mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
8cbd09c84a
* Stream-K smoke test config file generation This change converts the stream-k smoke tests to use tile engine. Since the m, n, and k values dependent on the CU count of a device, the configs are generated during the Configuration Phase. * Compute GEMM reference on GPU * Remove redundant Stream-K tests Removing redundant tests that are now run via tile engine. * Fix relative and absolute tolerance calculation This change updates the Stream-K tile engine interface to ensure that num_wgs_per_tile is propaged and passed into the compare_results function to calculate the rel and abs tolerance. Before, split-k was used, which is incorrect for Stream-K since the split-k value is always 1. * Cleanup imports, types, and other misc items This commit makes the following changes: - Uses Typing module for nested type hints - Uses quotes around cu_count_arg argument in generate_configs.cmake in if statements - Adds explicit include for tuple in test_gemm_streamk_simple.cpp - Adds a type for the tiles argument in argparser to check argument validity * Use CU count as return value for better parsing * Add reduction tests for bf16, fp8, and bf8
40 lines
2.0 KiB
CMake
40 lines
2.0 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
set(EXAMPLE_GEMM_COMPILE_OPTIONS)
|
|
if(CK_USE_OCP_FP8)
|
|
list(APPEND EXAMPLE_GEMM_COMPILE_OPTIONS -DCK_TILE_USE_OCP_FP8)
|
|
endif()
|
|
set(EXAMPLE_GEMM_COMPILE_COMPUTE_V4_OPTIONS)
|
|
if(CK_USE_OCP_FP8)
|
|
list(APPEND EXAMPLE_GEMM_COMPILE_COMPUTE_V4_OPTIONS -DCK_TILE_USE_OCP_FP8)
|
|
endif()
|
|
list(APPEND EXAMPLE_GEMM_COMPILE_COMPUTE_V4_OPTIONS
|
|
-mllvm
|
|
-enable-noalias-to-md-conversion=0
|
|
)
|
|
set(EXAMPLE_GEMM_COMPILE_COMPUTE_ASYNC_OPTIONS ${EXAMPLE_GEMM_COMPILE_COMPUTE_V4_OPTIONS})
|
|
|
|
# Currently test_ck_tile_streamk_smoke is only built on gfx9
|
|
if(GPU_TARGETS MATCHES "gfx90a|gfx942|gfx950")
|
|
|
|
include_directories(BEFORE ${CMAKE_CURRENT_SOURCE_DIR})
|
|
|
|
#TODO: support all arches
|
|
#TODO: current c-shuffle only supports C layout as R
|
|
add_gtest_executable(test_ck_tile_streamk_tile_partitioner test_streamk_tile_partitioner.cpp)
|
|
add_gtest_executable(test_ck_tile_streamk_extended
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_fp16_persistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_bf16_persistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_fp8_persistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_bf8_persistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_fp16_nonpersistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_bf16_nonpersistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_fp8_nonpersistent.cpp
|
|
${CMAKE_CURRENT_SOURCE_DIR}/extended_tests/test_gemm_streamk_bf8_nonpersistent.cpp
|
|
test_gemm_streamk_util.cpp)
|
|
target_compile_options(test_ck_tile_streamk_extended PRIVATE ${EXAMPLE_GEMM_COMPILE_OPTIONS})
|
|
else()
|
|
message(DEBUG "Skipping test_ck_tile_streamk unit tests for current target")
|
|
endif()
|