mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
26d29374e5
[CK] Fix warp tile combination selection in absence of a GPU (#5213) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## Motivation The `get_gpu_name_by_id()` function in `gemm_streamk_validation_utils.py` relies on `rocminfo` to detect the GPU architecture at runtime. However, __`rocminfo` fails in CI/build environments__ where: - No physical GPU is present - ROCm tools are not installed - The build is running in a container without GPU access In any of these environments, the problem manifests itself in incorrect kernel validation and will generate template instantiations that do not exist: ``` [composable_kernel] FAILED: test/ck_tile/gemm_streamk_tile_engine/CMakeFiles/test_gemm_streamk_tile_engine_fp16_rcr_streamk_atomic_smoke_tests_config_fp16_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.dir/test_gemm_streamk_simple.cpp.o [composable_kernel] /__w/TheRock/TheRock/build/core/clr/dist/lib/llvm/bin/clang++ -DCK_ENABLE_BF16 -DCK_ENABLE_BF8 -DCK_ENABLE_FP16 -DCK_ENABLE_FP32 -DCK_ENABLE_FP64 -DCK_ENABLE_FP8 -DCK_ENABLE_INT8 -DCK_ENABLE_TF32 -DCK_TILE_USE_WMMA=0 -DCK_TIME_KERNEL=1 -DCK_USE_FNUZ_FP8 -DCK_USE_GFX94 -DCK_USE_XDL -DDPP_KERNELS -DGEMM_SINGLE_INSTANCE_HPP=\"/__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/test/ck_tile/gemm_streamk_tile_engine/fp16/rcr/streamk_atomic_smoke_tests_config_fp16/gemm_streamk_single_fp16_rcr_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.hpp\" -DGEMM_TEST_PARAMS_HPP=\"/__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/test/ck_tile/gemm_streamk_tile_engine/fp16/rcr/streamk_atomic_smoke_tests_config_fp16/test_params.hpp\" -DUSE_PROF_API=1 -D__HIP_PLATFORM_AMD__=1 -D__HIP_PLATFORM_HCC__=1 -D__HIP_ROCclr__=1 -I/__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/profiler/include -I/__w/TheRock/TheRock/rocm-libraries/projects/composablekernel -I/__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/library/include -I/__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/include -I/__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/include -I/__w/TheRock/TheRock/build/profiler/rocprofiler-sdk/stage/include -I/__w/TheRock/TheRock/build/profiler/roctracer/stage/include -I/__w/TheRock/TheRock/build/base/half/stage/include -I/__w/TheRock/TheRock/build/third-party/sysdeps/linux/libdrm/build/stage/lib/rocm_sysdeps/include -isystem /__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/_deps/gtest-src/googletest/include -isystem /__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/_deps/gtest-src/googletest -O3 -DNDEBUG -std=gnu++20 --offload-arch=gfx942 -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Wno-missing-field-initializers -Wno-error=deprecated-declarations -Wall -Wextra -Wcomment -Wendif-labels -Wformat -Winit-self -Wreturn-type -Wsequence-point -Wswitch -Wtrigraphs -Wundef -Wuninitialized -Wunreachable-code -Wunused -Wno-reserved-identifier -Wno-option-ignored -Wsign-compare -Wno-extra-semi-stmt -Wno-unused-template -Weverything -Wno-c++98-compat -Wno-c++98-compat-pedantic -Wno-conversion -Wno-double-promotion -Wno-exit-time-destructors -Wno-extra-semi -Wno-float-conversion -Wno-gnu-anonymous-struct -Wno-gnu-zero-variadic-macro-arguments -Wno-missing-prototypes -Wno-nested-anon-types -Wno-padded -Wno-return-std-move-in-c++11 -Wno-shorten-64-to-32 -Wno-sign-conversion -Wno-unknown-warning-option -Wno-unused-command-line-argument -Wno-weak-vtables -Wno-covered-switch-default -Wno-unsafe-buffer-usage -Wno-unused-lambda-capture -Wno-nvcc-compat -Wno-c++20-compat -Wno-bit-int-extension -Wno-pass-failed -Wno-switch-default -Wno-unique-object-duplication -fbracket-depth=1024 -Wno-nrvo -fno-offload-uniform-block -mllvm --lsr-drop-solution=1 -mllvm -enable-post-misched=0 -mllvm -amdgpu-early-inline-all=true -mllvm -amdgpu-function-calls=false -Werror -Weverything -fcolor-diagnostics -Wno-c++20-extensions -Wno-global-constructors -Wno-undef -Wno-undefined-func-template -Wno-float-equal --offload-compress -include /__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/test/ck_tile/gemm_streamk_tile_engine/fp16/rcr/streamk_atomic_smoke_tests_config_fp16/gemm_streamk_single_fp16_rcr_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.hpp -MD -MT test/ck_tile/gemm_streamk_tile_engine/CMakeFiles/test_gemm_streamk_tile_engine_fp16_rcr_streamk_atomic_smoke_tests_config_fp16_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.dir/test_gemm_streamk_simple.cpp.o -MF test/ck_tile/gemm_streamk_tile_engine/CMakeFiles/test_gemm_streamk_tile_engine_fp16_rcr_streamk_atomic_smoke_tests_config_fp16_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.dir/test_gemm_streamk_simple.cpp.o.d -o test/ck_tile/gemm_streamk_tile_engine/CMakeFiles/test_gemm_streamk_tile_engine_fp16_rcr_streamk_atomic_smoke_tests_config_fp16_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.dir/test_gemm_streamk_simple.cpp.o -x hip -c /__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/test/ck_tile/gemm_streamk_tile_engine/test_gemm_streamk_simple.cpp [composable_kernel] In file included from <built-in>:2: [composable_kernel] In file included from /__w/TheRock/TheRock/build/ml-libs/composable_kernel/build/test/ck_tile/gemm_streamk_tile_engine/fp16/rcr/streamk_atomic_smoke_tests_config_fp16/gemm_streamk_single_fp16_rcr_compv3_cshuffle_intrawave_atomic_False_False_False_False_256x256x32_2x2x1_16x16x8.hpp:9: [composable_kernel] In file included from /__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/include/ck_tile/ops/gemm.hpp:23: [composable_kernel] In file included from /__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/include/ck_tile/ops/gemm/block/block_gemm_asmem_bsmem_creg_v1.hpp:7: [composable_kernel] In file included from /__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/include/ck_tile/ops/gemm/block/block_gemm_asmem_bsmem_creg_v1_default_policy.hpp:8: [composable_kernel] /__w/TheRock/TheRock/rocm-libraries/projects/composablekernel/include/ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp:185:1: error: implicit instantiation of undefined template 'ck_tile::impl::warp_gemm_dispatcher::Dispatcher<_Float16, _Float16, float, 16, 16, 8, false, false, false, ck_tile::WGAttrNumAccessEnum::Single, ck_tile::WGAttrNumAccessEnum::Single>' ``` ## Technical Details ### Changes Made: #### 1. __gemm_streamk_validation_utils.py__ - Added module-level storage: `_configured_gpu_targets` - Added `set_gpu_targets(targets: List[str])` to configure fallback GPU targets - Added `get_configured_gpu_targets() -> List[str]` to retrieve configured targets - Enhanced `get_gpu_name_by_id()` to: - First try `rocminfo` (existing behavior) - If `rocminfo` fails, fall back to first configured GPU target - Extract base gfx name (e.g., "gfx90a" from "gfx90a:xnack+") - Log debug messages when using fallback #### 2. __gemm_streamk_instance_builder.py__ - Added `--gpu_targets` command-line argument - Automatically calls `set_gpu_targets()` when `--gpu_targets` is provided - Parses semicolon-separated GPU target list from CMake #### 3. __test/ck_tile/gemm_streamk_tile_engine/CMakeLists.txt__ - Modified both `--list_kernels` and `--gen_single` invocations to pass `--gpu_targets "${SUPPORTED_GPU_TARGETS}"` - GPU targets are now automatically wired from CMake to Python scripts ### How It Works: 1. __CMake Configuration__: `SUPPORTED_GPU_TARGETS` is determined from `GPU_TARGETS` or defaults 2. __CMake → Python__: CMake passes targets via `--gpu_targets` argument to Python scripts 3. __Python Configuration__: Scripts call `set_gpu_targets()` to configure the fallback 4. __Fallback Mechanism__: When `rocminfo` fails, `get_gpu_name_by_id()` uses the first configured target 5. __Target Parsing__: Extracts clean gfx name (e.g., "gfx90a" from "gfx90a:xnack+") ## Test Plan Confirm that only the appropriate kernels are selected and that CI passes. ## Test Result 1. Waiting on CI 2. Compilation succeeded locally and the kernel list does not contain the 16x16x8 kernel for gfx942 anymore: ``` (.venv) bhargrea@ctr-cx66-mi300x-02:~/github/TheRock$ cat build/ml-libs/composable_kernel/build/test/ck_tile/gemm_streamk_tile_engine/fp16/rcr/streamk_atomic_smoke_tests_config_fp16/gemm_kernel_list.txt gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_True_256x256x32_2x2x1_16x16x16|256x256x32_2x2x1_16x16x16|compv3_cshuffle_intrawave_atomic_False_False_False_True gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_False_256x256x32_2x2x1_16x16x16|256x256x32_2x2x1_16x16x16|compv3_cshuffle_intrawave_atomic_False_False_False_False gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_True_256x256x32_2x2x1_16x16x32|256x256x32_2x2x1_16x16x32|compv3_cshuffle_intrawave_atomic_False_False_False_True gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_False_256x256x32_2x2x1_16x16x32|256x256x32_2x2x1_16x16x32|compv3_cshuffle_intrawave_atomic_False_False_False_False gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_True_256x256x32_2x2x1_32x32x8|256x256x32_2x2x1_32x32x8|compv3_cshuffle_intrawave_atomic_False_False_False_True gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_False_256x256x32_2x2x1_32x32x8|256x256x32_2x2x1_32x32x8|compv3_cshuffle_intrawave_atomic_False_False_False_False gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_True_256x256x32_2x2x1_32x32x16|256x256x32_2x2x1_32x32x16|compv3_cshuffle_intrawave_atomic_False_False_False_True gemm_fp16_rcr_compv3_cshuffle_intrawave_Atomic_False_False_False_False_256x256x32_2x2x1_32x32x16|256x256x32_2x2x1_32x32x16|compv3_cshuffle_intrawave_atomic_False_False_False_False ``` ## Submission Checklist - [ x ] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
CK Tile Testing Guide
This document describes the test organization and available test targets for CK Tile operations.
Overview
CK Tile tests are organized with multiple levels of granularity to support different development workflows:
- Global test labels - Run tests across all operations
- Operation-specific umbrella targets - Run all tests for a specific operation
- Individual test executables - Run specific tests
Global Test Labels
These targets run tests across all CK operations (not just CK Tile):
ninja smoke
Run fast smoke tests (tests that complete within ~30 seconds on gfx90a).
ninja smoke
ninja regression
Run slower, more comprehensive regression tests.
ninja regression
ninja check
Run ALL available tests in the entire codebase.
ninja check
Operation-Specific Umbrella Targets
These targets allow you to run all tests for a specific CK Tile operation. This is useful when making changes to a particular operation and wanting to validate all related tests without running the entire test suite.
GEMM Operations
ck_tile_gemm_tests
Run all basic GEMM pipeline tests (memory, compute variants, persistent, etc.)
ninja ck_tile_gemm_tests
Test executables included:
test_ck_tile_gemm_pipeline_memtest_ck_tile_gemm_pipeline_compv3test_ck_tile_gemm_pipeline_compv4test_ck_tile_gemm_pipeline_persistenttest_ck_tile_gemm_pipeline_compv6test_ck_tile_gemm_pipeline_comp_async(gfx95 only)test_ck_tile_gemm_pipeline_*_wmmavariants (gfx11/gfx12 only)
ck_tile_gemm_block_scale_tests
Run all GEMM tests with block-scale quantization (AQuant, BQuant, ABQuant, etc.)
ninja ck_tile_gemm_block_scale_tests
Test executables included: 29 test executables covering:
- AQuant tests (memory pipelines, base layouts, prefill, preshuffle, transpose)
- ABQuant tests (base, padding, preshuffle)
- BQuant tests (1D/2D variants, transpose)
- BQuant with PreshuffleB (decode/prefill, 1D/2D)
- BQuant with PreshuffleQuant (decode/prefill, 1D/2D)
- RowColQuant and TensorQuant tests
ck_tile_gemm_streamk_tests
Run all GEMM StreamK tests (tile partitioner, reduction, smoke, extended)
ninja ck_tile_gemm_streamk_tests
Test executables included:
test_ck_tile_streamk_tile_partitionertest_ck_tile_streamk_reductiontest_ck_tile_streamk_smoketest_ck_tile_streamk_extended
ck_tile_grouped_gemm_quant_tests
Run all grouped GEMM quantization tests
ninja ck_tile_grouped_gemm_quant_tests
Test executables included:
test_ck_tile_grouped_gemm_quant_rowcoltest_ck_tile_grouped_gemm_quant_tensortest_ck_tile_grouped_gemm_quant_aquanttest_ck_tile_grouped_gemm_quant_bquanttest_ck_tile_grouped_gemm_quant_bquant_preshuffleb
Other Operations
ck_tile_fmha_tests
Run all FMHA (Flash Multi-Head Attention) tests
ninja ck_tile_fmha_tests
Test executables included: Forward and backward tests for fp16, bf16, fp8bf16, fp32
ck_tile_reduce_tests
Run all reduce operation tests
ninja ck_tile_reduce_tests
Test executables included:
test_ck_tile_reduce2dtest_ck_tile_multi_reduce2d_threadwisetest_ck_tile_multi_reduce2d_multiblock
Individual Test Executables
You can also build and run individual test executables:
Build a specific test
ninja test_ck_tile_gemm_pipeline_mem
Run a specific test directly
./build/bin/test_ck_tile_gemm_pipeline_mem
Run a specific test through ctest
ctest -R test_ck_tile_gemm_pipeline_mem --output-on-failure