https://bugs.llvm.org/show_bug.cgi?id=38497
Bug ID: 38497
Summary: Merge r339316 into the 7.0 branch: [NVPTX] Select
atomic loads and stores
Product: libraries
Version: 7.0
Hardware: All
OS: All
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: PTX
Assignee: unassignedb...@nondot.org
Reporter: hah...@hahnjo.de
CC: llvm-bugs@lists.llvm.org
I'm aware that this was no "classical" regression, so feel free to close if
deemed invalid. That said, the commit fixes a pretty annoying compiler crash
when using most atomic operations in an OpenMP target region offloaded to
Nvidia GPUs. For more details please refer to
https://reviews.llvm.org/rL339316.
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
