commit | 12216172c04fe76a90e9de34fc4161e92d097278 | [log] [tgz] |
---|---|---|
author | Craig Topper <craig.topper@gmail.com> | Fri Jan 13 08:12:35 2012 +0000 |
committer | Craig Topper <craig.topper@gmail.com> | Fri Jan 13 08:12:35 2012 +0000 |
tree | 6015625f4477bedeb225a8509b1726a279102b80 | |
parent | db080e814fcc2b67e2790351539053c8b9d13639 [diff] |
Make X86 instruction selection use 256-bit VPXOR for build_vector of all ones if AVX2 is enabled. This gives the ExeDepsFix pass a chance to choose FP vs int as appropriate. Also use v8i32 as the type for getZeroVector if AVX2 is enabled. This is consistent with SSE2 using prefering v4i32. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148108 91177308-0d34-0410-b5e6-96231b3b80d8