[PATCH] D16252: AMDGPU: Reduce 64-bit lshr by constant to 32-bit

[Tom Stellard via llvm-commits]

tstellarAMD accepted this revision.
tstellarAMD added a comment.
This revision is now accepted and ready to land.

With those fixed, LGTM.


================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2567-2569
@@ +2566,5 @@
+
+  SDValue Vec = DAG.getNode(ISD::BUILD_VECTOR, SL, MVT::v2i32, Zero, Lo);
+  return DAG.getNode(ISD::BITCAST, SL, MVT::i64, Vec);
+}
+
----------------
Was this change meant for another commit?

================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2584-2586
@@ +2583,5 @@
+
+  // srl (i64 x), C for C >= 32
+  // =>
+  //   build_pair (srl (i32 hi_32(x)), (C - 32), 0)
+
----------------
The parentheses in this comment should be fixed to make it less confusing.


http://reviews.llvm.org/D16252