# How to make a GPU socket multiple cpu cores?

**URL:** <https://forums.developer.nvidia.com/t/how-to-make-a-gpu-socket-multiple-cpu-cores/51974>\
**Category:** CUDA Programming and Performance\
**Created:** [July 26, 2017, 8:28am UTC](https://forums.developer.nvidia.com/t/how-to-make-a-gpu-socket-multiple-cpu-cores/51974 "2017-07-26T08:28:29Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jhuang008](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Jhuang008](https://forums.developer.nvidia.com/u/Jhuang008)\
**Post date:** [July 26, 2017, 8:28am UTC](https://forums.developer.nvidia.com/t/how-to-make-a-gpu-socket-multiple-cpu-cores/51974/1 "2017-07-26T08:28:29Z")

</div>

Hi, I recently tried to program with pycuda + CUDA8.0 + mpi4py,and I found that my desktop (with 1 i7 4770 and 1 GTX 1080)computing faster than the school’s HPC platform(with 2 Xeon E5-2660 v3 and 2 Tesla K80),We think this is because the performance of a single CPU core of E5-2660 v3 is not as good as i7 4770 and one GPU defaults to socket one CPU core. So,the question is how can I get an mpi process to call a GPU and multiple CPU cores?