[PATCH] D32831: [AMDGPU] In the new waitcnt insertion pass, use getHeader instead of getTopBlock to find the loop header.

Kannan Narayanan via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed May 3 16:25:39 PDT 2017


kanarayan updated this revision to Diff 97741.
kanarayan added a comment.

Updated to the correct test with loop.

I have not removed the metadata but cleaned up others. How do you run the instanter?


https://reviews.llvm.org/D32831

Files:
  lib/Target/AMDGPU/SIInsertWaitcnts.cpp
  test/CodeGen/AMDGPU/waitcnt-looptest.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D32831.97741.patch
Type: text/x-patch
Size: 15875 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170503/52f79b80/attachment.bin>


More information about the llvm-commits mailing list