Low level profiling for onnxrt Conv kernel(default backend)

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

https://onnxruntime.ai

MIT License

13.96k stars 2.82k forks source link

Low level profiling for onnxrt Conv kernel(default backend) #11702

Open Darshvino opened 2 years ago

Darshvino commented 2 years ago

Hi,

I want to do the low-level profiling for onnxrt Conv kernel(default backend), is there any way that I can do that to get the hotspots, cache access, etc.? It would be very helpful for me.

Thank you

Darshvino commented 2 years ago

Look forward to the reply