[PATCH] D123221: [X86] `lowerBuildVectorAsBroadcast()`: with AVX512VL, allow i64 broadcasts from constant pool

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:9507
+    if (ScalarSize == 32 ||
+        (ScalarSize == 64 && (IsGE256 || Subtarget.hasAVX512())) ||
         (ScalarSize == 16 && Subtarget.hasFP16() && CVT.isFloatingPoint()) ||
----------------
RKSimon wrote:
> I think you need hasVLX() not hasAVX512() - that should fix the KNL (AVX512F only) regressions
D'oh. Thanks!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D123221/new/

https://reviews.llvm.org/D123221