[PATCH] D136244: [AArch64] Optimize memcmp when the result is tested for [in]equality with 0

[Eli Friedman via Phabricator via llvm-commits]

efriedma added inline comments.


================
Comment at: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp:19468
+  // cmp A0, A0; ccmp A0, B1, 0, eq; cmp inv(CB) flag
+  // Skip BRCOND as it may be combined with others operand.
+  if (!DCI.isBeforeLegalize() && VT.isScalarInteger() &&
----------------
Leftover comment about brcond


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D136244/new/

https://reviews.llvm.org/D136244