFactor = 0.0f,
.lineWidth = 1.0f,
};
const VkPipelineMultisampleStateCreateInfo multisample_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.rasterizationSamples = ConvertMsaaMode(state.msaa_mode),
.sampleShadingEnable = VK_FALSE,
.minSampleShading = 0.0f,
.pSampleMask = nullptr,
.alphaToCoverageEnable = VK_FALSE,
.alphaToOneEnable = VK_FALSE,
};
const VkPipelineDepthStencilStateCreateInfo depth_stencil_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_DEPTH_STENCIL_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.depthTestEnable = dynamic.depth_test_enable,
.depthWriteEnable = dynamic.depth_write_enable,
.depthCompareOp = dynamic.depth_test_enable
? MaxwellToVK::ComparisonOp(dynamic.DepthTestFunc())
: VK_COMPARE_OP_ALWAYS,
.depthBoundsTestEnable = dynamic.depth_bounds_enable,
.stencilTestEnable = dynamic.stencil_enable,
.front = GetStencilFaceState(dynamic.front),
.back = GetStencilFaceState(dynamic.back),
.minDepthBounds = 0.0f,
.maxDepthBounds = 0.0f,
};
std::array<VkPipelineColorBlendAttachmentState, Maxwell::NumRenderTargets> cb_attachments;
for (std::size_t index = 0; index < num_color_buffers; ++index) {
static constexpr std::array COMPONENT_TABLE{
VK_COLOR_COMPONENT_R_BIT,
VK_COLOR_COMPONENT_G_BIT,
VK_COLOR_COMPONENT_B_BIT,
VK_COLOR_COMPONENT_A_BIT,
};
const auto& blend = state.attachments[index];
VkColorComponentFlags color_components = 0;
for (std::size_t i = 0; i < COMPONENT_TABLE.size(); ++i) {
if (blend.Mask()[i]) {
color_components |= COMPONENT_TABLE[i];
}
}
cb_attachments[index] = {
.blendEnable = blend.enable != 0,
.srcColorBlendFactor = MaxwellToVK::BlendFactor(blend.SourceRGBFactor()),
.dstColorBlendFactor = MaxwellToVK::BlendFactor(blend.DestRGBFactor()),
.colorBlendOp = MaxwellToVK::BlendEquation(blend.EquationRGB()),
.srcAlphaBlendFactor = MaxwellToVK::BlendFactor(blend.SourceAlphaFactor()),
.dstAlphaBlendFactor = MaxwellToVK::BlendFactor(blend.DestAlphaFactor()),
.alphaBlendOp = MaxwellToVK::BlendEquation(blend.EquationAlpha()),
.colorWriteMask = color_components,
};
}
const VkPipelineColorBlendStateCreateInfo color_blend_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.logicOpEnable = VK_FALSE,
.logicOp = VK_LOGIC_OP_COPY,
.attachmentCount = num_color_buffers,
.pAttachments = cb_attachments.data(),
.blendConstants = {},
};
std::vector dynamic_states{
VK_DYNAMIC_STATE_VIEWPORT, VK_DYNAMIC_STATE_SCISSOR,
VK_DYNAMIC_STATE_DEPTH_BIAS, VK_DYNAMIC_STATE_BLEND_CONSTANTS,
VK_DYNAMIC_STATE_DEPTH_BOUNDS, VK_DYNAMIC_STATE_STENCIL_COMPARE_MASK,
VK_DYNAMIC_STATE_STENCIL_WRITE_MASK, VK_DYNAMIC_STATE_STENCIL_REFERENCE,
};
if (device.IsExtExtendedDynamicStateSupported()) {
static constexpr std::array extended{
VK_DYNAMIC_STATE_CULL_MODE_EXT,
VK_DYNAMIC_STATE_FRONT_FACE_EXT,
VK_DYNAMIC_STATE_VERTEX_INPUT_BINDING_STRIDE_EXT,
VK_DYNAMIC_STATE_DEPTH_TEST_ENABLE_EXT,
VK_DYNAMIC_STATE_DEPTH_WRITE_ENABLE_EXT,
VK_DYNAMIC_STATE_DEPTH_COMPARE_OP_EXT,
VK_DYNAMIC_STATE_DEPTH_BOUNDS_TEST_ENABLE_EXT,
VK_DYNAMIC_STATE_STENCIL_TEST_ENABLE_EXT,
VK_DYNAMIC_STATE_STENCIL_OP_EXT,
};
dynamic_states.insert(dynamic_states.end(), extended.begin(), extended.end());
}
const VkPipelineDynamicStateCreateInfo dynamic_state_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.dynamicStateCount = static_cast<u32>(dynamic_states.size()),
.pDynamicStates = dynamic_states.data(),
};
const VkPipelineShaderStageRequiredSubgroupSizeCreateInfoEXT subgroup_size_ci{
.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_REQUIRED_SUBGROUP_SIZE_CREATE_INFO_EXT,
.pNext = nullptr,
.requiredSubgroupSize = GuestWarpSize,
};
std::vector<VkPipelineShaderStageCreateInfo> shader_stages;
std::size_t module_index = 0;
for (std::size_t stage = 0; stage < Maxwell::MaxShaderStage; ++stage) {
if (!program[stage]) {
continue;
}
VkPipelineShaderStageCreateInfo& stage_ci = shader_stages.emplace_back();
stage_ci.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
stage_ci.pNext = nullptr;
stage_ci.flags = 0;
stage_ci.stage = MaxwellToVK::ShaderStage(static_cast<Tegra::Engines::ShaderType>(stage));
stage_ci.module = *modules[module_index++];
stage_ci.pName = "main";
stage_ci.pSpecializationInfo = nullptr;
if (program[stage]->entries.uses_warps && device.IsGuestWarpSizeSupported(stage_ci.stage)) {
stage_ci.pNext = &subgroup_size_ci;
}
}
return device.GetLogical().CreateGraphicsPipeline(VkGraphicsPipelineCreateInfo{
.sType = VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO,
.pNext = nullptr,
.flags = 0,
.stageCount = static_cast<u32>(shader_stages.size()),
.pStages = shader_stages.data(),
.pVertexInputState = &vertex_input_ci,
.pInputAssemblyState = &input_assembly_ci,
.pTessellationState = &tessellation_ci,
.pViewportState = &viewport_ci,
.pRasterizationState = &rasterization_ci,
.pMultisampleState = &multisample_ci,
.pDepthStencilState = &depth_stencil_ci,
.pColorBlendState = &color_blend_ci,
.pDynamicState = &dynamic_state_ci,
.layout = *layout,
.renderPass = renderpass,
.subpass = 0,
.basePipelineHandle = nullptr,
.basePipelineIndex = 0,
});
}
} // namespace Vulkan

103
src/video_core/renderer_vulkan/vk_graphics_pipeline.h
View file

@ -1,103 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <array>
#include <optional>
#include <vector>
#include "common/common_types.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/renderer_vulkan/fixed_pipeline_state.h"
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_shader_decompiler.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
namespace Vulkan {
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
struct GraphicsPipelineCacheKey {
VkRenderPass renderpass;
std::array<GPUVAddr, Maxwell::MaxShaderProgram> shaders;
FixedPipelineState fixed_state;
std::size_t Hash() const noexcept;
bool operator==(const GraphicsPipelineCacheKey& rhs) const noexcept;
bool operator!=(const GraphicsPipelineCacheKey& rhs) const noexcept {
return !operator==(rhs);
}
std::size_t Size() const noexcept {
return sizeof(renderpass) + sizeof(shaders) + fixed_state.Size();
}
};
static_assert(std::has_unique_object_representations_v<GraphicsPipelineCacheKey>);
static_assert(std::is_trivially_copyable_v<GraphicsPipelineCacheKey>);
static_assert(std::is_trivially_constructible_v<GraphicsPipelineCacheKey>);
class Device;
class VKDescriptorPool;
class VKScheduler;
class VKUpdateDescriptorQueue;
using SPIRVProgram = std::array<std::optional<SPIRVShader>, Maxwell::MaxShaderStage>;
class VKGraphicsPipeline final {
public:
explicit VKGraphicsPipeline(const Device& device_, VKScheduler& scheduler_,
VKDescriptorPool& descriptor_pool,
VKUpdateDescriptorQueue& update_descriptor_queue_,
const GraphicsPipelineCacheKey& key,
vk::Span<VkDescriptorSetLayoutBinding> bindings,
const SPIRVProgram& program, u32 num_color_buffers);
~VKGraphicsPipeline();
VkDescriptorSet CommitDescriptorSet();
VkPipeline GetHandle() const {
return *pipeline;
}
VkPipelineLayout GetLayout() const {
return *layout;
}
GraphicsPipelineCacheKey GetCacheKey() const {
return cache_key;
}
private:
vk::DescriptorSetLayout CreateDescriptorSetLayout(
vk::Span<VkDescriptorSetLayoutBinding> bindings) const;
vk::PipelineLayout CreatePipelineLayout() const;
vk::DescriptorUpdateTemplateKHR CreateDescriptorUpdateTemplate(
const SPIRVProgram& program) const;
std::vector<vk::ShaderModule> CreateShaderModules(const SPIRVProgram& program) const;
vk::Pipeline CreatePipeline(const SPIRVProgram& program, VkRenderPass renderpass,
u32 num_color_buffers) const;
const Device& device;
VKScheduler& scheduler;
const GraphicsPipelineCacheKey cache_key;
const u64 hash;
vk::DescriptorSetLayout descriptor_set_layout;
DescriptorAllocator descriptor_allocator;
VKUpdateDescriptorQueue& update_descriptor_queue;
vk::PipelineLayout layout;
vk::DescriptorUpdateTemplateKHR descriptor_template;
std::vector<vk::ShaderModule> modules;
vk::Pipeline pipeline;
};
} // namespace Vulkan

375
src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
View file

@ -19,49 +19,27 @@
#include "video_core/renderer_vulkan/maxwell_to_vk.h"
#include "video_core/renderer_vulkan/vk_compute_pipeline.h"
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_graphics_pipeline.h"
#include "video_core/renderer_vulkan/vk_pipeline_cache.h"
#include "video_core/renderer_vulkan/vk_rasterizer.h"
#include "video_core/renderer_vulkan/vk_scheduler.h"
#include "video_core/renderer_vulkan/vk_update_descriptor.h"
#include "video_core/shader/compiler_settings.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader_cache.h"
#include "video_core/shader_notify.h"
#include "video_core/vulkan_common/vulkan_device.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
namespace Vulkan {
MICROPROFILE_DECLARE(Vulkan_PipelineCache);
using Tegra::Engines::ShaderType;
using VideoCommon::Shader::GetShaderAddress;
using VideoCommon::Shader::GetShaderCode;
using VideoCommon::Shader::KERNEL_MAIN_OFFSET;
using VideoCommon::Shader::ProgramCode;
using VideoCommon::Shader::STAGE_MAIN_OFFSET;
namespace {
constexpr VkDescriptorType UNIFORM_BUFFER = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER;
constexpr VkDescriptorType STORAGE_BUFFER = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
constexpr VkDescriptorType UNIFORM_TEXEL_BUFFER = VK_DESCRIPTOR_TYPE_UNIFORM_TEXEL_BUFFER;
constexpr VkDescriptorType COMBINED_IMAGE_SAMPLER = VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER;
constexpr VkDescriptorType STORAGE_TEXEL_BUFFER = VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER;
constexpr VkDescriptorType STORAGE_IMAGE = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE;
constexpr VideoCommon::Shader::CompilerSettings compiler_settings{
.depth = VideoCommon::Shader::CompileDepth::FullDecompile,
.disable_else_derivation = true,
};
constexpr std::size_t GetStageFromProgram(std::size_t program) {
size_t StageFromProgram(size_t program) {
return program == 0 ? 0 : program - 1;
}
constexpr ShaderType GetStageFromProgram(Maxwell::ShaderProgram program) {
return static_cast<ShaderType>(GetStageFromProgram(static_cast<std::size_t>(program)));
ShaderType StageFromProgram(Maxwell::ShaderProgram program) {
return static_cast<ShaderType>(StageFromProgram(static_cast<size_t>(program)));
}
ShaderType GetShaderType(Maxwell::ShaderProgram program) {
@ -81,165 +59,35 @@ ShaderType GetShaderType(Maxwell::ShaderProgram program) {
return ShaderType::Vertex;
}
}
template <VkDescriptorType descriptor_type, class Container>
void AddBindings(std::vector<VkDescriptorSetLayoutBinding>& bindings, u32& binding,
VkShaderStageFlags stage_flags, const Container& container) {
const u32 num_entries = static_cast<u32>(std::size(container));
for (std::size_t i = 0; i < num_entries; ++i) {
u32 count = 1;
if constexpr (descriptor_type == VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER) {
// Combined image samplers can be arrayed.
count = container[i].size;
}
bindings.push_back({
.binding = binding++,
.descriptorType = descriptor_type,
.descriptorCount = count,
.stageFlags = stage_flags,
.pImmutableSamplers = nullptr,
});
}
}
u32 FillDescriptorLayout(const ShaderEntries& entries,
std::vector<VkDescriptorSetLayoutBinding>& bindings,
Maxwell::ShaderProgram program_type, u32 base_binding) {
const ShaderType stage = GetStageFromProgram(program_type);
const VkShaderStageFlags flags = MaxwellToVK::ShaderStage(stage);
u32 binding = base_binding;
AddBindings<UNIFORM_BUFFER>(bindings, binding, flags, entries.const_buffers);
AddBindings<STORAGE_BUFFER>(bindings, binding, flags, entries.global_buffers);
AddBindings<UNIFORM_TEXEL_BUFFER>(bindings, binding, flags, entries.uniform_texels);
AddBindings<COMBINED_IMAGE_SAMPLER>(bindings, binding, flags, entries.samplers);
AddBindings<STORAGE_TEXEL_BUFFER>(bindings, binding, flags, entries.storage_texels);
AddBindings<STORAGE_IMAGE>(bindings, binding, flags, entries.images);
return binding;
}
} // Anonymous namespace
std::size_t GraphicsPipelineCacheKey::Hash() const noexcept {
const u64 hash = Common::CityHash64(reinterpret_cast<const char*>(this), Size());
return static_cast<std::size_t>(hash);
}
bool GraphicsPipelineCacheKey::operator==(const GraphicsPipelineCacheKey& rhs) const noexcept {
return std::memcmp(&rhs, this, Size()) == 0;
}
std::size_t ComputePipelineCacheKey::Hash() const noexcept {
size_t ComputePipelineCacheKey::Hash() const noexcept {
const u64 hash = Common::CityHash64(reinterpret_cast<const char*>(this), sizeof *this);
return static_cast<std::size_t>(hash);
return static_cast<size_t>(hash);
}
bool ComputePipelineCacheKey::operator==(const ComputePipelineCacheKey& rhs) const noexcept {
return std::memcmp(&rhs, this, sizeof *this) == 0;
}
Shader::Shader(Tegra::Engines::ConstBufferEngineInterface& engine_, ShaderType stage_,
GPUVAddr gpu_addr_, VAddr cpu_addr_, ProgramCode program_code_, u32 main_offset_)
: gpu_addr(gpu_addr_), program_code(std::move(program_code_)), registry(stage_, engine_),
shader_ir(program_code, main_offset_, compiler_settings, registry),
entries(GenerateShaderEntries(shader_ir)) {}
Shader::Shader() = default;
Shader::~Shader() = default;
VKPipelineCache::VKPipelineCache(RasterizerVulkan& rasterizer_, Tegra::GPU& gpu_,
Tegra::Engines::Maxwell3D& maxwell3d_,
Tegra::Engines::KeplerCompute& kepler_compute_,
Tegra::MemoryManager& gpu_memory_, const Device& device_,
VKScheduler& scheduler_, VKDescriptorPool& descriptor_pool_,
VKUpdateDescriptorQueue& update_descriptor_queue_)
PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, Tegra::GPU& gpu_,
Tegra::Engines::Maxwell3D& maxwell3d_,
Tegra::Engines::KeplerCompute& kepler_compute_,
Tegra::MemoryManager& gpu_memory_, const Device& device_,
VKScheduler& scheduler_, VKDescriptorPool& descriptor_pool_,
VKUpdateDescriptorQueue& update_descriptor_queue_)
: VideoCommon::ShaderCache<Shader>{rasterizer_}, gpu{gpu_}, maxwell3d{maxwell3d_},
kepler_compute{kepler_compute_}, gpu_memory{gpu_memory_}, device{device_},
scheduler{scheduler_}, descriptor_pool{descriptor_pool_}, update_descriptor_queue{
update_descriptor_queue_} {}
VKPipelineCache::~VKPipelineCache() = default;
PipelineCache::~PipelineCache() = default;
std::array<Shader*, Maxwell::MaxShaderProgram> VKPipelineCache::GetShaders() {
std::array<Shader*, Maxwell::MaxShaderProgram> shaders{};
for (std::size_t index = 0; index < Maxwell::MaxShaderProgram; ++index) {
const auto program{static_cast<Maxwell::ShaderProgram>(index)};
// Skip stages that are not enabled
if (!maxwell3d.regs.IsShaderConfigEnabled(index)) {
continue;
}
const GPUVAddr gpu_addr{GetShaderAddress(maxwell3d, program)};
const std::optional<VAddr> cpu_addr = gpu_memory.GpuToCpuAddress(gpu_addr);
ASSERT(cpu_addr);
Shader* result = cpu_addr ? TryGet(*cpu_addr) : null_shader.get();
if (!result) {
const u8* const host_ptr{gpu_memory.GetPointer(gpu_addr)};
// No shader found - create a new one
static constexpr u32 stage_offset = STAGE_MAIN_OFFSET;
const auto stage = static_cast<ShaderType>(index == 0 ? 0 : index - 1);
ProgramCode code = GetShaderCode(gpu_memory, gpu_addr, host_ptr, false);
const std::size_t size_in_bytes = code.size() * sizeof(u64);
auto shader = std::make_unique<Shader>(maxwell3d, stage, gpu_addr, *cpu_addr,
std::move(code), stage_offset);
result = shader.get();
if (cpu_addr) {
Register(std::move(shader), *cpu_addr, size_in_bytes);
} else {
null_shader = std::move(shader);
}
}
shaders[index] = result;
}
return last_shaders = shaders;
}
VKGraphicsPipeline* VKPipelineCache::GetGraphicsPipeline(
const GraphicsPipelineCacheKey& key, u32 num_color_buffers,
VideoCommon::Shader::AsyncShaders& async_shaders) {
MICROPROFILE_SCOPE(Vulkan_PipelineCache);
if (last_graphics_pipeline && last_graphics_key == key) {
return last_graphics_pipeline;
}
last_graphics_key = key;
if (device.UseAsynchronousShaders() && async_shaders.IsShaderAsync(gpu)) {
std::unique_lock lock{pipeline_cache};
const auto [pair, is_cache_miss] = graphics_cache.try_emplace(key);
if (is_cache_miss) {
gpu.ShaderNotify().MarkSharderBuilding();
LOG_INFO(Render_Vulkan, "Compile 0x{:016X}", key.Hash());
const auto [program, bindings] = DecompileShaders(key.fixed_state);
async_shaders.QueueVulkanShader(this, device, scheduler, descriptor_pool,
update_descriptor_queue, bindings, program, key,
num_color_buffers);
}
last_graphics_pipeline = pair->second.get();
return last_graphics_pipeline;
}
const auto [pair, is_cache_miss] = graphics_cache.try_emplace(key);
auto& entry = pair->second;
if (is_cache_miss) {
gpu.ShaderNotify().MarkSharderBuilding();
LOG_INFO(Render_Vulkan, "Compile 0x{:016X}", key.Hash());
const auto [program, bindings] = DecompileShaders(key.fixed_state);
entry = std::make_unique<VKGraphicsPipeline>(device, scheduler, descriptor_pool,
update_descriptor_queue, key, bindings,
program, num_color_buffers);
gpu.ShaderNotify().MarkShaderComplete();
}
last_graphics_pipeline = entry.get();
return last_graphics_pipeline;
}
VKComputePipeline& VKPipelineCache::GetComputePipeline(const ComputePipelineCacheKey& key) {
ComputePipeline& PipelineCache::GetComputePipeline(const ComputePipelineCacheKey& key) {
MICROPROFILE_SCOPE(Vulkan_PipelineCache);
const auto [pair, is_cache_miss] = compute_cache.try_emplace(key);
@ -248,200 +96,9 @@ VKComputePipeline& VKPipelineCache::GetComputePipeline(const ComputePipelineCach
return *entry;
}
LOG_INFO(Render_Vulkan, "Compile 0x{:016X}", key.Hash());
const GPUVAddr gpu_addr = key.shader;
const std::optional<VAddr> cpu_addr = gpu_memory.GpuToCpuAddress(gpu_addr);
ASSERT(cpu_addr);
Shader* shader = cpu_addr ? TryGet(*cpu_addr) : null_kernel.get();
if (!shader) {
// No shader found - create a new one
const auto host_ptr = gpu_memory.GetPointer(gpu_addr);
ProgramCode code = GetShaderCode(gpu_memory, gpu_addr, host_ptr, true);
const std::size_t size_in_bytes = code.size() * sizeof(u64);
auto shader_info = std::make_unique<Shader>(kepler_compute, ShaderType::Compute, gpu_addr,
*cpu_addr, std::move(code), KERNEL_MAIN_OFFSET);
shader = shader_info.get();
if (cpu_addr) {
Register(std::move(shader_info), *cpu_addr, size_in_bytes);
} else {
null_kernel = std::move(shader_info);
}
}
const Specialization specialization{
.base_binding = 0,
.workgroup_size = key.workgroup_size,
.shared_memory_size = key.shared_memory_size,
.point_size = std::nullopt,
.enabled_attributes = {},
.attribute_types = {},
.ndc_minus_one_to_one = false,
};
const SPIRVShader spirv_shader{Decompile(device, shader->GetIR(), ShaderType::Compute,
shader->GetRegistry(), specialization),
shader->GetEntries()};
entry = std::make_unique<VKComputePipeline>(device, scheduler, descriptor_pool,
update_descriptor_queue, spirv_shader);
return *entry;
throw "Bad";
}
void VKPipelineCache::EmplacePipeline(std::unique_ptr<VKGraphicsPipeline> pipeline) {
gpu.ShaderNotify().MarkShaderComplete();
std::unique_lock lock{pipeline_cache};
graphics_cache.at(pipeline->GetCacheKey()) = std::move(pipeline);
}
void VKPipelineCache::OnShaderRemoval(Shader* shader) {
bool finished = false;
const auto Finish = [&] {
// TODO(Rodrigo): Instead of finishing here, wait for the fences that use this pipeline and
// flush.
if (finished) {
return;
}
finished = true;
scheduler.Finish();
};
const GPUVAddr invalidated_addr = shader->GetGpuAddr();
for (auto it = graphics_cache.begin(); it != graphics_cache.end();) {
auto& entry = it->first;
if (std::find(entry.shaders.begin(), entry.shaders.end(), invalidated_addr) ==
entry.shaders.end()) {
++it;
continue;
}
Finish();
it = graphics_cache.erase(it);
}
for (auto it = compute_cache.begin(); it != compute_cache.end();) {
auto& entry = it->first;
if (entry.shader != invalidated_addr) {
++it;
continue;
}
Finish();
it = compute_cache.erase(it);
}
}
std::pair<SPIRVProgram, std::vector<VkDescriptorSetLayoutBinding>>
VKPipelineCache::DecompileShaders(const FixedPipelineState& fixed_state) {
Specialization specialization;
if (fixed_state.topology == Maxwell::PrimitiveTopology::Points) {
float point_size;
std::memcpy(&point_size, &fixed_state.point_size, sizeof(float));
specialization.point_size = point_size;
ASSERT(point_size != 0.0f);
}
for (std::size_t i = 0; i < Maxwell::NumVertexAttributes; ++i) {
const auto& attribute = fixed_state.attributes[i];
specialization.enabled_attributes[i] = attribute.enabled.Value() != 0;
specialization.attribute_types[i] = attribute.Type();
}
specialization.ndc_minus_one_to_one = fixed_state.ndc_minus_one_to_one;
specialization.early_fragment_tests = fixed_state.early_z;
// Alpha test
specialization.alpha_test_func =
FixedPipelineState::UnpackComparisonOp(fixed_state.alpha_test_func.Value());
specialization.alpha_test_ref = Common::BitCast<float>(fixed_state.alpha_test_ref);
SPIRVProgram program;
std::vector<VkDescriptorSetLayoutBinding> bindings;
for (std::size_t index = 1; index < Maxwell::MaxShaderProgram; ++index) {
const auto program_enum = static_cast<Maxwell::ShaderProgram>(index);
// Skip stages that are not enabled
if (!maxwell3d.regs.IsShaderConfigEnabled(index)) {
continue;
}
const GPUVAddr gpu_addr = GetShaderAddress(maxwell3d, program_enum);
const std::optional<VAddr> cpu_addr = gpu_memory.GpuToCpuAddress(gpu_addr);
Shader* const shader = cpu_addr ? TryGet(*cpu_addr) : null_shader.get();
const std::size_t stage = index == 0 ? 0 : index - 1; // Stage indices are 0 - 5
const ShaderType program_type = GetShaderType(program_enum);
const auto& entries = shader->GetEntries();
program[stage] = {
Decompile(device, shader->GetIR(), program_type, shader->GetRegistry(), specialization),
entries,
};
const u32 old_binding = specialization.base_binding;
specialization.base_binding =
FillDescriptorLayout(entries, bindings, program_enum, specialization.base_binding);
ASSERT(old_binding + entries.NumBindings() == specialization.base_binding);
}
return {std::move(program), std::move(bindings)};
}
template <VkDescriptorType descriptor_type, class Container>
void AddEntry(std::vector<VkDescriptorUpdateTemplateEntry>& template_entries, u32& binding,
u32& offset, const Container& container) {
static constexpr u32 entry_size = static_cast<u32>(sizeof(DescriptorUpdateEntry));
const u32 count = static_cast<u32>(std::size(container));
if constexpr (descriptor_type == COMBINED_IMAGE_SAMPLER) {
for (u32 i = 0; i < count; ++i) {
const u32 num_samplers = container[i].size;
template_entries.push_back({
.dstBinding = binding,
.dstArrayElement = 0,
.descriptorCount = num_samplers,
.descriptorType = descriptor_type,
.offset = offset,
.stride = entry_size,
});
++binding;
offset += num_samplers * entry_size;
}
return;
}
if constexpr (descriptor_type == UNIFORM_TEXEL_BUFFER ||
descriptor_type == STORAGE_TEXEL_BUFFER) {
// Nvidia has a bug where updating multiple texels at once causes the driver to crash.
// Note: Fixed in driver Windows 443.24, Linux 440.66.15
for (u32 i = 0; i < count; ++i) {
template_entries.push_back({
.dstBinding = binding + i,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = descriptor_type,
.offset = static_cast<std::size_t>(offset + i * entry_size),
.stride = entry_size,
});
}
} else if (count > 0) {
template_entries.push_back({
.dstBinding = binding,
.dstArrayElement = 0,
.descriptorCount = count,
.descriptorType = descriptor_type,
.offset = offset,
.stride = entry_size,
});
}
offset += count * entry_size;
binding += count;
}
void FillDescriptorUpdateTemplateEntries(
const ShaderEntries& entries, u32& binding, u32& offset,
std::vector<VkDescriptorUpdateTemplateEntryKHR>& template_entries) {
AddEntry<UNIFORM_BUFFER>(template_entries, offset, binding, entries.const_buffers);
AddEntry<STORAGE_BUFFER>(template_entries, offset, binding, entries.global_buffers);
AddEntry<UNIFORM_TEXEL_BUFFER>(template_entries, offset, binding, entries.uniform_texels);
AddEntry<COMBINED_IMAGE_SAMPLER>(template_entries, offset, binding, entries.samplers);
AddEntry<STORAGE_TEXEL_BUFFER>(template_entries, offset, binding, entries.storage_texels);
AddEntry<STORAGE_IMAGE>(template_entries, offset, binding, entries.images);
}
void PipelineCache::OnShaderRemoval(Shader*) {}
} // namespace Vulkan

91
src/video_core/renderer_vulkan/vk_pipeline_cache.h
View file

@ -15,15 +15,8 @@
#include <boost/functional/hash.hpp>
#include "common/common_types.h"
#include "video_core/engines/const_buffer_engine_interface.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/renderer_vulkan/fixed_pipeline_state.h"
#include "video_core/renderer_vulkan/vk_graphics_pipeline.h"
#include "video_core/renderer_vulkan/vk_shader_decompiler.h"
#include "video_core/shader/async_shaders.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
#include "video_core/shader_cache.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
@ -35,7 +28,7 @@ namespace Vulkan {
class Device;
class RasterizerVulkan;
class VKComputePipeline;
class ComputePipeline;
class VKDescriptorPool;
class VKScheduler;
class VKUpdateDescriptorQueue;
@ -47,7 +40,7 @@ struct ComputePipelineCacheKey {
u32 shared_memory_size;
std::array<u32, 3> workgroup_size;
std::size_t Hash() const noexcept;
size_t Hash() const noexcept;
bool operator==(const ComputePipelineCacheKey& rhs) const noexcept;
@ -63,16 +56,9 @@ static_assert(std::is_trivially_constructible_v<ComputePipelineCacheKey>);
namespace std {
template <>
struct hash<Vulkan::GraphicsPipelineCacheKey> {
std::size_t operator()(const Vulkan::GraphicsPipelineCacheKey& k) const noexcept {
return k.Hash();
}
};
template <>
struct hash<Vulkan::ComputePipelineCacheKey> {
std::size_t operator()(const Vulkan::ComputePipelineCacheKey& k) const noexcept {
size_t operator()(const Vulkan::ComputePipelineCacheKey& k) const noexcept {
return k.Hash();
}
};
@ -83,66 +69,26 @@ namespace Vulkan {
class Shader {
public:
explicit Shader(Tegra::Engines::ConstBufferEngineInterface& engine_,
Tegra::Engines::ShaderType stage_, GPUVAddr gpu_addr, VAddr cpu_addr_,
VideoCommon::Shader::ProgramCode program_code, u32 main_offset_);
explicit Shader();
~Shader();
GPUVAddr GetGpuAddr() const {
return gpu_addr;
}
VideoCommon::Shader::ShaderIR& GetIR() {
return shader_ir;
}
const VideoCommon::Shader::ShaderIR& GetIR() const {
return shader_ir;
}
const VideoCommon::Shader::Registry& GetRegistry() const {
return registry;
}
const ShaderEntries& GetEntries() const {
return entries;
}
private:
GPUVAddr gpu_addr{};
VideoCommon::Shader::ProgramCode program_code;
VideoCommon::Shader::Registry registry;
VideoCommon::Shader::ShaderIR shader_ir;
ShaderEntries entries;
};
class VKPipelineCache final : public VideoCommon::ShaderCache<Shader> {
class PipelineCache final : public VideoCommon::ShaderCache<Shader> {
public:
explicit VKPipelineCache(RasterizerVulkan& rasterizer, Tegra::GPU& gpu,
Tegra::Engines::Maxwell3D& maxwell3d,
Tegra::Engines::KeplerCompute& kepler_compute,
Tegra::MemoryManager& gpu_memory, const Device& device,
VKScheduler& scheduler, VKDescriptorPool& descriptor_pool,
VKUpdateDescriptorQueue& update_descriptor_queue);
~VKPipelineCache() override;
explicit PipelineCache(RasterizerVulkan& rasterizer, Tegra::GPU& gpu,
Tegra::Engines::Maxwell3D& maxwell3d,
Tegra::Engines::KeplerCompute& kepler_compute,
Tegra::MemoryManager& gpu_memory, const Device& device,
VKScheduler& scheduler, VKDescriptorPool& descriptor_pool,
VKUpdateDescriptorQueue& update_descriptor_queue);
~PipelineCache() override;
std::array<Shader*, Maxwell::MaxShaderProgram> GetShaders();
VKGraphicsPipeline* GetGraphicsPipeline(const GraphicsPipelineCacheKey& key,
u32 num_color_buffers,
VideoCommon::Shader::AsyncShaders& async_shaders);
VKComputePipeline& GetComputePipeline(const ComputePipelineCacheKey& key);
void EmplacePipeline(std::unique_ptr<VKGraphicsPipeline> pipeline);
ComputePipeline& GetComputePipeline(const ComputePipelineCacheKey& key);
protected:
void OnShaderRemoval(Shader* shader) final;
private:
std::pair<SPIRVProgram, std::vector<VkDescriptorSetLayoutBinding>> DecompileShaders(
const FixedPipelineState& fixed_state);
Tegra::GPU& gpu;
Tegra::Engines::Maxwell3D& maxwell3d;
Tegra::Engines::KeplerCompute& kepler_compute;
@ -158,17 +104,8 @@ private:
std::array<Shader*, Maxwell::MaxShaderProgram> last_shaders{};
GraphicsPipelineCacheKey last_graphics_key;
VKGraphicsPipeline* last_graphics_pipeline = nullptr;
std::mutex pipeline_cache;
std::unordered_map<GraphicsPipelineCacheKey, std::unique_ptr<VKGraphicsPipeline>>
graphics_cache;
std::unordered_map<ComputePipelineCacheKey, std::unique_ptr<VKComputePipeline>> compute_cache;
std::unordered_map<ComputePipelineCacheKey, std::unique_ptr<ComputePipeline>> compute_cache;
};
void FillDescriptorUpdateTemplateEntries(
const ShaderEntries& entries, u32& binding, u32& offset,
std::vector<VkDescriptorUpdateTemplateEntryKHR>& template_entries);
} // namespace Vulkan

361
src/video_core/renderer_vulkan/vk_rasterizer.cpp
View file

@ -24,7 +24,6 @@
#include "video_core/renderer_vulkan/vk_buffer_cache.h"
#include "video_core/renderer_vulkan/vk_compute_pipeline.h"
#include "video_core/renderer_vulkan/vk_descriptor_pool.h"
#include "video_core/renderer_vulkan/vk_graphics_pipeline.h"
#include "video_core/renderer_vulkan/vk_pipeline_cache.h"
#include "video_core/renderer_vulkan/vk_rasterizer.h"
#include "video_core/renderer_vulkan/vk_scheduler.h"
@ -97,15 +96,6 @@ VkRect2D GetScissorState(const Maxwell& regs, size_t index) {
return scissor;
}
std::array<GPUVAddr, Maxwell::MaxShaderProgram> GetShaderAddresses(
const std::array<Shader*, Maxwell::MaxShaderProgram>& shaders) {
std::array<GPUVAddr, Maxwell::MaxShaderProgram> addresses;
for (size_t i = 0; i < std::size(addresses); ++i) {
addresses[i] = shaders[i] ? shaders[i]->GetGpuAddr() : 0;
}
return addresses;
}
struct TextureHandle {
constexpr TextureHandle(u32 data, bool via_header_index) {
const Tegra::Texture::TextureHandle handle{data};
@ -117,98 +107,6 @@ struct TextureHandle {
u32 sampler;
};
template <typename Engine, typename Entry>
TextureHandle GetTextureInfo(const Engine& engine, bool via_header_index, const Entry& entry,
size_t stage, size_t index = 0) {
const auto shader_type = static_cast<Tegra::Engines::ShaderType>(stage);
if constexpr (std::is_same_v<Entry, SamplerEntry>) {
if (entry.is_separated) {
const u32 buffer_1 = entry.buffer;
const u32 buffer_2 = entry.secondary_buffer;
const u32 offset_1 = entry.offset;
const u32 offset_2 = entry.secondary_offset;
const u32 handle_1 = engine.AccessConstBuffer32(shader_type, buffer_1, offset_1);
const u32 handle_2 = engine.AccessConstBuffer32(shader_type, buffer_2, offset_2);
return TextureHandle(handle_1 | handle_2, via_header_index);
}
}
if (entry.is_bindless) {
const u32 raw = engine.AccessConstBuffer32(shader_type, entry.buffer, entry.offset);
return TextureHandle(raw, via_header_index);
}
const u32 buffer = engine.GetBoundBuffer();
const u64 offset = (entry.offset + index) * sizeof(u32);
return TextureHandle(engine.AccessConstBuffer32(shader_type, buffer, offset), via_header_index);
}
ImageViewType ImageViewTypeFromEntry(const SamplerEntry& entry) {
if (entry.is_buffer) {
return ImageViewType::e2D;
}
switch (entry.type) {
case Tegra::Shader::TextureType::Texture1D:
return entry.is_array ? ImageViewType::e1DArray : ImageViewType::e1D;
case Tegra::Shader::TextureType::Texture2D:
return entry.is_array ? ImageViewType::e2DArray : ImageViewType::e2D;
case Tegra::Shader::TextureType::Texture3D:
return ImageViewType::e3D;
case Tegra::Shader::TextureType::TextureCube:
return entry.is_array ? ImageViewType::CubeArray : ImageViewType::Cube;
}
UNREACHABLE();
return ImageViewType::e2D;
}
ImageViewType ImageViewTypeFromEntry(const ImageEntry& entry) {
switch (entry.type) {
case Tegra::Shader::ImageType::Texture1D:
return ImageViewType::e1D;
case Tegra::Shader::ImageType::Texture1DArray:
return ImageViewType::e1DArray;
case Tegra::Shader::ImageType::Texture2D:
return ImageViewType::e2D;
case Tegra::Shader::ImageType::Texture2DArray:
return ImageViewType::e2DArray;
case Tegra::Shader::ImageType::Texture3D:
return ImageViewType::e3D;
case Tegra::Shader::ImageType::TextureBuffer:
return ImageViewType::Buffer;
}
UNREACHABLE();
return ImageViewType::e2D;
}
void PushImageDescriptors(const ShaderEntries& entries, TextureCache& texture_cache,
VKUpdateDescriptorQueue& update_descriptor_queue,
ImageViewId*& image_view_id_ptr, VkSampler*& sampler_ptr) {
for ([[maybe_unused]] const auto& entry : entries.uniform_texels) {
const ImageViewId image_view_id = *image_view_id_ptr++;
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
update_descriptor_queue.AddTexelBuffer(image_view.BufferView());
}
for (const auto& entry : entries.samplers) {
for (size_t i = 0; i < entry.size; ++i) {
const VkSampler sampler = *sampler_ptr++;
const ImageViewId image_view_id = *image_view_id_ptr++;
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
const VkImageView handle = image_view.Handle(ImageViewTypeFromEntry(entry));
update_descriptor_queue.AddSampledImage(handle, sampler);
}
}
for ([[maybe_unused]] const auto& entry : entries.storage_texels) {
const ImageViewId image_view_id = *image_view_id_ptr++;
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
update_descriptor_queue.AddTexelBuffer(image_view.BufferView());
}
for (const auto& entry : entries.images) {
// TODO: Mark as modified
const ImageViewId image_view_id = *image_view_id_ptr++;
const ImageView& image_view = texture_cache.GetImageView(image_view_id);
const VkImageView handle = image_view.Handle(ImageViewTypeFromEntry(entry));
update_descriptor_queue.AddImage(handle);
}
}
DrawParams MakeDrawParams(const Maxwell& regs, u32 num_instances, bool is_instanced,
bool is_indexed) {
DrawParams params{
@ -253,71 +151,14 @@ RasterizerVulkan::RasterizerVulkan(Core::Frontend::EmuWindow& emu_window_, Tegra
descriptor_pool, update_descriptor_queue),
query_cache{*this, maxwell3d, gpu_memory, device, scheduler}, accelerate_dma{buffer_cache},
fence_manager(*this, gpu, texture_cache, buffer_cache, query_cache, device, scheduler),
wfi_event(device.GetLogical().CreateEvent()), async_shaders(emu_window_) {
wfi_event(device.GetLogical().CreateEvent()) {
scheduler.SetQueryCache(query_cache);
if (device.UseAsynchronousShaders()) {
async_shaders.AllocateWorkers();
}
}
RasterizerVulkan::~RasterizerVulkan() = default;
void RasterizerVulkan::Draw(bool is_indexed, bool is_instanced) {
MICROPROFILE_SCOPE(Vulkan_Drawing);
SCOPE_EXIT({ gpu.TickWork(); });
FlushWork();
query_cache.UpdateCounters();
graphics_key.fixed_state.Refresh(maxwell3d, device.IsExtExtendedDynamicStateSupported());
std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
texture_cache.SynchronizeGraphicsDescriptors();
texture_cache.UpdateRenderTargets(false);
const auto shaders = pipeline_cache.GetShaders();
graphics_key.shaders = GetShaderAddresses(shaders);
SetupShaderDescriptors(shaders, is_indexed);
const Framebuffer* const framebuffer = texture_cache.GetFramebuffer();
graphics_key.renderpass = framebuffer->RenderPass();
VKGraphicsPipeline* const pipeline = pipeline_cache.GetGraphicsPipeline(
graphics_key, framebuffer->NumColorBuffers(), async_shaders);
if (pipeline == nullptr || pipeline->GetHandle() == VK_NULL_HANDLE) {
// Async graphics pipeline was not ready.
return;
}
BeginTransformFeedback();
scheduler.RequestRenderpass(framebuffer);
scheduler.BindGraphicsPipeline(pipeline->GetHandle());
UpdateDynamicStates();
const auto& regs = maxwell3d.regs;
const u32 num_instances = maxwell3d.mme_draw.instance_count;
const DrawParams draw_params = MakeDrawParams(regs, num_instances, is_instanced, is_indexed);
const VkPipelineLayout pipeline_layout = pipeline->GetLayout();
const VkDescriptorSet descriptor_set = pipeline->CommitDescriptorSet();
scheduler.Record([pipeline_layout, descriptor_set, draw_params](vk::CommandBuffer cmdbuf) {
if (descriptor_set) {
cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_GRAPHICS, pipeline_layout,
DESCRIPTOR_SET, descriptor_set, nullptr);
}
if (draw_params.is_indexed) {
cmdbuf.DrawIndexed(draw_params.num_vertices, draw_params.num_instances, 0,
draw_params.base_vertex, draw_params.base_instance);
} else {
cmdbuf.Draw(draw_params.num_vertices, draw_params.num_instances,
draw_params.base_vertex, draw_params.base_instance);
}
});
EndTransformFeedback();
UNREACHABLE_MSG("Rendering not implemented {} {}", is_indexed, is_instanced);
}
void RasterizerVulkan::Clear() {
@ -395,73 +236,8 @@ void RasterizerVulkan::Clear() {
});
}
void RasterizerVulkan::DispatchCompute(GPUVAddr code_addr) {
MICROPROFILE_SCOPE(Vulkan_Compute);
query_cache.UpdateCounters();
const auto& launch_desc = kepler_compute.launch_description;
auto& pipeline = pipeline_cache.GetComputePipeline({
.shader = code_addr,
.shared_memory_size = launch_desc.shared_alloc,
.workgroup_size{
launch_desc.block_dim_x,
launch_desc.block_dim_y,
launch_desc.block_dim_z,
},
});
// Compute dispatches can't be executed inside a renderpass
scheduler.RequestOutsideRenderPassOperationContext();
image_view_indices.clear();
sampler_handles.clear();
std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
const auto& entries = pipeline.GetEntries();
buffer_cache.SetEnabledComputeUniformBuffers(entries.enabled_uniform_buffers);
buffer_cache.UnbindComputeStorageBuffers();
u32 ssbo_index = 0;
for (const auto& buffer : entries.global_buffers) {
buffer_cache.BindComputeStorageBuffer(ssbo_index, buffer.cbuf_index, buffer.cbuf_offset,
buffer.is_written);
++ssbo_index;
}
buffer_cache.UpdateComputeBuffers();
texture_cache.SynchronizeComputeDescriptors();
SetupComputeUniformTexels(entries);
SetupComputeTextures(entries);
SetupComputeStorageTexels(entries);
SetupComputeImages(entries);
const std::span indices_span(image_view_indices.data(), image_view_indices.size());
texture_cache.FillComputeImageViews(indices_span, image_view_ids);
update_descriptor_queue.Acquire();
buffer_cache.BindHostComputeBuffers();
ImageViewId* image_view_id_ptr = image_view_ids.data();
VkSampler* sampler_ptr = sampler_handles.data();
PushImageDescriptors(entries, texture_cache, update_descriptor_queue, image_view_id_ptr,
sampler_ptr);
const VkPipeline pipeline_handle = pipeline.GetHandle();
const VkPipelineLayout pipeline_layout = pipeline.GetLayout();
const VkDescriptorSet descriptor_set = pipeline.CommitDescriptorSet();
scheduler.Record([grid_x = launch_desc.grid_dim_x, grid_y = launch_desc.grid_dim_y,
grid_z = launch_desc.grid_dim_z, pipeline_handle, pipeline_layout,
descriptor_set](vk::CommandBuffer cmdbuf) {
cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, pipeline_handle);
if (descriptor_set) {
cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, pipeline_layout,
DESCRIPTOR_SET, descriptor_set, nullptr);
}
cmdbuf.Dispatch(grid_x, grid_y, grid_z);
});
void RasterizerVulkan::DispatchCompute() {
UNREACHABLE_MSG("Not implemented");
}
void RasterizerVulkan::ResetCounter(VideoCore::QueryType type) {
@ -716,52 +492,6 @@ bool AccelerateDMA::BufferCopy(GPUVAddr src_address, GPUVAddr dest_address, u64
return buffer_cache.DMACopy(src_address, dest_address, amount);
}
void RasterizerVulkan::SetupShaderDescriptors(
const std::array<Shader*, Maxwell::MaxShaderProgram>& shaders, bool is_indexed) {
image_view_indices.clear();
sampler_handles.clear();
for (size_t stage = 0; stage < Maxwell::MaxShaderStage; ++stage) {
Shader* const shader = shaders[stage + 1];
if (!shader) {
continue;
}
const ShaderEntries& entries = shader->GetEntries();
SetupGraphicsUniformTexels(entries, stage);
SetupGraphicsTextures(entries, stage);
SetupGraphicsStorageTexels(entries, stage);
SetupGraphicsImages(entries, stage);
buffer_cache.SetEnabledUniformBuffers(stage, entries.enabled_uniform_buffers);
buffer_cache.UnbindGraphicsStorageBuffers(stage);
u32 ssbo_index = 0;
for (const auto& buffer : entries.global_buffers) {
buffer_cache.BindGraphicsStorageBuffer(stage, ssbo_index, buffer.cbuf_index,
buffer.cbuf_offset, buffer.is_written);
++ssbo_index;
}
}
const std::span indices_span(image_view_indices.data(), image_view_indices.size());
buffer_cache.UpdateGraphicsBuffers(is_indexed);
texture_cache.FillGraphicsImageViews(indices_span, image_view_ids);
buffer_cache.BindHostGeometryBuffers(is_indexed);
update_descriptor_queue.Acquire();
ImageViewId* image_view_id_ptr = image_view_ids.data();
VkSampler* sampler_ptr = sampler_handles.data();
for (size_t stage = 0; stage < Maxwell::MaxShaderStage; ++stage) {
// Skip VertexA stage
Shader* const shader = shaders[stage + 1];
if (!shader) {
continue;
}
buffer_cache.BindHostStageBuffers(stage);
PushImageDescriptors(shader->GetEntries(), texture_cache, update_descriptor_queue,
image_view_id_ptr, sampler_ptr);
}
}
void RasterizerVulkan::UpdateDynamicStates() {
auto& regs = maxwell3d.regs;
UpdateViewportsState(regs);
@ -810,89 +540,6 @@ void RasterizerVulkan::EndTransformFeedback() {
[](vk::CommandBuffer cmdbuf) { cmdbuf.EndTransformFeedbackEXT(0, 0, nullptr, nullptr); });
}
void RasterizerVulkan::SetupGraphicsUniformTexels(const ShaderEntries& entries, size_t stage) {
const auto& regs = maxwell3d.regs;
const bool via_header_index = regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : entries.uniform_texels) {
const TextureHandle handle = GetTextureInfo(maxwell3d, via_header_index, entry, stage);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::SetupGraphicsTextures(const ShaderEntries& entries, size_t stage) {
const auto& regs = maxwell3d.regs;
const bool via_header_index = regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : entries.samplers) {
for (size_t index = 0; index < entry.size; ++index) {
const TextureHandle handle =
GetTextureInfo(maxwell3d, via_header_index, entry, stage, index);
image_view_indices.push_back(handle.image);
Sampler* const sampler = texture_cache.GetGraphicsSampler(handle.sampler);
sampler_handles.push_back(sampler->Handle());
}
}
}
void RasterizerVulkan::SetupGraphicsStorageTexels(const ShaderEntries& entries, size_t stage) {
const auto& regs = maxwell3d.regs;
const bool via_header_index = regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : entries.storage_texels) {
const TextureHandle handle = GetTextureInfo(maxwell3d, via_header_index, entry, stage);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::SetupGraphicsImages(const ShaderEntries& entries, size_t stage) {
const auto& regs = maxwell3d.regs;
const bool via_header_index = regs.sampler_index == Maxwell::SamplerIndex::ViaHeaderIndex;
for (const auto& entry : entries.images) {
const TextureHandle handle = GetTextureInfo(maxwell3d, via_header_index, entry, stage);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::SetupComputeUniformTexels(const ShaderEntries& entries) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : entries.uniform_texels) {
const TextureHandle handle =
GetTextureInfo(kepler_compute, via_header_index, entry, COMPUTE_SHADER_INDEX);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::SetupComputeTextures(const ShaderEntries& entries) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : entries.samplers) {
for (size_t index = 0; index < entry.size; ++index) {
const TextureHandle handle = GetTextureInfo(kepler_compute, via_header_index, entry,
COMPUTE_SHADER_INDEX, index);
image_view_indices.push_back(handle.image);
Sampler* const sampler = texture_cache.GetComputeSampler(handle.sampler);
sampler_handles.push_back(sampler->Handle());
}
}
}
void RasterizerVulkan::SetupComputeStorageTexels(const ShaderEntries& entries) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : entries.storage_texels) {
const TextureHandle handle =
GetTextureInfo(kepler_compute, via_header_index, entry, COMPUTE_SHADER_INDEX);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::SetupComputeImages(const ShaderEntries& entries) {
const bool via_header_index = kepler_compute.launch_description.linked_tsc;
for (const auto& entry : entries.images) {
const TextureHandle handle =
GetTextureInfo(kepler_compute, via_header_index, entry, COMPUTE_SHADER_INDEX);
image_view_indices.push_back(handle.image);
}
}
void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& regs) {
if (!state_tracker.TouchViewports()) {
return;

47
src/video_core/renderer_vulkan/vk_rasterizer.h
View file

@ -28,7 +28,6 @@
#include "video_core/renderer_vulkan/vk_staging_buffer_pool.h"
#include "video_core/renderer_vulkan/vk_texture_cache.h"
#include "video_core/renderer_vulkan/vk_update_descriptor.h"
#include "video_core/shader/async_shaders.h"
#include "video_core/vulkan_common/vulkan_memory_allocator.h"
#include "video_core/vulkan_common/vulkan_wrapper.h"
@ -73,7 +72,7 @@ public:
void Draw(bool is_indexed, bool is_instanced) override;
void Clear() override;
void DispatchCompute(GPUVAddr code_addr) override;
void DispatchCompute() override;
void ResetCounter(VideoCore::QueryType type) override;
void Query(GPUVAddr gpu_addr, VideoCore::QueryType type, std::optional<u64> timestamp) override;
void BindGraphicsUniformBuffer(size_t stage, u32 index, GPUVAddr gpu_addr, u32 size) override;
@ -103,19 +102,6 @@ public:
bool AccelerateDisplay(const Tegra::FramebufferConfig& config, VAddr framebuffer_addr,
u32 pixel_stride) override;
VideoCommon::Shader::AsyncShaders& GetAsyncShaders() {
return async_shaders;
}
const VideoCommon::Shader::AsyncShaders& GetAsyncShaders() const {
return async_shaders;
}
/// Maximum supported size that a constbuffer can have in bytes.
static constexpr size_t MaxConstbufferSize = 0x10000;
static_assert(MaxConstbufferSize % (4 * sizeof(float)) == 0,
"The maximum size of a constbuffer must be a multiple of the size of GLvec4");
private:
static constexpr size_t MAX_TEXTURES = 192;
static constexpr size_t MAX_IMAGES = 48;
@ -125,40 +111,12 @@ private:
void FlushWork();
/// Setup descriptors in the graphics pipeline.
void SetupShaderDescriptors(const std::array<Shader*, Maxwell::MaxShaderProgram>& shaders,
bool is_indexed);
void UpdateDynamicStates();
void BeginTransformFeedback();
void EndTransformFeedback();
/// Setup uniform texels in the graphics pipeline.
void SetupGraphicsUniformTexels(const ShaderEntries& entries, std::size_t stage);
/// Setup textures in the graphics pipeline.
void SetupGraphicsTextures(const ShaderEntries& entries, std::size_t stage);
/// Setup storage texels in the graphics pipeline.
void SetupGraphicsStorageTexels(const ShaderEntries& entries, std::size_t stage);
/// Setup images in the graphics pipeline.
void SetupGraphicsImages(const ShaderEntries& entries, std::size_t stage);
/// Setup texel buffers in the compute pipeline.
void SetupComputeUniformTexels(const ShaderEntries& entries);
/// Setup textures in the compute pipeline.
void SetupComputeTextures(const ShaderEntries& entries);
/// Setup storage texels in the compute pipeline.
void SetupComputeStorageTexels(const ShaderEntries& entries);
/// Setup images in the compute pipeline.
void SetupComputeImages(const ShaderEntries& entries);
void UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& regs);
void UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs);
void UpdateDepthBias(Tegra::Engines::Maxwell3D::Regs& regs);
@ -198,13 +156,12 @@ private:
TextureCache texture_cache;
BufferCacheRuntime buffer_cache_runtime;
BufferCache buffer_cache;
VKPipelineCache pipeline_cache;
PipelineCache pipeline_cache;
VKQueryCache query_cache;
AccelerateDMA accelerate_dma;
VKFenceManager fence_manager;
vk::Event wfi_event;
VideoCommon::Shader::AsyncShaders async_shaders;
boost::container::static_vector<u32, MAX_IMAGE_VIEWS> image_view_indices;
std::array<VideoCommon::ImageViewId, MAX_IMAGE_VIEWS> image_view_ids;

752
src/video_core/shader/ast.cpp
View file

@ -1,752 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <string>
#include <string_view>
#include <fmt/format.h>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/shader/ast.h"
#include "video_core/shader/expr.h"
namespace VideoCommon::Shader {
ASTZipper::ASTZipper() = default;
void ASTZipper::Init(const ASTNode new_first, const ASTNode parent) {
ASSERT(new_first->manager == nullptr);
first = new_first;
last = new_first;
ASTNode current = first;
while (current) {
current->manager = this;
current->parent = parent;
last = current;
current = current->next;
}
}
void ASTZipper::PushBack(const ASTNode new_node) {
ASSERT(new_node->manager == nullptr);
new_node->previous = last;
if (last) {
last->next = new_node;
}
new_node->next.reset();
last = new_node;
if (!first) {
first = new_node;
}
new_node->manager = this;
}
void ASTZipper::PushFront(const ASTNode new_node) {
ASSERT(new_node->manager == nullptr);
new_node->previous.reset();
new_node->next = first;
if (first) {
first->previous = new_node;
}
if (last == first) {
last = new_node;
}
first = new_node;
new_node->manager = this;
}
void ASTZipper::InsertAfter(const ASTNode new_node, const ASTNode at_node) {
ASSERT(new_node->manager == nullptr);
if (!at_node) {
PushFront(new_node);
return;
}
const ASTNode next = at_node->next;
if (next) {
next->previous = new_node;
}
new_node->previous = at_node;
if (at_node == last) {
last = new_node;
}
new_node->next = next;
at_node->next = new_node;
new_node->manager = this;
}
void ASTZipper::InsertBefore(const ASTNode new_node, const ASTNode at_node) {
ASSERT(new_node->manager == nullptr);
if (!at_node) {
PushBack(new_node);
return;
}
const ASTNode previous = at_node->previous;
if (previous) {
previous->next = new_node;
}
new_node->next = at_node;
if (at_node == first) {
first = new_node;
}
new_node->previous = previous;
at_node->previous = new_node;
new_node->manager = this;
}
void ASTZipper::DetachTail(ASTNode node) {
ASSERT(node->manager == this);
if (node == first) {
first.reset();
last.reset();
return;
}
last = node->previous;
last->next.reset();
node->previous.reset();
ASTNode current = std::move(node);
while (current) {
current->manager = nullptr;
current->parent.reset();
current = current->next;
}
}
void ASTZipper::DetachSegment(const ASTNode start, const ASTNode end) {
ASSERT(start->manager == this && end->manager == this);
if (start == end) {
DetachSingle(start);
return;
}
const ASTNode prev = start->previous;
const ASTNode post = end->next;
if (!prev) {
first = post;
} else {
prev->next = post;
}
if (!post) {
last = prev;
} else {
post->previous = prev;
}
start->previous.reset();
end->next.reset();
ASTNode current = start;
bool found = false;
while (current) {
current->manager = nullptr;
current->parent.reset();
found |= current == end;
current = current->next;
}
ASSERT(found);
}
void ASTZipper::DetachSingle(const ASTNode node) {
ASSERT(node->manager == this);
const ASTNode prev = node->previous;
const ASTNode post = node->next;
node->previous.reset();
node->next.reset();
if (!prev) {
first = post;
} else {
prev->next = post;
}
if (!post) {
last = prev;
} else {
post->previous = prev;
}
node->manager = nullptr;
node->parent.reset();
}
void ASTZipper::Remove(const ASTNode node) {
ASSERT(node->manager == this);
const ASTNode next = node->next;
const ASTNode previous = node->previous;
if (previous) {
previous->next = next;
}
if (next) {
next->previous = previous;
}
node->parent.reset();
node->manager = nullptr;
if (node == last) {
last = previous;
}
if (node == first) {
first = next;
}
}
class ExprPrinter final {
public:
void operator()(const ExprAnd& expr) {
inner += "( ";
std::visit(*this, *expr.operand1);
inner += " && ";
std::visit(*this, *expr.operand2);
inner += ')';
}
void operator()(const ExprOr& expr) {
inner += "( ";
std::visit(*this, *expr.operand1);
inner += " || ";
std::visit(*this, *expr.operand2);
inner += ')';
}
void operator()(const ExprNot& expr) {
inner += "!";
std::visit(*this, *expr.operand1);
}
void operator()(const ExprPredicate& expr) {
inner += fmt::format("P{}", expr.predicate);
}
void operator()(const ExprCondCode& expr) {
inner += fmt::format("CC{}", expr.cc);
}
void operator()(const ExprVar& expr) {
inner += fmt::format("V{}", expr.var_index);
}
void operator()(const ExprBoolean& expr) {
inner += expr.value ? "true" : "false";
}
void operator()(const ExprGprEqual& expr) {
inner += fmt::format("(gpr_{} == {})", expr.gpr, expr.value);
}
const std::string& GetResult() const {
return inner;
}
private:
std::string inner;
};
class ASTPrinter {
public:
void operator()(const ASTProgram& ast) {
scope++;
inner += "program {\n";
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
inner += "}\n";
scope--;
}
void operator()(const ASTIfThen& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner += fmt::format("{}if ({}) {{\n", Indent(), expr_parser.GetResult());
scope++;
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
scope--;
inner += fmt::format("{}}}\n", Indent());
}
void operator()(const ASTIfElse& ast) {
inner += Indent();
inner += "else {\n";
scope++;
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
scope--;
inner += Indent();
inner += "}\n";
}
void operator()(const ASTBlockEncoded& ast) {
inner += fmt::format("{}Block({}, {});\n", Indent(), ast.start, ast.end);
}
void operator()([[maybe_unused]] const ASTBlockDecoded& ast) {
inner += Indent();
inner += "Block;\n";
}
void operator()(const ASTVarSet& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner += fmt::format("{}V{} := {};\n", Indent(), ast.index, expr_parser.GetResult());
}
void operator()(const ASTLabel& ast) {
inner += fmt::format("Label_{}:\n", ast.index);
}
void operator()(const ASTGoto& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner +=
fmt::format("{}({}) -> goto Label_{};\n", Indent(), expr_parser.GetResult(), ast.label);
}
void operator()(const ASTDoWhile& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner += fmt::format("{}do {{\n", Indent());
scope++;
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
scope--;
inner += fmt::format("{}}} while ({});\n", Indent(), expr_parser.GetResult());
}
void operator()(const ASTReturn& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner += fmt::format("{}({}) -> {};\n", Indent(), expr_parser.GetResult(),
ast.kills ? "discard" : "exit");
}
void operator()(const ASTBreak& ast) {
ExprPrinter expr_parser{};
std::visit(expr_parser, *ast.condition);
inner += fmt::format("{}({}) -> break;\n", Indent(), expr_parser.GetResult());
}
void Visit(const ASTNode& node) {
std::visit(*this, *node->GetInnerData());
}
const std::string& GetResult() const {
return inner;
}
private:
std::string_view Indent() {
if (space_segment_scope == scope) {
return space_segment;
}
// Ensure that we don't exceed our view.
ASSERT(scope * 2 < spaces.size());
space_segment = spaces.substr(0, scope * 2);
space_segment_scope = scope;
return space_segment;
}
std::string inner{};
std::string_view space_segment;
u32 scope{};
u32 space_segment_scope{};
static constexpr std::string_view spaces{" "};
};
std::string ASTManager::Print() const {
ASTPrinter printer{};
printer.Visit(main_node);
return printer.GetResult();
}
ASTManager::ASTManager(bool do_full_decompile, bool disable_else_derivation_)
: full_decompile{do_full_decompile}, disable_else_derivation{disable_else_derivation_} {}
ASTManager::~ASTManager() {
Clear();
}
void ASTManager::Init() {
main_node = ASTBase::Make<ASTProgram>(ASTNode{});
program = std::get_if<ASTProgram>(main_node->GetInnerData());
false_condition = MakeExpr<ExprBoolean>(false);
}
void ASTManager::DeclareLabel(u32 address) {
const auto pair = labels_map.emplace(address, labels_count);
if (pair.second) {
labels_count++;
labels.resize(labels_count);
}
}
void ASTManager::InsertLabel(u32 address) {
const u32 index = labels_map[address];
const ASTNode label = ASTBase::Make<ASTLabel>(main_node, index);
labels[index] = label;
program->nodes.PushBack(label);
}
void ASTManager::InsertGoto(Expr condition, u32 address) {
const u32 index = labels_map[address];
const ASTNode goto_node = ASTBase::Make<ASTGoto>(main_node, std::move(condition), index);
gotos.push_back(goto_node);
program->nodes.PushBack(goto_node);
}
void ASTManager::InsertBlock(u32 start_address, u32 end_address) {
ASTNode block = ASTBase::Make<ASTBlockEncoded>(main_node, start_address, end_address);
program->nodes.PushBack(std::move(block));
}
void ASTManager::InsertReturn(Expr condition, bool kills) {
ASTNode node = ASTBase::Make<ASTReturn>(main_node, std::move(condition), kills);
program->nodes.PushBack(std::move(node));
}
// The decompile algorithm is based on
// "Taming control flow: A structured approach to eliminating goto statements"
// by AM Erosa, LJ Hendren 1994. In general, the idea is to get gotos to be
// on the same structured level as the label which they jump to. This is done,
// through outward/inward movements and lifting. Once they are at the same
// level, you can enclose them in an "if" structure or a "do-while" structure.
void ASTManager::Decompile() {
auto it = gotos.begin();
while (it != gotos.end()) {
const ASTNode goto_node = *it;
const auto label_index = goto_node->GetGotoLabel();
if (!label_index) {
return;
}
const ASTNode label = labels[*label_index];
if (!full_decompile) {
// We only decompile backward jumps
if (!IsBackwardsJump(goto_node, label)) {
it++;
continue;
}
}
if (IndirectlyRelated(goto_node, label)) {
while (!DirectlyRelated(goto_node, label)) {
MoveOutward(goto_node);
}
}
if (DirectlyRelated(goto_node, label)) {
u32 goto_level = goto_node->GetLevel();
const u32 label_level = label->GetLevel();
while (label_level < goto_level) {
MoveOutward(goto_node);
goto_level--;
}
// TODO(Blinkhawk): Implement Lifting and Inward Movements
}
if (label->GetParent() == goto_node->GetParent()) {
bool is_loop = false;
ASTNode current = goto_node->GetPrevious();
while (current) {
if (current == label) {
is_loop = true;
break;
}
current = current->GetPrevious();
}
if (is_loop) {
EncloseDoWhile(goto_node, label);
} else {
EncloseIfThen(goto_node, label);
}
it = gotos.erase(it);
continue;
}
it++;
}
if (full_decompile) {
for (const ASTNode& label : labels) {
auto& manager = label->GetManager();
manager.Remove(label);
}
labels.clear();
} else {
auto label_it = labels.begin();
while (label_it != labels.end()) {
bool can_remove = true;
ASTNode label = *label_it;
for (const ASTNode& goto_node : gotos) {
const auto label_index = goto_node->GetGotoLabel();
if (!label_index) {
return;
}
ASTNode& glabel = labels[*label_index];
if (glabel == label) {
can_remove = false;
break;
}
}
if (can_remove) {
label->MarkLabelUnused();
}
}
}
}
bool ASTManager::IsBackwardsJump(ASTNode goto_node, ASTNode label_node) const {
u32 goto_level = goto_node->GetLevel();
u32 label_level = label_node->GetLevel();
while (goto_level > label_level) {
goto_level--;
goto_node = goto_node->GetParent();
}
while (label_level > goto_level) {
label_level--;
label_node = label_node->GetParent();
}
while (goto_node->GetParent() != label_node->GetParent()) {
goto_node = goto_node->GetParent();
label_node = label_node->GetParent();
}
ASTNode current = goto_node->GetPrevious();
while (current) {
if (current == label_node) {
return true;
}
current = current->GetPrevious();
}
return false;
}
bool ASTManager::IndirectlyRelated(const ASTNode& first, const ASTNode& second) const {
return !(first->GetParent() == second->GetParent() || DirectlyRelated(first, second));
}
bool ASTManager::DirectlyRelated(const ASTNode& first, const ASTNode& second) const {
if (first->GetParent() == second->GetParent()) {
return false;
}
const u32 first_level = first->GetLevel();
const u32 second_level = second->GetLevel();
u32 min_level;
u32 max_level;
ASTNode max;
ASTNode min;
if (first_level > second_level) {
min_level = second_level;
min = second;
max_level = first_level;
max = first;
} else {
min_level = first_level;
min = first;
max_level = second_level;
max = second;
}
while (max_level > min_level) {
max_level--;
max = max->GetParent();
}
return min->GetParent() == max->GetParent();
}
void ASTManager::ShowCurrentState(std::string_view state) const {
LOG_CRITICAL(HW_GPU, "\nState {}:\n\n{}\n", state, Print());
SanityCheck();
}
void ASTManager::SanityCheck() const {
for (const auto& label : labels) {
if (!label->GetParent()) {
LOG_CRITICAL(HW_GPU, "Sanity Check Failed");
}
}
}
void ASTManager::EncloseDoWhile(ASTNode goto_node, ASTNode label) {
ASTZipper& zipper = goto_node->GetManager();
const ASTNode loop_start = label->GetNext();
if (loop_start == goto_node) {
zipper.Remove(goto_node);
return;
}
const ASTNode parent = label->GetParent();
const Expr condition = goto_node->GetGotoCondition();
zipper.DetachSegment(loop_start, goto_node);
const ASTNode do_while_node = ASTBase::Make<ASTDoWhile>(parent, condition);
ASTZipper* sub_zipper = do_while_node->GetSubNodes();
sub_zipper->Init(loop_start, do_while_node);
zipper.InsertAfter(do_while_node, label);
sub_zipper->Remove(goto_node);
}
void ASTManager::EncloseIfThen(ASTNode goto_node, ASTNode label) {
ASTZipper& zipper = goto_node->GetManager();
const ASTNode if_end = label->GetPrevious();
if (if_end == goto_node) {
zipper.Remove(goto_node);
return;
}
const ASTNode prev = goto_node->GetPrevious();
const Expr condition = goto_node->GetGotoCondition();
bool do_else = false;
if (!disable_else_derivation && prev->IsIfThen()) {
const Expr if_condition = prev->GetIfCondition();
do_else = ExprAreEqual(if_condition, condition);
}
const ASTNode parent = label->GetParent();
zipper.DetachSegment(goto_node, if_end);
ASTNode if_node;
if (do_else) {
if_node = ASTBase::Make<ASTIfElse>(parent);
} else {
Expr neg_condition = MakeExprNot(condition);
if_node = ASTBase::Make<ASTIfThen>(parent, neg_condition);
}
ASTZipper* sub_zipper = if_node->GetSubNodes();
sub_zipper->Init(goto_node, if_node);
zipper.InsertAfter(if_node, prev);
sub_zipper->Remove(goto_node);
}
void ASTManager::MoveOutward(ASTNode goto_node) {
ASTZipper& zipper = goto_node->GetManager();
const ASTNode parent = goto_node->GetParent();
ASTZipper& zipper2 = parent->GetManager();
const ASTNode grandpa = parent->GetParent();
const bool is_loop = parent->IsLoop();
const bool is_else = parent->IsIfElse();
const bool is_if = parent->IsIfThen();
const ASTNode prev = goto_node->GetPrevious();
const ASTNode post = goto_node->GetNext();
const Expr condition = goto_node->GetGotoCondition();
zipper.DetachSingle(goto_node);
if (is_loop) {
const u32 var_index = NewVariable();
const Expr var_condition = MakeExpr<ExprVar>(var_index);
const ASTNode var_node = ASTBase::Make<ASTVarSet>(parent, var_index, condition);
const ASTNode var_node_init = ASTBase::Make<ASTVarSet>(parent, var_index, false_condition);
zipper2.InsertBefore(var_node_init, parent);
zipper.InsertAfter(var_node, prev);
goto_node->SetGotoCondition(var_condition);
const ASTNode break_node = ASTBase::Make<ASTBreak>(parent, var_condition);
zipper.InsertAfter(break_node, var_node);
} else if (is_if || is_else) {
const u32 var_index = NewVariable();
const Expr var_condition = MakeExpr<ExprVar>(var_index);
const ASTNode var_node = ASTBase::Make<ASTVarSet>(parent, var_index, condition);
const ASTNode var_node_init = ASTBase::Make<ASTVarSet>(parent, var_index, false_condition);
if (is_if) {
zipper2.InsertBefore(var_node_init, parent);
} else {
zipper2.InsertBefore(var_node_init, parent->GetPrevious());
}
zipper.InsertAfter(var_node, prev);
goto_node->SetGotoCondition(var_condition);
if (post) {
zipper.DetachTail(post);
const ASTNode if_node = ASTBase::Make<ASTIfThen>(parent, MakeExprNot(var_condition));
ASTZipper* sub_zipper = if_node->GetSubNodes();
sub_zipper->Init(post, if_node);
zipper.InsertAfter(if_node, var_node);
}
} else {
UNREACHABLE();
}
const ASTNode next = parent->GetNext();
if (is_if && next && next->IsIfElse()) {
zipper2.InsertAfter(goto_node, next);
goto_node->SetParent(grandpa);
return;
}
zipper2.InsertAfter(goto_node, parent);
goto_node->SetParent(grandpa);
}
class ASTClearer {
public:
ASTClearer() = default;
void operator()(const ASTProgram& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(const ASTIfThen& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(const ASTIfElse& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()([[maybe_unused]] const ASTBlockEncoded& ast) {}
void operator()(ASTBlockDecoded& ast) {
ast.nodes.clear();
}
void operator()([[maybe_unused]] const ASTVarSet& ast) {}
void operator()([[maybe_unused]] const ASTLabel& ast) {}
void operator()([[maybe_unused]] const ASTGoto& ast) {}
void operator()(const ASTDoWhile& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()([[maybe_unused]] const ASTReturn& ast) {}
void operator()([[maybe_unused]] const ASTBreak& ast) {}
void Visit(const ASTNode& node) {
std::visit(*this, *node->GetInnerData());
node->Clear();
}
};
void ASTManager::Clear() {
if (!main_node) {
return;
}
ASTClearer clearer{};
clearer.Visit(main_node);
main_node.reset();
program = nullptr;
labels_map.clear();
labels.clear();
gotos.clear();
}
} // namespace VideoCommon::Shader

398
src/video_core/shader/ast.h
View file

@ -1,398 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <functional>
#include <list>
#include <memory>
#include <optional>
#include <string>
#include <unordered_map>
#include <vector>
#include "video_core/shader/expr.h"
#include "video_core/shader/node.h"
namespace VideoCommon::Shader {
class ASTBase;
class ASTBlockDecoded;
class ASTBlockEncoded;
class ASTBreak;
class ASTDoWhile;
class ASTGoto;
class ASTIfElse;
class ASTIfThen;
class ASTLabel;
class ASTProgram;
class ASTReturn;
class ASTVarSet;
using ASTData = std::variant<ASTProgram, ASTIfThen, ASTIfElse, ASTBlockEncoded, ASTBlockDecoded,
ASTVarSet, ASTGoto, ASTLabel, ASTDoWhile, ASTReturn, ASTBreak>;
using ASTNode = std::shared_ptr<ASTBase>;
enum class ASTZipperType : u32 {
Program,
IfThen,
IfElse,
Loop,
};
class ASTZipper final {
public:
explicit ASTZipper();
void Init(ASTNode first, ASTNode parent);
ASTNode GetFirst() const {
return first;
}
ASTNode GetLast() const {
return last;
}
void PushBack(ASTNode new_node);
void PushFront(ASTNode new_node);
void InsertAfter(ASTNode new_node, ASTNode at_node);
void InsertBefore(ASTNode new_node, ASTNode at_node);
void DetachTail(ASTNode node);
void DetachSingle(ASTNode node);
void DetachSegment(ASTNode start, ASTNode end);
void Remove(ASTNode node);
ASTNode first;
ASTNode last;
};
class ASTProgram {
public:
ASTZipper nodes{};
};
class ASTIfThen {
public:
explicit ASTIfThen(Expr condition_) : condition{std::move(condition_)} {}
Expr condition;
ASTZipper nodes{};
};
class ASTIfElse {
public:
ASTZipper nodes{};
};
class ASTBlockEncoded {
public:
explicit ASTBlockEncoded(u32 start_, u32 _) : start{start_}, end{_} {}
u32 start;
u32 end;
};
class ASTBlockDecoded {
public:
explicit ASTBlockDecoded(NodeBlock&& new_nodes_) : nodes(std::move(new_nodes_)) {}
NodeBlock nodes;
};
class ASTVarSet {
public:
explicit ASTVarSet(u32 index_, Expr condition_)
: index{index_}, condition{std::move(condition_)} {}
u32 index;
Expr condition;
};
class ASTLabel {
public:
explicit ASTLabel(u32 index_) : index{index_} {}
u32 index;
bool unused{};
};
class ASTGoto {
public:
explicit ASTGoto(Expr condition_, u32 label_)
: condition{std::move(condition_)}, label{label_} {}
Expr condition;
u32 label;
};
class ASTDoWhile {
public:
explicit ASTDoWhile(Expr condition_) : condition{std::move(condition_)} {}
Expr condition;
ASTZipper nodes{};
};
class ASTReturn {
public:
explicit ASTReturn(Expr condition_, bool kills_)
: condition{std::move(condition_)}, kills{kills_} {}
Expr condition;
bool kills;
};
class ASTBreak {
public:
explicit ASTBreak(Expr condition_) : condition{std::move(condition_)} {}
Expr condition;
};
class ASTBase {
public:
explicit ASTBase(ASTNode parent_, ASTData data_)
: data{std::move(data_)}, parent{std::move(parent_)} {}
template <class U, class... Args>
static ASTNode Make(ASTNode parent, Args&&... args) {
return std::make_shared<ASTBase>(std::move(parent),
ASTData(U(std::forward<Args>(args)...)));
}
void SetParent(ASTNode new_parent) {
parent = std::move(new_parent);
}
ASTNode& GetParent() {
return parent;
}
const ASTNode& GetParent() const {
return parent;
}
u32 GetLevel() const {
u32 level = 0;
auto next_parent = parent;
while (next_parent) {
next_parent = next_parent->GetParent();
level++;
}
return level;
}
ASTData* GetInnerData() {
return &data;
}
const ASTData* GetInnerData() const {
return &data;
}
ASTNode GetNext() const {
return next;
}
ASTNode GetPrevious() const {
return previous;
}
ASTZipper& GetManager() {
return *manager;
}
const ASTZipper& GetManager() const {
return *manager;
}
std::optional<u32> GetGotoLabel() const {
if (const auto* inner = std::get_if<ASTGoto>(&data)) {
return {inner->label};
}
return std::nullopt;
}
Expr GetGotoCondition() const {
if (const auto* inner = std::get_if<ASTGoto>(&data)) {
return inner->condition;
}
return nullptr;
}
void MarkLabelUnused() {
if (auto* inner = std::get_if<ASTLabel>(&data)) {
inner->unused = true;
}
}
bool IsLabelUnused() const {
if (const auto* inner = std::get_if<ASTLabel>(&data)) {
return inner->unused;
}
return true;
}
std::optional<u32> GetLabelIndex() const {
if (const auto* inner = std::get_if<ASTLabel>(&data)) {
return {inner->index};
}
return std::nullopt;
}
Expr GetIfCondition() const {
if (const auto* inner = std::get_if<ASTIfThen>(&data)) {
return inner->condition;
}
return nullptr;
}
void SetGotoCondition(Expr new_condition) {
if (auto* inner = std::get_if<ASTGoto>(&data)) {
inner->condition = std::move(new_condition);
}
}
bool IsIfThen() const {
return std::holds_alternative<ASTIfThen>(data);
}
bool IsIfElse() const {
return std::holds_alternative<ASTIfElse>(data);
}
bool IsBlockEncoded() const {
return std::holds_alternative<ASTBlockEncoded>(data);
}
void TransformBlockEncoded(NodeBlock&& nodes) {
data = ASTBlockDecoded(std::move(nodes));
}
bool IsLoop() const {
return std::holds_alternative<ASTDoWhile>(data);
}
ASTZipper* GetSubNodes() {
if (std::holds_alternative<ASTProgram>(data)) {
return &std::get_if<ASTProgram>(&data)->nodes;
}
if (std::holds_alternative<ASTIfThen>(data)) {
return &std::get_if<ASTIfThen>(&data)->nodes;
}
if (std::holds_alternative<ASTIfElse>(data)) {
return &std::get_if<ASTIfElse>(&data)->nodes;
}
if (std::holds_alternative<ASTDoWhile>(data)) {
return &std::get_if<ASTDoWhile>(&data)->nodes;
}
return nullptr;
}
void Clear() {
next.reset();
previous.reset();
parent.reset();
manager = nullptr;
}
private:
friend class ASTZipper;
ASTData data;
ASTNode parent;
ASTNode next;
ASTNode previous;
ASTZipper* manager{};
};
class ASTManager final {
public:
explicit ASTManager(bool do_full_decompile, bool disable_else_derivation_);
~ASTManager();
ASTManager(const ASTManager& o) = delete;
ASTManager& operator=(const ASTManager& other) = delete;
ASTManager(ASTManager&& other) noexcept = default;
ASTManager& operator=(ASTManager&& other) noexcept = default;
void Init();
void DeclareLabel(u32 address);
void InsertLabel(u32 address);
void InsertGoto(Expr condition, u32 address);
void InsertBlock(u32 start_address, u32 end_address);
void InsertReturn(Expr condition, bool kills);
std::string Print() const;
void Decompile();
void ShowCurrentState(std::string_view state) const;
void SanityCheck() const;
void Clear();
bool IsFullyDecompiled() const {
if (full_decompile) {
return gotos.empty();
}
for (ASTNode goto_node : gotos) {
auto label_index = goto_node->GetGotoLabel();
if (!label_index) {
return false;
}
ASTNode glabel = labels[*label_index];
if (IsBackwardsJump(goto_node, glabel)) {
return false;
}
}
return true;
}
ASTNode GetProgram() const {
return main_node;
}
u32 GetVariables() const {
return variables;
}
const std::vector<ASTNode>& GetLabels() const {
return labels;
}
private:
bool IsBackwardsJump(ASTNode goto_node, ASTNode label_node) const;
bool IndirectlyRelated(const ASTNode& first, const ASTNode& second) const;
bool DirectlyRelated(const ASTNode& first, const ASTNode& second) const;
void EncloseDoWhile(ASTNode goto_node, ASTNode label);
void EncloseIfThen(ASTNode goto_node, ASTNode label);
void MoveOutward(ASTNode goto_node);
u32 NewVariable() {
return variables++;
}
bool full_decompile{};
bool disable_else_derivation{};
std::unordered_map<u32, u32> labels_map{};
u32 labels_count{};
std::vector<ASTNode> labels{};
std::list<ASTNode> gotos{};
u32 variables{};
ASTProgram* program{};
ASTNode main_node{};
Expr false_condition{};
};
} // namespace VideoCommon::Shader

234
src/video_core/shader/async_shaders.cpp
View file

@ -1,234 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <condition_variable>
#include <mutex>
#include <thread>
#include <vector>
#include "video_core/engines/maxwell_3d.h"
#include "video_core/renderer_base.h"
#include "video_core/renderer_opengl/gl_shader_cache.h"
#include "video_core/shader/async_shaders.h"
namespace VideoCommon::Shader {
AsyncShaders::AsyncShaders(Core::Frontend::EmuWindow& emu_window_) : emu_window(emu_window_) {}
AsyncShaders::~AsyncShaders() {
KillWorkers();
}
void AsyncShaders::AllocateWorkers() {
// Use at least one thread
u32 num_workers = 1;
// Deduce how many more threads we can use
const u32 thread_count = std::thread::hardware_concurrency();
if (thread_count >= 8) {
// Increase async workers by 1 for every 2 threads >= 8
num_workers += 1 + (thread_count - 8) / 2;
}
// If we already have workers queued, ignore
if (num_workers == worker_threads.size()) {
return;
}
// If workers already exist, clear them
if (!worker_threads.empty()) {
FreeWorkers();
}
// Create workers
for (std::size_t i = 0; i < num_workers; i++) {
context_list.push_back(emu_window.CreateSharedContext());
worker_threads.emplace_back(&AsyncShaders::ShaderCompilerThread, this,
context_list[i].get());
}
}
void AsyncShaders::FreeWorkers() {
// Mark all threads to quit
is_thread_exiting.store(true);
cv.notify_all();
for (auto& thread : worker_threads) {
thread.join();
}
// Clear our shared contexts
context_list.clear();
// Clear our worker threads
worker_threads.clear();
}
void AsyncShaders::KillWorkers() {
is_thread_exiting.store(true);
cv.notify_all();
for (auto& thread : worker_threads) {
thread.detach();
}
// Clear our shared contexts
context_list.clear();
// Clear our worker threads
worker_threads.clear();
}
bool AsyncShaders::HasWorkQueued() const {
return !pending_queue.empty();
}
bool AsyncShaders::HasCompletedWork() const {
std::shared_lock lock{completed_mutex};
return !finished_work.empty();
}
bool AsyncShaders::IsShaderAsync(const Tegra::GPU& gpu) const {
const auto& regs = gpu.Maxwell3D().regs;
// If something is using depth, we can assume that games are not rendering anything which will
// be used one time.
if (regs.zeta_enable) {
return true;
}
// If games are using a small index count, we can assume these are full screen quads. Usually
// these shaders are only used once for building textures so we can assume they can't be built
// async
if (regs.index_array.count <= 6 || regs.vertex_buffer.count <= 6) {
return false;
}
return true;
}
std::vector<AsyncShaders::Result> AsyncShaders::GetCompletedWork() {
std::vector<Result> results;
{
std::unique_lock lock{completed_mutex};
results = std::move(finished_work);
finished_work.clear();
}
return results;
}
void AsyncShaders::QueueOpenGLShader(const OpenGL::Device& device,
Tegra::Engines::ShaderType shader_type, u64 uid,
std::vector<u64> code, std::vector<u64> code_b,
u32 main_offset, CompilerSettings compiler_settings,
const Registry& registry, VAddr cpu_addr) {
std::unique_lock lock(queue_mutex);
pending_queue.push({
.backend = device.UseAssemblyShaders() ? Backend::GLASM : Backend::OpenGL,
.device = &device,
.shader_type = shader_type,
.uid = uid,
.code = std::move(code),
.code_b = std::move(code_b),
.main_offset = main_offset,
.compiler_settings = compiler_settings,
.registry = registry,
.cpu_address = cpu_addr,
.pp_cache = nullptr,
.vk_device = nullptr,
.scheduler = nullptr,
.descriptor_pool = nullptr,
.update_descriptor_queue = nullptr,
.bindings{},
.program{},
.key{},
.num_color_buffers = 0,
});
cv.notify_one();
}
void AsyncShaders::QueueVulkanShader(Vulkan::VKPipelineCache* pp_cache,
const Vulkan::Device& device, Vulkan::VKScheduler& scheduler,
Vulkan::VKDescriptorPool& descriptor_pool,
Vulkan::VKUpdateDescriptorQueue& update_descriptor_queue,
std::vector<VkDescriptorSetLayoutBinding> bindings,
Vulkan::SPIRVProgram program,
Vulkan::GraphicsPipelineCacheKey key, u32 num_color_buffers) {
std::unique_lock lock(queue_mutex);
pending_queue.push({
.backend = Backend::Vulkan,
.device = nullptr,
.shader_type{},
.uid = 0,
.code{},
.code_b{},
.main_offset = 0,
.compiler_settings{},
.registry{},
.cpu_address = 0,
.pp_cache = pp_cache,
.vk_device = &device,
.scheduler = &scheduler,
.descriptor_pool = &descriptor_pool,
.update_descriptor_queue = &update_descriptor_queue,
.bindings = std::move(bindings),
.program = std::move(program),
.key = key,
.num_color_buffers = num_color_buffers,
});
cv.notify_one();
}
void AsyncShaders::ShaderCompilerThread(Core::Frontend::GraphicsContext* context) {
while (!is_thread_exiting.load(std::memory_order_relaxed)) {
std::unique_lock lock{queue_mutex};
cv.wait(lock, [this] { return HasWorkQueued() || is_thread_exiting; });
if (is_thread_exiting) {
return;
}
// Partial lock to allow all threads to read at the same time
if (!HasWorkQueued()) {
continue;
}
// Another thread beat us, just unlock and wait for the next load
if (pending_queue.empty()) {
continue;
}
// Pull work from queue
WorkerParams work = std::move(pending_queue.front());
pending_queue.pop();
lock.unlock();
if (work.backend == Backend::OpenGL || work.backend == Backend::GLASM) {
const ShaderIR ir(work.code, work.main_offset, work.compiler_settings, *work.registry);
const auto scope = context->Acquire();
auto program =
OpenGL::BuildShader(*work.device, work.shader_type, work.uid, ir, *work.registry);
Result result{};
result.backend = work.backend;
result.cpu_address = work.cpu_address;
result.uid = work.uid;
result.code = std::move(work.code);
result.code_b = std::move(work.code_b);
result.shader_type = work.shader_type;
if (work.backend == Backend::OpenGL) {
result.program.opengl = std::move(program->source_program);
} else if (work.backend == Backend::GLASM) {
result.program.glasm = std::move(program->assembly_program);
}
{
std::unique_lock complete_lock(completed_mutex);
finished_work.push_back(std::move(result));
}
} else if (work.backend == Backend::Vulkan) {
auto pipeline = std::make_unique<Vulkan::VKGraphicsPipeline>(
*work.vk_device, *work.scheduler, *work.descriptor_pool,
*work.update_descriptor_queue, work.key, work.bindings, work.program,
work.num_color_buffers);
work.pp_cache->EmplacePipeline(std::move(pipeline));
}
}
}
} // namespace VideoCommon::Shader

138
src/video_core/shader/async_shaders.h
View file

@ -1,138 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <condition_variable>
#include <memory>
#include <shared_mutex>
#include <thread>
#include <glad/glad.h>
#include "common/common_types.h"
#include "video_core/renderer_opengl/gl_device.h"
#include "video_core/renderer_opengl/gl_resource_manager.h"
#include "video_core/renderer_opengl/gl_shader_decompiler.h"
#include "video_core/renderer_vulkan/vk_pipeline_cache.h"
#include "video_core/renderer_vulkan/vk_scheduler.h"
#include "video_core/vulkan_common/vulkan_device.h"
namespace Core::Frontend {
class EmuWindow;
class GraphicsContext;
} // namespace Core::Frontend
namespace Tegra {
class GPU;
}
namespace Vulkan {
class VKPipelineCache;
}
namespace VideoCommon::Shader {
class AsyncShaders {
public:
enum class Backend {
OpenGL,
GLASM,
Vulkan,
};
struct ResultPrograms {
OpenGL::OGLProgram opengl;
OpenGL::OGLAssemblyProgram glasm;
};
struct Result {
u64 uid;
VAddr cpu_address;
Backend backend;
ResultPrograms program;
std::vector<u64> code;
std::vector<u64> code_b;
Tegra::Engines::ShaderType shader_type;
};
explicit AsyncShaders(Core::Frontend::EmuWindow& emu_window_);
~AsyncShaders();
/// Start up shader worker threads
void AllocateWorkers();
/// Clear the shader queue and kill all worker threads
void FreeWorkers();
// Force end all threads
void KillWorkers();
/// Check to see if any shaders have actually been compiled
[[nodiscard]] bool HasCompletedWork() const;
/// Deduce if a shader can be build on another thread of MUST be built in sync. We cannot build
/// every shader async as some shaders are only built and executed once. We try to "guess" which
/// shader would be used only once
[[nodiscard]] bool IsShaderAsync(const Tegra::GPU& gpu) const;
/// Pulls completed compiled shaders
[[nodiscard]] std::vector<Result> GetCompletedWork();
void QueueOpenGLShader(const OpenGL::Device& device, Tegra::Engines::ShaderType shader_type,
u64 uid, std::vector<u64> code, std::vector<u64> code_b, u32 main_offset,
CompilerSettings compiler_settings, const Registry& registry,
VAddr cpu_addr);
void QueueVulkanShader(Vulkan::VKPipelineCache* pp_cache, const Vulkan::Device& device,
Vulkan::VKScheduler& scheduler,
Vulkan::VKDescriptorPool& descriptor_pool,
Vulkan::VKUpdateDescriptorQueue& update_descriptor_queue,
std::vector<VkDescriptorSetLayoutBinding> bindings,
Vulkan::SPIRVProgram program, Vulkan::GraphicsPipelineCacheKey key,
u32 num_color_buffers);
private:
void ShaderCompilerThread(Core::Frontend::GraphicsContext* context);
/// Check our worker queue to see if we have any work queued already
[[nodiscard]] bool HasWorkQueued() const;
struct WorkerParams {
Backend backend;
// For OGL
const OpenGL::Device* device;
Tegra::Engines::ShaderType shader_type;
u64 uid;
std::vector<u64> code;
std::vector<u64> code_b;
u32 main_offset;
CompilerSettings compiler_settings;
std::optional<Registry> registry;
VAddr cpu_address;
// For Vulkan
Vulkan::VKPipelineCache* pp_cache;
const Vulkan::Device* vk_device;
Vulkan::VKScheduler* scheduler;
Vulkan::VKDescriptorPool* descriptor_pool;
Vulkan::VKUpdateDescriptorQueue* update_descriptor_queue;
std::vector<VkDescriptorSetLayoutBinding> bindings;
Vulkan::SPIRVProgram program;
Vulkan::GraphicsPipelineCacheKey key;
u32 num_color_buffers;
};
std::condition_variable cv;
mutable std::mutex queue_mutex;
mutable std::shared_mutex completed_mutex;
std::atomic<bool> is_thread_exiting{};
std::vector<std::unique_ptr<Core::Frontend::GraphicsContext>> context_list;
std::vector<std::thread> worker_threads;
std::queue<WorkerParams> pending_queue;
std::vector<Result> finished_work;
Core::Frontend::EmuWindow& emu_window;
};
} // namespace VideoCommon::Shader

26
src/video_core/shader/compiler_settings.cpp
View file

@ -1,26 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "video_core/shader/compiler_settings.h"
namespace VideoCommon::Shader {
std::string CompileDepthAsString(const CompileDepth cd) {
switch (cd) {
case CompileDepth::BruteForce:
return "Brute Force Compile";
case CompileDepth::FlowStack:
return "Simple Flow Stack Mode";
case CompileDepth::NoFlowStack:
return "Remove Flow Stack";
case CompileDepth::DecompileBackwards:
return "Decompile Backward Jumps";
case CompileDepth::FullDecompile:
return "Full Decompilation";
default:
return "Unknown Compiler Process";
}
}
} // namespace VideoCommon::Shader

26
src/video_core/shader/compiler_settings.h
View file

@ -1,26 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include "video_core/engines/shader_bytecode.h"
namespace VideoCommon::Shader {
enum class CompileDepth : u32 {
BruteForce = 0,
FlowStack = 1,
NoFlowStack = 2,
DecompileBackwards = 3,
FullDecompile = 4,
};
std::string CompileDepthAsString(CompileDepth cd);
struct CompilerSettings {
CompileDepth depth{CompileDepth::NoFlowStack};
bool disable_else_derivation{true};
};
} // namespace VideoCommon::Shader

751
src/video_core/shader/control_flow.cpp
View file

@ -1,751 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <list>
#include <map>
#include <set>
#include <stack>
#include <unordered_map>
#include <vector>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/shader/ast.h"
#include "video_core/shader/control_flow.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
namespace {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
constexpr s32 unassigned_branch = -2;
struct Query {
u32 address{};
std::stack<u32> ssy_stack{};
std::stack<u32> pbk_stack{};
};
struct BlockStack {
BlockStack() = default;
explicit BlockStack(const Query& q) : ssy_stack{q.ssy_stack}, pbk_stack{q.pbk_stack} {}
std::stack<u32> ssy_stack{};
std::stack<u32> pbk_stack{};
};
template <typename T, typename... Args>
BlockBranchInfo MakeBranchInfo(Args&&... args) {
static_assert(std::is_convertible_v<T, BranchData>);
return std::make_shared<BranchData>(T(std::forward<Args>(args)...));
}
bool BlockBranchIsIgnored(BlockBranchInfo first) {
bool ignore = false;
if (std::holds_alternative<SingleBranch>(*first)) {
const auto branch = std::get_if<SingleBranch>(first.get());
ignore = branch->ignore;
}
return ignore;
}
struct BlockInfo {
u32 start{};
u32 end{};
bool visited{};
BlockBranchInfo branch{};
bool IsInside(const u32 address) const {
return start <= address && address <= end;
}
};
struct CFGRebuildState {
explicit CFGRebuildState(const ProgramCode& program_code_, u32 start_, Registry& registry_)
: program_code{program_code_}, registry{registry_}, start{start_} {}
const ProgramCode& program_code;
Registry& registry;
u32 start{};
std::vector<BlockInfo> block_info;
std::list<u32> inspect_queries;
std::list<Query> queries;
std::unordered_map<u32, u32> registered;
std::set<u32> labels;
std::map<u32, u32> ssy_labels;
std::map<u32, u32> pbk_labels;
std::unordered_map<u32, BlockStack> stacks;
ASTManager* manager{};
};
enum class BlockCollision : u32 { None, Found, Inside };
std::pair<BlockCollision, u32> TryGetBlock(CFGRebuildState& state, u32 address) {
const auto& blocks = state.block_info;
for (u32 index = 0; index < blocks.size(); index++) {
if (blocks[index].start == address) {
return {BlockCollision::Found, index};
}
if (blocks[index].IsInside(address)) {
return {BlockCollision::Inside, index};
}
}
return {BlockCollision::None, 0xFFFFFFFF};
}
struct ParseInfo {
BlockBranchInfo branch_info{};
u32 end_address{};
};
BlockInfo& CreateBlockInfo(CFGRebuildState& state, u32 start, u32 end) {
auto& it = state.block_info.emplace_back();
it.start = start;
it.end = end;
const u32 index = static_cast<u32>(state.block_info.size() - 1);
state.registered.insert({start, index});
return it;
}
Pred GetPredicate(u32 index, bool negated) {
return static_cast<Pred>(static_cast<u64>(index) + (negated ? 8ULL : 0ULL));
}
enum class ParseResult : u32 {
ControlCaught,
BlockEnd,
AbnormalFlow,
};
struct BranchIndirectInfo {
u32 buffer{};
u32 offset{};
u32 entries{};
s32 relative_position{};
};
struct BufferInfo {
u32 index;
u32 offset;
};
std::optional<std::pair<s32, u64>> GetBRXInfo(const CFGRebuildState& state, u32& pos) {
const Instruction instr = state.program_code[pos];
const auto opcode = OpCode::Decode(instr);
if (opcode->get().GetId() != OpCode::Id::BRX) {
return std::nullopt;
}
if (instr.brx.constant_buffer != 0) {
return std::nullopt;
}
--pos;
return std::make_pair(instr.brx.GetBranchExtend(), instr.gpr8.Value());
}
template <typename Result, typename TestCallable, typename PackCallable>
// requires std::predicate<TestCallable, Instruction, const OpCode::Matcher&>
// requires std::invocable<PackCallable, Instruction, const OpCode::Matcher&>
std::optional<Result> TrackInstruction(const CFGRebuildState& state, u32& pos, TestCallable test,
PackCallable pack) {
for (; pos >= state.start; --pos) {
if (IsSchedInstruction(pos, state.start)) {
continue;
}
const Instruction instr = state.program_code[pos];
const auto opcode = OpCode::Decode(instr);
if (!opcode) {
continue;
}
if (test(instr, opcode->get())) {
--pos;
return std::make_optional(pack(instr, opcode->get()));
}
}
return std::nullopt;
}
std::optional<std::pair<BufferInfo, u64>> TrackLDC(const CFGRebuildState& state, u32& pos,
u64 brx_tracked_register) {
return TrackInstruction<std::pair<BufferInfo, u64>>(
state, pos,
[brx_tracked_register](auto instr, const auto& opcode) {
return opcode.GetId() == OpCode::Id::LD_C &&
instr.gpr0.Value() == brx_tracked_register &&
instr.ld_c.type.Value() == Tegra::Shader::UniformType::Single;
},
[](auto instr, const auto& opcode) {
const BufferInfo info = {static_cast<u32>(instr.cbuf36.index.Value()),
static_cast<u32>(instr.cbuf36.GetOffset())};
return std::make_pair(info, instr.gpr8.Value());
});
}
std::optional<u64> TrackSHLRegister(const CFGRebuildState& state, u32& pos,
u64 ldc_tracked_register) {
return TrackInstruction<u64>(
state, pos,
[ldc_tracked_register](auto instr, const auto& opcode) {
return opcode.GetId() == OpCode::Id::SHL_IMM &&
instr.gpr0.Value() == ldc_tracked_register;
},
[](auto instr, const auto&) { return instr.gpr8.Value(); });
}
std::optional<u32> TrackIMNMXValue(const CFGRebuildState& state, u32& pos,
u64 shl_tracked_register) {
return TrackInstruction<u32>(
state, pos,
[shl_tracked_register](auto instr, const auto& opcode) {
return opcode.GetId() == OpCode::Id::IMNMX_IMM &&
instr.gpr0.Value() == shl_tracked_register;
},
[](auto instr, const auto&) {
return static_cast<u32>(instr.alu.GetSignedImm20_20() + 1);
});
}
std::optional<BranchIndirectInfo> TrackBranchIndirectInfo(const CFGRebuildState& state, u32 pos) {
const auto brx_info = GetBRXInfo(state, pos);
if (!brx_info) {
return std::nullopt;
}
const auto [relative_position, brx_tracked_register] = *brx_info;
const auto ldc_info = TrackLDC(state, pos, brx_tracked_register);
if (!ldc_info) {
return std::nullopt;
}
const auto [buffer_info, ldc_tracked_register] = *ldc_info;
const auto shl_tracked_register = TrackSHLRegister(state, pos, ldc_tracked_register);
if (!shl_tracked_register) {
return std::nullopt;
}
const auto entries = TrackIMNMXValue(state, pos, *shl_tracked_register);
if (!entries) {
return std::nullopt;
}
return BranchIndirectInfo{buffer_info.index, buffer_info.offset, *entries, relative_position};
}
std::pair<ParseResult, ParseInfo> ParseCode(CFGRebuildState& state, u32 address) {
u32 offset = static_cast<u32>(address);
const u32 end_address = static_cast<u32>(state.program_code.size());
ParseInfo parse_info{};
SingleBranch single_branch{};
const auto insert_label = [](CFGRebuildState& rebuild_state, u32 label_address) {
const auto pair = rebuild_state.labels.emplace(label_address);
if (pair.second) {
rebuild_state.inspect_queries.push_back(label_address);
}
};
while (true) {
if (offset >= end_address) {
// ASSERT_OR_EXECUTE can't be used, as it ignores the break
ASSERT_MSG(false, "Shader passed the current limit!");
single_branch.address = exit_branch;
single_branch.ignore = false;
break;
}
if (state.registered.contains(offset)) {
single_branch.address = offset;
single_branch.ignore = true;
break;
}
if (IsSchedInstruction(offset, state.start)) {
offset++;
continue;
}
const Instruction instr = {state.program_code[offset]};
const auto opcode = OpCode::Decode(instr);
if (!opcode || opcode->get().GetType() != OpCode::Type::Flow) {
offset++;
continue;
}
switch (opcode->get().GetId()) {
case OpCode::Id::EXIT: {
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
single_branch.condition.predicate = GetPredicate(pred_index, instr.negate_pred != 0);
if (single_branch.condition.predicate == Pred::NeverExecute) {
offset++;
continue;
}
const ConditionCode cc = instr.flow_condition_code;
single_branch.condition.cc = cc;
if (cc == ConditionCode::F) {
offset++;
continue;
}
single_branch.address = exit_branch;
single_branch.kill = false;
single_branch.is_sync = false;
single_branch.is_brk = false;
single_branch.ignore = false;
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill,
single_branch.is_sync, single_branch.is_brk, single_branch.ignore);
return {ParseResult::ControlCaught, parse_info};
}
case OpCode::Id::BRA: {
if (instr.bra.constant_buffer != 0) {
return {ParseResult::AbnormalFlow, parse_info};
}
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
single_branch.condition.predicate = GetPredicate(pred_index, instr.negate_pred != 0);
if (single_branch.condition.predicate == Pred::NeverExecute) {
offset++;
continue;
}
const ConditionCode cc = instr.flow_condition_code;
single_branch.condition.cc = cc;
if (cc == ConditionCode::F) {
offset++;
continue;
}
const u32 branch_offset = offset + instr.bra.GetBranchTarget();
if (branch_offset == 0) {
single_branch.address = exit_branch;
} else {
single_branch.address = branch_offset;
}
insert_label(state, branch_offset);
single_branch.kill = false;
single_branch.is_sync = false;
single_branch.is_brk = false;
single_branch.ignore = false;
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill,
single_branch.is_sync, single_branch.is_brk, single_branch.ignore);
return {ParseResult::ControlCaught, parse_info};
}
case OpCode::Id::SYNC: {
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
single_branch.condition.predicate = GetPredicate(pred_index, instr.negate_pred != 0);
if (single_branch.condition.predicate == Pred::NeverExecute) {
offset++;
continue;
}
const ConditionCode cc = instr.flow_condition_code;
single_branch.condition.cc = cc;
if (cc == ConditionCode::F) {
offset++;
continue;
}
single_branch.address = unassigned_branch;
single_branch.kill = false;
single_branch.is_sync = true;
single_branch.is_brk = false;
single_branch.ignore = false;
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill,
single_branch.is_sync, single_branch.is_brk, single_branch.ignore);
return {ParseResult::ControlCaught, parse_info};
}
case OpCode::Id::BRK: {
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
single_branch.condition.predicate = GetPredicate(pred_index, instr.negate_pred != 0);
if (single_branch.condition.predicate == Pred::NeverExecute) {
offset++;
continue;
}
const ConditionCode cc = instr.flow_condition_code;
single_branch.condition.cc = cc;
if (cc == ConditionCode::F) {
offset++;
continue;
}
single_branch.address = unassigned_branch;
single_branch.kill = false;
single_branch.is_sync = false;
single_branch.is_brk = true;
single_branch.ignore = false;
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill,
single_branch.is_sync, single_branch.is_brk, single_branch.ignore);
return {ParseResult::ControlCaught, parse_info};
}
case OpCode::Id::KIL: {
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
single_branch.condition.predicate = GetPredicate(pred_index, instr.negate_pred != 0);
if (single_branch.condition.predicate == Pred::NeverExecute) {
offset++;
continue;
}
const ConditionCode cc = instr.flow_condition_code;
single_branch.condition.cc = cc;
if (cc == ConditionCode::F) {
offset++;
continue;
}
single_branch.address = exit_branch;
single_branch.kill = true;
single_branch.is_sync = false;
single_branch.is_brk = false;
single_branch.ignore = false;
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill,
single_branch.is_sync, single_branch.is_brk, single_branch.ignore);
return {ParseResult::ControlCaught, parse_info};
}
case OpCode::Id::SSY: {
const u32 target = offset + instr.bra.GetBranchTarget();
insert_label(state, target);
state.ssy_labels.emplace(offset, target);
break;
}
case OpCode::Id::PBK: {
const u32 target = offset + instr.bra.GetBranchTarget();
insert_label(state, target);
state.pbk_labels.emplace(offset, target);
break;
}
case OpCode::Id::BRX: {
const auto tmp = TrackBranchIndirectInfo(state, offset);
if (!tmp) {
LOG_WARNING(HW_GPU, "BRX Track Unsuccesful");
return {ParseResult::AbnormalFlow, parse_info};
}
const auto result = *tmp;
const s32 pc_target = offset + result.relative_position;
std::vector<CaseBranch> branches;
for (u32 i = 0; i < result.entries; i++) {
auto key = state.registry.ObtainKey(result.buffer, result.offset + i * 4);
if (!key) {
return {ParseResult::AbnormalFlow, parse_info};
}
u32 value = *key;
u32 target = static_cast<u32>((value >> 3) + pc_target);
insert_label(state, target);
branches.emplace_back(value, target);
}
parse_info.end_address = offset;
parse_info.branch_info = MakeBranchInfo<MultiBranch>(
static_cast<u32>(instr.gpr8.Value()), std::move(branches));
return {ParseResult::ControlCaught, parse_info};
}
default:
break;
}
offset++;
}
single_branch.kill = false;
single_branch.is_sync = false;
single_branch.is_brk = false;
parse_info.end_address = offset - 1;
parse_info.branch_info = MakeBranchInfo<SingleBranch>(
single_branch.condition, single_branch.address, single_branch.kill, single_branch.is_sync,
single_branch.is_brk, single_branch.ignore);
return {ParseResult::BlockEnd, parse_info};
}
bool TryInspectAddress(CFGRebuildState& state) {
if (state.inspect_queries.empty()) {
return false;
}
const u32 address = state.inspect_queries.front();
state.inspect_queries.pop_front();
const auto [result, block_index] = TryGetBlock(state, address);
switch (result) {
case BlockCollision::Found: {
return true;
}
case BlockCollision::Inside: {
// This case is the tricky one:
// We need to split the block into 2 separate blocks
const u32 end = state.block_info[block_index].end;
BlockInfo& new_block = CreateBlockInfo(state, address, end);
BlockInfo& current_block = state.block_info[block_index];
current_block.end = address - 1;
new_block.branch = std::move(current_block.branch);
BlockBranchInfo forward_branch = MakeBranchInfo<SingleBranch>();
const auto branch = std::get_if<SingleBranch>(forward_branch.get());
branch->address = address;
branch->ignore = true;
current_block.branch = std::move(forward_branch);
return true;
}
default:
break;
}
const auto [parse_result, parse_info] = ParseCode(state, address);
if (parse_result == ParseResult::AbnormalFlow) {
// if it's AbnormalFlow, we end it as false, ending the CFG reconstruction
return false;
}
BlockInfo& block_info = CreateBlockInfo(state, address, parse_info.end_address);
block_info.branch = parse_info.branch_info;
if (std::holds_alternative<SingleBranch>(*block_info.branch)) {
const auto branch = std::get_if<SingleBranch>(block_info.branch.get());
if (branch->condition.IsUnconditional()) {
return true;
}
const u32 fallthrough_address = parse_info.end_address + 1;
state.inspect_queries.push_front(fallthrough_address);
return true;
}
return true;
}
bool TryQuery(CFGRebuildState& state) {
const auto gather_labels = [](std::stack<u32>& cc, std::map<u32, u32>& labels,
BlockInfo& block) {
auto gather_start = labels.lower_bound(block.start);
const auto gather_end = labels.upper_bound(block.end);
while (gather_start != gather_end) {
cc.push(gather_start->second);
++gather_start;
}
};
if (state.queries.empty()) {
return false;
}
Query& q = state.queries.front();
const u32 block_index = state.registered[q.address];
BlockInfo& block = state.block_info[block_index];
// If the block is visited, check if the stacks match, else gather the ssy/pbk
// labels into the current stack and look if the branch at the end of the block
// consumes a label. Schedule new queries accordingly
if (block.visited) {
BlockStack& stack = state.stacks[q.address];
const bool all_okay = (stack.ssy_stack.empty() || q.ssy_stack == stack.ssy_stack) &&
(stack.pbk_stack.empty() || q.pbk_stack == stack.pbk_stack);
state.queries.pop_front();
return all_okay;
}
block.visited = true;
state.stacks.insert_or_assign(q.address, BlockStack{q});
Query q2(q);
state.queries.pop_front();
gather_labels(q2.ssy_stack, state.ssy_labels, block);
gather_labels(q2.pbk_stack, state.pbk_labels, block);
if (std::holds_alternative<SingleBranch>(*block.branch)) {
auto* branch = std::get_if<SingleBranch>(block.branch.get());
if (!branch->condition.IsUnconditional()) {
q2.address = block.end + 1;
state.queries.push_back(q2);
}
auto& conditional_query = state.queries.emplace_back(q2);
if (branch->is_sync) {
if (branch->address == unassigned_branch) {
branch->address = conditional_query.ssy_stack.top();
}
conditional_query.ssy_stack.pop();
}
if (branch->is_brk) {
if (branch->address == unassigned_branch) {
branch->address = conditional_query.pbk_stack.top();
}
conditional_query.pbk_stack.pop();
}
conditional_query.address = branch->address;
return true;
}
const auto* multi_branch = std::get_if<MultiBranch>(block.branch.get());
for (const auto& branch_case : multi_branch->branches) {
auto& conditional_query = state.queries.emplace_back(q2);
conditional_query.address = branch_case.address;
}
return true;
}
void InsertBranch(ASTManager& mm, const BlockBranchInfo& branch_info) {
const auto get_expr = [](const Condition& cond) -> Expr {
Expr result;
if (cond.cc != ConditionCode::T) {
result = MakeExpr<ExprCondCode>(cond.cc);
}
if (cond.predicate != Pred::UnusedIndex) {
u32 pred = static_cast<u32>(cond.predicate);
bool negate = false;
if (pred > 7) {
negate = true;
pred -= 8;
}
Expr extra = MakeExpr<ExprPredicate>(pred);
if (negate) {
extra = MakeExpr<ExprNot>(std::move(extra));
}
if (result) {
return MakeExpr<ExprAnd>(std::move(extra), std::move(result));
}
return extra;
}
if (result) {
return result;
}
return MakeExpr<ExprBoolean>(true);
};
if (std::holds_alternative<SingleBranch>(*branch_info)) {
const auto* branch = std::get_if<SingleBranch>(branch_info.get());
if (branch->address < 0) {
if (branch->kill) {
mm.InsertReturn(get_expr(branch->condition), true);
return;
}
mm.InsertReturn(get_expr(branch->condition), false);
return;
}
mm.InsertGoto(get_expr(branch->condition), branch->address);
return;
}
const auto* multi_branch = std::get_if<MultiBranch>(branch_info.get());
for (const auto& branch_case : multi_branch->branches) {
mm.InsertGoto(MakeExpr<ExprGprEqual>(multi_branch->gpr, branch_case.cmp_value),
branch_case.address);
}
}
void DecompileShader(CFGRebuildState& state) {
state.manager->Init();
for (auto label : state.labels) {
state.manager->DeclareLabel(label);
}
for (const auto& block : state.block_info) {
if (state.labels.contains(block.start)) {
state.manager->InsertLabel(block.start);
}
const bool ignore = BlockBranchIsIgnored(block.branch);
const u32 end = ignore ? block.end + 1 : block.end;
state.manager->InsertBlock(block.start, end);
if (!ignore) {
InsertBranch(*state.manager, block.branch);
}
}
state.manager->Decompile();
}
} // Anonymous namespace
std::unique_ptr<ShaderCharacteristics> ScanFlow(const ProgramCode& program_code, u32 start_address,
const CompilerSettings& settings,
Registry& registry) {
auto result_out = std::make_unique<ShaderCharacteristics>();
if (settings.depth == CompileDepth::BruteForce) {
result_out->settings.depth = CompileDepth::BruteForce;
return result_out;
}
CFGRebuildState state{program_code, start_address, registry};
// Inspect Code and generate blocks
state.labels.clear();
state.labels.emplace(start_address);
state.inspect_queries.push_back(state.start);
while (!state.inspect_queries.empty()) {
if (!TryInspectAddress(state)) {
result_out->settings.depth = CompileDepth::BruteForce;
return result_out;
}
}
bool use_flow_stack = true;
bool decompiled = false;
if (settings.depth != CompileDepth::FlowStack) {
// Decompile Stacks
state.queries.push_back(Query{state.start, {}, {}});
decompiled = true;
while (!state.queries.empty()) {
if (!TryQuery(state)) {
decompiled = false;
break;
}
}
}
use_flow_stack = !decompiled;
// Sort and organize results
std::sort(state.block_info.begin(), state.block_info.end(),
[](const BlockInfo& a, const BlockInfo& b) -> bool { return a.start < b.start; });
if (decompiled && settings.depth != CompileDepth::NoFlowStack) {
ASTManager manager{settings.depth != CompileDepth::DecompileBackwards,
settings.disable_else_derivation};
state.manager = &manager;
DecompileShader(state);
decompiled = state.manager->IsFullyDecompiled();
if (!decompiled) {
if (settings.depth == CompileDepth::FullDecompile) {
LOG_CRITICAL(HW_GPU, "Failed to remove all the gotos!:");
} else {
LOG_CRITICAL(HW_GPU, "Failed to remove all backward gotos!:");
}
state.manager->ShowCurrentState("Of Shader");
state.manager->Clear();
} else {
auto characteristics = std::make_unique<ShaderCharacteristics>();
characteristics->start = start_address;
characteristics->settings.depth = settings.depth;
characteristics->manager = std::move(manager);
characteristics->end = state.block_info.back().end + 1;
return characteristics;
}
}
result_out->start = start_address;
result_out->settings.depth =
use_flow_stack ? CompileDepth::FlowStack : CompileDepth::NoFlowStack;
result_out->blocks.clear();
for (auto& block : state.block_info) {
ShaderBlock new_block{};
new_block.start = block.start;
new_block.end = block.end;
new_block.ignore_branch = BlockBranchIsIgnored(block.branch);
if (!new_block.ignore_branch) {
new_block.branch = block.branch;
}
result_out->end = std::max(result_out->end, block.end);
result_out->blocks.push_back(new_block);
}
if (!use_flow_stack) {
result_out->labels = std::move(state.labels);
return result_out;
}
auto back = result_out->blocks.begin();
auto next = std::next(back);
while (next != result_out->blocks.end()) {
if (!state.labels.contains(next->start) && next->start == back->end + 1) {
back->end = next->end;
next = result_out->blocks.erase(next);
continue;
}
back = next;
++next;
}
return result_out;
}
} // namespace VideoCommon::Shader

117
src/video_core/shader/control_flow.h
View file

@ -1,117 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <list>
#include <optional>
#include <set>
#include <variant>
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/ast.h"
#include "video_core/shader/compiler_settings.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::ConditionCode;
using Tegra::Shader::Pred;
constexpr s32 exit_branch = -1;
struct Condition {
Pred predicate{Pred::UnusedIndex};
ConditionCode cc{ConditionCode::T};
bool IsUnconditional() const {
return predicate == Pred::UnusedIndex && cc == ConditionCode::T;
}
bool operator==(const Condition& other) const {
return std::tie(predicate, cc) == std::tie(other.predicate, other.cc);
}
bool operator!=(const Condition& other) const {
return !operator==(other);
}
};
class SingleBranch {
public:
SingleBranch() = default;
explicit SingleBranch(Condition condition_, s32 address_, bool kill_, bool is_sync_,
bool is_brk_, bool ignore_)
: condition{condition_}, address{address_}, kill{kill_}, is_sync{is_sync_}, is_brk{is_brk_},
ignore{ignore_} {}
bool operator==(const SingleBranch& b) const {
return std::tie(condition, address, kill, is_sync, is_brk, ignore) ==
std::tie(b.condition, b.address, b.kill, b.is_sync, b.is_brk, b.ignore);
}
bool operator!=(const SingleBranch& b) const {
return !operator==(b);
}
Condition condition{};
s32 address{exit_branch};
bool kill{};
bool is_sync{};
bool is_brk{};
bool ignore{};
};
struct CaseBranch {
explicit CaseBranch(u32 cmp_value_, u32 address_) : cmp_value{cmp_value_}, address{address_} {}
u32 cmp_value;
u32 address;
};
class MultiBranch {
public:
explicit MultiBranch(u32 gpr_, std::vector<CaseBranch>&& branches_)
: gpr{gpr_}, branches{std::move(branches_)} {}
u32 gpr{};
std::vector<CaseBranch> branches{};
};
using BranchData = std::variant<SingleBranch, MultiBranch>;
using BlockBranchInfo = std::shared_ptr<BranchData>;
bool BlockBranchInfoAreEqual(BlockBranchInfo first, BlockBranchInfo second);
struct ShaderBlock {
u32 start{};
u32 end{};
bool ignore_branch{};
BlockBranchInfo branch{};
bool operator==(const ShaderBlock& sb) const {
return std::tie(start, end, ignore_branch) ==
std::tie(sb.start, sb.end, sb.ignore_branch) &&
BlockBranchInfoAreEqual(branch, sb.branch);
}
bool operator!=(const ShaderBlock& sb) const {
return !operator==(sb);
}
};
struct ShaderCharacteristics {
std::list<ShaderBlock> blocks{};
std::set<u32> labels{};
u32 start{};
u32 end{};
ASTManager manager{true, true};
CompilerSettings settings{};
};
std::unique_ptr<ShaderCharacteristics> ScanFlow(const ProgramCode& program_code, u32 start_address,
const CompilerSettings& settings,
Registry& registry);
} // namespace VideoCommon::Shader

368
src/video_core/shader/decode.cpp
View file

@ -1,368 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <cstring>
#include <limits>
#include <set>
#include <fmt/format.h>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/engines/shader_header.h"
#include "video_core/shader/control_flow.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
namespace {
void DeduceTextureHandlerSize(VideoCore::GuestDriverProfile& gpu_driver,
const std::list<SamplerEntry>& used_samplers) {
if (gpu_driver.IsTextureHandlerSizeKnown() || used_samplers.size() <= 1) {
return;
}
u32 count{};
std::vector<u32> bound_offsets;
for (const auto& sampler : used_samplers) {
if (sampler.is_bindless) {
continue;
}
++count;
bound_offsets.emplace_back(sampler.offset);
}
if (count > 1) {
gpu_driver.DeduceTextureHandlerSize(std::move(bound_offsets));
}
}
std::optional<u32> TryDeduceSamplerSize(const SamplerEntry& sampler_to_deduce,
VideoCore::GuestDriverProfile& gpu_driver,
const std::list<SamplerEntry>& used_samplers) {
const u32 base_offset = sampler_to_deduce.offset;
u32 max_offset{std::numeric_limits<u32>::max()};
for (const auto& sampler : used_samplers) {
if (sampler.is_bindless) {
continue;
}
if (sampler.offset > base_offset) {
max_offset = std::min(sampler.offset, max_offset);
}
}
if (max_offset == std::numeric_limits<u32>::max()) {
return std::nullopt;
}
return ((max_offset - base_offset) * 4) / gpu_driver.GetTextureHandlerSize();
}
} // Anonymous namespace
class ASTDecoder {
public:
explicit ASTDecoder(ShaderIR& ir_) : ir(ir_) {}
void operator()(ASTProgram& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(ASTIfThen& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(ASTIfElse& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(ASTBlockEncoded& ast) {}
void operator()(ASTBlockDecoded& ast) {}
void operator()(ASTVarSet& ast) {}
void operator()(ASTLabel& ast) {}
void operator()(ASTGoto& ast) {}
void operator()(ASTDoWhile& ast) {
ASTNode current = ast.nodes.GetFirst();
while (current) {
Visit(current);
current = current->GetNext();
}
}
void operator()(ASTReturn& ast) {}
void operator()(ASTBreak& ast) {}
void Visit(ASTNode& node) {
std::visit(*this, *node->GetInnerData());
if (node->IsBlockEncoded()) {
auto block = std::get_if<ASTBlockEncoded>(node->GetInnerData());
NodeBlock bb = ir.DecodeRange(block->start, block->end);
node->TransformBlockEncoded(std::move(bb));
}
}
private:
ShaderIR& ir;
};
void ShaderIR::Decode() {
std::memcpy(&header, program_code.data(), sizeof(Tegra::Shader::Header));
decompiled = false;
auto info = ScanFlow(program_code, main_offset, settings, registry);
auto& shader_info = *info;
coverage_begin = shader_info.start;
coverage_end = shader_info.end;
switch (shader_info.settings.depth) {
case CompileDepth::FlowStack: {
for (const auto& block : shader_info.blocks) {
basic_blocks.insert({block.start, DecodeRange(block.start, block.end + 1)});
}
break;
}
case CompileDepth::NoFlowStack: {
disable_flow_stack = true;
const auto insert_block = [this](NodeBlock& nodes, u32 label) {
if (label == static_cast<u32>(exit_branch)) {
return;
}
basic_blocks.insert({label, nodes});
};
const auto& blocks = shader_info.blocks;
NodeBlock current_block;
u32 current_label = static_cast<u32>(exit_branch);
for (const auto& block : blocks) {
if (shader_info.labels.contains(block.start)) {
insert_block(current_block, current_label);
current_block.clear();
current_label = block.start;
}
if (!block.ignore_branch) {
DecodeRangeInner(current_block, block.start, block.end);
InsertControlFlow(current_block, block);
} else {
DecodeRangeInner(current_block, block.start, block.end + 1);
}
}
insert_block(current_block, current_label);
break;
}
case CompileDepth::DecompileBackwards:
case CompileDepth::FullDecompile: {
program_manager = std::move(shader_info.manager);
disable_flow_stack = true;
decompiled = true;
ASTDecoder decoder{*this};
ASTNode program = GetASTProgram();
decoder.Visit(program);
break;
}
default:
LOG_CRITICAL(HW_GPU, "Unknown decompilation mode!");
[[fallthrough]];
case CompileDepth::BruteForce: {
const auto shader_end = static_cast<u32>(program_code.size());
coverage_begin = main_offset;
coverage_end = shader_end;
for (u32 label = main_offset; label < shader_end; ++label) {
basic_blocks.insert({label, DecodeRange(label, label + 1)});
}
break;
}
}
if (settings.depth != shader_info.settings.depth) {
LOG_WARNING(
HW_GPU, "Decompiling to this setting \"{}\" failed, downgrading to this setting \"{}\"",
CompileDepthAsString(settings.depth), CompileDepthAsString(shader_info.settings.depth));
}
}
NodeBlock ShaderIR::DecodeRange(u32 begin, u32 end) {
NodeBlock basic_block;
DecodeRangeInner(basic_block, begin, end);
return basic_block;
}
void ShaderIR::DecodeRangeInner(NodeBlock& bb, u32 begin, u32 end) {
for (u32 pc = begin; pc < (begin > end ? MAX_PROGRAM_LENGTH : end);) {
pc = DecodeInstr(bb, pc);
}
}
void ShaderIR::InsertControlFlow(NodeBlock& bb, const ShaderBlock& block) {
const auto apply_conditions = [&](const Condition& cond, Node n) -> Node {
Node result = n;
if (cond.cc != ConditionCode::T) {
result = Conditional(GetConditionCode(cond.cc), {result});
}
if (cond.predicate != Pred::UnusedIndex) {
u32 pred = static_cast<u32>(cond.predicate);
const bool is_neg = pred > 7;
if (is_neg) {
pred -= 8;
}
result = Conditional(GetPredicate(pred, is_neg), {result});
}
return result;
};
if (std::holds_alternative<SingleBranch>(*block.branch)) {
auto branch = std::get_if<SingleBranch>(block.branch.get());
if (branch->address < 0) {
if (branch->kill) {
Node n = Operation(OperationCode::Discard);
n = apply_conditions(branch->condition, n);
bb.push_back(n);
global_code.push_back(n);
return;
}
Node n = Operation(OperationCode::Exit);
n = apply_conditions(branch->condition, n);
bb.push_back(n);
global_code.push_back(n);
return;
}
Node n = Operation(OperationCode::Branch, Immediate(branch->address));
n = apply_conditions(branch->condition, n);
bb.push_back(n);
global_code.push_back(n);
return;
}
auto multi_branch = std::get_if<MultiBranch>(block.branch.get());
Node op_a = GetRegister(multi_branch->gpr);
for (auto& branch_case : multi_branch->branches) {
Node n = Operation(OperationCode::Branch, Immediate(branch_case.address));
Node op_b = Immediate(branch_case.cmp_value);
Node condition =
GetPredicateComparisonInteger(Tegra::Shader::PredCondition::EQ, false, op_a, op_b);
auto result = Conditional(condition, {n});
bb.push_back(result);
global_code.push_back(result);
}
}
u32 ShaderIR::DecodeInstr(NodeBlock& bb, u32 pc) {
// Ignore sched instructions when generating code.
if (IsSchedInstruction(pc, main_offset)) {
return pc + 1;
}
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
const u32 nv_address = ConvertAddressToNvidiaSpace(pc);
// Decoding failure
if (!opcode) {
UNIMPLEMENTED_MSG("Unhandled instruction: {0:x}", instr.value);
bb.push_back(Comment(fmt::format("{:05x} Unimplemented Shader instruction (0x{:016x})",
nv_address, instr.value)));
return pc + 1;
}
bb.push_back(Comment(
fmt::format("{:05x} {} (0x{:016x})", nv_address, opcode->get().GetName(), instr.value)));
using Tegra::Shader::Pred;
UNIMPLEMENTED_IF_MSG(instr.pred.full_pred == Pred::NeverExecute,
"NeverExecute predicate not implemented");
static const std::map<OpCode::Type, u32 (ShaderIR::*)(NodeBlock&, u32)> decoders = {
{OpCode::Type::Arithmetic, &ShaderIR::DecodeArithmetic},
{OpCode::Type::ArithmeticImmediate, &ShaderIR::DecodeArithmeticImmediate},
{OpCode::Type::Bfe, &ShaderIR::DecodeBfe},
{OpCode::Type::Bfi, &ShaderIR::DecodeBfi},
{OpCode::Type::Shift, &ShaderIR::DecodeShift},
{OpCode::Type::ArithmeticInteger, &ShaderIR::DecodeArithmeticInteger},
{OpCode::Type::ArithmeticIntegerImmediate, &ShaderIR::DecodeArithmeticIntegerImmediate},
{OpCode::Type::ArithmeticHalf, &ShaderIR::DecodeArithmeticHalf},
{OpCode::Type::ArithmeticHalfImmediate, &ShaderIR::DecodeArithmeticHalfImmediate},
{OpCode::Type::Ffma, &ShaderIR::DecodeFfma},
{OpCode::Type::Hfma2, &ShaderIR::DecodeHfma2},
{OpCode::Type::Conversion, &ShaderIR::DecodeConversion},
{OpCode::Type::Warp, &ShaderIR::DecodeWarp},
{OpCode::Type::Memory, &ShaderIR::DecodeMemory},
{OpCode::Type::Texture, &ShaderIR::DecodeTexture},
{OpCode::Type::Image, &ShaderIR::DecodeImage},
{OpCode::Type::FloatSetPredicate, &ShaderIR::DecodeFloatSetPredicate},
{OpCode::Type::IntegerSetPredicate, &ShaderIR::DecodeIntegerSetPredicate},
{OpCode::Type::HalfSetPredicate, &ShaderIR::DecodeHalfSetPredicate},
{OpCode::Type::PredicateSetRegister, &ShaderIR::DecodePredicateSetRegister},
{OpCode::Type::PredicateSetPredicate, &ShaderIR::DecodePredicateSetPredicate},
{OpCode::Type::RegisterSetPredicate, &ShaderIR::DecodeRegisterSetPredicate},
{OpCode::Type::FloatSet, &ShaderIR::DecodeFloatSet},
{OpCode::Type::IntegerSet, &ShaderIR::DecodeIntegerSet},
{OpCode::Type::HalfSet, &ShaderIR::DecodeHalfSet},
{OpCode::Type::Video, &ShaderIR::DecodeVideo},
{OpCode::Type::Xmad, &ShaderIR::DecodeXmad},
};
std::vector<Node> tmp_block;
if (const auto decoder = decoders.find(opcode->get().GetType()); decoder != decoders.end()) {
pc = (this->*decoder->second)(tmp_block, pc);
} else {
pc = DecodeOther(tmp_block, pc);
}
// Some instructions (like SSY) don't have a predicate field, they are always unconditionally
// executed.
const bool can_be_predicated = OpCode::IsPredicatedInstruction(opcode->get().GetId());
const auto pred_index = static_cast<u32>(instr.pred.pred_index);
if (can_be_predicated && pred_index != static_cast<u32>(Pred::UnusedIndex)) {
const Node conditional =
Conditional(GetPredicate(pred_index, instr.negate_pred != 0), std::move(tmp_block));
global_code.push_back(conditional);
bb.push_back(conditional);
} else {
for (auto& node : tmp_block) {
global_code.push_back(node);
bb.push_back(node);
}
}
return pc + 1;
}
void ShaderIR::PostDecode() {
// Deduce texture handler size if needed
auto gpu_driver = registry.AccessGuestDriverProfile();
DeduceTextureHandlerSize(gpu_driver, used_samplers);
// Deduce Indexed Samplers
if (!uses_indexed_samplers) {
return;
}
for (auto& sampler : used_samplers) {
if (!sampler.is_indexed) {
continue;
}
if (const auto size = TryDeduceSamplerSize(sampler, gpu_driver, used_samplers)) {
sampler.size = *size;
} else {
LOG_CRITICAL(HW_GPU, "Failed to deduce size of indexed sampler");
sampler.size = 1;
}
}
}
} // namespace VideoCommon::Shader

166
src/video_core/shader/decode/arithmetic.cpp
View file

@ -1,166 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::SubOp;
u32 ShaderIR::DecodeArithmetic(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node op_a = GetRegister(instr.gpr8);
Node op_b = [&] {
if (instr.is_b_imm) {
return GetImmediate19(instr);
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
switch (opcode->get().GetId()) {
case OpCode::Id::MOV_C:
case OpCode::Id::MOV_R: {
// MOV does not have neither 'abs' nor 'neg' bits.
SetRegister(bb, instr.gpr0, op_b);
break;
}
case OpCode::Id::FMUL_C:
case OpCode::Id::FMUL_R:
case OpCode::Id::FMUL_IMM: {
// FMUL does not have 'abs' bits and only the second operand has a 'neg' bit.
if (instr.fmul.tab5cb8_2 != 0) {
LOG_DEBUG(HW_GPU, "FMUL tab5cb8_2({}) is not implemented",
instr.fmul.tab5cb8_2.Value());
}
if (instr.fmul.tab5c68_0 != 1) {
LOG_DEBUG(HW_GPU, "FMUL tab5cb8_0({}) is not implemented",
instr.fmul.tab5c68_0.Value());
}
op_b = GetOperandAbsNegFloat(op_b, false, instr.fmul.negate_b);
static constexpr std::array FmulPostFactor = {
1.000f, // None
0.500f, // Divide 2
0.250f, // Divide 4
0.125f, // Divide 8
8.000f, // Mul 8
4.000f, // Mul 4
2.000f, // Mul 2
};
if (instr.fmul.postfactor != 0) {
op_a = Operation(OperationCode::FMul, NO_PRECISE, op_a,
Immediate(FmulPostFactor[instr.fmul.postfactor]));
}
// TODO(Rodrigo): Should precise be used when there's a postfactor?
Node value = Operation(OperationCode::FMul, PRECISE, op_a, op_b);
value = GetSaturatedFloat(value, instr.alu.saturate_d);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::FADD_C:
case OpCode::Id::FADD_R:
case OpCode::Id::FADD_IMM: {
op_a = GetOperandAbsNegFloat(op_a, instr.alu.abs_a, instr.alu.negate_a);
op_b = GetOperandAbsNegFloat(op_b, instr.alu.abs_b, instr.alu.negate_b);
Node value = Operation(OperationCode::FAdd, PRECISE, op_a, op_b);
value = GetSaturatedFloat(value, instr.alu.saturate_d);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::MUFU: {
op_a = GetOperandAbsNegFloat(op_a, instr.alu.abs_a, instr.alu.negate_a);
Node value = [&]() {
switch (instr.sub_op) {
case SubOp::Cos:
return Operation(OperationCode::FCos, PRECISE, op_a);
case SubOp::Sin:
return Operation(OperationCode::FSin, PRECISE, op_a);
case SubOp::Ex2:
return Operation(OperationCode::FExp2, PRECISE, op_a);
case SubOp::Lg2:
return Operation(OperationCode::FLog2, PRECISE, op_a);
case SubOp::Rcp:
return Operation(OperationCode::FDiv, PRECISE, Immediate(1.0f), op_a);
case SubOp::Rsq:
return Operation(OperationCode::FInverseSqrt, PRECISE, op_a);
case SubOp::Sqrt:
return Operation(OperationCode::FSqrt, PRECISE, op_a);
default:
UNIMPLEMENTED_MSG("Unhandled MUFU sub op={0:x}", instr.sub_op.Value());
return Immediate(0);
}
}();
value = GetSaturatedFloat(value, instr.alu.saturate_d);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::FMNMX_C:
case OpCode::Id::FMNMX_R:
case OpCode::Id::FMNMX_IMM: {
op_a = GetOperandAbsNegFloat(op_a, instr.alu.abs_a, instr.alu.negate_a);
op_b = GetOperandAbsNegFloat(op_b, instr.alu.abs_b, instr.alu.negate_b);
const Node condition = GetPredicate(instr.alu.fmnmx.pred, instr.alu.fmnmx.negate_pred != 0);
const Node min = Operation(OperationCode::FMin, NO_PRECISE, op_a, op_b);
const Node max = Operation(OperationCode::FMax, NO_PRECISE, op_a, op_b);
const Node value = Operation(OperationCode::Select, NO_PRECISE, condition, min, max);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::FCMP_RR:
case OpCode::Id::FCMP_RC:
case OpCode::Id::FCMP_IMMR: {
UNIMPLEMENTED_IF(instr.fcmp.ftz == 0);
Node op_c = GetRegister(instr.gpr39);
Node comp = GetPredicateComparisonFloat(instr.fcmp.cond, std::move(op_c), Immediate(0.0f));
SetRegister(
bb, instr.gpr0,
Operation(OperationCode::Select, std::move(comp), std::move(op_a), std::move(op_b)));
break;
}
case OpCode::Id::RRO_C:
case OpCode::Id::RRO_R:
case OpCode::Id::RRO_IMM: {
LOG_DEBUG(HW_GPU, "(STUBBED) RRO used");
// Currently RRO is only implemented as a register move.
op_b = GetOperandAbsNegFloat(op_b, instr.alu.abs_b, instr.alu.negate_b);
SetRegister(bb, instr.gpr0, op_b);
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled arithmetic instruction: {}", opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

101
src/video_core/shader/decode/arithmetic_half.cpp
View file

@ -1,101 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::HalfType;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeArithmeticHalf(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
bool negate_a = false;
bool negate_b = false;
bool absolute_a = false;
bool absolute_b = false;
switch (opcode->get().GetId()) {
case OpCode::Id::HADD2_R:
if (instr.alu_half.ftz == 0) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
negate_a = ((instr.value >> 43) & 1) != 0;
negate_b = ((instr.value >> 31) & 1) != 0;
absolute_a = ((instr.value >> 44) & 1) != 0;
absolute_b = ((instr.value >> 30) & 1) != 0;
break;
case OpCode::Id::HADD2_C:
if (instr.alu_half.ftz == 0) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
negate_a = ((instr.value >> 43) & 1) != 0;
negate_b = ((instr.value >> 56) & 1) != 0;
absolute_a = ((instr.value >> 44) & 1) != 0;
absolute_b = ((instr.value >> 54) & 1) != 0;
break;
case OpCode::Id::HMUL2_R:
negate_a = ((instr.value >> 43) & 1) != 0;
absolute_a = ((instr.value >> 44) & 1) != 0;
absolute_b = ((instr.value >> 30) & 1) != 0;
break;
case OpCode::Id::HMUL2_C:
negate_b = ((instr.value >> 31) & 1) != 0;
absolute_a = ((instr.value >> 44) & 1) != 0;
absolute_b = ((instr.value >> 54) & 1) != 0;
break;
default:
UNREACHABLE();
break;
}
Node op_a = UnpackHalfFloat(GetRegister(instr.gpr8), instr.alu_half.type_a);
op_a = GetOperandAbsNegHalf(op_a, absolute_a, negate_a);
auto [type_b, op_b] = [this, instr, opcode]() -> std::pair<HalfType, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::HADD2_C:
case OpCode::Id::HMUL2_C:
return {HalfType::F32, GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
case OpCode::Id::HADD2_R:
case OpCode::Id::HMUL2_R:
return {instr.alu_half.type_b, GetRegister(instr.gpr20)};
default:
UNREACHABLE();
return {HalfType::F32, Immediate(0)};
}
}();
op_b = UnpackHalfFloat(op_b, type_b);
op_b = GetOperandAbsNegHalf(op_b, absolute_b, negate_b);
Node value = [this, opcode, op_a, op_b = op_b] {
switch (opcode->get().GetId()) {
case OpCode::Id::HADD2_C:
case OpCode::Id::HADD2_R:
return Operation(OperationCode::HAdd, PRECISE, op_a, op_b);
case OpCode::Id::HMUL2_C:
case OpCode::Id::HMUL2_R:
return Operation(OperationCode::HMul, PRECISE, op_a, op_b);
default:
UNIMPLEMENTED_MSG("Unhandled half float instruction: {}", opcode->get().GetName());
return Immediate(0);
}
}();
value = GetSaturatedHalfFloat(value, instr.alu_half.saturate);
value = HalfMerge(GetRegister(instr.gpr0), value, instr.alu_half.merge);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

54
src/video_core/shader/decode/arithmetic_half_immediate.cpp
View file

@ -1,54 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeArithmeticHalfImmediate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
if (opcode->get().GetId() == OpCode::Id::HADD2_IMM) {
if (instr.alu_half_imm.ftz == 0) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
} else {
if (instr.alu_half_imm.precision != Tegra::Shader::HalfPrecision::FTZ) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
}
Node op_a = UnpackHalfFloat(GetRegister(instr.gpr8), instr.alu_half_imm.type_a);
op_a = GetOperandAbsNegHalf(op_a, instr.alu_half_imm.abs_a, instr.alu_half_imm.negate_a);
const Node op_b = UnpackHalfImmediate(instr, true);
Node value = [&]() {
switch (opcode->get().GetId()) {
case OpCode::Id::HADD2_IMM:
return Operation(OperationCode::HAdd, PRECISE, op_a, op_b);
case OpCode::Id::HMUL2_IMM:
return Operation(OperationCode::HMul, PRECISE, op_a, op_b);
default:
UNREACHABLE();
return Immediate(0);
}
}();
value = GetSaturatedHalfFloat(value, instr.alu_half_imm.saturate);
value = HalfMerge(GetRegister(instr.gpr0), value, instr.alu_half_imm.merge);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

53
src/video_core/shader/decode/arithmetic_immediate.cpp
View file

@ -1,53 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeArithmeticImmediate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
switch (opcode->get().GetId()) {
case OpCode::Id::MOV32_IMM: {
SetRegister(bb, instr.gpr0, GetImmediate32(instr));
break;
}
case OpCode::Id::FMUL32_IMM: {
Node value =
Operation(OperationCode::FMul, PRECISE, GetRegister(instr.gpr8), GetImmediate32(instr));
value = GetSaturatedFloat(value, instr.fmul32.saturate);
SetInternalFlagsFromFloat(bb, value, instr.op_32.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::FADD32I: {
const Node op_a = GetOperandAbsNegFloat(GetRegister(instr.gpr8), instr.fadd32i.abs_a,
instr.fadd32i.negate_a);
const Node op_b = GetOperandAbsNegFloat(GetImmediate32(instr), instr.fadd32i.abs_b,
instr.fadd32i.negate_b);
const Node value = Operation(OperationCode::FAdd, PRECISE, op_a, op_b);
SetInternalFlagsFromFloat(bb, value, instr.op_32.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled arithmetic immediate instruction: {}",
opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

375
src/video_core/shader/decode/arithmetic_integer.cpp
View file

@ -1,375 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::IAdd3Height;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
using Tegra::Shader::Register;
u32 ShaderIR::DecodeArithmeticInteger(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node op_a = GetRegister(instr.gpr8);
Node op_b = [&]() {
if (instr.is_b_imm) {
return Immediate(instr.alu.GetSignedImm20_20());
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
switch (opcode->get().GetId()) {
case OpCode::Id::IADD_C:
case OpCode::Id::IADD_R:
case OpCode::Id::IADD_IMM: {
UNIMPLEMENTED_IF_MSG(instr.alu.saturate_d, "IADD.SAT");
UNIMPLEMENTED_IF_MSG(instr.iadd.x && instr.generates_cc, "IADD.X Rd.CC");
op_a = GetOperandAbsNegInteger(op_a, false, instr.alu_integer.negate_a, true);
op_b = GetOperandAbsNegInteger(op_b, false, instr.alu_integer.negate_b, true);
Node value = Operation(OperationCode::UAdd, op_a, op_b);
if (instr.iadd.x) {
Node carry = GetInternalFlag(InternalFlag::Carry);
Node x = Operation(OperationCode::Select, std::move(carry), Immediate(1), Immediate(0));
value = Operation(OperationCode::UAdd, std::move(value), std::move(x));
}
if (instr.generates_cc) {
const Node i0 = Immediate(0);
Node zero = Operation(OperationCode::LogicalIEqual, value, i0);
Node sign = Operation(OperationCode::LogicalILessThan, value, i0);
Node carry = Operation(OperationCode::LogicalAddCarry, op_a, op_b);
Node pos_a = Operation(OperationCode::LogicalIGreaterThan, op_a, i0);
Node pos_b = Operation(OperationCode::LogicalIGreaterThan, op_b, i0);
Node pos = Operation(OperationCode::LogicalAnd, std::move(pos_a), std::move(pos_b));
Node overflow = Operation(OperationCode::LogicalAnd, pos, sign);
SetInternalFlag(bb, InternalFlag::Zero, std::move(zero));
SetInternalFlag(bb, InternalFlag::Sign, std::move(sign));
SetInternalFlag(bb, InternalFlag::Carry, std::move(carry));
SetInternalFlag(bb, InternalFlag::Overflow, std::move(overflow));
}
SetRegister(bb, instr.gpr0, std::move(value));
break;
}
case OpCode::Id::IADD3_C:
case OpCode::Id::IADD3_R:
case OpCode::Id::IADD3_IMM: {
Node op_c = GetRegister(instr.gpr39);
const auto ApplyHeight = [&](IAdd3Height height, Node value) {
switch (height) {
case IAdd3Height::None:
return value;
case IAdd3Height::LowerHalfWord:
return BitfieldExtract(value, 0, 16);
case IAdd3Height::UpperHalfWord:
return BitfieldExtract(value, 16, 16);
default:
UNIMPLEMENTED_MSG("Unhandled IADD3 height: {}", height);
return Immediate(0);
}
};
if (opcode->get().GetId() == OpCode::Id::IADD3_R) {
op_a = ApplyHeight(instr.iadd3.height_a, op_a);
op_b = ApplyHeight(instr.iadd3.height_b, op_b);
op_c = ApplyHeight(instr.iadd3.height_c, op_c);
}
op_a = GetOperandAbsNegInteger(op_a, false, instr.iadd3.neg_a, true);
op_b = GetOperandAbsNegInteger(op_b, false, instr.iadd3.neg_b, true);
op_c = GetOperandAbsNegInteger(op_c, false, instr.iadd3.neg_c, true);
const Node value = [&] {
Node add_ab = Operation(OperationCode::IAdd, NO_PRECISE, op_a, op_b);
if (opcode->get().GetId() != OpCode::Id::IADD3_R) {
return Operation(OperationCode::IAdd, NO_PRECISE, add_ab, op_c);
}
const Node shifted = [&] {
switch (instr.iadd3.mode) {
case Tegra::Shader::IAdd3Mode::RightShift:
// TODO(tech4me): According to
// https://envytools.readthedocs.io/en/latest/hw/graph/maxwell/cuda/int.html?highlight=iadd3
// The addition between op_a and op_b should be done in uint33, more
// investigation required
return Operation(OperationCode::ILogicalShiftRight, NO_PRECISE, add_ab,
Immediate(16));
case Tegra::Shader::IAdd3Mode::LeftShift:
return Operation(OperationCode::ILogicalShiftLeft, NO_PRECISE, add_ab,
Immediate(16));
default:
return add_ab;
}
}();
return Operation(OperationCode::IAdd, NO_PRECISE, shifted, op_c);
}();
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::ISCADD_C:
case OpCode::Id::ISCADD_R:
case OpCode::Id::ISCADD_IMM: {
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in ISCADD is not implemented");
op_a = GetOperandAbsNegInteger(op_a, false, instr.alu_integer.negate_a, true);
op_b = GetOperandAbsNegInteger(op_b, false, instr.alu_integer.negate_b, true);
const Node shift = Immediate(static_cast<u32>(instr.alu_integer.shift_amount));
const Node shifted_a = Operation(OperationCode::ILogicalShiftLeft, NO_PRECISE, op_a, shift);
const Node value = Operation(OperationCode::IAdd, NO_PRECISE, shifted_a, op_b);
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::POPC_C:
case OpCode::Id::POPC_R:
case OpCode::Id::POPC_IMM: {
if (instr.popc.invert) {
op_b = Operation(OperationCode::IBitwiseNot, NO_PRECISE, op_b);
}
const Node value = Operation(OperationCode::IBitCount, PRECISE, op_b);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::FLO_R:
case OpCode::Id::FLO_C:
case OpCode::Id::FLO_IMM: {
Node value;
if (instr.flo.invert) {
op_b = Operation(OperationCode::IBitwiseNot, NO_PRECISE, std::move(op_b));
}
if (instr.flo.is_signed) {
value = Operation(OperationCode::IBitMSB, NO_PRECISE, std::move(op_b));
} else {
value = Operation(OperationCode::UBitMSB, NO_PRECISE, std::move(op_b));
}
if (instr.flo.sh) {
value =
Operation(OperationCode::UBitwiseXor, NO_PRECISE, std::move(value), Immediate(31));
}
SetRegister(bb, instr.gpr0, std::move(value));
break;
}
case OpCode::Id::SEL_C:
case OpCode::Id::SEL_R:
case OpCode::Id::SEL_IMM: {
const Node condition = GetPredicate(instr.sel.pred, instr.sel.neg_pred != 0);
const Node value = Operation(OperationCode::Select, PRECISE, condition, op_a, op_b);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::ICMP_CR:
case OpCode::Id::ICMP_R:
case OpCode::Id::ICMP_RC:
case OpCode::Id::ICMP_IMM: {
const Node zero = Immediate(0);
const auto [op_rhs, test] = [&]() -> std::pair<Node, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::ICMP_CR:
return {GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
GetRegister(instr.gpr39)};
case OpCode::Id::ICMP_R:
return {GetRegister(instr.gpr20), GetRegister(instr.gpr39)};
case OpCode::Id::ICMP_RC:
return {GetRegister(instr.gpr39),
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
case OpCode::Id::ICMP_IMM:
return {Immediate(instr.alu.GetSignedImm20_20()), GetRegister(instr.gpr39)};
default:
UNREACHABLE();
return {zero, zero};
}
}();
const Node op_lhs = GetRegister(instr.gpr8);
const Node comparison =
GetPredicateComparisonInteger(instr.icmp.cond, instr.icmp.is_signed != 0, test, zero);
SetRegister(bb, instr.gpr0, Operation(OperationCode::Select, comparison, op_lhs, op_rhs));
break;
}
case OpCode::Id::LOP_C:
case OpCode::Id::LOP_R:
case OpCode::Id::LOP_IMM: {
if (instr.alu.lop.invert_a)
op_a = Operation(OperationCode::IBitwiseNot, NO_PRECISE, op_a);
if (instr.alu.lop.invert_b)
op_b = Operation(OperationCode::IBitwiseNot, NO_PRECISE, op_b);
WriteLogicOperation(bb, instr.gpr0, instr.alu.lop.operation, op_a, op_b,
instr.alu.lop.pred_result_mode, instr.alu.lop.pred48,
instr.generates_cc);
break;
}
case OpCode::Id::LOP3_C:
case OpCode::Id::LOP3_R:
case OpCode::Id::LOP3_IMM: {
const Node op_c = GetRegister(instr.gpr39);
const Node lut = [&]() {
if (opcode->get().GetId() == OpCode::Id::LOP3_R) {
return Immediate(instr.alu.lop3.GetImmLut28());
} else {
return Immediate(instr.alu.lop3.GetImmLut48());
}
}();
WriteLop3Instruction(bb, instr.gpr0, op_a, op_b, op_c, lut, instr.generates_cc);
break;
}
case OpCode::Id::IMNMX_C:
case OpCode::Id::IMNMX_R:
case OpCode::Id::IMNMX_IMM: {
UNIMPLEMENTED_IF(instr.imnmx.exchange != Tegra::Shader::IMinMaxExchange::None);
const bool is_signed = instr.imnmx.is_signed;
const Node condition = GetPredicate(instr.imnmx.pred, instr.imnmx.negate_pred != 0);
const Node min = SignedOperation(OperationCode::IMin, is_signed, NO_PRECISE, op_a, op_b);
const Node max = SignedOperation(OperationCode::IMax, is_signed, NO_PRECISE, op_a, op_b);
const Node value = Operation(OperationCode::Select, NO_PRECISE, condition, min, max);
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::LEA_R2:
case OpCode::Id::LEA_R1:
case OpCode::Id::LEA_IMM:
case OpCode::Id::LEA_RZ:
case OpCode::Id::LEA_HI: {
auto [op_a_, op_b_, op_c_] = [&]() -> std::tuple<Node, Node, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::LEA_R2: {
return {GetRegister(instr.gpr20), GetRegister(instr.gpr39),
Immediate(static_cast<u32>(instr.lea.r2.entry_a))};
}
case OpCode::Id::LEA_R1: {
const bool neg = instr.lea.r1.neg != 0;
return {GetOperandAbsNegInteger(GetRegister(instr.gpr8), false, neg, true),
GetRegister(instr.gpr20),
Immediate(static_cast<u32>(instr.lea.r1.entry_a))};
}
case OpCode::Id::LEA_IMM: {
const bool neg = instr.lea.imm.neg != 0;
return {GetOperandAbsNegInteger(GetRegister(instr.gpr8), false, neg, true),
Immediate(static_cast<u32>(instr.lea.imm.entry_a)),
Immediate(static_cast<u32>(instr.lea.imm.entry_b))};
}
case OpCode::Id::LEA_RZ: {
const bool neg = instr.lea.rz.neg != 0;
return {GetConstBuffer(instr.lea.rz.cb_index, instr.lea.rz.cb_offset),
GetOperandAbsNegInteger(GetRegister(instr.gpr8), false, neg, true),
Immediate(static_cast<u32>(instr.lea.rz.entry_a))};
}
case OpCode::Id::LEA_HI:
default:
UNIMPLEMENTED_MSG("Unhandled LEA subinstruction: {}", opcode->get().GetName());
return {Immediate(static_cast<u32>(instr.lea.imm.entry_a)), GetRegister(instr.gpr8),
Immediate(static_cast<u32>(instr.lea.imm.entry_b))};
}
}();
UNIMPLEMENTED_IF_MSG(instr.lea.pred48 != static_cast<u64>(Pred::UnusedIndex),
"Unhandled LEA Predicate");
Node value =
Operation(OperationCode::ILogicalShiftLeft, std::move(op_a_), std::move(op_c_));
value = Operation(OperationCode::IAdd, std::move(op_b_), std::move(value));
SetRegister(bb, instr.gpr0, std::move(value));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled ArithmeticInteger instruction: {}", opcode->get().GetName());
}
return pc;
}
void ShaderIR::WriteLop3Instruction(NodeBlock& bb, Register dest, Node op_a, Node op_b, Node op_c,
Node imm_lut, bool sets_cc) {
const Node lop3_fast = [&](const Node na, const Node nb, const Node nc, const Node ttbl) {
Node value = Immediate(0);
const ImmediateNode imm = std::get<ImmediateNode>(*ttbl);
if (imm.GetValue() & 0x01) {
const Node a = Operation(OperationCode::IBitwiseNot, na);
const Node b = Operation(OperationCode::IBitwiseNot, nb);
const Node c = Operation(OperationCode::IBitwiseNot, nc);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, a, b);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, c);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x02) {
const Node a = Operation(OperationCode::IBitwiseNot, na);
const Node b = Operation(OperationCode::IBitwiseNot, nb);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, a, b);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, nc);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x04) {
const Node a = Operation(OperationCode::IBitwiseNot, na);
const Node c = Operation(OperationCode::IBitwiseNot, nc);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, a, nb);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, c);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x08) {
const Node a = Operation(OperationCode::IBitwiseNot, na);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, a, nb);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, nc);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x10) {
const Node b = Operation(OperationCode::IBitwiseNot, nb);
const Node c = Operation(OperationCode::IBitwiseNot, nc);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, na, b);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, c);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x20) {
const Node b = Operation(OperationCode::IBitwiseNot, nb);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, na, b);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, nc);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x40) {
const Node c = Operation(OperationCode::IBitwiseNot, nc);
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, na, nb);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, c);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
if (imm.GetValue() & 0x80) {
Node r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, na, nb);
r = Operation(OperationCode::IBitwiseAnd, NO_PRECISE, r, nc);
value = Operation(OperationCode::IBitwiseOr, value, r);
}
return value;
}(op_a, op_b, op_c, imm_lut);
SetInternalFlagsFromInteger(bb, lop3_fast, sets_cc);
SetRegister(bb, dest, lop3_fast);
}
} // namespace VideoCommon::Shader

99
src/video_core/shader/decode/arithmetic_integer_immediate.cpp
View file

@ -1,99 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::LogicOperation;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
using Tegra::Shader::PredicateResultMode;
using Tegra::Shader::Register;
u32 ShaderIR::DecodeArithmeticIntegerImmediate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node op_a = GetRegister(instr.gpr8);
Node op_b = Immediate(static_cast<s32>(instr.alu.imm20_32));
switch (opcode->get().GetId()) {
case OpCode::Id::IADD32I: {
UNIMPLEMENTED_IF_MSG(instr.iadd32i.saturate, "IADD32I saturation is not implemented");
op_a = GetOperandAbsNegInteger(std::move(op_a), false, instr.iadd32i.negate_a != 0, true);
Node value = Operation(OperationCode::IAdd, PRECISE, std::move(op_a), std::move(op_b));
SetInternalFlagsFromInteger(bb, value, instr.op_32.generates_cc != 0);
SetRegister(bb, instr.gpr0, std::move(value));
break;
}
case OpCode::Id::LOP32I: {
if (instr.alu.lop32i.invert_a) {
op_a = Operation(OperationCode::IBitwiseNot, NO_PRECISE, std::move(op_a));
}
if (instr.alu.lop32i.invert_b) {
op_b = Operation(OperationCode::IBitwiseNot, NO_PRECISE, std::move(op_b));
}
WriteLogicOperation(bb, instr.gpr0, instr.alu.lop32i.operation, std::move(op_a),
std::move(op_b), PredicateResultMode::None, Pred::UnusedIndex,
instr.op_32.generates_cc != 0);
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled ArithmeticIntegerImmediate instruction: {}",
opcode->get().GetName());
}
return pc;
}
void ShaderIR::WriteLogicOperation(NodeBlock& bb, Register dest, LogicOperation logic_op, Node op_a,
Node op_b, PredicateResultMode predicate_mode, Pred predicate,
bool sets_cc) {
Node result = [&] {
switch (logic_op) {
case LogicOperation::And:
return Operation(OperationCode::IBitwiseAnd, PRECISE, std::move(op_a), std::move(op_b));
case LogicOperation::Or:
return Operation(OperationCode::IBitwiseOr, PRECISE, std::move(op_a), std::move(op_b));
case LogicOperation::Xor:
return Operation(OperationCode::IBitwiseXor, PRECISE, std::move(op_a), std::move(op_b));
case LogicOperation::PassB:
return op_b;
default:
UNIMPLEMENTED_MSG("Unimplemented logic operation={}", logic_op);
return Immediate(0);
}
}();
SetInternalFlagsFromInteger(bb, result, sets_cc);
SetRegister(bb, dest, result);
// Write the predicate value depending on the predicate mode.
switch (predicate_mode) {
case PredicateResultMode::None:
// Do nothing.
return;
case PredicateResultMode::NotZero: {
// Set the predicate to true if the result is not zero.
Node compare = Operation(OperationCode::LogicalINotEqual, std::move(result), Immediate(0));
SetPredicate(bb, static_cast<u64>(predicate), std::move(compare));
break;
}
default:
UNIMPLEMENTED_MSG("Unimplemented predicate result mode: {}", predicate_mode);
}
}
} // namespace VideoCommon::Shader

77
src/video_core/shader/decode/bfe.cpp
View file

@ -1,77 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeBfe(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node op_a = GetRegister(instr.gpr8);
Node op_b = [&] {
switch (opcode->get().GetId()) {
case OpCode::Id::BFE_R:
return GetRegister(instr.gpr20);
case OpCode::Id::BFE_C:
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::BFE_IMM:
return Immediate(instr.alu.GetSignedImm20_20());
default:
UNREACHABLE();
return Immediate(0);
}
}();
UNIMPLEMENTED_IF_MSG(instr.bfe.rd_cc, "Condition codes in BFE is not implemented");
const bool is_signed = instr.bfe.is_signed;
// using reverse parallel method in
// https://graphics.stanford.edu/~seander/bithacks.html#ReverseParallel
// note for later if possible to implement faster method.
if (instr.bfe.brev) {
const auto swap = [&](u32 s, u32 mask) {
Node v1 =
SignedOperation(OperationCode::ILogicalShiftRight, is_signed, op_a, Immediate(s));
if (mask != 0) {
v1 = SignedOperation(OperationCode::IBitwiseAnd, is_signed, std::move(v1),
Immediate(mask));
}
Node v2 = op_a;
if (mask != 0) {
v2 = SignedOperation(OperationCode::IBitwiseAnd, is_signed, std::move(v2),
Immediate(mask));
}
v2 = SignedOperation(OperationCode::ILogicalShiftLeft, is_signed, std::move(v2),
Immediate(s));
return SignedOperation(OperationCode::IBitwiseOr, is_signed, std::move(v1),
std::move(v2));
};
op_a = swap(1, 0x55555555U);
op_a = swap(2, 0x33333333U);
op_a = swap(4, 0x0F0F0F0FU);
op_a = swap(8, 0x00FF00FFU);
op_a = swap(16, 0);
}
const auto offset = SignedOperation(OperationCode::IBitfieldExtract, is_signed, op_b,
Immediate(0), Immediate(8));
const auto bits = SignedOperation(OperationCode::IBitfieldExtract, is_signed, op_b,
Immediate(8), Immediate(8));
auto result = SignedOperation(OperationCode::IBitfieldExtract, is_signed, op_a, offset, bits);
SetRegister(bb, instr.gpr0, std::move(result));
return pc;
}
} // namespace VideoCommon::Shader

45
src/video_core/shader/decode/bfi.cpp
View file

@ -1,45 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeBfi(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
const auto [packed_shift, base] = [&]() -> std::pair<Node, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::BFI_RC:
return {GetRegister(instr.gpr39),
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
case OpCode::Id::BFI_IMM_R:
return {Immediate(instr.alu.GetSignedImm20_20()), GetRegister(instr.gpr39)};
default:
UNREACHABLE();
return {Immediate(0), Immediate(0)};
}
}();
const Node insert = GetRegister(instr.gpr8);
const Node offset = BitfieldExtract(packed_shift, 0, 8);
const Node bits = BitfieldExtract(packed_shift, 8, 8);
const Node value =
Operation(OperationCode::UBitfieldInsert, PRECISE, base, insert, offset, bits);
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

321
src/video_core/shader/decode/conversion.cpp
View file

@ -1,321 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <limits>
#include <optional>
#include <utility>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Register;
namespace {
constexpr OperationCode GetFloatSelector(u64 selector) {
return selector == 0 ? OperationCode::FCastHalf0 : OperationCode::FCastHalf1;
}
constexpr u32 SizeInBits(Register::Size size) {
switch (size) {
case Register::Size::Byte:
return 8;
case Register::Size::Short:
return 16;
case Register::Size::Word:
return 32;
case Register::Size::Long:
return 64;
}
return 0;
}
constexpr std::optional<std::pair<s32, s32>> IntegerSaturateBounds(Register::Size src_size,
Register::Size dst_size,
bool src_signed,
bool dst_signed) {
const u32 dst_bits = SizeInBits(dst_size);
if (src_size == Register::Size::Word && dst_size == Register::Size::Word) {
if (src_signed == dst_signed) {
return std::nullopt;
}
return std::make_pair(0, std::numeric_limits<s32>::max());
}
if (dst_signed) {
// Signed destination, clamp to [-128, 127] for instance
return std::make_pair(-(1 << (dst_bits - 1)), (1 << (dst_bits - 1)) - 1);
} else {
// Unsigned destination
if (dst_bits == 32) {
// Avoid shifting by 32, that is undefined behavior
return std::make_pair(0, s32(std::numeric_limits<u32>::max()));
}
return std::make_pair(0, (1 << dst_bits) - 1);
}
}
} // Anonymous namespace
u32 ShaderIR::DecodeConversion(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
switch (opcode->get().GetId()) {
case OpCode::Id::I2I_R:
case OpCode::Id::I2I_C:
case OpCode::Id::I2I_IMM: {
const bool src_signed = instr.conversion.is_input_signed;
const bool dst_signed = instr.conversion.is_output_signed;
const Register::Size src_size = instr.conversion.src_size;
const Register::Size dst_size = instr.conversion.dst_size;
const u32 selector = static_cast<u32>(instr.conversion.int_src.selector);
Node value = [this, instr, opcode] {
switch (opcode->get().GetId()) {
case OpCode::Id::I2I_R:
return GetRegister(instr.gpr20);
case OpCode::Id::I2I_C:
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::I2I_IMM:
return Immediate(instr.alu.GetSignedImm20_20());
default:
UNREACHABLE();
return Immediate(0);
}
}();
// Ensure the source selector is valid
switch (instr.conversion.src_size) {
case Register::Size::Byte:
break;
case Register::Size::Short:
ASSERT(selector == 0 || selector == 2);
break;
default:
ASSERT(selector == 0);
break;
}
if (src_size != Register::Size::Word || selector != 0) {
value = SignedOperation(OperationCode::IBitfieldExtract, src_signed, std::move(value),
Immediate(selector * 8), Immediate(SizeInBits(src_size)));
}
value = GetOperandAbsNegInteger(std::move(value), instr.conversion.abs_a,
instr.conversion.negate_a, src_signed);
if (instr.alu.saturate_d) {
if (src_signed && !dst_signed) {
Node is_negative = Operation(OperationCode::LogicalUGreaterEqual, value,
Immediate(1 << (SizeInBits(src_size) - 1)));
value = Operation(OperationCode::Select, std::move(is_negative), Immediate(0),
std::move(value));
// Simplify generated expressions, this can be removed without semantic impact
SetTemporary(bb, 0, std::move(value));
value = GetTemporary(0);
if (dst_size != Register::Size::Word) {
const Node limit = Immediate((1 << SizeInBits(dst_size)) - 1);
Node is_large =
Operation(OperationCode::LogicalUGreaterThan, std::move(value), limit);
value = Operation(OperationCode::Select, std::move(is_large), limit,
std::move(value));
}
} else if (const std::optional bounds =
IntegerSaturateBounds(src_size, dst_size, src_signed, dst_signed)) {
value = SignedOperation(OperationCode::IMax, src_signed, std::move(value),
Immediate(bounds->first));
value = SignedOperation(OperationCode::IMin, src_signed, std::move(value),
Immediate(bounds->second));
}
} else if (dst_size != Register::Size::Word) {
// No saturation, we only have to mask the result
Node mask = Immediate((1 << SizeInBits(dst_size)) - 1);
value = Operation(OperationCode::UBitwiseAnd, std::move(value), std::move(mask));
}
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, std::move(value));
break;
}
case OpCode::Id::I2F_R:
case OpCode::Id::I2F_C:
case OpCode::Id::I2F_IMM: {
UNIMPLEMENTED_IF(instr.conversion.dst_size == Register::Size::Long);
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in I2F is not implemented");
Node value = [&] {
switch (opcode->get().GetId()) {
case OpCode::Id::I2F_R:
return GetRegister(instr.gpr20);
case OpCode::Id::I2F_C:
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::I2F_IMM:
return Immediate(instr.alu.GetSignedImm20_20());
default:
UNREACHABLE();
return Immediate(0);
}
}();
const bool input_signed = instr.conversion.is_input_signed;
if (const u32 offset = static_cast<u32>(instr.conversion.int_src.selector); offset > 0) {
ASSERT(instr.conversion.src_size == Register::Size::Byte ||
instr.conversion.src_size == Register::Size::Short);
if (instr.conversion.src_size == Register::Size::Short) {
ASSERT(offset == 0 || offset == 2);
}
value = SignedOperation(OperationCode::ILogicalShiftRight, input_signed,
std::move(value), Immediate(offset * 8));
}
value = ConvertIntegerSize(value, instr.conversion.src_size, input_signed);
value = GetOperandAbsNegInteger(value, instr.conversion.abs_a, false, input_signed);
value = SignedOperation(OperationCode::FCastInteger, input_signed, PRECISE, value);
value = GetOperandAbsNegFloat(value, false, instr.conversion.negate_a);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
if (instr.conversion.dst_size == Register::Size::Short) {
value = Operation(OperationCode::HCastFloat, PRECISE, value);
}
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::F2F_R:
case OpCode::Id::F2F_C:
case OpCode::Id::F2F_IMM: {
UNIMPLEMENTED_IF(instr.conversion.dst_size == Register::Size::Long);
UNIMPLEMENTED_IF(instr.conversion.src_size == Register::Size::Long);
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in F2F is not implemented");
Node value = [&]() {
switch (opcode->get().GetId()) {
case OpCode::Id::F2F_R:
return GetRegister(instr.gpr20);
case OpCode::Id::F2F_C:
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::F2F_IMM:
return GetImmediate19(instr);
default:
UNREACHABLE();
return Immediate(0);
}
}();
if (instr.conversion.src_size == Register::Size::Short) {
value = Operation(GetFloatSelector(instr.conversion.float_src.selector), NO_PRECISE,
std::move(value));
} else {
ASSERT(instr.conversion.float_src.selector == 0);
}
value = GetOperandAbsNegFloat(value, instr.conversion.abs_a, instr.conversion.negate_a);
value = [&] {
if (instr.conversion.src_size != instr.conversion.dst_size) {
// Rounding operations only matter when the source and destination conversion size
// is the same.
return value;
}
switch (instr.conversion.f2f.GetRoundingMode()) {
case Tegra::Shader::F2fRoundingOp::None:
return value;
case Tegra::Shader::F2fRoundingOp::Round:
return Operation(OperationCode::FRoundEven, value);
case Tegra::Shader::F2fRoundingOp::Floor:
return Operation(OperationCode::FFloor, value);
case Tegra::Shader::F2fRoundingOp::Ceil:
return Operation(OperationCode::FCeil, value);
case Tegra::Shader::F2fRoundingOp::Trunc:
return Operation(OperationCode::FTrunc, value);
default:
UNIMPLEMENTED_MSG("Unimplemented F2F rounding mode {}",
instr.conversion.f2f.rounding.Value());
return value;
}
}();
value = GetSaturatedFloat(value, instr.alu.saturate_d);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
if (instr.conversion.dst_size == Register::Size::Short) {
value = Operation(OperationCode::HCastFloat, PRECISE, value);
}
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::F2I_R:
case OpCode::Id::F2I_C:
case OpCode::Id::F2I_IMM: {
UNIMPLEMENTED_IF(instr.conversion.src_size == Register::Size::Long);
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in F2I is not implemented");
Node value = [&]() {
switch (opcode->get().GetId()) {
case OpCode::Id::F2I_R:
return GetRegister(instr.gpr20);
case OpCode::Id::F2I_C:
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::F2I_IMM:
return GetImmediate19(instr);
default:
UNREACHABLE();
return Immediate(0);
}
}();
if (instr.conversion.src_size == Register::Size::Short) {
value = Operation(GetFloatSelector(instr.conversion.float_src.selector), NO_PRECISE,
std::move(value));
} else {
ASSERT(instr.conversion.float_src.selector == 0);
}
value = GetOperandAbsNegFloat(value, instr.conversion.abs_a, instr.conversion.negate_a);
value = [&]() {
switch (instr.conversion.f2i.rounding) {
case Tegra::Shader::F2iRoundingOp::RoundEven:
return Operation(OperationCode::FRoundEven, PRECISE, value);
case Tegra::Shader::F2iRoundingOp::Floor:
return Operation(OperationCode::FFloor, PRECISE, value);
case Tegra::Shader::F2iRoundingOp::Ceil:
return Operation(OperationCode::FCeil, PRECISE, value);
case Tegra::Shader::F2iRoundingOp::Trunc:
return Operation(OperationCode::FTrunc, PRECISE, value);
default:
UNIMPLEMENTED_MSG("Unimplemented F2I rounding mode {}",
instr.conversion.f2i.rounding.Value());
return Immediate(0);
}
}();
const bool is_signed = instr.conversion.is_output_signed;
value = SignedOperation(OperationCode::ICastFloat, is_signed, PRECISE, value);
value = ConvertIntegerSize(value, instr.conversion.dst_size, is_signed);
SetRegister(bb, instr.gpr0, value);
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled conversion instruction: {}", opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

62
src/video_core/shader/decode/ffma.cpp
View file

@ -1,62 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeFfma(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
UNIMPLEMENTED_IF_MSG(instr.ffma.cc != 0, "FFMA cc not implemented");
if (instr.ffma.tab5980_0 != 1) {
LOG_DEBUG(HW_GPU, "FFMA tab5980_0({}) not implemented", instr.ffma.tab5980_0.Value());
}
if (instr.ffma.tab5980_1 != 0) {
LOG_DEBUG(HW_GPU, "FFMA tab5980_1({}) not implemented", instr.ffma.tab5980_1.Value());
}
const Node op_a = GetRegister(instr.gpr8);
auto [op_b, op_c] = [&]() -> std::tuple<Node, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::FFMA_CR: {
return {GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
GetRegister(instr.gpr39)};
}
case OpCode::Id::FFMA_RR:
return {GetRegister(instr.gpr20), GetRegister(instr.gpr39)};
case OpCode::Id::FFMA_RC: {
return {GetRegister(instr.gpr39),
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
}
case OpCode::Id::FFMA_IMM:
return {GetImmediate19(instr), GetRegister(instr.gpr39)};
default:
UNIMPLEMENTED_MSG("Unhandled FFMA instruction: {}", opcode->get().GetName());
return {Immediate(0), Immediate(0)};
}
}();
op_b = GetOperandAbsNegFloat(op_b, false, instr.ffma.negate_b);
op_c = GetOperandAbsNegFloat(op_c, false, instr.ffma.negate_c);
Node value = Operation(OperationCode::FFma, PRECISE, op_a, op_b, op_c);
value = GetSaturatedFloat(value, instr.alu.saturate_d);
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

58
src/video_core/shader/decode/float_set.cpp
View file

@ -1,58 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeFloatSet(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const Node op_a = GetOperandAbsNegFloat(GetRegister(instr.gpr8), instr.fset.abs_a != 0,
instr.fset.neg_a != 0);
Node op_b = [&]() {
if (instr.is_b_imm) {
return GetImmediate19(instr);
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
op_b = GetOperandAbsNegFloat(op_b, instr.fset.abs_b != 0, instr.fset.neg_b != 0);
// The fset instruction sets a register to 1.0 or -1 (depending on the bf bit) if the
// condition is true, and to 0 otherwise.
const Node second_pred = GetPredicate(instr.fset.pred39, instr.fset.neg_pred != 0);
const OperationCode combiner = GetPredicateCombiner(instr.fset.op);
const Node first_pred = GetPredicateComparisonFloat(instr.fset.cond, op_a, op_b);
const Node predicate = Operation(combiner, first_pred, second_pred);
const Node true_value = instr.fset.bf ? Immediate(1.0f) : Immediate(-1);
const Node false_value = instr.fset.bf ? Immediate(0.0f) : Immediate(0);
const Node value =
Operation(OperationCode::Select, PRECISE, predicate, true_value, false_value);
if (instr.fset.bf) {
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
} else {
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
}
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

57
src/video_core/shader/decode/float_set_predicate.cpp
View file

@ -1,57 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
u32 ShaderIR::DecodeFloatSetPredicate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
Node op_a = GetOperandAbsNegFloat(GetRegister(instr.gpr8), instr.fsetp.abs_a != 0,
instr.fsetp.neg_a != 0);
Node op_b = [&]() {
if (instr.is_b_imm) {
return GetImmediate19(instr);
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
op_b = GetOperandAbsNegFloat(std::move(op_b), instr.fsetp.abs_b, instr.fsetp.neg_b);
// We can't use the constant predicate as destination.
ASSERT(instr.fsetp.pred3 != static_cast<u64>(Pred::UnusedIndex));
const Node predicate =
GetPredicateComparisonFloat(instr.fsetp.cond, std::move(op_a), std::move(op_b));
const Node second_pred = GetPredicate(instr.fsetp.pred39, instr.fsetp.neg_pred != 0);
const OperationCode combiner = GetPredicateCombiner(instr.fsetp.op);
const Node value = Operation(combiner, predicate, second_pred);
// Set the primary predicate to the result of Predicate OP SecondPredicate
SetPredicate(bb, instr.fsetp.pred3, value);
if (instr.fsetp.pred0 != static_cast<u64>(Pred::UnusedIndex)) {
// Set the secondary predicate to the result of !Predicate OP SecondPredicate,
// if enabled
const Node negated_pred = Operation(OperationCode::LogicalNegate, predicate);
const Node second_value = Operation(combiner, negated_pred, second_pred);
SetPredicate(bb, instr.fsetp.pred0, second_value);
}
return pc;
}
} // namespace VideoCommon::Shader

115
src/video_core/shader/decode/half_set.cpp
View file

@ -1,115 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <array>
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::PredCondition;
u32 ShaderIR::DecodeHalfSet(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
PredCondition cond{};
bool bf = false;
bool ftz = false;
bool neg_a = false;
bool abs_a = false;
bool neg_b = false;
bool abs_b = false;
switch (opcode->get().GetId()) {
case OpCode::Id::HSET2_C:
case OpCode::Id::HSET2_IMM:
cond = instr.hsetp2.cbuf_and_imm.cond;
bf = instr.Bit(53);
ftz = instr.Bit(54);
neg_a = instr.Bit(43);
abs_a = instr.Bit(44);
neg_b = instr.Bit(56);
abs_b = instr.Bit(54);
break;
case OpCode::Id::HSET2_R:
cond = instr.hsetp2.reg.cond;
bf = instr.Bit(49);
ftz = instr.Bit(50);
neg_a = instr.Bit(43);
abs_a = instr.Bit(44);
neg_b = instr.Bit(31);
abs_b = instr.Bit(30);
break;
default:
UNREACHABLE();
}
Node op_b = [this, instr, opcode] {
switch (opcode->get().GetId()) {
case OpCode::Id::HSET2_C:
// Inform as unimplemented as this is not tested.
UNIMPLEMENTED_MSG("HSET2_C is not implemented");
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
case OpCode::Id::HSET2_R:
return GetRegister(instr.gpr20);
case OpCode::Id::HSET2_IMM:
return UnpackHalfImmediate(instr, true);
default:
UNREACHABLE();
return Node{};
}
}();
if (!ftz) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
Node op_a = UnpackHalfFloat(GetRegister(instr.gpr8), instr.hset2.type_a);
op_a = GetOperandAbsNegHalf(op_a, abs_a, neg_a);
switch (opcode->get().GetId()) {
case OpCode::Id::HSET2_R:
op_b = GetOperandAbsNegHalf(move(op_b), abs_b, neg_b);
[[fallthrough]];
case OpCode::Id::HSET2_C:
op_b = UnpackHalfFloat(move(op_b), instr.hset2.type_b);
break;
default:
break;
}
Node second_pred = GetPredicate(instr.hset2.pred39, instr.hset2.neg_pred);
Node comparison_pair = GetPredicateComparisonHalf(cond, op_a, op_b);
const OperationCode combiner = GetPredicateCombiner(instr.hset2.op);
// HSET2 operates on each half float in the pack.
std::array<Node, 2> values;
for (u32 i = 0; i < 2; ++i) {
const u32 raw_value = bf ? 0x3c00 : 0xffff;
Node true_value = Immediate(raw_value << (i * 16));
Node false_value = Immediate(0);
Node comparison = Operation(OperationCode::LogicalPick2, comparison_pair, Immediate(i));
Node predicate = Operation(combiner, comparison, second_pred);
values[i] =
Operation(OperationCode::Select, predicate, move(true_value), move(false_value));
}
Node value = Operation(OperationCode::UBitwiseOr, values[0], values[1]);
SetRegister(bb, instr.gpr0, move(value));
return pc;
}
} // namespace VideoCommon::Shader

80
src/video_core/shader/decode/half_set_predicate.cpp
View file

@ -1,80 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
u32 ShaderIR::DecodeHalfSetPredicate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
if (instr.hsetp2.ftz != 0) {
LOG_DEBUG(HW_GPU, "{} without FTZ is not implemented", opcode->get().GetName());
}
Node op_a = UnpackHalfFloat(GetRegister(instr.gpr8), instr.hsetp2.type_a);
op_a = GetOperandAbsNegHalf(op_a, instr.hsetp2.abs_a, instr.hsetp2.negate_a);
Tegra::Shader::PredCondition cond{};
bool h_and{};
Node op_b{};
switch (opcode->get().GetId()) {
case OpCode::Id::HSETP2_C:
cond = instr.hsetp2.cbuf_and_imm.cond;
h_and = instr.hsetp2.cbuf_and_imm.h_and;
op_b = GetOperandAbsNegHalf(GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
instr.hsetp2.cbuf.abs_b, instr.hsetp2.cbuf.negate_b);
// F32 is hardcoded in hardware
op_b = UnpackHalfFloat(std::move(op_b), Tegra::Shader::HalfType::F32);
break;
case OpCode::Id::HSETP2_IMM:
cond = instr.hsetp2.cbuf_and_imm.cond;
h_and = instr.hsetp2.cbuf_and_imm.h_and;
op_b = UnpackHalfImmediate(instr, true);
break;
case OpCode::Id::HSETP2_R:
cond = instr.hsetp2.reg.cond;
h_and = instr.hsetp2.reg.h_and;
op_b =
GetOperandAbsNegHalf(UnpackHalfFloat(GetRegister(instr.gpr20), instr.hsetp2.reg.type_b),
instr.hsetp2.reg.abs_b, instr.hsetp2.reg.negate_b);
break;
default:
UNREACHABLE();
op_b = Immediate(0);
}
const OperationCode combiner = GetPredicateCombiner(instr.hsetp2.op);
const Node combined_pred = GetPredicate(instr.hsetp2.pred39, instr.hsetp2.neg_pred);
const auto Write = [&](u64 dest, Node src) {
SetPredicate(bb, dest, Operation(combiner, std::move(src), combined_pred));
};
const Node comparison = GetPredicateComparisonHalf(cond, op_a, op_b);
const u64 first = instr.hsetp2.pred3;
const u64 second = instr.hsetp2.pred0;
if (h_and) {
Node joined = Operation(OperationCode::LogicalAnd2, comparison);
Write(first, joined);
Write(second, Operation(OperationCode::LogicalNegate, std::move(joined)));
} else {
Write(first, Operation(OperationCode::LogicalPick2, comparison, Immediate(0U)));
Write(second, Operation(OperationCode::LogicalPick2, comparison, Immediate(1U)));
}
return pc;
}
} // namespace VideoCommon::Shader

73
src/video_core/shader/decode/hfma2.cpp
View file

@ -1,73 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <tuple>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::HalfPrecision;
using Tegra::Shader::HalfType;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeHfma2(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
if (opcode->get().GetId() == OpCode::Id::HFMA2_RR) {
DEBUG_ASSERT(instr.hfma2.rr.precision == HalfPrecision::None);
} else {
DEBUG_ASSERT(instr.hfma2.precision == HalfPrecision::None);
}
constexpr auto identity = HalfType::H0_H1;
bool neg_b{}, neg_c{};
auto [saturate, type_b, op_b, type_c,
op_c] = [&]() -> std::tuple<bool, HalfType, Node, HalfType, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::HFMA2_CR:
neg_b = instr.hfma2.negate_b;
neg_c = instr.hfma2.negate_c;
return {instr.hfma2.saturate, HalfType::F32,
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
instr.hfma2.type_reg39, GetRegister(instr.gpr39)};
case OpCode::Id::HFMA2_RC:
neg_b = instr.hfma2.negate_b;
neg_c = instr.hfma2.negate_c;
return {instr.hfma2.saturate, instr.hfma2.type_reg39, GetRegister(instr.gpr39),
HalfType::F32, GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
case OpCode::Id::HFMA2_RR:
neg_b = instr.hfma2.rr.negate_b;
neg_c = instr.hfma2.rr.negate_c;
return {instr.hfma2.rr.saturate, instr.hfma2.type_b, GetRegister(instr.gpr20),
instr.hfma2.rr.type_c, GetRegister(instr.gpr39)};
case OpCode::Id::HFMA2_IMM_R:
neg_c = instr.hfma2.negate_c;
return {instr.hfma2.saturate, identity, UnpackHalfImmediate(instr, true),
instr.hfma2.type_reg39, GetRegister(instr.gpr39)};
default:
return {false, identity, Immediate(0), identity, Immediate(0)};
}
}();
const Node op_a = UnpackHalfFloat(GetRegister(instr.gpr8), instr.hfma2.type_a);
op_b = GetOperandAbsNegHalf(UnpackHalfFloat(op_b, type_b), false, neg_b);
op_c = GetOperandAbsNegHalf(UnpackHalfFloat(op_c, type_c), false, neg_c);
Node value = Operation(OperationCode::HFma, PRECISE, op_a, op_b, op_c);
value = GetSaturatedHalfFloat(value, saturate);
value = HalfMerge(GetRegister(instr.gpr0), value, instr.hfma2.merge);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

536
src/video_core/shader/decode/image.cpp
View file

@ -1,536 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <vector>
#include <fmt/format.h>
#include "common/assert.h"
#include "common/bit_field.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
#include "video_core/textures/texture.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::PredCondition;
using Tegra::Shader::StoreType;
using Tegra::Texture::ComponentType;
using Tegra::Texture::TextureFormat;
using Tegra::Texture::TICEntry;
namespace {
ComponentType GetComponentType(Tegra::Engines::SamplerDescriptor descriptor,
std::size_t component) {
const TextureFormat format{descriptor.format};
switch (format) {
case TextureFormat::R16G16B16A16:
case TextureFormat::R32G32B32A32:
case TextureFormat::R32G32B32:
case TextureFormat::R32G32:
case TextureFormat::R16G16:
case TextureFormat::R32:
case TextureFormat::R16:
case TextureFormat::R8:
case TextureFormat::R1:
if (component == 0) {
return descriptor.r_type;
}
if (component == 1) {
return descriptor.g_type;
}
if (component == 2) {
return descriptor.b_type;
}
if (component == 3) {
return descriptor.a_type;
}
break;
case TextureFormat::A8R8G8B8:
if (component == 0) {
return descriptor.a_type;
}
if (component == 1) {
return descriptor.r_type;
}
if (component == 2) {
return descriptor.g_type;
}
if (component == 3) {
return descriptor.b_type;
}
break;
case TextureFormat::A2B10G10R10:
case TextureFormat::A4B4G4R4:
case TextureFormat::A5B5G5R1:
case TextureFormat::A1B5G5R5:
if (component == 0) {
return descriptor.a_type;
}
if (component == 1) {
return descriptor.b_type;
}
if (component == 2) {
return descriptor.g_type;
}
if (component == 3) {
return descriptor.r_type;
}
break;
case TextureFormat::R32_B24G8:
if (component == 0) {
return descriptor.r_type;
}
if (component == 1) {
return descriptor.b_type;
}
if (component == 2) {
return descriptor.g_type;
}
break;
case TextureFormat::B5G6R5:
case TextureFormat::B6G5R5:
case TextureFormat::B10G11R11:
if (component == 0) {
return descriptor.b_type;
}
if (component == 1) {
return descriptor.g_type;
}
if (component == 2) {
return descriptor.r_type;
}
break;
case TextureFormat::R24G8:
case TextureFormat::R8G24:
case TextureFormat::R8G8:
case TextureFormat::G4R4:
if (component == 0) {
return descriptor.g_type;
}
if (component == 1) {
return descriptor.r_type;
}
break;
default:
break;
}
UNIMPLEMENTED_MSG("Texture format not implemented={}", format);
return ComponentType::FLOAT;
}
bool IsComponentEnabled(std::size_t component_mask, std::size_t component) {
constexpr u8 R = 0b0001;
constexpr u8 G = 0b0010;
constexpr u8 B = 0b0100;
constexpr u8 A = 0b1000;
constexpr std::array<u8, 16> mask = {
0, (R), (G), (R | G), (B), (R | B), (G | B), (R | G | B),
(A), (R | A), (G | A), (R | G | A), (B | A), (R | B | A), (G | B | A), (R | G | B | A)};
return std::bitset<4>{mask.at(component_mask)}.test(component);
}
u32 GetComponentSize(TextureFormat format, std::size_t component) {
switch (format) {
case TextureFormat::R32G32B32A32:
return 32;
case TextureFormat::R16G16B16A16:
return 16;
case TextureFormat::R32G32B32:
return component <= 2 ? 32 : 0;
case TextureFormat::R32G32:
return component <= 1 ? 32 : 0;
case TextureFormat::R16G16:
return component <= 1 ? 16 : 0;
case TextureFormat::R32:
return component == 0 ? 32 : 0;
case TextureFormat::R16:
return component == 0 ? 16 : 0;
case TextureFormat::R8:
return component == 0 ? 8 : 0;
case TextureFormat::R1:
return component == 0 ? 1 : 0;
case TextureFormat::A8R8G8B8:
return 8;
case TextureFormat::A2B10G10R10:
return (component == 3 || component == 2 || component == 1) ? 10 : 2;
case TextureFormat::A4B4G4R4:
return 4;
case TextureFormat::A5B5G5R1:
return (component == 0 || component == 1 || component == 2) ? 5 : 1;
case TextureFormat::A1B5G5R5:
return (component == 1 || component == 2 || component == 3) ? 5 : 1;
case TextureFormat::R32_B24G8:
if (component == 0) {
return 32;
}
if (component == 1) {
return 24;
}
if (component == 2) {
return 8;
}
return 0;
case TextureFormat::B5G6R5:
if (component == 0 || component == 2) {
return 5;
}
if (component == 1) {
return 6;
}
return 0;
case TextureFormat::B6G5R5:
if (component == 1 || component == 2) {
return 5;
}
if (component == 0) {
return 6;
}
return 0;
case TextureFormat::B10G11R11:
if (component == 1 || component == 2) {
return 11;
}
if (component == 0) {
return 10;
}
return 0;
case TextureFormat::R24G8:
if (component == 0) {
return 8;
}
if (component == 1) {
return 24;
}
return 0;
case TextureFormat::R8G24:
if (component == 0) {
return 24;
}
if (component == 1) {
return 8;
}
return 0;
case TextureFormat::R8G8:
return (component == 0 || component == 1) ? 8 : 0;
case TextureFormat::G4R4:
return (component == 0 || component == 1) ? 4 : 0;
default:
UNIMPLEMENTED_MSG("Texture format not implemented={}", format);
return 0;
}
}
std::size_t GetImageComponentMask(TextureFormat format) {
constexpr u8 R = 0b0001;
constexpr u8 G = 0b0010;
constexpr u8 B = 0b0100;
constexpr u8 A = 0b1000;
switch (format) {
case TextureFormat::R32G32B32A32:
case TextureFormat::R16G16B16A16:
case TextureFormat::A8R8G8B8:
case TextureFormat::A2B10G10R10:
case TextureFormat::A4B4G4R4:
case TextureFormat::A5B5G5R1:
case TextureFormat::A1B5G5R5:
return std::size_t{R | G | B | A};
case TextureFormat::R32G32B32:
case TextureFormat::R32_B24G8:
case TextureFormat::B5G6R5:
case TextureFormat::B6G5R5:
case TextureFormat::B10G11R11:
return std::size_t{R | G | B};
case TextureFormat::R32G32:
case TextureFormat::R16G16:
case TextureFormat::R24G8:
case TextureFormat::R8G24:
case TextureFormat::R8G8:
case TextureFormat::G4R4:
return std::size_t{R | G};
case TextureFormat::R32:
case TextureFormat::R16:
case TextureFormat::R8:
case TextureFormat::R1:
return std::size_t{R};
default:
UNIMPLEMENTED_MSG("Texture format not implemented={}", format);
return std::size_t{R | G | B | A};
}
}
std::size_t GetImageTypeNumCoordinates(Tegra::Shader::ImageType image_type) {
switch (image_type) {
case Tegra::Shader::ImageType::Texture1D:
case Tegra::Shader::ImageType::TextureBuffer:
return 1;
case Tegra::Shader::ImageType::Texture1DArray:
case Tegra::Shader::ImageType::Texture2D:
return 2;
case Tegra::Shader::ImageType::Texture2DArray:
case Tegra::Shader::ImageType::Texture3D:
return 3;
}
UNREACHABLE();
return 1;
}
} // Anonymous namespace
std::pair<Node, bool> ShaderIR::GetComponentValue(ComponentType component_type, u32 component_size,
Node original_value) {
switch (component_type) {
case ComponentType::SNORM: {
// range [-1.0, 1.0]
auto cnv_value = Operation(OperationCode::FMul, original_value,
Immediate(static_cast<float>(1 << component_size) / 2.f - 1.f));
cnv_value = Operation(OperationCode::ICastFloat, std::move(cnv_value));
return {BitfieldExtract(std::move(cnv_value), 0, component_size), true};
}
case ComponentType::SINT:
case ComponentType::UNORM: {
bool is_signed = component_type == ComponentType::SINT;
// range [0.0, 1.0]
auto cnv_value = Operation(OperationCode::FMul, original_value,
Immediate(static_cast<float>(1 << component_size) - 1.f));
return {SignedOperation(OperationCode::ICastFloat, is_signed, std::move(cnv_value)),
is_signed};
}
case ComponentType::UINT: // range [0, (1 << component_size) - 1]
return {std::move(original_value), false};
case ComponentType::FLOAT:
if (component_size == 16) {
return {Operation(OperationCode::HCastFloat, original_value), true};
} else {
return {std::move(original_value), true};
}
default:
UNIMPLEMENTED_MSG("Unimplemented component type={}", component_type);
return {std::move(original_value), true};
}
}
u32 ShaderIR::DecodeImage(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
const auto GetCoordinates = [this, instr](Tegra::Shader::ImageType image_type) {
std::vector<Node> coords;
const std::size_t num_coords{GetImageTypeNumCoordinates(image_type)};
coords.reserve(num_coords);
for (std::size_t i = 0; i < num_coords; ++i) {
coords.push_back(GetRegister(instr.gpr8.Value() + i));
}
return coords;
};
switch (opcode->get().GetId()) {
case OpCode::Id::SULD: {
UNIMPLEMENTED_IF(instr.suldst.out_of_bounds_store !=
Tegra::Shader::OutOfBoundsStore::Ignore);
const auto type{instr.suldst.image_type};
auto& image{instr.suldst.is_immediate ? GetImage(instr.image, type)
: GetBindlessImage(instr.gpr39, type)};
image.MarkRead();
if (instr.suldst.mode == Tegra::Shader::SurfaceDataMode::P) {
u32 indexer = 0;
for (u32 element = 0; element < 4; ++element) {
if (!instr.suldst.IsComponentEnabled(element)) {
continue;
}
MetaImage meta{image, {}, element};
Node value = Operation(OperationCode::ImageLoad, meta, GetCoordinates(type));
SetTemporary(bb, indexer++, std::move(value));
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
} else if (instr.suldst.mode == Tegra::Shader::SurfaceDataMode::D_BA) {
UNIMPLEMENTED_IF(instr.suldst.GetStoreDataLayout() != StoreType::Bits32 &&
instr.suldst.GetStoreDataLayout() != StoreType::Bits64);
auto descriptor = [this, instr] {
std::optional<Tegra::Engines::SamplerDescriptor> sampler_descriptor;
if (instr.suldst.is_immediate) {
sampler_descriptor =
registry.ObtainBoundSampler(static_cast<u32>(instr.image.index.Value()));
} else {
const Node image_register = GetRegister(instr.gpr39);
const auto result = TrackCbuf(image_register, global_code,
static_cast<s64>(global_code.size()));
const auto buffer = std::get<1>(result);
const auto offset = std::get<2>(result);
sampler_descriptor = registry.ObtainBindlessSampler(buffer, offset);
}
if (!sampler_descriptor) {
UNREACHABLE_MSG("Failed to obtain image descriptor");
}
return *sampler_descriptor;
}();
const auto comp_mask = GetImageComponentMask(descriptor.format);
switch (instr.suldst.GetStoreDataLayout()) {
case StoreType::Bits32:
case StoreType::Bits64: {
u32 indexer = 0;
u32 shifted_counter = 0;
Node value = Immediate(0);
for (u32 element = 0; element < 4; ++element) {
if (!IsComponentEnabled(comp_mask, element)) {
continue;
}
const auto component_type = GetComponentType(descriptor, element);
const auto component_size = GetComponentSize(descriptor.format, element);
MetaImage meta{image, {}, element};
auto [converted_value, is_signed] = GetComponentValue(
component_type, component_size,
Operation(OperationCode::ImageLoad, meta, GetCoordinates(type)));
// shift element to correct position
const auto shifted = shifted_counter;
if (shifted > 0) {
converted_value =
SignedOperation(OperationCode::ILogicalShiftLeft, is_signed,
std::move(converted_value), Immediate(shifted));
}
shifted_counter += component_size;
// add value into result
value = Operation(OperationCode::UBitwiseOr, value, std::move(converted_value));
// if we shifted enough for 1 byte -> we save it into temp
if (shifted_counter >= 32) {
SetTemporary(bb, indexer++, std::move(value));
// reset counter and value to prepare pack next byte
value = Immediate(0);
shifted_counter = 0;
}
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
default:
UNREACHABLE();
break;
}
}
break;
}
case OpCode::Id::SUST: {
UNIMPLEMENTED_IF(instr.suldst.mode != Tegra::Shader::SurfaceDataMode::P);
UNIMPLEMENTED_IF(instr.suldst.out_of_bounds_store !=
Tegra::Shader::OutOfBoundsStore::Ignore);
UNIMPLEMENTED_IF(instr.suldst.component_mask_selector != 0xf); // Ensure we have RGBA
std::vector<Node> values;
constexpr std::size_t hardcoded_size{4};
for (std::size_t i = 0; i < hardcoded_size; ++i) {
values.push_back(GetRegister(instr.gpr0.Value() + i));
}
const auto type{instr.suldst.image_type};
auto& image{instr.suldst.is_immediate ? GetImage(instr.image, type)
: GetBindlessImage(instr.gpr39, type)};
image.MarkWrite();
MetaImage meta{image, std::move(values)};
bb.push_back(Operation(OperationCode::ImageStore, meta, GetCoordinates(type)));
break;
}
case OpCode::Id::SUATOM: {
UNIMPLEMENTED_IF(instr.suatom_d.is_ba != 0);
const OperationCode operation_code = [instr] {
switch (instr.suatom_d.operation_type) {
case Tegra::Shader::ImageAtomicOperationType::S32:
case Tegra::Shader::ImageAtomicOperationType::U32:
switch (instr.suatom_d.operation) {
case Tegra::Shader::ImageAtomicOperation::Add:
return OperationCode::AtomicImageAdd;
case Tegra::Shader::ImageAtomicOperation::And:
return OperationCode::AtomicImageAnd;
case Tegra::Shader::ImageAtomicOperation::Or:
return OperationCode::AtomicImageOr;
case Tegra::Shader::ImageAtomicOperation::Xor:
return OperationCode::AtomicImageXor;
case Tegra::Shader::ImageAtomicOperation::Exch:
return OperationCode::AtomicImageExchange;
default:
break;
}
break;
default:
break;
}
UNIMPLEMENTED_MSG("Unimplemented operation={}, type={}",
static_cast<u64>(instr.suatom_d.operation.Value()),
static_cast<u64>(instr.suatom_d.operation_type.Value()));
return OperationCode::AtomicImageAdd;
}();
Node value = GetRegister(instr.gpr0);
const auto type = instr.suatom_d.image_type;
auto& image = GetImage(instr.image, type);
image.MarkAtomic();
MetaImage meta{image, {std::move(value)}};
SetRegister(bb, instr.gpr0, Operation(operation_code, meta, GetCoordinates(type)));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled image instruction: {}", opcode->get().GetName());
}
return pc;
}
ImageEntry& ShaderIR::GetImage(Tegra::Shader::Image image, Tegra::Shader::ImageType type) {
const auto offset = static_cast<u32>(image.index.Value());
const auto it =
std::find_if(std::begin(used_images), std::end(used_images),
[offset](const ImageEntry& entry) { return entry.offset == offset; });
if (it != std::end(used_images)) {
ASSERT(!it->is_bindless && it->type == type);
return *it;
}
const auto next_index = static_cast<u32>(used_images.size());
return used_images.emplace_back(next_index, offset, type);
}
ImageEntry& ShaderIR::GetBindlessImage(Tegra::Shader::Register reg, Tegra::Shader::ImageType type) {
const Node image_register = GetRegister(reg);
const auto result =
TrackCbuf(image_register, global_code, static_cast<s64>(global_code.size()));
const auto buffer = std::get<1>(result);
const auto offset = std::get<2>(result);
const auto it = std::find_if(std::begin(used_images), std::end(used_images),
[buffer, offset](const ImageEntry& entry) {
return entry.buffer == buffer && entry.offset == offset;
});
if (it != std::end(used_images)) {
ASSERT(it->is_bindless && it->type == type);
return *it;
}
const auto next_index = static_cast<u32>(used_images.size());
return used_images.emplace_back(next_index, offset, buffer, type);
}
} // namespace VideoCommon::Shader

49
src/video_core/shader/decode/integer_set.cpp
View file

@ -1,49 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodeIntegerSet(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const Node op_a = GetRegister(instr.gpr8);
const Node op_b = [&]() {
if (instr.is_b_imm) {
return Immediate(instr.alu.GetSignedImm20_20());
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
// The iset instruction sets a register to 1.0 or -1 (depending on the bf bit) if the condition
// is true, and to 0 otherwise.
const Node second_pred = GetPredicate(instr.iset.pred39, instr.iset.neg_pred != 0);
const Node first_pred =
GetPredicateComparisonInteger(instr.iset.cond, instr.iset.is_signed, op_a, op_b);
const OperationCode combiner = GetPredicateCombiner(instr.iset.op);
const Node predicate = Operation(combiner, first_pred, second_pred);
const Node true_value = instr.iset.bf ? Immediate(1.0f) : Immediate(-1);
const Node false_value = instr.iset.bf ? Immediate(0.0f) : Immediate(0);
const Node value =
Operation(OperationCode::Select, PRECISE, predicate, true_value, false_value);
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

53
src/video_core/shader/decode/integer_set_predicate.cpp
View file

@ -1,53 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
u32 ShaderIR::DecodeIntegerSetPredicate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const Node op_a = GetRegister(instr.gpr8);
const Node op_b = [&]() {
if (instr.is_b_imm) {
return Immediate(instr.alu.GetSignedImm20_20());
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
// We can't use the constant predicate as destination.
ASSERT(instr.isetp.pred3 != static_cast<u64>(Pred::UnusedIndex));
const Node second_pred = GetPredicate(instr.isetp.pred39, instr.isetp.neg_pred != 0);
const Node predicate =
GetPredicateComparisonInteger(instr.isetp.cond, instr.isetp.is_signed, op_a, op_b);
// Set the primary predicate to the result of Predicate OP SecondPredicate
const OperationCode combiner = GetPredicateCombiner(instr.isetp.op);
const Node value = Operation(combiner, predicate, second_pred);
SetPredicate(bb, instr.isetp.pred3, value);
if (instr.isetp.pred0 != static_cast<u64>(Pred::UnusedIndex)) {
// Set the secondary predicate to the result of !Predicate OP SecondPredicate, if enabled
const Node negated_pred = Operation(OperationCode::LogicalNegate, predicate);
SetPredicate(bb, instr.isetp.pred0, Operation(combiner, negated_pred, second_pred));
}
return pc;
}
} // namespace VideoCommon::Shader

493
src/video_core/shader/decode/memory.cpp
View file

@ -1,493 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <utility>
#include <vector>
#include <fmt/format.h>
#include "common/alignment.h"
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::AtomicOp;
using Tegra::Shader::AtomicType;
using Tegra::Shader::Attribute;
using Tegra::Shader::GlobalAtomicType;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Register;
using Tegra::Shader::StoreType;
namespace {
OperationCode GetAtomOperation(AtomicOp op) {
switch (op) {
case AtomicOp::Add:
return OperationCode::AtomicIAdd;
case AtomicOp::Min:
return OperationCode::AtomicIMin;
case AtomicOp::Max:
return OperationCode::AtomicIMax;
case AtomicOp::And:
return OperationCode::AtomicIAnd;
case AtomicOp::Or:
return OperationCode::AtomicIOr;
case AtomicOp::Xor:
return OperationCode::AtomicIXor;
case AtomicOp::Exch:
return OperationCode::AtomicIExchange;
default:
UNIMPLEMENTED_MSG("op={}", op);
return OperationCode::AtomicIAdd;
}
}
bool IsUnaligned(Tegra::Shader::UniformType uniform_type) {
return uniform_type == Tegra::Shader::UniformType::UnsignedByte ||
uniform_type == Tegra::Shader::UniformType::UnsignedShort;
}
u32 GetUnalignedMask(Tegra::Shader::UniformType uniform_type) {
switch (uniform_type) {
case Tegra::Shader::UniformType::UnsignedByte:
return 0b11;
case Tegra::Shader::UniformType::UnsignedShort:
return 0b10;
default:
UNREACHABLE();
return 0;
}
}
u32 GetMemorySize(Tegra::Shader::UniformType uniform_type) {
switch (uniform_type) {
case Tegra::Shader::UniformType::UnsignedByte:
return 8;
case Tegra::Shader::UniformType::UnsignedShort:
return 16;
case Tegra::Shader::UniformType::Single:
return 32;
case Tegra::Shader::UniformType::Double:
return 64;
case Tegra::Shader::UniformType::Quad:
case Tegra::Shader::UniformType::UnsignedQuad:
return 128;
default:
UNIMPLEMENTED_MSG("Unimplemented size={}!", uniform_type);
return 32;
}
}
Node ExtractUnaligned(Node value, Node address, u32 mask, u32 size) {
Node offset = Operation(OperationCode::UBitwiseAnd, address, Immediate(mask));
offset = Operation(OperationCode::ULogicalShiftLeft, move(offset), Immediate(3));
return Operation(OperationCode::UBitfieldExtract, move(value), move(offset), Immediate(size));
}
Node InsertUnaligned(Node dest, Node value, Node address, u32 mask, u32 size) {
Node offset = Operation(OperationCode::UBitwiseAnd, move(address), Immediate(mask));
offset = Operation(OperationCode::ULogicalShiftLeft, move(offset), Immediate(3));
return Operation(OperationCode::UBitfieldInsert, move(dest), move(value), move(offset),
Immediate(size));
}
Node Sign16Extend(Node value) {
Node sign = Operation(OperationCode::UBitwiseAnd, value, Immediate(1U << 15));
Node is_sign = Operation(OperationCode::LogicalUEqual, move(sign), Immediate(1U << 15));
Node extend = Operation(OperationCode::Select, is_sign, Immediate(0xFFFF0000), Immediate(0));
return Operation(OperationCode::UBitwiseOr, move(value), move(extend));
}
} // Anonymous namespace
u32 ShaderIR::DecodeMemory(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
switch (opcode->get().GetId()) {
case OpCode::Id::LD_A: {
// Note: Shouldn't this be interp mode flat? As in no interpolation made.
UNIMPLEMENTED_IF_MSG(instr.gpr8.Value() != Register::ZeroIndex,
"Indirect attribute loads are not supported");
UNIMPLEMENTED_IF_MSG((instr.attribute.fmt20.immediate.Value() % sizeof(u32)) != 0,
"Unaligned attribute loads are not supported");
UNIMPLEMENTED_IF_MSG(instr.attribute.fmt20.IsPhysical() &&
instr.attribute.fmt20.size != Tegra::Shader::AttributeSize::Word,
"Non-32 bits PHYS reads are not implemented");
const Node buffer{GetRegister(instr.gpr39)};
u64 next_element = instr.attribute.fmt20.element;
auto next_index = static_cast<u64>(instr.attribute.fmt20.index.Value());
const auto LoadNextElement = [&](u32 reg_offset) {
const Node attribute{instr.attribute.fmt20.IsPhysical()
? GetPhysicalInputAttribute(instr.gpr8, buffer)
: GetInputAttribute(static_cast<Attribute::Index>(next_index),
next_element, buffer)};
SetRegister(bb, instr.gpr0.Value() + reg_offset, attribute);
// Load the next attribute element into the following register. If the element
// to load goes beyond the vec4 size, load the first element of the next
// attribute.
next_element = (next_element + 1) % 4;
next_index = next_index + (next_element == 0 ? 1 : 0);
};
const u32 num_words = static_cast<u32>(instr.attribute.fmt20.size.Value()) + 1;
for (u32 reg_offset = 0; reg_offset < num_words; ++reg_offset) {
LoadNextElement(reg_offset);
}
break;
}
case OpCode::Id::LD_C: {
UNIMPLEMENTED_IF(instr.ld_c.unknown != 0);
Node index = GetRegister(instr.gpr8);
const Node op_a =
GetConstBufferIndirect(instr.cbuf36.index, instr.cbuf36.GetOffset() + 0, index);
switch (instr.ld_c.type.Value()) {
case Tegra::Shader::UniformType::Single:
SetRegister(bb, instr.gpr0, op_a);
break;
case Tegra::Shader::UniformType::Double: {
const Node op_b =
GetConstBufferIndirect(instr.cbuf36.index, instr.cbuf36.GetOffset() + 4, index);
SetTemporary(bb, 0, op_a);
SetTemporary(bb, 1, op_b);
SetRegister(bb, instr.gpr0, GetTemporary(0));
SetRegister(bb, instr.gpr0.Value() + 1, GetTemporary(1));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled type: {}", instr.ld_c.type.Value());
}
break;
}
case OpCode::Id::LD_L:
LOG_DEBUG(HW_GPU, "LD_L cache management mode: {}", instr.ld_l.unknown);
[[fallthrough]];
case OpCode::Id::LD_S: {
const auto GetAddress = [&](s32 offset) {
ASSERT(offset % 4 == 0);
const Node immediate_offset = Immediate(static_cast<s32>(instr.smem_imm) + offset);
return Operation(OperationCode::IAdd, GetRegister(instr.gpr8), immediate_offset);
};
const auto GetMemory = [&](s32 offset) {
return opcode->get().GetId() == OpCode::Id::LD_S ? GetSharedMemory(GetAddress(offset))
: GetLocalMemory(GetAddress(offset));
};
switch (instr.ldst_sl.type.Value()) {
case StoreType::Signed16:
SetRegister(bb, instr.gpr0,
Sign16Extend(ExtractUnaligned(GetMemory(0), GetAddress(0), 0b10, 16)));
break;
case StoreType::Bits32:
case StoreType::Bits64:
case StoreType::Bits128: {
const u32 count = [&] {
switch (instr.ldst_sl.type.Value()) {
case StoreType::Bits32:
return 1;
case StoreType::Bits64:
return 2;
case StoreType::Bits128:
return 4;
default:
UNREACHABLE();
return 0;
}
}();
for (u32 i = 0; i < count; ++i) {
SetTemporary(bb, i, GetMemory(i * 4));
}
for (u32 i = 0; i < count; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
default:
UNIMPLEMENTED_MSG("{} Unhandled type: {}", opcode->get().GetName(),
instr.ldst_sl.type.Value());
}
break;
}
case OpCode::Id::LD:
case OpCode::Id::LDG: {
const auto type = [instr, &opcode]() -> Tegra::Shader::UniformType {
switch (opcode->get().GetId()) {
case OpCode::Id::LD:
UNIMPLEMENTED_IF_MSG(!instr.generic.extended, "Unextended LD is not implemented");
return instr.generic.type;
case OpCode::Id::LDG:
return instr.ldg.type;
default:
UNREACHABLE();
return {};
}
}();
const auto [real_address_base, base_address, descriptor] =
TrackGlobalMemory(bb, instr, true, false);
const u32 size = GetMemorySize(type);
const u32 count = Common::AlignUp(size, 32) / 32;
if (!real_address_base || !base_address) {
// Tracking failed, load zeroes.
for (u32 i = 0; i < count; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, Immediate(0.0f));
}
break;
}
for (u32 i = 0; i < count; ++i) {
const Node it_offset = Immediate(i * 4);
const Node real_address = Operation(OperationCode::UAdd, real_address_base, it_offset);
Node gmem = MakeNode<GmemNode>(real_address, base_address, descriptor);
// To handle unaligned loads get the bytes used to dereference global memory and extract
// those bytes from the loaded u32.
if (IsUnaligned(type)) {
gmem = ExtractUnaligned(gmem, real_address, GetUnalignedMask(type), size);
}
SetTemporary(bb, i, gmem);
}
for (u32 i = 0; i < count; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
case OpCode::Id::ST_A: {
UNIMPLEMENTED_IF_MSG(instr.gpr8.Value() != Register::ZeroIndex,
"Indirect attribute loads are not supported");
UNIMPLEMENTED_IF_MSG((instr.attribute.fmt20.immediate.Value() % sizeof(u32)) != 0,
"Unaligned attribute loads are not supported");
u64 element = instr.attribute.fmt20.element;
auto index = static_cast<u64>(instr.attribute.fmt20.index.Value());
const u32 num_words = static_cast<u32>(instr.attribute.fmt20.size.Value()) + 1;
for (u32 reg_offset = 0; reg_offset < num_words; ++reg_offset) {
Node dest;
if (instr.attribute.fmt20.patch) {
const u32 offset = static_cast<u32>(index) * 4 + static_cast<u32>(element);
dest = MakeNode<PatchNode>(offset);
} else {
dest = GetOutputAttribute(static_cast<Attribute::Index>(index), element,
GetRegister(instr.gpr39));
}
const auto src = GetRegister(instr.gpr0.Value() + reg_offset);
bb.push_back(Operation(OperationCode::Assign, dest, src));
// Load the next attribute element into the following register. If the element to load
// goes beyond the vec4 size, load the first element of the next attribute.
element = (element + 1) % 4;
index = index + (element == 0 ? 1 : 0);
}
break;
}
case OpCode::Id::ST_L:
LOG_DEBUG(HW_GPU, "ST_L cache management mode: {}", instr.st_l.cache_management.Value());
[[fallthrough]];
case OpCode::Id::ST_S: {
const auto GetAddress = [&](s32 offset) {
ASSERT(offset % 4 == 0);
const Node immediate = Immediate(static_cast<s32>(instr.smem_imm) + offset);
return Operation(OperationCode::IAdd, NO_PRECISE, GetRegister(instr.gpr8), immediate);
};
const bool is_local = opcode->get().GetId() == OpCode::Id::ST_L;
const auto set_memory = is_local ? &ShaderIR::SetLocalMemory : &ShaderIR::SetSharedMemory;
const auto get_memory = is_local ? &ShaderIR::GetLocalMemory : &ShaderIR::GetSharedMemory;
switch (instr.ldst_sl.type.Value()) {
case StoreType::Bits128:
(this->*set_memory)(bb, GetAddress(12), GetRegister(instr.gpr0.Value() + 3));
(this->*set_memory)(bb, GetAddress(8), GetRegister(instr.gpr0.Value() + 2));
[[fallthrough]];
case StoreType::Bits64:
(this->*set_memory)(bb, GetAddress(4), GetRegister(instr.gpr0.Value() + 1));
[[fallthrough]];
case StoreType::Bits32:
(this->*set_memory)(bb, GetAddress(0), GetRegister(instr.gpr0));
break;
case StoreType::Unsigned16:
case StoreType::Signed16: {
Node address = GetAddress(0);
Node memory = (this->*get_memory)(address);
(this->*set_memory)(
bb, address, InsertUnaligned(memory, GetRegister(instr.gpr0), address, 0b10, 16));
break;
}
default:
UNIMPLEMENTED_MSG("{} unhandled type: {}", opcode->get().GetName(),
instr.ldst_sl.type.Value());
}
break;
}
case OpCode::Id::ST:
case OpCode::Id::STG: {
const auto type = [instr, &opcode]() -> Tegra::Shader::UniformType {
switch (opcode->get().GetId()) {
case OpCode::Id::ST:
UNIMPLEMENTED_IF_MSG(!instr.generic.extended, "Unextended ST is not implemented");
return instr.generic.type;
case OpCode::Id::STG:
return instr.stg.type;
default:
UNREACHABLE();
return {};
}
}();
// For unaligned reads we have to read memory too.
const bool is_read = IsUnaligned(type);
const auto [real_address_base, base_address, descriptor] =
TrackGlobalMemory(bb, instr, is_read, true);
if (!real_address_base || !base_address) {
// Tracking failed, skip the store.
break;
}
const u32 size = GetMemorySize(type);
const u32 count = Common::AlignUp(size, 32) / 32;
for (u32 i = 0; i < count; ++i) {
const Node it_offset = Immediate(i * 4);
const Node real_address = Operation(OperationCode::UAdd, real_address_base, it_offset);
const Node gmem = MakeNode<GmemNode>(real_address, base_address, descriptor);
Node value = GetRegister(instr.gpr0.Value() + i);
if (IsUnaligned(type)) {
const u32 mask = GetUnalignedMask(type);
value = InsertUnaligned(gmem, move(value), real_address, mask, size);
}
bb.push_back(Operation(OperationCode::Assign, gmem, value));
}
break;
}
case OpCode::Id::RED: {
UNIMPLEMENTED_IF_MSG(instr.red.type != GlobalAtomicType::U32, "type={}",
instr.red.type.Value());
const auto [real_address, base_address, descriptor] =
TrackGlobalMemory(bb, instr, true, true);
if (!real_address || !base_address) {
// Tracking failed, skip atomic.
break;
}
Node gmem = MakeNode<GmemNode>(real_address, base_address, descriptor);
Node value = GetRegister(instr.gpr0);
bb.push_back(Operation(GetAtomOperation(instr.red.operation), move(gmem), move(value)));
break;
}
case OpCode::Id::ATOM: {
UNIMPLEMENTED_IF_MSG(instr.atom.operation == AtomicOp::Inc ||
instr.atom.operation == AtomicOp::Dec ||
instr.atom.operation == AtomicOp::SafeAdd,
"operation={}", instr.atom.operation.Value());
UNIMPLEMENTED_IF_MSG(instr.atom.type == GlobalAtomicType::S64 ||
instr.atom.type == GlobalAtomicType::U64 ||
instr.atom.type == GlobalAtomicType::F16x2_FTZ_RN ||
instr.atom.type == GlobalAtomicType::F32_FTZ_RN,
"type={}", instr.atom.type.Value());
const auto [real_address, base_address, descriptor] =
TrackGlobalMemory(bb, instr, true, true);
if (!real_address || !base_address) {
// Tracking failed, skip atomic.
break;
}
const bool is_signed =
instr.atom.type == GlobalAtomicType::S32 || instr.atom.type == GlobalAtomicType::S64;
Node gmem = MakeNode<GmemNode>(real_address, base_address, descriptor);
SetRegister(bb, instr.gpr0,
SignedOperation(GetAtomOperation(instr.atom.operation), is_signed, gmem,
GetRegister(instr.gpr20)));
break;
}
case OpCode::Id::ATOMS: {
UNIMPLEMENTED_IF_MSG(instr.atoms.operation == AtomicOp::Inc ||
instr.atoms.operation == AtomicOp::Dec,
"operation={}", instr.atoms.operation.Value());
UNIMPLEMENTED_IF_MSG(instr.atoms.type == AtomicType::S64 ||
instr.atoms.type == AtomicType::U64,
"type={}", instr.atoms.type.Value());
const bool is_signed =
instr.atoms.type == AtomicType::S32 || instr.atoms.type == AtomicType::S64;
const s32 offset = instr.atoms.GetImmediateOffset();
Node address = GetRegister(instr.gpr8);
address = Operation(OperationCode::IAdd, move(address), Immediate(offset));
SetRegister(bb, instr.gpr0,
SignedOperation(GetAtomOperation(instr.atoms.operation), is_signed,
GetSharedMemory(move(address)), GetRegister(instr.gpr20)));
break;
}
case OpCode::Id::AL2P: {
// Ignore al2p.direction since we don't care about it.
// Calculate emulation fake physical address.
const Node fixed_address{Immediate(static_cast<u32>(instr.al2p.address))};
const Node reg{GetRegister(instr.gpr8)};
const Node fake_address{Operation(OperationCode::IAdd, NO_PRECISE, reg, fixed_address)};
// Set the fake address to target register.
SetRegister(bb, instr.gpr0, fake_address);
// Signal the shader IR to declare all possible attributes and varyings
uses_physical_attributes = true;
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled memory instruction: {}", opcode->get().GetName());
}
return pc;
}
std::tuple<Node, Node, GlobalMemoryBase> ShaderIR::TrackGlobalMemory(NodeBlock& bb,
Instruction instr,
bool is_read, bool is_write) {
const auto addr_register{GetRegister(instr.gmem.gpr)};
const auto immediate_offset{static_cast<u32>(instr.gmem.offset)};
const auto [base_address, index, offset] =
TrackCbuf(addr_register, global_code, static_cast<s64>(global_code.size()));
ASSERT_OR_EXECUTE_MSG(
base_address != nullptr, { return std::make_tuple(nullptr, nullptr, GlobalMemoryBase{}); },
"Global memory tracking failed");
bb.push_back(Comment(fmt::format("Base address is c[0x{:x}][0x{:x}]", index, offset)));
const GlobalMemoryBase descriptor{index, offset};
const auto& entry = used_global_memory.try_emplace(descriptor).first;
auto& usage = entry->second;
usage.is_written |= is_write;
usage.is_read |= is_read;
const auto real_address =
Operation(OperationCode::UAdd, NO_PRECISE, Immediate(immediate_offset), addr_register);
return {real_address, base_address, descriptor};
}
} // namespace VideoCommon::Shader

322
src/video_core/shader/decode/other.cpp
View file

@ -1,322 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::ConditionCode;
using Tegra::Shader::Instruction;
using Tegra::Shader::IpaInterpMode;
using Tegra::Shader::OpCode;
using Tegra::Shader::PixelImap;
using Tegra::Shader::Register;
using Tegra::Shader::SystemVariable;
using Index = Tegra::Shader::Attribute::Index;
u32 ShaderIR::DecodeOther(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
switch (opcode->get().GetId()) {
case OpCode::Id::NOP: {
UNIMPLEMENTED_IF(instr.nop.cc != Tegra::Shader::ConditionCode::T);
UNIMPLEMENTED_IF(instr.nop.trigger != 0);
// With the previous preconditions, this instruction is a no-operation.
break;
}
case OpCode::Id::EXIT: {
const ConditionCode cc = instr.flow_condition_code;
UNIMPLEMENTED_IF_MSG(cc != ConditionCode::T, "EXIT condition code used: {}", cc);
switch (instr.flow.cond) {
case Tegra::Shader::FlowCondition::Always:
bb.push_back(Operation(OperationCode::Exit));
if (instr.pred.pred_index == static_cast<u64>(Pred::UnusedIndex)) {
// If this is an unconditional exit then just end processing here,
// otherwise we have to account for the possibility of the condition
// not being met, so continue processing the next instruction.
pc = MAX_PROGRAM_LENGTH - 1;
}
break;
case Tegra::Shader::FlowCondition::Fcsm_Tr:
// TODO(bunnei): What is this used for? If we assume this conditon is not
// satisifed, dual vertex shaders in Farming Simulator make more sense
UNIMPLEMENTED_MSG("Skipping unknown FlowCondition::Fcsm_Tr");
break;
default:
UNIMPLEMENTED_MSG("Unhandled flow condition: {}", instr.flow.cond.Value());
}
break;
}
case OpCode::Id::KIL: {
UNIMPLEMENTED_IF(instr.flow.cond != Tegra::Shader::FlowCondition::Always);
const ConditionCode cc = instr.flow_condition_code;
UNIMPLEMENTED_IF_MSG(cc != ConditionCode::T, "KIL condition code used: {}", cc);
bb.push_back(Operation(OperationCode::Discard));
break;
}
case OpCode::Id::S2R: {
const Node value = [this, instr] {
switch (instr.sys20) {
case SystemVariable::LaneId:
return Operation(OperationCode::ThreadId);
case SystemVariable::InvocationId:
return Operation(OperationCode::InvocationId);
case SystemVariable::Ydirection:
uses_y_negate = true;
return Operation(OperationCode::YNegate);
case SystemVariable::InvocationInfo:
LOG_WARNING(HW_GPU, "S2R instruction with InvocationInfo is incomplete");
return Immediate(0x00ff'0000U);
case SystemVariable::WscaleFactorXY:
UNIMPLEMENTED_MSG("S2R WscaleFactorXY is not implemented");
return Immediate(0U);
case SystemVariable::WscaleFactorZ:
UNIMPLEMENTED_MSG("S2R WscaleFactorZ is not implemented");
return Immediate(0U);
case SystemVariable::Tid: {
Node val = Immediate(0);
val = BitfieldInsert(val, Operation(OperationCode::LocalInvocationIdX), 0, 9);
val = BitfieldInsert(val, Operation(OperationCode::LocalInvocationIdY), 16, 9);
val = BitfieldInsert(val, Operation(OperationCode::LocalInvocationIdZ), 26, 5);
return val;
}
case SystemVariable::TidX:
return Operation(OperationCode::LocalInvocationIdX);
case SystemVariable::TidY:
return Operation(OperationCode::LocalInvocationIdY);
case SystemVariable::TidZ:
return Operation(OperationCode::LocalInvocationIdZ);
case SystemVariable::CtaIdX:
return Operation(OperationCode::WorkGroupIdX);
case SystemVariable::CtaIdY:
return Operation(OperationCode::WorkGroupIdY);
case SystemVariable::CtaIdZ:
return Operation(OperationCode::WorkGroupIdZ);
case SystemVariable::EqMask:
case SystemVariable::LtMask:
case SystemVariable::LeMask:
case SystemVariable::GtMask:
case SystemVariable::GeMask:
uses_warps = true;
switch (instr.sys20) {
case SystemVariable::EqMask:
return Operation(OperationCode::ThreadEqMask);
case SystemVariable::LtMask:
return Operation(OperationCode::ThreadLtMask);
case SystemVariable::LeMask:
return Operation(OperationCode::ThreadLeMask);
case SystemVariable::GtMask:
return Operation(OperationCode::ThreadGtMask);
case SystemVariable::GeMask:
return Operation(OperationCode::ThreadGeMask);
default:
UNREACHABLE();
return Immediate(0u);
}
default:
UNIMPLEMENTED_MSG("Unhandled system move: {}", instr.sys20.Value());
return Immediate(0u);
}
}();
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::BRA: {
Node branch;
if (instr.bra.constant_buffer == 0) {
const u32 target = pc + instr.bra.GetBranchTarget();
branch = Operation(OperationCode::Branch, Immediate(target));
} else {
const u32 target = pc + 1;
const Node op_a = GetConstBuffer(instr.cbuf36.index, instr.cbuf36.GetOffset());
const Node convert = SignedOperation(OperationCode::IArithmeticShiftRight, true,
PRECISE, op_a, Immediate(3));
const Node operand =
Operation(OperationCode::IAdd, PRECISE, convert, Immediate(target));
branch = Operation(OperationCode::BranchIndirect, operand);
}
const Tegra::Shader::ConditionCode cc = instr.flow_condition_code;
if (cc != Tegra::Shader::ConditionCode::T) {
bb.push_back(Conditional(GetConditionCode(cc), {branch}));
} else {
bb.push_back(branch);
}
break;
}
case OpCode::Id::BRX: {
Node operand;
if (instr.brx.constant_buffer != 0) {
const s32 target = pc + 1;
const Node index = GetRegister(instr.gpr8);
const Node op_a =
GetConstBufferIndirect(instr.cbuf36.index, instr.cbuf36.GetOffset() + 0, index);
const Node convert = SignedOperation(OperationCode::IArithmeticShiftRight, true,
PRECISE, op_a, Immediate(3));
operand = Operation(OperationCode::IAdd, PRECISE, convert, Immediate(target));
} else {
const s32 target = pc + instr.brx.GetBranchExtend();
const Node op_a = GetRegister(instr.gpr8);
const Node convert = SignedOperation(OperationCode::IArithmeticShiftRight, true,
PRECISE, op_a, Immediate(3));
operand = Operation(OperationCode::IAdd, PRECISE, convert, Immediate(target));
}
const Node branch = Operation(OperationCode::BranchIndirect, operand);
const ConditionCode cc = instr.flow_condition_code;
if (cc != ConditionCode::T) {
bb.push_back(Conditional(GetConditionCode(cc), {branch}));
} else {
bb.push_back(branch);
}
break;
}
case OpCode::Id::SSY: {
UNIMPLEMENTED_IF_MSG(instr.bra.constant_buffer != 0,
"Constant buffer flow is not supported");
if (disable_flow_stack) {
break;
}
// The SSY opcode tells the GPU where to re-converge divergent execution paths with SYNC.
const u32 target = pc + instr.bra.GetBranchTarget();
bb.push_back(
Operation(OperationCode::PushFlowStack, MetaStackClass::Ssy, Immediate(target)));
break;
}
case OpCode::Id::PBK: {
UNIMPLEMENTED_IF_MSG(instr.bra.constant_buffer != 0,
"Constant buffer PBK is not supported");
if (disable_flow_stack) {
break;
}
// PBK pushes to a stack the address where BRK will jump to.
const u32 target = pc + instr.bra.GetBranchTarget();
bb.push_back(
Operation(OperationCode::PushFlowStack, MetaStackClass::Pbk, Immediate(target)));
break;
}
case OpCode::Id::SYNC: {
const ConditionCode cc = instr.flow_condition_code;
UNIMPLEMENTED_IF_MSG(cc != ConditionCode::T, "SYNC condition code used: {}", cc);
if (decompiled) {
break;
}
// The SYNC opcode jumps to the address previously set by the SSY opcode
bb.push_back(Operation(OperationCode::PopFlowStack, MetaStackClass::Ssy));
break;
}
case OpCode::Id::BRK: {
const ConditionCode cc = instr.flow_condition_code;
UNIMPLEMENTED_IF_MSG(cc != ConditionCode::T, "BRK condition code used: {}", cc);
if (decompiled) {
break;
}
// The BRK opcode jumps to the address previously set by the PBK opcode
bb.push_back(Operation(OperationCode::PopFlowStack, MetaStackClass::Pbk));
break;
}
case OpCode::Id::IPA: {
const bool is_physical = instr.ipa.idx && instr.gpr8.Value() != 0xff;
const auto attribute = instr.attribute.fmt28;
const Index index = attribute.index;
Node value = is_physical ? GetPhysicalInputAttribute(instr.gpr8)
: GetInputAttribute(index, attribute.element);
// Code taken from Ryujinx.
if (index >= Index::Attribute_0 && index <= Index::Attribute_31) {
const u32 location = static_cast<u32>(index) - static_cast<u32>(Index::Attribute_0);
if (header.ps.GetPixelImap(location) == PixelImap::Perspective) {
Node position_w = GetInputAttribute(Index::Position, 3);
value = Operation(OperationCode::FMul, move(value), move(position_w));
}
}
if (instr.ipa.interp_mode == IpaInterpMode::Multiply) {
value = Operation(OperationCode::FMul, move(value), GetRegister(instr.gpr20));
}
value = GetSaturatedFloat(move(value), instr.ipa.saturate);
SetRegister(bb, instr.gpr0, move(value));
break;
}
case OpCode::Id::OUT_R: {
UNIMPLEMENTED_IF_MSG(instr.gpr20.Value() != Register::ZeroIndex,
"Stream buffer is not supported");
if (instr.out.emit) {
// gpr0 is used to store the next address and gpr8 contains the address to emit.
// Hardware uses pointers here but we just ignore it
bb.push_back(Operation(OperationCode::EmitVertex));
SetRegister(bb, instr.gpr0, Immediate(0));
}
if (instr.out.cut) {
bb.push_back(Operation(OperationCode::EndPrimitive));
}
break;
}
case OpCode::Id::ISBERD: {
UNIMPLEMENTED_IF(instr.isberd.o != 0);
UNIMPLEMENTED_IF(instr.isberd.skew != 0);
UNIMPLEMENTED_IF(instr.isberd.shift != Tegra::Shader::IsberdShift::None);
UNIMPLEMENTED_IF(instr.isberd.mode != Tegra::Shader::IsberdMode::None);
LOG_WARNING(HW_GPU, "ISBERD instruction is incomplete");
SetRegister(bb, instr.gpr0, GetRegister(instr.gpr8));
break;
}
case OpCode::Id::BAR: {
UNIMPLEMENTED_IF_MSG(instr.value != 0xF0A81B8000070000ULL, "BAR is not BAR.SYNC 0x0");
bb.push_back(Operation(OperationCode::Barrier));
break;
}
case OpCode::Id::MEMBAR: {
UNIMPLEMENTED_IF(instr.membar.unknown != Tegra::Shader::MembarUnknown::Default);
const OperationCode type = [instr] {
switch (instr.membar.type) {
case Tegra::Shader::MembarType::CTA:
return OperationCode::MemoryBarrierGroup;
case Tegra::Shader::MembarType::GL:
return OperationCode::MemoryBarrierGlobal;
default:
UNIMPLEMENTED_MSG("MEMBAR type={}", instr.membar.type.Value());
return OperationCode::MemoryBarrierGlobal;
}
}();
bb.push_back(Operation(type));
break;
}
case OpCode::Id::DEPBAR: {
LOG_DEBUG(HW_GPU, "DEPBAR instruction is stubbed");
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled instruction: {}", opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

68
src/video_core/shader/decode/predicate_set_predicate.cpp
View file

@ -1,68 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
u32 ShaderIR::DecodePredicateSetPredicate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
switch (opcode->get().GetId()) {
case OpCode::Id::PSETP: {
const Node op_a = GetPredicate(instr.psetp.pred12, instr.psetp.neg_pred12 != 0);
const Node op_b = GetPredicate(instr.psetp.pred29, instr.psetp.neg_pred29 != 0);
// We can't use the constant predicate as destination.
ASSERT(instr.psetp.pred3 != static_cast<u64>(Pred::UnusedIndex));
const Node second_pred = GetPredicate(instr.psetp.pred39, instr.psetp.neg_pred39 != 0);
const OperationCode combiner = GetPredicateCombiner(instr.psetp.op);
const Node predicate = Operation(combiner, op_a, op_b);
// Set the primary predicate to the result of Predicate OP SecondPredicate
SetPredicate(bb, instr.psetp.pred3, Operation(combiner, predicate, second_pred));
if (instr.psetp.pred0 != static_cast<u64>(Pred::UnusedIndex)) {
// Set the secondary predicate to the result of !Predicate OP SecondPredicate, if
// enabled
SetPredicate(bb, instr.psetp.pred0,
Operation(combiner, Operation(OperationCode::LogicalNegate, predicate),
second_pred));
}
break;
}
case OpCode::Id::CSETP: {
const Node pred = GetPredicate(instr.csetp.pred39, instr.csetp.neg_pred39 != 0);
const Node condition_code = GetConditionCode(instr.csetp.cc);
const OperationCode combiner = GetPredicateCombiner(instr.csetp.op);
if (instr.csetp.pred3 != static_cast<u64>(Pred::UnusedIndex)) {
SetPredicate(bb, instr.csetp.pred3, Operation(combiner, condition_code, pred));
}
if (instr.csetp.pred0 != static_cast<u64>(Pred::UnusedIndex)) {
const Node neg_cc = Operation(OperationCode::LogicalNegate, condition_code);
SetPredicate(bb, instr.csetp.pred0, Operation(combiner, neg_cc, pred));
}
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled predicate instruction: {}", opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

46
src/video_core/shader/decode/predicate_set_register.cpp
View file

@ -1,46 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
u32 ShaderIR::DecodePredicateSetRegister(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in PSET is not implemented");
const Node op_a = GetPredicate(instr.pset.pred12, instr.pset.neg_pred12 != 0);
const Node op_b = GetPredicate(instr.pset.pred29, instr.pset.neg_pred29 != 0);
const Node first_pred = Operation(GetPredicateCombiner(instr.pset.cond), op_a, op_b);
const Node second_pred = GetPredicate(instr.pset.pred39, instr.pset.neg_pred39 != 0);
const OperationCode combiner = GetPredicateCombiner(instr.pset.op);
const Node predicate = Operation(combiner, first_pred, second_pred);
const Node true_value = instr.pset.bf ? Immediate(1.0f) : Immediate(0xffffffff);
const Node false_value = instr.pset.bf ? Immediate(0.0f) : Immediate(0);
const Node value =
Operation(OperationCode::Select, PRECISE, predicate, true_value, false_value);
if (instr.pset.bf) {
SetInternalFlagsFromFloat(bb, value, instr.generates_cc);
} else {
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
}
SetRegister(bb, instr.gpr0, value);
return pc;
}
} // namespace VideoCommon::Shader

86
src/video_core/shader/decode/register_set_predicate.cpp
View file

@ -1,86 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <utility>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
namespace {
constexpr u64 NUM_CONDITION_CODES = 4;
constexpr u64 NUM_PREDICATES = 7;
} // namespace
u32 ShaderIR::DecodeRegisterSetPredicate(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node apply_mask = [this, opcode, instr] {
switch (opcode->get().GetId()) {
case OpCode::Id::R2P_IMM:
case OpCode::Id::P2R_IMM:
return Immediate(static_cast<u32>(instr.p2r_r2p.immediate_mask));
default:
UNREACHABLE();
return Immediate(0);
}
}();
const u32 offset = static_cast<u32>(instr.p2r_r2p.byte) * 8;
const bool cc = instr.p2r_r2p.mode == Tegra::Shader::R2pMode::Cc;
const u64 num_entries = cc ? NUM_CONDITION_CODES : NUM_PREDICATES;
const auto get_entry = [this, cc](u64 entry) {
return cc ? GetInternalFlag(static_cast<InternalFlag>(entry)) : GetPredicate(entry);
};
switch (opcode->get().GetId()) {
case OpCode::Id::R2P_IMM: {
Node mask = GetRegister(instr.gpr8);
for (u64 entry = 0; entry < num_entries; ++entry) {
const u32 shift = static_cast<u32>(entry);
Node apply = BitfieldExtract(apply_mask, shift, 1);
Node condition = Operation(OperationCode::LogicalUNotEqual, apply, Immediate(0));
Node compare = BitfieldExtract(mask, offset + shift, 1);
Node value = Operation(OperationCode::LogicalUNotEqual, move(compare), Immediate(0));
Node code = Operation(OperationCode::LogicalAssign, get_entry(entry), move(value));
bb.push_back(Conditional(condition, {move(code)}));
}
break;
}
case OpCode::Id::P2R_IMM: {
Node value = Immediate(0);
for (u64 entry = 0; entry < num_entries; ++entry) {
Node bit = Operation(OperationCode::Select, get_entry(entry), Immediate(1U << entry),
Immediate(0));
value = Operation(OperationCode::UBitwiseOr, move(value), move(bit));
}
value = Operation(OperationCode::UBitwiseAnd, move(value), apply_mask);
value = BitfieldInsert(GetRegister(instr.gpr8), move(value), offset, 8);
SetRegister(bb, instr.gpr0, move(value));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled P2R/R2R instruction: {}", opcode->get().GetName());
break;
}
return pc;
}
} // namespace VideoCommon::Shader

153
src/video_core/shader/decode/shift.cpp
View file

@ -1,153 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::ShfType;
using Tegra::Shader::ShfXmode;
namespace {
Node IsFull(Node shift) {
return Operation(OperationCode::LogicalIEqual, move(shift), Immediate(32));
}
Node Shift(OperationCode opcode, Node value, Node shift) {
Node shifted = Operation(opcode, move(value), shift);
return Operation(OperationCode::Select, IsFull(move(shift)), Immediate(0), move(shifted));
}
Node ClampShift(Node shift, s32 size = 32) {
shift = Operation(OperationCode::IMax, move(shift), Immediate(0));
return Operation(OperationCode::IMin, move(shift), Immediate(size));
}
Node WrapShift(Node shift, s32 size = 32) {
return Operation(OperationCode::UBitwiseAnd, move(shift), Immediate(size - 1));
}
Node ShiftRight(Node low, Node high, Node shift, Node low_shift, ShfType type) {
// These values are used when the shift value is less than 32
Node less_low = Shift(OperationCode::ILogicalShiftRight, low, shift);
Node less_high = Shift(OperationCode::ILogicalShiftLeft, high, low_shift);
Node less = Operation(OperationCode::IBitwiseOr, move(less_high), move(less_low));
if (type == ShfType::Bits32) {
// On 32 bit shifts we are either full (shifting 32) or shifting less than 32 bits
return Operation(OperationCode::Select, IsFull(move(shift)), move(high), move(less));
}
// And these when it's larger than or 32
const bool is_signed = type == ShfType::S64;
const auto opcode = SignedToUnsignedCode(OperationCode::IArithmeticShiftRight, is_signed);
Node reduced = Operation(OperationCode::IAdd, shift, Immediate(-32));
Node greater = Shift(opcode, high, move(reduced));
Node is_less = Operation(OperationCode::LogicalILessThan, shift, Immediate(32));
Node is_zero = Operation(OperationCode::LogicalIEqual, move(shift), Immediate(0));
Node value = Operation(OperationCode::Select, move(is_less), move(less), move(greater));
return Operation(OperationCode::Select, move(is_zero), move(high), move(value));
}
Node ShiftLeft(Node low, Node high, Node shift, Node low_shift, ShfType type) {
// These values are used when the shift value is less than 32
Node less_low = Operation(OperationCode::ILogicalShiftRight, low, low_shift);
Node less_high = Operation(OperationCode::ILogicalShiftLeft, high, shift);
Node less = Operation(OperationCode::IBitwiseOr, move(less_low), move(less_high));
if (type == ShfType::Bits32) {
// On 32 bit shifts we are either full (shifting 32) or shifting less than 32 bits
return Operation(OperationCode::Select, IsFull(move(shift)), move(low), move(less));
}
// And these when it's larger than or 32
Node reduced = Operation(OperationCode::IAdd, shift, Immediate(-32));
Node greater = Shift(OperationCode::ILogicalShiftLeft, move(low), move(reduced));
Node is_less = Operation(OperationCode::LogicalILessThan, shift, Immediate(32));
Node is_zero = Operation(OperationCode::LogicalIEqual, move(shift), Immediate(0));
Node value = Operation(OperationCode::Select, move(is_less), move(less), move(greater));
return Operation(OperationCode::Select, move(is_zero), move(high), move(value));
}
} // Anonymous namespace
u32 ShaderIR::DecodeShift(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
Node op_a = GetRegister(instr.gpr8);
Node op_b = [this, instr] {
if (instr.is_b_imm) {
return Immediate(instr.alu.GetSignedImm20_20());
} else if (instr.is_b_gpr) {
return GetRegister(instr.gpr20);
} else {
return GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset());
}
}();
switch (const auto opid = opcode->get().GetId(); opid) {
case OpCode::Id::SHR_C:
case OpCode::Id::SHR_R:
case OpCode::Id::SHR_IMM: {
op_b = instr.shr.wrap ? WrapShift(move(op_b)) : ClampShift(move(op_b));
Node value = SignedOperation(OperationCode::IArithmeticShiftRight, instr.shift.is_signed,
move(op_a), move(op_b));
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, move(value));
break;
}
case OpCode::Id::SHL_C:
case OpCode::Id::SHL_R:
case OpCode::Id::SHL_IMM: {
Node value = Operation(OperationCode::ILogicalShiftLeft, op_a, op_b);
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, move(value));
break;
}
case OpCode::Id::SHF_RIGHT_R:
case OpCode::Id::SHF_RIGHT_IMM:
case OpCode::Id::SHF_LEFT_R:
case OpCode::Id::SHF_LEFT_IMM: {
UNIMPLEMENTED_IF(instr.generates_cc);
UNIMPLEMENTED_IF_MSG(instr.shf.xmode != ShfXmode::None, "xmode={}",
instr.shf.xmode.Value());
if (instr.is_b_imm) {
op_b = Immediate(static_cast<u32>(instr.shf.immediate));
}
const s32 size = instr.shf.type == ShfType::Bits32 ? 32 : 64;
Node shift = instr.shf.wrap ? WrapShift(move(op_b), size) : ClampShift(move(op_b), size);
Node negated_shift = Operation(OperationCode::INegate, shift);
Node low_shift = Operation(OperationCode::IAdd, move(negated_shift), Immediate(32));
const bool is_right = opid == OpCode::Id::SHF_RIGHT_R || opid == OpCode::Id::SHF_RIGHT_IMM;
Node value = (is_right ? ShiftRight : ShiftLeft)(
move(op_a), GetRegister(instr.gpr39), move(shift), move(low_shift), instr.shf.type);
SetRegister(bb, instr.gpr0, move(value));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled shift instruction: {}", opcode->get().GetName());
}
return pc;
}
} // namespace VideoCommon::Shader

935
src/video_core/shader/decode/texture.cpp
View file

@ -1,935 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <vector>
#include <fmt/format.h>
#include "common/assert.h"
#include "common/bit_field.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Register;
using Tegra::Shader::TextureMiscMode;
using Tegra::Shader::TextureProcessMode;
using Tegra::Shader::TextureType;
static std::size_t GetCoordCount(TextureType texture_type) {
switch (texture_type) {
case TextureType::Texture1D:
return 1;
case TextureType::Texture2D:
return 2;
case TextureType::Texture3D:
case TextureType::TextureCube:
return 3;
default:
UNIMPLEMENTED_MSG("Unhandled texture type: {}", texture_type);
return 0;
}
}
u32 ShaderIR::DecodeTexture(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
bool is_bindless = false;
switch (opcode->get().GetId()) {
case OpCode::Id::TEX: {
const TextureType texture_type{instr.tex.texture_type};
const bool is_array = instr.tex.array != 0;
const bool is_aoffi = instr.tex.UsesMiscMode(TextureMiscMode::AOFFI);
const bool depth_compare = instr.tex.UsesMiscMode(TextureMiscMode::DC);
const auto process_mode = instr.tex.GetTextureProcessMode();
WriteTexInstructionFloat(
bb, instr,
GetTexCode(instr, texture_type, process_mode, depth_compare, is_array, is_aoffi, {}));
break;
}
case OpCode::Id::TEX_B: {
UNIMPLEMENTED_IF_MSG(instr.tex.UsesMiscMode(TextureMiscMode::AOFFI),
"AOFFI is not implemented");
const TextureType texture_type{instr.tex_b.texture_type};
const bool is_array = instr.tex_b.array != 0;
const bool is_aoffi = instr.tex.UsesMiscMode(TextureMiscMode::AOFFI);
const bool depth_compare = instr.tex_b.UsesMiscMode(TextureMiscMode::DC);
const auto process_mode = instr.tex_b.GetTextureProcessMode();
WriteTexInstructionFloat(bb, instr,
GetTexCode(instr, texture_type, process_mode, depth_compare,
is_array, is_aoffi, {instr.gpr20}));
break;
}
case OpCode::Id::TEXS: {
const TextureType texture_type{instr.texs.GetTextureType()};
const bool is_array{instr.texs.IsArrayTexture()};
const bool depth_compare = instr.texs.UsesMiscMode(TextureMiscMode::DC);
const auto process_mode = instr.texs.GetTextureProcessMode();
const Node4 components =
GetTexsCode(instr, texture_type, process_mode, depth_compare, is_array);
if (instr.texs.fp32_flag) {
WriteTexsInstructionFloat(bb, instr, components);
} else {
WriteTexsInstructionHalfFloat(bb, instr, components);
}
break;
}
case OpCode::Id::TLD4_B: {
is_bindless = true;
[[fallthrough]];
}
case OpCode::Id::TLD4: {
UNIMPLEMENTED_IF_MSG(instr.tld4.UsesMiscMode(TextureMiscMode::NDV),
"NDV is not implemented");
const auto texture_type = instr.tld4.texture_type.Value();
const bool depth_compare = is_bindless ? instr.tld4_b.UsesMiscMode(TextureMiscMode::DC)
: instr.tld4.UsesMiscMode(TextureMiscMode::DC);
const bool is_array = instr.tld4.array != 0;
const bool is_aoffi = is_bindless ? instr.tld4_b.UsesMiscMode(TextureMiscMode::AOFFI)
: instr.tld4.UsesMiscMode(TextureMiscMode::AOFFI);
const bool is_ptp = is_bindless ? instr.tld4_b.UsesMiscMode(TextureMiscMode::PTP)
: instr.tld4.UsesMiscMode(TextureMiscMode::PTP);
WriteTexInstructionFloat(bb, instr,
GetTld4Code(instr, texture_type, depth_compare, is_array, is_aoffi,
is_ptp, is_bindless));
break;
}
case OpCode::Id::TLD4S: {
constexpr std::size_t num_coords = 2;
const bool is_aoffi = instr.tld4s.UsesMiscMode(TextureMiscMode::AOFFI);
const bool is_depth_compare = instr.tld4s.UsesMiscMode(TextureMiscMode::DC);
const Node op_a = GetRegister(instr.gpr8);
const Node op_b = GetRegister(instr.gpr20);
// TODO(Subv): Figure out how the sampler type is encoded in the TLD4S instruction.
std::vector<Node> coords;
std::vector<Node> aoffi;
Node depth_compare;
if (is_depth_compare) {
// Note: TLD4S coordinate encoding works just like TEXS's
const Node op_y = GetRegister(instr.gpr8.Value() + 1);
coords.push_back(op_a);
coords.push_back(op_y);
if (is_aoffi) {
aoffi = GetAoffiCoordinates(op_b, num_coords, true);
depth_compare = GetRegister(instr.gpr20.Value() + 1);
} else {
depth_compare = op_b;
}
} else {
// There's no depth compare
coords.push_back(op_a);
if (is_aoffi) {
coords.push_back(GetRegister(instr.gpr8.Value() + 1));
aoffi = GetAoffiCoordinates(op_b, num_coords, true);
} else {
coords.push_back(op_b);
}
}
const Node component = Immediate(static_cast<u32>(instr.tld4s.component));
SamplerInfo info;
info.is_shadow = is_depth_compare;
const std::optional<SamplerEntry> sampler = GetSampler(instr.sampler, info);
Node4 values;
for (u32 element = 0; element < values.size(); ++element) {
MetaTexture meta{*sampler, {}, depth_compare, aoffi, {}, {},
{}, {}, component, element, {}};
values[element] = Operation(OperationCode::TextureGather, meta, coords);
}
if (instr.tld4s.fp16_flag) {
WriteTexsInstructionHalfFloat(bb, instr, values, true);
} else {
WriteTexsInstructionFloat(bb, instr, values, true);
}
break;
}
case OpCode::Id::TXD_B:
is_bindless = true;
[[fallthrough]];
case OpCode::Id::TXD: {
UNIMPLEMENTED_IF_MSG(instr.txd.UsesMiscMode(TextureMiscMode::AOFFI),
"AOFFI is not implemented");
const bool is_array = instr.txd.is_array != 0;
const auto derivate_reg = instr.gpr20.Value();
const auto texture_type = instr.txd.texture_type.Value();
const auto coord_count = GetCoordCount(texture_type);
u64 base_reg = instr.gpr8.Value();
Node index_var;
SamplerInfo info;
info.type = texture_type;
info.is_array = is_array;
const std::optional<SamplerEntry> sampler =
is_bindless ? GetBindlessSampler(base_reg, info, index_var)
: GetSampler(instr.sampler, info);
Node4 values;
if (!sampler) {
std::generate(values.begin(), values.end(), [this] { return Immediate(0); });
WriteTexInstructionFloat(bb, instr, values);
break;
}
if (is_bindless) {
base_reg++;
}
std::vector<Node> coords;
std::vector<Node> derivates;
for (std::size_t i = 0; i < coord_count; ++i) {
coords.push_back(GetRegister(base_reg + i));
const std::size_t derivate = i * 2;
derivates.push_back(GetRegister(derivate_reg + derivate));
derivates.push_back(GetRegister(derivate_reg + derivate + 1));
}
Node array_node = {};
if (is_array) {
const Node info_reg = GetRegister(base_reg + coord_count);
array_node = BitfieldExtract(info_reg, 0, 16);
}
for (u32 element = 0; element < values.size(); ++element) {
MetaTexture meta{*sampler, array_node, {}, {}, {}, derivates,
{}, {}, {}, element, index_var};
values[element] = Operation(OperationCode::TextureGradient, std::move(meta), coords);
}
WriteTexInstructionFloat(bb, instr, values);
break;
}
case OpCode::Id::TXQ_B:
is_bindless = true;
[[fallthrough]];
case OpCode::Id::TXQ: {
Node index_var;
const std::optional<SamplerEntry> sampler =
is_bindless ? GetBindlessSampler(instr.gpr8, {}, index_var)
: GetSampler(instr.sampler, {});
if (!sampler) {
u32 indexer = 0;
for (u32 element = 0; element < 4; ++element) {
if (!instr.txq.IsComponentEnabled(element)) {
continue;
}
const Node value = Immediate(0);
SetTemporary(bb, indexer++, value);
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
u32 indexer = 0;
switch (instr.txq.query_type) {
case Tegra::Shader::TextureQueryType::Dimension: {
for (u32 element = 0; element < 4; ++element) {
if (!instr.txq.IsComponentEnabled(element)) {
continue;
}
MetaTexture meta{*sampler, {}, {}, {}, {}, {}, {}, {}, {}, element, index_var};
const Node value =
Operation(OperationCode::TextureQueryDimensions, meta,
GetRegister(instr.gpr8.Value() + (is_bindless ? 1 : 0)));
SetTemporary(bb, indexer++, value);
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled texture query type: {}", instr.txq.query_type.Value());
}
break;
}
case OpCode::Id::TMML_B:
is_bindless = true;
[[fallthrough]];
case OpCode::Id::TMML: {
UNIMPLEMENTED_IF_MSG(instr.tmml.UsesMiscMode(Tegra::Shader::TextureMiscMode::NDV),
"NDV is not implemented");
const auto texture_type = instr.tmml.texture_type.Value();
const bool is_array = instr.tmml.array != 0;
SamplerInfo info;
info.type = texture_type;
info.is_array = is_array;
Node index_var;
const std::optional<SamplerEntry> sampler =
is_bindless ? GetBindlessSampler(instr.gpr20, info, index_var)
: GetSampler(instr.sampler, info);
if (!sampler) {
u32 indexer = 0;
for (u32 element = 0; element < 2; ++element) {
if (!instr.tmml.IsComponentEnabled(element)) {
continue;
}
const Node value = Immediate(0);
SetTemporary(bb, indexer++, value);
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
const u64 base_index = is_array ? 1 : 0;
const u64 num_components = [texture_type] {
switch (texture_type) {
case TextureType::Texture1D:
return 1;
case TextureType::Texture2D:
return 2;
case TextureType::TextureCube:
return 3;
default:
UNIMPLEMENTED_MSG("Unhandled texture type {}", texture_type);
return 2;
}
}();
// TODO: What's the array component used for?
std::vector<Node> coords;
coords.reserve(num_components);
for (u64 component = 0; component < num_components; ++component) {
coords.push_back(GetRegister(instr.gpr8.Value() + base_index + component));
}
u32 indexer = 0;
for (u32 element = 0; element < 2; ++element) {
if (!instr.tmml.IsComponentEnabled(element)) {
continue;
}
MetaTexture meta{*sampler, {}, {}, {}, {}, {}, {}, {}, {}, element, index_var};
Node value = Operation(OperationCode::TextureQueryLod, meta, coords);
SetTemporary(bb, indexer++, std::move(value));
}
for (u32 i = 0; i < indexer; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
break;
}
case OpCode::Id::TLD: {
UNIMPLEMENTED_IF_MSG(instr.tld.aoffi, "AOFFI is not implemented");
UNIMPLEMENTED_IF_MSG(instr.tld.ms, "MS is not implemented");
UNIMPLEMENTED_IF_MSG(instr.tld.cl, "CL is not implemented");
WriteTexInstructionFloat(bb, instr, GetTldCode(instr));
break;
}
case OpCode::Id::TLDS: {
const TextureType texture_type{instr.tlds.GetTextureType()};
const bool is_array{instr.tlds.IsArrayTexture()};
UNIMPLEMENTED_IF_MSG(instr.tlds.UsesMiscMode(TextureMiscMode::AOFFI),
"AOFFI is not implemented");
UNIMPLEMENTED_IF_MSG(instr.tlds.UsesMiscMode(TextureMiscMode::MZ), "MZ is not implemented");
const Node4 components = GetTldsCode(instr, texture_type, is_array);
if (instr.tlds.fp32_flag) {
WriteTexsInstructionFloat(bb, instr, components);
} else {
WriteTexsInstructionHalfFloat(bb, instr, components);
}
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled memory instruction: {}", opcode->get().GetName());
}
return pc;
}
ShaderIR::SamplerInfo ShaderIR::GetSamplerInfo(
SamplerInfo info, std::optional<Tegra::Engines::SamplerDescriptor> sampler) {
if (info.IsComplete()) {
return info;
}
if (!sampler) {
LOG_WARNING(HW_GPU, "Unknown sampler info");
info.type = info.type.value_or(Tegra::Shader::TextureType::Texture2D);
info.is_array = info.is_array.value_or(false);
info.is_shadow = info.is_shadow.value_or(false);
info.is_buffer = info.is_buffer.value_or(false);
return info;
}
info.type = info.type.value_or(sampler->texture_type);
info.is_array = info.is_array.value_or(sampler->is_array != 0);
info.is_shadow = info.is_shadow.value_or(sampler->is_shadow != 0);
info.is_buffer = info.is_buffer.value_or(sampler->is_buffer != 0);
return info;
}
std::optional<SamplerEntry> ShaderIR::GetSampler(Tegra::Shader::Sampler sampler,
SamplerInfo sampler_info) {
const u32 offset = static_cast<u32>(sampler.index.Value());
const auto info = GetSamplerInfo(sampler_info, registry.ObtainBoundSampler(offset));
// If this sampler has already been used, return the existing mapping.
const auto it =
std::find_if(used_samplers.begin(), used_samplers.end(),
[offset](const SamplerEntry& entry) { return entry.offset == offset; });
if (it != used_samplers.end()) {
ASSERT(!it->is_bindless && it->type == info.type && it->is_array == info.is_array &&
it->is_shadow == info.is_shadow && it->is_buffer == info.is_buffer);
return *it;
}
// Otherwise create a new mapping for this sampler
const auto next_index = static_cast<u32>(used_samplers.size());
return used_samplers.emplace_back(next_index, offset, *info.type, *info.is_array,
*info.is_shadow, *info.is_buffer, false);
}
std::optional<SamplerEntry> ShaderIR::GetBindlessSampler(Tegra::Shader::Register reg,
SamplerInfo info, Node& index_var) {
const Node sampler_register = GetRegister(reg);
const auto [base_node, tracked_sampler_info] =
TrackBindlessSampler(sampler_register, global_code, static_cast<s64>(global_code.size()));
if (!base_node) {
UNREACHABLE();
return std::nullopt;
}
if (const auto sampler_info = std::get_if<BindlessSamplerNode>(&*tracked_sampler_info)) {
const u32 buffer = sampler_info->index;
const u32 offset = sampler_info->offset;
info = GetSamplerInfo(info, registry.ObtainBindlessSampler(buffer, offset));
// If this sampler has already been used, return the existing mapping.
const auto it = std::find_if(used_samplers.begin(), used_samplers.end(),
[buffer, offset](const SamplerEntry& entry) {
return entry.buffer == buffer && entry.offset == offset;
});
if (it != used_samplers.end()) {
ASSERT(it->is_bindless && it->type == info.type && it->is_array == info.is_array &&
it->is_shadow == info.is_shadow);
return *it;
}
// Otherwise create a new mapping for this sampler
const auto next_index = static_cast<u32>(used_samplers.size());
return used_samplers.emplace_back(next_index, offset, buffer, *info.type, *info.is_array,
*info.is_shadow, *info.is_buffer, false);
}
if (const auto sampler_info = std::get_if<SeparateSamplerNode>(&*tracked_sampler_info)) {
const std::pair indices = sampler_info->indices;
const std::pair offsets = sampler_info->offsets;
info = GetSamplerInfo(info, registry.ObtainSeparateSampler(indices, offsets));
// Try to use an already created sampler if it exists
const auto it =
std::find_if(used_samplers.begin(), used_samplers.end(),
[indices, offsets](const SamplerEntry& entry) {
return offsets == std::pair{entry.offset, entry.secondary_offset} &&
indices == std::pair{entry.buffer, entry.secondary_buffer};
});
if (it != used_samplers.end()) {
ASSERT(it->is_separated && it->type == info.type && it->is_array == info.is_array &&
it->is_shadow == info.is_shadow && it->is_buffer == info.is_buffer);
return *it;
}
// Otherwise create a new mapping for this sampler
const u32 next_index = static_cast<u32>(used_samplers.size());
return used_samplers.emplace_back(next_index, offsets, indices, *info.type, *info.is_array,
*info.is_shadow, *info.is_buffer);
}
if (const auto sampler_info = std::get_if<ArraySamplerNode>(&*tracked_sampler_info)) {
const u32 base_offset = sampler_info->base_offset / 4;
index_var = GetCustomVariable(sampler_info->bindless_var);
info = GetSamplerInfo(info, registry.ObtainBoundSampler(base_offset));
// If this sampler has already been used, return the existing mapping.
const auto it = std::find_if(
used_samplers.begin(), used_samplers.end(),
[base_offset](const SamplerEntry& entry) { return entry.offset == base_offset; });
if (it != used_samplers.end()) {
ASSERT(!it->is_bindless && it->type == info.type && it->is_array == info.is_array &&
it->is_shadow == info.is_shadow && it->is_buffer == info.is_buffer &&
it->is_indexed);
return *it;
}
uses_indexed_samplers = true;
// Otherwise create a new mapping for this sampler
const auto next_index = static_cast<u32>(used_samplers.size());
return used_samplers.emplace_back(next_index, base_offset, *info.type, *info.is_array,
*info.is_shadow, *info.is_buffer, true);
}
return std::nullopt;
}
void ShaderIR::WriteTexInstructionFloat(NodeBlock& bb, Instruction instr, const Node4& components) {
u32 dest_elem = 0;
for (u32 elem = 0; elem < 4; ++elem) {
if (!instr.tex.IsComponentEnabled(elem)) {
// Skip disabled components
continue;
}
SetTemporary(bb, dest_elem++, components[elem]);
}
// After writing values in temporals, move them to the real registers
for (u32 i = 0; i < dest_elem; ++i) {
SetRegister(bb, instr.gpr0.Value() + i, GetTemporary(i));
}
}
void ShaderIR::WriteTexsInstructionFloat(NodeBlock& bb, Instruction instr, const Node4& components,
bool ignore_mask) {
// TEXS has two destination registers and a swizzle. The first two elements in the swizzle
// go into gpr0+0 and gpr0+1, and the rest goes into gpr28+0 and gpr28+1
u32 dest_elem = 0;
for (u32 component = 0; component < 4; ++component) {
if (!instr.texs.IsComponentEnabled(component) && !ignore_mask)
continue;
SetTemporary(bb, dest_elem++, components[component]);
}
for (u32 i = 0; i < dest_elem; ++i) {
if (i < 2) {
// Write the first two swizzle components to gpr0 and gpr0+1
SetRegister(bb, instr.gpr0.Value() + i % 2, GetTemporary(i));
} else {
ASSERT(instr.texs.HasTwoDestinations());
// Write the rest of the swizzle components to gpr28 and gpr28+1
SetRegister(bb, instr.gpr28.Value() + i % 2, GetTemporary(i));
}
}
}
void ShaderIR::WriteTexsInstructionHalfFloat(NodeBlock& bb, Instruction instr,
const Node4& components, bool ignore_mask) {
// TEXS.F16 destionation registers are packed in two registers in pairs (just like any half
// float instruction).
Node4 values;
u32 dest_elem = 0;
for (u32 component = 0; component < 4; ++component) {
if (!instr.texs.IsComponentEnabled(component) && !ignore_mask)
continue;
values[dest_elem++] = components[component];
}
if (dest_elem == 0)
return;
std::generate(values.begin() + dest_elem, values.end(), [&]() { return Immediate(0); });
const Node first_value = Operation(OperationCode::HPack2, values[0], values[1]);
if (dest_elem <= 2) {
SetRegister(bb, instr.gpr0, first_value);
return;
}
SetTemporary(bb, 0, first_value);
SetTemporary(bb, 1, Operation(OperationCode::HPack2, values[2], values[3]));
SetRegister(bb, instr.gpr0, GetTemporary(0));
SetRegister(bb, instr.gpr28, GetTemporary(1));
}
Node4 ShaderIR::GetTextureCode(Instruction instr, TextureType texture_type,
TextureProcessMode process_mode, std::vector<Node> coords,
Node array, Node depth_compare, u32 bias_offset,
std::vector<Node> aoffi,
std::optional<Tegra::Shader::Register> bindless_reg) {
const bool is_array = array != nullptr;
const bool is_shadow = depth_compare != nullptr;
const bool is_bindless = bindless_reg.has_value();
ASSERT_MSG(texture_type != TextureType::Texture3D || !is_array || !is_shadow,
"Illegal texture type");
SamplerInfo info;
info.type = texture_type;
info.is_array = is_array;
info.is_shadow = is_shadow;
info.is_buffer = false;
Node index_var;
const std::optional<SamplerEntry> sampler =
is_bindless ? GetBindlessSampler(*bindless_reg, info, index_var)
: GetSampler(instr.sampler, info);
if (!sampler) {
return {Immediate(0), Immediate(0), Immediate(0), Immediate(0)};
}
const bool lod_needed = process_mode == TextureProcessMode::LZ ||
process_mode == TextureProcessMode::LL ||
process_mode == TextureProcessMode::LLA;
const OperationCode opcode = lod_needed ? OperationCode::TextureLod : OperationCode::Texture;
Node bias;
Node lod;
switch (process_mode) {
case TextureProcessMode::None:
break;
case TextureProcessMode::LZ:
lod = Immediate(0.0f);
break;
case TextureProcessMode::LB:
// If present, lod or bias are always stored in the register indexed by the gpr20 field with
// an offset depending on the usage of the other registers.
bias = GetRegister(instr.gpr20.Value() + bias_offset);
break;
case TextureProcessMode::LL:
lod = GetRegister(instr.gpr20.Value() + bias_offset);
break;
default:
UNIMPLEMENTED_MSG("Unimplemented process mode={}", process_mode);
break;
}
Node4 values;
for (u32 element = 0; element < values.size(); ++element) {
MetaTexture meta{*sampler, array, depth_compare, aoffi, {}, {}, bias,
lod, {}, element, index_var};
values[element] = Operation(opcode, meta, coords);
}
return values;
}
Node4 ShaderIR::GetTexCode(Instruction instr, TextureType texture_type,
TextureProcessMode process_mode, bool depth_compare, bool is_array,
bool is_aoffi, std::optional<Tegra::Shader::Register> bindless_reg) {
const bool lod_bias_enabled{
(process_mode != TextureProcessMode::None && process_mode != TextureProcessMode::LZ)};
const bool is_bindless = bindless_reg.has_value();
u64 parameter_register = instr.gpr20.Value();
if (is_bindless) {
++parameter_register;
}
const u32 bias_lod_offset = (is_bindless ? 1 : 0);
if (lod_bias_enabled) {
++parameter_register;
}
const auto coord_counts = ValidateAndGetCoordinateElement(texture_type, depth_compare, is_array,
lod_bias_enabled, 4, 5);
const auto coord_count = std::get<0>(coord_counts);
// If enabled arrays index is always stored in the gpr8 field
const u64 array_register = instr.gpr8.Value();
// First coordinate index is the gpr8 or gpr8 + 1 when arrays are used
const u64 coord_register = array_register + (is_array ? 1 : 0);
std::vector<Node> coords;
for (std::size_t i = 0; i < coord_count; ++i) {
coords.push_back(GetRegister(coord_register + i));
}
// 1D.DC in OpenGL the 2nd component is ignored.
if (depth_compare && !is_array && texture_type == TextureType::Texture1D) {
coords.push_back(Immediate(0.0f));
}
const Node array = is_array ? GetRegister(array_register) : nullptr;
std::vector<Node> aoffi;
if (is_aoffi) {
aoffi = GetAoffiCoordinates(GetRegister(parameter_register++), coord_count, false);
}
Node dc;
if (depth_compare) {
// Depth is always stored in the register signaled by gpr20 or in the next register if lod
// or bias are used
dc = GetRegister(parameter_register++);
}
return GetTextureCode(instr, texture_type, process_mode, coords, array, dc, bias_lod_offset,
aoffi, bindless_reg);
}
Node4 ShaderIR::GetTexsCode(Instruction instr, TextureType texture_type,
TextureProcessMode process_mode, bool depth_compare, bool is_array) {
const bool lod_bias_enabled =
(process_mode != TextureProcessMode::None && process_mode != TextureProcessMode::LZ);
const auto coord_counts = ValidateAndGetCoordinateElement(texture_type, depth_compare, is_array,
lod_bias_enabled, 4, 4);
const auto coord_count = std::get<0>(coord_counts);
// If enabled arrays index is always stored in the gpr8 field
const u64 array_register = instr.gpr8.Value();
// First coordinate index is stored in gpr8 field or (gpr8 + 1) when arrays are used
const u64 coord_register = array_register + (is_array ? 1 : 0);
const u64 last_coord_register =
(is_array || !(lod_bias_enabled || depth_compare) || (coord_count > 2))
? static_cast<u64>(instr.gpr20.Value())
: coord_register + 1;
const u32 bias_offset = coord_count > 2 ? 1 : 0;
std::vector<Node> coords;
for (std::size_t i = 0; i < coord_count; ++i) {
const bool last = (i == (coord_count - 1)) && (coord_count > 1);
coords.push_back(GetRegister(last ? last_coord_register : coord_register + i));
}
const Node array = is_array ? GetRegister(array_register) : nullptr;
Node dc;
if (depth_compare) {
// Depth is always stored in the register signaled by gpr20 or in the next register if lod
// or bias are used
const u64 depth_register = instr.gpr20.Value() + (lod_bias_enabled ? 1 : 0);
dc = GetRegister(depth_register);
}
return GetTextureCode(instr, texture_type, process_mode, coords, array, dc, bias_offset, {},
{});
}
Node4 ShaderIR::GetTld4Code(Instruction instr, TextureType texture_type, bool depth_compare,
bool is_array, bool is_aoffi, bool is_ptp, bool is_bindless) {
ASSERT_MSG(!(is_aoffi && is_ptp), "AOFFI and PTP can't be enabled at the same time");
const std::size_t coord_count = GetCoordCount(texture_type);
// If enabled arrays index is always stored in the gpr8 field
const u64 array_register = instr.gpr8.Value();
// First coordinate index is the gpr8 or gpr8 + 1 when arrays are used
const u64 coord_register = array_register + (is_array ? 1 : 0);
std::vector<Node> coords;
for (std::size_t i = 0; i < coord_count; ++i) {
coords.push_back(GetRegister(coord_register + i));
}
u64 parameter_register = instr.gpr20.Value();
SamplerInfo info;
info.type = texture_type;
info.is_array = is_array;
info.is_shadow = depth_compare;
Node index_var;
const std::optional<SamplerEntry> sampler =
is_bindless ? GetBindlessSampler(parameter_register++, info, index_var)
: GetSampler(instr.sampler, info);
Node4 values;
if (!sampler) {
for (u32 element = 0; element < values.size(); ++element) {
values[element] = Immediate(0);
}
return values;
}
std::vector<Node> aoffi, ptp;
if (is_aoffi) {
aoffi = GetAoffiCoordinates(GetRegister(parameter_register++), coord_count, true);
} else if (is_ptp) {
ptp = GetPtpCoordinates(
{GetRegister(parameter_register++), GetRegister(parameter_register++)});
}
Node dc;
if (depth_compare) {
dc = GetRegister(parameter_register++);
}
const Node component = is_bindless ? Immediate(static_cast<u32>(instr.tld4_b.component))
: Immediate(static_cast<u32>(instr.tld4.component));
for (u32 element = 0; element < values.size(); ++element) {
auto coords_copy = coords;
MetaTexture meta{
*sampler, GetRegister(array_register), dc, aoffi, ptp, {}, {}, {}, component, element,
index_var};
values[element] = Operation(OperationCode::TextureGather, meta, std::move(coords_copy));
}
return values;
}
Node4 ShaderIR::GetTldCode(Tegra::Shader::Instruction instr) {
const auto texture_type{instr.tld.texture_type};
const bool is_array{instr.tld.is_array != 0};
const bool lod_enabled{instr.tld.GetTextureProcessMode() == TextureProcessMode::LL};
const std::size_t coord_count{GetCoordCount(texture_type)};
u64 gpr8_cursor{instr.gpr8.Value()};
const Node array_register{is_array ? GetRegister(gpr8_cursor++) : nullptr};
std::vector<Node> coords;
coords.reserve(coord_count);
for (std::size_t i = 0; i < coord_count; ++i) {
coords.push_back(GetRegister(gpr8_cursor++));
}
u64 gpr20_cursor{instr.gpr20.Value()};
// const Node bindless_register{is_bindless ? GetRegister(gpr20_cursor++) : nullptr};
const Node lod{lod_enabled ? GetRegister(gpr20_cursor++) : Immediate(0u)};
// const Node aoffi_register{is_aoffi ? GetRegister(gpr20_cursor++) : nullptr};
// const Node multisample{is_multisample ? GetRegister(gpr20_cursor++) : nullptr};
const std::optional<SamplerEntry> sampler = GetSampler(instr.sampler, {});
Node4 values;
for (u32 element = 0; element < values.size(); ++element) {
auto coords_copy = coords;
MetaTexture meta{*sampler, array_register, {}, {}, {}, {}, {}, lod, {}, element, {}};
values[element] = Operation(OperationCode::TexelFetch, meta, std::move(coords_copy));
}
return values;
}
Node4 ShaderIR::GetTldsCode(Instruction instr, TextureType texture_type, bool is_array) {
SamplerInfo info;
info.type = texture_type;
info.is_array = is_array;
info.is_shadow = false;
const std::optional<SamplerEntry> sampler = GetSampler(instr.sampler, info);
const std::size_t type_coord_count = GetCoordCount(texture_type);
const bool lod_enabled = instr.tlds.GetTextureProcessMode() == TextureProcessMode::LL;
const bool aoffi_enabled = instr.tlds.UsesMiscMode(TextureMiscMode::AOFFI);
// If enabled arrays index is always stored in the gpr8 field
const u64 array_register = instr.gpr8.Value();
// if is array gpr20 is used
const u64 coord_register = is_array ? instr.gpr20.Value() : instr.gpr8.Value();
const u64 last_coord_register =
((type_coord_count > 2) || (type_coord_count == 2 && !lod_enabled)) && !is_array
? static_cast<u64>(instr.gpr20.Value())
: coord_register + 1;
std::vector<Node> coords;
for (std::size_t i = 0; i < type_coord_count; ++i) {
const bool last = (i == (type_coord_count - 1)) && (type_coord_count > 1);
coords.push_back(
GetRegister(last && !aoffi_enabled ? last_coord_register : coord_register + i));
}
const Node array = is_array ? GetRegister(array_register) : nullptr;
// When lod is used always is in gpr20
const Node lod = lod_enabled ? GetRegister(instr.gpr20) : Immediate(0);
std::vector<Node> aoffi;
if (aoffi_enabled) {
aoffi = GetAoffiCoordinates(GetRegister(instr.gpr20), type_coord_count, false);
}
Node4 values;
for (u32 element = 0; element < values.size(); ++element) {
auto coords_copy = coords;
MetaTexture meta{*sampler, array, {}, aoffi, {}, {}, {}, lod, {}, element, {}};
values[element] = Operation(OperationCode::TexelFetch, meta, std::move(coords_copy));
}
return values;
}
std::tuple<std::size_t, std::size_t> ShaderIR::ValidateAndGetCoordinateElement(
TextureType texture_type, bool depth_compare, bool is_array, bool lod_bias_enabled,
std::size_t max_coords, std::size_t max_inputs) {
const std::size_t coord_count = GetCoordCount(texture_type);
std::size_t total_coord_count = coord_count + (is_array ? 1 : 0) + (depth_compare ? 1 : 0);
const std::size_t total_reg_count = total_coord_count + (lod_bias_enabled ? 1 : 0);
if (total_coord_count > max_coords || total_reg_count > max_inputs) {
UNIMPLEMENTED_MSG("Unsupported Texture operation");
total_coord_count = std::min(total_coord_count, max_coords);
}
// 1D.DC OpenGL is using a vec3 but 2nd component is ignored later.
total_coord_count +=
(depth_compare && !is_array && texture_type == TextureType::Texture1D) ? 1 : 0;
return {coord_count, total_coord_count};
}
std::vector<Node> ShaderIR::GetAoffiCoordinates(Node aoffi_reg, std::size_t coord_count,
bool is_tld4) {
const std::array coord_offsets = is_tld4 ? std::array{0U, 8U, 16U} : std::array{0U, 4U, 8U};
const u32 size = is_tld4 ? 6 : 4;
const s32 wrap_value = is_tld4 ? 32 : 8;
const s32 diff_value = is_tld4 ? 64 : 16;
const u32 mask = (1U << size) - 1;
std::vector<Node> aoffi;
aoffi.reserve(coord_count);
const auto aoffi_immediate{
TrackImmediate(aoffi_reg, global_code, static_cast<s64>(global_code.size()))};
if (!aoffi_immediate) {
// Variable access, not supported on AMD.
LOG_WARNING(HW_GPU,
"AOFFI constant folding failed, some hardware might have graphical issues");
for (std::size_t coord = 0; coord < coord_count; ++coord) {
const Node value = BitfieldExtract(aoffi_reg, coord_offsets[coord], size);
const Node condition =
Operation(OperationCode::LogicalIGreaterEqual, value, Immediate(wrap_value));
const Node negative = Operation(OperationCode::IAdd, value, Immediate(-diff_value));
aoffi.push_back(Operation(OperationCode::Select, condition, negative, value));
}
return aoffi;
}
for (std::size_t coord = 0; coord < coord_count; ++coord) {
s32 value = (*aoffi_immediate >> coord_offsets[coord]) & mask;
if (value >= wrap_value) {
value -= diff_value;
}
aoffi.push_back(Immediate(value));
}
return aoffi;
}
std::vector<Node> ShaderIR::GetPtpCoordinates(std::array<Node, 2> ptp_regs) {
static constexpr u32 num_entries = 8;
std::vector<Node> ptp;
ptp.reserve(num_entries);
const auto global_size = static_cast<s64>(global_code.size());
const std::optional low = TrackImmediate(ptp_regs[0], global_code, global_size);
const std::optional high = TrackImmediate(ptp_regs[1], global_code, global_size);
if (!low || !high) {
for (u32 entry = 0; entry < num_entries; ++entry) {
const u32 reg = entry / 4;
const u32 offset = entry % 4;
const Node value = BitfieldExtract(ptp_regs[reg], offset * 8, 6);
const Node condition =
Operation(OperationCode::LogicalIGreaterEqual, value, Immediate(32));
const Node negative = Operation(OperationCode::IAdd, value, Immediate(-64));
ptp.push_back(Operation(OperationCode::Select, condition, negative, value));
}
return ptp;
}
const u64 immediate = (static_cast<u64>(*high) << 32) | static_cast<u64>(*low);
for (u32 entry = 0; entry < num_entries; ++entry) {
s32 value = (immediate >> (entry * 8)) & 0b111111;
if (value >= 32) {
value -= 64;
}
ptp.push_back(Immediate(value));
}
return ptp;
}
} // namespace VideoCommon::Shader

169
src/video_core/shader/decode/video.cpp
View file

@ -1,169 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using std::move;
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
using Tegra::Shader::VideoType;
using Tegra::Shader::VmadShr;
using Tegra::Shader::VmnmxOperation;
using Tegra::Shader::VmnmxType;
u32 ShaderIR::DecodeVideo(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
if (opcode->get().GetId() == OpCode::Id::VMNMX) {
DecodeVMNMX(bb, instr);
return pc;
}
const Node op_a =
GetVideoOperand(GetRegister(instr.gpr8), instr.video.is_byte_chunk_a, instr.video.signed_a,
instr.video.type_a, instr.video.byte_height_a);
const Node op_b = [this, instr] {
if (instr.video.use_register_b) {
return GetVideoOperand(GetRegister(instr.gpr20), instr.video.is_byte_chunk_b,
instr.video.signed_b, instr.video.type_b,
instr.video.byte_height_b);
}
if (instr.video.signed_b) {
const auto imm = static_cast<s16>(instr.alu.GetImm20_16());
return Immediate(static_cast<u32>(imm));
} else {
return Immediate(instr.alu.GetImm20_16());
}
}();
switch (opcode->get().GetId()) {
case OpCode::Id::VMAD: {
const bool result_signed = instr.video.signed_a == 1 || instr.video.signed_b == 1;
const Node op_c = GetRegister(instr.gpr39);
Node value = SignedOperation(OperationCode::IMul, result_signed, NO_PRECISE, op_a, op_b);
value = SignedOperation(OperationCode::IAdd, result_signed, NO_PRECISE, value, op_c);
if (instr.vmad.shr == VmadShr::Shr7 || instr.vmad.shr == VmadShr::Shr15) {
const Node shift = Immediate(instr.vmad.shr == VmadShr::Shr7 ? 7 : 15);
value =
SignedOperation(OperationCode::IArithmeticShiftRight, result_signed, value, shift);
}
SetInternalFlagsFromInteger(bb, value, instr.generates_cc);
SetRegister(bb, instr.gpr0, value);
break;
}
case OpCode::Id::VSETP: {
// We can't use the constant predicate as destination.
ASSERT(instr.vsetp.pred3 != static_cast<u64>(Pred::UnusedIndex));
const bool sign = instr.video.signed_a == 1 || instr.video.signed_b == 1;
const Node first_pred = GetPredicateComparisonInteger(instr.vsetp.cond, sign, op_a, op_b);
const Node second_pred = GetPredicate(instr.vsetp.pred39, false);
const OperationCode combiner = GetPredicateCombiner(instr.vsetp.op);
// Set the primary predicate to the result of Predicate OP SecondPredicate
SetPredicate(bb, instr.vsetp.pred3, Operation(combiner, first_pred, second_pred));
if (instr.vsetp.pred0 != static_cast<u64>(Pred::UnusedIndex)) {
// Set the secondary predicate to the result of !Predicate OP SecondPredicate,
// if enabled
const Node negate_pred = Operation(OperationCode::LogicalNegate, first_pred);
SetPredicate(bb, instr.vsetp.pred0, Operation(combiner, negate_pred, second_pred));
}
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled video instruction: {}", opcode->get().GetName());
}
return pc;
}
Node ShaderIR::GetVideoOperand(Node op, bool is_chunk, bool is_signed, VideoType type,
u64 byte_height) {
if (!is_chunk) {
return BitfieldExtract(op, static_cast<u32>(byte_height * 8), 8);
}
switch (type) {
case VideoType::Size16_Low:
return BitfieldExtract(op, 0, 16);
case VideoType::Size16_High:
return BitfieldExtract(op, 16, 16);
case VideoType::Size32:
// TODO(Rodrigo): From my hardware tests it becomes a bit "mad" when this type is used
// (1 * 1 + 0 == 0x5b800000). Until a better explanation is found: abort.
UNIMPLEMENTED();
return Immediate(0);
case VideoType::Invalid:
UNREACHABLE_MSG("Invalid instruction encoding");
return Immediate(0);
default:
UNREACHABLE();
return Immediate(0);
}
}
void ShaderIR::DecodeVMNMX(NodeBlock& bb, Tegra::Shader::Instruction instr) {
UNIMPLEMENTED_IF(!instr.vmnmx.is_op_b_register);
UNIMPLEMENTED_IF(instr.vmnmx.SourceFormatA() != VmnmxType::Bits32);
UNIMPLEMENTED_IF(instr.vmnmx.SourceFormatB() != VmnmxType::Bits32);
UNIMPLEMENTED_IF(instr.vmnmx.is_src_a_signed != instr.vmnmx.is_src_b_signed);
UNIMPLEMENTED_IF(instr.vmnmx.sat);
UNIMPLEMENTED_IF(instr.generates_cc);
Node op_a = GetRegister(instr.gpr8);
Node op_b = GetRegister(instr.gpr20);
Node op_c = GetRegister(instr.gpr39);
const bool is_oper1_signed = instr.vmnmx.is_src_a_signed; // Stubbed
const bool is_oper2_signed = instr.vmnmx.is_dest_signed;
const auto operation_a = instr.vmnmx.mx ? OperationCode::IMax : OperationCode::IMin;
Node value = SignedOperation(operation_a, is_oper1_signed, move(op_a), move(op_b));
switch (instr.vmnmx.operation) {
case VmnmxOperation::Mrg_16H:
value = BitfieldInsert(move(op_c), move(value), 16, 16);
break;
case VmnmxOperation::Mrg_16L:
value = BitfieldInsert(move(op_c), move(value), 0, 16);
break;
case VmnmxOperation::Mrg_8B0:
value = BitfieldInsert(move(op_c), move(value), 0, 8);
break;
case VmnmxOperation::Mrg_8B2:
value = BitfieldInsert(move(op_c), move(value), 16, 8);
break;
case VmnmxOperation::Acc:
value = Operation(OperationCode::IAdd, move(value), move(op_c));
break;
case VmnmxOperation::Min:
value = SignedOperation(OperationCode::IMin, is_oper2_signed, move(value), move(op_c));
break;
case VmnmxOperation::Max:
value = SignedOperation(OperationCode::IMax, is_oper2_signed, move(value), move(op_c));
break;
case VmnmxOperation::Nop:
break;
default:
UNREACHABLE();
break;
}
SetRegister(bb, instr.gpr0, move(value));
}
} // namespace VideoCommon::Shader

117
src/video_core/shader/decode/warp.cpp
View file

@ -1,117 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::Pred;
using Tegra::Shader::ShuffleOperation;
using Tegra::Shader::VoteOperation;
namespace {
OperationCode GetOperationCode(VoteOperation vote_op) {
switch (vote_op) {
case VoteOperation::All:
return OperationCode::VoteAll;
case VoteOperation::Any:
return OperationCode::VoteAny;
case VoteOperation::Eq:
return OperationCode::VoteEqual;
default:
UNREACHABLE_MSG("Invalid vote operation={}", vote_op);
return OperationCode::VoteAll;
}
}
} // Anonymous namespace
u32 ShaderIR::DecodeWarp(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
// Signal the backend that this shader uses warp instructions.
uses_warps = true;
switch (opcode->get().GetId()) {
case OpCode::Id::VOTE: {
const Node value = GetPredicate(instr.vote.value, instr.vote.negate_value != 0);
const Node active = Operation(OperationCode::BallotThread, value);
const Node vote = Operation(GetOperationCode(instr.vote.operation), value);
SetRegister(bb, instr.gpr0, active);
SetPredicate(bb, instr.vote.dest_pred, vote);
break;
}
case OpCode::Id::SHFL: {
Node mask = instr.shfl.is_mask_imm ? Immediate(static_cast<u32>(instr.shfl.mask_imm))
: GetRegister(instr.gpr39);
Node index = instr.shfl.is_index_imm ? Immediate(static_cast<u32>(instr.shfl.index_imm))
: GetRegister(instr.gpr20);
Node thread_id = Operation(OperationCode::ThreadId);
Node clamp = Operation(OperationCode::IBitwiseAnd, mask, Immediate(0x1FU));
Node seg_mask = BitfieldExtract(mask, 8, 16);
Node neg_seg_mask = Operation(OperationCode::IBitwiseNot, seg_mask);
Node min_thread_id = Operation(OperationCode::IBitwiseAnd, thread_id, seg_mask);
Node max_thread_id = Operation(OperationCode::IBitwiseOr, min_thread_id,
Operation(OperationCode::IBitwiseAnd, clamp, neg_seg_mask));
Node src_thread_id = [instr, index, neg_seg_mask, min_thread_id, thread_id] {
switch (instr.shfl.operation) {
case ShuffleOperation::Idx:
return Operation(OperationCode::IBitwiseOr,
Operation(OperationCode::IBitwiseAnd, index, neg_seg_mask),
min_thread_id);
case ShuffleOperation::Down:
return Operation(OperationCode::IAdd, thread_id, index);
case ShuffleOperation::Up:
return Operation(OperationCode::IAdd, thread_id,
Operation(OperationCode::INegate, index));
case ShuffleOperation::Bfly:
return Operation(OperationCode::IBitwiseXor, thread_id, index);
}
UNREACHABLE();
return Immediate(0U);
}();
Node in_bounds = [instr, src_thread_id, min_thread_id, max_thread_id] {
if (instr.shfl.operation == ShuffleOperation::Up) {
return Operation(OperationCode::LogicalIGreaterEqual, src_thread_id, min_thread_id);
} else {
return Operation(OperationCode::LogicalILessEqual, src_thread_id, max_thread_id);
}
}();
SetPredicate(bb, instr.shfl.pred48, in_bounds);
SetRegister(
bb, instr.gpr0,
Operation(OperationCode::ShuffleIndexed, GetRegister(instr.gpr8), src_thread_id));
break;
}
case OpCode::Id::FSWZADD: {
UNIMPLEMENTED_IF(instr.fswzadd.ndv);
Node op_a = GetRegister(instr.gpr8);
Node op_b = GetRegister(instr.gpr20);
Node mask = Immediate(static_cast<u32>(instr.fswzadd.swizzle));
SetRegister(bb, instr.gpr0, Operation(OperationCode::FSwizzleAdd, op_a, op_b, mask));
break;
}
default:
UNIMPLEMENTED_MSG("Unhandled warp instruction: {}", opcode->get().GetName());
break;
}
return pc;
}
} // namespace VideoCommon::Shader

156
src/video_core/shader/decode/xmad.cpp
View file

@ -1,156 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Instruction;
using Tegra::Shader::OpCode;
using Tegra::Shader::PredCondition;
u32 ShaderIR::DecodeXmad(NodeBlock& bb, u32 pc) {
const Instruction instr = {program_code[pc]};
const auto opcode = OpCode::Decode(instr);
UNIMPLEMENTED_IF(instr.xmad.sign_a);
UNIMPLEMENTED_IF(instr.xmad.sign_b);
UNIMPLEMENTED_IF_MSG(instr.generates_cc,
"Condition codes generation in XMAD is not implemented");
Node op_a = GetRegister(instr.gpr8);
// TODO(bunnei): Needs to be fixed once op_a or op_b is signed
UNIMPLEMENTED_IF(instr.xmad.sign_a != instr.xmad.sign_b);
const bool is_signed_a = instr.xmad.sign_a == 1;
const bool is_signed_b = instr.xmad.sign_b == 1;
const bool is_signed_c = is_signed_a;
auto [is_merge, is_psl, is_high_b, mode, op_b_binding,
op_c] = [&]() -> std::tuple<bool, bool, bool, Tegra::Shader::XmadMode, Node, Node> {
switch (opcode->get().GetId()) {
case OpCode::Id::XMAD_CR:
return {instr.xmad.merge_56,
instr.xmad.product_shift_left_second,
instr.xmad.high_b,
instr.xmad.mode_cbf,
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
GetRegister(instr.gpr39)};
case OpCode::Id::XMAD_RR:
return {instr.xmad.merge_37, instr.xmad.product_shift_left, instr.xmad.high_b_rr,
instr.xmad.mode, GetRegister(instr.gpr20), GetRegister(instr.gpr39)};
case OpCode::Id::XMAD_RC:
return {false,
false,
instr.xmad.high_b,
instr.xmad.mode_cbf,
GetRegister(instr.gpr39),
GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
case OpCode::Id::XMAD_IMM:
return {instr.xmad.merge_37,
instr.xmad.product_shift_left,
false,
instr.xmad.mode,
Immediate(static_cast<u32>(instr.xmad.imm20_16)),
GetRegister(instr.gpr39)};
default:
UNIMPLEMENTED_MSG("Unhandled XMAD instruction: {}", opcode->get().GetName());
return {false, false, false, Tegra::Shader::XmadMode::None, Immediate(0), Immediate(0)};
}
}();
op_a = SignedOperation(OperationCode::IBitfieldExtract, is_signed_a, std::move(op_a),
instr.xmad.high_a ? Immediate(16) : Immediate(0), Immediate(16));
const Node original_b = op_b_binding;
const Node op_b =
SignedOperation(OperationCode::IBitfieldExtract, is_signed_b, std::move(op_b_binding),
is_high_b ? Immediate(16) : Immediate(0), Immediate(16));
// we already check sign_a and sign_b is difference or not before so just use one in here.
Node product = SignedOperation(OperationCode::IMul, is_signed_a, op_a, op_b);
if (is_psl) {
product =
SignedOperation(OperationCode::ILogicalShiftLeft, is_signed_a, product, Immediate(16));
}
SetTemporary(bb, 0, product);
product = GetTemporary(0);
Node original_c = op_c;
const Tegra::Shader::XmadMode set_mode = mode; // Workaround to clang compile error
op_c = [&] {
switch (set_mode) {
case Tegra::Shader::XmadMode::None:
return original_c;
case Tegra::Shader::XmadMode::CLo:
return BitfieldExtract(std::move(original_c), 0, 16);
case Tegra::Shader::XmadMode::CHi:
return BitfieldExtract(std::move(original_c), 16, 16);
case Tegra::Shader::XmadMode::CBcc: {
Node shifted_b = SignedOperation(OperationCode::ILogicalShiftLeft, is_signed_b,
original_b, Immediate(16));
return SignedOperation(OperationCode::IAdd, is_signed_c, std::move(original_c),
std::move(shifted_b));
}
case Tegra::Shader::XmadMode::CSfu: {
const Node comp_a =
GetPredicateComparisonInteger(PredCondition::EQ, is_signed_a, op_a, Immediate(0));
const Node comp_b =
GetPredicateComparisonInteger(PredCondition::EQ, is_signed_b, op_b, Immediate(0));
const Node comp = Operation(OperationCode::LogicalOr, comp_a, comp_b);
const Node comp_minus_a = GetPredicateComparisonInteger(
PredCondition::NE, is_signed_a,
SignedOperation(OperationCode::IBitwiseAnd, is_signed_a, op_a,
Immediate(0x80000000)),
Immediate(0));
const Node comp_minus_b = GetPredicateComparisonInteger(
PredCondition::NE, is_signed_b,
SignedOperation(OperationCode::IBitwiseAnd, is_signed_b, op_b,
Immediate(0x80000000)),
Immediate(0));
Node new_c = Operation(
OperationCode::Select, comp_minus_a,
SignedOperation(OperationCode::IAdd, is_signed_c, original_c, Immediate(-65536)),
original_c);
new_c = Operation(
OperationCode::Select, comp_minus_b,
SignedOperation(OperationCode::IAdd, is_signed_c, new_c, Immediate(-65536)),
std::move(new_c));
return Operation(OperationCode::Select, comp, original_c, std::move(new_c));
}
default:
UNREACHABLE();
return Immediate(0);
}
}();
SetTemporary(bb, 1, op_c);
op_c = GetTemporary(1);
// TODO(Rodrigo): Use an appropiate sign for this operation
Node sum = SignedOperation(OperationCode::IAdd, is_signed_a, product, std::move(op_c));
SetTemporary(bb, 2, sum);
sum = GetTemporary(2);
if (is_merge) {
const Node a = SignedOperation(OperationCode::IBitfieldExtract, is_signed_a, std::move(sum),
Immediate(0), Immediate(16));
const Node b = SignedOperation(OperationCode::ILogicalShiftLeft, is_signed_b, original_b,
Immediate(16));
sum = SignedOperation(OperationCode::IBitwiseOr, is_signed_a, a, b);
}
SetInternalFlagsFromInteger(bb, sum, instr.generates_cc);
SetRegister(bb, instr.gpr0, std::move(sum));
return pc;
}
} // namespace VideoCommon::Shader

93
src/video_core/shader/expr.cpp
View file

@ -1,93 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <memory>
#include <variant>
#include "video_core/shader/expr.h"
namespace VideoCommon::Shader {
namespace {
bool ExprIsBoolean(const Expr& expr) {
return std::holds_alternative<ExprBoolean>(*expr);
}
bool ExprBooleanGet(const Expr& expr) {
return std::get_if<ExprBoolean>(expr.get())->value;
}
} // Anonymous namespace
bool ExprAnd::operator==(const ExprAnd& b) const {
return (*operand1 == *b.operand1) && (*operand2 == *b.operand2);
}
bool ExprAnd::operator!=(const ExprAnd& b) const {
return !operator==(b);
}
bool ExprOr::operator==(const ExprOr& b) const {
return (*operand1 == *b.operand1) && (*operand2 == *b.operand2);
}
bool ExprOr::operator!=(const ExprOr& b) const {
return !operator==(b);
}
bool ExprNot::operator==(const ExprNot& b) const {
return *operand1 == *b.operand1;
}
bool ExprNot::operator!=(const ExprNot& b) const {
return !operator==(b);
}
Expr MakeExprNot(Expr first) {
if (std::holds_alternative<ExprNot>(*first)) {
return std::get_if<ExprNot>(first.get())->operand1;
}
return MakeExpr<ExprNot>(std::move(first));
}
Expr MakeExprAnd(Expr first, Expr second) {
if (ExprIsBoolean(first)) {
return ExprBooleanGet(first) ? second : first;
}
if (ExprIsBoolean(second)) {
return ExprBooleanGet(second) ? first : second;
}
return MakeExpr<ExprAnd>(std::move(first), std::move(second));
}
Expr MakeExprOr(Expr first, Expr second) {
if (ExprIsBoolean(first)) {
return ExprBooleanGet(first) ? first : second;
}
if (ExprIsBoolean(second)) {
return ExprBooleanGet(second) ? second : first;
}
return MakeExpr<ExprOr>(std::move(first), std::move(second));
}
bool ExprAreEqual(const Expr& first, const Expr& second) {
return (*first) == (*second);
}
bool ExprAreOpposite(const Expr& first, const Expr& second) {
if (std::holds_alternative<ExprNot>(*first)) {
return ExprAreEqual(std::get_if<ExprNot>(first.get())->operand1, second);
}
if (std::holds_alternative<ExprNot>(*second)) {
return ExprAreEqual(std::get_if<ExprNot>(second.get())->operand1, first);
}
return false;
}
bool ExprIsTrue(const Expr& first) {
if (ExprIsBoolean(first)) {
return ExprBooleanGet(first);
}
return false;
}
} // namespace VideoCommon::Shader

156
src/video_core/shader/expr.h
View file

@ -1,156 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <memory>
#include <variant>
#include "video_core/engines/shader_bytecode.h"
namespace VideoCommon::Shader {
using Tegra::Shader::ConditionCode;
using Tegra::Shader::Pred;
class ExprAnd;
class ExprBoolean;
class ExprCondCode;
class ExprGprEqual;
class ExprNot;
class ExprOr;
class ExprPredicate;
class ExprVar;
using ExprData = std::variant<ExprVar, ExprCondCode, ExprPredicate, ExprNot, ExprOr, ExprAnd,
ExprBoolean, ExprGprEqual>;
using Expr = std::shared_ptr<ExprData>;
class ExprAnd final {
public:
explicit ExprAnd(Expr a, Expr b) : operand1{std::move(a)}, operand2{std::move(b)} {}
bool operator==(const ExprAnd& b) const;
bool operator!=(const ExprAnd& b) const;
Expr operand1;
Expr operand2;
};
class ExprOr final {
public:
explicit ExprOr(Expr a, Expr b) : operand1{std::move(a)}, operand2{std::move(b)} {}
bool operator==(const ExprOr& b) const;
bool operator!=(const ExprOr& b) const;
Expr operand1;
Expr operand2;
};
class ExprNot final {
public:
explicit ExprNot(Expr a) : operand1{std::move(a)} {}
bool operator==(const ExprNot& b) const;
bool operator!=(const ExprNot& b) const;
Expr operand1;
};
class ExprVar final {
public:
explicit ExprVar(u32 index) : var_index{index} {}
bool operator==(const ExprVar& b) const {
return var_index == b.var_index;
}
bool operator!=(const ExprVar& b) const {
return !operator==(b);
}
u32 var_index;
};
class ExprPredicate final {
public:
explicit ExprPredicate(u32 predicate_) : predicate{predicate_} {}
bool operator==(const ExprPredicate& b) const {
return predicate == b.predicate;
}
bool operator!=(const ExprPredicate& b) const {
return !operator==(b);
}
u32 predicate;
};
class ExprCondCode final {
public:
explicit ExprCondCode(ConditionCode condition_code) : cc{condition_code} {}
bool operator==(const ExprCondCode& b) const {
return cc == b.cc;
}
bool operator!=(const ExprCondCode& b) const {
return !operator==(b);
}
ConditionCode cc;
};
class ExprBoolean final {
public:
explicit ExprBoolean(bool val) : value{val} {}
bool operator==(const ExprBoolean& b) const {
return value == b.value;
}
bool operator!=(const ExprBoolean& b) const {
return !operator==(b);
}
bool value;
};
class ExprGprEqual final {
public:
explicit ExprGprEqual(u32 gpr_, u32 value_) : gpr{gpr_}, value{value_} {}
bool operator==(const ExprGprEqual& b) const {
return gpr == b.gpr && value == b.value;
}
bool operator!=(const ExprGprEqual& b) const {
return !operator==(b);
}
u32 gpr;
u32 value;
};
template <typename T, typename... Args>
Expr MakeExpr(Args&&... args) {
static_assert(std::is_convertible_v<T, ExprData>);
return std::make_shared<ExprData>(T(std::forward<Args>(args)...));
}
bool ExprAreEqual(const Expr& first, const Expr& second);
bool ExprAreOpposite(const Expr& first, const Expr& second);
Expr MakeExprNot(Expr first);
Expr MakeExprAnd(Expr first, Expr second);
Expr MakeExprOr(Expr first, Expr second);
bool ExprIsTrue(const Expr& first);
} // namespace VideoCommon::Shader

76
src/video_core/shader/memory_util.cpp
View file

@ -1,76 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <cstddef>
#include <boost/container_hash/hash.hpp>
#include "common/common_types.h"
#include "core/core.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/memory_manager.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
GPUVAddr GetShaderAddress(Tegra::Engines::Maxwell3D& maxwell3d,
Tegra::Engines::Maxwell3D::Regs::ShaderProgram program) {
const auto& shader_config{maxwell3d.regs.shader_config[static_cast<std::size_t>(program)]};
return maxwell3d.regs.code_address.CodeAddress() + shader_config.offset;
}
bool IsSchedInstruction(std::size_t offset, std::size_t main_offset) {
// Sched instructions appear once every 4 instructions.
constexpr std::size_t SchedPeriod = 4;
const std::size_t absolute_offset = offset - main_offset;
return (absolute_offset % SchedPeriod) == 0;
}
std::size_t CalculateProgramSize(const ProgramCode& program, bool is_compute) {
// This is the encoded version of BRA that jumps to itself. All Nvidia
// shaders end with one.
static constexpr u64 SELF_JUMPING_BRANCH = 0xE2400FFFFF07000FULL;
static constexpr u64 MASK = 0xFFFFFFFFFF7FFFFFULL;
const std::size_t start_offset = is_compute ? KERNEL_MAIN_OFFSET : STAGE_MAIN_OFFSET;
std::size_t offset = start_offset;
while (offset < program.size()) {
const u64 instruction = program[offset];
if (!IsSchedInstruction(offset, start_offset)) {
if ((instruction & MASK) == SELF_JUMPING_BRANCH) {
// End on Maxwell's "nop" instruction
break;
}
if (instruction == 0) {
break;
}
}
++offset;
}
// The last instruction is included in the program size
return std::min(offset + 1, program.size());
}
ProgramCode GetShaderCode(Tegra::MemoryManager& memory_manager, GPUVAddr gpu_addr,
const u8* host_ptr, bool is_compute) {
ProgramCode code(VideoCommon::Shader::MAX_PROGRAM_LENGTH);
ASSERT_OR_EXECUTE(host_ptr != nullptr, { return code; });
memory_manager.ReadBlockUnsafe(gpu_addr, code.data(), code.size() * sizeof(u64));
code.resize(CalculateProgramSize(code, is_compute));
return code;
}
u64 GetUniqueIdentifier(Tegra::Engines::ShaderType shader_type, bool is_a, const ProgramCode& code,
const ProgramCode& code_b) {
size_t unique_identifier = boost::hash_value(code);
if (is_a) {
// VertexA programs include two programs
boost::hash_combine(unique_identifier, boost::hash_value(code_b));
}
return static_cast<u64>(unique_identifier);
}
} // namespace VideoCommon::Shader

43
src/video_core/shader/memory_util.h
View file

@ -1,43 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <cstddef>
#include <vector>
#include "common/common_types.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_type.h"
namespace Tegra {
class MemoryManager;
}
namespace VideoCommon::Shader {
using ProgramCode = std::vector<u64>;
constexpr u32 STAGE_MAIN_OFFSET = 10;
constexpr u32 KERNEL_MAIN_OFFSET = 0;
/// Gets the address for the specified shader stage program
GPUVAddr GetShaderAddress(Tegra::Engines::Maxwell3D& maxwell3d,
Tegra::Engines::Maxwell3D::Regs::ShaderProgram program);
/// Gets if the current instruction offset is a scheduler instruction
bool IsSchedInstruction(std::size_t offset, std::size_t main_offset);
/// Calculates the size of a program stream
std::size_t CalculateProgramSize(const ProgramCode& program, bool is_compute);
/// Gets the shader program code from memory for the specified address
ProgramCode GetShaderCode(Tegra::MemoryManager& memory_manager, GPUVAddr gpu_addr,
const u8* host_ptr, bool is_compute);
/// Hashes one (or two) program streams
u64 GetUniqueIdentifier(Tegra::Engines::ShaderType shader_type, bool is_a, const ProgramCode& code,
const ProgramCode& code_b = {});
} // namespace VideoCommon::Shader

701
src/video_core/shader/node.h
View file

@ -1,701 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <array>
#include <cstddef>
#include <memory>
#include <optional>
#include <string>
#include <tuple>
#include <utility>
#include <variant>
#include <vector>
#include "common/common_types.h"
#include "video_core/engines/shader_bytecode.h"
namespace VideoCommon::Shader {
enum class OperationCode {
Assign, /// (float& dest, float src) -> void
Select, /// (MetaArithmetic, bool pred, float a, float b) -> float
FAdd, /// (MetaArithmetic, float a, float b) -> float
FMul, /// (MetaArithmetic, float a, float b) -> float
FDiv, /// (MetaArithmetic, float a, float b) -> float
FFma, /// (MetaArithmetic, float a, float b, float c) -> float
FNegate, /// (MetaArithmetic, float a) -> float
FAbsolute, /// (MetaArithmetic, float a) -> float
FClamp, /// (MetaArithmetic, float value, float min, float max) -> float
FCastHalf0, /// (MetaArithmetic, f16vec2 a) -> float
FCastHalf1, /// (MetaArithmetic, f16vec2 a) -> float
FMin, /// (MetaArithmetic, float a, float b) -> float
FMax, /// (MetaArithmetic, float a, float b) -> float
FCos, /// (MetaArithmetic, float a) -> float
FSin, /// (MetaArithmetic, float a) -> float
FExp2, /// (MetaArithmetic, float a) -> float
FLog2, /// (MetaArithmetic, float a) -> float
FInverseSqrt, /// (MetaArithmetic, float a) -> float
FSqrt, /// (MetaArithmetic, float a) -> float
FRoundEven, /// (MetaArithmetic, float a) -> float
FFloor, /// (MetaArithmetic, float a) -> float
FCeil, /// (MetaArithmetic, float a) -> float
FTrunc, /// (MetaArithmetic, float a) -> float
FCastInteger, /// (MetaArithmetic, int a) -> float
FCastUInteger, /// (MetaArithmetic, uint a) -> float
FSwizzleAdd, /// (float a, float b, uint mask) -> float
IAdd, /// (MetaArithmetic, int a, int b) -> int
IMul, /// (MetaArithmetic, int a, int b) -> int
IDiv, /// (MetaArithmetic, int a, int b) -> int
INegate, /// (MetaArithmetic, int a) -> int
IAbsolute, /// (MetaArithmetic, int a) -> int
IMin, /// (MetaArithmetic, int a, int b) -> int
IMax, /// (MetaArithmetic, int a, int b) -> int
ICastFloat, /// (MetaArithmetic, float a) -> int
ICastUnsigned, /// (MetaArithmetic, uint a) -> int
ILogicalShiftLeft, /// (MetaArithmetic, int a, uint b) -> int
ILogicalShiftRight, /// (MetaArithmetic, int a, uint b) -> int
IArithmeticShiftRight, /// (MetaArithmetic, int a, uint b) -> int
IBitwiseAnd, /// (MetaArithmetic, int a, int b) -> int
IBitwiseOr, /// (MetaArithmetic, int a, int b) -> int
IBitwiseXor, /// (MetaArithmetic, int a, int b) -> int
IBitwiseNot, /// (MetaArithmetic, int a) -> int
IBitfieldInsert, /// (MetaArithmetic, int base, int insert, int offset, int bits) -> int
IBitfieldExtract, /// (MetaArithmetic, int value, int offset, int offset) -> int
IBitCount, /// (MetaArithmetic, int) -> int
IBitMSB, /// (MetaArithmetic, int) -> int
UAdd, /// (MetaArithmetic, uint a, uint b) -> uint
UMul, /// (MetaArithmetic, uint a, uint b) -> uint
UDiv, /// (MetaArithmetic, uint a, uint b) -> uint
UMin, /// (MetaArithmetic, uint a, uint b) -> uint
UMax, /// (MetaArithmetic, uint a, uint b) -> uint
UCastFloat, /// (MetaArithmetic, float a) -> uint
UCastSigned, /// (MetaArithmetic, int a) -> uint
ULogicalShiftLeft, /// (MetaArithmetic, uint a, uint b) -> uint
ULogicalShiftRight, /// (MetaArithmetic, uint a, uint b) -> uint
UArithmeticShiftRight, /// (MetaArithmetic, uint a, uint b) -> uint
UBitwiseAnd, /// (MetaArithmetic, uint a, uint b) -> uint
UBitwiseOr, /// (MetaArithmetic, uint a, uint b) -> uint
UBitwiseXor, /// (MetaArithmetic, uint a, uint b) -> uint
UBitwiseNot, /// (MetaArithmetic, uint a) -> uint
UBitfieldInsert, /// (MetaArithmetic, uint base, uint insert, int offset, int bits) -> uint
UBitfieldExtract, /// (MetaArithmetic, uint value, int offset, int offset) -> uint
UBitCount, /// (MetaArithmetic, uint) -> uint
UBitMSB, /// (MetaArithmetic, uint) -> uint
HAdd, /// (MetaArithmetic, f16vec2 a, f16vec2 b) -> f16vec2
HMul, /// (MetaArithmetic, f16vec2 a, f16vec2 b) -> f16vec2
HFma, /// (MetaArithmetic, f16vec2 a, f16vec2 b, f16vec2 c) -> f16vec2
HAbsolute, /// (f16vec2 a) -> f16vec2
HNegate, /// (f16vec2 a, bool first, bool second) -> f16vec2
HClamp, /// (f16vec2 src, float min, float max) -> f16vec2
HCastFloat, /// (MetaArithmetic, float a) -> f16vec2
HUnpack, /// (Tegra::Shader::HalfType, T value) -> f16vec2
HMergeF32, /// (f16vec2 src) -> float
HMergeH0, /// (f16vec2 dest, f16vec2 src) -> f16vec2
HMergeH1, /// (f16vec2 dest, f16vec2 src) -> f16vec2
HPack2, /// (float a, float b) -> f16vec2
LogicalAssign, /// (bool& dst, bool src) -> void
LogicalAnd, /// (bool a, bool b) -> bool
LogicalOr, /// (bool a, bool b) -> bool
LogicalXor, /// (bool a, bool b) -> bool
LogicalNegate, /// (bool a) -> bool
LogicalPick2, /// (bool2 pair, uint index) -> bool
LogicalAnd2, /// (bool2 a) -> bool
LogicalFOrdLessThan, /// (float a, float b) -> bool
LogicalFOrdEqual, /// (float a, float b) -> bool
LogicalFOrdLessEqual, /// (float a, float b) -> bool
LogicalFOrdGreaterThan, /// (float a, float b) -> bool
LogicalFOrdNotEqual, /// (float a, float b) -> bool
LogicalFOrdGreaterEqual, /// (float a, float b) -> bool
LogicalFOrdered, /// (float a, float b) -> bool
LogicalFUnordered, /// (float a, float b) -> bool
LogicalFUnordLessThan, /// (float a, float b) -> bool
LogicalFUnordEqual, /// (float a, float b) -> bool
LogicalFUnordLessEqual, /// (float a, float b) -> bool
LogicalFUnordGreaterThan, /// (float a, float b) -> bool
LogicalFUnordNotEqual, /// (float a, float b) -> bool
LogicalFUnordGreaterEqual, /// (float a, float b) -> bool
LogicalILessThan, /// (int a, int b) -> bool
LogicalIEqual, /// (int a, int b) -> bool
LogicalILessEqual, /// (int a, int b) -> bool
LogicalIGreaterThan, /// (int a, int b) -> bool
LogicalINotEqual, /// (int a, int b) -> bool
LogicalIGreaterEqual, /// (int a, int b) -> bool
LogicalULessThan, /// (uint a, uint b) -> bool
LogicalUEqual, /// (uint a, uint b) -> bool
LogicalULessEqual, /// (uint a, uint b) -> bool
LogicalUGreaterThan, /// (uint a, uint b) -> bool
LogicalUNotEqual, /// (uint a, uint b) -> bool
LogicalUGreaterEqual, /// (uint a, uint b) -> bool
LogicalAddCarry, /// (uint a, uint b) -> bool
Logical2HLessThan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HEqual, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HLessEqual, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HGreaterThan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HNotEqual, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HGreaterEqual, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HLessThanWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HEqualWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HLessEqualWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HGreaterThanWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HNotEqualWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Logical2HGreaterEqualWithNan, /// (MetaHalfArithmetic, f16vec2 a, f16vec2) -> bool2
Texture, /// (MetaTexture, float[N] coords) -> float4
TextureLod, /// (MetaTexture, float[N] coords) -> float4
TextureGather, /// (MetaTexture, float[N] coords) -> float4
TextureQueryDimensions, /// (MetaTexture, float a) -> float4
TextureQueryLod, /// (MetaTexture, float[N] coords) -> float4
TexelFetch, /// (MetaTexture, int[N], int) -> float4
TextureGradient, /// (MetaTexture, float[N] coords, float[N*2] derivates) -> float4
ImageLoad, /// (MetaImage, int[N] coords) -> void
ImageStore, /// (MetaImage, int[N] coords) -> void
AtomicImageAdd, /// (MetaImage, int[N] coords) -> void
AtomicImageAnd, /// (MetaImage, int[N] coords) -> void
AtomicImageOr, /// (MetaImage, int[N] coords) -> void
AtomicImageXor, /// (MetaImage, int[N] coords) -> void
AtomicImageExchange, /// (MetaImage, int[N] coords) -> void
AtomicUExchange, /// (memory, uint) -> uint
AtomicUAdd, /// (memory, uint) -> uint
AtomicUMin, /// (memory, uint) -> uint
AtomicUMax, /// (memory, uint) -> uint
AtomicUAnd, /// (memory, uint) -> uint
AtomicUOr, /// (memory, uint) -> uint
AtomicUXor, /// (memory, uint) -> uint
AtomicIExchange, /// (memory, int) -> int
AtomicIAdd, /// (memory, int) -> int
AtomicIMin, /// (memory, int) -> int
AtomicIMax, /// (memory, int) -> int
AtomicIAnd, /// (memory, int) -> int
AtomicIOr, /// (memory, int) -> int
AtomicIXor, /// (memory, int) -> int
ReduceUAdd, /// (memory, uint) -> void
ReduceUMin, /// (memory, uint) -> void
ReduceUMax, /// (memory, uint) -> void
ReduceUAnd, /// (memory, uint) -> void
ReduceUOr, /// (memory, uint) -> void
ReduceUXor, /// (memory, uint) -> void
ReduceIAdd, /// (memory, int) -> void
ReduceIMin, /// (memory, int) -> void
ReduceIMax, /// (memory, int) -> void
ReduceIAnd, /// (memory, int) -> void
ReduceIOr, /// (memory, int) -> void
ReduceIXor, /// (memory, int) -> void
Branch, /// (uint branch_target) -> void
BranchIndirect, /// (uint branch_target) -> void
PushFlowStack, /// (uint branch_target) -> void
PopFlowStack, /// () -> void
Exit, /// () -> void
Discard, /// () -> void
EmitVertex, /// () -> void
EndPrimitive, /// () -> void
InvocationId, /// () -> int
YNegate, /// () -> float
LocalInvocationIdX, /// () -> uint
LocalInvocationIdY, /// () -> uint
LocalInvocationIdZ, /// () -> uint
WorkGroupIdX, /// () -> uint
WorkGroupIdY, /// () -> uint
WorkGroupIdZ, /// () -> uint
BallotThread, /// (bool) -> uint
VoteAll, /// (bool) -> bool
VoteAny, /// (bool) -> bool
VoteEqual, /// (bool) -> bool
ThreadId, /// () -> uint
ThreadEqMask, /// () -> uint
ThreadGeMask, /// () -> uint
ThreadGtMask, /// () -> uint
ThreadLeMask, /// () -> uint
ThreadLtMask, /// () -> uint
ShuffleIndexed, /// (uint value, uint index) -> uint
Barrier, /// () -> void
MemoryBarrierGroup, /// () -> void
MemoryBarrierGlobal, /// () -> void
Amount,
};
enum class InternalFlag {
Zero = 0,
Sign = 1,
Carry = 2,
Overflow = 3,
Amount = 4,
};
enum class MetaStackClass {
Ssy,
Pbk,
};
class OperationNode;
class ConditionalNode;
class GprNode;
class CustomVarNode;
class ImmediateNode;
class InternalFlagNode;
class PredicateNode;
class AbufNode;
class CbufNode;
class LmemNode;
class PatchNode;
class SmemNode;
class GmemNode;
class CommentNode;
using NodeData = std::variant<OperationNode, ConditionalNode, GprNode, CustomVarNode, ImmediateNode,
InternalFlagNode, PredicateNode, AbufNode, PatchNode, CbufNode,
LmemNode, SmemNode, GmemNode, CommentNode>;
using Node = std::shared_ptr<NodeData>;
using Node4 = std::array<Node, 4>;
using NodeBlock = std::vector<Node>;
struct ArraySamplerNode;
struct BindlessSamplerNode;
struct SeparateSamplerNode;
using TrackSamplerData = std::variant<BindlessSamplerNode, SeparateSamplerNode, ArraySamplerNode>;
using TrackSampler = std::shared_ptr<TrackSamplerData>;
struct SamplerEntry {
/// Bound samplers constructor
explicit SamplerEntry(u32 index_, u32 offset_, Tegra::Shader::TextureType type_, bool is_array_,
bool is_shadow_, bool is_buffer_, bool is_indexed_)
: index{index_}, offset{offset_}, type{type_}, is_array{is_array_}, is_shadow{is_shadow_},
is_buffer{is_buffer_}, is_indexed{is_indexed_} {}
/// Separate sampler constructor
explicit SamplerEntry(u32 index_, std::pair<u32, u32> offsets, std::pair<u32, u32> buffers,
Tegra::Shader::TextureType type_, bool is_array_, bool is_shadow_,
bool is_buffer_)
: index{index_}, offset{offsets.first}, secondary_offset{offsets.second},
buffer{buffers.first}, secondary_buffer{buffers.second}, type{type_}, is_array{is_array_},
is_shadow{is_shadow_}, is_buffer{is_buffer_}, is_separated{true} {}
/// Bindless samplers constructor
explicit SamplerEntry(u32 index_, u32 offset_, u32 buffer_, Tegra::Shader::TextureType type_,
bool is_array_, bool is_shadow_, bool is_buffer_, bool is_indexed_)
: index{index_}, offset{offset_}, buffer{buffer_}, type{type_}, is_array{is_array_},
is_shadow{is_shadow_}, is_buffer{is_buffer_}, is_bindless{true}, is_indexed{is_indexed_} {
}
u32 index = 0; ///< Emulated index given for the this sampler.
u32 offset = 0; ///< Offset in the const buffer from where the sampler is being read.
u32 secondary_offset = 0; ///< Secondary offset in the const buffer.
u32 buffer = 0; ///< Buffer where the bindless sampler is read.
u32 secondary_buffer = 0; ///< Secondary buffer where the bindless sampler is read.
u32 size = 1; ///< Size of the sampler.
Tegra::Shader::TextureType type{}; ///< The type used to sample this texture (Texture2D, etc)
bool is_array = false; ///< Whether the texture is being sampled as an array texture or not.
bool is_shadow = false; ///< Whether the texture is being sampled as a depth texture or not.
bool is_buffer = false; ///< Whether the texture is a texture buffer without sampler.
bool is_bindless = false; ///< Whether this sampler belongs to a bindless texture or not.
bool is_indexed = false; ///< Whether this sampler is an indexed array of textures.
bool is_separated = false; ///< Whether the image and sampler is separated or not.
};
/// Represents a tracked bindless sampler into a direct const buffer
struct ArraySamplerNode {
u32 index;
u32 base_offset;
u32 bindless_var;
};
/// Represents a tracked separate sampler image pair that was folded statically
struct SeparateSamplerNode {
std::pair<u32, u32> indices;
std::pair<u32, u32> offsets;
};
/// Represents a tracked bindless sampler into a direct const buffer
struct BindlessSamplerNode {
u32 index;
u32 offset;
};
struct ImageEntry {
public:
/// Bound images constructor
explicit ImageEntry(u32 index_, u32 offset_, Tegra::Shader::ImageType type_)
: index{index_}, offset{offset_}, type{type_} {}
/// Bindless samplers constructor
explicit ImageEntry(u32 index_, u32 offset_, u32 buffer_, Tegra::Shader::ImageType type_)
: index{index_}, offset{offset_}, buffer{buffer_}, type{type_}, is_bindless{true} {}
void MarkWrite() {
is_written = true;
}
void MarkRead() {
is_read = true;
}
void MarkAtomic() {
MarkWrite();
MarkRead();
is_atomic = true;
}
u32 index = 0;
u32 offset = 0;
u32 buffer = 0;
Tegra::Shader::ImageType type{};
bool is_bindless = false;
bool is_written = false;
bool is_read = false;
bool is_atomic = false;
};
struct GlobalMemoryBase {
u32 cbuf_index = 0;
u32 cbuf_offset = 0;
[[nodiscard]] bool operator<(const GlobalMemoryBase& rhs) const {
return std::tie(cbuf_index, cbuf_offset) < std::tie(rhs.cbuf_index, rhs.cbuf_offset);
}
};
/// Parameters describing an arithmetic operation
struct MetaArithmetic {
bool precise{}; ///< Whether the operation can be constraint or not
};
/// Parameters describing a texture sampler
struct MetaTexture {
SamplerEntry sampler;
Node array;
Node depth_compare;
std::vector<Node> aoffi;
std::vector<Node> ptp;
std::vector<Node> derivates;
Node bias;
Node lod;
Node component;
u32 element{};
Node index;
};
struct MetaImage {
const ImageEntry& image;
std::vector<Node> values;
u32 element{};
};
/// Parameters that modify an operation but are not part of any particular operand
using Meta =
std::variant<MetaArithmetic, MetaTexture, MetaImage, MetaStackClass, Tegra::Shader::HalfType>;
class AmendNode {
public:
[[nodiscard]] std::optional<std::size_t> GetAmendIndex() const {
if (amend_index == amend_null_index) {
return std::nullopt;
}
return {amend_index};
}
void SetAmendIndex(std::size_t index) {
amend_index = index;
}
void ClearAmend() {
amend_index = amend_null_index;
}
private:
static constexpr std::size_t amend_null_index = 0xFFFFFFFFFFFFFFFFULL;
std::size_t amend_index{amend_null_index};
};
/// Holds any kind of operation that can be done in the IR
class OperationNode final : public AmendNode {
public:
explicit OperationNode(OperationCode code_) : OperationNode(code_, Meta{}) {}
explicit OperationNode(OperationCode code_, Meta meta_)
: OperationNode(code_, std::move(meta_), std::vector<Node>{}) {}
explicit OperationNode(OperationCode code_, std::vector<Node> operands_)
: OperationNode(code_, Meta{}, std::move(operands_)) {}
explicit OperationNode(OperationCode code_, Meta meta_, std::vector<Node> operands_)
: code{code_}, meta{std::move(meta_)}, operands{std::move(operands_)} {}
template <typename... Args>
explicit OperationNode(OperationCode code_, Meta meta_, Args&&... operands_)
: code{code_}, meta{std::move(meta_)}, operands{operands_...} {}
[[nodiscard]] OperationCode GetCode() const {
return code;
}
[[nodiscard]] const Meta& GetMeta() const {
return meta;
}
[[nodiscard]] std::size_t GetOperandsCount() const {
return operands.size();
}
[[nodiscard]] const Node& operator[](std::size_t operand_index) const {
return operands.at(operand_index);
}
private:
OperationCode code{};
Meta meta{};
std::vector<Node> operands;
};
/// Encloses inside any kind of node that returns a boolean conditionally-executed code
class ConditionalNode final : public AmendNode {
public:
explicit ConditionalNode(Node condition_, std::vector<Node>&& code_)
: condition{std::move(condition_)}, code{std::move(code_)} {}
[[nodiscard]] const Node& GetCondition() const {
return condition;
}
[[nodiscard]] const std::vector<Node>& GetCode() const {
return code;
}
private:
Node condition; ///< Condition to be satisfied
std::vector<Node> code; ///< Code to execute
};
/// A general purpose register
class GprNode final {
public:
explicit constexpr GprNode(Tegra::Shader::Register index_) : index{index_} {}
[[nodiscard]] constexpr u32 GetIndex() const {
return static_cast<u32>(index);
}
private:
Tegra::Shader::Register index{};
};
/// A custom variable
class CustomVarNode final {
public:
explicit constexpr CustomVarNode(u32 index_) : index{index_} {}
[[nodiscard]] constexpr u32 GetIndex() const {
return index;
}
private:
u32 index{};
};
/// A 32-bits value that represents an immediate value
class ImmediateNode final {
public:
explicit constexpr ImmediateNode(u32 value_) : value{value_} {}
[[nodiscard]] constexpr u32 GetValue() const {
return value;
}
private:
u32 value{};
};
/// One of Maxwell's internal flags
class InternalFlagNode final {
public:
explicit constexpr InternalFlagNode(InternalFlag flag_) : flag{flag_} {}
[[nodiscard]] constexpr InternalFlag GetFlag() const {
return flag;
}
private:
InternalFlag flag{};
};
/// A predicate register, it can be negated without additional nodes
class PredicateNode final {
public:
explicit constexpr PredicateNode(Tegra::Shader::Pred index_, bool negated_)
: index{index_}, negated{negated_} {}
[[nodiscard]] constexpr Tegra::Shader::Pred GetIndex() const {
return index;
}
[[nodiscard]] constexpr bool IsNegated() const {
return negated;
}
private:
Tegra::Shader::Pred index{};
bool negated{};
};
/// Attribute buffer memory (known as attributes or varyings in GLSL terms)
class AbufNode final {
public:
// Initialize for standard attributes (index is explicit).
explicit AbufNode(Tegra::Shader::Attribute::Index index_, u32 element_, Node buffer_ = {})
: buffer{std::move(buffer_)}, index{index_}, element{element_} {}
// Initialize for physical attributes (index is a variable value).
explicit AbufNode(Node physical_address_, Node buffer_ = {})
: physical_address{std::move(physical_address_)}, buffer{std::move(buffer_)} {}
[[nodiscard]] Tegra::Shader::Attribute::Index GetIndex() const {
return index;
}
[[nodiscard]] u32 GetElement() const {
return element;
}
[[nodiscard]] const Node& GetBuffer() const {
return buffer;
}
[[nodiscard]] bool IsPhysicalBuffer() const {
return static_cast<bool>(physical_address);
}
[[nodiscard]] const Node& GetPhysicalAddress() const {
return physical_address;
}
private:
Node physical_address;
Node buffer;
Tegra::Shader::Attribute::Index index{};
u32 element{};
};
/// Patch memory (used to communicate tessellation stages).
class PatchNode final {
public:
explicit constexpr PatchNode(u32 offset_) : offset{offset_} {}
[[nodiscard]] constexpr u32 GetOffset() const {
return offset;
}
private:
u32 offset{};
};
/// Constant buffer node, usually mapped to uniform buffers in GLSL
class CbufNode final {
public:
explicit CbufNode(u32 index_, Node offset_) : index{index_}, offset{std::move(offset_)} {}
[[nodiscard]] u32 GetIndex() const {
return index;
}
[[nodiscard]] const Node& GetOffset() const {
return offset;
}
private:
u32 index{};
Node offset;
};
/// Local memory node
class LmemNode final {
public:
explicit LmemNode(Node address_) : address{std::move(address_)} {}
[[nodiscard]] const Node& GetAddress() const {
return address;
}
private:
Node address;
};
/// Shared memory node
class SmemNode final {
public:
explicit SmemNode(Node address_) : address{std::move(address_)} {}
[[nodiscard]] const Node& GetAddress() const {
return address;
}
private:
Node address;
};
/// Global memory node
class GmemNode final {
public:
explicit GmemNode(Node real_address_, Node base_address_, const GlobalMemoryBase& descriptor_)
: real_address{std::move(real_address_)}, base_address{std::move(base_address_)},
descriptor{descriptor_} {}
[[nodiscard]] const Node& GetRealAddress() const {
return real_address;
}
[[nodiscard]] const Node& GetBaseAddress() const {
return base_address;
}
[[nodiscard]] const GlobalMemoryBase& GetDescriptor() const {
return descriptor;
}
private:
Node real_address;
Node base_address;
GlobalMemoryBase descriptor;
};
/// Commentary, can be dropped
class CommentNode final {
public:
explicit CommentNode(std::string text_) : text{std::move(text_)} {}
[[nodiscard]] const std::string& GetText() const {
return text;
}
private:
std::string text;
};
} // namespace VideoCommon::Shader

115
src/video_core/shader/node_helper.cpp
View file

@ -1,115 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <cstring>
#include <vector>
#include "common/common_types.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
Node Conditional(Node condition, std::vector<Node> code) {
return MakeNode<ConditionalNode>(std::move(condition), std::move(code));
}
Node Comment(std::string text) {
return MakeNode<CommentNode>(std::move(text));
}
Node Immediate(u32 value) {
return MakeNode<ImmediateNode>(value);
}
Node Immediate(s32 value) {
return Immediate(static_cast<u32>(value));
}
Node Immediate(f32 value) {
u32 integral;
std::memcpy(&integral, &value, sizeof(u32));
return Immediate(integral);
}
OperationCode SignedToUnsignedCode(OperationCode operation_code, bool is_signed) {
if (is_signed) {
return operation_code;
}
switch (operation_code) {
case OperationCode::FCastInteger:
return OperationCode::FCastUInteger;
case OperationCode::IAdd:
return OperationCode::UAdd;
case OperationCode::IMul:
return OperationCode::UMul;
case OperationCode::IDiv:
return OperationCode::UDiv;
case OperationCode::IMin:
return OperationCode::UMin;
case OperationCode::IMax:
return OperationCode::UMax;
case OperationCode::ICastFloat:
return OperationCode::UCastFloat;
case OperationCode::ICastUnsigned:
return OperationCode::UCastSigned;
case OperationCode::ILogicalShiftLeft:
return OperationCode::ULogicalShiftLeft;
case OperationCode::ILogicalShiftRight:
return OperationCode::ULogicalShiftRight;
case OperationCode::IArithmeticShiftRight:
return OperationCode::UArithmeticShiftRight;
case OperationCode::IBitwiseAnd:
return OperationCode::UBitwiseAnd;
case OperationCode::IBitwiseOr:
return OperationCode::UBitwiseOr;
case OperationCode::IBitwiseXor:
return OperationCode::UBitwiseXor;
case OperationCode::IBitwiseNot:
return OperationCode::UBitwiseNot;
case OperationCode::IBitfieldExtract:
return OperationCode::UBitfieldExtract;
case OperationCode::IBitfieldInsert:
return OperationCode::UBitfieldInsert;
case OperationCode::IBitCount:
return OperationCode::UBitCount;
case OperationCode::LogicalILessThan:
return OperationCode::LogicalULessThan;
case OperationCode::LogicalIEqual:
return OperationCode::LogicalUEqual;
case OperationCode::LogicalILessEqual:
return OperationCode::LogicalULessEqual;
case OperationCode::LogicalIGreaterThan:
return OperationCode::LogicalUGreaterThan;
case OperationCode::LogicalINotEqual:
return OperationCode::LogicalUNotEqual;
case OperationCode::LogicalIGreaterEqual:
return OperationCode::LogicalUGreaterEqual;
case OperationCode::AtomicIExchange:
return OperationCode::AtomicUExchange;
case OperationCode::AtomicIAdd:
return OperationCode::AtomicUAdd;
case OperationCode::AtomicIMin:
return OperationCode::AtomicUMin;
case OperationCode::AtomicIMax:
return OperationCode::AtomicUMax;
case OperationCode::AtomicIAnd:
return OperationCode::AtomicUAnd;
case OperationCode::AtomicIOr:
return OperationCode::AtomicUOr;
case OperationCode::AtomicIXor:
return OperationCode::AtomicUXor;
case OperationCode::INegate:
UNREACHABLE_MSG("Can't negate an unsigned integer");
return {};
case OperationCode::IAbsolute:
UNREACHABLE_MSG("Can't apply absolute to an unsigned integer");
return {};
default:
UNREACHABLE_MSG("Unknown signed operation with code={}", operation_code);
return {};
}
}
} // namespace VideoCommon::Shader

71
src/video_core/shader/node_helper.h
View file

@ -1,71 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <memory>
#include <string>
#include <tuple>
#include <type_traits>
#include <utility>
#include <vector>
#include "common/common_types.h"
#include "video_core/shader/node.h"
namespace VideoCommon::Shader {
/// This arithmetic operation cannot be constraint
inline constexpr MetaArithmetic PRECISE = {true};
/// This arithmetic operation can be optimized away
inline constexpr MetaArithmetic NO_PRECISE = {false};
/// Creates a conditional node
Node Conditional(Node condition, std::vector<Node> code);
/// Creates a commentary node
Node Comment(std::string text);
/// Creates an u32 immediate
Node Immediate(u32 value);
/// Creates a s32 immediate
Node Immediate(s32 value);
/// Creates a f32 immediate
Node Immediate(f32 value);
/// Converts an signed operation code to an unsigned operation code
OperationCode SignedToUnsignedCode(OperationCode operation_code, bool is_signed);
template <typename T, typename... Args>
Node MakeNode(Args&&... args) {
static_assert(std::is_convertible_v<T, NodeData>);
return std::make_shared<NodeData>(T(std::forward<Args>(args)...));
}
template <typename T, typename... Args>
TrackSampler MakeTrackSampler(Args&&... args) {
static_assert(std::is_convertible_v<T, TrackSamplerData>);
return std::make_shared<TrackSamplerData>(T{std::forward<Args>(args)...});
}
template <typename... Args>
Node Operation(OperationCode code, Args&&... args) {
if constexpr (sizeof...(args) == 0) {
return MakeNode<OperationNode>(code);
} else if constexpr (std::is_convertible_v<std::tuple_element_t<0, std::tuple<Args...>>,
Meta>) {
return MakeNode<OperationNode>(code, std::forward<Args>(args)...);
} else {
return MakeNode<OperationNode>(code, Meta{}, std::forward<Args>(args)...);
}
}
template <typename... Args>
Node SignedOperation(OperationCode code, bool is_signed, Args&&... args) {
return Operation(SignedToUnsignedCode(code, is_signed), std::forward<Args>(args)...);
}
} // namespace VideoCommon::Shader

181
src/video_core/shader/registry.cpp
View file

@ -1,181 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <tuple>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/kepler_compute.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_type.h"
#include "video_core/shader/registry.h"
namespace VideoCommon::Shader {
using Tegra::Engines::ConstBufferEngineInterface;
using Tegra::Engines::SamplerDescriptor;
using Tegra::Engines::ShaderType;
namespace {
GraphicsInfo MakeGraphicsInfo(ShaderType shader_stage, ConstBufferEngineInterface& engine) {
if (shader_stage == ShaderType::Compute) {
return {};
}
auto& graphics = dynamic_cast<Tegra::Engines::Maxwell3D&>(engine);
return {
.tfb_layouts = graphics.regs.tfb_layouts,
.tfb_varying_locs = graphics.regs.tfb_varying_locs,
.primitive_topology = graphics.regs.draw.topology,
.tessellation_primitive = graphics.regs.tess_mode.prim,
.tessellation_spacing = graphics.regs.tess_mode.spacing,
.tfb_enabled = graphics.regs.tfb_enabled != 0,
.tessellation_clockwise = graphics.regs.tess_mode.cw.Value() != 0,
};
}
ComputeInfo MakeComputeInfo(ShaderType shader_stage, ConstBufferEngineInterface& engine) {
if (shader_stage != ShaderType::Compute) {
return {};
}
auto& compute = dynamic_cast<Tegra::Engines::KeplerCompute&>(engine);
const auto& launch = compute.launch_description;
return {
.workgroup_size = {launch.block_dim_x, launch.block_dim_y, launch.block_dim_z},
.shared_memory_size_in_words = launch.shared_alloc,
.local_memory_size_in_words = launch.local_pos_alloc,
};
}
} // Anonymous namespace
Registry::Registry(ShaderType shader_stage, const SerializedRegistryInfo& info)
: stage{shader_stage}, stored_guest_driver_profile{info.guest_driver_profile},
bound_buffer{info.bound_buffer}, graphics_info{info.graphics}, compute_info{info.compute} {}
Registry::Registry(ShaderType shader_stage, ConstBufferEngineInterface& engine_)
: stage{shader_stage}, engine{&engine_}, bound_buffer{engine_.GetBoundBuffer()},
graphics_info{MakeGraphicsInfo(shader_stage, engine_)}, compute_info{MakeComputeInfo(
shader_stage, engine_)} {}
Registry::~Registry() = default;
std::optional<u32> Registry::ObtainKey(u32 buffer, u32 offset) {
const std::pair<u32, u32> key = {buffer, offset};
const auto iter = keys.find(key);
if (iter != keys.end()) {
return iter->second;
}
if (!engine) {
return std::nullopt;
}
const u32 value = engine->AccessConstBuffer32(stage, buffer, offset);
keys.emplace(key, value);
return value;
}
std::optional<SamplerDescriptor> Registry::ObtainBoundSampler(u32 offset) {
const u32 key = offset;
const auto iter = bound_samplers.find(key);
if (iter != bound_samplers.end()) {
return iter->second;
}
if (!engine) {
return std::nullopt;
}
const SamplerDescriptor value = engine->AccessBoundSampler(stage, offset);
bound_samplers.emplace(key, value);
return value;
}
std::optional<Tegra::Engines::SamplerDescriptor> Registry::ObtainSeparateSampler(
std::pair<u32, u32> buffers, std::pair<u32, u32> offsets) {
SeparateSamplerKey key;
key.buffers = buffers;
key.offsets = offsets;
const auto iter = separate_samplers.find(key);
if (iter != separate_samplers.end()) {
return iter->second;
}
if (!engine) {
return std::nullopt;
}
const u32 handle_1 = engine->AccessConstBuffer32(stage, key.buffers.first, key.offsets.first);
const u32 handle_2 = engine->AccessConstBuffer32(stage, key.buffers.second, key.offsets.second);
const SamplerDescriptor value = engine->AccessSampler(handle_1 | handle_2);
separate_samplers.emplace(key, value);
return value;
}
std::optional<SamplerDescriptor> Registry::ObtainBindlessSampler(u32 buffer, u32 offset) {
const std::pair key = {buffer, offset};
const auto iter = bindless_samplers.find(key);
if (iter != bindless_samplers.end()) {
return iter->second;
}
if (!engine) {
return std::nullopt;
}
const SamplerDescriptor value = engine->AccessBindlessSampler(stage, buffer, offset);
bindless_samplers.emplace(key, value);
return value;
}
void Registry::InsertKey(u32 buffer, u32 offset, u32 value) {
keys.insert_or_assign({buffer, offset}, value);
}
void Registry::InsertBoundSampler(u32 offset, SamplerDescriptor sampler) {
bound_samplers.insert_or_assign(offset, sampler);
}
void Registry::InsertBindlessSampler(u32 buffer, u32 offset, SamplerDescriptor sampler) {
bindless_samplers.insert_or_assign({buffer, offset}, sampler);
}
bool Registry::IsConsistent() const {
if (!engine) {
return true;
}
return std::all_of(keys.begin(), keys.end(),
[this](const auto& pair) {
const auto [cbuf, offset] = pair.first;
const auto value = pair.second;
return value == engine->AccessConstBuffer32(stage, cbuf, offset);
}) &&
std::all_of(bound_samplers.begin(), bound_samplers.end(),
[this](const auto& sampler) {
const auto [key, value] = sampler;
return value == engine->AccessBoundSampler(stage, key);
}) &&
std::all_of(bindless_samplers.begin(), bindless_samplers.end(),
[this](const auto& sampler) {
const auto [cbuf, offset] = sampler.first;
const auto value = sampler.second;
return value == engine->AccessBindlessSampler(stage, cbuf, offset);
});
}
bool Registry::HasEqualKeys(const Registry& rhs) const {
return std::tie(keys, bound_samplers, bindless_samplers) ==
std::tie(rhs.keys, rhs.bound_samplers, rhs.bindless_samplers);
}
const GraphicsInfo& Registry::GetGraphicsInfo() const {
ASSERT(stage != Tegra::Engines::ShaderType::Compute);
return graphics_info;
}
const ComputeInfo& Registry::GetComputeInfo() const {
ASSERT(stage == Tegra::Engines::ShaderType::Compute);
return compute_info;
}
} // namespace VideoCommon::Shader

172
src/video_core/shader/registry.h
View file

@ -1,172 +0,0 @@
// Copyright 2019 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <array>
#include <optional>
#include <type_traits>
#include <unordered_map>
#include <utility>
#include "common/common_types.h"
#include "common/hash.h"
#include "video_core/engines/const_buffer_engine_interface.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_type.h"
#include "video_core/guest_driver.h"
namespace VideoCommon::Shader {
struct SeparateSamplerKey {
std::pair<u32, u32> buffers;
std::pair<u32, u32> offsets;
};
} // namespace VideoCommon::Shader
namespace std {
template <>
struct hash<VideoCommon::Shader::SeparateSamplerKey> {
std::size_t operator()(const VideoCommon::Shader::SeparateSamplerKey& key) const noexcept {
return std::hash<u32>{}(key.buffers.first ^ key.buffers.second ^ key.offsets.first ^
key.offsets.second);
}
};
template <>
struct equal_to<VideoCommon::Shader::SeparateSamplerKey> {
bool operator()(const VideoCommon::Shader::SeparateSamplerKey& lhs,
const VideoCommon::Shader::SeparateSamplerKey& rhs) const noexcept {
return lhs.buffers == rhs.buffers && lhs.offsets == rhs.offsets;
}
};
} // namespace std
namespace VideoCommon::Shader {
using KeyMap = std::unordered_map<std::pair<u32, u32>, u32, Common::PairHash>;
using BoundSamplerMap = std::unordered_map<u32, Tegra::Engines::SamplerDescriptor>;
using SeparateSamplerMap =
std::unordered_map<SeparateSamplerKey, Tegra::Engines::SamplerDescriptor>;
using BindlessSamplerMap =
std::unordered_map<std::pair<u32, u32>, Tegra::Engines::SamplerDescriptor, Common::PairHash>;
struct GraphicsInfo {
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
std::array<Maxwell::TransformFeedbackLayout, Maxwell::NumTransformFeedbackBuffers>
tfb_layouts{};
std::array<std::array<u8, 128>, Maxwell::NumTransformFeedbackBuffers> tfb_varying_locs{};
Maxwell::PrimitiveTopology primitive_topology{};
Maxwell::TessellationPrimitive tessellation_primitive{};
Maxwell::TessellationSpacing tessellation_spacing{};
bool tfb_enabled = false;
bool tessellation_clockwise = false;
};
static_assert(std::is_trivially_copyable_v<GraphicsInfo> &&
std::is_standard_layout_v<GraphicsInfo>);
struct ComputeInfo {
std::array<u32, 3> workgroup_size{};
u32 shared_memory_size_in_words = 0;
u32 local_memory_size_in_words = 0;
};
static_assert(std::is_trivially_copyable_v<ComputeInfo> && std::is_standard_layout_v<ComputeInfo>);
struct SerializedRegistryInfo {
VideoCore::GuestDriverProfile guest_driver_profile;
u32 bound_buffer = 0;
GraphicsInfo graphics;
ComputeInfo compute;
};
/**
* The Registry is a class use to interface the 3D and compute engines with the shader compiler.
* With it, the shader can obtain required data from GPU state and store it for disk shader
* compilation.
*/
class Registry {
public:
explicit Registry(Tegra::Engines::ShaderType shader_stage, const SerializedRegistryInfo& info);
explicit Registry(Tegra::Engines::ShaderType shader_stage,
Tegra::Engines::ConstBufferEngineInterface& engine_);
~Registry();
/// Retrieves a key from the registry, if it's registered, it will give the registered value, if
/// not it will obtain it from maxwell3d and register it.
std::optional<u32> ObtainKey(u32 buffer, u32 offset);
std::optional<Tegra::Engines::SamplerDescriptor> ObtainBoundSampler(u32 offset);
std::optional<Tegra::Engines::SamplerDescriptor> ObtainSeparateSampler(
std::pair<u32, u32> buffers, std::pair<u32, u32> offsets);
std::optional<Tegra::Engines::SamplerDescriptor> ObtainBindlessSampler(u32 buffer, u32 offset);
/// Inserts a key.
void InsertKey(u32 buffer, u32 offset, u32 value);
/// Inserts a bound sampler key.
void InsertBoundSampler(u32 offset, Tegra::Engines::SamplerDescriptor sampler);
/// Inserts a bindless sampler key.
void InsertBindlessSampler(u32 buffer, u32 offset, Tegra::Engines::SamplerDescriptor sampler);
/// Checks keys and samplers against engine's current const buffers.
/// Returns true if they are the same value, false otherwise.
bool IsConsistent() const;
/// Returns true if the keys are equal to the other ones in the registry.
bool HasEqualKeys(const Registry& rhs) const;
/// Returns graphics information from this shader
const GraphicsInfo& GetGraphicsInfo() const;
/// Returns compute information from this shader
const ComputeInfo& GetComputeInfo() const;
/// Gives an getter to the const buffer keys in the database.
const KeyMap& GetKeys() const {
return keys;
}
/// Gets samplers database.
const BoundSamplerMap& GetBoundSamplers() const {
return bound_samplers;
}
/// Gets bindless samplers database.
const BindlessSamplerMap& GetBindlessSamplers() const {
return bindless_samplers;
}
/// Gets bound buffer used on this shader
u32 GetBoundBuffer() const {
return bound_buffer;
}
/// Obtains access to the guest driver's profile.
VideoCore::GuestDriverProfile& AccessGuestDriverProfile() {
return engine ? engine->AccessGuestDriverProfile() : stored_guest_driver_profile;
}
private:
const Tegra::Engines::ShaderType stage;
VideoCore::GuestDriverProfile stored_guest_driver_profile;
Tegra::Engines::ConstBufferEngineInterface* engine = nullptr;
KeyMap keys;
BoundSamplerMap bound_samplers;
SeparateSamplerMap separate_samplers;
BindlessSamplerMap bindless_samplers;
u32 bound_buffer;
GraphicsInfo graphics_info;
ComputeInfo compute_info;
};
} // namespace VideoCommon::Shader

464
src/video_core/shader/shader_ir.cpp
View file

@ -1,464 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <array>
#include <cmath>
#include "common/assert.h"
#include "common/common_types.h"
#include "common/logging/log.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/shader/node.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
using Tegra::Shader::Attribute;
using Tegra::Shader::Instruction;
using Tegra::Shader::IpaMode;
using Tegra::Shader::Pred;
using Tegra::Shader::PredCondition;
using Tegra::Shader::PredOperation;
using Tegra::Shader::Register;
ShaderIR::ShaderIR(const ProgramCode& program_code_, u32 main_offset_, CompilerSettings settings_,
Registry& registry_)
: program_code{program_code_}, main_offset{main_offset_}, settings{settings_}, registry{
registry_} {
Decode();
PostDecode();
}
ShaderIR::~ShaderIR() = default;
Node ShaderIR::GetRegister(Register reg) {
if (reg != Register::ZeroIndex) {
used_registers.insert(static_cast<u32>(reg));
}
return MakeNode<GprNode>(reg);
}
Node ShaderIR::GetCustomVariable(u32 id) {
return MakeNode<CustomVarNode>(id);
}
Node ShaderIR::GetImmediate19(Instruction instr) {
return Immediate(instr.alu.GetImm20_19());
}
Node ShaderIR::GetImmediate32(Instruction instr) {
return Immediate(instr.alu.GetImm20_32());
}
Node ShaderIR::GetConstBuffer(u64 index_, u64 offset_) {
const auto index = static_cast<u32>(index_);
const auto offset = static_cast<u32>(offset_);
used_cbufs.try_emplace(index).first->second.MarkAsUsed(offset);
return MakeNode<CbufNode>(index, Immediate(offset));
}
Node ShaderIR::GetConstBufferIndirect(u64 index_, u64 offset_, Node node) {
const auto index = static_cast<u32>(index_);
const auto offset = static_cast<u32>(offset_);
used_cbufs.try_emplace(index).first->second.MarkAsUsedIndirect();
Node final_offset = [&] {
// Attempt to inline constant buffer without a variable offset. This is done to allow
// tracking LDC calls.
if (const auto gpr = std::get_if<GprNode>(&*node)) {
if (gpr->GetIndex() == Register::ZeroIndex) {
return Immediate(offset);
}
}
return Operation(OperationCode::UAdd, NO_PRECISE, std::move(node), Immediate(offset));
}();
return MakeNode<CbufNode>(index, std::move(final_offset));
}
Node ShaderIR::GetPredicate(u64 pred_, bool negated) {
const auto pred = static_cast<Pred>(pred_);
if (pred != Pred::UnusedIndex && pred != Pred::NeverExecute) {
used_predicates.insert(pred);
}
return MakeNode<PredicateNode>(pred, negated);
}
Node ShaderIR::GetPredicate(bool immediate) {
return GetPredicate(static_cast<u64>(immediate ? Pred::UnusedIndex : Pred::NeverExecute));
}
Node ShaderIR::GetInputAttribute(Attribute::Index index, u64 element, Node buffer) {
MarkAttributeUsage(index, element);
used_input_attributes.emplace(index);
return MakeNode<AbufNode>(index, static_cast<u32>(element), std::move(buffer));
}
Node ShaderIR::GetPhysicalInputAttribute(Tegra::Shader::Register physical_address, Node buffer) {
uses_physical_attributes = true;
return MakeNode<AbufNode>(GetRegister(physical_address), buffer);
}
Node ShaderIR::GetOutputAttribute(Attribute::Index index, u64 element, Node buffer) {
MarkAttributeUsage(index, element);
used_output_attributes.insert(index);
return MakeNode<AbufNode>(index, static_cast<u32>(element), std::move(buffer));
}
Node ShaderIR::GetInternalFlag(InternalFlag flag, bool negated) const {
Node node = MakeNode<InternalFlagNode>(flag);
if (negated) {
return Operation(OperationCode::LogicalNegate, std::move(node));
}
return node;
}
Node ShaderIR::GetLocalMemory(Node address) {
return MakeNode<LmemNode>(std::move(address));
}
Node ShaderIR::GetSharedMemory(Node address) {
return MakeNode<SmemNode>(std::move(address));
}
Node ShaderIR::GetTemporary(u32 id) {
return GetRegister(Register::ZeroIndex + 1 + id);
}
Node ShaderIR::GetOperandAbsNegFloat(Node value, bool absolute, bool negate) {
if (absolute) {
value = Operation(OperationCode::FAbsolute, NO_PRECISE, std::move(value));
}
if (negate) {
value = Operation(OperationCode::FNegate, NO_PRECISE, std::move(value));
}
return value;
}
Node ShaderIR::GetSaturatedFloat(Node value, bool saturate) {
if (!saturate) {
return value;
}
Node positive_zero = Immediate(std::copysignf(0, 1));
Node positive_one = Immediate(1.0f);
return Operation(OperationCode::FClamp, NO_PRECISE, std::move(value), std::move(positive_zero),
std::move(positive_one));
}
Node ShaderIR::ConvertIntegerSize(Node value, Register::Size size, bool is_signed) {
switch (size) {
case Register::Size::Byte:
value = SignedOperation(OperationCode::ILogicalShiftLeft, is_signed, NO_PRECISE,
std::move(value), Immediate(24));
value = SignedOperation(OperationCode::IArithmeticShiftRight, is_signed, NO_PRECISE,
std::move(value), Immediate(24));
return value;
case Register::Size::Short:
value = SignedOperation(OperationCode::ILogicalShiftLeft, is_signed, NO_PRECISE,
std::move(value), Immediate(16));
value = SignedOperation(OperationCode::IArithmeticShiftRight, is_signed, NO_PRECISE,
std::move(value), Immediate(16));
return value;
case Register::Size::Word:
// Default - do nothing
return value;
default:
UNREACHABLE_MSG("Unimplemented conversion size: {}", size);
return value;
}
}
Node ShaderIR::GetOperandAbsNegInteger(Node value, bool absolute, bool negate, bool is_signed) {
if (!is_signed) {
// Absolute or negate on an unsigned is pointless
return value;
}
if (absolute) {
value = Operation(OperationCode::IAbsolute, NO_PRECISE, std::move(value));
}
if (negate) {
value = Operation(OperationCode::INegate, NO_PRECISE, std::move(value));
}
return value;
}
Node ShaderIR::UnpackHalfImmediate(Instruction instr, bool has_negation) {
Node value = Immediate(instr.half_imm.PackImmediates());
if (!has_negation) {
return value;
}
Node first_negate = GetPredicate(instr.half_imm.first_negate != 0);
Node second_negate = GetPredicate(instr.half_imm.second_negate != 0);
return Operation(OperationCode::HNegate, NO_PRECISE, std::move(value), std::move(first_negate),
std::move(second_negate));
}
Node ShaderIR::UnpackHalfFloat(Node value, Tegra::Shader::HalfType type) {
return Operation(OperationCode::HUnpack, type, std::move(value));
}
Node ShaderIR::HalfMerge(Node dest, Node src, Tegra::Shader::HalfMerge merge) {
switch (merge) {
case Tegra::Shader::HalfMerge::H0_H1:
return src;
case Tegra::Shader::HalfMerge::F32:
return Operation(OperationCode::HMergeF32, std::move(src));
case Tegra::Shader::HalfMerge::Mrg_H0:
return Operation(OperationCode::HMergeH0, std::move(dest), std::move(src));
case Tegra::Shader::HalfMerge::Mrg_H1:
return Operation(OperationCode::HMergeH1, std::move(dest), std::move(src));
}
UNREACHABLE();
return src;
}
Node ShaderIR::GetOperandAbsNegHalf(Node value, bool absolute, bool negate) {
if (absolute) {
value = Operation(OperationCode::HAbsolute, NO_PRECISE, std::move(value));
}
if (negate) {
value = Operation(OperationCode::HNegate, NO_PRECISE, std::move(value), GetPredicate(true),
GetPredicate(true));
}
return value;
}
Node ShaderIR::GetSaturatedHalfFloat(Node value, bool saturate) {
if (!saturate) {
return value;
}
Node positive_zero = Immediate(std::copysignf(0, 1));
Node positive_one = Immediate(1.0f);
return Operation(OperationCode::HClamp, NO_PRECISE, std::move(value), std::move(positive_zero),
std::move(positive_one));
}
Node ShaderIR::GetPredicateComparisonFloat(PredCondition condition, Node op_a, Node op_b) {
if (condition == PredCondition::T) {
return GetPredicate(true);
} else if (condition == PredCondition::F) {
return GetPredicate(false);
}
static constexpr std::array comparison_table{
OperationCode(0),
OperationCode::LogicalFOrdLessThan, // LT
OperationCode::LogicalFOrdEqual, // EQ
OperationCode::LogicalFOrdLessEqual, // LE
OperationCode::LogicalFOrdGreaterThan, // GT
OperationCode::LogicalFOrdNotEqual, // NE
OperationCode::LogicalFOrdGreaterEqual, // GE
OperationCode::LogicalFOrdered, // NUM
OperationCode::LogicalFUnordered, // NAN
OperationCode::LogicalFUnordLessThan, // LTU
OperationCode::LogicalFUnordEqual, // EQU
OperationCode::LogicalFUnordLessEqual, // LEU
OperationCode::LogicalFUnordGreaterThan, // GTU
OperationCode::LogicalFUnordNotEqual, // NEU
OperationCode::LogicalFUnordGreaterEqual, // GEU
};
const std::size_t index = static_cast<std::size_t>(condition);
ASSERT_MSG(index < std::size(comparison_table), "Invalid condition={}", index);
return Operation(comparison_table[index], op_a, op_b);
}
Node ShaderIR::GetPredicateComparisonInteger(PredCondition condition, bool is_signed, Node op_a,
Node op_b) {
static constexpr std::array comparison_table{
std::pair{PredCondition::LT, OperationCode::LogicalILessThan},
std::pair{PredCondition::EQ, OperationCode::LogicalIEqual},
std::pair{PredCondition::LE, OperationCode::LogicalILessEqual},
std::pair{PredCondition::GT, OperationCode::LogicalIGreaterThan},
std::pair{PredCondition::NE, OperationCode::LogicalINotEqual},
std::pair{PredCondition::GE, OperationCode::LogicalIGreaterEqual},
};
const auto comparison =
std::find_if(comparison_table.cbegin(), comparison_table.cend(),
[condition](const auto entry) { return condition == entry.first; });
UNIMPLEMENTED_IF_MSG(comparison == comparison_table.cend(),
"Unknown predicate comparison operation");
return SignedOperation(comparison->second, is_signed, NO_PRECISE, std::move(op_a),
std::move(op_b));
}
Node ShaderIR::GetPredicateComparisonHalf(Tegra::Shader::PredCondition condition, Node op_a,
Node op_b) {
static constexpr std::array comparison_table{
std::pair{PredCondition::LT, OperationCode::Logical2HLessThan},
std::pair{PredCondition::EQ, OperationCode::Logical2HEqual},
std::pair{PredCondition::LE, OperationCode::Logical2HLessEqual},
std::pair{PredCondition::GT, OperationCode::Logical2HGreaterThan},
std::pair{PredCondition::NE, OperationCode::Logical2HNotEqual},
std::pair{PredCondition::GE, OperationCode::Logical2HGreaterEqual},
std::pair{PredCondition::LTU, OperationCode::Logical2HLessThanWithNan},
std::pair{PredCondition::LEU, OperationCode::Logical2HLessEqualWithNan},
std::pair{PredCondition::GTU, OperationCode::Logical2HGreaterThanWithNan},
std::pair{PredCondition::NEU, OperationCode::Logical2HNotEqualWithNan},
std::pair{PredCondition::GEU, OperationCode::Logical2HGreaterEqualWithNan},
};
const auto comparison =
std::find_if(comparison_table.cbegin(), comparison_table.cend(),
[condition](const auto entry) { return condition == entry.first; });
UNIMPLEMENTED_IF_MSG(comparison == comparison_table.cend(),
"Unknown predicate comparison operation");
return Operation(comparison->second, NO_PRECISE, std::move(op_a), std::move(op_b));
}
OperationCode ShaderIR::GetPredicateCombiner(PredOperation operation) {
static constexpr std::array operation_table{
OperationCode::LogicalAnd,
OperationCode::LogicalOr,
OperationCode::LogicalXor,
};
const auto index = static_cast<std::size_t>(operation);
if (index >= operation_table.size()) {
UNIMPLEMENTED_MSG("Unknown predicate operation.");
return {};
}
return operation_table[index];
}
Node ShaderIR::GetConditionCode(ConditionCode cc) const {
switch (cc) {
case ConditionCode::NEU:
return GetInternalFlag(InternalFlag::Zero, true);
case ConditionCode::FCSM_TR:
UNIMPLEMENTED_MSG("EXIT.FCSM_TR is not implemented");
return MakeNode<PredicateNode>(Pred::NeverExecute, false);
default:
UNIMPLEMENTED_MSG("Unimplemented condition code: {}", cc);
return MakeNode<PredicateNode>(Pred::NeverExecute, false);
}
}
void ShaderIR::SetRegister(NodeBlock& bb, Register dest, Node src) {
bb.push_back(Operation(OperationCode::Assign, GetRegister(dest), std::move(src)));
}
void ShaderIR::SetPredicate(NodeBlock& bb, u64 dest, Node src) {
bb.push_back(Operation(OperationCode::LogicalAssign, GetPredicate(dest), std::move(src)));
}
void ShaderIR::SetInternalFlag(NodeBlock& bb, InternalFlag flag, Node value) {
bb.push_back(Operation(OperationCode::LogicalAssign, GetInternalFlag(flag), std::move(value)));
}
void ShaderIR::SetLocalMemory(NodeBlock& bb, Node address, Node value) {
bb.push_back(
Operation(OperationCode::Assign, GetLocalMemory(std::move(address)), std::move(value)));
}
void ShaderIR::SetSharedMemory(NodeBlock& bb, Node address, Node value) {
bb.push_back(
Operation(OperationCode::Assign, GetSharedMemory(std::move(address)), std::move(value)));
}
void ShaderIR::SetTemporary(NodeBlock& bb, u32 id, Node value) {
SetRegister(bb, Register::ZeroIndex + 1 + id, std::move(value));
}
void ShaderIR::SetInternalFlagsFromFloat(NodeBlock& bb, Node value, bool sets_cc) {
if (!sets_cc) {
return;
}
Node zerop = Operation(OperationCode::LogicalFOrdEqual, std::move(value), Immediate(0.0f));
SetInternalFlag(bb, InternalFlag::Zero, std::move(zerop));
LOG_WARNING(HW_GPU, "Condition codes implementation is incomplete");
}
void ShaderIR::SetInternalFlagsFromInteger(NodeBlock& bb, Node value, bool sets_cc) {
if (!sets_cc) {
return;
}
Node zerop = Operation(OperationCode::LogicalIEqual, std::move(value), Immediate(0));
SetInternalFlag(bb, InternalFlag::Zero, std::move(zerop));
LOG_WARNING(HW_GPU, "Condition codes implementation is incomplete");
}
Node ShaderIR::BitfieldExtract(Node value, u32 offset, u32 bits) {
return Operation(OperationCode::UBitfieldExtract, NO_PRECISE, std::move(value),
Immediate(offset), Immediate(bits));
}
Node ShaderIR::BitfieldInsert(Node base, Node insert, u32 offset, u32 bits) {
return Operation(OperationCode::UBitfieldInsert, NO_PRECISE, base, insert, Immediate(offset),
Immediate(bits));
}
void ShaderIR::MarkAttributeUsage(Attribute::Index index, u64 element) {
switch (index) {
case Attribute::Index::LayerViewportPointSize:
switch (element) {
case 0:
UNIMPLEMENTED();
break;
case 1:
uses_layer = true;
break;
case 2:
uses_viewport_index = true;
break;
case 3:
uses_point_size = true;
break;
}
break;
case Attribute::Index::TessCoordInstanceIDVertexID:
switch (element) {
case 2:
uses_instance_id = true;
break;
case 3:
uses_vertex_id = true;
break;
}
break;
case Attribute::Index::ClipDistances0123:
case Attribute::Index::ClipDistances4567: {
const u64 clip_index = (index == Attribute::Index::ClipDistances4567 ? 4 : 0) + element;
used_clip_distances.at(clip_index) = true;
break;
}
case Attribute::Index::FrontColor:
case Attribute::Index::FrontSecondaryColor:
case Attribute::Index::BackColor:
case Attribute::Index::BackSecondaryColor:
uses_legacy_varyings = true;
break;
default:
if (index >= Attribute::Index::TexCoord_0 && index <= Attribute::Index::TexCoord_7) {
uses_legacy_varyings = true;
}
break;
}
}
std::size_t ShaderIR::DeclareAmend(Node new_amend) {
const auto id = amend_code.size();
amend_code.push_back(std::move(new_amend));
return id;
}
u32 ShaderIR::NewCustomVariable() {
return num_custom_variables++;
}
} // namespace VideoCommon::Shader

479
src/video_core/shader/shader_ir.h
View file

@ -1,479 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <array>
#include <list>
#include <map>
#include <optional>
#include <set>
#include <tuple>
#include <vector>
#include "common/common_types.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/engines/shader_bytecode.h"
#include "video_core/engines/shader_header.h"
#include "video_core/shader/ast.h"
#include "video_core/shader/compiler_settings.h"
#include "video_core/shader/memory_util.h"
#include "video_core/shader/node.h"
#include "video_core/shader/registry.h"
namespace VideoCommon::Shader {
struct ShaderBlock;
constexpr u32 MAX_PROGRAM_LENGTH = 0x1000;
struct ConstBuffer {
constexpr explicit ConstBuffer(u32 max_offset_, bool is_indirect_)
: max_offset{max_offset_}, is_indirect{is_indirect_} {}
constexpr ConstBuffer() = default;
void MarkAsUsed(u64 offset) {
max_offset = std::max(max_offset, static_cast<u32>(offset));
}
void MarkAsUsedIndirect() {
is_indirect = true;
}
bool IsIndirect() const {
return is_indirect;
}
u32 GetSize() const {
return max_offset + static_cast<u32>(sizeof(float));
}
u32 GetMaxOffset() const {
return max_offset;
}
private:
u32 max_offset = 0;
bool is_indirect = false;
};
struct GlobalMemoryUsage {
bool is_read{};
bool is_written{};
};
class ShaderIR final {
public:
explicit ShaderIR(const ProgramCode& program_code_, u32 main_offset_,
CompilerSettings settings_, Registry& registry_);
~ShaderIR();
const std::map<u32, NodeBlock>& GetBasicBlocks() const {
return basic_blocks;
}
const std::set<u32>& GetRegisters() const {
return used_registers;
}
const std::set<Tegra::Shader::Pred>& GetPredicates() const {
return used_predicates;
}
const std::set<Tegra::Shader::Attribute::Index>& GetInputAttributes() const {
return used_input_attributes;
}
const std::set<Tegra::Shader::Attribute::Index>& GetOutputAttributes() const {
return used_output_attributes;
}
const std::map<u32, ConstBuffer>& GetConstantBuffers() const {
return used_cbufs;
}
const std::list<SamplerEntry>& GetSamplers() const {
return used_samplers;
}
const std::list<ImageEntry>& GetImages() const {
return used_images;
}
const std::array<bool, Tegra::Engines::Maxwell3D::Regs::NumClipDistances>& GetClipDistances()
const {
return used_clip_distances;
}
const std::map<GlobalMemoryBase, GlobalMemoryUsage>& GetGlobalMemory() const {
return used_global_memory;
}
std::size_t GetLength() const {
return static_cast<std::size_t>(coverage_end * sizeof(u64));
}
bool UsesLayer() const {
return uses_layer;
}
bool UsesViewportIndex() const {
return uses_viewport_index;
}
bool UsesPointSize() const {
return uses_point_size;
}
bool UsesInstanceId() const {
return uses_instance_id;
}
bool UsesVertexId() const {
return uses_vertex_id;
}
bool UsesLegacyVaryings() const {
return uses_legacy_varyings;
}
bool UsesYNegate() const {
return uses_y_negate;
}
bool UsesWarps() const {
return uses_warps;
}
bool HasPhysicalAttributes() const {
return uses_physical_attributes;
}
const Tegra::Shader::Header& GetHeader() const {
return header;
}
bool IsFlowStackDisabled() const {
return disable_flow_stack;
}
bool IsDecompiled() const {
return decompiled;
}
const ASTManager& GetASTManager() const {
return program_manager;
}
ASTNode GetASTProgram() const {
return program_manager.GetProgram();
}
u32 GetASTNumVariables() const {
return program_manager.GetVariables();
}
u32 ConvertAddressToNvidiaSpace(u32 address) const {
return (address - main_offset) * static_cast<u32>(sizeof(Tegra::Shader::Instruction));
}
/// Returns a condition code evaluated from internal flags
Node GetConditionCode(Tegra::Shader::ConditionCode cc) const;
const Node& GetAmendNode(std::size_t index) const {
return amend_code[index];
}
u32 GetNumCustomVariables() const {
return num_custom_variables;
}
private:
friend class ASTDecoder;
struct SamplerInfo {
std::optional<Tegra::Shader::TextureType> type;
std::optional<bool> is_array;
std::optional<bool> is_shadow;
std::optional<bool> is_buffer;
constexpr bool IsComplete() const noexcept {
return type && is_array && is_shadow && is_buffer;
}
};
void Decode();
void PostDecode();
NodeBlock DecodeRange(u32 begin, u32 end);
void DecodeRangeInner(NodeBlock& bb, u32 begin, u32 end);
void InsertControlFlow(NodeBlock& bb, const ShaderBlock& block);
/**
* Decodes a single instruction from Tegra to IR.
* @param bb Basic block where the nodes will be written to.
* @param pc Program counter. Offset to decode.
* @return Next address to decode.
*/
u32 DecodeInstr(NodeBlock& bb, u32 pc);
u32 DecodeArithmetic(NodeBlock& bb, u32 pc);
u32 DecodeArithmeticImmediate(NodeBlock& bb, u32 pc);
u32 DecodeBfe(NodeBlock& bb, u32 pc);
u32 DecodeBfi(NodeBlock& bb, u32 pc);
u32 DecodeShift(NodeBlock& bb, u32 pc);
u32 DecodeArithmeticInteger(NodeBlock& bb, u32 pc);
u32 DecodeArithmeticIntegerImmediate(NodeBlock& bb, u32 pc);
u32 DecodeArithmeticHalf(NodeBlock& bb, u32 pc);
u32 DecodeArithmeticHalfImmediate(NodeBlock& bb, u32 pc);
u32 DecodeFfma(NodeBlock& bb, u32 pc);
u32 DecodeHfma2(NodeBlock& bb, u32 pc);
u32 DecodeConversion(NodeBlock& bb, u32 pc);
u32 DecodeWarp(NodeBlock& bb, u32 pc);
u32 DecodeMemory(NodeBlock& bb, u32 pc);
u32 DecodeTexture(NodeBlock& bb, u32 pc);
u32 DecodeImage(NodeBlock& bb, u32 pc);
u32 DecodeFloatSetPredicate(NodeBlock& bb, u32 pc);
u32 DecodeIntegerSetPredicate(NodeBlock& bb, u32 pc);
u32 DecodeHalfSetPredicate(NodeBlock& bb, u32 pc);
u32 DecodePredicateSetRegister(NodeBlock& bb, u32 pc);
u32 DecodePredicateSetPredicate(NodeBlock& bb, u32 pc);
u32 DecodeRegisterSetPredicate(NodeBlock& bb, u32 pc);
u32 DecodeFloatSet(NodeBlock& bb, u32 pc);
u32 DecodeIntegerSet(NodeBlock& bb, u32 pc);
u32 DecodeHalfSet(NodeBlock& bb, u32 pc);
u32 DecodeVideo(NodeBlock& bb, u32 pc);
u32 DecodeXmad(NodeBlock& bb, u32 pc);
u32 DecodeOther(NodeBlock& bb, u32 pc);
/// Generates a node for a passed register.
Node GetRegister(Tegra::Shader::Register reg);
/// Generates a node for a custom variable
Node GetCustomVariable(u32 id);
/// Generates a node representing a 19-bit immediate value
Node GetImmediate19(Tegra::Shader::Instruction instr);
/// Generates a node representing a 32-bit immediate value
Node GetImmediate32(Tegra::Shader::Instruction instr);
/// Generates a node representing a constant buffer
Node GetConstBuffer(u64 index, u64 offset);
/// Generates a node representing a constant buffer with a variadic offset
Node GetConstBufferIndirect(u64 index, u64 offset, Node node);
/// Generates a node for a passed predicate. It can be optionally negated
Node GetPredicate(u64 pred, bool negated = false);
/// Generates a predicate node for an immediate true or false value
Node GetPredicate(bool immediate);
/// Generates a node representing an input attribute. Keeps track of used attributes.
Node GetInputAttribute(Tegra::Shader::Attribute::Index index, u64 element, Node buffer = {});
/// Generates a node representing a physical input attribute.
Node GetPhysicalInputAttribute(Tegra::Shader::Register physical_address, Node buffer = {});
/// Generates a node representing an output attribute. Keeps track of used attributes.
Node GetOutputAttribute(Tegra::Shader::Attribute::Index index, u64 element, Node buffer);
/// Generates a node representing an internal flag
Node GetInternalFlag(InternalFlag flag, bool negated = false) const;
/// Generates a node representing a local memory address
Node GetLocalMemory(Node address);
/// Generates a node representing a shared memory address
Node GetSharedMemory(Node address);
/// Generates a temporary, internally it uses a post-RZ register
Node GetTemporary(u32 id);
/// Sets a register. src value must be a number-evaluated node.
void SetRegister(NodeBlock& bb, Tegra::Shader::Register dest, Node src);
/// Sets a predicate. src value must be a bool-evaluated node
void SetPredicate(NodeBlock& bb, u64 dest, Node src);
/// Sets an internal flag. src value must be a bool-evaluated node
void SetInternalFlag(NodeBlock& bb, InternalFlag flag, Node value);
/// Sets a local memory address with a value.
void SetLocalMemory(NodeBlock& bb, Node address, Node value);
/// Sets a shared memory address with a value.
void SetSharedMemory(NodeBlock& bb, Node address, Node value);
/// Sets a temporary. Internally it uses a post-RZ register
void SetTemporary(NodeBlock& bb, u32 id, Node value);
/// Sets internal flags from a float
void SetInternalFlagsFromFloat(NodeBlock& bb, Node value, bool sets_cc = true);
/// Sets internal flags from an integer
void SetInternalFlagsFromInteger(NodeBlock& bb, Node value, bool sets_cc = true);
/// Conditionally absolute/negated float. Absolute is applied first
Node GetOperandAbsNegFloat(Node value, bool absolute, bool negate);
/// Conditionally saturates a float
Node GetSaturatedFloat(Node value, bool saturate = true);
/// Converts an integer to different sizes.
Node ConvertIntegerSize(Node value, Tegra::Shader::Register::Size size, bool is_signed);
/// Conditionally absolute/negated integer. Absolute is applied first
Node GetOperandAbsNegInteger(Node value, bool absolute, bool negate, bool is_signed);
/// Unpacks a half immediate from an instruction
Node UnpackHalfImmediate(Tegra::Shader::Instruction instr, bool has_negation);
/// Unpacks a binary value into a half float pair with a type format
Node UnpackHalfFloat(Node value, Tegra::Shader::HalfType type);
/// Merges a half pair into another value
Node HalfMerge(Node dest, Node src, Tegra::Shader::HalfMerge merge);
/// Conditionally absolute/negated half float pair. Absolute is applied first
Node GetOperandAbsNegHalf(Node value, bool absolute, bool negate);
/// Conditionally saturates a half float pair
Node GetSaturatedHalfFloat(Node value, bool saturate = true);
/// Get image component value by type and size
std::pair<Node, bool> GetComponentValue(Tegra::Texture::ComponentType component_type,
u32 component_size, Node original_value);
/// Returns a predicate comparing two floats
Node GetPredicateComparisonFloat(Tegra::Shader::PredCondition condition, Node op_a, Node op_b);
/// Returns a predicate comparing two integers
Node GetPredicateComparisonInteger(Tegra::Shader::PredCondition condition, bool is_signed,
Node op_a, Node op_b);
/// Returns a predicate comparing two half floats. meta consumes how both pairs will be compared
Node GetPredicateComparisonHalf(Tegra::Shader::PredCondition condition, Node op_a, Node op_b);
/// Returns a predicate combiner operation
OperationCode GetPredicateCombiner(Tegra::Shader::PredOperation operation);
/// Queries the missing sampler info from the execution context.
SamplerInfo GetSamplerInfo(SamplerInfo info,
std::optional<Tegra::Engines::SamplerDescriptor> sampler);
/// Accesses a texture sampler.
std::optional<SamplerEntry> GetSampler(Tegra::Shader::Sampler sampler, SamplerInfo info);
/// Accesses a texture sampler for a bindless texture.
std::optional<SamplerEntry> GetBindlessSampler(Tegra::Shader::Register reg, SamplerInfo info,
Node& index_var);
/// Accesses an image.
ImageEntry& GetImage(Tegra::Shader::Image image, Tegra::Shader::ImageType type);
/// Access a bindless image sampler.
ImageEntry& GetBindlessImage(Tegra::Shader::Register reg, Tegra::Shader::ImageType type);
/// Extracts a sequence of bits from a node
Node BitfieldExtract(Node value, u32 offset, u32 bits);
/// Inserts a sequence of bits from a node
Node BitfieldInsert(Node base, Node insert, u32 offset, u32 bits);
/// Marks the usage of a input or output attribute.
void MarkAttributeUsage(Tegra::Shader::Attribute::Index index, u64 element);
/// Decodes VMNMX instruction and inserts its code into the passed basic block.
void DecodeVMNMX(NodeBlock& bb, Tegra::Shader::Instruction instr);
void WriteTexInstructionFloat(NodeBlock& bb, Tegra::Shader::Instruction instr,
const Node4& components);
void WriteTexsInstructionFloat(NodeBlock& bb, Tegra::Shader::Instruction instr,
const Node4& components, bool ignore_mask = false);
void WriteTexsInstructionHalfFloat(NodeBlock& bb, Tegra::Shader::Instruction instr,
const Node4& components, bool ignore_mask = false);
Node4 GetTexCode(Tegra::Shader::Instruction instr, Tegra::Shader::TextureType texture_type,
Tegra::Shader::TextureProcessMode process_mode, bool depth_compare,
bool is_array, bool is_aoffi,
std::optional<Tegra::Shader::Register> bindless_reg);
Node4 GetTexsCode(Tegra::Shader::Instruction instr, Tegra::Shader::TextureType texture_type,
Tegra::Shader::TextureProcessMode process_mode, bool depth_compare,
bool is_array);
Node4 GetTld4Code(Tegra::Shader::Instruction instr, Tegra::Shader::TextureType texture_type,
bool depth_compare, bool is_array, bool is_aoffi, bool is_ptp,
bool is_bindless);
Node4 GetTldCode(Tegra::Shader::Instruction instr);
Node4 GetTldsCode(Tegra::Shader::Instruction instr, Tegra::Shader::TextureType texture_type,
bool is_array);
std::tuple<std::size_t, std::size_t> ValidateAndGetCoordinateElement(
Tegra::Shader::TextureType texture_type, bool depth_compare, bool is_array,
bool lod_bias_enabled, std::size_t max_coords, std::size_t max_inputs);
std::vector<Node> GetAoffiCoordinates(Node aoffi_reg, std::size_t coord_count, bool is_tld4);
std::vector<Node> GetPtpCoordinates(std::array<Node, 2> ptp_regs);
Node4 GetTextureCode(Tegra::Shader::Instruction instr, Tegra::Shader::TextureType texture_type,
Tegra::Shader::TextureProcessMode process_mode, std::vector<Node> coords,
Node array, Node depth_compare, u32 bias_offset, std::vector<Node> aoffi,
std::optional<Tegra::Shader::Register> bindless_reg);
Node GetVideoOperand(Node op, bool is_chunk, bool is_signed, Tegra::Shader::VideoType type,
u64 byte_height);
void WriteLogicOperation(NodeBlock& bb, Tegra::Shader::Register dest,
Tegra::Shader::LogicOperation logic_op, Node op_a, Node op_b,
Tegra::Shader::PredicateResultMode predicate_mode,
Tegra::Shader::Pred predicate, bool sets_cc);
void WriteLop3Instruction(NodeBlock& bb, Tegra::Shader::Register dest, Node op_a, Node op_b,
Node op_c, Node imm_lut, bool sets_cc);
std::tuple<Node, u32, u32> TrackCbuf(Node tracked, const NodeBlock& code, s64 cursor) const;
std::pair<Node, TrackSampler> TrackBindlessSampler(Node tracked, const NodeBlock& code,
s64 cursor);
std::pair<Node, TrackSampler> HandleBindlessIndirectRead(const CbufNode& cbuf,
const OperationNode& operation,
Node gpr, Node base_offset,
Node tracked, const NodeBlock& code,
s64 cursor);
std::optional<u32> TrackImmediate(Node tracked, const NodeBlock& code, s64 cursor) const;
std::pair<Node, s64> TrackRegister(const GprNode* tracked, const NodeBlock& code,
s64 cursor) const;
std::tuple<Node, Node, GlobalMemoryBase> TrackGlobalMemory(NodeBlock& bb,
Tegra::Shader::Instruction instr,
bool is_read, bool is_write);
/// Register new amending code and obtain the reference id.
std::size_t DeclareAmend(Node new_amend);
u32 NewCustomVariable();
const ProgramCode& program_code;
const u32 main_offset;
const CompilerSettings settings;
Registry& registry;
bool decompiled{};
bool disable_flow_stack{};
u32 coverage_begin{};
u32 coverage_end{};
std::map<u32, NodeBlock> basic_blocks;
NodeBlock global_code;
ASTManager program_manager{true, true};
std::vector<Node> amend_code;
u32 num_custom_variables{};
std::set<u32> used_registers;
std::set<Tegra::Shader::Pred> used_predicates;
std::set<Tegra::Shader::Attribute::Index> used_input_attributes;
std::set<Tegra::Shader::Attribute::Index> used_output_attributes;
std::map<u32, ConstBuffer> used_cbufs;
std::list<SamplerEntry> used_samplers;
std::list<ImageEntry> used_images;
std::array<bool, Tegra::Engines::Maxwell3D::Regs::NumClipDistances> used_clip_distances{};
std::map<GlobalMemoryBase, GlobalMemoryUsage> used_global_memory;
bool uses_layer{};
bool uses_viewport_index{};
bool uses_point_size{};
bool uses_physical_attributes{}; // Shader uses AL2P or physical attribute read/writes
bool uses_instance_id{};
bool uses_vertex_id{};
bool uses_legacy_varyings{};
bool uses_y_negate{};
bool uses_warps{};
bool uses_indexed_samplers{};
Tegra::Shader::Header header;
};
} // namespace VideoCommon::Shader

236
src/video_core/shader/track.cpp
View file

@ -1,236 +0,0 @@
// Copyright 2018 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <utility>
#include <variant>
#include "common/common_types.h"
#include "video_core/shader/node.h"
#include "video_core/shader/node_helper.h"
#include "video_core/shader/shader_ir.h"
namespace VideoCommon::Shader {
namespace {
std::pair<Node, s64> FindOperation(const NodeBlock& code, s64 cursor,
OperationCode operation_code) {
for (; cursor >= 0; --cursor) {
Node node = code.at(cursor);
if (const auto operation = std::get_if<OperationNode>(&*node)) {
if (operation->GetCode() == operation_code) {
return {std::move(node), cursor};
}
}
if (const auto conditional = std::get_if<ConditionalNode>(&*node)) {
const auto& conditional_code = conditional->GetCode();
auto result = FindOperation(
conditional_code, static_cast<s64>(conditional_code.size() - 1), operation_code);
auto& found = result.first;
if (found) {
return {std::move(found), cursor};
}
}
}
return {};
}
std::optional<std::pair<Node, Node>> DecoupleIndirectRead(const OperationNode& operation) {
if (operation.GetCode() != OperationCode::UAdd) {
return std::nullopt;
}
Node gpr;
Node offset;
ASSERT(operation.GetOperandsCount() == 2);
for (std::size_t i = 0; i < operation.GetOperandsCount(); i++) {
Node operand = operation[i];
if (std::holds_alternative<ImmediateNode>(*operand)) {
offset = operation[i];
} else if (std::holds_alternative<GprNode>(*operand)) {
gpr = operation[i];
}
}
if (offset && gpr) {
return std::make_pair(gpr, offset);
}
return std::nullopt;
}
bool AmendNodeCv(std::size_t amend_index, Node node) {
if (const auto operation = std::get_if<OperationNode>(&*node)) {
operation->SetAmendIndex(amend_index);
return true;
}
if (const auto conditional = std::get_if<ConditionalNode>(&*node)) {
conditional->SetAmendIndex(amend_index);
return true;
}
return false;
}
} // Anonymous namespace
std::pair<Node, TrackSampler> ShaderIR::TrackBindlessSampler(Node tracked, const NodeBlock& code,
s64 cursor) {
if (const auto cbuf = std::get_if<CbufNode>(&*tracked)) {
const u32 cbuf_index = cbuf->GetIndex();
// Constant buffer found, test if it's an immediate
const auto& offset = cbuf->GetOffset();
if (const auto immediate = std::get_if<ImmediateNode>(&*offset)) {
auto track = MakeTrackSampler<BindlessSamplerNode>(cbuf_index, immediate->GetValue());
return {tracked, track};
}
if (const auto operation = std::get_if<OperationNode>(&*offset)) {
const u32 bound_buffer = registry.GetBoundBuffer();
if (bound_buffer != cbuf_index) {
return {};
}
if (const std::optional pair = DecoupleIndirectRead(*operation)) {
auto [gpr, base_offset] = *pair;
return HandleBindlessIndirectRead(*cbuf, *operation, gpr, base_offset, tracked,
code, cursor);
}
}
return {};
}
if (const auto gpr = std::get_if<GprNode>(&*tracked)) {
if (gpr->GetIndex() == Tegra::Shader::Register::ZeroIndex) {
return {};
}
// Reduce the cursor in one to avoid infinite loops when the instruction sets the same
// register that it uses as operand
const auto [source, new_cursor] = TrackRegister(gpr, code, cursor - 1);
if (!source) {
return {};
}
return TrackBindlessSampler(source, code, new_cursor);
}
if (const auto operation = std::get_if<OperationNode>(&*tracked)) {
const OperationNode& op = *operation;
const OperationCode opcode = operation->GetCode();
if (opcode == OperationCode::IBitwiseOr || opcode == OperationCode::UBitwiseOr) {
ASSERT(op.GetOperandsCount() == 2);
auto [node_a, index_a, offset_a] = TrackCbuf(op[0], code, cursor);
auto [node_b, index_b, offset_b] = TrackCbuf(op[1], code, cursor);
if (node_a && node_b) {
auto track = MakeTrackSampler<SeparateSamplerNode>(std::pair{index_a, index_b},
std::pair{offset_a, offset_b});
return {tracked, std::move(track)};
}
}
std::size_t i = op.GetOperandsCount();
while (i--) {
if (auto found = TrackBindlessSampler(op[i - 1], code, cursor); std::get<0>(found)) {
// Constant buffer found in operand.
return found;
}
}
return {};
}
if (const auto conditional = std::get_if<ConditionalNode>(&*tracked)) {
const auto& conditional_code = conditional->GetCode();
return TrackBindlessSampler(tracked, conditional_code,
static_cast<s64>(conditional_code.size()));
}
return {};
}
std::pair<Node, TrackSampler> ShaderIR::HandleBindlessIndirectRead(
const CbufNode& cbuf, const OperationNode& operation, Node gpr, Node base_offset, Node tracked,
const NodeBlock& code, s64 cursor) {
const auto offset_imm = std::get<ImmediateNode>(*base_offset);
const auto& gpu_driver = registry.AccessGuestDriverProfile();
const u32 bindless_cv = NewCustomVariable();
const u32 texture_handler_size = gpu_driver.GetTextureHandlerSize();
Node op = Operation(OperationCode::UDiv, gpr, Immediate(texture_handler_size));
Node cv_node = GetCustomVariable(bindless_cv);
Node amend_op = Operation(OperationCode::Assign, std::move(cv_node), std::move(op));
const std::size_t amend_index = DeclareAmend(std::move(amend_op));
AmendNodeCv(amend_index, code[cursor]);
// TODO: Implement bindless index custom variable
auto track =
MakeTrackSampler<ArraySamplerNode>(cbuf.GetIndex(), offset_imm.GetValue(), bindless_cv);
return {tracked, track};
}
std::tuple<Node, u32, u32> ShaderIR::TrackCbuf(Node tracked, const NodeBlock& code,
s64 cursor) const {
if (const auto cbuf = std::get_if<CbufNode>(&*tracked)) {
// Constant buffer found, test if it's an immediate
const auto& offset = cbuf->GetOffset();
if (const auto immediate = std::get_if<ImmediateNode>(&*offset)) {
return {tracked, cbuf->GetIndex(), immediate->GetValue()};
}
return {};
}
if (const auto gpr = std::get_if<GprNode>(&*tracked)) {
if (gpr->GetIndex() == Tegra::Shader::Register::ZeroIndex) {
return {};
}
// Reduce the cursor in one to avoid infinite loops when the instruction sets the same
// register that it uses as operand
const auto [source, new_cursor] = TrackRegister(gpr, code, cursor - 1);
if (!source) {
return {};
}
return TrackCbuf(source, code, new_cursor);
}
if (const auto operation = std::get_if<OperationNode>(&*tracked)) {
for (std::size_t i = operation->GetOperandsCount(); i > 0; --i) {
if (auto found = TrackCbuf((*operation)[i - 1], code, cursor); std::get<0>(found)) {
// Cbuf found in operand.
return found;
}
}
return {};
}
if (const auto conditional = std::get_if<ConditionalNode>(&*tracked)) {
const auto& conditional_code = conditional->GetCode();
return TrackCbuf(tracked, conditional_code, static_cast<s64>(conditional_code.size()));
}
return {};
}
std::optional<u32> ShaderIR::TrackImmediate(Node tracked, const NodeBlock& code, s64 cursor) const {
// Reduce the cursor in one to avoid infinite loops when the instruction sets the same register
// that it uses as operand
const auto result = TrackRegister(&std::get<GprNode>(*tracked), code, cursor - 1);
const auto& found = result.first;
if (!found) {
return std::nullopt;
}
if (const auto immediate = std::get_if<ImmediateNode>(&*found)) {
return immediate->GetValue();
}
return std::nullopt;
}
std::pair<Node, s64> ShaderIR::TrackRegister(const GprNode* tracked, const NodeBlock& code,
s64 cursor) const {
for (; cursor >= 0; --cursor) {
const auto [found_node, new_cursor] = FindOperation(code, cursor, OperationCode::Assign);
if (!found_node) {
return {};
}
const auto operation = std::get_if<OperationNode>(&*found_node);
ASSERT(operation);
const auto& target = (*operation)[0];
if (const auto gpr_target = std::get_if<GprNode>(&*target)) {
if (gpr_target->GetIndex() == tracked->GetIndex()) {
return {(*operation)[1], new_cursor};
}
}
}
return {};
}
} // namespace VideoCommon::Shader

115
src/video_core/shader/transform_feedback.cpp
View file

@ -1,115 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <algorithm>
#include <array>
#include <unordered_map>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/engines/maxwell_3d.h"
#include "video_core/shader/registry.h"
#include "video_core/shader/transform_feedback.h"
namespace VideoCommon::Shader {
namespace {
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
// TODO(Rodrigo): Change this to constexpr std::unordered_set in C++20
/// Attribute offsets that describe a vector
constexpr std::array VECTORS = {
28, // gl_Position
32, // Generic 0
36, // Generic 1
40, // Generic 2
44, // Generic 3
48, // Generic 4
52, // Generic 5
56, // Generic 6
60, // Generic 7
64, // Generic 8
68, // Generic 9
72, // Generic 10
76, // Generic 11
80, // Generic 12
84, // Generic 13
88, // Generic 14
92, // Generic 15
96, // Generic 16
100, // Generic 17
104, // Generic 18
108, // Generic 19
112, // Generic 20
116, // Generic 21
120, // Generic 22
124, // Generic 23
128, // Generic 24
132, // Generic 25
136, // Generic 26
140, // Generic 27
144, // Generic 28
148, // Generic 29
152, // Generic 30
156, // Generic 31
160, // gl_FrontColor
164, // gl_FrontSecondaryColor
160, // gl_BackColor
164, // gl_BackSecondaryColor
192, // gl_TexCoord[0]
196, // gl_TexCoord[1]
200, // gl_TexCoord[2]
204, // gl_TexCoord[3]
208, // gl_TexCoord[4]
212, // gl_TexCoord[5]
216, // gl_TexCoord[6]
220, // gl_TexCoord[7]
};
} // namespace
std::unordered_map<u8, VaryingTFB> BuildTransformFeedback(const GraphicsInfo& info) {
std::unordered_map<u8, VaryingTFB> tfb;
for (std::size_t buffer = 0; buffer < Maxwell::NumTransformFeedbackBuffers; ++buffer) {
const auto& locations = info.tfb_varying_locs[buffer];
const auto& layout = info.tfb_layouts[buffer];
const std::size_t varying_count = layout.varying_count;
std::size_t highest = 0;
for (std::size_t offset = 0; offset < varying_count; ++offset) {
const std::size_t base_offset = offset;
const u8 location = locations[offset];
VaryingTFB varying;
varying.buffer = layout.stream;
varying.stride = layout.stride;
varying.offset = offset * sizeof(u32);
varying.components = 1;
if (std::find(VECTORS.begin(), VECTORS.end(), location / 4 * 4) != VECTORS.end()) {
UNIMPLEMENTED_IF_MSG(location % 4 != 0, "Unaligned TFB");
const u8 base_index = location / 4;
while (offset + 1 < varying_count && base_index == locations[offset + 1] / 4) {
++offset;
++varying.components;
}
}
[[maybe_unused]] const bool inserted = tfb.emplace(location, varying).second;
UNIMPLEMENTED_IF_MSG(!inserted, "Varying already stored");
highest = std::max(highest, (base_offset + varying.components) * sizeof(u32));
}
UNIMPLEMENTED_IF(highest != layout.stride);
}
return tfb;
}
} // namespace VideoCommon::Shader

23
src/video_core/shader/transform_feedback.h
View file

@ -1,23 +0,0 @@
// Copyright 2020 yuzu Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#pragma once
#include <unordered_map>
#include "common/common_types.h"
#include "video_core/shader/registry.h"
namespace VideoCommon::Shader {
struct VaryingTFB {
std::size_t buffer;
std::size_t stride;
std::size_t offset;
std::size_t components;
};
std::unordered_map<u8, VaryingTFB> BuildTransformFeedback(const GraphicsInfo& info);
} // namespace VideoCommon::Shader