Supercharging the TensorFlow.js WebAssembly backend with SIMD and multi-threading — The TensorFlow Blog
TensorFlow.js version 2.3.0, our Wasm backend has become up to 10X faster by leveraging SIMD (vector) instructions and multithreading via XNNPACK, a highly optimized library of neural network operators. BlazeFace
a light model with 0.1 million parameters and about 20 million multiply-add operations:
WebGLより早い
MobileNet V2
medium-sized model with 3.5 million parameters and roughly 300 million multiply-add operation
これでもWebGL同等