diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2020-05-14 08:33:59 -0400 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2020-05-14 08:36:03 -0400 |
| commit | 26e742fd848b27ff925eab23e4d2a5675b418721 (patch) | |
| tree | af00fb934d67c452231a00930719783df697fbc0 /llvm/lib/Bitcode/Reader/BitcodeReader.cpp | |
| parent | c5ff4031c6d1dd20e9b9a4929f537a1e50bcf76c (diff) | |
[x86][CGP] improve sinking of splatted vector shift amount operand
Expands on the enablement of the shouldSinkOperands() TLI hook in:
D79718
The last codegen/IR test diff shows what I suspected could happen - we were
sinking all splat shift operands into a loop. But that's not what we want in
general; we only want to sink the *shift amount* operand if it is a splat.
Differential Revision: https://reviews.llvm.org/D79827
Diffstat (limited to 'llvm/lib/Bitcode/Reader/BitcodeReader.cpp')
0 files changed, 0 insertions, 0 deletions