maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
264,786 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

12 Commits

Author SHA1 Message Date
Vyacheslav Klochkov 6daefcf626 X86-FMA3: Implemented commute transformation for EVEX/AVX512 FMA3 opcodes. 
This helped to improved memory-folding and register coalescing optimizations.

Also, this patch fixed the tracker #17229.

Reviewer: Craig Topper.
Differential Revision: https://reviews.llvm.org/D23108

llvm-svn: 278431
 2016-08-11 22:07:33 +00:00
Craig Topper 6bcbf5338c [AVX512] Cleanup FMA operand order in patterns to match the VEX versions and to really be 213, 231, and 132. 
llvm-svn: 276613
 2016-07-25 07:20:28 +00:00
Craig Topper f4151bea72 [AVX512] Add initial support for the Execution Domain fixing pass to change some EVEX instructions. 
llvm-svn: 276393
 2016-07-22 05:00:52 +00:00
Igor Breger dd6522c653 AVX512 : Change v8i1 bitconvert GR8 pattern, remove unnecessary movzbl instruction. 
code example , previous implementation.
    movzbl  %dil, %eax
    kmovw  %eax, %k0
  new code
    kmovw  %edi, %k0

Differential Revision: http://reviews.llvm.org/D16287

llvm-svn: 258045
 2016-01-18 12:02:45 +00:00
Igor Breger a7a8e9a018 AVX-512: Implemented missing encoding and intrinsics for FMA instructions 
Added tests for DAG lowering ,encoding and intrinsics

Differential Revision: http://reviews.llvm.org/D10796

llvm-svn: 240926
 2015-06-29 09:10:00 +00:00
Ahmed Bougacha f1eccbecf8 [X86] Accept hasAVX512() as well as hasFMA() when generating FMA. 
We don't always have FMA, for example when using 'clang -mavx512f'
without an explicit CPU.

Also check for an explicit +avx512f instead of CPUs in a couple
related tests.

llvm-svn: 240616
 2015-06-25 00:44:46 +00:00
Elena Demikhovsky d8fda62247 AVX-512: blank lines, duplicated tests, no functional changes 
see comments http://reviews.llvm.org/D6835

llvm-svn: 233528
 2015-03-30 09:29:28 +00:00
Elena Demikhovsky 7b0dd39db6 AVX-512: Added FMA intrinsics with rounding mode 
By Asaf Badouh and Elena Demikhovsky

Added special nodes for rounding: FMADD_RND, FMSUB_RND..
It will prevent merge between nodes with rounding and other standard nodes.

llvm-svn: 227303
 2015-01-28 10:21:27 +00:00
Elena Demikhovsky fcea06acb5 AVX-512: Added FMA instructions, intrinsics an tests for KNL and SKX targets 
by Asaf Badouh

http://reviews.llvm.org/D6456

llvm-svn: 224764
 2014-12-23 10:30:39 +00:00
Adam Nemet 241c3252c3 [AVX512] Add test for FMA masking instrinsics 
llvm-svn: 215665
 2014-08-14 17:13:33 +00:00
Adam Nemet 6fa675754a [AVX512] Switch FMA intrinsics to the masking version 
This does the renaming and updates the lowering logic.

Part of <rdar://problem/17688758>

llvm-svn: 215664
 2014-08-14 17:13:30 +00:00
Cameron McInally ad41f1f693 Add AVX512 unmasked FMA intrinsics and support. 
llvm-svn: 194824
 2013-11-15 17:01:14 +00:00