# Question about CUDA-aware MPI
**URL:** https://discourse.julialang.org/t/question-about-cuda-aware-mpi/37487
**Category:** GPU
**Created:** [April 13, 2020, 4:29am UTC](https://discourse.julialang.org/t/question-about-cuda-aware-mpi/37487 "2020-04-13T04:29:52Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@marius311](https://discourse.julialang.org/u/marius311)
#### Post date: [April 13, 2020, 4:29am UTC](https://discourse.julialang.org/t/question-about-cuda-aware-mpi/37487/1 "2020-04-13T04:29:53Z")
I’d like to make sure I understand how Julia hooks in to CUDA-aware MPI. Basically, is it true that when send/receiving Julia objects which may have a CuArray somewhere in them, that the CuArray is never moved to the CPU, and instead passed from GPU to GPU?
Here’s an example script:
```julia
using MPI
MPI.Init()
using CuArrays
using CUDAdrv
using CUDAnative
comm = MPI.COMM_WORLD
rank = MPI.Comm_rank(comm)
device!(rank)
@info "MPI process $rank is using $(device())"
if rank == 0
dat = (x = cu(ones(4,4)),)
MPI.send(dat, 1, 0, comm)
else
dat, = MPI.recv(0, 0, comm)
@show dat
end
```
When I `mpiexec -n 2` this script on a machine with 2 GPUs, does the CuArray inside `dat` ever have to go through CPU? Is there a way to check? Thanks.
---
### Author:  [@vchuravy](https://discourse.julialang.org/u/vchuravy)
#### Post date: [April 17, 2020, 2:25pm UTC](https://discourse.julialang.org/t/question-about-cuda-aware-mpi/37487/2 "2020-04-17T14:25:00Z")
There is no easy way to check :), but the fact that your code runs without crashing is a good indication.
I am not sure we are handling the situation where a CuArray is wrapped in a tuple right now…,
The current version of MPI.jl has a `MPI.has_cuda()` function with which you can check the availability of CUDA-aware MPI.
A good indication is to use the nvidia system profiler with the MPI integration and check whether or not you are seeing unnecessary copies to the host.