[PATCH] D109963: [AArch64] Split bitmask immediate of bitwise AND operation

[JinGu Kang via Phabricator via llvm-commits]

jaykang10 added inline comments.


================
Comment at: llvm/test/CodeGen/AArch64/aarch64-split-and-bitmask-immediate.ll:132
+  %iv = phi i64 [ %inc, %for.inc ], [ 0, %loop.ph ]
+  %and = and i64 %a, 2098176
+  %cmp = icmp ult i64 %iv, %and
----------------
dmgreen wrote:
> I think Eli was referring to something like this: https://godbolt.org/z/YMYcqrroT
> Which may or may be meaningfully worse, depending on vectorizations and constant hoisting.
Ah, let me have a look.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D109963/new/

https://reviews.llvm.org/D109963