[Openmp-commits] [PATCH] D145831: [OpenMP][libomptarget] Add support for critical regions in AMD GPU device offloading

[Gheorghe-Teodor Bercea via Phabricator via Openmp-commits]

doru1004 added inline comments.


================
Comment at: openmp/libomptarget/DeviceRTL/src/Synchronization.cpp:283
+  if (mapping::getThreadIdInWarp() == LowestActiveThread) {
+    fenceKernel(atomic::release);
+    while (!atomicCAS((uint32_t *)Lock, UNSET, SET, atomic::relaxed,
----------------
dhruvachak wrote:
> Why do we need the release fence in setLock before the CAS?
You have to release all of the ordinary stores before you write to the lock.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D145831/new/

https://reviews.llvm.org/D145831