diff options
| author | Craig Topper <craig.topper@intel.com> | 2017-12-21 20:45:13 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2017-12-21 20:45:13 +0000 |
| commit | 32c9aed373b988066f2608c215ccb694df029650 (patch) | |
| tree | 211931c2f066283947c9d4cbdcf38bdbae4c925b /test/Analysis/BasicAA/cs-cs.ll | |
| parent | bd4e6fc5e7d023ff3ef0f2bd1b4c232dab2de1cd (diff) | |
[X86] When lowering truncates to vXi1, don't sign extend i16/i8 types to 512-bit if we have VLX.
This should only affect what we do for v8i16. Previously we went to v8i64, but if we have VLX we only need v8i32. This prevents an unnecessary zmm usage.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@321303 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Analysis/BasicAA/cs-cs.ll')
0 files changed, 0 insertions, 0 deletions