[X86] Improve the AVX512 bailout in combineTruncateWithSat to allow pack...
[X86] Improve the AVX512 bailout in combineTruncateWithSat to allow pack instructions in more situations. If we don't have VLX we won't end up selecting a saturating truncate for 256-bit or smaller vectors so we should just use the pack lowering. llvm-svn: 374487
Loading
Please register or sign in to comment