[PATCH] D33367: [AMDGPU] Narrow lshl from 64 to 32 bit if possible

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2622
+    KnownBits Known;
+    SDValue X = LHS->getOperand(0);
+    DAG.computeKnownBits(X, Known);
----------------
vpykhtin wrote:
> What type is expected for X? I mean, can it be 16 or 8 bit type?
An arbitrary type is accepted, it does work with any.


Repository:
  rL LLVM

https://reviews.llvm.org/D33367