Ningxin Hu
Ningxin Hu
> In the new version Na is working on, we first compile and link everything without waiting because they are async, and then check and wait everything at the end,...
@juj , thanks for the spreadsheet. It is very informative! I happened to work on JS-SIMD in emscripten a bit. As my understanding, emscripten generates SIMD.js code from 1) LLVM...
> So, when Emscripten+OdinMonkey are ready to rock some intersection-style SIMD together (and this is coming soon!), we'll compile some code and do some hopefully realistic benchmarking So excited about...
Side note, I tried the bullet3 SSE path (native) on Linux before. However I didn't get good speedup there. See https://github.com/bulletphysics/bullet3/issues/66 for details.
According to IE doc, [Add](https://docs.openvinotoolkit.org/latest/_docs_ops_arithmetic_Add_1.html) and [Multiply](https://docs.openvinotoolkit.org/latest/_docs_ops_arithmetic_Multiply_1.html) support broadcasting. We may need to revisit #751 and #725.
Thanks @fujunwei for bringing this point. It would be good that you can elaborate the design of this change.
Thanks. Could you make a PR for code review?
@NALLEIN , could you please send a PR to preview your change?
@NALLEIN , I just checked with @axinging , if you have any new ops implementation for TF.js WebGPU backend, please feel free to submit your PR to TF.js repo. If...
Generally WebNN uses channel-last layout, OpenVINO uses channel-first layout. Could you please share what are the shapes (convolution, reshape, permute) when you run it with webml-polyfill?