Another try on unswizzling

2026-08-28 09:41:36 +00:00 · 2026-08-27 22:48:53 -04:00
parent faaf1bac64
commit 34f9c0fdec
9 changed files with 427 additions and 18 deletions
@@ -206,6 +206,39 @@ foreach(VARIANT IN ITEMS ${SHADER_TYPE_VARIANTS})
    set(SHADER_HEADERS ${SHADER_HEADERS} ${VARIANT_HEADER_FILE})
 endforeach()

+set(SHADER_DEFINE_VARIANTS
+    "block_linear_unswizzle_2d.comp|nonarrow|HAS_EXTENDED_TYPES=0"
+    "pitch_unswizzle.comp|nonarrow|HAS_EXTENDED_TYPES=0"
+)
+
+foreach(VARIANT IN ITEMS ${SHADER_DEFINE_VARIANTS})
+    string(REPLACE "|" ";" VARIANT_PARTS ${VARIANT})
+    list(GET VARIANT_PARTS 0 VARIANT_FILENAME)
+    list(GET VARIANT_PARTS 1 VARIANT_SUFFIX)
+    list(GET VARIANT_PARTS 2 VARIANT_DEFINE)
+
+    set(VARIANT_SOURCE ${CMAKE_CURRENT_SOURCE_DIR}/${VARIANT_FILENAME})
+    get_filename_component(VARIANT_STEM ${VARIANT_FILENAME} NAME_WE)
+    get_filename_component(VARIANT_EXT ${VARIANT_FILENAME} EXT)
+    string(REPLACE "." "" VARIANT_EXT ${VARIANT_EXT})
+    set(VARIANT_NAME ${VARIANT_STEM}_${VARIANT_SUFFIX}_${VARIANT_EXT})
+
+    string(TOUPPER ${VARIANT_NAME}_SPV VARIANT_VARIABLE_NAME)
+    set(VARIANT_HEADER_FILE ${SHADER_DIR}/${VARIANT_NAME}_spv.h)
+    add_custom_command(
+        OUTPUT
+            ${VARIANT_HEADER_FILE}
+        COMMAND
+            ${GLSLANGVALIDATOR} -V ${QUIET_FLAG} -I"${FIDELITYFX_INCLUDE_DIR}" ${GLSL_FLAGS}
+            -D${VARIANT_DEFINE}
+            --variable-name ${VARIANT_VARIABLE_NAME} -o ${VARIANT_HEADER_FILE} ${VARIANT_SOURCE}
+            --target-env ${SPIR_V_VERSION}
+        MAIN_DEPENDENCY
+            ${VARIANT_SOURCE}
+    )
+    set(SHADER_HEADERS ${SHADER_HEADERS} ${VARIANT_HEADER_FILE})
+endforeach()
+
 foreach(FILEPATH IN ITEMS ${FIDELITYFX_FILES})
    get_filename_component(FILENAME ${FILEPATH} NAME)
    string(REPLACE "." "_" HEADER_NAME ${FILENAME})
@@ -5,9 +5,13 @@

 #ifdef VULKAN

+#ifndef HAS_EXTENDED_TYPES
+#define HAS_EXTENDED_TYPES 1
+#endif
+#if HAS_EXTENDED_TYPES
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_shader_8bit_storage : require
-#define HAS_EXTENDED_TYPES 1
+#endif
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)
@@ -5,9 +5,13 @@

 #ifdef VULKAN

+#ifndef HAS_EXTENDED_TYPES
+#define HAS_EXTENDED_TYPES 1
+#endif
+#if HAS_EXTENDED_TYPES
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_shader_8bit_storage : require
-#define HAS_EXTENDED_TYPES 1
+#endif
 #define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
 #define END_PUSH_CONSTANTS };
 #define UNIFORM(n)
@@ -22,7 +22,11 @@
 #include "video_core/host_shaders/resolve_conditional_render_comp_spv.h"
 #include "video_core/host_shaders/vulkan_quad_indexed_comp_spv.h"
 #include "video_core/host_shaders/vulkan_uint8_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_2d_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_2d_nonarrow_comp_spv.h"
 #include "video_core/host_shaders/block_linear_unswizzle_3d_bcn_comp_spv.h"
+#include "video_core/host_shaders/pitch_unswizzle_comp_spv.h"
+#include "video_core/host_shaders/pitch_unswizzle_nonarrow_comp_spv.h"
 #include "video_core/renderer_vulkan/vk_compute_pass.h"
 #include "video_core/surface.h"
 #include "video_core/renderer_vulkan/vk_descriptor_pool.h"
@@ -872,4 +876,239 @@ void BlockLinearUnswizzle3DPass::UnswizzleChunk(
    });
 }

+constexpr u32 UNSWIZZLE_BINDING_INPUT_BUFFER = 0;
+constexpr u32 UNSWIZZLE_BINDING_OUTPUT_IMAGE = 1;
+constexpr size_t UNSWIZZLE_NUM_BINDINGS = 2;
+
+constexpr std::array<VkDescriptorSetLayoutBinding, UNSWIZZLE_NUM_BINDINGS>
+    UNSWIZZLE_DESCRIPTOR_SET_BINDINGS{{
+        {
+            .binding = UNSWIZZLE_BINDING_INPUT_BUFFER,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
+            .descriptorCount = 1,
+            .stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
+            .pImmutableSamplers = nullptr,
+        },
+        {
+            .binding = UNSWIZZLE_BINDING_OUTPUT_IMAGE,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE,
+            .descriptorCount = 1,
+            .stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
+            .pImmutableSamplers = nullptr,
+        },
+    }};
+
+constexpr std::array<VkDescriptorUpdateTemplateEntry, UNSWIZZLE_NUM_BINDINGS>
+    UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE{{
+        {
+            .dstBinding = UNSWIZZLE_BINDING_INPUT_BUFFER,
+            .dstArrayElement = 0,
+            .descriptorCount = 1,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
+            .offset = UNSWIZZLE_BINDING_INPUT_BUFFER * sizeof(DescriptorUpdateEntry),
+            .stride = sizeof(DescriptorUpdateEntry),
+        },
+        {
+            .dstBinding = UNSWIZZLE_BINDING_OUTPUT_IMAGE,
+            .dstArrayElement = 0,
+            .descriptorCount = 1,
+            .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE,
+            .offset = UNSWIZZLE_BINDING_OUTPUT_IMAGE * sizeof(DescriptorUpdateEntry),
+            .stride = sizeof(DescriptorUpdateEntry),
+        },
+    }};
+
+constexpr DescriptorBankInfo UNSWIZZLE_BANK_INFO{
+    .uniform_buffers = 0,
+    .storage_buffers = 1,
+    .texture_buffers = 0,
+    .image_buffers = 0,
+    .textures = 0,
+    .images = 1,
+    .score = 2,
+};
+
+[[nodiscard]] std::span<const u32> UnswizzleSpv(const Device& device,
+                                                std::span<const u32> extended,
+                                                std::span<const u32> narrow) {
+    if (device.IsStorageBuffer8BitAccessSupported() &&
+        device.IsStorageBuffer16BitAccessSupported()) {
+        return extended;
+    }
+    return narrow;
+}
+
+struct PitchUnswizzlePushConstants {
+    alignas(8) std::array<u32, 2> origin;
+    alignas(8) std::array<s32, 2> destination;
+    u32 bytes_per_block;
+    u32 pitch;
+};
+
+void RecordUnswizzleEntryBarrier(Scheduler& scheduler, VkPipeline vk_pipeline, VkImage vk_image,
+                                 VkImageAspectFlags aspect_mask, bool is_initialized) {
+    scheduler.Record([vk_pipeline, vk_image, aspect_mask,
+                      is_initialized](vk::CommandBuffer cmdbuf) {
+        VkAccessFlags src_access = VK_ACCESS_NONE;
+        VkImageLayout old_layout = VK_IMAGE_LAYOUT_UNDEFINED;
+        if (is_initialized) {
+            src_access = VK_ACCESS_SHADER_WRITE_BIT | VK_ACCESS_TRANSFER_WRITE_BIT |
+                         VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
+            old_layout = VK_IMAGE_LAYOUT_GENERAL;
+        }
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = src_access,
+            .dstAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .oldLayout = old_layout,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        VkPipelineStageFlags src_stage = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
+        if (is_initialized) {
+            src_stage = vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER;
+        }
+        cmdbuf.PipelineBarrier(src_stage, VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, image_barrier);
+        cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, vk_pipeline);
+    });
+}
+
+void RecordUnswizzleExitBarrier(Scheduler& scheduler, VkImage vk_image,
+                                VkImageAspectFlags aspect_mask) {
+    scheduler.Record([vk_image, aspect_mask](vk::CommandBuffer cmdbuf) {
+        const VkImageMemoryBarrier image_barrier{
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_TRANSFER_READ_BIT |
+                             VK_ACCESS_COLOR_ATTACHMENT_READ_BIT,
+            .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .newLayout = VK_IMAGE_LAYOUT_GENERAL,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = vk_image,
+            .subresourceRange{
+                .aspectMask = aspect_mask,
+                .baseMipLevel = 0,
+                .levelCount = VK_REMAINING_MIP_LEVELS,
+                .baseArrayLayer = 0,
+                .layerCount = VK_REMAINING_ARRAY_LAYERS,
+            },
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
+                               vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER, 0, image_barrier);
+    });
+}
+
+BlockLinearUnswizzle2DPass::BlockLinearUnswizzle2DPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, UNSWIZZLE_DESCRIPTOR_SET_BINDINGS,
+                  UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE, UNSWIZZLE_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(
+                      VideoCommon::Accelerated::BlockLinearSwizzle2DParams)>,
+                  UnswizzleSpv(device_, BLOCK_LINEAR_UNSWIZZLE_2D_COMP_SPV,
+                               BLOCK_LINEAR_UNSWIZZLE_2D_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzle2DPass::~BlockLinearUnswizzle2DPass() = default;
+
+void BlockLinearUnswizzle2DPass::Unswizzle(
+    Image& image, const StagingBufferRef& map,
+    std::span<const VideoCommon::SwizzleParameters> swizzles) {
+    using namespace VideoCommon::Accelerated;
+    scheduler.RequestOutsideRenderPassOperationContext();
+    const VkPipeline vk_pipeline = *pipeline;
+    const VkImageAspectFlags aspect_mask = image.AspectMask();
+    const VkImage vk_image = image.Handle();
+    const bool is_initialized = image.ExchangeInitialization();
+    RecordUnswizzleEntryBarrier(scheduler, vk_pipeline, vk_image, aspect_mask, is_initialized);
+
+    const u32 num_layers = static_cast<u32>(image.info.resources.layers);
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        const size_t input_offset = swizzle.buffer_offset + map.offset;
+        const u32 num_dispatches_x = Common::DivCeil(swizzle.num_tiles.width, 32U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 32U);
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(map.buffer, input_offset,
+                                                image.guest_size_bytes - swizzle.buffer_offset);
+        compute_pass_descriptor_queue.AddImage(image.StorageImageView(swizzle.level));
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+
+        const auto params = MakeBlockLinearSwizzle2DParams(swizzle, image.info);
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, num_layers, params,
+                          descriptor_data](vk::CommandBuffer cmdbuf) {
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, params);
+            cmdbuf.Dispatch(num_dispatches_x, num_dispatches_y, num_layers);
+        });
+    }
+    RecordUnswizzleExitBarrier(scheduler, vk_image, aspect_mask);
+}
+
+PitchUnswizzlePass::PitchUnswizzlePass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, UNSWIZZLE_DESCRIPTOR_SET_BINDINGS,
+                  UNSWIZZLE_DESCRIPTOR_UPDATE_TEMPLATE, UNSWIZZLE_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(PitchUnswizzlePushConstants)>,
+                  UnswizzleSpv(device_, PITCH_UNSWIZZLE_COMP_SPV,
+                               PITCH_UNSWIZZLE_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+PitchUnswizzlePass::~PitchUnswizzlePass() = default;
+
+void PitchUnswizzlePass::Unswizzle(Image& image, const StagingBufferRef& map,
+                                   std::span<const VideoCommon::SwizzleParameters> swizzles) {
+    scheduler.RequestOutsideRenderPassOperationContext();
+    const VkPipeline vk_pipeline = *pipeline;
+    const VkImageAspectFlags aspect_mask = image.AspectMask();
+    const VkImage vk_image = image.Handle();
+    const bool is_initialized = image.ExchangeInitialization();
+    RecordUnswizzleEntryBarrier(scheduler, vk_pipeline, vk_image, aspect_mask, is_initialized);
+
+    const u32 bytes_per_block = VideoCore::Surface::BytesPerBlock(image.info.format);
+    const u32 pitch = image.info.pitch;
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        const size_t input_offset = swizzle.buffer_offset + map.offset;
+        const u32 num_dispatches_x = Common::DivCeil(swizzle.num_tiles.width, 32U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 32U);
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(map.buffer, input_offset,
+                                                image.guest_size_bytes - swizzle.buffer_offset);
+        compute_pass_descriptor_queue.AddImage(image.StorageImageView(swizzle.level));
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+
+        const PitchUnswizzlePushConstants params{
+            .origin{0, 0},
+            .destination{0, 0},
+            .bytes_per_block = bytes_per_block,
+            .pitch = pitch,
+        };
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, params,
+                          descriptor_data](vk::CommandBuffer cmdbuf) {
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, params);
+            cmdbuf.Dispatch(num_dispatches_x, num_dispatches_y, 1);
+        });
+    }
+    RecordUnswizzleExitBarrier(scheduler, vk_image, aspect_mask);
+}
+
 } // namespace Vulkan
@@ -164,4 +164,34 @@ private:
    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
 };

+class BlockLinearUnswizzle2DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzle2DPass(
+        const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+        ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzle2DPass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
+class PitchUnswizzlePass final : public ComputePass {
+public:
+    explicit PitchUnswizzlePass(const Device& device_, Scheduler& scheduler_,
+                                DescriptorPool& descriptor_pool_,
+                                ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~PitchUnswizzlePass();
+
+    void Unswizzle(Image& image, const StagingBufferRef& map,
+                   std::span<const VideoCommon::SwizzleParameters> swizzles);
+
+private:
+    Scheduler& scheduler;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
 } // namespace Vulkan
@@ -449,7 +449,9 @@ void Scheduler::EndRenderPass()
                                         | VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
                                         | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT
                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_READ_BIT
-                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
+                                         | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT
+                                         | VK_ACCESS_TRANSFER_READ_BIT
+                                         | VK_ACCESS_TRANSFER_WRITE_BIT,
                        .oldLayout = VK_IMAGE_LAYOUT_GENERAL,
                        .newLayout = VK_IMAGE_LAYOUT_GENERAL,
                        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
@@ -460,7 +462,7 @@ void Scheduler::EndRenderPass()
            }
            cmdbuf.EndRenderPass();
            cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
-                                   VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE,
+                                   VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE_TRANSFER,
                                   0, nullptr, nullptr, vk::Span(barriers.data(), num_images));
            if (has_transform_feedback) {
                static constexpr VkMemoryBarrier XFB_OUTPUT_BARRIER{
@@ -160,6 +160,54 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
          info.size.depth == 1;
 }

+[[nodiscard]] PixelFormat UnswizzleViewFormat(u32 bytes_per_block) {
+    switch (bytes_per_block) {
+    case 1:
+        return PixelFormat::R8_UINT;
+    case 2:
+        return PixelFormat::R16_UINT;
+    case 4:
+        return PixelFormat::R32_UINT;
+    case 8:
+        return PixelFormat::R32G32_UINT;
+    case 16:
+        return PixelFormat::R32G32B32A32_UINT;
+    default:
+        return PixelFormat::Invalid;
+    }
+}
+
+constexpr u32 UNSWIZZLE_WORKGROUP_INVOCATIONS = 32 * 32;
+
+[[nodiscard]] bool SupportsAcceleratedUnswizzleDevice(const Device& device) {
+    return device.IsKhrImageFormatListSupported() &&
+           device.GetMaxComputeWorkGroupInvocations() >= UNSWIZZLE_WORKGROUP_INVOCATIONS;
+}
+
+[[nodiscard]] bool SupportsAcceleratedUnswizzle(const Device& device, const ImageInfo& info) {
+    if (!SupportsAcceleratedUnswizzleDevice(device)) {
+        return false;
+    }
+    if (info.num_samples > 1) {
+        return false;
+    }
+    if (info.type != ImageType::e2D && info.type != ImageType::Linear) {
+        return false;
+    }
+    const PixelFormat view_format =
+        UnswizzleViewFormat(VideoCore::Surface::BytesPerBlock(info.format));
+    if (view_format == PixelFormat::Invalid) {
+        return false;
+    }
+    if (!VideoCore::Surface::IsViewCompatible(info.format, view_format, false, true)) {
+        return false;
+    }
+    const auto host_format =
+        MaxwellToVK::SurfaceFormat(device, FormatType::Optimal, false, view_format);
+    return device.IsFormatSupported(host_format.format, VK_FORMAT_FEATURE_STORAGE_IMAGE_BIT,
+                                    FormatType::Optimal);
+}
+
 [[nodiscard]] VkImageCreateInfo MakeImageCreateInfo(const Device& device, const ImageInfo& info,
                                                    std::optional<VkFormat> format_override = {}) {
    auto format_info =
@@ -248,8 +296,18 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
    return allocator.CreateImage(image_ci);
 }

+[[nodiscard]] VkImageViewType StorageViewType(ImageType type) {
+    if (type == ImageType::e3D) {
+        return VK_IMAGE_VIEW_TYPE_3D;
+    }
+    if (type == ImageType::Linear) {
+        return VK_IMAGE_VIEW_TYPE_2D;
+    }
+    return VK_IMAGE_VIEW_TYPE_2D_ARRAY;
+}
+
 [[nodiscard]] vk::ImageView MakeStorageView(const vk::Device& device, u32 level, VkImage image,
-                                            VkFormat format) {
+                                            VkFormat format, VkImageViewType view_type) {
    static constexpr VkImageViewUsageCreateInfo storage_image_view_usage_create_info{
        .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_USAGE_CREATE_INFO,
        .pNext = nullptr,
@@ -260,7 +318,7 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) {
        .pNext = &storage_image_view_usage_create_info,
        .flags = 0,
        .image = image,
-        .viewType = VK_IMAGE_VIEW_TYPE_2D_ARRAY,
+        .viewType = view_type,
        .format = format,
        .components{
            .r = VK_COMPONENT_SWIZZLE_IDENTITY,
@@ -968,6 +1026,12 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
        bl3d_unswizzle_pass.emplace(device, scheduler, descriptor_pool,
                                   staging_buffer_pool, compute_pass_descriptor_queue);
    }
+    if (SupportsAcceleratedUnswizzleDevice(device)) {
+        bl_unswizzle_2d_pass.emplace(device, scheduler, descriptor_pool,
+                                     compute_pass_descriptor_queue);
+        pitch_unswizzle_pass.emplace(device, scheduler, descriptor_pool,
+                                     compute_pass_descriptor_queue);
+    }
 }

 void TextureCacheRuntime::Finish() {
@@ -1902,16 +1966,12 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu
    if (runtime->device.HasDebuggingToolAttached()) {
        original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str());
    }
+    if (False(flags & VideoCommon::ImageFlagBits::Converted) &&
+        SupportsAcceleratedUnswizzle(runtime->device, info)) {
+        flags |= VideoCommon::ImageFlagBits::AcceleratedUpload;
+    }
    current_image = &Image::original_image;
    storage_image_views.resize(info.resources.levels);
-    if (WillUseAcceleratedAstcDecode(runtime->device, info)) {
-        const auto& device = runtime->device.GetLogical();
-        const VkFormat storage_format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
-        for (s32 level = 0; level < info.resources.levels; ++level) {
-            storage_image_views[level] =
-                MakeStorageView(device, level, *original_image, storage_format);
-        }
-    }
 }

 Image::Image(const VideoCommon::NullImageParams& params) : VideoCommon::ImageBase{params} {}
@@ -2321,16 +2381,39 @@ void Image::DownloadMemory(const StagingBufferRef& map, std::span<const BufferIm
    DownloadMemory(buffers, offsets, copies);
 }

+std::vector<vk::ImageView>& Image::StorageViewsFor(vk::Image Image::*image) {
+    if (image == &Image::scaled_image) {
+        if (scaled_storage_image_views.empty()) {
+            scaled_storage_image_views.resize(info.resources.levels);
+        }
+        return scaled_storage_image_views;
+    }
+    return storage_image_views;
+}
+
 VkImageView Image::StorageImageView(s32 level) noexcept {
-    auto& view = storage_image_views[level];
+    const bool astc_decode = WillUseAcceleratedAstcDecode(runtime->device, info);
+    const bool unswizzle_upload =
+        !astc_decode && True(flags & ImageFlagBits::AcceleratedUpload);
+    vk::Image Image::*target = current_image;
+    if (astc_decode || unswizzle_upload) {
+        target = &Image::original_image;
+    }
+    auto& view = StorageViewsFor(target)[level];
    if (!view) {
        auto format_info =
            MaxwellToVK::SurfaceFormat(runtime->device, FormatType::Optimal, true, info.format);
-        if (WillUseAcceleratedAstcDecode(runtime->device, info)) {
+        if (astc_decode) {
            format_info.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32;
        }
-        view = MakeStorageView(runtime->device.GetLogical(), level, *(this->*current_image),
-                               format_info.format);
+        if (unswizzle_upload) {
+            const PixelFormat view_format =
+                UnswizzleViewFormat(VideoCore::Surface::BytesPerBlock(info.format));
+            format_info = MaxwellToVK::SurfaceFormat(runtime->device, FormatType::Optimal, false,
+                                                     view_format);
+        }
+        view = MakeStorageView(runtime->device.GetLogical(), level, *(this->*target),
+                               format_info.format, StorageViewType(info.type));
    }
    return *view;
 }
@@ -3141,6 +3224,14 @@ void TextureCacheRuntime::AccelerateImageUpload(
        return astc_decoder_pass->Assemble(image, map, swizzles);
    }

+    if (bl_unswizzle_2d_pass && image.info.type == ImageType::e2D) {
+        return bl_unswizzle_2d_pass->Unswizzle(image, map, swizzles);
+    }
+
+    if (pitch_unswizzle_pass && image.info.type == ImageType::Linear) {
+        return pitch_unswizzle_pass->Unswizzle(image, map, swizzles);
+    }
+
    if (!Settings::values.gpu_unswizzle_enabled.GetValue() || !bl3d_unswizzle_pass) {
        if (IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D) {
            ASSERT(false && "GPU unswizzle is disabled for BCn 3D texture");
@@ -159,6 +159,8 @@ public:
    std::optional<ASTCDecoderPass> astc_decoder_pass;

    std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
+    std::optional<BlockLinearUnswizzle2DPass> bl_unswizzle_2d_pass;
+    std::optional<PitchUnswizzlePass> pitch_unswizzle_pass;
    const Settings::ResolutionScalingInfo& resolution;
    std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;

@@ -370,6 +372,8 @@ private:

    bool NeedsScaleHelper() const;

+    std::vector<vk::ImageView>& StorageViewsFor(vk::Image Image::*image);
+
    Scheduler* scheduler{};
    TextureCacheRuntime* runtime{};

@@ -387,6 +391,7 @@ private:
    vk::Image Image::*current_image{};

    std::vector<vk::ImageView> storage_image_views;
+    std::vector<vk::ImageView> scaled_storage_image_views;
    VkImageAspectFlags aspect_mask = 0;
    bool initialized = false;

@@ -354,6 +354,7 @@ public:

 #define FN_MAX_LIMIT_LIST \
    FN_MAX_LIMIT_ELEM(ComputeSharedMemorySize) \
+    FN_MAX_LIMIT_ELEM(ComputeWorkGroupInvocations) \
    FN_MAX_LIMIT_ELEM(PerStageDescriptorSampledImages) \
    FN_MAX_LIMIT_ELEM(PerStageResources) \
    FN_MAX_LIMIT_ELEM(DescriptorSetSamplers) \