Stack Overflow
Stack Overflow

Questions tagged [julia-gpu]

Questions pertaining to using julia-lang to interface with graphics processing units (GPUs)

24 questions
16
votes
1 answer

Minimum distances among a Euclidean distance matrix

I have some code that will calculate the distances between every Cartesian coordinate in one matrix to every other coordinate in another. For each coordinate, the minimum distance will be returned along with the index positions for the coordinates…
JJL
  • 342
  • 2
  • 17
12
votes
3 answers

Can I use Julia to program my GPU & CPU?

My system has graphics card. I do not play games. I want to program some high performance computing stuff for fun. Can I use JULIA lang to leverage my hardware?
suryakrupa
  • 3,852
  • 1
  • 25
  • 34
8
votes
2 answers

How to Synchronize with Julia CUDArt?

I'm just starting to use Julia's CUDArt package to manage GPU computing. I am wondering how to ensure that if I go to pull data from the gpu (e.g. using to_host()) that I don't do so before all of the necessary computations have been performed on…
Michael Ohlrogge
  • 10,559
  • 5
  • 48
  • 76
7
votes
2 answers

Julia: Parallel CUSPARSE calculations on multiple GPUs

I have n separate GPUs, each storing its own data. I would like to have each of them perform a set of calculations simultaneously. The CUDArt documentation here describes the use of streams to asynchronously call custom C kernels in order to…
Michael Ohlrogge
  • 10,559
  • 5
  • 48
  • 76
7
votes
2 answers

What does it mean to "finalize" in Julia?

I am currently working with the CUDArt package. The GitHub documentation includes the following snippet of code when loading a ptx module containing a custom CUDA C kernel: md = CuModule("mycudamodule.ptx", false) # false means it will not be…
Michael Ohlrogge
  • 10,559
  • 5
  • 48
  • 76
4
votes
1 answer

Options for GPU computing in Julia

I am considering buying a GPU card to experiment with GPU computing in Julia. As I see it now there are basically two options: NVIDIA or AMD chipsets. My question is: is there a recommended option for use with Julia? As I am new to GPU computing,…
InkPen
  • 197
  • 6
3
votes
1 answer

Correct way to generate Poisson-distributed random numbers in Julia GPU code?

For a stochastic solver that will run on a GPU, I'm currently trying to draw Poisson-distributed random numbers. I will need one number for each entry of a large array. The array lives in device memory and will also be deterministically updated…
physicsjoke
  • 31
  • 3
3
votes
1 answer

How can you animate a time-varying function using Makie's streamplot?

I've been trying to plot a simple function: v(x, y) = (y*t, 2*x*t) (actual implementation: v(x::Point2{T}, t) where T = Point2{T}(one(T) * x[2] * t, 4 * x[1])) using Makie's 2D streamplot function. While I can plot each timestep individually, by…
Anshul Singhvi
  • 1,692
  • 8
  • 20
3
votes
0 answers

Julia benchmarking DSP.jl, CUDANative and CuArrays

I'm experimenting with DSP.jl - the conv() method, in particular. I'm using CUDANative and CuArrays to create arrays to be arguments to conv(), so that the cuda versions of fft(), etc. will be used. I'm using BenchmarkTools to get performance data.…
user888379
  • 1,343
  • 12
  • 30
3
votes
1 answer

OpenCL BLAS in julia

I am really amazed by the julia language, having implemented lots of machine learning algorithms there for my current project. Even though julia 0.2 manages to get some great results out of my 2011 MBA outperforming all other solutuions on similar…
Terminus
  • 925
  • 10
  • 23
2
votes
1 answer

Problem installing MXNet.jl using Julia1.2 in UBUNTU 16.04

I am having some trouble installing "MXNet.jl" package in julia. 1) I first tryed typing: (v1.2) pkg> add MXNet and I get this: (v1.2) pkg> add MXNet Updating registry at `~/.julia/registries/General` Updating git-repo…
GEBRU
  • 495
  • 2
  • 11
2
votes
1 answer

Julia Flux double inference issue

Recently I found that Julia lang become more powerful and it's time to revisit it again. But in every tutorial, I found the same problem with double inference - for each batch you have to calculate the model to get gradients and then recalculate it…
Bogdan Ruzhitskiy
  • 1,167
  • 1
  • 12
  • 21
2
votes
1 answer

Limit GPU Memory in Julia using CuArrays

I'm fairly new to julia and I'm currently trying out some deep convolution networks with recurrent structures. I'm training the networks on a GPU using CuArrays(CUDA Version 9.0). Having two separate GPU's, I started two instances with different…
SeVe
  • 354
  • 1
  • 6
2
votes
0 answers

OpenCL not reading all data back to buffer

So I'm using the OpenCL API in Julia, and when I run the following code: using OpenCL device, context, queue = OpenCL.create_compute_context() a = rand(Float32, 125356789) abuf = OpenCL.Buffer(Float32, context, (:r, :copy), hostbuf=a) b =…
Set
  • 934
  • 6
  • 25
1
vote
0 answers

How to apply Cuda.jl on DataFrames in julia

I am using dataframes.jl package in the below mentioned code to perform certain operations. I would like to know, how may I apply CUDA.jl on this code, if possible while keeping the dataframe aspect? Secondly, is it possible to allow the code to…
Mohammad Saad
  • 1,935
  • 10
  • 28
1
2