diff options
Diffstat (limited to 'llvm/lib/Transforms/Vectorize')
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp | 12 |
1 files changed, 9 insertions, 3 deletions
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index c0c2c85b8f4..72fc9cf41ef 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -6105,6 +6105,9 @@ public: unsigned ReduxWidth = PowerOf2Floor(NumReducedVals); Value *VectorizedTree = nullptr; + + // FIXME: Fast-math-flags should be set based on the instructions in the + // reduction (not all of 'fast' are required). IRBuilder<> Builder(cast<Instruction>(ReductionRoot)); FastMathFlags Unsafe; Unsafe.setFast(); @@ -6294,11 +6297,14 @@ private: assert(isPowerOf2_32(ReduxWidth) && "We only handle power-of-two reductions for now"); - if (!IsPairwiseReduction) + if (!IsPairwiseReduction) { + // FIXME: The builder should use an FMF guard. It should not be hard-coded + // to 'fast'. + assert(Builder.getFastMathFlags().isFast() && "Expected 'fast' FMF"); return createSimpleTargetReduction( Builder, TTI, ReductionData.getOpcode(), VectorizedValue, - ReductionData.getFlags(), FastMathFlags::getFast(), - ReductionOps.back()); + ReductionData.getFlags(), ReductionOps.back()); + } Value *TmpVec = VectorizedValue; for (unsigned i = ReduxWidth / 2; i != 0; i >>= 1) { |
