diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-01-07 06:24:30 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-01-07 06:24:30 +0000 |
| commit | d0859a03b560629f58498d1346e1c47ae32c6cc1 (patch) | |
| tree | d8e85b0d69cd31d3c48c62db1fb023141eeae23a /llvm/test/Transforms/LoopVectorize/loop-form.ll | |
| parent | aa739411765ed97ebf818eb556eafce4d1055891 (diff) | |
| download | bcm5719-llvm-d0859a03b560629f58498d1346e1c47ae32c6cc1.tar.gz bcm5719-llvm-d0859a03b560629f58498d1346e1c47ae32c6cc1.zip | |
[X86] Correct the load folding flags for xmm fp->mmx conversion instructions.
The instructions that load 64-bits or an xmm register should be TB_NO_REVERSE to avoid the load being widened during unfold. The instructions that load 128-bits need to ensure 128-bit alignment.
llvm-svn: 321956
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/loop-form.ll')
0 files changed, 0 insertions, 0 deletions
