Comment by mattip
3 years ago
If you find your bottlenecks in SciPy or Numpy, then PyPy will not help. Those are primarily written in C, so the PyPy JIT cannot peer inside and do any magic.
3 years ago
If you find your bottlenecks in SciPy or Numpy, then PyPy will not help. Those are primarily written in C, so the PyPy JIT cannot peer inside and do any magic.
My effort was rather in trying to speed up all the python looping, etc. around the np calls. But I never went far trying to actually benchmark the entire pipeline in order to find out what was the actual bottleneck.