[PATCH] D91255: [AArch64] Rearrange mul(dup(sext/zext)) to mul(sext/zext(dup))

[Dave Green via Phabricator via llvm-commits]

dmgreen accepted this revision.
dmgreen added a comment.
This revision is now accepted and ready to land.

Thanks. LGTM with a couple of suggestions.



================
Comment at: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp:11714
+
+  if (VectorShuffle.getOpcode() != ISD::VECTOR_SHUFFLE)
+    return SDValue();
----------------
You can probably remove this now and just rely on the dyn_cast<ShuffleVectorSDNode> check below.


================
Comment at: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp:11724
+  if (!ShuffleNode->isSplat() || ShuffleNode->getSplatIndex() != 0)
+    // Non-zero mask
+    return SDValue();
----------------
Maybe move this comment up above the if, to avoid the misleading indentation.


================
Comment at: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp:11733-11739
+  ConstantSDNode *Constant;
+  // Ensures the insert is inserting into lane 0
+  if (!(Constant = dyn_cast<ConstantSDNode>(InsertLane.getNode())))
+    return SDValue();
+
+  if (Constant->getZExtValue() != 0)
+    return SDValue();
----------------
Maybe something like this?
```
  // Ensures the insert is inserting into lane 0
  auto *Constant = dyn_cast<ConstantSDNode>(InsertLane.getNode());
  if (!Constant || Constant->getZExtValue() != 0)
    return SDValue();
```


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D91255/new/

https://reviews.llvm.org/D91255