[PATCH] D40373: [x86][icelake]GFNI

[coby via Phabricator via llvm-commits]

coby added inline comments.


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:19568
     case INTR_TYPE_2OP_MASK:
+    case INTR_TYPE_2OP_MASKZ:
     case INTR_TYPE_2OP_IMM8_MASK: {
----------------
craig.topper wrote:
> craig.topper wrote:
> > I have trouble believing you need a 2OP_MASKZ. Can't the caller pass the zero vector to the mask version like we do for everything else? The reason we have OP3_MASKZ is because the OP3_MASK uses the passthru input in both the select op and the operation. So we needed a separate intrinsic to define the zero semantics of the select independent of the operation.
> sorry that should have said FMA_MASKZ not OP3_MASKZ.
interesting
is this logic applies to anywhere else a MASKZ variant is being used?
nevertheless you are correct, i'll remove the (self) added Z variants


Repository:
  rL LLVM

https://reviews.llvm.org/D40373