forked from OSchip/llvm-project
e5dfb08fcb
This change adds a new hook for estimating the cost of vector extracts followed by zero- and sign-extensions. The motivating example for this change is the SMOV and UMOV instructions on AArch64. These instructions move data from vector to general purpose registers while performing the corresponding extension (sign-extend for SMOV and zero-extend for UMOV) at the same time. For these operations, TargetTransformInfo can assume the extensions are free and only report the cost of the vector extract. The SLP vectorizer has been updated to make use of the new hook. Differential Revision: http://reviews.llvm.org/D18523 llvm-svn: 267725 |
||
|---|---|---|
| .. | ||
| commute.ll | ||
| gather-reduce.ll | ||
| getelementptr.ll | ||
| horizontal.ll | ||
| lit.local.cfg | ||
| load-store-q.ll | ||
| minimum-sizes.ll | ||
| mismatched-intrinsics.ll | ||
| nontemporal.ll | ||
| sdiv-pow2.ll | ||