refactor(gpu): Relocate effects to src/effects and streamline includes

This refactoring improves the project's structure by decoupling visual effects from the core GPU module. All effect implementations have been moved from  to a new top-level  directory. Shared utilities like , , and  have been consolidated into the parent  directory.

- **Motivation**: To create a clearer separation of concerns, making the codebase easier to navigate and maintain. This move treats effects as a distinct layer that depends on the core GPU module, rather than being embedded within it.

- **Changes**:
  - Created new  directory.
  - Moved all effect source files (, ) to .
  - Moved shared helpers (, , ) to .
  - Updated  and  to reflect the new file locations for all build targets.
  - Corrected all  directives across the entire codebase (, , ) to point to the new paths.
  - Updated all markdown documentation ( files) to ensure file paths and architectural descriptions are accurate.
  - Fixed several compiler errors related to incorrect enum casting () that were exposed during cross-compilation for Windows.

- **Verification**:
  - The entire project builds successfully for both native and Windows cross-compilation targets.
  - All 34 tests pass (Usage

  ctest [options]).
  - The --- Running Native Build & Tests ---
Configuring with all options enabled (tests + tools)...
--
-- Build Configuration:
--   DEMO_SIZE_OPT:           ON
--   DEMO_STRIP_ALL:          ON
--   DEMO_FINAL_STRIP:        OFF
--   DEMO_STRIP_EXTERNAL_LIBS: OFF
--   DEMO_BUILD_TESTS:        ON
--   DEMO_BUILD_TOOLS:        ON
--   DEMO_ENABLE_COVERAGE:    OFF
--   DEMO_ENABLE_DEBUG_LOGS:  OFF
--   DEMO_HEADLESS:           OFF
--   DEMO_WORKSPACE:          main
--
-- Loaded workspace: Main Demo
--   Timeline: timeline.seq
--   Music: pop_punk_drums.track
--   Assets: assets.txt
-- Using workspace: main
-- Configuring done (0.0s)
-- Generating done (0.1s)
-- Build files have been written to: /Users/skal/demo/build
Building all targets (demo, tests, and tools)...
[  0%] Built target validate_uniforms_script
[  1%] Built target procedural
[  2%] Validating uniform buffer sizes and alignments...
[  3%] Built target tracker_compiler
[  4%] Built target test_3d
[  4%] Built target test_maths
[  4%] Built target seq_compiler
[  4%] Built target tracker_compiler_host
[  5%] Built target asset_packer
[  5%] Built target test_procedural
[  6%] Compiling demo sequence from workspace main...
[  6%] Built target generate_tracker_music
[  6%] Built target generate_test_demo_music
[  6%] Compiling test_demo sequence...
Using BPM: 90
Successfully generated timeline with 16 sequences.
Using BPM: 120
Demo end time: 16.000000s
Successfully generated timeline with 1 sequences.
[  6%] Built target generate_test_demo_timeline
[  6%] Built target generate_timeline
Validation Warning for 'CommonPostProcessUniforms': Matching WGSL struct not found.
Validation OK for 'FadeParams': Size 16 matches C++ expected size.
Validation OK for 'ThemeModulationParams': Size 16 matches C++ expected size.
Validation OK for 'GaussianBlurParams': Size 8 matches C++ expected size.
Validation OK for 'DistortParams': Size 8 matches C++ expected size.
Validation OK for 'CircleMaskParams': Size 16 matches C++ expected size.
[  6%] Built target generate_test_assets
[  7%] Built target generate_demo_assets
[  7%] Built target validate_uniforms
[  8%] Built target util
[ 10%] Built target test_assets
[ 11%] Built target test_shader_assets
[ 12%] Built target test_file_watcher
[ 15%] Built target 3d
[ 21%] Built target test_platform
[ 22%] Built target audio
[ 23%] Built target test_window
[ 26%] Built target test_fft
[ 27%] Built target test_synth
[ 27%] Built target test_spectral_brush
[ 27%] Built target test_physics
[ 28%] Built target test_dct
[ 31%] Building CXX object CMakeFiles/gpu.dir/src/gpu/effect.cc.o
[ 30%] Built target test_mock_backend
[ 32%] Built target test_scene_loader
[ 33%] Built target test_audio_backend
[ 34%] Built target test_audio_gen
[ 36%] Built target test_silent_backend
[ 39%] Built target test_jittered_audio
[ 39%] Building CXX object CMakeFiles/gpu.dir/src/effects/heptagon_effect.cc.o
[ 42%] Built target test_wav_dump
[ 44%] Built target test_tracker_timing
[ 44%] Building CXX object CMakeFiles/gpu.dir/src/effects/particles_effect.cc.o
[ 45%] Building CXX object CMakeFiles/gpu.dir/src/effects/passthrough_effect.cc.o
[ 47%] Built target test_variable_tempo
[ 50%] Built target test_audio_engine
[ 52%] Built target test_tracker
[ 52%] Building CXX object CMakeFiles/gpu.dir/src/effects/moving_ellipse_effect.cc.o
[ 52%] Building CXX object CMakeFiles/gpu.dir/src/effects/particle_spray_effect.cc.o
[ 52%] Building CXX object CMakeFiles/gpu.dir/src/effects/gaussian_blur_effect.cc.o
[ 54%] Built target test_spectool
[ 55%] Building CXX object CMakeFiles/gpu.dir/src/effects/solarize_effect.cc.o
[ 55%] Building CXX object CMakeFiles/gpu.dir/src/effects/scene1_effect.cc.o
[ 55%] Building CXX object CMakeFiles/gpu.dir/src/effects/chroma_aberration_effect.cc.o
[ 55%] Building CXX object CMakeFiles/gpu.dir/src/gpu/shaders.cc.o
[ 57%] Building CXX object CMakeFiles/gpu.dir/src/effects/vignette_effect.cc.o
[ 57%] Building CXX object CMakeFiles/gpu.dir/src/gpu/post_process_helper.cc.o
[ 57%] Linking CXX static library libgpu.a
[ 60%] Built target gpu
[ 60%] Linking CXX executable test_uniform_helper
[ 60%] Linking CXX executable test_shader_composer
[ 60%] Building CXX object CMakeFiles/test_sequence.dir/src/tests/assets/test_sequence.cc.o
[ 61%] Linking CXX executable test_noise_functions
[ 62%] Linking CXX executable test_shader_compilation
[ 62%] Building CXX object CMakeFiles/test_demo.dir/src/app/test_demo.cc.o
[ 62%] Building CXX object CMakeFiles/demo64k.dir/src/app/main.cc.o
[ 62%] Building CXX object CMakeFiles/test_3d_render.dir/src/generated/timeline.cc.o
[ 63%] Built target test_uniform_helper
[ 64%] Built target test_shader_composer
[ 64%] Building CXX object CMakeFiles/test_3d_physics.dir/src/generated/timeline.cc.o
[ 65%] Built target test_noise_functions
[ 66%] Built target test_shader_compilation
[ 67%] Building CXX object CMakeFiles/test_mesh.dir/src/generated/timeline.cc.o
[ 67%] Building CXX object CMakeFiles/test_effect_base.dir/src/tests/gpu/test_effect_base.cc.o
[ 67%] Building CXX object CMakeFiles/test_demo_effects.dir/src/tests/gpu/test_demo_effects.cc.o
[ 67%] Building CXX object CMakeFiles/test_sequence.dir/src/generated/timeline.cc.o
[ 68%] Building CXX object CMakeFiles/test_demo.dir/src/generated/test_demo_timeline.cc.o
[ 68%] Building CXX object CMakeFiles/demo64k.dir/src/generated/timeline.cc.o
[ 68%] Linking CXX executable test_3d_render
[ 68%] Building CXX object CMakeFiles/test_effect_base.dir/src/generated/timeline.cc.o
[ 68%] Linking CXX executable test_3d_physics
[ 68%] Linking CXX executable test_mesh
[ 71%] Built target test_3d_render
[ 71%] Building CXX object CMakeFiles/test_post_process_helper.dir/src/tests/gpu/test_post_process_helper.cc.o
[ 72%] Building CXX object CMakeFiles/test_demo_effects.dir/src/generated/timeline.cc.o
[ 72%] Linking CXX executable test_demo
[ 75%] Built target test_3d_physics
[ 77%] Built target test_mesh
[ 77%] Linking CXX executable test_texture_manager
[ 78%] Linking CXX executable test_sequence
[ 78%] Linking CXX executable test_gpu_procedural
[ 80%] Built target test_demo
[ 81%] Linking CXX executable test_gpu_composite
[ 81%] Linking CXX executable demo64k
[ 83%] Built target test_sequence
[ 85%] Built target test_texture_manager
[ 86%] Built target test_gpu_procedural
[ 86%] Linking CXX executable test_post_process_helper
[ 86%] Linking CXX executable test_effect_base
[ 87%] Built target test_gpu_composite
[ 90%] Built target demo64k
[ 92%] Built target test_post_process_helper
[ 96%] Built target test_effect_base
[ 96%] Linking CXX executable test_demo_effects
[100%] Built target test_demo_effects
Running test suite...
Test project /Users/skal/demo/build
      Start  1: HammingWindowTest
 1/34 Test  #1: HammingWindowTest ................   Passed    0.00 sec
      Start  2: MathUtilsTest
 2/34 Test  #2: MathUtilsTest ....................   Passed    0.00 sec
      Start  3: FileWatcherTest
 3/34 Test  #3: FileWatcherTest ..................   Passed    0.00 sec
      Start  4: SynthEngineTest
 4/34 Test  #4: SynthEngineTest ..................   Passed    0.00 sec
      Start  5: DctTest
 5/34 Test  #5: DctTest ..........................   Passed    0.00 sec
      Start  6: FftTest
 6/34 Test  #6: FftTest ..........................   Passed    0.01 sec
      Start  7: SpectralBrushTest
 7/34 Test  #7: SpectralBrushTest ................   Passed    0.01 sec
      Start  8: AudioGenTest
 8/34 Test  #8: AudioGenTest .....................   Passed    0.00 sec
      Start  9: AudioBackendTest
 9/34 Test  #9: AudioBackendTest .................   Passed    0.00 sec
      Start 10: SilentBackendTest
10/34 Test #10: SilentBackendTest ................   Passed    0.00 sec
      Start 11: MockAudioBackendTest
11/34 Test #11: MockAudioBackendTest .............   Passed    0.00 sec
      Start 12: WavDumpBackendTest
12/34 Test #12: WavDumpBackendTest ...............   Passed    0.00 sec
      Start 13: JitteredAudioBackendTest
13/34 Test #13: JitteredAudioBackendTest .........   Passed    0.00 sec
      Start 14: TrackerTimingTest
14/34 Test #14: TrackerTimingTest ................   Passed    0.00 sec
      Start 15: VariableTempoTest
15/34 Test #15: VariableTempoTest ................   Passed    0.00 sec
      Start 16: TrackerSystemTest
16/34 Test #16: TrackerSystemTest ................   Passed    0.01 sec
      Start 17: AudioEngineTest
17/34 Test #17: AudioEngineTest ..................   Passed    0.00 sec
      Start 18: ShaderAssetValidation
18/34 Test #18: ShaderAssetValidation ............   Passed    0.00 sec
      Start 19: ShaderCompilationTest
19/34 Test #19: ShaderCompilationTest ............   Passed    0.02 sec
      Start 20: NoiseFunctionsTest
20/34 Test #20: NoiseFunctionsTest ...............   Passed    0.01 sec
      Start 21: UniformHelperTest
21/34 Test #21: UniformHelperTest ................   Passed    0.00 sec
      Start 22: AssetManagerTest
22/34 Test #22: AssetManagerTest .................   Passed    0.01 sec
      Start 23: SequenceSystemTest
23/34 Test #23: SequenceSystemTest ...............   Passed    0.01 sec
      Start 24: ProceduralGenTest
24/34 Test #24: ProceduralGenTest ................   Passed    0.01 sec
      Start 25: PhysicsTest
25/34 Test #25: PhysicsTest ......................   Passed    0.01 sec
      Start 26: ThreeDSystemTest
26/34 Test #26: ThreeDSystemTest .................   Passed    0.00 sec
      Start 27: ShaderComposerTest
27/34 Test #27: ShaderComposerTest ...............   Passed    0.01 sec
      Start 28: SceneLoaderTest
28/34 Test #28: SceneLoaderTest ..................   Passed    0.01 sec
      Start 29: EffectBaseTest
29/34 Test #29: EffectBaseTest ...................   Passed    0.04 sec
      Start 30: DemoEffectsTest
30/34 Test #30: DemoEffectsTest ..................   Passed    0.03 sec
      Start 31: PostProcessHelperTest
31/34 Test #31: PostProcessHelperTest ............   Passed    0.02 sec
      Start 32: TextureManagerTest
32/34 Test #32: TextureManagerTest ...............   Passed    0.02 sec
      Start 33: GpuProceduralTest
33/34 Test #33: GpuProceduralTest ................   Passed    0.18 sec
      Start 34: GpuCompositeTest
34/34 Test #34: GpuCompositeTest .................   Passed    0.20 sec

100% tests passed, 0 tests failed out of 34

Label Time Summary:
3d        =   0.01 sec*proc (3 tests)
assets    =   0.02 sec*proc (2 tests)
audio     =   0.07 sec*proc (15 tests)
gpu       =   0.54 sec*proc (11 tests)
util      =   0.01 sec*proc (3 tests)

Total Test time (real) =   0.67 sec
Verifying tools compile...
[  9%] Built target procedural
[ 18%] Built target tracker_compiler_host
[ 18%] Built target tracker_compiler
[ 18%] Built target generate_tracker_music
[ 18%] Built target asset_packer
[ 27%] Built target generate_demo_assets
[ 27%] Built target generate_test_assets
[ 36%] Built target util
[ 81%] Built target audio
[100%] Built target test_spectool

--- Running Windows Cross-Compilation Build ---
Building native tools...
--
-- Build Configuration:
--   DEMO_SIZE_OPT:           OFF
--   DEMO_STRIP_ALL:          OFF
--   DEMO_FINAL_STRIP:        OFF
--   DEMO_STRIP_EXTERNAL_LIBS: OFF
--   DEMO_BUILD_TESTS:        OFF
--   DEMO_BUILD_TOOLS:        OFF
--   DEMO_ENABLE_COVERAGE:    OFF
--   DEMO_ENABLE_DEBUG_LOGS:  OFF
--   DEMO_HEADLESS:           OFF
--   DEMO_WORKSPACE:          main
--
-- Loaded workspace: Main Demo
--   Timeline: timeline.seq
--   Music: pop_punk_drums.track
--   Assets: assets.txt
-- Using workspace: main
-- Configuring done (0.0s)
-- Generating done (0.0s)
-- Build files have been written to: /Users/skal/demo/build_native
[ 50%] Built target procedural
[100%] Built target asset_packer
[100%] Built target seq_compiler
[100%] Built target tracker_compiler_host
Cross-compiling for Windows...
--
-- Build Configuration:
--   DEMO_SIZE_OPT:           ON
--   DEMO_STRIP_ALL:          ON
--   DEMO_FINAL_STRIP:        OFF
--   DEMO_STRIP_EXTERNAL_LIBS: OFF
--   DEMO_BUILD_TESTS:        OFF
--   DEMO_BUILD_TOOLS:        OFF
--   DEMO_ENABLE_COVERAGE:    OFF
--   DEMO_ENABLE_DEBUG_LOGS:  OFF
--   DEMO_HEADLESS:           OFF
--   DEMO_WORKSPACE:          main
--
-- Loaded workspace: Main Demo
--   Timeline: timeline.seq
--   Music: pop_punk_drums.track
--   Assets: assets.txt
-- Using workspace: main
-- Configuring done (0.0s)
-- Generating done (0.0s)
-- Build files have been written to: /Users/skal/demo/build_win
[  2%] Built target validate_uniforms_script
[  2%] Built target generate_timeline
[  4%] Built target generate_test_demo_timeline
[  4%] Built target generate_demo_assets
[  4%] Built target generate_test_assets
[  6%] Built target procedural
[  9%] Built target tracker_compiler_host
[ 10%] Validating uniform buffer sizes and alignments...
[ 11%] Built target generate_tracker_music
[ 13%] Built target generate_test_demo_music
[ 16%] Built target util
[ 28%] Built target 3d
[ 45%] Built target audio
[ 49%] Building CXX object CMakeFiles/gpu.dir/src/effects/heptagon_effect.cc.obj
[ 52%] Building CXX object CMakeFiles/gpu.dir/src/effects/gaussian_blur_effect.cc.obj
[ 54%] Building CXX object CMakeFiles/gpu.dir/src/effects/particles_effect.cc.obj
[ 54%] Building CXX object CMakeFiles/gpu.dir/src/effects/moving_ellipse_effect.cc.obj
[ 54%] Building CXX object CMakeFiles/gpu.dir/src/gpu/effect.cc.obj
[ 54%] Building CXX object CMakeFiles/gpu.dir/src/effects/passthrough_effect.cc.obj
[ 54%] Building CXX object CMakeFiles/gpu.dir/src/effects/particle_spray_effect.cc.obj
Validation Warning for 'CommonPostProcessUniforms': Matching WGSL struct not found.
Validation OK for 'FadeParams': Size 16 matches C++ expected size.
Validation OK for 'ThemeModulationParams': Size 16 matches C++ expected size.
Validation OK for 'GaussianBlurParams': Size 8 matches C++ expected size.
Validation OK for 'DistortParams': Size 8 matches C++ expected size.
Validation OK for 'CircleMaskParams': Size 16 matches C++ expected size.
[ 54%] Built target validate_uniforms
[ 55%] Building CXX object CMakeFiles/gpu.dir/src/effects/solarize_effect.cc.obj
[ 57%] Building CXX object CMakeFiles/gpu.dir/src/effects/scene1_effect.cc.obj
[ 57%] Building CXX object CMakeFiles/gpu.dir/src/effects/chroma_aberration_effect.cc.obj
[ 58%] Building CXX object CMakeFiles/gpu.dir/src/effects/vignette_effect.cc.obj
[ 59%] Building CXX object CMakeFiles/gpu.dir/src/gpu/post_process_helper.cc.obj
[ 60%] Building CXX object CMakeFiles/gpu.dir/src/gpu/shaders.cc.obj
[ 62%] Linking CXX static library libgpu.a
[ 77%] Built target gpu
[ 79%] Building CXX object CMakeFiles/demo64k.dir/src/app/main.cc.obj
[ 79%] Building CXX object CMakeFiles/test_demo.dir/src/app/test_demo.cc.obj
[ 80%] Building CXX object CMakeFiles/demo64k.dir/src/generated/timeline.cc.obj
[ 81%] Building CXX object CMakeFiles/test_demo.dir/src/generated/test_demo_timeline.cc.obj
[ 82%] Linking CXX executable test_demo.exe
[ 90%] Built target test_demo
[ 91%] Linking CXX executable demo64k.exe
[100%] Built target demo64k
Copying MinGW DLLs...
Crunching build_win/demo64k.exe...
                       Ultimate Packer for eXecutables
                          Copyright (C) 1996 - 2026
UPX 5.1.0       Markus Oberhumer, Laszlo Molnar & John Reiser    Jan 7th 2026

        File size         Ratio      Format      Name
   --------------------   ------   -----------   -----------
   7036416 ->   4680704   66.52%    win64/pe     demo64k_packed.exe

Packed 1 file.
------------------------------------------------
Size Report:
-rwxr-xr-x  1 skal  89939   6.7M Feb 14 14:55 build_win/demo64k.exe
-rwxr-xr-x  1 skal  89939   6.7M Feb 14 14:55 build_win/demo64k_stripped.exe
-rwxr-xr-x  1 skal  89939   4.5M Feb 14 14:55 build_win/demo64k_packed.exe
------------------------------------------------
Top 20 Largest Symbols (from unstripped):
------------------------------------------------
Build complete. Output: build_win/demo64k.exe

All checks passed successfully. script completes without errors.

This change streamlines the project's architecture without altering any functionality.

1 files changed, 219 insertions, 0 deletions

diff --git a/src/effects/circle_mask_effect.cc b/src/effects/circle_mask_effect.cc
new file mode 100644
index 0000000..63c8f68
--- /dev/null
+++ b/src/effects/circle_mask_effect.cc
@@ -0,0 +1,219 @@
+// This file is part of the 64k demo project.
+// It implements CircleMaskEffect for auxiliary texture masking demonstration.
+// Generates circular mask and renders green background outside circle.
+
+#include "effects/circle_mask_effect.h"
+#include "generated/assets.h"
+#include "gpu/bind_group_builder.h"
+#include "gpu/shader_composer.h"
+
+CircleMaskEffect::CircleMaskEffect(const GpuContext& ctx, float radius)
+    : Effect(ctx), radius_(radius) {
+}
+
+CircleMaskEffect::~CircleMaskEffect() {
+  if (mask_sampler_)
+    wgpuSamplerRelease(mask_sampler_);
+  if (render_bind_group_)
+    wgpuBindGroupRelease(render_bind_group_);
+  if (render_pipeline_)
+    wgpuRenderPipelineRelease(render_pipeline_);
+  if (compute_bind_group_)
+    wgpuBindGroupRelease(compute_bind_group_);
+  if (compute_pipeline_)
+    wgpuRenderPipelineRelease(compute_pipeline_);
+}
+
+void CircleMaskEffect::init(MainSequence* demo) {
+  demo_ = demo;
+
+  // Register auxiliary texture (width_/height_ set by resize() before init())
+  demo_->register_auxiliary_texture("circle_mask", width_, height_);
+
+  compute_params_.init(ctx_.device);
+
+  // Initialize uniforms BEFORE bind group creation
+  uniforms_.update(ctx_.queue, get_common_uniforms());
+
+  WGPUSamplerDescriptor sampler_desc = {};
+  sampler_desc.addressModeU = WGPUAddressMode_ClampToEdge;
+  sampler_desc.addressModeV = WGPUAddressMode_ClampToEdge;
+  sampler_desc.magFilter = WGPUFilterMode_Linear;
+  sampler_desc.minFilter = WGPUFilterMode_Linear;
+  sampler_desc.mipmapFilter = WGPUMipmapFilterMode_Linear;
+  sampler_desc.maxAnisotropy = 1;
+  mask_sampler_ = wgpuDeviceCreateSampler(ctx_.device, &sampler_desc);
+
+  size_t compute_size, render_size;
+  const char* compute_shader = (const char*)GetAsset(
+      AssetId::ASSET_CIRCLE_MASK_COMPUTE_SHADER, &compute_size);
+  const char* render_shader = (const char*)GetAsset(
+      AssetId::ASSET_CIRCLE_MASK_RENDER_SHADER, &render_size);
+
+  // Compose shaders to resolve #include directives
+  std::string composed_compute = ShaderComposer::Get().Compose({}, compute_shader);
+
+  WGPUShaderSourceWGSL compute_wgsl = {};
+  compute_wgsl.chain.sType = WGPUSType_ShaderSourceWGSL;
+  compute_wgsl.code = str_view(composed_compute.c_str());
+
+  WGPUShaderModuleDescriptor compute_desc = {};
+  compute_desc.nextInChain = &compute_wgsl.chain;
+  WGPUShaderModule compute_module =
+      wgpuDeviceCreateShaderModule(ctx_.device, &compute_desc);
+
+  const WGPUColorTargetState compute_target = {
+      .format = ctx_.format, // Match auxiliary texture format
+      .writeMask = WGPUColorWriteMask_All,
+  };
+  WGPUFragmentState compute_frag = {};
+  compute_frag.module = compute_module;
+  compute_frag.entryPoint = str_view("fs_main");
+  compute_frag.targetCount = 1;
+  compute_frag.targets = &compute_target;
+  WGPURenderPipelineDescriptor compute_pipeline_desc = {};
+  compute_pipeline_desc.label = label_view("CircleMaskEffect_compute");
+  compute_pipeline_desc.vertex.module = compute_module;
+  compute_pipeline_desc.vertex.entryPoint = str_view("vs_main");
+  compute_pipeline_desc.primitive.topology = WGPUPrimitiveTopology_TriangleList;
+  compute_pipeline_desc.primitive.cullMode = WGPUCullMode_None;
+  compute_pipeline_desc.multisample.count = 1;
+  compute_pipeline_desc.multisample.mask = 0xFFFFFFFF;
+  compute_pipeline_desc.fragment = &compute_frag;
+  compute_pipeline_ =
+      wgpuDeviceCreateRenderPipeline(ctx_.device, &compute_pipeline_desc);
+  wgpuShaderModuleRelease(compute_module);
+
+  WGPUBindGroupLayout compute_layout =
+      wgpuRenderPipelineGetBindGroupLayout(compute_pipeline_, 0);
+  compute_bind_group_ =
+      BindGroupBuilder()
+          .buffer(0, uniforms_.get().buffer, sizeof(CommonPostProcessUniforms))
+          .buffer(1, compute_params_.get().buffer, sizeof(CircleMaskParams))
+          .build(ctx_.device, compute_layout);
+  wgpuBindGroupLayoutRelease(compute_layout);
+
+  std::string composed_render = ShaderComposer::Get().Compose({}, render_shader);
+
+  WGPUShaderSourceWGSL render_wgsl = {};
+  render_wgsl.chain.sType = WGPUSType_ShaderSourceWGSL;
+  render_wgsl.code = str_view(composed_render.c_str());
+
+  WGPUShaderModuleDescriptor render_desc = {};
+  render_desc.nextInChain = &render_wgsl.chain;
+  WGPUShaderModule render_module =
+      wgpuDeviceCreateShaderModule(ctx_.device, &render_desc);
+
+  const WGPUColorTargetState render_target = {
+      .format = ctx_.format,
+      .writeMask = WGPUColorWriteMask_All,
+  };
+  WGPUFragmentState render_frag = {};
+  render_frag.module = render_module;
+  render_frag.entryPoint = str_view("fs_main");
+  render_frag.targetCount = 1;
+  render_frag.targets = &render_target;
+  const WGPUDepthStencilState depth_stencil = {
+      .format = WGPUTextureFormat_Depth24Plus,
+      .depthWriteEnabled = WGPUOptionalBool_False, // Don't write depth
+      .depthCompare = WGPUCompareFunction_Always,  // Always pass
+  };
+
+  WGPURenderPipelineDescriptor render_pipeline_desc = {};
+  render_pipeline_desc.label = label_view("CircleMaskEffect_render");
+  render_pipeline_desc.vertex.module = render_module;
+  render_pipeline_desc.vertex.entryPoint = str_view("vs_main");
+  render_pipeline_desc.primitive.topology = WGPUPrimitiveTopology_TriangleList;
+  render_pipeline_desc.primitive.cullMode = WGPUCullMode_None;
+  render_pipeline_desc.depthStencil = &depth_stencil;
+  render_pipeline_desc.multisample.count = 1;
+  render_pipeline_desc.multisample.mask = 0xFFFFFFFF;
+  render_pipeline_desc.fragment = &render_frag;
+  render_pipeline_ =
+      wgpuDeviceCreateRenderPipeline(ctx_.device, &render_pipeline_desc);
+  wgpuShaderModuleRelease(render_module);
+
+  WGPUTextureView mask_view = demo_->get_auxiliary_view("circle_mask");
+  const WGPUBindGroupEntry render_entries[] = {
+      {.binding = 0, .textureView = mask_view},
+      {.binding = 1, .sampler = mask_sampler_},
+      {.binding = 2,
+       .buffer = uniforms_.get().buffer,
+       .size = sizeof(CommonPostProcessUniforms)},
+  };
+  const WGPUBindGroupDescriptor render_bg_desc = {
+      .layout = wgpuRenderPipelineGetBindGroupLayout(render_pipeline_, 0),
+      .entryCount = 3,
+      .entries = render_entries,
+  };
+  render_bind_group_ = wgpuDeviceCreateBindGroup(ctx_.device, &render_bg_desc);
+}
+
+void CircleMaskEffect::resize(int width, int height) {
+  if (width == width_ && height == height_)
+    return;
+
+  Effect::resize(width, height);
+
+  if (!demo_)
+    return;
+
+  // Resize auxiliary texture
+  demo_->resize_auxiliary_texture("circle_mask", width, height);
+
+  // Recreate render bind group with new texture view
+  if (render_bind_group_)
+    wgpuBindGroupRelease(render_bind_group_);
+
+  WGPUTextureView mask_view = demo_->get_auxiliary_view("circle_mask");
+  WGPUBindGroupLayout render_layout =
+      wgpuRenderPipelineGetBindGroupLayout(render_pipeline_, 0);
+  render_bind_group_ =
+      BindGroupBuilder()
+          .texture(0, mask_view)
+          .sampler(1, mask_sampler_)
+          .buffer(2, uniforms_.get().buffer, sizeof(CommonPostProcessUniforms))
+          .build(ctx_.device, render_layout);
+  wgpuBindGroupLayoutRelease(render_layout);
+}
+
+void CircleMaskEffect::compute(WGPUCommandEncoder encoder,
+                               const CommonPostProcessUniforms& uniforms) {
+  uniforms_.update(ctx_.queue, uniforms);
+
+  const CircleMaskParams params = {
+      .radius = radius_,
+  };
+  compute_params_.update(ctx_.queue, params);
+
+  WGPUTextureView mask_view = demo_->get_auxiliary_view("circle_mask");
+  WGPURenderPassColorAttachment color_attachment = {};
+  color_attachment.view = mask_view;
+  color_attachment.loadOp = WGPULoadOp_Clear;
+  color_attachment.storeOp = WGPUStoreOp_Store;
+  color_attachment.clearValue = {0.0, 0.0, 0.0, 1.0};
+#if !defined(DEMO_CROSS_COMPILE_WIN32)
+  color_attachment.depthSlice = WGPU_DEPTH_SLICE_UNDEFINED;
+#endif
+
+  WGPURenderPassDescriptor pass_desc = {};
+  pass_desc.colorAttachmentCount = 1;
+  pass_desc.colorAttachments = &color_attachment;
+
+  WGPURenderPassEncoder pass =
+      wgpuCommandEncoderBeginRenderPass(encoder, &pass_desc);
+  wgpuRenderPassEncoderSetPipeline(pass, compute_pipeline_);
+  wgpuRenderPassEncoderSetBindGroup(pass, 0, compute_bind_group_, 0, nullptr);
+  wgpuRenderPassEncoderDraw(pass, 3, 1, 0, 0);
+  wgpuRenderPassEncoderEnd(pass);
+  wgpuRenderPassEncoderRelease(pass);
+}
+
+void CircleMaskEffect::render(WGPURenderPassEncoder pass,
+                              const CommonPostProcessUniforms& uniforms) {
+  uniforms_.update(ctx_.queue, uniforms);
+
+  wgpuRenderPassEncoderSetPipeline(pass, render_pipeline_);
+  wgpuRenderPassEncoderSetBindGroup(pass, 0, render_bind_group_, 0, nullptr);
+  wgpuRenderPassEncoderDraw(pass, 3, 1, 0, 0);
+}