Use the GPU during optimisation



  • Hello,
    does anyone knows if it is possible to use the GPU during the optimisation ?
    I have seen the parameter maxcpu but I don't if it include GPU.
    https://www.backtrader.com/docu/optimization-improvements.html


  • administrators

    The optimization is based on the standard multiprocessing module.

    Moving that to the GPU would require for example adding PyCuda. A quick glance at the documentation shows that code has to be written specifically for it. It is not simply meant to replace multiprocessing

    An alternative would be to use numba for CUDA, which would require lots of decoration with unknown results. Furthermore the numba approach is probably numpy array centered and as such unlikely to produce a huge benefit given the non-use of numpy arrays.

    A migration to an architecture with underlying numpy arrays would be required. A possibility would be dask, which follows thepandas paradigms whilst at the same time allowing distribution and GPU usage (by means of numba)

    Short answer: no.



  • Thank you , My dream was it would be simple to implement . Now , back to the reality :) good night


Log in to reply
 

Looks like your connection to Backtrader Community was lost, please wait while we try to reconnect.