hdkv/yuzu
1
Fork 0
Code Issues Pull Requests Releases 1 Activity

early-access version 3710

Browse Source
This commit is contained in:
pineappleEA
2023-06-27 19:16:39 +02:00
parent c9635ec98a
commit 23df90e651
30 changed files with 1981 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

129
src/video_core/texture_cache/decode_bc.cpp Executable file
View File

@@ -0,0 +1,129 @@
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#include <algorithm>
#include <array>
#include <span>
#include <bc_decoder.h>
#include "common/common_types.h"
#include "video_core/texture_cache/decode_bc.h"
namespace VideoCommon {
namespace {
constexpr u32 BLOCK_SIZE = 4;
using VideoCore::Surface::PixelFormat;
constexpr bool IsSigned(PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM:
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT:
return true;
default:
return false;
}
}
constexpr u32 BlockSize(PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC1_RGBA_SRGB:
case PixelFormat::BC1_RGBA_UNORM:
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
return 8;
default:
return 16;
}
}
} // Anonymous namespace
u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
return 1;
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM:
return 2;
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT:
return 8;
default:
return 4;
}
}
template <auto decompress, PixelFormat pixel_format>
void DecompressBlocks(std::span<const u8> input, std::span<u8> output, Extent3D extent,
bool is_signed = false) {
const u32 out_bpp = ConvertedBytesPerBlock(pixel_format);
const u32 block_width = std::min(extent.width, BLOCK_SIZE);
const u32 block_height = std::min(extent.height, BLOCK_SIZE);
const u32 pitch = extent.width * out_bpp;
size_t input_offset = 0;
size_t output_offset = 0;
for (u32 slice = 0; slice < extent.depth; ++slice) {
for (u32 y = 0; y < extent.height; y += block_height) {
size_t row_offset = 0;
for (u32 x = 0; x < extent.width;
x += block_width, row_offset += block_width * out_bpp) {
const u8* src = input.data() + input_offset;
u8* const dst = output.data() + output_offset + row_offset;
if constexpr (IsSigned(pixel_format)) {
decompress(src, dst, x, y, extent.width, extent.height, is_signed);
} else {
decompress(src, dst, x, y, extent.width, extent.height);
}
input_offset += BlockSize(pixel_format);
}
output_offset += block_height * pitch;
}
}
}
void DecompressBCn(std::span<const u8> input, std::span<u8> output, Extent3D extent,
VideoCore::Surface::PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC1_RGBA_UNORM:
case PixelFormat::BC1_RGBA_SRGB:
DecompressBlocks<bcn::DecodeBc1, PixelFormat::BC1_RGBA_UNORM>(input, output, extent);
break;
case PixelFormat::BC2_UNORM:
case PixelFormat::BC2_SRGB:
DecompressBlocks<bcn::DecodeBc2, PixelFormat::BC2_UNORM>(input, output, extent);
break;
case PixelFormat::BC3_UNORM:
case PixelFormat::BC3_SRGB:
DecompressBlocks<bcn::DecodeBc3, PixelFormat::BC3_UNORM>(input, output, extent);
break;
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
DecompressBlocks<bcn::DecodeBc4, PixelFormat::BC4_UNORM>(
input, output, extent, pixel_format == PixelFormat::BC4_SNORM);
break;
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM:
DecompressBlocks<bcn::DecodeBc5, PixelFormat::BC5_UNORM>(
input, output, extent, pixel_format == PixelFormat::BC5_SNORM);
break;
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT:
DecompressBlocks<bcn::DecodeBc6, PixelFormat::BC6H_UFLOAT>(
input, output, extent, pixel_format == PixelFormat::BC6H_SFLOAT);
break;
case PixelFormat::BC7_SRGB:
case PixelFormat::BC7_UNORM:
DecompressBlocks<bcn::DecodeBc7, PixelFormat::BC7_UNORM>(input, output, extent);
break;
default:
LOG_WARNING(HW_GPU, "Unimplemented BCn decompression {}", pixel_format);
}
}
} // namespace VideoCommon

19
src/video_core/texture_cache/decode_bc.h Executable file
View File

@@ -0,0 +1,19 @@
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#pragma once
#include <span>
#include "common/common_types.h"
#include "video_core/surface.h"
#include "video_core/texture_cache/types.h"
namespace VideoCommon {
[[nodiscard]] u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format);
void DecompressBCn(std::span<const u8> input, std::span<u8> output, Extent3D extent,
VideoCore::Surface::PixelFormat pixel_format);
} // namespace VideoCommon

24
src/video_core/texture_cache/util.cpp
View File

@@ -24,7 +24,7 @@
#include "video_core/engines/maxwell_3d.h"
#include "video_core/memory_manager.h"
#include "video_core/surface.h"
#include "video_core/texture_cache/decode_bc4.h"
#include "video_core/texture_cache/decode_bc.h"
#include "video_core/texture_cache/format_lookup_table.h"
#include "video_core/texture_cache/formatter.h"
#include "video_core/texture_cache/samples_helper.h"
@@ -61,8 +61,6 @@ using VideoCore::Surface::PixelFormatFromDepthFormat;
using VideoCore::Surface::PixelFormatFromRenderTargetFormat;
using VideoCore::Surface::SurfaceType;
constexpr u32 CONVERTED_BYTES_PER_BLOCK = BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
struct LevelInfo {
Extent3D size;
Extent3D block;
@@ -612,7 +610,8 @@ u32 CalculateConvertedSizeBytes(const ImageInfo& info) noexcept {
}
return output_size;
}
return NumBlocksPerLayer(info, TILE_SIZE) * info.resources.layers * CONVERTED_BYTES_PER_BLOCK;
return NumBlocksPerLayer(info, TILE_SIZE) * info.resources.layers *
ConvertedBytesPerBlock(info.format);
}
u32 CalculateLayerStride(const ImageInfo& info) noexcept {
@@ -945,7 +944,8 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
tile_size.height, output.subspan(output_offset));
output_offset += copy.image_extent.width * copy.image_extent.height *
copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
copy.image_subresource.num_layers *
BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
} else if (astc) {
// BC1 uses 0.5 bytes per texel
// BC3 uses 1 byte per texel
@@ -956,7 +956,8 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
const u32 plane_dim = copy.image_extent.width * copy.image_extent.height;
const u32 level_size = plane_dim * copy.image_extent.depth *
copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
copy.image_subresource.num_layers *
BytesPerBlock(PixelFormat::A8B8G8R8_UNORM);
decode_scratch.resize_destructive(level_size);
Tegra::Texture::ASTC::Decompress(
@@ -976,10 +977,15 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
bpp_div;
output_offset += static_cast<u32>(copy.buffer_size);
} else {
DecompressBC4(input_offset, copy.image_extent, output.subspan(output_offset));
const Extent3D image_extent{
.width = copy.image_extent.width,
.height = copy.image_extent.height * copy.image_subresource.num_layers,
.depth = copy.image_extent.depth,
};
DecompressBCn(input_offset, output.subspan(output_offset), image_extent, info.format);
output_offset += copy.image_extent.width * copy.image_extent.height *
copy.image_subresource.num_layers * CONVERTED_BYTES_PER_BLOCK;
copy.image_subresource.num_layers *
ConvertedBytesPerBlock(info.format);
}
}
}