- Add RenderDocCapture include
- Initialize RenderDocCapture before D3D12 device creation
- SetDevice after D3D12 device initialization
- TriggerCapture on frame 29 before Present
- Add RenderDocCapture::Get().Shutdown() on exit
- Remove BeginCapture/EndCapture complexity for manual frame capture
- Use TriggerCapture for single frame capture (simpler API)
- Move TriggerCapture before Present to ensure frame is captured
- Add SetForegroundWindow/SetFocus before TriggerCapture
- Remove default capture path in Initialize to allow SetCaptureFilePath to work
- OpenGL test: Use BeginCapture/EndCapture with bool return values
- D3D12 test: Use BeginCapture/EndCapture with bool return values
- Both tests: Use GetCapture() to log capture file info
- Added capture file path and size logging after capture
- Add SetDevice() and GetNumCaptures() methods to RenderDocCapture
- Fix initialization order: RenderDoc before D3D12, then SetDevice after
- Use nullptr for window param in StartFrameCapture/EndFrameCapture
- Add BeginCapture at frame 29, EndCapture at frame 30
- Set capture file path template to .\minimal_frame30
- Copy renderdoc.dll (26MB redistributable) to test output
- Engine/third_party/renderdoc/ now contains working renderdoc.dll
- Rename D3D12Enum.h to D3D12Enums.h for naming consistency
- Fix OpenGL unit test GLAD initialization by using gladLoadGL()
instead of gladLoadGLLoader(wglGetProcAddress) for fallback support
- Migrate remaining tests to use gtest_discover_tests for granular
test discovery (math, core, containers, memory, threading, debug,
components, scene, resources, input, opengl)
- Remove obsolete TEST_RESOURCES_DIR and copy_directory commands
from OpenGL unit test CMakeLists (minimal/Res doesn't exist)
- Update TEST_SPEC.md with performance metrics and per-module
build/test commands for faster development workflow
- Update CMake path references to use lowercase paths
Replace add_test() with gtest_discover_tests() to enable CTest to
discover all 55 individual Google Test cases instead of treating them
as a single test. This improves test reporting granularity from 1/1
to 55/55 tests.
- Use Matrix4x4 type directly instead of float[16]
- Remove wrapper functions (IdentityMatrix, TranslationMatrix, PerspectiveMatrix, LookAtMatrix, MultiplyMatrix, TransposeMatrix)
- Direct use of Matrix4x4::Identity(), Matrix4x4::Translation(), Matrix4x4::Perspective()
- Transpose matrices before uploading to GPU to match HLSL column-major
- Update Math module Perspective and Orthographic to left-handed coordinate system
- Update math unit tests for new matrix values
- Add quad and sphere to integration test directory structure
- Update current integration tests table with both tests
- Update file structure section
- Bump version to 1.4
- Enable depth write mask (D3D12_DEPTH_WRITE_MASK_ALL) to fix rendering artifacts
- Change texture address mode from Wrap to Clamp to fix UV seam tearing
- Remove V coordinate flip in shader to fix upside-down texture
- Add ground truth screenshot (GT.ppm) for testing
- Fix TranslationMatrix to use correct indices (m12/m13/m14 for translation)
- Fix PerspectiveMatrix projection formula
- Enable depth testing (was disabled)
- Add texture sampling in pixel shader
- Adjust sphere radius to 1.0 and position to z=5
- Fix D3D12Buffer copy size calculation
- Add triangle test with vertex buffer and custom pipeline state
- Add triangle.hlsl shader with position and color per vertex
- Fix cull mode (NONE) and disable depth test for correct rendering
- Register D3D12_Triangle_Integration CTest
- Add GT.ppm golden image
- Add assert() bounds check to GetBackBuffer() to catch invalid indices
- Include <cassert> in D3D12SwapChain.cpp
- Update test_swap_chain.cpp to use reference return type
- Mark InvalidIndex test as DISABLED (assert aborts on invalid index)
- Update get-back-buffer.md documentation
- Add D3D12Screenshot::Capture(D3D12Device&, D3D12CommandQueue&, D3D12Texture&, const char*) wrapper overload
- Update minimal integration test to use encapsulated APIs
- Add DescriptorHeap wrapper unit tests
- Document minimal GetBuffer native call as known limitation in TEST_SPEC.md
- Move test_*.cpp and fixtures/ to tests/RHI/D3D12/unit/
- Create unit/CMakeLists.txt with proper test configuration
- Simplify parent CMakeLists.txt to use add_subdirectory
- Integration tests remain in integration/ folder
- Each test now creates its own D3D12 device, command queue, allocator, and command list
- Properly cleanup in TearDown to avoid GPU state issues
- All 29 tests now pass
- CommandAllocator: Reset, MultipleReset, DifferentTypes
- CommandList: Close, GetDesc
- CommandQueue: GetTimestampFrequency, ExecuteCommandLists
- Note: Some tests fail after ExecuteCommandLists due to GPU state
