Add trace event control for ORT Web performance profiling #23393
Conversation
|
@microsoft-github-policy-service agree company="Intel" |
|
@Honry Please help review this PR, thanks~ |
| @@ -37,6 +42,11 @@ common::Status DataTransfer::CopyTensor(const Tensor& src, Tensor& dst) const { | |||
| } | |||
| } | |||
|
|
|||
| if (trace) { | |||
| console.call<void>("timeEnd", emscripten::val("ORT::DataTransfer::CopyTensor")); | |||
There was a problem hiding this comment.
Do you want to distinguish the tensor downloading and tensor uploading? If so, you can add event tracing to both if and else branch.
There was a problem hiding this comment.
tensor downloading and uploading can be distinguished through MLContext::writeTensor and MLContenxt::readTensor event in tracing, so i simply add this trace event for both tensor downloading and uploading.
| @@ -178,6 +183,9 @@ onnxruntime::common::Status Model::Dispatch(const InlinedHashMap<std::string, On | |||
| promises.call<void>("push", ml_tensor); | |||
| } | |||
| auto ml_tensors = emscripten::val::global("Promise").call<emscripten::val>("all", promises).await(); | |||
There was a problem hiding this comment.
I'd suggest just adding the console.time before this line, Promise.all is the major time consumer for constructing the ml tensors.
There was a problem hiding this comment.
We can get a high level view of time spending before wasm Dispatch API call if Promise.all is included.
Description
Add trace event control to better profile ORT web performance
Motivation and Context
ORT Web's current tracing implementation lacks interfaces for performance profiling using about://tracing. This PR introduces these interfaces, enabling performance bottleneck identification in ORT Web and adding several trace events for WebNN.