AQUI LLEGO TU LOBITO, MI LOBA.

This reverts commit 2ea449f71a.

src/android/app/build.gradle.kts

@@ -188,7 +188,7 @@ android {
         create("mainline") {
             dimension = "version"
             isDefault = true
-            minSdk = 30
+            minSdk = 33
 
             manifestPlaceholders += mapOf("appNameBase" to "Eden")
             resValue("string", "app_name_suffixed", "Eden")

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/model/StringSetting.kt

@@ -11,7 +11,6 @@ import org.yuzu.yuzu_emu.utils.NativeConfig
 enum class StringSetting(override val key: String) : AbstractStringSetting {
     DRIVER_PATH("driver_path"),
     DEVICE_NAME("device_name"),
-    LOG_FILTER("log_filter"),
     PROGRAM_ARGS("program_args"),
 
     WEB_TOKEN("eden_token"),

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/model/view/SettingsItem.kt

@@ -1032,13 +1032,6 @@ abstract class SettingsItem(
                     descriptionId = R.string.use_auto_stub_description
                 )
             )
-            put(
-                StringInputSetting(
-                    StringSetting.LOG_FILTER,
-                    titleId = R.string.log_filter,
-                    descriptionId = R.string.log_filter_description
-                )
-            )
             put(
                 SpinBoxSetting(
                     ShortSetting.DEBUG_KNOBS,

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/ui/SettingsFragmentPresenter.kt

@@ -1322,7 +1322,6 @@ class SettingsFragmentPresenter(
                 add(HeaderSetting(R.string.log))
 
                 add(BooleanSetting.DEBUG_FLUSH_BY_LINE.key)
-                add(StringSetting.LOG_FILTER.key)
             }
 
             add(HeaderSetting(R.string.general))

src/android/app/src/main/res/values/strings.xml

@@ -636,8 +636,6 @@
     <string name="log">Logging</string>
     <string name="flush_by_line">Flush debug logs by line</string>
     <string name="flush_by_line_description">Flushes debugging logs on each line written, making debugging easier in cases of crashing or freezing.</string>
-    <string name="log_filter">Log filter</string>
-    <string name="log_filter_description">Controls Eden\'s log categories. Example: *:Info Service.LM:Debug</string>
 
     <!-- GPU Logging strings -->
     <string name="gpu_logging_header">GPU Logging</string>

src/common/logging.cpp

@@ -224,7 +224,7 @@ struct ColorConsoleBackend final : public Backend {
             auto const df = GetDirectFormatArgs(entry);
             // more restrictive, because take for example this simple prelude:
             // [  50.872256] Config <Info> common/settings.cpp:142:LogSettings:
-            char buffer[128];
+            char buffer[256];
             auto result = fmt::format_to_n(buffer, sizeof(buffer) - 1, "\x1b{}[{:4d}.{:06d}] {} <{}> {}:{}:{}: ", color_str, df.time_seconds, df.time_fractional, df.class_name, df.level_name, entry.filename, entry.line_num, entry.function, entry.message);
             std::fwrite(buffer, 1, (std::min)(sizeof(buffer) - 1, result.size), stdout);
             std::fwrite(entry.message, 1, entry.message_len, stdout);
@@ -425,14 +425,14 @@ void SetColorConsoleBackendEnabled(bool enabled) {
 
 void FmtLogMessageImpl(Class log_class, Level log_level, const char* filename, unsigned int line_num, const char* function, fmt::string_view format, const fmt::format_args& args) {
     if (logging_instance && logging_instance->filter.CheckMessage(log_class, log_level)) {
+        auto const flush = ::Settings::values.log_flush_line.GetValue();
         char buffer[BUFSIZ];
         auto result = fmt::vformat_to_n(buffer, sizeof(buffer) - 1, format, args);
-        buffer[result.size] = '\0';
+        buffer[(std::min)(result.size, sizeof(buffer) - 1)] = '\0';
-        auto const flush = ::Settings::values.log_flush_line.GetValue();
         logging_instance->ForEachBackend([=](Backend& backend) {
             backend.Write(Entry{
                 .message = buffer,
-                .message_len = (std::min)(sizeof(buffer) - 1, result.size),
+                .message_len = (std::min)(result.size, sizeof(buffer) - 1),
                 .timestamp = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - logging_instance->time_origin),
                 .log_class = log_class,
                 .log_level = log_level,

src/common/settings.cpp

@@ -132,11 +132,9 @@ void LogSettings() {
             }
         }
     }
-
+    LOG_INFO(Config, "Eden Configuration:");
-    std::string settings_str{};
     for (auto const& e : settings_list)
-        settings_str += e;
+        LOG_INFO(Config, "{}", e);
-    LOG_INFO(Config, "Eden Configuration:\n{}", settings_str);
 #define LOG_PATH(NAME) \
     LOG_INFO(Config, #NAME ": {}", Common::FS::PathToUTF8String(Common::FS::GetEdenPath(Common::FS::EdenPath::NAME)))
     LOG_PATH(CacheDir);
@@ -371,7 +369,7 @@ void TranslateResolutionInfo(ResolutionSetup setup, ResolutionScalingInfo& info)
     }
     info.up_factor = static_cast<f32>(info.up_scale) / (1U << info.down_shift);
     info.down_factor = static_cast<f32>(1U << info.down_shift) / info.up_scale;
-    info.active = info.up_scale != 1 || info.down_shift != 0;
+    info.active = true;
 }
 
 void UpdateRescalingInfo() {

src/common/settings.h

@@ -904,7 +904,7 @@ struct Values {
                                            0,
                                            65535,
                                            "debug_knobs",
-                                           Category::System,
+                                           Category::Debugging,
                                            Specialization::Countable,
                                            true,
                                            true};

src/core/arm/arm_interface.cpp

@@ -3,158 +3,14 @@
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-#include <algorithm>
-#include <array>
-#include <cctype>
-#include <string>
-#include <string_view>
-#include <vector>
-
 #include "common/logging.h"
 #include "core/arm/arm_interface.h"
 #include "core/arm/debug.h"
 #include "core/core.h"
-#include "core/hle/kernel/k_memory_block.h"
 #include "core/hle/kernel/k_process.h"
-#include "core/hle/kernel/svc_types.h"
 
 namespace Core {
 
-namespace {
-
-constexpr std::size_t GuestStringProbeBytes = 0x100;
-constexpr std::size_t StackProbeWords = 96;
-constexpr std::size_t MaxGuestStringLogs = 16;
-constexpr std::size_t MaxBacktraceFrames = 64;
-constexpr std::size_t MinGuestStringLength = 4;
-
-std::string SanitizeGuestString(std::string_view text) {
-    std::string sanitized;
-    sanitized.reserve(text.size());
-
-    for (const char ch : text) {
-        switch (ch) {
-        case '\\':
-            sanitized += "\\\\";
-            break;
-        case '"':
-            sanitized += "\\\"";
-            break;
-        default:
-            sanitized += ch;
-            break;
-        }
-    }
-
-    return sanitized;
-}
-
-bool IsUsefulGuestString(std::string_view text) {
-    if (text.size() < MinGuestStringLength) {
-        return false;
-    }
-
-    std::size_t alpha_numeric_count{};
-    for (const char ch : text) {
-        const auto byte = static_cast<unsigned char>(ch);
-        if (std::isprint(byte) == 0) {
-            return false;
-        }
-
-        if (std::isalnum(byte) != 0) {
-            alpha_numeric_count++;
-        }
-    }
-
-    return alpha_numeric_count > 0;
-}
-
-bool QueryGuestMemoryInfo(Kernel::KProcess* process, u64 address,
-                          Kernel::Svc::MemoryInfo* out_info) {
-    if (address == 0) {
-        return false;
-    }
-
-    Kernel::KMemoryInfo mem_info{};
-    Kernel::Svc::PageInfo page_info{};
-    if (process->GetPageTable().QueryInfo(&mem_info, &page_info, address).IsFailure()) {
-        return false;
-    }
-
-    *out_info = mem_info.GetSvcMemoryInfo();
-    return true;
-}
-
-void LogGuestStringCandidate(Kernel::KProcess* process, u64 address, std::string_view label,
-                             std::vector<u64>& logged_strings) {
-    if (logged_strings.size() >= MaxGuestStringLogs) {
-        return;
-    }
-    if (std::find(logged_strings.begin(), logged_strings.end(), address) != logged_strings.end()) {
-        return;
-    }
-
-    Kernel::Svc::MemoryInfo mem_info{};
-    if (!QueryGuestMemoryInfo(process, address, &mem_info)) {
-        return;
-    }
-    if (mem_info.state == Kernel::Svc::MemoryState::Free ||
-        mem_info.permission == Kernel::Svc::MemoryPermission::None) {
-        return;
-    }
-
-    if (address < mem_info.base_address) {
-        return;
-    }
-
-    const u64 region_offset = address - mem_info.base_address;
-    if (region_offset >= mem_info.size) {
-        return;
-    }
-
-    const u64 available_bytes = mem_info.size - region_offset;
-    const auto probe_size =
-        static_cast<std::size_t>(std::min<u64>(GuestStringProbeBytes, available_bytes));
-    if (probe_size < MinGuestStringLength ||
-        !process->GetMemory().IsValidVirtualAddressRange(address, probe_size)) {
-        return;
-    }
-
-    const auto text = process->GetMemory().ReadCString(address, probe_size);
-    if (!IsUsefulGuestString(text)) {
-        return;
-    }
-
-    logged_strings.push_back(address);
-    LOG_ERROR(Core_ARM, "Guest backtrace string {:02}: {}={:016X} \"{}\"",
-              logged_strings.size() - 1, label, address, SanitizeGuestString(text));
-}
-
-void LogStackStringCandidates(Kernel::KProcess* process, u64 base, std::string_view label,
-                              std::vector<u64>& logged_strings) {
-    if (base == 0) {
-        return;
-    }
-
-    auto& memory = process->GetMemory();
-    for (std::size_t i = 0; i < StackProbeWords; i++) {
-        const u64 address = base + i * sizeof(u64);
-        if (!memory.IsValidVirtualAddressRange(address, sizeof(u64))) {
-            break;
-        }
-
-        u64 value{};
-        if (!memory.ReadBlock(address, &value, sizeof(value))) {
-            continue;
-        }
-
-        LogGuestStringCandidate(process, value, fmt::format("{}+{:03X}", label, i * sizeof(u64)),
-                                logged_strings);
-    }
-}
-
-} // namespace
-
 void ArmInterface::LogBacktrace(Kernel::KProcess* process) const {
     Kernel::Svc::ThreadContext ctx;
     this->GetContext(ctx);
@@ -170,45 +26,21 @@ void ArmInterface::LogBacktrace(Kernel::KProcess* process) const {
         ctx.r[28], ctx.fp, ctx.lr, ctx.sp,
     };
 
-    LOG_ERROR(Core_ARM,
+    std::string msg = fmt::format("Backtrace @ PC={:016X}\n", ctx.pc);
-              "Guest backtrace context: process=\"{}\" pid={} program_id={:016X} pc={:016X} "
+    for (size_t i = 0; i < 32; i += 4)
-              "lr={:016X} fp={:016X} sp={:016X} pstate={:08X}",
+        msg += fmt::format("R{:02}={:016X} R{:02}={:016X} R{:02}={:016X} R{:02}={:016X}\n",
-              process->GetName(), process->GetProcessId(), process->GetProgramId(), ctx.pc,
+            i + 0, xreg[i + 0], i + 1, xreg[i + 1],
-              ctx.lr, ctx.fp, ctx.sp, ctx.pstate);
+            i + 2, xreg[i + 2], i + 3, xreg[i + 3]);
-
+    for (size_t i = 0; i < 32; i += 2)
-    std::vector<u64> logged_strings;
+        msg += fmt::format("V{:02}={:016X}_{:016X} V{:02}={:016X}_{:016X}\n",
-    for (size_t i = 0; i < xreg.size(); i++) {
+            i + 0, ctx.v[i + 0][0], ctx.v[i + 0][1],
-        LogGuestStringCandidate(process, xreg[i], fmt::format("R{:02}", i), logged_strings);
+            i + 1, ctx.v[i + 1][0], ctx.v[i + 1][1]);
-    }
+    msg += fmt::format("PSTATE={:08X} FPCR={:08X} FPSR={:08X} TPIDR={:016X}\n", ctx.pstate, ctx.fpcr, ctx.fpsr, ctx.tpidr);
-    LogStackStringCandidates(process, ctx.sp, "SP", logged_strings);
+    msg += fmt::format("{:20}{:20}{:20}{:20}{}\n", "Module", "Address", "Original Address", "Offset", "Symbol");
-    if (ctx.fp != ctx.sp) {
-        LogStackStringCandidates(process, ctx.fp, "FP", logged_strings);
-    }
-    if (logged_strings.empty()) {
-        LOG_ERROR(Core_ARM, "Guest backtrace strings: none found in registers or stack");
-    }
-
     auto const backtrace = GetBacktraceFromContext(process, ctx);
-    for (size_t i = 0; i < std::min(backtrace.size(), MaxBacktraceFrames); i++) {
+    for (auto const& entry : backtrace)
-        const auto& entry = backtrace[i];
+        msg += fmt::format("{:20}{:016X}    {:016X}    {:016X}    {}\n", entry.module, entry.address, entry.original_address, entry.offset, entry.name);
-        if (entry.original_address == 0) {
+    LOG_ERROR(Core_ARM, "{}", msg);
-            break;
-        }
-
-        if (entry.name.empty()) {
-            LOG_ERROR(Core_ARM, "Guest backtrace frame {:03}: {}+0x{:X} pc={:016X} mapped={:016X}",
-                      i, entry.module, entry.offset, entry.original_address, entry.address);
-        } else {
-            LOG_ERROR(Core_ARM,
-                      "Guest backtrace frame {:03}: {}+0x{:X} pc={:016X} mapped={:016X} symbol={}",
-                      i, entry.module, entry.offset, entry.original_address, entry.address,
-                      entry.name);
-        }
-    }
-    if (backtrace.size() > MaxBacktraceFrames) {
-        LOG_ERROR(Core_ARM, "Guest backtrace truncated: logged={} total={}", MaxBacktraceFrames,
-                  backtrace.size());
-    }
 }
 
 const Kernel::DebugWatchpoint* ArmInterface::MatchingWatchpoint(

src/core/hle/service/filesystem/fsp/fs_i_storage.cpp

@@ -3,9 +3,6 @@
 
 // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
-#include <chrono>
-#include <thread>
-#include "common/settings.h"
 
 #include "core/file_sys/errors.h"
 #include "core/hle/service/cmif_serialization.h"
@@ -33,15 +30,6 @@ Result IStorage::Read(
 
     R_UNLESS(length >= 0, FileSys::ResultInvalidSize);
     R_UNLESS(offset >= 0, FileSys::ResultInvalidOffset);
-    static thread_local std::chrono::steady_clock::time_point last_read_tick{};
-    const auto now = std::chrono::steady_clock::now();
-    const auto period = Settings::values.debug_knobs.GetValue();
-    const auto ReadInterval = std::chrono::microseconds{period};
-    if (last_read_tick != std::chrono::steady_clock::time_point{} &&
-        now - last_read_tick < ReadInterval) {
-        std::this_thread::sleep_for(ReadInterval - (now - last_read_tick));
-    }
-    last_read_tick = std::chrono::steady_clock::now();
 
     // Read the data from the Storage backend
     backend->Read(out_bytes.data(), length, offset);

src/video_core/host_shaders/CMakeLists.txt

@@ -206,6 +206,40 @@ 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"
+    "block_linear_unswizzle_3d.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})

src/video_core/host_shaders/block_linear_unswizzle_2d.comp

@@ -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)

src/video_core/host_shaders/block_linear_unswizzle_3d.comp

@@ -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)

src/video_core/host_shaders/pitch_unswizzle.comp

@@ -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)

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -22,7 +22,13 @@
 #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/block_linear_unswizzle_3d_comp_spv.h"
+#include "video_core/host_shaders/block_linear_unswizzle_3d_nonarrow_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 +878,291 @@ void BlockLinearUnswizzle3DPass::UnswizzleChunk(
     });
 }
 
+namespace {
+
+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);
+    });
+}
+
+} // Anonymous namespace
+
+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);
+}
+
+BlockLinearUnswizzleImage3DPass::BlockLinearUnswizzleImage3DPass(
+    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(BlockLinearSwizzle3DParams)>,
+                  UnswizzleSpv(device_, BLOCK_LINEAR_UNSWIZZLE_3D_COMP_SPV,
+                               BLOCK_LINEAR_UNSWIZZLE_3D_NONARROW_COMP_SPV)),
+      scheduler{scheduler_}, compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzleImage3DPass::~BlockLinearUnswizzleImage3DPass() = default;
+
+void BlockLinearUnswizzleImage3DPass::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);
+
+    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, 16U);
+        const u32 num_dispatches_y = Common::DivCeil(swizzle.num_tiles.height, 8U);
+        const u32 num_dispatches_z = Common::DivCeil(swizzle.num_tiles.depth, 8U);
+
+        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 = MakeBlockLinearSwizzle3DParams(swizzle, image.info);
+        scheduler.Record([this, num_dispatches_x, num_dispatches_y, num_dispatches_z, 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_dispatches_z);
+        });
+    }
+    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

src/video_core/renderer_vulkan/vk_compute_pass.h

@@ -164,4 +164,49 @@ 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 BlockLinearUnswizzleImage3DPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzleImage3DPass(
+        const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+        ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzleImage3DPass();
+
+    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

src/video_core/renderer_vulkan/vk_scheduler.cpp

@@ -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{

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -160,6 +160,55 @@ 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::e3D &&
+        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 +297,18 @@ 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 +319,7 @@ 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,
@@ -658,18 +717,11 @@ void CopyBufferToImage(vk::CommandBuffer cmdbuf, VkBuffer src_buffer, VkImage im
             .subresourceRange = subresource_range,
     };
 
-    cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
+    cmdbuf.PipelineBarrier(vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, VK_PIPELINE_STAGE_TRANSFER_BIT, 0,
-                           VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT |
-                           VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, VK_PIPELINE_STAGE_TRANSFER_BIT, 0,
                            read_barrier);
     cmdbuf.CopyBufferToImage(src_buffer, image, VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, copies);
-    // TODO: Move this to another API
+    cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT, vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, 0,
-    cmdbuf.PipelineBarrier(
+                           nullptr, nullptr, write_barrier);
-            VK_PIPELINE_STAGE_TRANSFER_BIT,
-            VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
-            VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT |
-            VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
-            0, nullptr, nullptr, write_barrier);
 }
 
 [[nodiscard]] VkImageBlit MakeImageBlit(const Region2D& dst_region, const Region2D& src_region,
@@ -968,6 +1020,14 @@ 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);
+        bl_unswizzle_image_3d_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 +1962,12 @@ 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 +2377,39 @@ 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),
+        if (unswizzle_upload) {
-                               format_info.format);
+            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;
 }
@@ -2361,6 +2440,7 @@ bool Image::ScaleUp(bool ignore) {
                                  runtime->ViewFormats(info.format));
         ignore = false;
     }
+    ignore = true;
     current_image = &Image::scaled_image;
     if (ignore) {
         return true;
@@ -2389,6 +2469,7 @@ bool Image::ScaleDown(bool ignore) {
     }
     ASSERT(info.type != ImageType::Linear);
     flags &= ~ImageFlagBits::Rescaled;
+    ignore = true;
     current_image = &Image::original_image;
     if (ignore) {
         return true;
@@ -3141,6 +3222,19 @@ 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 (bl_unswizzle_image_3d_pass && image.info.type == ImageType::e3D &&
+        !IsPixelFormatBCn(image.info.format)) {
+        return bl_unswizzle_image_3d_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");

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -159,6 +159,9 @@ public:
     std::optional<ASTCDecoderPass> astc_decoder_pass;
 
     std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
+    std::optional<BlockLinearUnswizzle2DPass> bl_unswizzle_2d_pass;
+    std::optional<BlockLinearUnswizzleImage3DPass> bl_unswizzle_image_3d_pass;
+    std::optional<PitchUnswizzlePass> pitch_unswizzle_pass;
     const Settings::ResolutionScalingInfo& resolution;
     std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;
 
@@ -370,6 +373,8 @@ private:
 
     bool NeedsScaleHelper() const;
 
+    std::vector<vk::ImageView>& StorageViewsFor(vk::Image Image::*image);
+
     Scheduler* scheduler{};
     TextureCacheRuntime* runtime{};
 
@@ -387,6 +392,7 @@ 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;
 

src/video_core/texture_cache/accelerated_swizzle.h

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -23,8 +26,8 @@ struct BlockLinearSwizzle2DParams {
 };
 
 struct BlockLinearSwizzle3DParams {
-    std::array<u32, 3> origin;
+    alignas(16) std::array<u32, 3> origin;
-    std::array<s32, 3> destination;
+    alignas(16) std::array<s32, 3> destination;
     u32 bytes_per_block_log2;
     u32 slice_size;
     u32 block_size;

src/video_core/texture_cache/texture_cache.h

@@ -279,11 +279,11 @@ void TextureCache<P>::CheckFeedbackLoop(std::span<const ImageViewInOut> views) {
 
             const ImageId view_image_id = slot_image_views[view.id].image_id;
             {
-                bool is_continue = false;
+                bool is_feedback = false;
                 for (size_t i = 0; i < 8; ++i)
-                    is_continue |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
+                    is_feedback |= (rt_active_mask & (1u << i)) && view_image_id == rt_image_id[i];
-                if (is_continue)
+                if (is_feedback)
-                    continue;
+                    return true;
             }
             if (depth_active && view_image_id == rt_depth_image_id) {
                 return true;

src/video_core/vulkan_common/vulkan_device.h

@@ -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) \