Merge pull request #6464 from ameerj/disable-astc

textures: Add a toggle for GPU Accelerated ASTC decoder

src/common/settings.cpp

@@ -55,6 +55,7 @@ void LogSettings() {
     log_setting("Renderer_UseAsynchronousGpuEmulation",
                 values.use_asynchronous_gpu_emulation.GetValue());
     log_setting("Renderer_UseNvdecEmulation", values.use_nvdec_emulation.GetValue());
+    log_setting("Renderer_AccelerateASTC", values.accelerate_astc.GetValue());
     log_setting("Renderer_UseVsync", values.use_vsync.GetValue());
     log_setting("Renderer_UseAssemblyShaders", values.use_assembly_shaders.GetValue());
     log_setting("Renderer_UseAsynchronousShaders", values.use_asynchronous_shaders.GetValue());
@@ -135,6 +136,7 @@ void RestoreGlobalState(bool is_powered_on) {
     values.gpu_accuracy.SetGlobal(true);
     values.use_asynchronous_gpu_emulation.SetGlobal(true);
     values.use_nvdec_emulation.SetGlobal(true);
+    values.accelerate_astc.SetGlobal(true);
     values.use_vsync.SetGlobal(true);
     values.use_assembly_shaders.SetGlobal(true);
     values.use_asynchronous_shaders.SetGlobal(true);

src/common/settings.h

@@ -147,6 +147,7 @@ struct Values {
     Setting<GPUAccuracy> gpu_accuracy;
     Setting<bool> use_asynchronous_gpu_emulation;
     Setting<bool> use_nvdec_emulation;
+    Setting<bool> accelerate_astc;
     Setting<bool> use_vsync;
     Setting<bool> use_assembly_shaders;
     Setting<bool> use_asynchronous_shaders;

src/core/telemetry_session.cpp

@@ -230,6 +230,7 @@ void TelemetrySession::AddInitialInfo(Loader::AppLoader& app_loader,
              Settings::values.use_asynchronous_gpu_emulation.GetValue());
     AddField(field_type, "Renderer_UseNvdecEmulation",
              Settings::values.use_nvdec_emulation.GetValue());
+    AddField(field_type, "Renderer_AccelerateASTC", Settings::values.accelerate_astc.GetValue());
     AddField(field_type, "Renderer_UseVsync", Settings::values.use_vsync.GetValue());
     AddField(field_type, "Renderer_UseAssemblyShaders",
              Settings::values.use_assembly_shaders.GetValue());

src/video_core/CMakeLists.txt

@@ -237,6 +237,7 @@ add_library(video_core STATIC
     texture_cache/util.cpp
     texture_cache/util.h
     textures/astc.h
+    textures/astc.cpp
     textures/decoders.cpp
     textures/decoders.h
     textures/texture.cpp

src/video_core/host_shaders/astc_decoder.comp

@@ -763,7 +763,7 @@ void ComputeEndpoints(out uvec4 ep1, out uvec4 ep2, uint color_endpoint_mode) {
     case 1: {
         READ_UINT_VALUES(2)
         uint L0 = (v[0] >> 2) | (v[1] & 0xC0);
-        uint L1 = max(L0 + (v[1] & 0x3F), 0xFFU);
+        uint L1 = min(L0 + (v[1] & 0x3F), 0xFFU);
         ep1 = uvec4(0xFF, L0, L0, L0);
         ep2 = uvec4(0xFF, L1, L1, L1);
         break;

src/video_core/renderer_opengl/gl_texture_cache.cpp

@@ -9,6 +9,8 @@
 
 #include <glad/glad.h>
 
+#include "common/settings.h"
+
 #include "video_core/renderer_opengl/gl_device.h"
 #include "video_core/renderer_opengl/gl_shader_manager.h"
 #include "video_core/renderer_opengl/gl_state_tracker.h"
@@ -307,7 +309,9 @@ void ApplySwizzle(GLuint handle, PixelFormat format, std::array<SwizzleSource, 4
 
 [[nodiscard]] bool CanBeAccelerated(const TextureCacheRuntime& runtime,
                                     const VideoCommon::ImageInfo& info) {
-    return !runtime.HasNativeASTC() && IsPixelFormatASTC(info.format);
+    if (IsPixelFormatASTC(info.format)) {
+        return !runtime.HasNativeASTC() && Settings::values.accelerate_astc.GetValue();
+    }
     // Disable other accelerated uploads for now as they don't implement swizzled uploads
     return false;
     switch (info.type) {

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -8,6 +8,7 @@
 #include <vector>
 
 #include "common/bit_cast.h"
+#include "common/settings.h"
 
 #include "video_core/engines/fermi_2d.h"
 #include "video_core/renderer_vulkan/blit_image.h"
@@ -828,7 +829,11 @@ Image::Image(TextureCacheRuntime& runtime, const ImageInfo& info_, GPUVAddr gpu_
         commit = runtime.memory_allocator.Commit(buffer, MemoryUsage::DeviceLocal);
     }
     if (IsPixelFormatASTC(info.format) && !runtime.device.IsOptimalAstcSupported()) {
+        if (Settings::values.accelerate_astc.GetValue()) {
             flags |= VideoCommon::ImageFlagBits::AcceleratedUpload;
+        } else {
+            flags |= VideoCommon::ImageFlagBits::Converted;
+        }
     }
     if (runtime.device.HasDebuggingToolAttached()) {
         if (image) {

src/video_core/texture_cache/util.cpp

@@ -47,6 +47,7 @@
 #include "video_core/texture_cache/formatter.h"
 #include "video_core/texture_cache/samples_helper.h"
 #include "video_core/texture_cache/util.h"
+#include "video_core/textures/astc.h"
 #include "video_core/textures/decoders.h"
 
 namespace VideoCommon {
@@ -884,8 +885,16 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
         ASSERT(copy.image_extent == mip_size);
         ASSERT(copy.buffer_row_length == Common::AlignUp(mip_size.width, tile_size.width));
         ASSERT(copy.buffer_image_height == Common::AlignUp(mip_size.height, tile_size.height));
+        if (IsPixelFormatASTC(info.format)) {
+            ASSERT(copy.image_extent.depth == 1);
+            Tegra::Texture::ASTC::Decompress(input.subspan(copy.buffer_offset),
+                                             copy.image_extent.width, copy.image_extent.height,
+                                             copy.image_subresource.num_layers, tile_size.width,
+                                             tile_size.height, output.subspan(output_offset));
+        } else {
             DecompressBC4(input.subspan(copy.buffer_offset), copy.image_extent,
                           output.subspan(output_offset));
+        }
         copy.buffer_offset = output_offset;
         copy.buffer_row_length = mip_size.width;
         copy.buffer_image_height = mip_size.height;

src/video_core/textures/astc.h

@@ -129,4 +129,7 @@ struct AstcBufferData {
     decltype(REPLICATE_BYTE_TO_16_TABLE) replicate_byte_to_16 = REPLICATE_BYTE_TO_16_TABLE;
 } constexpr ASTC_BUFFER_DATA;
 
+void Decompress(std::span<const uint8_t> data, uint32_t width, uint32_t height, uint32_t depth,
+                uint32_t block_width, uint32_t block_height, std::span<uint8_t> output);
+
 } // namespace Tegra::Texture::ASTC

src/yuzu/configuration/config.cpp

@@ -809,6 +809,7 @@ void Config::ReadRendererValues() {
                       QStringLiteral("use_asynchronous_gpu_emulation"), true);
     ReadSettingGlobal(Settings::values.use_nvdec_emulation, QStringLiteral("use_nvdec_emulation"),
                       true);
+    ReadSettingGlobal(Settings::values.accelerate_astc, QStringLiteral("accelerate_astc"), true);
     ReadSettingGlobal(Settings::values.use_vsync, QStringLiteral("use_vsync"), true);
     ReadSettingGlobal(Settings::values.use_assembly_shaders, QStringLiteral("use_assembly_shaders"),
                       false);
@@ -1392,6 +1393,7 @@ void Config::SaveRendererValues() {
                        Settings::values.use_asynchronous_gpu_emulation, true);
     WriteSettingGlobal(QStringLiteral("use_nvdec_emulation"), Settings::values.use_nvdec_emulation,
                        true);
+    WriteSettingGlobal(QStringLiteral("accelerate_astc"), Settings::values.accelerate_astc, true);
     WriteSettingGlobal(QStringLiteral("use_vsync"), Settings::values.use_vsync, true);
     WriteSettingGlobal(QStringLiteral("use_assembly_shaders"),
                        Settings::values.use_assembly_shaders, false);

src/yuzu/configuration/configure_graphics.cpp

@@ -70,10 +70,12 @@ void ConfigureGraphics::SetConfiguration() {
     ui->use_asynchronous_gpu_emulation->setEnabled(runtime_lock);
     ui->use_disk_shader_cache->setEnabled(runtime_lock);
     ui->use_nvdec_emulation->setEnabled(runtime_lock);
+    ui->accelerate_astc->setEnabled(runtime_lock);
     ui->use_disk_shader_cache->setChecked(Settings::values.use_disk_shader_cache.GetValue());
     ui->use_asynchronous_gpu_emulation->setChecked(
         Settings::values.use_asynchronous_gpu_emulation.GetValue());
     ui->use_nvdec_emulation->setChecked(Settings::values.use_nvdec_emulation.GetValue());
+    ui->accelerate_astc->setChecked(Settings::values.accelerate_astc.GetValue());
 
     if (Settings::IsConfiguringGlobal()) {
         ui->api->setCurrentIndex(static_cast<int>(Settings::values.renderer_backend.GetValue()));
@@ -118,6 +120,8 @@ void ConfigureGraphics::ApplyConfiguration() {
                                              use_asynchronous_gpu_emulation);
     ConfigurationShared::ApplyPerGameSetting(&Settings::values.use_nvdec_emulation,
                                              ui->use_nvdec_emulation, use_nvdec_emulation);
+    ConfigurationShared::ApplyPerGameSetting(&Settings::values.accelerate_astc, ui->accelerate_astc,
+                                             accelerate_astc);
 
     if (Settings::IsConfiguringGlobal()) {
         // Guard if during game and set to game-specific value
@@ -254,6 +258,7 @@ void ConfigureGraphics::SetupPerGameUI() {
         ui->use_asynchronous_gpu_emulation->setEnabled(
             Settings::values.use_asynchronous_gpu_emulation.UsingGlobal());
         ui->use_nvdec_emulation->setEnabled(Settings::values.use_nvdec_emulation.UsingGlobal());
+        ui->accelerate_astc->setEnabled(Settings::values.accelerate_astc.UsingGlobal());
         ui->use_disk_shader_cache->setEnabled(Settings::values.use_disk_shader_cache.UsingGlobal());
         ui->bg_button->setEnabled(Settings::values.bg_red.UsingGlobal());
 
@@ -269,6 +274,8 @@ void ConfigureGraphics::SetupPerGameUI() {
         ui->use_disk_shader_cache, Settings::values.use_disk_shader_cache, use_disk_shader_cache);
     ConfigurationShared::SetColoredTristate(
         ui->use_nvdec_emulation, Settings::values.use_nvdec_emulation, use_nvdec_emulation);
+    ConfigurationShared::SetColoredTristate(ui->accelerate_astc, Settings::values.accelerate_astc,
+                                            accelerate_astc);
     ConfigurationShared::SetColoredTristate(ui->use_asynchronous_gpu_emulation,
                                             Settings::values.use_asynchronous_gpu_emulation,
                                             use_asynchronous_gpu_emulation);

src/yuzu/configuration/configure_graphics.h

@@ -47,6 +47,7 @@ private:
     QColor bg_color;
 
     ConfigurationShared::CheckState use_nvdec_emulation;
+    ConfigurationShared::CheckState accelerate_astc;
     ConfigurationShared::CheckState use_disk_shader_cache;
     ConfigurationShared::CheckState use_asynchronous_gpu_emulation;
 

src/yuzu/configuration/configure_graphics.ui

@@ -104,6 +104,13 @@
           </property>
          </widget>
         </item>
+        <item>
+          <widget class="QCheckBox" name="accelerate_astc">
+            <property name="text">
+              <string>Accelerate ASTC texture decoding</string>
+            </property>
+          </widget>
+        </item>
         <item>
          <widget class="QWidget" name="fullscreen_mode_layout" native="true">
           <layout class="QHBoxLayout" name="horizontalLayout_1">

src/yuzu_cmd/config.cpp

@@ -447,8 +447,10 @@ void Config::ReadValues() {
         sdl2_config->GetBoolean("Renderer", "use_assembly_shaders", true));
     Settings::values.use_asynchronous_shaders.SetValue(
         sdl2_config->GetBoolean("Renderer", "use_asynchronous_shaders", false));
-    Settings::values.use_asynchronous_shaders.SetValue(
+    Settings::values.use_nvdec_emulation.SetValue(
-        sdl2_config->GetBoolean("Renderer", "use_asynchronous_shaders", false));
+        sdl2_config->GetBoolean("Renderer", "use_nvdec_emulation", true));
+    Settings::values.accelerate_astc.SetValue(
+        sdl2_config->GetBoolean("Renderer", "accelerate_astc", true));
     Settings::values.use_fast_gpu_time.SetValue(
         sdl2_config->GetBoolean("Renderer", "use_fast_gpu_time", true));
 

src/yuzu_cmd/default_ini.h

@@ -194,6 +194,14 @@ use_assembly_shaders =
 # 0 (default): Off, 1: On
 use_asynchronous_shaders =
 
+# Enable NVDEC emulation.
+# 0: Off, 1 (default): On
+use_nvdec_emulation =
+
+# Accelerate ASTC texture decoding.
+# 0: Off, 1 (default): On
+accelerate_astc =
+
 # Turns on the frame limiter, which will limit frames output to the target game speed
 # 0: Off, 1: On (default)
 use_frame_limit =