diff options
| author | Thomas Raoux <thomasraoux@google.com> | 2020-03-30 10:36:21 -0700 |
|---|---|---|
| committer | Thomas Raoux <thomasraoux@google.com> | 2020-03-30 11:27:09 -0700 |
| commit | 3ea0774b13a538759aa1a68f30130d18ddb0d3f2 (patch) | |
| tree | f19bd3ecf25f6fd958a60bc909e185b98b4eea2f /llvm/lib/IR/Instructions.cpp | |
| parent | 8242509a49e019c0279305d152c7ab2b9cdc2d0d (diff) | |
| download | llvm-3ea0774b13a538759aa1a68f30130d18ddb0d3f2.zip llvm-3ea0774b13a538759aa1a68f30130d18ddb0d3f2.tar.gz llvm-3ea0774b13a538759aa1a68f30130d18ddb0d3f2.tar.bz2 | |
[ConstantFold][NFC] Compile time optimization for large vectors
Optimize the common case of splat vector constant. For large vector
going through all elements is expensive. For splatr/broadcast cases we
can skip going through all elements.
Differential Revision: https://reviews.llvm.org/D76664
Diffstat (limited to 'llvm/lib/IR/Instructions.cpp')
| -rw-r--r-- | llvm/lib/IR/Instructions.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp index 0884a24..f6748c8 100644 --- a/llvm/lib/IR/Instructions.cpp +++ b/llvm/lib/IR/Instructions.cpp @@ -1958,7 +1958,11 @@ void ShuffleVectorInst::getShuffleMask(const Constant *Mask, assert(!Mask->getType()->getVectorElementCount().Scalable && "Length of scalable vectors unknown at compile time"); unsigned NumElts = Mask->getType()->getVectorNumElements(); - + if (isa<ConstantAggregateZero>(Mask)) { + Result.resize(NumElts, 0); + return; + } + Result.reserve(NumElts); if (auto *CDS = dyn_cast<ConstantDataSequential>(Mask)) { for (unsigned i = 0; i != NumElts; ++i) Result.push_back(CDS->getElementAsInteger(i)); |