diff --git a/transformer_engine/common/CMakeLists.txt b/transformer_engine/common/CMakeLists.txt index 5975efedaf..a83cbe3e30 100644 --- a/transformer_engine/common/CMakeLists.txt +++ b/transformer_engine/common/CMakeLists.txt @@ -230,12 +230,24 @@ add_library(transformer_engine SHARED ${transformer_engine_SOURCES}) target_include_directories(transformer_engine PUBLIC "${CMAKE_CURRENT_SOURCE_DIR}/include") -# CUTLASS kernels require SM90a and cause hang in debug build +# Grouped GEMM kernels require SM90a set_property( SOURCE gemm/cutlass_grouped_gemm.cu APPEND PROPERTY - COMPILE_OPTIONS "--generate-code=arch=compute_90a,code=sm_90a;-g0") + COMPILE_OPTIONS "--generate-code=arch=compute_90a,code=sm_90a") + +# CUTLASS kernels could cause hang in debug build +set(CUTLASS_KERNEL_SOURCES + gemm/cutlass_grouped_gemm.cu + hadamard_transform/group_hadamard_transform_cast_fusion.cu + hadamard_transform/group_row_cast_col_hadamard_transform_cast_fusion.cu + hadamard_transform/hadamard_transform_cast_fusion.cu) +set_property( + SOURCE ${CUTLASS_KERNEL_SOURCES} + APPEND + PROPERTY + COMPILE_OPTIONS "-g0;-dopt=on") # Configure dependencies target_link_libraries(transformer_engine PUBLIC