diff options
| author | Craig Topper <craig.topper@gmail.com> | 2020-02-09 18:35:57 -0800 |
|---|---|---|
| committer | Craig Topper <craig.topper@gmail.com> | 2020-02-09 20:39:52 -0800 |
| commit | 05d44204fa13767a366c37695c2131161158ea36 (patch) | |
| tree | 6a10024f1b2f6899cd90e7c3a73989743701e8dc /llvm/lib/CodeGen/MachineFunction.cpp | |
| parent | 64f417200e1020305f28f3c1e40691585f50f6ad (diff) | |
| download | llvm-05d44204fa13767a366c37695c2131161158ea36.zip llvm-05d44204fa13767a366c37695c2131161158ea36.tar.gz llvm-05d44204fa13767a366c37695c2131161158ea36.tar.bz2 | |
[X86] Use MOVZX instead of MOVSX in f16_to_fp isel patterns.
Using sign extend forces the adjacent element to either all zeros
or all ones. But all ones is a NAN. So that doesn't seem like a
great idea.
Trying to work on supporting this with strict FP where NAN would
definitely be bad.
Diffstat (limited to 'llvm/lib/CodeGen/MachineFunction.cpp')
0 files changed, 0 insertions, 0 deletions