mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
3d29bff2f0
* multi_abd wmma support: - Add multiple A and B support to multiple D implementation (gridwise level) - Add multi_abd GEMM (device level) - Add instances (xdl parity) - Add tests (both xdl and wmma) - Add examples - Add ckProfiler support (both xdl and wmma) * Fix bug in device print function * Fix unused template parameter * Fix batched gemm for multiABD gridwise implementation * Fix gemm_universal_reduce with multiABDs gridwise implementation --------- Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
9 lines
900 B
CMake
9 lines
900 B
CMake
add_example_executable(example_gemm_multi_ABD_wmma_fp16 gemm_multi_ABD_wmma_fp16.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_wmma_bias_fastgelu_bf16_i8 gemm_multi_ABD_wmma_bias_fastgelu_bf16_i8.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_wmma_multiply_bias_fastgelu_bf16_i8 gemm_multi_ABD_wmma_multiply_bias_fastgelu_bf16_i8.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_wmma_fastgelu_bf16_i8 gemm_multi_ABD_wmma_fastgelu_bf16_i8.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_xdl_fp16 gemm_multi_ABD_xdl_fp16.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_xdl_bias_fastgelu_bf16_i8 gemm_multi_ABD_xdl_bias_fastgelu_bf16_i8.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_xdl_multiply_bias_fastgelu_bf16_i8 gemm_multi_ABD_xdl_multiply_bias_fastgelu_bf16_i8.cpp)
|
|
add_example_executable(example_gemm_multi_ABD_xdl_fastgelu_bf16_i8 gemm_multi_ABD_xdl_fastgelu_bf16_i8.cpp)
|