# Whats the effect of CUDA-aware MPI?

**URL:** <https://pyfr.discourse.group/t/whats-the-effect-of-cuda-aware-mpi/140>\
**Category:** General\
**Created:** [28 February 2017 22:41 UTC](https://pyfr.discourse.group/t/whats-the-effect-of-cuda-aware-mpi/140 "2017-02-28T22:41:10Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Robert\_Sawko1](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@Robert\_Sawko1](https://pyfr.discourse.group/u/Robert_Sawko1)\
**Post date:** [28 February 2017 22:41 UTC](https://pyfr.discourse.group/t/whats-the-effect-of-cuda-aware-mpi/140/1 "2017-02-28T22:41:10Z")

</div>

Hello,

I have a quick exploratory question. At the moment our clusters have mvapich2  
installed but it appears to me that none of them is an MPI-aware version. I was  
just curious if anyone has already looked into potential performance benefits  
when using CUDA-aware MPIs. I realize it's a new feature in your code and I am  
also happy to act as a beachhead user.

Please let me know.

Best wishes,  
Robert

---

<div class="post-metadata">

**Author:** ![fdw](https://avatars.discourse-cdn.com/v4/letter/f/a587f6/32.png) [@fdw](https://pyfr.discourse.group/u/fdw)\
**Post date:** [2 March 2017 22:54 UTC](https://pyfr.discourse.group/t/whats-the-effect-of-cuda-aware-mpi/140/2 "2017-03-02T22:54:15Z")

</div>

Hi Robert,

To the best of my knowledge the most work on this area has been done by Filippo Spiga at Cambridge. If I recall (his findings were the subject of a GTC talk back in 2015 and should be available online) he found that using CUDA aware MPI did show an improvement in terms of the strong scalability of PyFR with performance improving by 10% or so in the limit. He also considered the impact of GPU direct over RDMA.

Regards, Freddie.