[llvm] 7fe4fa9 - [LV] Use onlyFirstLaneDemanded when widening pointer phis (NFCI).

[Florian Hahn via llvm-commits]

Author: Florian Hahn
Date: 2022-02-01T09:50:47Z
New Revision: 7fe4fa9a0a9b710b931887a9484ae09fb6323ca9

URL: https://github.com/llvm/llvm-project/commit/7fe4fa9a0a9b710b931887a9484ae09fb6323ca9
DIFF: https://github.com/llvm/llvm-project/commit/7fe4fa9a0a9b710b931887a9484ae09fb6323ca9.diff

LOG: [LV] Use onlyFirstLaneDemanded when widening pointer phis (NFCI).

This removes another instance of recipe execution still relying on
the cost model.

Depends on D116554.

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D116656

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 8e11f3de192f4..b0a316ffff8d6 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4502,7 +4502,7 @@ void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN,
       // Determine the number of scalars we need to generate for each unroll
       // iteration. If the instruction is uniform, we only need to generate the
       // first lane. Otherwise, we generate all VF values.
-      bool IsUniform = Cost->isUniformAfterVectorization(P, State.VF);
+      bool IsUniform = vputils::onlyFirstLaneUsed(PhiR);
       assert((IsUniform || !State.VF.isScalable()) &&
              "Cannot scalarize a scalable VF");
       unsigned Lanes = IsUniform ? 1 : State.VF.getFixedValue();