mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-22 22:01:08 +00:00
e803f8eb0f
We submit kernels in a batch (a fixed number 16 is used except for the last batch) for better performance. However, timestamp query support is at pass level so we disable the batch execution in profiling mode in previous implementation. Actually we can have multiple passes in a batch so that we don't have to disable batch execution, which is the first enhancement of this PR. Furthermore, WebGPU has an extension to support timestamp query inside passes, which isn't supported by all the platforms (e.g., Windows supports it, while macOS doesn't). This is expected to have lower cost compared with multiple passes solution. So this PR also introduce this support when available. This PR also refactors some implementation related to kernelInfo, and try to unify the related kernel names. |
||
|---|---|---|
| .. | ||
| backend-impl.ts | ||
| backend.ts | ||
| env-impl.ts | ||
| env.ts | ||
| index.ts | ||
| inference-session-impl.ts | ||
| inference-session.ts | ||
| onnx-model.ts | ||
| onnx-value.ts | ||
| tensor-conversion-impl.ts | ||
| tensor-conversion.ts | ||
| tensor-factory-impl.ts | ||
| tensor-factory.ts | ||
| tensor-impl-type-mapping.ts | ||
| tensor-impl.ts | ||
| tensor-utils-impl.ts | ||
| tensor-utils.ts | ||
| tensor.ts | ||
| trace.ts | ||
| training-session-impl.ts | ||
| training-session.ts | ||
| version.ts | ||