From ab97c9bdb747c873cd35a18229e2694156a7607d Mon Sep 17 00:00:00 2001 From: David Green Date: Sat, 12 Dec 2020 14:21:40 +0000 Subject: [PATCH] [LV] Fix scalar cost for tail predicated loops When it comes to the scalar cost of any predicated block, the loop vectorizer by default regards this predication as a sign that it is looking at an if-conversion and divides the scalar cost of the block by 2, assuming it would only be executed half the time. This however makes no sense if the predication has been introduced to tail predicate the loop. Original patch by Anna Welker Differential Revision: https://reviews.llvm.org/D86452 --- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 7 ++++--- llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index c381377..663ea50 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -6483,9 +6483,10 @@ LoopVectorizationCostModel::expectedCost(ElementCount VF) { // if-converted. This means that the block's instructions (aside from // stores and instructions that may divide by zero) will now be // unconditionally executed. For the scalar case, we may not always execute - // the predicated block. Thus, scale the block's cost by the probability of - // executing it. - if (VF.isScalar() && blockNeedsPredication(BB)) + // the predicated block, if it is an if-else block. Thus, scale the block's + // cost by the probability of executing it. blockNeedsPredication from + // Legal is used so as to not include all blocks in tail folded loops. + if (VF.isScalar() && Legal->blockNeedsPredication(BB)) BlockCost.first /= getReciprocalPredBlockProb(); Cost.first += BlockCost.first; diff --git a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll index 959fbe6..fc8ea4f 100644 --- a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll @@ -15,7 +15,7 @@ define void @pred_loop(i32* %off, i32* %data, i32* %dst, i32 %n) #0 { ; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %add1, i32* %arrayidx2, align 4 ; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction: %exitcond.not = icmp eq i32 %add, %n ; CHECK-COST-NEXT: LV: Found an estimated cost of 0 for VF 1 For instruction: br i1 %exitcond.not, label %exit.loopexit, label %for.body -; CHECK-COST-NEXT: LV: Scalar loop costs: 2. +; CHECK-COST-NEXT: LV: Scalar loop costs: 5. entry: %cmp8 = icmp sgt i32 %n, 0 -- 2.7.4