From 8d6aefdcc452b602d94a84d13bbbc15f806b689c Mon Sep 17 00:00:00 2001
From: Liam
Date: Wed, 14 Jun 2023 14:11:46 -0400
Subject: video_core: optionally skip barriers on feedback loops

---
 src/video_core/texture_cache/texture_cache.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index c7f7448e9..43b7ac0a6 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -186,6 +186,10 @@ void TextureCache<P>::FillComputeImageViews(std::span<ImageViewInOut> views) {
 
 template <class P>
 void TextureCache<P>::CheckFeedbackLoop(std::span<const ImageViewInOut> views) {
+    if (!Settings::values.barrier_feedback_loops.GetValue()) {
+        return;
+    }
+
     const bool requires_barrier = [&] {
         for (const auto& view : views) {
             if (!view.id) {
-- 
cgit v1.2.3


From 76a676883a17523fb12eeac6f2b9702e4916b2c2 Mon Sep 17 00:00:00 2001
From: FengChen
Date: Sat, 17 Jun 2023 23:26:39 +0800
Subject: video_core: add samples check when find render target

---
 src/video_core/texture_cache/texture_cache.h      | 22 ++++++++++------------
 src/video_core/texture_cache/texture_cache_base.h | 10 ++++------
 2 files changed, 14 insertions(+), 18 deletions(-)

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index c7f7448e9..f11998e20 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -280,7 +280,7 @@ void TextureCache<P>::SynchronizeComputeDescriptors() {
 }
 
 template <class P>
-bool TextureCache<P>::RescaleRenderTargets(bool is_clear) {
+bool TextureCache<P>::RescaleRenderTargets() {
     auto& flags = maxwell3d->dirty.flags;
     u32 scale_rating = 0;
     bool rescaled = false;
@@ -318,13 +318,13 @@ bool TextureCache<P>::RescaleRenderTargets(bool is_clear) {
             ImageViewId& color_buffer_id = render_targets.color_buffer_ids[index];
             if (flags[Dirty::ColorBuffer0 + index] || force) {
                 flags[Dirty::ColorBuffer0 + index] = false;
-                BindRenderTarget(&color_buffer_id, FindColorBuffer(index, is_clear));
+                BindRenderTarget(&color_buffer_id, FindColorBuffer(index));
             }
             check_rescale(color_buffer_id, tmp_color_images[index]);
         }
         if (flags[Dirty::ZetaBuffer] || force) {
             flags[Dirty::ZetaBuffer] = false;
-            BindRenderTarget(&render_targets.depth_buffer_id, FindDepthBuffer(is_clear));
+            BindRenderTarget(&render_targets.depth_buffer_id, FindDepthBuffer());
         }
         check_rescale(render_targets.depth_buffer_id, tmp_depth_image);
 
@@ -389,7 +389,7 @@ void TextureCache<P>::UpdateRenderTargets(bool is_clear) {
         return;
     }
 
-    const bool rescaled = RescaleRenderTargets(is_clear);
+    const bool rescaled = RescaleRenderTargets();
     if (is_rescaling != rescaled) {
         flags[Dirty::RescaleViewports] = true;
         flags[Dirty::RescaleScissors] = true;
@@ -1658,7 +1658,7 @@ SamplerId TextureCache<P>::FindSampler(const TSCEntry& config) {
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindColorBuffer(size_t index, bool is_clear) {
+ImageViewId TextureCache<P>::FindColorBuffer(size_t index) {
     const auto& regs = maxwell3d->regs;
     if (index >= regs.rt_control.count) {
         return ImageViewId{};
@@ -1672,11 +1672,11 @@ ImageViewId TextureCache<P>::FindColorBuffer(size_t index, bool is_clear) {
         return ImageViewId{};
     }
     const ImageInfo info(regs.rt[index], regs.anti_alias_samples_mode);
-    return FindRenderTargetView(info, gpu_addr, is_clear);
+    return FindRenderTargetView(info, gpu_addr);
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindDepthBuffer(bool is_clear) {
+ImageViewId TextureCache<P>::FindDepthBuffer() {
     const auto& regs = maxwell3d->regs;
     if (!regs.zeta_enable) {
         return ImageViewId{};
@@ -1686,18 +1686,16 @@ ImageViewId TextureCache<P>::FindDepthBuffer(bool is_clear) {
         return ImageViewId{};
     }
     const ImageInfo info(regs.zeta, regs.zeta_size, regs.anti_alias_samples_mode);
-    return FindRenderTargetView(info, gpu_addr, is_clear);
+    return FindRenderTargetView(info, gpu_addr);
 }
 
 template <class P>
-ImageViewId TextureCache<P>::FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr,
-                                                  bool is_clear) {
-    const auto options = is_clear ? RelaxedOptions::Samples : RelaxedOptions{};
+ImageViewId TextureCache<P>::FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr) {
     ImageId image_id{};
     bool delete_state = has_deleted_images;
     do {
         has_deleted_images = false;
-        image_id = FindOrInsertImage(info, gpu_addr, options);
+        image_id = FindOrInsertImage(info, gpu_addr);
         delete_state |= has_deleted_images;
     } while (has_deleted_images);
     has_deleted_images = delete_state;
diff --git a/src/video_core/texture_cache/texture_cache_base.h b/src/video_core/texture_cache/texture_cache_base.h
index 3bfa92154..c347eccd6 100644
--- a/src/video_core/texture_cache/texture_cache_base.h
+++ b/src/video_core/texture_cache/texture_cache_base.h
@@ -166,9 +166,8 @@ public:
     void SynchronizeComputeDescriptors();
 
     /// Updates the Render Targets if they can be rescaled
-    /// @param is_clear True when the render targets are being used for clears
     /// @retval True if the Render Targets have been rescaled.
-    bool RescaleRenderTargets(bool is_clear);
+    bool RescaleRenderTargets();
 
     /// Update bound render targets and upload memory if necessary
     /// @param is_clear True when the render targets are being used for clears
@@ -324,14 +323,13 @@ private:
     [[nodiscard]] SamplerId FindSampler(const TSCEntry& config);
 
     /// Find or create an image view for the given color buffer index
-    [[nodiscard]] ImageViewId FindColorBuffer(size_t index, bool is_clear);
+    [[nodiscard]] ImageViewId FindColorBuffer(size_t index);
 
     /// Find or create an image view for the depth buffer
-    [[nodiscard]] ImageViewId FindDepthBuffer(bool is_clear);
+    [[nodiscard]] ImageViewId FindDepthBuffer();
 
     /// Find or create a view for a render target with the given image parameters
-    [[nodiscard]] ImageViewId FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr,
-                                                   bool is_clear);
+    [[nodiscard]] ImageViewId FindRenderTargetView(const ImageInfo& info, GPUVAddr gpu_addr);
 
     /// Iterates over all the images in a region calling func
     template <typename Func>
-- 
cgit v1.2.3


From 5da70f719703084482933e103e561cc98163f370 Mon Sep 17 00:00:00 2001
From: Kelebek1
Date: Tue, 23 May 2023 14:45:54 +0100
Subject: Remove memory allocations in some hot paths

---
 src/video_core/texture_cache/image_base.h         |  5 ++-
 src/video_core/texture_cache/texture_cache.h      | 14 +++----
 src/video_core/texture_cache/texture_cache_base.h |  4 +-
 src/video_core/texture_cache/util.cpp             | 48 +++++++++++++----------
 src/video_core/texture_cache/util.h               | 31 ++++++++-------
 5 files changed, 55 insertions(+), 47 deletions(-)

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/image_base.h b/src/video_core/texture_cache/image_base.h
index 1b8a17ee8..55d49d017 100644
--- a/src/video_core/texture_cache/image_base.h
+++ b/src/video_core/texture_cache/image_base.h
@@ -6,6 +6,7 @@
 #include <array>
 #include <optional>
 #include <vector>
+#include <boost/container/small_vector.hpp>
 
 #include "common/common_funcs.h"
 #include "common/common_types.h"
@@ -108,8 +109,8 @@ struct ImageBase {
     std::vector<ImageViewInfo> image_view_infos;
     std::vector<ImageViewId> image_view_ids;
 
-    std::vector<u32> slice_offsets;
-    std::vector<SubresourceBase> slice_subresources;
+    boost::container::small_vector<u32, 16> slice_offsets;
+    boost::container::small_vector<SubresourceBase, 16> slice_subresources;
 
     std::vector<AliasedImage> aliased_images;
     std::vector<ImageId> overlapping_images;
diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index d58bb69ff..d3f03a995 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -526,7 +526,7 @@ void TextureCache<P>::WriteMemory(VAddr cpu_addr, size_t size) {
 
 template <class P>
 void TextureCache<P>::DownloadMemory(VAddr cpu_addr, size_t size) {
-    std::vector<ImageId> images;
+    boost::container::small_vector<ImageId, 16> images;
     ForEachImageInRegion(cpu_addr, size, [&images](ImageId image_id, ImageBase& image) {
         if (!image.IsSafeDownload()) {
             return;
@@ -579,7 +579,7 @@ std::optional<VideoCore::RasterizerDownloadArea> TextureCache<P>::GetFlushArea(V
 
 template <class P>
 void TextureCache<P>::UnmapMemory(VAddr cpu_addr, size_t size) {
-    std::vector<ImageId> deleted_images;
+    boost::container::small_vector<ImageId, 16> deleted_images;
     ForEachImageInRegion(cpu_addr, size, [&](ImageId id, Image&) { deleted_images.push_back(id); });
     for (const ImageId id : deleted_images) {
         Image& image = slot_images[id];
@@ -593,7 +593,7 @@ void TextureCache<P>::UnmapMemory(VAddr cpu_addr, size_t size) {
 
 template <class P>
 void TextureCache<P>::UnmapGPUMemory(size_t as_id, GPUVAddr gpu_addr, size_t size) {
-    std::vector<ImageId> deleted_images;
+    boost::container::small_vector<ImageId, 16> deleted_images;
     ForEachImageInRegionGPU(as_id, gpu_addr, size,
                             [&](ImageId id, Image&) { deleted_images.push_back(id); });
     for (const ImageId id : deleted_images) {
@@ -1101,7 +1101,7 @@ ImageId TextureCache<P>::FindImage(const ImageInfo& info, GPUVAddr gpu_addr,
     const bool native_bgr = runtime.HasNativeBgr();
     const bool flexible_formats = True(options & RelaxedOptions::Format);
     ImageId image_id{};
-    boost::container::small_vector<ImageId, 1> image_ids;
+    boost::container::small_vector<ImageId, 8> image_ids;
     const auto lambda = [&](ImageId existing_image_id, ImageBase& existing_image) {
         if (True(existing_image.flags & ImageFlagBits::Remapped)) {
             return false;
@@ -1622,7 +1622,7 @@ ImageId TextureCache<P>::FindDMAImage(const ImageInfo& info, GPUVAddr gpu_addr)
         }
     }
     ImageId image_id{};
-    boost::container::small_vector<ImageId, 1> image_ids;
+    boost::container::small_vector<ImageId, 8> image_ids;
     const auto lambda = [&](ImageId existing_image_id, ImageBase& existing_image) {
         if (True(existing_image.flags & ImageFlagBits::Remapped)) {
             return false;
@@ -1942,7 +1942,7 @@ void TextureCache<P>::RegisterImage(ImageId image_id) {
         image.map_view_id = map_id;
         return;
     }
-    std::vector<ImageViewId> sparse_maps{};
+    boost::container::small_vector<ImageViewId, 16> sparse_maps;
     ForEachSparseSegment(
         image, [this, image_id, &sparse_maps](GPUVAddr gpu_addr, VAddr cpu_addr, size_t size) {
             auto map_id = slot_map_views.insert(gpu_addr, cpu_addr, size, image_id);
@@ -2217,7 +2217,7 @@ void TextureCache<P>::MarkModification(ImageBase& image) noexcept {
 
 template <class P>
 void TextureCache<P>::SynchronizeAliases(ImageId image_id) {
-    boost::container::small_vector<const AliasedImage*, 1> aliased_images;
+    boost::container::small_vector<const AliasedImage*, 8> aliased_images;
     Image& image = slot_images[image_id];
     bool any_rescaled = True(image.flags & ImageFlagBits::Rescaled);
     bool any_modified = True(image.flags & ImageFlagBits::GpuModified);
diff --git a/src/video_core/texture_cache/texture_cache_base.h b/src/video_core/texture_cache/texture_cache_base.h
index 44232b961..e9ec91265 100644
--- a/src/video_core/texture_cache/texture_cache_base.h
+++ b/src/video_core/texture_cache/texture_cache_base.h
@@ -56,7 +56,7 @@ struct ImageViewInOut {
 struct AsyncDecodeContext {
     ImageId image_id;
     Common::ScratchBuffer<u8> decoded_data;
-    std::vector<BufferImageCopy> copies;
+    boost::container::small_vector<BufferImageCopy, 16> copies;
     std::mutex mutex;
     std::atomic_bool complete;
 };
@@ -429,7 +429,7 @@ private:
 
     std::unordered_map<u64, std::vector<ImageMapId>, Common::IdentityHash<u64>> page_table;
     std::unordered_map<u64, std::vector<ImageId>, Common::IdentityHash<u64>> sparse_page_table;
-    std::unordered_map<ImageId, std::vector<ImageViewId>> sparse_views;
+    std::unordered_map<ImageId, boost::container::small_vector<ImageViewId, 16>> sparse_views;
 
     VAddr virtual_invalid_space{};
 
diff --git a/src/video_core/texture_cache/util.cpp b/src/video_core/texture_cache/util.cpp
index 95a5b47d8..f781cb7a0 100644
--- a/src/video_core/texture_cache/util.cpp
+++ b/src/video_core/texture_cache/util.cpp
@@ -329,13 +329,13 @@ template <u32 GOB_EXTENT>
 
 [[nodiscard]] std::optional<SubresourceExtent> ResolveOverlapRightAddress3D(
     const ImageInfo& new_info, GPUVAddr gpu_addr, const ImageBase& overlap, bool strict_size) {
-    const std::vector<u32> slice_offsets = CalculateSliceOffsets(new_info);
+    const auto slice_offsets = CalculateSliceOffsets(new_info);
     const u32 diff = static_cast<u32>(overlap.gpu_addr - gpu_addr);
     const auto it = std::ranges::find(slice_offsets, diff);
     if (it == slice_offsets.end()) {
         return std::nullopt;
     }
-    const std::vector subresources = CalculateSliceSubresources(new_info);
+    const auto subresources = CalculateSliceSubresources(new_info);
     const SubresourceBase base = subresources[std::distance(slice_offsets.begin(), it)];
     const ImageInfo& info = overlap.info;
     if (!IsBlockLinearSizeCompatible(new_info, info, base.level, 0, strict_size)) {
@@ -655,9 +655,9 @@ LevelArray CalculateMipLevelSizes(const ImageInfo& info) noexcept {
     return sizes;
 }
 
-std::vector<u32> CalculateSliceOffsets(const ImageInfo& info) {
+boost::container::small_vector<u32, 16> CalculateSliceOffsets(const ImageInfo& info) {
     ASSERT(info.type == ImageType::e3D);
-    std::vector<u32> offsets;
+    boost::container::small_vector<u32, 16> offsets;
     offsets.reserve(NumSlices(info));
 
     const LevelInfo level_info = MakeLevelInfo(info);
@@ -679,9 +679,10 @@ std::vector<u32> CalculateSliceOffsets(const ImageInfo& info) {
     return offsets;
 }
 
-std::vector<SubresourceBase> CalculateSliceSubresources(const ImageInfo& info) {
+boost::container::small_vector<SubresourceBase, 16> CalculateSliceSubresources(
+    const ImageInfo& info) {
     ASSERT(info.type == ImageType::e3D);
-    std::vector<SubresourceBase> subresources;
+    boost::container::small_vector<SubresourceBase, 16> subresources;
     subresources.reserve(NumSlices(info));
     for (s32 level = 0; level < info.resources.levels; ++level) {
         const s32 depth = AdjustMipSize(info.size.depth, level);
@@ -723,8 +724,10 @@ ImageViewType RenderTargetImageViewType(const ImageInfo& info) noexcept {
     }
 }
 
-std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageInfo& src,
-                                             SubresourceBase base, u32 up_scale, u32 down_shift) {
+boost::container::small_vector<ImageCopy, 16> MakeShrinkImageCopies(const ImageInfo& dst,
+                                                                    const ImageInfo& src,
+                                                                    SubresourceBase base,
+                                                                    u32 up_scale, u32 down_shift) {
     ASSERT(dst.resources.levels >= src.resources.levels);
 
     const bool is_dst_3d = dst.type == ImageType::e3D;
@@ -733,7 +736,7 @@ std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageIn
         ASSERT(src.resources.levels == 1);
     }
     const bool both_2d{src.type == ImageType::e2D && dst.type == ImageType::e2D};
-    std::vector<ImageCopy> copies;
+    boost::container::small_vector<ImageCopy, 16> copies;
     copies.reserve(src.resources.levels);
     for (s32 level = 0; level < src.resources.levels; ++level) {
         ImageCopy& copy = copies.emplace_back();
@@ -770,9 +773,10 @@ std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst, const ImageIn
     return copies;
 }
 
-std::vector<ImageCopy> MakeReinterpretImageCopies(const ImageInfo& src, u32 up_scale,
-                                                  u32 down_shift) {
-    std::vector<ImageCopy> copies;
+boost::container::small_vector<ImageCopy, 16> MakeReinterpretImageCopies(const ImageInfo& src,
+                                                                         u32 up_scale,
+                                                                         u32 down_shift) {
+    boost::container::small_vector<ImageCopy, 16> copies;
     copies.reserve(src.resources.levels);
     const bool is_3d = src.type == ImageType::e3D;
     for (s32 level = 0; level < src.resources.levels; ++level) {
@@ -824,9 +828,11 @@ bool IsValidEntry(const Tegra::MemoryManager& gpu_memory, const TICEntry& config
     return gpu_memory.GpuToCpuAddress(address, guest_size_bytes).has_value();
 }
 
-std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr,
-                                            const ImageInfo& info, std::span<const u8> input,
-                                            std::span<u8> output) {
+boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(Tegra::MemoryManager& gpu_memory,
+                                                                   GPUVAddr gpu_addr,
+                                                                   const ImageInfo& info,
+                                                                   std::span<const u8> input,
+                                                                   std::span<u8> output) {
     const size_t guest_size_bytes = input.size_bytes();
     const u32 bpp_log2 = BytesPerBlockLog2(info.format);
     const Extent3D size = info.size;
@@ -861,7 +867,7 @@ std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory, GP
                                             info.tile_width_spacing);
     size_t guest_offset = 0;
     u32 host_offset = 0;
-    std::vector<BufferImageCopy> copies(num_levels);
+    boost::container::small_vector<BufferImageCopy, 16> copies(num_levels);
 
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
@@ -978,7 +984,7 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
     }
 }
 
-std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info) {
+boost::container::small_vector<BufferImageCopy, 16> FullDownloadCopies(const ImageInfo& info) {
     const Extent3D size = info.size;
     const u32 bytes_per_block = BytesPerBlock(info.format);
     if (info.type == ImageType::Linear) {
@@ -1006,7 +1012,7 @@ std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info) {
 
     u32 host_offset = 0;
 
-    std::vector<BufferImageCopy> copies(num_levels);
+    boost::container::small_vector<BufferImageCopy, 16> copies(num_levels);
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
         const u32 num_blocks_per_layer = NumBlocks(level_size, tile_size);
@@ -1042,10 +1048,10 @@ Extent3D MipBlockSize(const ImageInfo& info, u32 level) {
     return AdjustMipBlockSize(num_tiles, level_info.block, level);
 }
 
-std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info) {
+boost::container::small_vector<SwizzleParameters, 16> FullUploadSwizzles(const ImageInfo& info) {
     const Extent2D tile_size = DefaultBlockSize(info.format);
     if (info.type == ImageType::Linear) {
-        return std::vector{SwizzleParameters{
+        return {SwizzleParameters{
             .num_tiles = AdjustTileSize(info.size, tile_size),
             .block = {},
             .buffer_offset = 0,
@@ -1057,7 +1063,7 @@ std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info) {
     const s32 num_levels = info.resources.levels;
 
     u32 guest_offset = 0;
-    std::vector<SwizzleParameters> params(num_levels);
+    boost::container::small_vector<SwizzleParameters, 16> params(num_levels);
     for (s32 level = 0; level < num_levels; ++level) {
         const Extent3D level_size = AdjustMipSize(size, level);
         const Extent3D num_tiles = AdjustTileSize(level_size, tile_size);
diff --git a/src/video_core/texture_cache/util.h b/src/video_core/texture_cache/util.h
index 84aa6880d..ab45a43c4 100644
--- a/src/video_core/texture_cache/util.h
+++ b/src/video_core/texture_cache/util.h
@@ -5,6 +5,7 @@
 
 #include <optional>
 #include <span>
+#include <boost/container/small_vector.hpp>
 
 #include "common/common_types.h"
 #include "common/scratch_buffer.h"
@@ -40,9 +41,10 @@ struct OverlapResult {
 
 [[nodiscard]] LevelArray CalculateMipLevelSizes(const ImageInfo& info) noexcept;
 
-[[nodiscard]] std::vector<u32> CalculateSliceOffsets(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<u32, 16> CalculateSliceOffsets(const ImageInfo& info);
 
-[[nodiscard]] std::vector<SubresourceBase> CalculateSliceSubresources(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<SubresourceBase, 16> CalculateSliceSubresources(
+    const ImageInfo& info);
 
 [[nodiscard]] u32 CalculateLevelStrideAlignment(const ImageInfo& info, u32 level);
 
@@ -51,21 +53,18 @@ struct OverlapResult {
 
 [[nodiscard]] ImageViewType RenderTargetImageViewType(const ImageInfo& info) noexcept;
 
-[[nodiscard]] std::vector<ImageCopy> MakeShrinkImageCopies(const ImageInfo& dst,
-                                                           const ImageInfo& src,
-                                                           SubresourceBase base, u32 up_scale = 1,
-                                                           u32 down_shift = 0);
+[[nodiscard]] boost::container::small_vector<ImageCopy, 16> MakeShrinkImageCopies(
+    const ImageInfo& dst, const ImageInfo& src, SubresourceBase base, u32 up_scale = 1,
+    u32 down_shift = 0);
 
-[[nodiscard]] std::vector<ImageCopy> MakeReinterpretImageCopies(const ImageInfo& src,
-                                                                u32 up_scale = 1,
-                                                                u32 down_shift = 0);
+[[nodiscard]] boost::container::small_vector<ImageCopy, 16> MakeReinterpretImageCopies(
+    const ImageInfo& src, u32 up_scale = 1, u32 down_shift = 0);
 
 [[nodiscard]] bool IsValidEntry(const Tegra::MemoryManager& gpu_memory, const TICEntry& config);
 
-[[nodiscard]] std::vector<BufferImageCopy> UnswizzleImage(Tegra::MemoryManager& gpu_memory,
-                                                          GPUVAddr gpu_addr, const ImageInfo& info,
-                                                          std::span<const u8> input,
-                                                          std::span<u8> output);
+[[nodiscard]] boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(
+    Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr, const ImageInfo& info,
+    std::span<const u8> input, std::span<u8> output);
 
 [[nodiscard]] BufferCopy UploadBufferCopy(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr,
                                           const ImageBase& image, std::span<u8> output);
@@ -73,13 +72,15 @@ struct OverlapResult {
 void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output,
                   std::span<BufferImageCopy> copies);
 
-[[nodiscard]] std::vector<BufferImageCopy> FullDownloadCopies(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<BufferImageCopy, 16> FullDownloadCopies(
+    const ImageInfo& info);
 
 [[nodiscard]] Extent3D MipSize(Extent3D size, u32 level);
 
 [[nodiscard]] Extent3D MipBlockSize(const ImageInfo& info, u32 level);
 
-[[nodiscard]] std::vector<SwizzleParameters> FullUploadSwizzles(const ImageInfo& info);
+[[nodiscard]] boost::container::small_vector<SwizzleParameters, 16> FullUploadSwizzles(
+    const ImageInfo& info);
 
 void SwizzleImage(Tegra::MemoryManager& gpu_memory, GPUVAddr gpu_addr, const ImageInfo& info,
                   std::span<const BufferImageCopy> copies, std::span<const u8> memory,
-- 
cgit v1.2.3


From eac46ad7ceca5e35b396a8b80bfc38dc6ef1a4fe Mon Sep 17 00:00:00 2001
From: GPUCode
Date: Tue, 6 Jun 2023 23:10:06 +0300
Subject: video_core: Add BCn decoding support

---
 src/video_core/texture_cache/decode_bc.cpp  | 129 ++++++++++++++++++++++++++++
 src/video_core/texture_cache/decode_bc.h    |  19 ++++
 src/video_core/texture_cache/decode_bc4.cpp |  96 ---------------------
 src/video_core/texture_cache/decode_bc4.h   |  15 ----
 src/video_core/texture_cache/util.cpp       |  24 ++++--
 5 files changed, 163 insertions(+), 120 deletions(-)
 create mode 100644 src/video_core/texture_cache/decode_bc.cpp
 create mode 100644 src/video_core/texture_cache/decode_bc.h
 delete mode 100644 src/video_core/texture_cache/decode_bc4.cpp
 delete mode 100644 src/video_core/texture_cache/decode_bc4.h

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/decode_bc.cpp b/src/video_core/texture_cache/decode_bc.cpp
new file mode 100644
index 000000000..3e26474a3
--- /dev/null
+++ b/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
diff --git a/src/video_core/texture_cache/decode_bc.h b/src/video_core/texture_cache/decode_bc.h
new file mode 100644
index 000000000..41d1ec0a3
--- /dev/null
+++ b/src/video_core/texture_cache/decode_bc.h
@@ -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
diff --git a/src/video_core/texture_cache/decode_bc4.cpp b/src/video_core/texture_cache/decode_bc4.cpp
deleted file mode 100644
index ef98afdca..000000000
--- a/src/video_core/texture_cache/decode_bc4.cpp
+++ /dev/null
@@ -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
diff --git a/src/video_core/texture_cache/decode_bc4.h b/src/video_core/texture_cache/decode_bc4.h
deleted file mode 100644
index ab2f735be..000000000
--- a/src/video_core/texture_cache/decode_bc4.h
+++ /dev/null
@@ -1,15 +0,0 @@
-// 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/texture_cache/types.h"
-
-namespace VideoCommon {
-
-void DecompressBC4(std::span<const u8> data, Extent3D extent, std::span<u8> output);
-
-} // namespace VideoCommon
diff --git a/src/video_core/texture_cache/util.cpp b/src/video_core/texture_cache/util.cpp
index f781cb7a0..9a618a57a 100644
--- a/src/video_core/texture_cache/util.cpp
+++ b/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);
         }
     }
 }
-- 
cgit v1.2.3


From b62121fd605663dc9aaaae72fe8e444312f9c5d5 Mon Sep 17 00:00:00 2001
From: Fernando Sahmkow
Date: Thu, 29 Jun 2023 11:58:45 +0200
Subject: Texture cache: Fix YFC regression due to code testing

---
 src/video_core/texture_cache/texture_cache.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index d3f03a995..485f6b6f3 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -598,14 +598,6 @@ void TextureCache<P>::UnmapGPUMemory(size_t as_id, GPUVAddr gpu_addr, size_t siz
                             [&](ImageId id, Image&) { deleted_images.push_back(id); });
     for (const ImageId id : deleted_images) {
         Image& image = slot_images[id];
-        if (True(image.flags & ImageFlagBits::CpuModified)) {
-            return;
-        }
-        image.flags |= ImageFlagBits::CpuModified;
-        if (True(image.flags & ImageFlagBits::Tracked)) {
-            UntrackImage(image, id);
-        }
-        /*
         if (True(image.flags & ImageFlagBits::Remapped)) {
             continue;
         }
@@ -613,7 +605,6 @@ void TextureCache<P>::UnmapGPUMemory(size_t as_id, GPUVAddr gpu_addr, size_t siz
         if (True(image.flags & ImageFlagBits::Tracked)) {
             UntrackImage(image, id);
         }
-        */
     }
 }
 
-- 
cgit v1.2.3


From 596a6132b974dd73935854d8f51842424e058be8 Mon Sep 17 00:00:00 2001
From: Fernando Sahmkow
Date: Thu, 29 Jun 2023 17:23:29 +0200
Subject: AccelerateDMA: Don't accelerate 3D texture DMA operations

---
 src/video_core/texture_cache/texture_cache.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'src/video_core/texture_cache')

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index d3f03a995..0330415b7 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -879,6 +879,10 @@ ImageId TextureCache<P>::DmaImageId(const Tegra::DMA::ImageOperand& operand, boo
         return NULL_IMAGE_ID;
     }
     auto& image = slot_images[image_id];
+    if (image.info.type == ImageType::e3D) {
+        // Don't accelerate 3D images.
+        return NULL_IMAGE_ID;
+    }
     if (!is_upload && !image.info.dma_downloaded) {
         // Force a full sync.
         image.info.dma_downloaded = true;
-- 
cgit v1.2.3