review.tizen.org Git - platform/upstream/openblas.git/commit

projects / platform / upstream / openblas.git / commit

summary | shortlog | log | commit | commitdiff | tree
(parent: 17c46bf) | patch

author	Rajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
	Wed, 21 Oct 2020 14:53:45 +0000 (09:53 -0500)
committer	Rajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
	Wed, 21 Oct 2020 14:53:45 +0000 (09:53 -0500)
commit	ad745c0bae5a17e6460556b39dd991519c31ca4f
tree	d11a53d39ec2c3401420b66ed950094a66471c83	tree \| snapshot
parent	17c46bf06a3fdf110eb79d5cf6eda65f48d2ed3f	commit \| diff

Optimize scopy/ccopy for POWER10

This patch makes use of new POWER10 vector pair instructions for
loads and stores. Also reorganized all variants of copy functions
to make use of same kernel.

kernel/power/KERNEL.POWER10		diff \| blob \| history
kernel/power/ccopy_power10.c	[new file with mode: 0644]	blob
kernel/power/copy_microk_power10.c	[moved from kernel/power/dcopy_microk_power10.c with 91% similarity]	diff \| blob \| history
kernel/power/dcopy_power10.c		diff \| blob \| history
kernel/power/scopy_power10.c	[new file with mode: 0644]	blob
kernel/power/zcopy_microk_power10.c	[deleted file]	blob \| history
kernel/power/zcopy_power10.c		diff \| blob \| history

Domain: Machine Learning / ML Framework;