ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-01 04:07:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

add back the performance flags for f8gemm

Browse Source
This commit is contained in:
aska-0096
2025-08-18 08:57:45 +00:00
parent 753b6227c5
commit a9e2e0b969
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/65_gemm_multiply_multiply/CMakeLists.txt
View File

@@ -31,7 +31,7 @@ foreach(gpu IN LISTS GPU_TARGETS)
example_compile_options(example_moe_gemm1_xdl_pk_i4 PRIVATE ${EXAMPLE_COMPILE_OPTIONS})
example_compile_options(example_moe_gemm2_xdl_pk_i4 PRIVATE ${EXAMPLE_COMPILE_OPTIONS})
endif()
set(GEMM_OPTIONS "SHELL: -mllvm -greedy-reverse-local-assignment=1")
set(GEMM_OPTIONS "SHELL: -mllvm -greedy-reverse-local-assignment=1 -mllvm --slp-threshold=-16")
example_compile_options(example_gemm_multiply_multiply_xdl_fp8_bpreshuffle PRIVATE ${GEMM_OPTIONS})
example_compile_options(example_moe_gemm1_xdl_fp8 PRIVATE ${GEMM_OPTIONS})
example_compile_options(example_moe_gemm2_xdl_fp8 PRIVATE ${GEMM_OPTIONS})