[PATCH] D144759: [AMDGPU] Implement idempotent atomic lowering

Thu Mar 2 11:43:01 PST 2023

rampitec added inline comments.

================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:13371-13377
+  // We do not need to insert a fence here, memory legalizer will do.
+  LoadInst *LI = Builder.CreateAlignedLoad(
+      AI->getType(), AI->getPointerOperand(), AI->getAlign());
+  LI->setAtomic(Order, SSID);
+  LI->copyMetadata(*AI);
+  LI->takeName(AI);
+  AI->replaceAllUsesWith(LI);
----------------
arsenm wrote:
> I don't understand why this is a target hook. Why can't this unconditionally happen in the generic code?
Probably not. The only target implementing it is x86 and it issues target specific intrinsics. It also skips 'or' with zero as it claims to have a better lowering.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144759/new/

https://reviews.llvm.org/D144759