Add SobelFilter to SVE microbenchmark

[ylpoonlg]

Performance Results

Run on Neoverse-V2

Method	Size	Mean	Error	StdDev	Median	Min	Max	Allocated
Scalar	9	106.89 ns	0.027 ns	0.023 ns	106.89 ns	106.86 ns	106.94 ns	-
Vector128SobelFilter	9	47.21 ns	0.007 ns	0.006 ns	47.21 ns	47.20 ns	47.22 ns	-
SveSobelFilter	9	28.89 ns	0.134 ns	0.125 ns	28.81 ns	28.77 ns	29.07 ns	-
Scalar	64	7,125.25 ns	2.823 ns	2.503 ns	7,124.19 ns	7,122.83 ns	7,130.43 ns	-
Vector128SobelFilter	64	1,255.35 ns	0.913 ns	0.854 ns	1,255.21 ns	1,254.21 ns	1,256.87 ns	-
SveSobelFilter	64	1,339.70 ns	0.280 ns	0.219 ns	1,339.65 ns	1,339.41 ns	1,340.14 ns	-
Scalar	527	507,148.17 ns	324.567 ns	287.720 ns	507,050.40 ns	506,733.19 ns	507,636.12 ns	-
Vector128SobelFilter	527	73,998.18 ns	166.540 ns	147.634 ns	73,971.34 ns	73,795.42 ns	74,256.96 ns	-
SveSobelFilter	527	100,770.21 ns	1,836.759 ns	1,628.239 ns	100,470.79 ns	96,333.15 ns	103,294.79 ns	-

cc @dotnet/arm64-contrib @SwapnilGaikwad @LoopedBard3

[LoopedBard3]

Looks good, thanks for the benchmarks!

[Copilot]

Pull request overview

Adds a new SVE-focused microbenchmark for a 2D Sobel filter convolution, enabling comparison of scalar vs AdvSimd (Vector128) vs SVE implementations on Arm64/SVE-capable systems.

Changes:

• Introduces SobelFilter microbenchmark with Scalar, Vector128SobelFilter, and SveSobelFilter benchmarks.
• Adds setup/verification scaffolding and Sobel kernel initialization for repeatable runs.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

[LoopedBard3]

Looks great! Thank you for the tests.