[PATCH] D131964: [AArch64] Add support to loop vectorization for non temporal loads

[Dave Green via Phabricator via llvm-commits]

dmgreen added inline comments.


================
Comment at: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h:325
+  bool isLegalNTLoad(Type *DataType, Align Alignment) {
+    if (auto *DataTypeTy = dyn_cast<VectorType>(DataType)) {
+      unsigned NumElements =
----------------
This can be `dyn_cast<FixedVectorType>`, which avoids the need for the cast<..> below. The same thing can be done above in isLegalNTStore too.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D131964/new/

https://reviews.llvm.org/D131964