[PATCH][AVX512] PMIN/PMAX intrinsics and patterns

Demikhovsky, Elena elena.demikhovsky at intel.com
Sun Oct 27 01:24:01 PDT 2013


Cameron,

Thank you for contributing to AVX-512!
LGTM. Committed.


-  Elena

-----Original Message-----
From: Cameron McInally [mailto:cameron.mcinally at nyu.edu] 
Sent: Saturday, October 26, 2013 03:27
To: llvm-commits at cs.uiuc.edu
Cc: Demikhovsky, Elena; Craig Topper
Subject: [PATCH][AVX512] PMIN/PMAX intrinsics and patterns

Hey guys,

Here is a patch to support unmasked, signed and unsigned, PMIN/PMAX intrinsics.

The naming scheme is a bit wonky between the floating point MIN/MAX and integer PMIN/PMAX intrinsics. So, I continued from the AVX2 PMIN/PMAX intrinsic names.

Also, I extrapolated the GNU Builtin names for AVX512, similar to the other AVX512 intrinsics. AFAIK, those Builtin names have not been release yet. I could be wrong about that though.

And, I do not have commit access.

Thanks,
Cameron
---------------------------------------------------------------------
Intel Israel (74) Limited

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.




More information about the llvm-commits mailing list