Benchmark a KleidiAI micro-kernel in ExecuTorch
Introduction
Set up your environment
Cross-Compile ExecuTorch for the AArch64 platform
Accelerate ExecuTorch operators with KleidiAI micro-kernels
Create and quantize linear layer benchmark model
Create and quantize convolution layer benchmark model
Create matrix multiply layer benchmark model
Run model and generate the ETDump
Analyze ETRecord and ETDump
Next Steps
Benchmark a KleidiAI micro-kernel in ExecuTorch
Introduction
Set up your environment
Cross-Compile ExecuTorch for the AArch64 platform
Accelerate ExecuTorch operators with KleidiAI micro-kernels
Create and quantize linear layer benchmark model
Create and quantize convolution layer benchmark model
Create matrix multiply layer benchmark model
Run model and generate the ETDump
Analyze ETRecord and ETDump
Next Steps
Review frequently asked questions
These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
Yes. Keep your virtual environment active so build and runtime dependencies install and import from the same isolated location.
Verify the device supports SME or SME2. Also confirm that you deploy the AArch64 ExecuTorch binaries and libraries produced by cross-compilation.
The guide benchmarks an INT8-quantized Conv2d variant using
pqs8_qc8w_gemm. It also benchmarks a FP32 pointwise (1×1) Conv2d variant using pf32_gemm.Model export creates an
ETRecord file alongside the .pte model. executor_runner writes an ETDump file. Use the matching files with the ExecuTorch Inspector API to analyze kernel behavior.The guide exports FP16, FP32, INT8, and INT4 linear-model variants. It also exports FP16 and FP32 matrix-multiply models for comparison.