[PATCH] D149638: [AArch64] Handle VECTOR_SHUFFL mask with splats

[Eli Friedman via Phabricator via llvm-commits]

efriedma added a comment.

When I was mentioning the testcases in D149638 <https://reviews.llvm.org/D149638>, I was think of cases like test11 in build-vector-two-dup.ll.  For values already in vector registers, replacing a tbl with three shuffle instructions probably isn't an improvement (particularly on newer cores where tbl is fast).


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149638/new/

https://reviews.llvm.org/D149638