forked from OSchip/llvm-project
6f732bfb79
Summary: Teach vectorizer about vectorizing variant value stores to uniform address. Similar to rL343028, we do not allow vectorization if we have multiple stores to the same uniform address. Cost model already has the change for considering the extract instruction cost for a variant value store. See added test cases for how vectorization is done. The patch also contains changes to the ORE messages. Reviewers: Ayal, mkuper, anemet, hsaito Subscribers: rkruppe, llvm-commits Differential Revision: https://reviews.llvm.org/D52656 llvm-svn: 344613 |
||
|---|---|---|
| .. | ||
| backward-dep-different-types.ll | ||
| forward-loop-carried.ll | ||
| forward-loop-independent.ll | ||
| independent-interleaved.ll | ||
| interleave-innermost.ll | ||
| memcheck-for-loop-invariant.ll | ||
| memcheck-off-by-one-error.ll | ||
| memcheck-wrapping-pointers.ll | ||
| multiple-strides-rt-memory-checks.ll | ||
| non-wrapping-pointer.ll | ||
| nullptr.ll | ||
| number-of-memchecks.ll | ||
| pointer-with-unknown-bounds.ll | ||
| pr31098.ll | ||
| resort-to-memchecks-only.ll | ||
| reverse-memcheck-bounds.ll | ||
| safe-no-checks.ll | ||
| safe-with-dep-distance.ll | ||
| store-to-invariant-check1.ll | ||
| store-to-invariant-check2.ll | ||
| store-to-invariant-check3.ll | ||
| stride-access-dependence.ll | ||
| underlying-objects-1.ll | ||
| underlying-objects-2.ll | ||
| unsafe-and-rt-checks.ll | ||
| wrapping-pointer-ni.ll | ||
| wrapping-pointer-versioning.ll | ||