Optimize "(vec & cns) == zero" on arm64 #102705
Conversation
|
Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch |
|
@EgorBot -arm64 -profiler using BenchmarkDotNet.Attributes;
using System.Buffers;
using System.Text;
using BenchmarkDotNet.Running;
BenchmarkRunner.Run<Perf_Ascii>(args: args);
[DisassemblyDiagnoser(maxDepth: 5)]
public class Perf_Ascii
{
byte[] _bytes = new byte[128];
char[] _characters = new char[128];
[Benchmark]
public OperationStatus ToUtf16() => Ascii.ToUtf16(_bytes, _characters, out _);
} |
Results on Arm64
See BDN_Artifacts.zip for details. 🔥ProfilerFlame graphs: Main vs PR (interactive!) NotesFor clean |
| // If op is "vec & cnsVec" where both u64 components in that cnsVec are the same (for both SIMD12 and | ||
| // SIMD16) then we'd better do this AND on top of TYP_LONG NI_AdvSimd_Extract in the end - it produces a | ||
| // more optimal codegen. | ||
| if (op->OperIsHWIntrinsic(NI_AdvSimd_And) && op->AsHWIntrinsic()->Op(2)->OperIs(GT_CNS_VEC)) |
There was a problem hiding this comment.
This doesn't have to be a constant right?
Just any (x & y) == zero or (x & y) != zero can be optimzied down to a tst (on both xarch and arm64).
|
Draft Pull Request was automatically closed for 30 days of inactivity. Please let us know if you'd like to reopen it. |
|
Blocks #105047. |
|
Draft Pull Request was automatically closed for 30 days of inactivity. Please let us know if you'd like to reopen it. |
Fixes #100922 regression - it was regressed by #99982
Main:
PR: