summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp')
-rw-r--r--llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp14
1 files changed, 10 insertions, 4 deletions
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 99428c6c5de..75b4718392d 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -6981,10 +6981,16 @@ bool SLPVectorizerPass::vectorizeGEPIndices(BasicBlock *BB, BoUpSLP &R) {
LLVM_DEBUG(dbgs() << "SLP: Analyzing a getelementptr list of length "
<< Entry.second.size() << ".\n");
- // We process the getelementptr list in chunks of 16 (like we do for
- // stores) to minimize compile-time.
- for (unsigned BI = 0, BE = Entry.second.size(); BI < BE; BI += 16) {
- auto Len = std::min<unsigned>(BE - BI, 16);
+ // Process the GEP list in chunks suitable for the target's supported
+ // vector size. If a vector register can't hold 1 element, we are done.
+ unsigned MaxVecRegSize = R.getMaxVecRegSize();
+ unsigned EltSize = R.getVectorElementSize(Entry.second[0]);
+ if (MaxVecRegSize < EltSize)
+ continue;
+
+ unsigned MaxElts = MaxVecRegSize / EltSize;
+ for (unsigned BI = 0, BE = Entry.second.size(); BI < BE; BI += MaxElts) {
+ auto Len = std::min<unsigned>(BE - BI, MaxElts);
auto GEPList = makeArrayRef(&Entry.second[BI], Len);
// Initialize a set a candidate getelementptrs. Note that we use a
OpenPOWER on IntegriCloud