# Back and forth transfer of data between GPU neural net and CPU simulation

**URL:** <https://discourse.julialang.org/t/back-and-forth-transfer-of-data-between-gpu-neural-net-and-cpu-simulation/24328>\
**Category:** GPU\
**Tags:** performance, flux\
**Created:** [May 17, 2019, 2:51pm UTC](https://discourse.julialang.org/t/back-and-forth-transfer-of-data-between-gpu-neural-net-and-cpu-simulation/24328 "2019-05-17T14:51:13Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![HenriDeh](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/henrideh/32/8316_2.png) [@HenriDeh](https://discourse.julialang.org/u/HenriDeh)\
**Post date:** [May 17, 2019, 2:51pm UTC](https://discourse.julialang.org/t/back-and-forth-transfer-of-data-between-gpu-neural-net-and-cpu-simulation/24328/1 "2019-05-17T14:51:13Z")

</div>

Hello,

I have a neural network that interacts with a simulation. To accelerate its training, the network is transfered to my GPU. I implemented my simulation as a structure that handles other structures. In my toy example below, understand my SimEnvironment as the simulation structure of some sort of factory. I want to produce something to increase the level (currentlevel) but the production is limited by the capacity of a set of machines. Information is a vector that the nn is supposed to use to compute the production quantity.

To make this work I have to transfer the information vector to the gpu so that my network can read it and compute an output (prod). To execute the action decide by the nn, I have to transfer the prod vector back to the gpu. This back and forth transfer is not efficient but I don’t think it would work better to do the simulation on the GPU, would it ? Is there some kind of guidelines to improve these sorts of interactions ?

```julia
nn = Chain(Dense(3,1)) |> gpu

mutable struct Machine
    capacity::Float32
end

mutable struct SimEnvironment
    machines::Array{Machine,1}
    currentlevel::Float32
    information::Array{Float32}
end

sim = SimEnvironment([Machine(5.0f0), Machine(7.0f0)], 0.0f0, [4.0f0, 90.0f0, 10.0f0])

function produce!(sim::SimEnvironment, production::Array{Float32,1})
    production[1] = min(production[1], getfield.(sim.machines, :capacity)...)
    sim.currentlevel += production[1]
end

input = sim.information |> gpu
prod = nn(input) |> cpu
produce!(sim, prod)

```