port SpanHelpers.IndexOfAny(ref byte, byte, byte, byte, int) to Vector128/256

[adamsitnik]

The perf is on par for both x64 and arm64.

Details

BenchmarkDotNet=v0.13.1.1828-nightly, OS=ubuntu 20.04
Unknown processor
.NET SDK=7.0.100-rc.1.22405.1
  [Host]     : .NET 7.0.0 (7.0.22.40308), Arm64 RyuJIT AdvSIMD
  Job-NXYOFV : .NET 7.0.0 (42.42.42.42424), Arm64 RyuJIT AdvSIMD
  Job-PVCGZI : .NET 7.0.0 (42.42.42.42424), Arm64 RyuJIT AdvSIMD

Method	Toolchain	Size	Mean	Ratio
IndexOfAnyTwoValues	/PR/corerun	512	37.13 ns	0.98
IndexOfAnyTwoValues	/main/corerun	512	37.98 ns	1.00

BenchmarkDotNet=v0.13.1.1828-nightly, OS=Windows 11 (10.0.22000.795/21H2)
AMD Ryzen Threadripper PRO 3945WX 12-Cores, 1 CPU, 24 logical and 12 physical cores
.NET SDK=7.0.100-preview.7.22377.5
  [Host]     : .NET 7.0.0 (7.0.22.37506), X64 RyuJIT AVX2
  Job-MXBRWB : .NET 7.0.0 (42.42.42.42424), X64 RyuJIT AVX2
  Job-ABDMTJ : .NET 7.0.0 (42.42.42.42424), X64 RyuJIT AVX2

Method	Toolchain	Size	Mean	Ratio
IndexOfAnyTwoValues	\PR\corerun.exe	512	8.696 ns	1.03
IndexOfAnyTwoValues	\baseline\corerun.exe	512	8.475 ns	1.00

It's the last SpanHelper method from the #64451 TODO list!

[ghost]

Tagging subscribers to this area: @dotnet/area-system-memory
See info in area-owners.md if you want to be subscribed.

Issue Details

---

The perf is on par for both x64 and arm64.

Details

BenchmarkDotNet=v0.13.1.1828-nightly, OS=ubuntu 20.04
Unknown processor
.NET SDK=7.0.100-rc.1.22405.1
  [Host]     : .NET 7.0.0 (7.0.22.40308), Arm64 RyuJIT AdvSIMD
  Job-NXYOFV : .NET 7.0.0 (42.42.42.42424), Arm64 RyuJIT AdvSIMD
  Job-PVCGZI : .NET 7.0.0 (42.42.42.42424), Arm64 RyuJIT AdvSIMD

Method	Toolchain	Size	Mean	Ratio
IndexOfAnyTwoValues	/PR/corerun	512	37.13 ns	0.98
IndexOfAnyTwoValues	/main/corerun	512	37.98 ns	1.00

BenchmarkDotNet=v0.13.1.1828-nightly, OS=Windows 11 (10.0.22000.795/21H2)
AMD Ryzen Threadripper PRO 3945WX 12-Cores, 1 CPU, 24 logical and 12 physical cores
.NET SDK=7.0.100-preview.7.22377.5
  [Host]     : .NET 7.0.0 (7.0.22.37506), X64 RyuJIT AVX2
  Job-MXBRWB : .NET 7.0.0 (42.42.42.42424), X64 RyuJIT AVX2
  Job-ABDMTJ : .NET 7.0.0 (42.42.42.42424), X64 RyuJIT AVX2

Method	Toolchain	Size	Mean	Ratio
IndexOfAnyTwoValues	\PR\corerun.exe	512	8.696 ns	1.03
IndexOfAnyTwoValues	\baseline\corerun.exe	512	8.475 ns	1.00

It's the last SpanHelper method from the #64451 TODO list!

Author:	adamsitnik
Assignees:	-
Labels:	area-System.Memory, tenet-performance
Milestone:	7.0.0

[tannergooding]

Just noting that its somewhat unfortunate we're only testing 512 for this test and others. It means we're not seeing numbers for other interesting sizes. In particular, I'd think that most powers of 2 from 8-512 are interesting to look at when making such changes and I'd expect that inputs under 64-bytes might see a regression, but that its an overall acceptable tradeoff.