diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-06-05 10:52:29 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2018-06-05 10:52:29 +0000 |
| commit | fef9b6eea63b095ac32526342d45d726f6704050 (patch) | |
| tree | c0008825a721a0e344ea462ed81de16f1470fe67 /llvm/tools/llvm-exegesis/lib/BenchmarkResult.cpp | |
| parent | df4ca0eeda482f651cdc2b1bfe44bcd939ba756e (diff) | |
| download | bcm5719-llvm-fef9b6eea63b095ac32526342d45d726f6704050.tar.gz bcm5719-llvm-fef9b6eea63b095ac32526342d45d726f6704050.zip | |
[X86][SSE] Add target shuffle support to X86TargetLowering::computeKnownBitsForTargetNode
Ideally we'd use resolveTargetShuffleInputs to handle faux shuffles as well but:
(a) that code path doesn't handle general/pre-legalized ops/types very well.
(b) I'm concerned about the compute time as they recurse to calls to computeKnownBits/ComputeNumSignBits which would need depth limiting somehow.
llvm-svn: 334007
Diffstat (limited to 'llvm/tools/llvm-exegesis/lib/BenchmarkResult.cpp')
0 files changed, 0 insertions, 0 deletions
