[PATCH] D67841: [SLP] avoid reduction transform on patterns that the backend can load-combine

[Alexey Bataev via Phabricator via llvm-commits]

ABataev added inline comments.


================
Comment at: llvm/include/llvm/CodeGen/BasicTTIImpl.h:1698
+  ///       may not be necessary.
+  llvm::Optional<int> getLoadCombineCost(Value *V) {
+    using namespace llvm::PatternMatch;
----------------
Shall we just terminate the reduction of this special construct unconditionally? Do we need this cost calculation just to prevent the reduction all the time we see this pattern? If yes, then, probably, we don't need to calculate the cost.
There is a function `isTreeTinyAndNotFullyVectorizable()`. Can you put pattern matching analysis for this particular construct in this function without any additional cost analysis?


================
Comment at: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp:6504-6505
     case RK_Arithmetic:
-      ScalarReduxCost =
-          TTI->getArithmeticInstrCost(ReductionData.getOpcode(), ScalarTy);
+      if (ReductionData.getOpcode() == Instruction::Or)
+        LoadCombineCost = TTI->getLoadCombineCost(FirstReducedVal);
+      if (LoadCombineCost) {
----------------
Maybe better to put the check for the operation into the function itself?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D67841/new/

https://reviews.llvm.org/D67841