aboutsummaryrefslogtreecommitdiff
path: root/flang/lib/Frontend/CompilerInvocation.cpp
diff options
context:
space:
mode:
authorDhruva Chakrabarti <Dhruva.Chakrabarti@amd.com>2023-06-30 14:02:12 -0400
committerDhruva Chakrabarti <Dhruva.Chakrabarti@amd.com>2023-06-30 15:05:01 -0400
commit6a1d1f7eefe81faa1f7c6c47e8b9da0bfeb8c2e8 (patch)
tree5a980932d23fa84fbba1327814455d61fc04155b /flang/lib/Frontend/CompilerInvocation.cpp
parent917eddfdcb15bddf67a54ede1f1643d5fc83628d (diff)
downloadllvm-6a1d1f7eefe81faa1f7c6c47e8b9da0bfeb8c2e8.zip
llvm-6a1d1f7eefe81faa1f7c6c47e8b9da0bfeb8c2e8.tar.gz
llvm-6a1d1f7eefe81faa1f7c6c47e8b9da0bfeb8c2e8.tar.bz2
[OpenMP] Added memory scope to atomic::inc API and used the device scope in reduction.
With https://reviews.llvm.org/D137524, memory scope and ordering attributes are being used to generate the required instructions for atomic inc/dec on AMDGPU. This patch adds the memory scope attribute to the atomic::inc API and uses the device scope in reduction. Without the device scope in atomic_inc, the default system scope leads to unnecessary L2 write-backs/invalidates. Reviewed By: arsenm Differential Revision: https://reviews.llvm.org/D154172
Diffstat (limited to 'flang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions