diff options
| author | Craig Topper <craig.topper@gmail.com> | 2020-04-11 15:17:13 -0700 |
|---|---|---|
| committer | Craig Topper <craig.topper@gmail.com> | 2020-04-11 20:05:10 -0700 |
| commit | d3465e069127d95ac108636e008c513c924098dd (patch) | |
| tree | c129b2c1477494acbdb94f15eb487c4a44896dde /llvm/lib/Support/StringMap.cpp | |
| parent | 72ffeb2d38fb57995e904f02f86288b01ef73535 (diff) | |
| download | llvm-d3465e069127d95ac108636e008c513c924098dd.zip llvm-d3465e069127d95ac108636e008c513c924098dd.tar.gz llvm-d3465e069127d95ac108636e008c513c924098dd.tar.bz2 | |
[X86] Enable shuffle combining for AVX512 unless the root is used by a vselect
A lot of vectorized code doesn't use masks so we shouldn't penalize them by not doing shuffle combining on avx512 targets.
I've added support for VALIGNQ/VALIGND and 512-bit SHUF128 to prevent some regressions. I also prevented recombining 256-bit SHUF128 to PERM2X128. We may not need to add 256-bit SHUF128 support, but I don't think I found any cases requiring that in my testing.
Differential Revision: https://reviews.llvm.org/D77928
Diffstat (limited to 'llvm/lib/Support/StringMap.cpp')
0 files changed, 0 insertions, 0 deletions