mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 05:31:24 +00:00
* Revert "Revert "feature:tf32:add initial conv3d fwd kernel support (#2763)" (#2848)"
This reverts commit 03b59f8c76.
* fix compile error on gf12x
* only run tf32 example on gfx942
* only build tf32 instance on gfx942
* ckProfiler:only support tf32 in gfx942
* delete unuseful messages
149 lines
7.1 KiB
CMake
149 lines
7.1 KiB
CMake
add_custom_target(example_gemm_dl)
|
|
|
|
add_example_executable(example_gemm_dl_fp32 gemm_dl_fp32.cpp)
|
|
add_example_dependencies(example_gemm_dl example_gemm_dl_fp32)
|
|
|
|
add_example_executable(example_gemm_dl_fp16 gemm_dl_fp16.cpp)
|
|
add_example_dependencies(example_gemm_dl example_gemm_dl_fp16)
|
|
|
|
add_example_executable(example_gemm_dpp_fp16 gemm_dpp_fp16.cpp)
|
|
|
|
add_example_executable(example_gemm_dl_int8 gemm_dl_int8.cpp)
|
|
add_example_dependencies(example_gemm_dl example_gemm_dl_int8)
|
|
if(USE_BITINT_EXTENSION_INT4)
|
|
add_example_executable(example_gemm_dl_int4 gemm_dl_int4.cpp)
|
|
add_example_dependencies(example_gemm_dl example_gemm_dl_int4)
|
|
endif(USE_BITINT_EXTENSION_INT4)
|
|
|
|
add_custom_target(example_gemm_xdl)
|
|
add_example_executable(example_gemm_xdl_fp16 gemm_xdl_fp16.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16)
|
|
|
|
add_example_executable(example_gemm_xdl_fp16_v2 gemm_xdl_fp16_v2.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_v2)
|
|
|
|
add_example_executable(example_gemm_xdl_fp16_streamk_v3 gemm_xdl_fp16_streamk_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_streamk_v3)
|
|
add_example_executable(example_gemm_xdl_fp16_v3 gemm_xdl_fp16_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_v3)
|
|
add_example_executable(example_gemm_xdl_fp8_v3 gemm_xdl_fp8_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8_v3)
|
|
|
|
add_example_executable(example_gemm_xdl_fp16_fp8_v3 gemm_xdl_fp16_fp8_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_fp8_v3)
|
|
|
|
|
|
add_example_executable(example_gemm_xdl_fp16_fp8_streamk_v3 gemm_xdl_fp16_fp8_streamk_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_fp8_streamk_v3)
|
|
|
|
add_example_executable(example_gemm_xdl_bf16_v3 gemm_xdl_bf16_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_bf16_v3)
|
|
|
|
set(GEMM_OPTIONS)
|
|
list(APPEND GEMM_OPTIONS "SHELL: -mllvm -greedy-reverse-local-assignment=1 -mllvm --slp-threshold=-16")
|
|
example_compile_options(example_gemm_xdl_fp8_v3 PRIVATE ${GEMM_OPTIONS})
|
|
example_compile_options(example_gemm_xdl_bf16_v3 PRIVATE ${GEMM_OPTIONS})
|
|
|
|
list(APPEND gpu_list gfx942 gfx950 gfx1200 gfx1201 gfx12-generic)
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list AND target EQUAL 0)
|
|
add_example_executable(example_gemm_xdl_fp16_pk_i4_v3 gemm_xdl_fp16_pk_i4_v3.cpp)
|
|
add_example_executable(example_gemm_xdl_fp16_pk_i4_v3_b_scale gemm_xdl_fp16_pk_i4_v3_b_scale.cpp)
|
|
add_example_executable(example_gemm_xdl_bf16_pk_i4_v3 gemm_xdl_bf16_pk_i4_v3.cpp)
|
|
add_example_executable(example_gemm_xdl_fp8_pk_i4_bpreshuffle_v3 gemm_xdl_fp8_pk_i4_bpreshuffle_v3.cpp)
|
|
add_example_executable(example_gemm_xdl_fp8_pk_i4_v3 gemm_xdl_fp8_pk_i4_v3.cpp)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
|
|
add_example_executable(example_gemm_xdl_wavelet_fp16 gemm_xdl_wavelet_fp16.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_wavelet_fp16)
|
|
|
|
add_example_executable(example_gemm_xdl_skip_b_lds_fp16 gemm_xdl_skip_b_lds_fp16.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_skip_b_lds_fp16)
|
|
|
|
add_example_executable(example_gemm_xdl_bf16 gemm_xdl_bf16.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_bf16)
|
|
|
|
add_example_executable(example_gemm_xdl_int8 gemm_xdl_int8.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_int8)
|
|
|
|
if(USE_BITINT_EXTENSION_INT4)
|
|
add_example_executable(example_gemm_xdl_int4 gemm_xdl_int4.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_int4)
|
|
endif(USE_BITINT_EXTENSION_INT4)
|
|
|
|
add_example_executable(example_gemm_xdl_fp64 gemm_xdl_fp64.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp64)
|
|
|
|
add_example_executable(example_gemm_xdl_streamk gemm_xdl_streamk.cpp)
|
|
|
|
list(APPEND gpu_list gfx90a gfx942 gfx950)
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list AND target EQUAL 0)
|
|
add_example_executable(example_gemm_xdl_lds_direct_load_fp32 gemm_xdl_lds_direct_load_fp32.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_lds_direct_load_fp32)
|
|
|
|
add_example_executable(example_gemm_xdl_lds_direct_load_fp16 gemm_xdl_lds_direct_load_fp16.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_lds_direct_load_fp16)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
|
|
list(APPEND gpu_list gfx90a gfx942 gfx950 gfx1200 gfx1201 gfx12-generic)
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list AND target EQUAL 0)
|
|
add_example_executable(example_gemm_xdl_bf16_streamk_v3 gemm_xdl_bf16_streamk_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_bf16_streamk_v3)
|
|
|
|
add_example_executable(example_gemm_xdl_fp8_streamk_v3 gemm_xdl_fp8_streamk_v3.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8_streamk_v3)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
|
|
list(APPEND gpu_list_tf32 gfx942)
|
|
set(target 0)
|
|
foreach(gpu IN LISTS GPU_TARGETS)
|
|
if(gpu IN_LIST gpu_list_tf32 AND target EQUAL 0)
|
|
add_example_executable(example_gemm_xdl_lds_direct_load_fp32_tf32 gemm_xdl_lds_direct_load_fp32_tf32.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_lds_direct_load_fp32_tf32)
|
|
set(target 1)
|
|
endif()
|
|
endforeach()
|
|
|
|
add_example_executable(example_gemm_xdl_fp8 gemm_xdl_fp8.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8)
|
|
|
|
add_example_executable(example_gemm_xdl_fp8_bf8 gemm_xdl_fp8_bf8.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp8_bf8)
|
|
|
|
add_example_executable(example_gemm_xdl_fp16_fp8 gemm_xdl_fp16_fp8.cpp)
|
|
add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp16_fp8)
|
|
|
|
add_custom_target(example_gemm_wmma)
|
|
add_example_executable(example_gemm_wmma_fp16 gemm_wmma_fp16.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16)
|
|
add_example_executable(example_gemm_wmma_bf16 gemm_wmma_bf16.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_bf16)
|
|
add_example_executable(example_gemm_wmma_int8 gemm_wmma_int8.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_int8)
|
|
|
|
add_example_executable(example_gemm_wmma_bf16_v3 gemm_wmma_bf16_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_bf16_v3)
|
|
add_example_executable(example_gemm_wmma_bf16_pk_i4_v3 gemm_wmma_bf16_pk_i4_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_bf16_pk_i4_v3)
|
|
add_example_executable(example_gemm_wmma_fp8_v3 gemm_wmma_fp8_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp8_v3)
|
|
add_example_executable(example_gemm_wmma_fp16_v3 gemm_wmma_fp16_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16_v3)
|
|
add_example_executable(example_gemm_wmma_fp16_pk_i4_v3 gemm_wmma_fp16_pk_i4_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16_pk_i4_v3)
|
|
add_example_executable(example_gemm_wmma_fp16_fp8_v3 gemm_wmma_fp16_fp8_v3.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16_fp8_v3)
|
|
add_example_executable(example_gemm_wmma_fp16_pk_i4_v3_b_scale gemm_wmma_fp16_pk_i4_v3_b_scale.cpp)
|
|
add_example_dependencies(example_gemm_wmma example_gemm_wmma_fp16_pk_i4_v3_b_scale)
|