video_core: Add BCn decoding support

externals/CMakeLists.txt

@@ -157,6 +157,9 @@ endif()
 add_library(stb stb/stb_dxt.cpp)
 target_include_directories(stb PUBLIC ./stb)
 
+add_library(bc_decoder bc_decoder/bc_decoder.cpp)
+target_include_directories(bc_decoder PUBLIC ./bc_decoder)
+
 if (ANDROID)
    if (ARCHITECTURE_arm64)
        add_subdirectory(libadrenotools)

externals/bc_decoder/bc_decoder.h

@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: MPL-2.0
+// Copyright © 2022 Skyline Team and Contributors (https://github.com/skyline-emu/)
+
+#pragma once
+
+#include <cstdint>
+
+namespace bcn {
+    /**
+     * @brief Decodes a BC1 encoded image to R8G8B8A8
+     */
+    void DecodeBc1(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC2 encoded image to R8G8B8A8
+     */
+    void DecodeBc2(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC3 encoded image to R8G8B8A8
+     */
+    void DecodeBc3(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC4 encoded image to R8
+     */
+    void DecodeBc4(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
+
+    /**
+     * @brief Decodes a BC5 encoded image to R8G8
+     */
+    void DecodeBc5(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
+
+    /**
+     * @brief Decodes a BC6 encoded image to R16G16B16A16
+     */
+    void DecodeBc6(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
+
+    /**
+     * @brief Decodes a BC7 encoded image to R8G8B8A8
+     */
+    void DecodeBc7(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+}

src/video_core/CMakeLists.txt

@@ -220,8 +220,8 @@ add_library(video_core STATIC
     surface.h
     texture_cache/accelerated_swizzle.cpp
     texture_cache/accelerated_swizzle.h
-    texture_cache/decode_bc4.cpp
-    texture_cache/decode_bc4.h
+    texture_cache/decode_bc.cpp
+    texture_cache/decode_bc.h
     texture_cache/descriptor_table.h
     texture_cache/formatter.cpp
     texture_cache/formatter.h
@@ -279,7 +279,7 @@ add_library(video_core STATIC
 create_target_directory_groups(video_core)
 
 target_link_libraries(video_core PUBLIC common core)
-target_link_libraries(video_core PUBLIC glad shader_recompiler stb)
+target_link_libraries(video_core PUBLIC glad shader_recompiler stb bc_decoder)
 
 if (YUZU_USE_BUNDLED_FFMPEG AND NOT (WIN32 OR ANDROID))
     add_dependencies(video_core ffmpeg-build)

src/video_core/renderer_vulkan/maxwell_to_vk.cpp

@@ -259,6 +259,26 @@ FormatInfo SurfaceFormat(const Device& device, FormatType format_type, bool with
             break;
         }
     }
+    // Transcode on hardware that doesn't support BCn natively
+    if (!device.IsOptimalBcnSupported() && VideoCore::Surface::IsPixelFormatBCn(pixel_format)) {
+        const bool is_srgb = with_srgb && VideoCore::Surface::IsPixelFormatSRGB(pixel_format);
+        if (pixel_format == PixelFormat::BC4_SNORM) {
+            tuple.format = VK_FORMAT_R8_SNORM;
+        } else if (pixel_format == PixelFormat::BC4_UNORM) {
+            tuple.format = VK_FORMAT_R8_UNORM;
+        } else if (pixel_format == PixelFormat::BC5_SNORM) {
+            tuple.format = VK_FORMAT_R8G8_SNORM;
+        } else if (pixel_format == PixelFormat::BC5_UNORM) {
+            tuple.format = VK_FORMAT_R8G8_UNORM;
+        } else if (pixel_format == PixelFormat::BC6H_SFLOAT ||
+                   pixel_format == PixelFormat::BC6H_UFLOAT) {
+            tuple.format = VK_FORMAT_R16G16B16A16_SFLOAT;
+        } else if (is_srgb) {
+            tuple.format = VK_FORMAT_A8B8G8R8_SRGB_PACK32;
+        } else {
+            tuple.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
+        }
+    }
     const bool attachable = (tuple.usage & Attachable) != 0;
     const bool storage = (tuple.usage & Storage) != 0;
 

src/video_core/renderer_vulkan/vk_rasterizer.cpp

@@ -315,7 +315,14 @@ void RasterizerVulkan::Clear(u32 layer_count) {
     FlushWork();
     gpu_memory->FlushCaching();
 
+#if ANDROID
+    if (Settings::IsGPULevelHigh()) {
+        // This is problematic on Android, disable on GPU Normal.
         query_cache.UpdateCounters();
+    }
+#else
+    query_cache.UpdateCounters();
+#endif
 
     auto& regs = maxwell3d->regs;
     const bool use_color = regs.clear_surface.R || regs.clear_surface.G || regs.clear_surface.B ||

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -1279,6 +1279,10 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
         flags |= VideoCommon::ImageFlagBits::Converted;
         flags |= VideoCommon::ImageFlagBits::CostlyLoad;
     }
+    if (IsPixelFormatBCn(info.format) && !runtime->device.IsOptimalBcnSupported()) {
+        flags |= VideoCommon::ImageFlagBits::Converted;
+        flags |= VideoCommon::ImageFlagBits::CostlyLoad;
+    }
     if (runtime->device.HasDebuggingToolAttached()) {
         original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
     }

src/video_core/surface.cpp

@@ -269,6 +269,28 @@ bool IsPixelFormatASTC(PixelFormat format) {
     }
 }
 
+bool IsPixelFormatBCn(PixelFormat format) {
+    switch (format) {
+    case PixelFormat::BC1_RGBA_UNORM:
+    case PixelFormat::BC2_UNORM:
+    case PixelFormat::BC3_UNORM:
+    case PixelFormat::BC4_UNORM:
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC5_UNORM:
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC1_RGBA_SRGB:
+    case PixelFormat::BC2_SRGB:
+    case PixelFormat::BC3_SRGB:
+    case PixelFormat::BC7_UNORM:
+    case PixelFormat::BC6H_UFLOAT:
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC7_SRGB:
+        return true;
+    default:
+        return false;
+    }
+}
+
 bool IsPixelFormatSRGB(PixelFormat format) {
     switch (format) {
     case PixelFormat::A8B8G8R8_SRGB:

src/video_core/surface.h

@@ -501,6 +501,8 @@ SurfaceType GetFormatType(PixelFormat pixel_format);
 
 bool IsPixelFormatASTC(PixelFormat format);
 
+bool IsPixelFormatBCn(PixelFormat format);
+
 bool IsPixelFormatSRGB(PixelFormat format);
 
 bool IsPixelFormatInteger(PixelFormat format);

src/video_core/texture_cache/decode_bc.cpp

@@ -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

src/video_core/texture_cache/decode_bc4.h → src/video_core/texture_cache/decode_bc.h

@@ -6,10 +6,14 @@
 #include <span>
 
 #include "common/common_types.h"
+#include "video_core/surface.h"
 #include "video_core/texture_cache/types.h"
 
 namespace VideoCommon {
 
-void DecompressBC4(std::span<const u8> data, Extent3D extent, std::span<u8> output);
+[[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

src/video_core/texture_cache/decode_bc4.cpp

@@ -1,96 +0,0 @@
-// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-#include <algorithm>
-#include <array>
-#include <span>
-
-#include "common/assert.h"
-#include "common/common_types.h"
-#include "video_core/texture_cache/decode_bc4.h"
-#include "video_core/texture_cache/types.h"
-
-namespace VideoCommon {
-
-// https://www.khronos.org/registry/OpenGL/extensions/ARB/ARB_texture_compression_rgtc.txt
-[[nodiscard]] constexpr u32 DecompressBlock(u64 bits, u32 x, u32 y) {
-    const u32 code_offset = 16 + 3 * (4 * y + x);
-    const u32 code = (bits >> code_offset) & 7;
-    const u32 red0 = (bits >> 0) & 0xff;
-    const u32 red1 = (bits >> 8) & 0xff;
-    if (red0 > red1) {
-        switch (code) {
-        case 0:
-            return red0;
-        case 1:
-            return red1;
-        case 2:
-            return (6 * red0 + 1 * red1) / 7;
-        case 3:
-            return (5 * red0 + 2 * red1) / 7;
-        case 4:
-            return (4 * red0 + 3 * red1) / 7;
-        case 5:
-            return (3 * red0 + 4 * red1) / 7;
-        case 6:
-            return (2 * red0 + 5 * red1) / 7;
-        case 7:
-            return (1 * red0 + 6 * red1) / 7;
-        }
-    } else {
-        switch (code) {
-        case 0:
-            return red0;
-        case 1:
-            return red1;
-        case 2:
-            return (4 * red0 + 1 * red1) / 5;
-        case 3:
-            return (3 * red0 + 2 * red1) / 5;
-        case 4:
-            return (2 * red0 + 3 * red1) / 5;
-        case 5:
-            return (1 * red0 + 4 * red1) / 5;
-        case 6:
-            return 0;
-        case 7:
-            return 0xff;
-        }
-    }
-    return 0;
-}
-
-void DecompressBC4(std::span<const u8> input, Extent3D extent, std::span<u8> output) {
-    UNIMPLEMENTED_IF_MSG(extent.width % 4 != 0, "Unaligned width={}", extent.width);
-    UNIMPLEMENTED_IF_MSG(extent.height % 4 != 0, "Unaligned height={}", extent.height);
-    static constexpr u32 BLOCK_SIZE = 4;
-    size_t input_offset = 0;
-    for (u32 slice = 0; slice < extent.depth; ++slice) {
-        for (u32 block_y = 0; block_y < extent.height / 4; ++block_y) {
-            for (u32 block_x = 0; block_x < extent.width / 4; ++block_x) {
-                u64 bits;
-                std::memcpy(&bits, &input[input_offset], sizeof(bits));
-                input_offset += sizeof(bits);
-
-                for (u32 y = 0; y < BLOCK_SIZE; ++y) {
-                    for (u32 x = 0; x < BLOCK_SIZE; ++x) {
-                        const u32 linear_z = slice;
-                        const u32 linear_y = block_y * BLOCK_SIZE + y;
-                        const u32 linear_x = block_x * BLOCK_SIZE + x;
-                        const u32 offset_z = linear_z * extent.width * extent.height;
-                        const u32 offset_y = linear_y * extent.width;
-                        const u32 offset_x = linear_x;
-                        const u32 output_offset = (offset_z + offset_y + offset_x) * 4ULL;
-                        const u32 color = DecompressBlock(bits, x, y);
-                        output[output_offset + 0] = static_cast<u8>(color);
-                        output[output_offset + 1] = 0;
-                        output[output_offset + 2] = 0;
-                        output[output_offset + 3] = 0xff;
-                    }
-                }
-            }
-        }
-    }
-}
-
-} // namespace VideoCommon

src/video_core/texture_cache/util.cpp

@@ -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);
         }
     }
 }

src/video_core/textures/bcn.cpp

@@ -3,7 +3,6 @@
 
 #include <stb_dxt.h>
 #include <string.h>
-
 #include "common/alignment.h"
 #include "video_core/textures/bcn.h"
 #include "video_core/textures/workers.h"

src/video_core/textures/bcn.h

@@ -4,14 +4,13 @@
 #pragma once
 
 #include <span>
-#include <stdint.h>
+
+#include "common/common_types.h"
 
 namespace Tegra::Texture::BCN {
 
-void CompressBC1(std::span<const uint8_t> data, uint32_t width, uint32_t height, uint32_t depth,
-                 std::span<uint8_t> output);
+void CompressBC1(std::span<const u8> data, u32 width, u32 height, u32 depth, std::span<u8> output);
 
-void CompressBC3(std::span<const uint8_t> data, uint32_t width, uint32_t height, uint32_t depth,
-                 std::span<uint8_t> output);
+void CompressBC3(std::span<const u8> data, u32 width, u32 height, u32 depth, std::span<u8> output);
 
 } // namespace Tegra::Texture::BCN

src/video_core/vulkan_common/vulkan_device.h

@@ -293,6 +293,11 @@ public:
         return features.features.textureCompressionASTC_LDR;
     }
 
+    /// Returns true if BCn is natively supported.
+    bool IsOptimalBcnSupported() const {
+        return features.features.textureCompressionBC;
+    }
+
     /// Returns true if descriptor aliasing is natively supported.
     bool IsDescriptorAliasingSupported() const {
         return GetDriverID() != VK_DRIVER_ID_QUALCOMM_PROPRIETARY;
@@ -423,6 +428,11 @@ public:
         return extensions.sampler_filter_minmax;
     }
 
+    /// Returns true if the device supports VK_EXT_shader_stencil_export.
+    bool IsExtShaderStencilExportSupported() const {
+        return extensions.shader_stencil_export;
+    }
+
     /// Returns true if the device supports VK_EXT_depth_range_unrestricted.
     bool IsExtDepthRangeUnrestrictedSupported() const {
         return extensions.depth_range_unrestricted;
@@ -492,11 +502,6 @@ public:
         return extensions.vertex_input_dynamic_state;
     }
 
-    /// Returns true if the device supports VK_EXT_shader_stencil_export.
-    bool IsExtShaderStencilExportSupported() const {
-        return extensions.shader_stencil_export;
-    }
-
     /// Returns true if the device supports VK_EXT_shader_demote_to_helper_invocation
     bool IsExtShaderDemoteToHelperInvocationSupported() const {
         return extensions.shader_demote_to_helper_invocation;