mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-07-02 21:27:45 +00:00
947dcc2606
[CK Tile] Add transposed tile load implementation, and tests for load_and_convert_tile (#5510) ## Motivation Mixed precision b/fp16 x fp8 requires a transposed tile load implementation that supports mixed precision using these types. Implement this, use it in `load_and_convert_tile`, and add a unit test for `load_and_convert_tile` which covers this functionality. ## Technical Details <!-- Explain the changes along with any relevant GitHub links. --> ## Test Plan <!-- Explain any relevant testing done to verify this PR. --> ## Test Result <!-- Briefly summarize test outcomes. --> ## Submission Checklist - [x] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
83 lines
3.2 KiB
CMake
83 lines
3.2 KiB
CMake
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
################################################################################
|
|
# CK Tile Test Organization
|
|
################################################################################
|
|
# CK Tile tests can be run using several methods:
|
|
#
|
|
# 1. Global test labels (run tests across all operations):
|
|
# - ninja smoke - Fast tests (~30s on gfx90a)
|
|
# - ninja regression - Slower comprehensive tests
|
|
# - ninja check - All available tests
|
|
#
|
|
# 2. Operation-specific umbrella targets (run all tests for a specific operation):
|
|
# - ninja ck_tile_gemm_tests - All basic GEMM tests
|
|
# - ninja ck_tile_gemm_block_scale_tests - All GEMM with block-scale quantization tests
|
|
# - ninja ck_tile_gemm_streamk_tests - All GEMM StreamK tests
|
|
# - ninja ck_tile_grouped_gemm_quant_tests - All grouped GEMM quantization tests
|
|
# - ninja ck_tile_reduce_tests - All reduce operation tests
|
|
# - ninja ck_tile_fmha_tests - All FMHA (Flash Attention) tests
|
|
#
|
|
# 3. Individual test executables:
|
|
# - ninja test_<test_name> - Build specific test executable
|
|
# - ./build/bin/test_<test_name> - Run specific test directly
|
|
#
|
|
# These umbrella targets are useful when working on specific operations to quickly
|
|
# validate all related tests without running the entire test suite.
|
|
################################################################################
|
|
|
|
add_subdirectory(image_to_column)
|
|
add_subdirectory(gemm)
|
|
add_subdirectory(gemm_persistent_async_input)
|
|
add_subdirectory(gemm_weight_preshuffle)
|
|
add_subdirectory(batched_gemm)
|
|
add_subdirectory(grouped_gemm)
|
|
add_subdirectory(grouped_gemm_preshuffle)
|
|
add_subdirectory(grouped_gemm_multi_d)
|
|
add_subdirectory(grouped_gemm_quant)
|
|
add_subdirectory(grouped_gemm_abquant)
|
|
add_subdirectory(gemm_multi_d)
|
|
add_subdirectory(gemm_multi_abd)
|
|
add_subdirectory(gemm_streamk)
|
|
add_subdirectory(data_type)
|
|
add_subdirectory(container)
|
|
add_subdirectory(elementwise)
|
|
# Not including these tests as there is a bug on gfx90a and gfx942
|
|
# resulting in "GPU core dump"
|
|
#add_subdirectory(moe_smoothquant)
|
|
add_subdirectory(permute)
|
|
add_subdirectory(moe_sorting)
|
|
add_subdirectory(slice_tile)
|
|
add_subdirectory(memory_copy)
|
|
add_subdirectory(batched_transpose)
|
|
add_subdirectory(smoothquant)
|
|
add_subdirectory(topk_softmax)
|
|
add_subdirectory(add_rmsnorm2d_rdquant)
|
|
# add_subdirectory(layernorm2d)
|
|
# add_subdirectory(rmsnorm2d)
|
|
add_subdirectory(gemm_block_scale)
|
|
add_subdirectory(flatmm)
|
|
add_subdirectory(gemm_mx)
|
|
add_subdirectory(grouped_gemm_mx)
|
|
add_subdirectory(utility)
|
|
add_subdirectory(warp_gemm)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(tdm)
|
|
add_subdirectory(core)
|
|
add_subdirectory(epilogue)
|
|
add_subdirectory(atomic_add_op)
|
|
if(BUILD_CK_TILE_FMHA_TESTS)
|
|
add_subdirectory(fmha)
|
|
endif()
|
|
if(BUILD_CK_TILE_ENGINE_TESTS)
|
|
# TODO: The Universal GEMM tile engine test will be either removed
|
|
# or moved to the appropriate location in future work.
|
|
# add_subdirectory(gemm_tile_engine)
|
|
add_subdirectory(pooling_tile_engine)
|
|
endif()
|
|
add_subdirectory(pooling)
|
|
add_subdirectory(grouped_conv)
|
|
add_subdirectory(load_and_convert_tile)
|
|
add_subdirectory(multicast_load)
|