[llvm] [AMDGPU] Insert waitcnt for non-global fence release in GFX12 (PR #159282)
Sameer Sahasrabuddhe via llvm-commits
llvm-commits at lists.llvm.org
Sun Sep 21 22:34:23 PDT 2025
================
@@ -2522,8 +2522,7 @@ bool SIGfx12CacheControl::insertRelease(MachineBasicBlock::iterator &MI,
// sequentially consistent, and no other thread can access scratch
// memory.
- // Other address spaces do not have a cache.
- if ((AddrSpace & SIAtomicAddrSpace::GLOBAL) == SIAtomicAddrSpace::NONE)
+ if (AddrSpace == SIAtomicAddrSpace::SCRATCH)
return false;
----------------
ssahasra wrote:
The original code had an early return on a negative condition which matched the one in `insertAcquire()`. Why change it and move all the code inside a positive condition? That seems to have introduced a lot of whitespace noise due to reindentation.
https://github.com/llvm/llvm-project/pull/159282
More information about the llvm-commits
mailing list