forked from eden-emu/eden
		
	video_core: Use un-shifted block sizes to avoid integer divisions
Instead of storing all block width, height and depths in their shifted form: block_width = 1U << block_shift; Store them like they are provided by the emulated hardware (their block_shift form). This way we can avoid doing the costly Common::AlignUp operation to align texture sizes and drop CPU integer divisions with bitwise logic (defined in Common::AlignBits).
This commit is contained in:
		
							parent
							
								
									28d7c2f5a5
								
							
						
					
					
						commit
						345e73f2fe
					
				
					 10 changed files with 78 additions and 60 deletions
				
			
		|  | @ -19,6 +19,11 @@ constexpr T AlignDown(T value, std::size_t size) { | ||||||
|     return static_cast<T>(value - value % size); |     return static_cast<T>(value - value % size); | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
|  | template <typename T> | ||||||
|  | constexpr T AlignBits(T value, T align) { | ||||||
|  |     return (value + ((1 << align) - 1)) >> align << align; | ||||||
|  | } | ||||||
|  | 
 | ||||||
| template <typename T> | template <typename T> | ||||||
| constexpr bool Is4KBAligned(T value) { | constexpr bool Is4KBAligned(T value) { | ||||||
|     static_assert(std::is_unsigned_v<T>, "T must be an unsigned value."); |     static_assert(std::is_unsigned_v<T>, "T must be an unsigned value."); | ||||||
|  |  | ||||||
|  | @ -63,18 +63,15 @@ public: | ||||||
|             } |             } | ||||||
| 
 | 
 | ||||||
|             u32 BlockWidth() const { |             u32 BlockWidth() const { | ||||||
|                 // The block width is stored in log2 format.
 |                 return block_width; | ||||||
|                 return 1 << block_width; |  | ||||||
|             } |             } | ||||||
| 
 | 
 | ||||||
|             u32 BlockHeight() const { |             u32 BlockHeight() const { | ||||||
|                 // The block height is stored in log2 format.
 |                 return block_height; | ||||||
|                 return 1 << block_height; |  | ||||||
|             } |             } | ||||||
| 
 | 
 | ||||||
|             u32 BlockDepth() const { |             u32 BlockDepth() const { | ||||||
|                 // The block depth is stored in log2 format.
 |                 return block_depth; | ||||||
|                 return 1 << block_depth; |  | ||||||
|             } |             } | ||||||
|         }; |         }; | ||||||
|         static_assert(sizeof(Surface) == 0x28, "Surface has incorrect size"); |         static_assert(sizeof(Surface) == 0x28, "Surface has incorrect size"); | ||||||
|  |  | ||||||
|  | @ -59,11 +59,11 @@ public: | ||||||
|             }; |             }; | ||||||
| 
 | 
 | ||||||
|             u32 BlockHeight() const { |             u32 BlockHeight() const { | ||||||
|                 return 1 << block_height; |                 return block_height; | ||||||
|             } |             } | ||||||
| 
 | 
 | ||||||
|             u32 BlockDepth() const { |             u32 BlockDepth() const { | ||||||
|                 return 1 << block_depth; |                 return block_depth; | ||||||
|             } |             } | ||||||
|         }; |         }; | ||||||
| 
 | 
 | ||||||
|  |  | ||||||
|  | @ -22,7 +22,6 @@ SurfaceBaseImpl::SurfaceBaseImpl(GPUVAddr gpu_addr, const SurfaceParams& params) | ||||||
|     : params{params}, mipmap_sizes(params.num_levels), |     : params{params}, mipmap_sizes(params.num_levels), | ||||||
|       mipmap_offsets(params.num_levels), gpu_addr{gpu_addr}, host_memory_size{ |       mipmap_offsets(params.num_levels), gpu_addr{gpu_addr}, host_memory_size{ | ||||||
|                                                                  params.GetHostSizeInBytes()} { |                                                                  params.GetHostSizeInBytes()} { | ||||||
| 
 |  | ||||||
|     std::size_t offset = 0; |     std::size_t offset = 0; | ||||||
|     for (u32 level = 0; level < params.num_levels; ++level) { |     for (u32 level = 0; level < params.num_levels; ++level) { | ||||||
|         const std::size_t mipmap_size{params.GetGuestMipmapSize(level)}; |         const std::size_t mipmap_size{params.GetGuestMipmapSize(level)}; | ||||||
|  | @ -75,7 +74,7 @@ void SurfaceBaseImpl::LoadBuffer(Tegra::MemoryManager& memory_manager, | ||||||
|         return; |         return; | ||||||
|     } |     } | ||||||
|     if (params.is_tiled) { |     if (params.is_tiled) { | ||||||
|         ASSERT_MSG(params.block_width == 1, "Block width is defined as {} on texture target {}", |         ASSERT_MSG(params.block_width == 0, "Block width is defined as {} on texture target {}", | ||||||
|                    params.block_width, static_cast<u32>(params.target)); |                    params.block_width, static_cast<u32>(params.target)); | ||||||
|         for (u32 level = 0; level < params.num_levels; ++level) { |         for (u32 level = 0; level < params.num_levels; ++level) { | ||||||
|             const std::size_t host_offset{params.GetHostMipmapLevelOffset(level)}; |             const std::size_t host_offset{params.GetHostMipmapLevelOffset(level)}; | ||||||
|  |  | ||||||
|  | @ -96,9 +96,9 @@ SurfaceParams SurfaceParams::CreateForDepthBuffer( | ||||||
|     SurfaceParams params; |     SurfaceParams params; | ||||||
|     params.is_tiled = type == Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear; |     params.is_tiled = type == Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear; | ||||||
|     params.srgb_conversion = false; |     params.srgb_conversion = false; | ||||||
|     params.block_width = 1 << std::min(block_width, 5U); |     params.block_width = std::min(block_width, 5U); | ||||||
|     params.block_height = 1 << std::min(block_height, 5U); |     params.block_height = std::min(block_height, 5U); | ||||||
|     params.block_depth = 1 << std::min(block_depth, 5U); |     params.block_depth = std::min(block_depth, 5U); | ||||||
|     params.tile_width_spacing = 1; |     params.tile_width_spacing = 1; | ||||||
|     params.pixel_format = PixelFormatFromDepthFormat(format); |     params.pixel_format = PixelFormatFromDepthFormat(format); | ||||||
|     params.component_type = ComponentTypeFromDepthFormat(format); |     params.component_type = ComponentTypeFromDepthFormat(format); | ||||||
|  | @ -120,9 +120,9 @@ SurfaceParams SurfaceParams::CreateForFramebuffer(Core::System& system, std::siz | ||||||
|         config.memory_layout.type == Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear; |         config.memory_layout.type == Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear; | ||||||
|     params.srgb_conversion = config.format == Tegra::RenderTargetFormat::BGRA8_SRGB || |     params.srgb_conversion = config.format == Tegra::RenderTargetFormat::BGRA8_SRGB || | ||||||
|                              config.format == Tegra::RenderTargetFormat::RGBA8_SRGB; |                              config.format == Tegra::RenderTargetFormat::RGBA8_SRGB; | ||||||
|     params.block_width = 1 << config.memory_layout.block_width; |     params.block_width = config.memory_layout.block_width; | ||||||
|     params.block_height = 1 << config.memory_layout.block_height; |     params.block_height = config.memory_layout.block_height; | ||||||
|     params.block_depth = 1 << config.memory_layout.block_depth; |     params.block_depth = config.memory_layout.block_depth; | ||||||
|     params.tile_width_spacing = 1; |     params.tile_width_spacing = 1; | ||||||
|     params.pixel_format = PixelFormatFromRenderTargetFormat(config.format); |     params.pixel_format = PixelFormatFromRenderTargetFormat(config.format); | ||||||
|     params.component_type = ComponentTypeFromRenderTarget(config.format); |     params.component_type = ComponentTypeFromRenderTarget(config.format); | ||||||
|  | @ -149,9 +149,9 @@ SurfaceParams SurfaceParams::CreateForFermiCopySurface( | ||||||
|     params.is_tiled = !config.linear; |     params.is_tiled = !config.linear; | ||||||
|     params.srgb_conversion = config.format == Tegra::RenderTargetFormat::BGRA8_SRGB || |     params.srgb_conversion = config.format == Tegra::RenderTargetFormat::BGRA8_SRGB || | ||||||
|                              config.format == Tegra::RenderTargetFormat::RGBA8_SRGB; |                              config.format == Tegra::RenderTargetFormat::RGBA8_SRGB; | ||||||
|     params.block_width = params.is_tiled ? std::min(config.BlockWidth(), 32U) : 0, |     params.block_width = params.is_tiled ? std::min(config.BlockWidth(), 5U) : 0, | ||||||
|     params.block_height = params.is_tiled ? std::min(config.BlockHeight(), 32U) : 0, |     params.block_height = params.is_tiled ? std::min(config.BlockHeight(), 5U) : 0, | ||||||
|     params.block_depth = params.is_tiled ? std::min(config.BlockDepth(), 32U) : 0, |     params.block_depth = params.is_tiled ? std::min(config.BlockDepth(), 5U) : 0, | ||||||
|     params.tile_width_spacing = 1; |     params.tile_width_spacing = 1; | ||||||
|     params.pixel_format = PixelFormatFromRenderTargetFormat(config.format); |     params.pixel_format = PixelFormatFromRenderTargetFormat(config.format); | ||||||
|     params.component_type = ComponentTypeFromRenderTarget(config.format); |     params.component_type = ComponentTypeFromRenderTarget(config.format); | ||||||
|  | @ -190,9 +190,9 @@ u32 SurfaceParams::GetMipBlockHeight(u32 level) const { | ||||||
|     const u32 height{GetMipHeight(level)}; |     const u32 height{GetMipHeight(level)}; | ||||||
|     const u32 default_block_height{GetDefaultBlockHeight()}; |     const u32 default_block_height{GetDefaultBlockHeight()}; | ||||||
|     const u32 blocks_in_y{(height + default_block_height - 1) / default_block_height}; |     const u32 blocks_in_y{(height + default_block_height - 1) / default_block_height}; | ||||||
|     u32 block_height = 16; |     u32 block_height = 4; | ||||||
|     while (block_height > 1 && blocks_in_y <= block_height * 4) { |     while (block_height > 0 && blocks_in_y <= (1U << block_height) * 4) { | ||||||
|         block_height >>= 1; |         --block_height; | ||||||
|     } |     } | ||||||
|     return block_height; |     return block_height; | ||||||
| } | } | ||||||
|  | @ -202,17 +202,17 @@ u32 SurfaceParams::GetMipBlockDepth(u32 level) const { | ||||||
|         return this->block_depth; |         return this->block_depth; | ||||||
|     } |     } | ||||||
|     if (is_layered) { |     if (is_layered) { | ||||||
|         return 1; |         return 0; | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     const u32 depth{GetMipDepth(level)}; |     const u32 depth{GetMipDepth(level)}; | ||||||
|     u32 block_depth = 32; |     u32 block_depth = 5; | ||||||
|     while (block_depth > 1 && depth * 2 <= block_depth) { |     while (block_depth > 0 && depth * 2 <= (1U << block_depth)) { | ||||||
|         block_depth >>= 1; |         --block_depth; | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     if (block_depth == 32 && GetMipBlockHeight(level) >= 4) { |     if (block_depth == 5 && GetMipBlockHeight(level) >= 2) { | ||||||
|         return 16; |         return 4; | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     return block_depth; |     return block_depth; | ||||||
|  | @ -252,7 +252,8 @@ std::size_t SurfaceParams::GetLayerSize(bool as_host_size, bool uncompressed) co | ||||||
|         size += GetInnerMipmapMemorySize(level, as_host_size, uncompressed); |         size += GetInnerMipmapMemorySize(level, as_host_size, uncompressed); | ||||||
|     } |     } | ||||||
|     if (is_tiled && is_layered) { |     if (is_tiled && is_layered) { | ||||||
|         return Common::AlignUp(size, Tegra::Texture::GetGOBSize() * block_height * block_depth); |         return Common::AlignBits(size, | ||||||
|  |                                  Tegra::Texture::GetGOBSizeShift() + block_height + block_depth); | ||||||
|     } |     } | ||||||
|     return size; |     return size; | ||||||
| } | } | ||||||
|  |  | ||||||
|  | @ -54,12 +54,12 @@ public: | ||||||
|             constexpr std::size_t rgb8_bpp = 4ULL; |             constexpr std::size_t rgb8_bpp = 4ULL; | ||||||
|             // ASTC is uncompressed in software, in emulated as RGBA8
 |             // ASTC is uncompressed in software, in emulated as RGBA8
 | ||||||
|             host_size_in_bytes = 0; |             host_size_in_bytes = 0; | ||||||
|             for (std::size_t level = 0; level < num_levels; level++) { |             for (u32 level = 0; level < num_levels; ++level) { | ||||||
|                 const std::size_t width = |                 const std::size_t width = | ||||||
|                     Common::AlignUp(GetMipWidth(level), GetDefaultBlockWidth()); |                     Common::AlignUp(GetMipWidth(level), GetDefaultBlockWidth()); | ||||||
|                 const std::size_t height = |                 const std::size_t height = | ||||||
|                     Common::AlignUp(GetMipHeight(level), GetDefaultBlockHeight()); |                     Common::AlignUp(GetMipHeight(level), GetDefaultBlockHeight()); | ||||||
|                 const std::size_t depth = is_layered ? depth : GetMipDepth(level); |                 const std::size_t depth = is_layered ? this->depth : GetMipDepth(level); | ||||||
|                 host_size_in_bytes += width * height * depth * rgb8_bpp; |                 host_size_in_bytes += width * height * depth * rgb8_bpp; | ||||||
|             } |             } | ||||||
|         } else { |         } else { | ||||||
|  | @ -96,7 +96,8 @@ public: | ||||||
|     // Helper used for out of class size calculations
 |     // Helper used for out of class size calculations
 | ||||||
|     static std::size_t AlignLayered(const std::size_t out_size, const u32 block_height, |     static std::size_t AlignLayered(const std::size_t out_size, const u32 block_height, | ||||||
|                                     const u32 block_depth) { |                                     const u32 block_depth) { | ||||||
|         return Common::AlignUp(out_size, Tegra::Texture::GetGOBSize() * block_height * block_depth); |         return Common::AlignBits(out_size, | ||||||
|  |                                  Tegra::Texture::GetGOBSizeShift() + block_height + block_depth); | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     /// Returns the offset in bytes in guest memory of a given mipmap level.
 |     /// Returns the offset in bytes in guest memory of a given mipmap level.
 | ||||||
|  |  | ||||||
|  | @ -81,6 +81,9 @@ public: | ||||||
|         if (!gpu_addr) { |         if (!gpu_addr) { | ||||||
|             return {}; |             return {}; | ||||||
|         } |         } | ||||||
|  |         if (gpu_addr == 0x1b7ec0000) { | ||||||
|  |             // __debugbreak();
 | ||||||
|  |         } | ||||||
|         const auto params{SurfaceParams::CreateForTexture(system, config, entry)}; |         const auto params{SurfaceParams::CreateForTexture(system, config, entry)}; | ||||||
|         return GetSurface(gpu_addr, params, true).second; |         return GetSurface(gpu_addr, params, true).second; | ||||||
|     } |     } | ||||||
|  |  | ||||||
|  | @ -36,10 +36,16 @@ struct alignas(64) SwizzleTable { | ||||||
|     std::array<std::array<u16, M>, N> values{}; |     std::array<std::array<u16, M>, N> values{}; | ||||||
| }; | }; | ||||||
| 
 | 
 | ||||||
| constexpr u32 gob_size_x = 64; | constexpr u32 gob_size_x_shift = 6; | ||||||
| constexpr u32 gob_size_y = 8; | constexpr u32 gob_size_y_shift = 3; | ||||||
| constexpr u32 gob_size_z = 1; | constexpr u32 gob_size_z_shift = 0; | ||||||
| constexpr u32 gob_size = gob_size_x * gob_size_y * gob_size_z; | constexpr u32 gob_size_shift = gob_size_x_shift + gob_size_y_shift + gob_size_z_shift; | ||||||
|  | 
 | ||||||
|  | constexpr u32 gob_size_x = 1U << gob_size_x_shift; | ||||||
|  | constexpr u32 gob_size_y = 1U << gob_size_y_shift; | ||||||
|  | constexpr u32 gob_size_z = 1U << gob_size_z_shift; | ||||||
|  | constexpr u32 gob_size = 1U << gob_size_shift; | ||||||
|  | 
 | ||||||
| constexpr u32 fast_swizzle_align = 16; | constexpr u32 fast_swizzle_align = 16; | ||||||
| 
 | 
 | ||||||
| constexpr auto legacy_swizzle_table = SwizzleTable<gob_size_y, gob_size_x, gob_size_z>(); | constexpr auto legacy_swizzle_table = SwizzleTable<gob_size_y, gob_size_x, gob_size_z>(); | ||||||
|  | @ -171,14 +177,16 @@ void SwizzledData(u8* const swizzled_data, u8* const unswizzled_data, const bool | ||||||
| void CopySwizzledData(u32 width, u32 height, u32 depth, u32 bytes_per_pixel, | void CopySwizzledData(u32 width, u32 height, u32 depth, u32 bytes_per_pixel, | ||||||
|                       u32 out_bytes_per_pixel, u8* const swizzled_data, u8* const unswizzled_data, |                       u32 out_bytes_per_pixel, u8* const swizzled_data, u8* const unswizzled_data, | ||||||
|                       bool unswizzle, u32 block_height, u32 block_depth, u32 width_spacing) { |                       bool unswizzle, u32 block_height, u32 block_depth, u32 width_spacing) { | ||||||
|  |     const u32 block_height_size{1U << block_height}; | ||||||
|  |     const u32 block_depth_size{1U << block_depth}; | ||||||
|     if (bytes_per_pixel % 3 != 0 && (width * bytes_per_pixel) % fast_swizzle_align == 0) { |     if (bytes_per_pixel % 3 != 0 && (width * bytes_per_pixel) % fast_swizzle_align == 0) { | ||||||
|         SwizzledData<true>(swizzled_data, unswizzled_data, unswizzle, width, height, depth, |         SwizzledData<true>(swizzled_data, unswizzled_data, unswizzle, width, height, depth, | ||||||
|                            bytes_per_pixel, out_bytes_per_pixel, block_height, block_depth, |                            bytes_per_pixel, out_bytes_per_pixel, block_height_size, | ||||||
|                            width_spacing); |                            block_depth_size, width_spacing); | ||||||
|     } else { |     } else { | ||||||
|         SwizzledData<false>(swizzled_data, unswizzled_data, unswizzle, width, height, depth, |         SwizzledData<false>(swizzled_data, unswizzled_data, unswizzle, width, height, depth, | ||||||
|                             bytes_per_pixel, out_bytes_per_pixel, block_height, block_depth, |                             bytes_per_pixel, out_bytes_per_pixel, block_height_size, | ||||||
|                             width_spacing); |                             block_depth_size, width_spacing); | ||||||
|     } |     } | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
|  | @ -249,16 +257,18 @@ std::vector<u8> UnswizzleTexture(u8* address, u32 tile_size_x, u32 tile_size_y, | ||||||
| 
 | 
 | ||||||
| void SwizzleSubrect(u32 subrect_width, u32 subrect_height, u32 source_pitch, u32 swizzled_width, | void SwizzleSubrect(u32 subrect_width, u32 subrect_height, u32 source_pitch, u32 swizzled_width, | ||||||
|                     u32 bytes_per_pixel, u8* swizzled_data, u8* unswizzled_data, u32 block_height) { |                     u32 bytes_per_pixel, u8* swizzled_data, u8* unswizzled_data, u32 block_height) { | ||||||
|  |     const u32 block_height_size{1U << block_height}; | ||||||
|     const u32 image_width_in_gobs{(swizzled_width * bytes_per_pixel + (gob_size_x - 1)) / |     const u32 image_width_in_gobs{(swizzled_width * bytes_per_pixel + (gob_size_x - 1)) / | ||||||
|                                   gob_size_x}; |                                   gob_size_x}; | ||||||
|     for (u32 line = 0; line < subrect_height; ++line) { |     for (u32 line = 0; line < subrect_height; ++line) { | ||||||
|         const u32 gob_address_y = |         const u32 gob_address_y = | ||||||
|             (line / (gob_size_y * block_height)) * gob_size * block_height * image_width_in_gobs + |             (line / (gob_size_y * block_height_size)) * gob_size * block_height_size * | ||||||
|             ((line % (gob_size_y * block_height)) / gob_size_y) * gob_size; |                 image_width_in_gobs + | ||||||
|  |             ((line % (gob_size_y * block_height_size)) / gob_size_y) * gob_size; | ||||||
|         const auto& table = legacy_swizzle_table[line % gob_size_y]; |         const auto& table = legacy_swizzle_table[line % gob_size_y]; | ||||||
|         for (u32 x = 0; x < subrect_width; ++x) { |         for (u32 x = 0; x < subrect_width; ++x) { | ||||||
|             const u32 gob_address = |             const u32 gob_address = | ||||||
|                 gob_address_y + (x * bytes_per_pixel / gob_size_x) * gob_size * block_height; |                 gob_address_y + (x * bytes_per_pixel / gob_size_x) * gob_size * block_height_size; | ||||||
|             const u32 swizzled_offset = gob_address + table[(x * bytes_per_pixel) % gob_size_x]; |             const u32 swizzled_offset = gob_address + table[(x * bytes_per_pixel) % gob_size_x]; | ||||||
|             u8* source_line = unswizzled_data + line * source_pitch + x * bytes_per_pixel; |             u8* source_line = unswizzled_data + line * source_pitch + x * bytes_per_pixel; | ||||||
|             u8* dest_addr = swizzled_data + swizzled_offset; |             u8* dest_addr = swizzled_data + swizzled_offset; | ||||||
|  | @ -271,14 +281,17 @@ void SwizzleSubrect(u32 subrect_width, u32 subrect_height, u32 source_pitch, u32 | ||||||
| void UnswizzleSubrect(u32 subrect_width, u32 subrect_height, u32 dest_pitch, u32 swizzled_width, | void UnswizzleSubrect(u32 subrect_width, u32 subrect_height, u32 dest_pitch, u32 swizzled_width, | ||||||
|                       u32 bytes_per_pixel, u8* swizzled_data, u8* unswizzled_data, u32 block_height, |                       u32 bytes_per_pixel, u8* swizzled_data, u8* unswizzled_data, u32 block_height, | ||||||
|                       u32 offset_x, u32 offset_y) { |                       u32 offset_x, u32 offset_y) { | ||||||
|  |     const u32 block_height_size{1U << block_height}; | ||||||
|     for (u32 line = 0; line < subrect_height; ++line) { |     for (u32 line = 0; line < subrect_height; ++line) { | ||||||
|         const u32 y2 = line + offset_y; |         const u32 y2 = line + offset_y; | ||||||
|         const u32 gob_address_y = (y2 / (gob_size_y * block_height)) * gob_size * block_height + |         const u32 gob_address_y = | ||||||
|                                   ((y2 % (gob_size_y * block_height)) / gob_size_y) * gob_size; |             (y2 / (gob_size_y * block_height_size)) * gob_size * block_height_size + | ||||||
|  |             ((y2 % (gob_size_y * block_height_size)) / gob_size_y) * gob_size; | ||||||
|         const auto& table = legacy_swizzle_table[y2 % gob_size_y]; |         const auto& table = legacy_swizzle_table[y2 % gob_size_y]; | ||||||
|         for (u32 x = 0; x < subrect_width; ++x) { |         for (u32 x = 0; x < subrect_width; ++x) { | ||||||
|             const u32 x2 = (x + offset_x) * bytes_per_pixel; |             const u32 x2 = (x + offset_x) * bytes_per_pixel; | ||||||
|             const u32 gob_address = gob_address_y + (x2 / gob_size_x) * gob_size * block_height; |             const u32 gob_address = | ||||||
|  |                 gob_address_y + (x2 / gob_size_x) * gob_size * block_height_size; | ||||||
|             const u32 swizzled_offset = gob_address + table[x2 % gob_size_x]; |             const u32 swizzled_offset = gob_address + table[x2 % gob_size_x]; | ||||||
|             u8* dest_line = unswizzled_data + line * dest_pitch + x * bytes_per_pixel; |             u8* dest_line = unswizzled_data + line * dest_pitch + x * bytes_per_pixel; | ||||||
|             u8* source_addr = swizzled_data + swizzled_offset; |             u8* source_addr = swizzled_data + swizzled_offset; | ||||||
|  | @ -291,16 +304,18 @@ void UnswizzleSubrect(u32 subrect_width, u32 subrect_height, u32 dest_pitch, u32 | ||||||
| void SwizzleKepler(const u32 width, const u32 height, const u32 dst_x, const u32 dst_y, | void SwizzleKepler(const u32 width, const u32 height, const u32 dst_x, const u32 dst_y, | ||||||
|                    const u32 block_height, const std::size_t copy_size, const u8* source_data, |                    const u32 block_height, const std::size_t copy_size, const u8* source_data, | ||||||
|                    u8* swizzle_data) { |                    u8* swizzle_data) { | ||||||
|  |     const u32 block_height_size{1U << block_height}; | ||||||
|     const u32 image_width_in_gobs{(width + gob_size_x - 1) / gob_size_x}; |     const u32 image_width_in_gobs{(width + gob_size_x - 1) / gob_size_x}; | ||||||
|     std::size_t count = 0; |     std::size_t count = 0; | ||||||
|     for (std::size_t y = dst_y; y < height && count < copy_size; ++y) { |     for (std::size_t y = dst_y; y < height && count < copy_size; ++y) { | ||||||
|         const std::size_t gob_address_y = |         const std::size_t gob_address_y = | ||||||
|             (y / (gob_size_y * block_height)) * gob_size * block_height * image_width_in_gobs + |             (y / (gob_size_y * block_height_size)) * gob_size * block_height_size * | ||||||
|             ((y % (gob_size_y * block_height)) / gob_size_y) * gob_size; |                 image_width_in_gobs + | ||||||
|  |             ((y % (gob_size_y * block_height_size)) / gob_size_y) * gob_size; | ||||||
|         const auto& table = legacy_swizzle_table[y % gob_size_y]; |         const auto& table = legacy_swizzle_table[y % gob_size_y]; | ||||||
|         for (std::size_t x = dst_x; x < width && count < copy_size; ++x) { |         for (std::size_t x = dst_x; x < width && count < copy_size; ++x) { | ||||||
|             const std::size_t gob_address = |             const std::size_t gob_address = | ||||||
|                 gob_address_y + (x / gob_size_x) * gob_size * block_height; |                 gob_address_y + (x / gob_size_x) * gob_size * block_height_size; | ||||||
|             const std::size_t swizzled_offset = gob_address + table[x % gob_size_x]; |             const std::size_t swizzled_offset = gob_address + table[x % gob_size_x]; | ||||||
|             const u8* source_line = source_data + count; |             const u8* source_line = source_data + count; | ||||||
|             u8* dest_addr = swizzle_data + swizzled_offset; |             u8* dest_addr = swizzle_data + swizzled_offset; | ||||||
|  | @ -356,9 +371,9 @@ std::vector<u8> DecodeTexture(const std::vector<u8>& texture_data, TextureFormat | ||||||
| std::size_t CalculateSize(bool tiled, u32 bytes_per_pixel, u32 width, u32 height, u32 depth, | std::size_t CalculateSize(bool tiled, u32 bytes_per_pixel, u32 width, u32 height, u32 depth, | ||||||
|                           u32 block_height, u32 block_depth) { |                           u32 block_height, u32 block_depth) { | ||||||
|     if (tiled) { |     if (tiled) { | ||||||
|         const u32 aligned_width = Common::AlignUp(width * bytes_per_pixel, gob_size_x); |         const u32 aligned_width = Common::AlignBits(width * bytes_per_pixel, gob_size_x_shift); | ||||||
|         const u32 aligned_height = Common::AlignUp(height, gob_size_y * block_height); |         const u32 aligned_height = Common::AlignBits(height, gob_size_y_shift + block_height); | ||||||
|         const u32 aligned_depth = Common::AlignUp(depth, gob_size_z * block_depth); |         const u32 aligned_depth = Common::AlignBits(depth, gob_size_z_shift + block_depth); | ||||||
|         return aligned_width * aligned_height * aligned_depth; |         return aligned_width * aligned_height * aligned_depth; | ||||||
|     } else { |     } else { | ||||||
|         return width * height * depth * bytes_per_pixel; |         return width * height * depth * bytes_per_pixel; | ||||||
|  |  | ||||||
|  | @ -12,8 +12,8 @@ namespace Tegra::Texture { | ||||||
| 
 | 
 | ||||||
| // GOBSize constant. Calculated by 64 bytes in x multiplied by 8 y coords, represents
 | // GOBSize constant. Calculated by 64 bytes in x multiplied by 8 y coords, represents
 | ||||||
| // an small rect of (64/bytes_per_pixel)X8.
 | // an small rect of (64/bytes_per_pixel)X8.
 | ||||||
| inline std::size_t GetGOBSize() { | inline std::size_t GetGOBSizeShift() { | ||||||
|     return 512; |     return 9; | ||||||
| } | } | ||||||
| 
 | 
 | ||||||
| /// Unswizzles a swizzled texture without changing its format.
 | /// Unswizzles a swizzled texture without changing its format.
 | ||||||
|  |  | ||||||
|  | @ -219,20 +219,17 @@ struct TICEntry { | ||||||
| 
 | 
 | ||||||
|     u32 BlockWidth() const { |     u32 BlockWidth() const { | ||||||
|         ASSERT(IsTiled()); |         ASSERT(IsTiled()); | ||||||
|         // The block height is stored in log2 format.
 |         return block_width; | ||||||
|         return 1 << block_width; |  | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     u32 BlockHeight() const { |     u32 BlockHeight() const { | ||||||
|         ASSERT(IsTiled()); |         ASSERT(IsTiled()); | ||||||
|         // The block height is stored in log2 format.
 |         return block_height; | ||||||
|         return 1 << block_height; |  | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     u32 BlockDepth() const { |     u32 BlockDepth() const { | ||||||
|         ASSERT(IsTiled()); |         ASSERT(IsTiled()); | ||||||
|         // The block height is stored in log2 format.
 |         return block_depth; | ||||||
|         return 1 << block_depth; |  | ||||||
|     } |     } | ||||||
| 
 | 
 | ||||||
|     bool IsTiled() const { |     bool IsTiled() const { | ||||||
|  |  | ||||||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue
	
	 ReinUsesLisp
						ReinUsesLisp