projects / platform / upstream / openblas.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f7f97c6) | patch
Add optimized *copy versions for skylakex
authorArjan van de Ven <arjan@linux.intel.com>
Sat, 6 Oct 2018 13:47:20 +0000 (13:47 +0000)
committerArjan van de Ven <arjan@linux.intel.com>
Sat, 6 Oct 2018 13:51:44 +0000 (13:51 +0000)
commitd74dc39b0faeebb7aeb97e4099dcb50a1fcc7533
tree6ad5a58385a2a68095a641dc45999e75697e4fa4tree | snapshot
parentf7f97c614829488bc04c012a50391b3350176b69commit | diff
Add optimized *copy versions for skylakex

Add optimized n/t copy versions for skylakex; in the patch the
tcopy is also rewritten using intrinsics; the ncopy file
will be worked on in a future commit
kernel/x86_64/KERNEL.SKYLAKEX diff | blob | history
kernel/x86_64/dgemm_ncopy_8_skylakex.c [new file with mode: 0644] blob
kernel/x86_64/dgemm_tcopy_8_skylakex.c [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;