projects / platform / upstream / openblas.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ba31c8f) | patch
Optimize dcopy/zcopy for POWER10
authorRajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
Mon, 28 Sep 2020 02:42:32 +0000 (21:42 -0500)
committerRajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
Mon, 28 Sep 2020 02:42:32 +0000 (21:42 -0500)
commit2df4235e00a73ad61b7997c74497fd86eb278ebf
treea09fe7476c44c87bb6011e38811eca7f7fbb54c3tree | snapshot
parentba31c8f5f991c3fecdb5e19df682952076c0ed85commit | diff
Optimize dcopy/zcopy for POWER10

This patch makes use of new POWER10 vector pair instructions for
loads and stores. Tested in simulator and no new failures.
kernel/power/KERNEL.POWER10 diff | blob | history
kernel/power/dcopy_microk_power10.c [new file with mode: 0644] blob
kernel/power/dcopy_power10.c [new file with mode: 0644] blob
kernel/power/zcopy_microk_power10.c [new file with mode: 0644] blob
kernel/power/zcopy_power10.c [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;