| commit | 8177aafa74993a25caef8c9a54f41ea1d7c6163d | [log] [tgz] |
|---|---|---|
| author | Mark Searles <m.c.searles@gmail.com> | Mon Jun 04 16:51:59 2018 +0000 |
| committer | Mark Searles <m.c.searles@gmail.com> | Mon Jun 04 16:51:59 2018 +0000 |
| tree | 058ad8bad7cda6e51ec277576cc73e30adf06683 | |
| parent | 9d0b6a4e21f54b63a19918ca1be3e8c36f43c152 [diff] |
[AMDGPU][Waitcnt] Fix handling of flat instrs On GFX9 and earlier, flat memory ops may decrement VMCNT out-of-order as well as LGKMCNT out-of-order. Differential Revision: https://reviews.llvm.org/D46616 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@333926 91177308-0d34-0410-b5e6-96231b3b80d8