diff options
| author | Jianyu Huang <jianyuhuang@fb.com> | 2019-03-06 21:18:56 +0300 |
|---|---|---|
| committer | Facebook Github Bot <facebook-github-bot@users.noreply.github.com> | 2019-03-06 21:21:45 +0300 |
| commit | 66b41357561f2ff9895d2b4638273f07c49dbe29 (patch) | |
| tree | 1d0014e483a9fe5beb0cce3b1394b0eb550c12ba /CMakeLists.txt | |
| parent | 2eb84b8912f8340d8ffc54a3ef7653291f64f6f8 (diff) | |
Add Avx512BW/VL/DQ check (#84)
Summary:
Pull Request resolved: https://github.com/pytorch/FBGEMM/pull/84
Add AVX512BW Check:
AVX-512 Byte and Word Instructions add support for for 8-bit and 16-bit integer operations such as vpmaddubsw.
Similarly, add AVX512VL/DQ check.
Reviewed By: jspark1105
Differential Revision: D14321050
fbshipit-source-id: bd34745fd488ce4efe3248aeb78c54e1c2d91d47
Diffstat (limited to 'CMakeLists.txt')
| -rw-r--r-- | CMakeLists.txt | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index 607657e..494e261 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -100,7 +100,8 @@ set_target_properties(fbgemm_generic fbgemm_avx2 fbgemm_avx512 PROPERTIES target_compile_options(fbgemm_avx2 PRIVATE "-m64" "-mavx2" "-mfma" "-masm=intel") target_compile_options(fbgemm_avx512 PRIVATE - "-m64" "-mavx2" "-mfma" "-mavx512f" "-masm=intel") + "-m64" "-mavx2" "-mfma" "-mavx512f" "-mavx512bw" "-mavx512dq" + "-mavx512vl" "-masm=intel") if(NOT TARGET asmjit) #Download asmjit from github if ASMJIT_SRC_DIR is not specified. |