An array implementation (based on NumPy.ndarray) for GPU devices. For more information please refere to the gpuarray homepage
Questions tagged [gpuarray]
14 questions
5
votes
0 answers
Theano - pyGpuArray can't find libnvrtc.so
I recently changed config in order to train CNN's faster.
I got a gtx 1080.
For most of my existing neural nets, I'm using the theano back-end through python3.
Since I've read that pascal architecture wasn't fully used through CUDA 7.5, I've…
Axel Paccalin
- 136
- 1
- 13
3
votes
1 answer
Explanation of requirement from inputs to GPU computations having complex results
Consider this line of code:
gpuArray(-1)^0.5;
Which results in:
ans =
0.0000 + 1.0000i
Now consider the following line of code:
gpuArray(-1).^0.5;
Which results in:
Error using .^
POWER: needs to return a complex result, but this is not…
Dev-iL
- 23,742
- 7
- 57
- 99
3
votes
0 answers
Setting the path to CUDA in THEANO_FLAGS
I try to set the THEANO_FLAGS and then import Theano. This always results in an error.
In [1]: import os
In [2]: os.environ["THEANO_FLAGS"] = "cuda.root=/usr/local/cuda,device=cuda,floatX=float32"
In [3]: import theano
ERROR (theano.gpuarray):…
Andy
- 1,072
- 2
- 19
- 33
2
votes
1 answer
Converting all variables into gpuArrays doesn't speed up computation
I'm writing simulation with MATLAB where I used CUDA acceleration.
Suppose we have vector x and y, matrix A and scalar variables dt,dx,a,b,c.
What I found out was that by putting x,y,A into gpuArray() before running the iteration and built-in…
J C
- 181
- 7
1
vote
1 answer
How to use GPU to calculate double integral using Matlab
I want to implement a double integral using gpuArray in Matlab and plot my result as a 2D image of 128x128 points. I found the example shared by Joss Knight in Mathworks under the tag: “How to use GPU to calculate double integral with multivariable…
1
vote
1 answer
Possible to speed up this gpuArray calculation with arrayfun() (or otherwise)?
I have a complex matrix A, and would like to modify it Nt times according to A = exp( -1i*(A + abs(A).^2) ). The size of A is typically 1000x1000, and the number of times to run would be around 10000.
I am looking to reduce the time taken to carry…
teeeeee
- 641
- 5
- 15
1
vote
0 answers
pyCuda and gpuarray.maximum differs from numpy
Perhaps I'm missing something. I'm using pycuda and I have the following matrix m_gpu:
>>> m_gpu
array([[ 0., 2., 4., 1., 3.],
[ 2., 0., 5., 2., 1.],
[ 4., 5., 0., 3., 2.],
[ 1., 2., 3., 0., 4.],
[ 3., 1., 2., 4., 0.]],…
Al5678
- 117
- 2
- 10
1
vote
0 answers
Matlab pdist2 and mvnpdf with gpuArray
I have trouble using the pdist2 or mvnpdf functions of the Statistics and Machine Learning Toolbox with gpuArrays, although its explicitly stated that it should…
Daniel
- 31
- 2
0
votes
2 answers
How to construct a matrix from selected columns of a 3D array?
I have a 3D GPU array A with dimensions K x M x N and an int vector v of length M and want to construct 2D GPU arrays of the form
X = [A(:,1,v(1)), A(:,2,v(2)),..., A(:,M,v(M))] (depending on v)
in the most time-efficient way. Since all these are…
M.G.
- 293
- 1
- 13
0
votes
0 answers
How to evaluate a very complicated function on GPU Using MATLAB
I have a very Complicated symbolic function in Matlab and I want to evaluate it on GPU.
As I searched, for evaluation, we need to use gpuArray but when I try to evaluate function on GPU matlab using this code :
joint_pdf_function_handle =…
Captain
- 193
- 1
- 10
0
votes
0 answers
How to monitor GPU Usage in Matlab
I have a question about using the GPU in Matlab.
I followed a simple code for the code running on GPU on the Matlab website
But when I run the code and I check the CPU and GPU simultaneously, I see that the code runs on CPU instead of GPU!…
Captain
- 193
- 1
- 10
0
votes
1 answer
Is it possible to preallocate an array using gpuArray, and have write permission to it in a mexcuda setup?
I have written a piece of code in MatLab (2018a) that is a hybrid between standard matlab code and CUDA code, which I have linked using compilation with mexcuda. The core loop in my code contains an interpolation of a matrix, say from size [n x m]…
Floris
- 508
- 2
- 9
0
votes
1 answer
Problems with Theano installation using CUDA when using non-root user
I have followed the instructions to install Theano an GPUArray from source (git versions), in the system folders (not as a user). The GPUArray tests run just fine without errors.
The problem is Theano only works with GPU if I run as root. Running…
rll
- 5,509
- 3
- 31
- 46
-1
votes
1 answer
is using gpuArray instead of array in matlab more performant?
If i use any function in the list at the following link:
Run Built-In Functions on a GPU
with the argument being of the type gpuArray instead of array, will the result be computed faster? If the answer is yes, is there some case where it is more…
gibarsin
- 151
- 4
- 13