commit | 4fee3cff4d923744aa87dd87175a8b6f91deb4a0 | [log] [tgz] |
---|---|---|
author | Neil Henning <neil.henning@amd.com> | Mon Feb 11 14:44:14 2019 +0000 |
committer | Neil Henning <neil.henning@amd.com> | Mon Feb 11 14:44:14 2019 +0000 |
tree | e1a2f9ba68b7627c38b610905b093d56dd028be6 | |
parent | 45caba411d27a8f2d42e7471b67fe25d0e1dd464 [diff] |
[AMDGPU] Fix DPP sequence in atomic optimizer. This commit fixes the DPP sequence in the atomic optimizer (which was previously missing the row_shr:3 step), and works around a read_register exec bug by using a ballot instead. Differential Revision: https://reviews.llvm.org/D57737 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@353703 91177308-0d34-0410-b5e6-96231b3b80d8