mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
b9c6cb1452
* First look at mfma / wmma unification * Refactor * Re-org file structure * Restructure transform selection and WaveWiseMma class * Update license files. Add missing gfx1151 support. Change wave size for HOST to 1. Update datatypes naming consistency * Fixes default MmaSelector implentation * Adds unit tests for amdgcn_mma and arch * Consolidate common arch id checks to constexpr functions. Strongly type ids as amdgcn_target_arch_id object. * Refactor is_any_value_of * Fixes mma_selector logic * Fix typo * Add mma selector test for tile decomposition * Fix compilation of mma.hpp * Revert back to c++17 compatibility * Fix compiler error by returning index_t from get_warp_size() * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fixes compiler error for missing is_wave32() function * Fixes compiler error for host wave_size() should be 64 * Fixes compiler errors where __cpp_concepts is not defined * Fixes compiler errors where __cpp_concepts is not defined * Fix test failure for host is wave64 by default --------- Co-authored-by: Chris Millette <you@example.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
37 lines
1.1 KiB
CMake
37 lines
1.1 KiB
CMake
add_subdirectory(image_to_column)
|
|
add_subdirectory(gemm)
|
|
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(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(utility)
|
|
add_subdirectory(reduce)
|
|
add_subdirectory(core)
|
|
add_subdirectory(epilogue)
|
|
add_subdirectory(atomic_add_op)
|
|
add_subdirectory(fmha)
|
|
add_subdirectory(gemm_tile_engine)
|
|
add_subdirectory(pooling)
|