diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2021-07-26 11:11:56 +0100 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2021-07-26 11:11:56 +0100 |
| commit | c8472db0a88701e8c1b183d6568028fefc3406c0 (patch) | |
| tree | 1a174defcab35960d2547af87cd9f755fe50bfed /llvm/lib/CodeGen/MachineFunction.cpp | |
| parent | f64e251560203adf0258c96440c0cd637d3a43fc (diff) | |
| download | llvm-c8472db0a88701e8c1b183d6568028fefc3406c0.zip llvm-c8472db0a88701e8c1b183d6568028fefc3406c0.tar.gz llvm-c8472db0a88701e8c1b183d6568028fefc3406c0.tar.bz2 | |
[X86][AVX] Prefer vinsertf128 to vperm2f128 on AVX1 targets
Splatting the lower xmm with vinsertf128 is at least as quick as vperm2f128, and a lot faster on some AMD targets.
First step towards PR50053
Diffstat (limited to 'llvm/lib/CodeGen/MachineFunction.cpp')
0 files changed, 0 insertions, 0 deletions