[Example] FPS drops when integrate refactored BaseRunner.js

[ibelem]

When trying to integrate @BruceDai's latest refactored BaseRunner.js, the FPS drops 2 (9->7) in WebNN meeting (Deeplab 257 Atrous) on i7-6700 + Ubuntu desktop.

This issue also occurs on WebML SS Examples (Linux Laptop). Good news is the inference time is faster than before.

Full Screen (WebNN SS Examples)	Before Refactor	Before Refactor	After Refactor	After Refactor
	Inference Time(ms)	FPS	Inference Time(ms)	FPS
DeepLab 224	52.72	16	48.18	12 (25% ↓)
DeepLab 257 Atrous	45.92	17	41.75	12 (30% ↓)

[BruceDai]

The root cause was that converting inputTensor of none typedArray to inputTensor of specified typedArray consumed some timing.

    tensorArray = getTensorArray(src, options);

    const typedArray = this._getInputTensorTypedArray();
    this._inputTensor = [new typedArray(tensorArray)]; # This converting will consume some timing

Full Screen (WebNN SS Examples)	Before fixing	After fixing
	FPS	FPS
DeepLab 224	12	16
DeepLab 257 Atrous	12	17

The inference time after fixing were similar to ones before refactoring.

[huningxin]

Thanks for documenting the root cause. So the learning is to avoid creating typed array in hot loop, is that correct?

[BruceDai]

I did type converting by

typedArray(tensorArray)

Here tensorArray is just an array from

new Array([size])

it's not ArrayBuffer type, while 'typedArray ' could be Float32Array or Uint8Array on condition.

We need avoid to type converting for those array of large size in hot loop on Camera scene , thanks @huningxin

[huningxin]

Creation of typed array from array is expensive. Thanks for fixing that.