[PATCH] D149488: [RISCV] Use AMOSWAP for 32 and 64-bit atomic stores

[Paul Kirth via Phabricator via llvm-commits]

paulkirth added inline comments.


================
Comment at: llvm/lib/Target/RISCV/RISCVISelLowering.cpp:15057
+  if (auto *SI = dyn_cast<StoreInst>(I))
+    return !canAmoSwapStoreInst(SI);
+  return false;
----------------
paulkirth wrote:
> @jrtc27  Maybe we should forgo the optimization when forced atomics are used? As you've pointed out there seem to be some unintended interactions in that configuration.
oh, this is the wrong place anyway, so ignore my suggestion


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149488/new/

https://reviews.llvm.org/D149488