forked from eden-emu/eden
		
	Implement Block Linear copies in Kepler Memory.
This commit is contained in:
		
							parent
							
								
									02c84726ed
								
							
						
					
					
						commit
						15368c6070
					
				
					 3 changed files with 38 additions and 5 deletions
				
			
		|  | @ -10,7 +10,6 @@ | |||
| #include "video_core/memory_manager.h" | ||||
| #include "video_core/rasterizer_interface.h" | ||||
| #include "video_core/renderer_base.h" | ||||
| #include "video_core/textures/convert.h" | ||||
| #include "video_core/textures/decoders.h" | ||||
| 
 | ||||
| namespace Tegra::Engines { | ||||
|  | @ -47,13 +46,12 @@ void KeplerMemory::ProcessExec() { | |||
| 
 | ||||
| void KeplerMemory::ProcessData(u32 data, bool is_last_call) { | ||||
|     const u32 sub_copy_size = std::min(4U, state.copy_size - state.write_offset); | ||||
|     std::memcpy(&state.inner_buffer[state.write_offset], &data, sub_copy_size); | ||||
|     std::memcpy(&state.inner_buffer[state.write_offset], ®s.data, sub_copy_size); | ||||
|     state.write_offset += sub_copy_size; | ||||
|     if (is_last_call) { | ||||
|         UNIMPLEMENTED_IF_MSG(regs.exec.linear == 0, "Block Linear Copy is not implemented"); | ||||
|         const GPUVAddr address{regs.dest.Address()}; | ||||
|         const auto host_ptr = memory_manager.GetPointer(address); | ||||
|         if (regs.exec.linear != 0) { | ||||
|             const GPUVAddr address{regs.dest.Address()}; | ||||
|             const auto host_ptr = memory_manager.GetPointer(address); | ||||
|             // We have to invalidate the destination region to evict any outdated surfaces from the
 | ||||
|             // cache. We do this before actually writing the new data because the destination
 | ||||
|             // address might contain a dirty surface that will have to be written back to memory.
 | ||||
|  | @ -61,6 +59,17 @@ void KeplerMemory::ProcessData(u32 data, bool is_last_call) { | |||
|             rasterizer.InvalidateRegion(ToCacheAddr(host_ptr), state.copy_size); | ||||
|             std::memcpy(host_ptr, state.inner_buffer.data(), state.copy_size); | ||||
|             system.GPU().Maxwell3D().dirty_flags.OnMemoryWrite(); | ||||
|         } else { | ||||
|             UNIMPLEMENTED_IF(regs.dest.z != 0); | ||||
|             UNIMPLEMENTED_IF(regs.dest.depth != 1); | ||||
|             UNIMPLEMENTED_IF(regs.dest.BlockWidth() != 1); | ||||
|             UNIMPLEMENTED_IF(regs.dest.BlockDepth() != 1); | ||||
|             const std::size_t dst_size = Tegra::Texture::CalculateSize( | ||||
|                 true, 1, regs.dest.width, regs.dest.height, 1, regs.dest.BlockHeight(), 1); | ||||
|             rasterizer.InvalidateRegion(ToCacheAddr(host_ptr), dst_size); | ||||
|             Tegra::Texture::SwizzleKepler(regs.dest.width, regs.dest.height, regs.dest.x, | ||||
|                                           regs.dest.y, regs.dest.BlockHeight(), state.copy_size, | ||||
|                                           state.inner_buffer.data(), host_ptr); | ||||
|         } | ||||
|     } | ||||
| } | ||||
|  |  | |||
|  | @ -288,6 +288,27 @@ void UnswizzleSubrect(u32 subrect_width, u32 subrect_height, u32 dest_pitch, u32 | |||
|     } | ||||
| } | ||||
| 
 | ||||
| void SwizzleKepler(u32 width, u32 height, u32 dst_x, u32 dst_y, u32 block_height, | ||||
|                    std::size_t copy_size, u8* source_data, u8* swizzle_data) { | ||||
|     const u32 image_width_in_gobs{(width + gob_size_x - 1) / gob_size_x}; | ||||
|     std::size_t count = 0; | ||||
|     for (u32 y = dst_y; y < height && count < copy_size; ++y) { | ||||
|         const u32 gob_address_y = | ||||
|             (y / (gob_size_y * block_height)) * gob_size * block_height * image_width_in_gobs + | ||||
|             ((y % (gob_size_y * block_height)) / gob_size_y) * gob_size; | ||||
|         const auto& table = legacy_swizzle_table[y % gob_size_y]; | ||||
|         for (u32 x = dst_x; x < width && count < copy_size; ++x) { | ||||
|             const u32 gob_address = gob_address_y + (x / gob_size_x) * gob_size * block_height; | ||||
|             const u32 swizzled_offset = gob_address + table[x % gob_size_x]; | ||||
|             const u8* source_line = source_data + count; | ||||
|             u8* dest_addr = swizzle_data + swizzled_offset; | ||||
|             count++; | ||||
| 
 | ||||
|             std::memcpy(dest_addr, source_line, 1); | ||||
|         } | ||||
|     } | ||||
| } | ||||
| 
 | ||||
| std::vector<u8> DecodeTexture(const std::vector<u8>& texture_data, TextureFormat format, u32 width, | ||||
|                               u32 height) { | ||||
|     std::vector<u8> rgba_data; | ||||
|  |  | |||
|  | @ -51,4 +51,7 @@ void UnswizzleSubrect(u32 subrect_width, u32 subrect_height, u32 dest_pitch, u32 | |||
|                       u32 bytes_per_pixel, u8* swizzled_data, u8* unswizzled_data, u32 block_height, | ||||
|                       u32 offset_x, u32 offset_y); | ||||
| 
 | ||||
| void SwizzleKepler(u32 width, u32 height, u32 dst_x, u32 dst_y, u32 block_height, | ||||
|                    std::size_t copy_size, u8* source_data, u8* swizzle_data); | ||||
| 
 | ||||
| } // namespace Tegra::Texture
 | ||||
|  |  | |||
		Loading…
	
	Add table
		Add a link
		
	
		Reference in a new issue
	
	 Fernando Sahmkow
						Fernando Sahmkow