Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> difficult to use heavy computation libraries

what do you mean? What's the blocker? Something like numpy for js would fill this role, calling wasm in the background. Just the missing SIMD-instructions? Some quick googling shows that one can't compile BLAS for wasm yet. This might be due to wasm64 not being available yet, i think? So would this help to tap into the existing ecosystem of optimised mathematical routines?

Ideally...I would leave js and just use python ;) It has the whole ecosystem at hands with numpy, scipy, statsmodels etc. But nobody is doing it and idk why. I think it might be due to fortran not compiling to wasm.



Yes I forgot about wasm64 not being available still. Yes, that's a big block.

About numpy for js I believe js is still not comfortable enough for this kind of use, especially with the lack of operator overloading.

Anyway there are some builds of BLAS (or equivalents) to wasm and even of python. Check out pyodide and brython




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: