[PATCH] D61830: [X86][SSE] Disable shouldFoldConstantShiftPairToMask for scalar shifts on AMD targets (PR40758)

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon marked an inline comment as done.
RKSimon added inline comments.


================
Comment at: lib/Target/X86/X86.td:430
 
+def FeatureFastScalarShiftMasks
+    : SubtargetFeature<
----------------
lebedev.ri wrote:
> This is talking about 'scalar', but the hook is '..Constant..'.
> This target feature is not specifically about fast shifts by immediate?
The scalar/vector feature flags indicate that shifts have a similar throughput to ANDs


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61830/new/

https://reviews.llvm.org/D61830