diff options
| author | Gengxin Xie <gengxin.xie@intel.com> | 2020-04-07 15:17:01 +0800 |
|---|---|---|
| committer | Gengxin Xie <gengxin.xie@intel.com> | 2020-04-07 15:17:01 +0800 |
| commit | 1cabf5bf7d494c02e019a77049614a45beae6bdc (patch) | |
| tree | 5bd3ba654e936239f9a3af591a0fa52bafb86e60 | |
| parent | d3f5fc5daa1f9db8d8364e28b7c2688ce91f17b4 (diff) | |
| download | numpy-1cabf5bf7d494c02e019a77049614a45beae6bdc.tar.gz | |
DOC: Release note about upcoming changes
| -rw-r--r-- | doc/release/upcoming_changes/15648.improvement.rst | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/doc/release/upcoming_changes/15648.improvement.rst b/doc/release/upcoming_changes/15648.improvement.rst new file mode 100644 index 000000000..59522c75f --- /dev/null +++ b/doc/release/upcoming_changes/15648.improvement.rst @@ -0,0 +1,7 @@ +Use AVX512 intrinsic to implement ``np.exp`` when input is ``np.float64`` +------------------------------------------------------------------------- +Use AVX512 intrinsic to implement ``np.exp`` when input is ``np.float64``, +which can imporve the performance of ``np.exp`` with ``np.float64`` input 5-7x +faster than before. The _multiarray_umath.so module has grown about 63 kB on +linux64. + |