Cinder: Instagram's performance-oriented fork of CPython

Re:Cinder: Instagram's performance-oriented fork of CPython by FartyMcFarter on Wednesday May 05, 2021 @05:45AM (#27047967)

> It's easy to forget that CPython is not that optimised generally,

"Not that optimised" is actually an understatement. In my experience, CPU-heavy code typically becomes 10-100x faster if you port it from Python to a language like C (without even trying to be clever or using SIMD assembly).

[ Parent | on HN ]

Re:Cinder: Instagram's performance-oriented fork of CPython by stevesimmons on Wednesday May 05, 2021 @08:03AM (#27048827)

Often you can put a "@numba.jit" decorator at the top of a calc-heavy function, and reclaim a good portion of C's performance.

It is so simple it is definitely worth trying.

I did it for Bloom tree implementation, and got to within around 3x of the C code it replaced.

[ Parent | on HN ]