11 Commits

Author SHA1 Message Date
NAKAMURA Takumi
598658d792 Fix warnings discovered by rL317076. [-Wunused-private-field]
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317091 91177308-0d34-0410-b5e6-96231b3b80d8
2017-11-01 13:47:55 +00:00
Evgeny Mankov
cb139f4145 [AMDGPU] NFC: test commit
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@311019 91177308-0d34-0410-b5e6-96231b3b80d8
2017-08-16 16:47:29 +00:00
Eugene Zelenko
5ca94f31ee [AMDGPU] Fix some Clang-tidy modernize-use-using and Include What You Use warnings; other minor fixes (NFC).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@310328 91177308-0d34-0410-b5e6-96231b3b80d8
2017-08-08 00:47:13 +00:00
Matt Arsenault
3ff37decad AMDGPU: Partially fix improper reliance on memoperands
There are 2 more places doing this, but I'm not sure
what they are doing and don't make any sense to me

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308770 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-21 18:54:54 +00:00
Matt Arsenault
ecba33a1f4 AMDGPU: Don't track lgkmcnt for global_/scratch_ instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@308766 91177308-0d34-0410-b5e6-96231b3b80d8
2017-07-21 18:34:51 +00:00
Mark Searles
cc713d1bdd [AMDGPU] Fix uninit'ed var (RevisitLoop)
Differential Revision: https://reviews.llvm.org/D33907

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@304729 91177308-0d34-0410-b5e6-96231b3b80d8
2017-06-05 19:29:01 +00:00
Konstantin Zhuravlyov
e0fcf72467 AMDGPU: Make auto waitcnt before barrier a feature
Differential Revision: https://reviews.llvm.org/D33793


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@304571 91177308-0d34-0410-b5e6-96231b3b80d8
2017-06-02 17:40:26 +00:00
Mark Searles
fa784827e1 [AMDGPU] Fix bugs in new waitcnt pass. Add test.
- new waitcnt pass remains off by default; -enable-si-insert-waitcnts=1 to enable it
- fix handling of PERMUTE ops
- fix insertion of waitcnt instrs at function begin/end ( port of analogous code that was added to old waitcnt pass )
- add new test

  Differential Revision: https://reviews.llvm.org/D33114

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@304311 91177308-0d34-0410-b5e6-96231b3b80d8
2017-05-31 16:44:23 +00:00
Kannan Narayanan
96d48fac54 [AMDGPU] In the new waitcnt insertion pass, use getHeader
instead of getTopBlock to find the loop header.

Differential Revision: https://reviews.llvm.org/D32831



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@302290 91177308-0d34-0410-b5e6-96231b3b80d8
2017-05-05 21:10:17 +00:00
Krzysztof Parzyszek
36d7c2b2e5 Move size and alignment information of regclass to TargetRegisterInfo
1. RegisterClass::getSize() is split into two functions:
   - TargetRegisterInfo::getRegSizeInBits(const TargetRegisterClass &RC) const;
   - TargetRegisterInfo::getSpillSize(const TargetRegisterClass &RC) const;
2. RegisterClass::getAlignment() is replaced by:
   - TargetRegisterInfo::getSpillAlignment(const TargetRegisterClass &RC) const;

This will allow making those values depend on subtarget features in the
future.

Differential Revision: https://reviews.llvm.org/D31783


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301221 91177308-0d34-0410-b5e6-96231b3b80d8
2017-04-24 18:55:33 +00:00
Kannan Narayanan
d3302ddc52 [AMDGPU] Add a new pass to insert waitcnts. Leave under an option for testing.
Based on comments in https://reviews.llvm.org/D31161.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@300023 91177308-0d34-0410-b5e6-96231b3b80d8
2017-04-12 03:25:12 +00:00