[PATCH] D60897: [SLP] Look-ahead operand reordering heuristic.

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: lib/Transforms/Vectorize/SLPVectorizer.cpp:760
+      if (LI1 && LI2)
+        return (isConsecutiveAccess(LI1, LI2, DL, SE))
+                   ? VLOperands::ScoreConsecutiveLoads
----------------
(style) remove outer brackets


================
Comment at: lib/Transforms/Vectorize/SLPVectorizer.cpp:773
+        InstructionsState S = getSameOpcode({I1, I2});
+        if (S.getOpcode())
+          return (I1 == I2) ? VLOperands::ScoreSplat
----------------
What happens in the case where we have alt opcodes? Should we have a preference for all the same opcode vs with alt-opcode? Sometimes the alt-opcodes will fold away (shl + mul etc.) - other times it won't (shl + lshr).


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60897/new/

https://reviews.llvm.org/D60897