We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 9526007 commit 75ffe91Copy full SHA for 75ffe91
doc/release/upcoming_changes/27147.performance.rst
@@ -0,0 +1,8 @@
1
+* OpenBLAS on x86_64 and i686 is built with fewer kernels. Based on
2
+ benchmarking, there are 5 clusters of performance around these kernels:
3
+ ``PRESCOTT NEHALEM SANDYBRIDGE HASWELL SKYLAKEX``.
4
+
5
+* OpenBLAS on windows is linked without quadmath, simplfying licensing
6
7
+* Due to a regression in OpenBLAS on windows, the performance improvements
8
+ when using multiple threads for OpenBLAS 0.3.26 were reverted.
0 commit comments