Answered
GPU: Iteratively adding 2D gaussians to a 2D array
You are already getting a lot of data parallelism out of what you have - you are performing multiple element-wise operations on ...

10 years ago | 0

| accepted

Answered
Can I speed up big matrix operation with Parallel computing toolbox?
It looks like you've misunderstood how to use the Parallel Computing Toolbox's parallel pools. Once you've opened a pool, you ne...

10 years ago | 0

Answered
failed to attach matlab in Visual Studio 2010 in order to debug cuda kernel
Debugging kernels from Nsight and Visual Studio using Attach to Process is difficult to get right. I've done my best to come up ...

10 years ago | 0

Answered
Odd Profiler GPU Bug?
When you have the profiler on (from MATLAB R2015a onwards), to get realistic timings the GPU is forced to run synchronously. ...

10 years ago | 0

Answered
gpuArray with besselj for non-integral order values
This is a limitation of the NVIDIA libraries MATLAB uses to compute the bessel functions.

10 years ago | 0

| accepted

Answered
CUDA and Matlab on Linux : mexcuda not working
I believe this is due to missing C++ libraries that aren't linked by default by |mexcuda| because they can cause issues with |nv...

10 years ago | 0

Answered
Vectorization of for loop (indexing of a vector)
first = gpuArray.colon(1,n); indexA = bsxfun(@plus, first, [0:9]'); indexB = indexA + 16; A = vector_1(indexA); B ...

10 years ago | 0

| accepted

Answered
GPU computing on macbook pro with intel graphics card
MathWorks has no current plans to provide |gpuArray| support for Intel GPUs. It would be useful to know what is the main barrier...

10 years ago | 0

Answered
Anyone can help me to benchmark this code on high end GPU (CUDA)?
I was able to get your images to display at 30Hz with the help of a Tesla K20c. I can't get any faster than that because the res...

10 years ago | 1

| accepted

Answered
Why does my code only run slightly faster on GPU than CPU?
Your real problem here? You're not processing enough data at once. If I reduce the paging factor |nBlock| I could process more d...

10 years ago | 2

Answered
CUDA and Matlab on mac: mex command not working
I can see that this code on File Exchange brings with it its own copies of the CUDA MEX options files for each platform ('mex_fi...

10 years ago | 1

Answered
Rules of thumb on GPU usage?
You ought to provide some examples so that we know the kind of thing you're getting at. The main rule of thumb is that the GP...

10 years ago | 1

Answered
Detect when no GPU is selected
You can query device properties without selecting it using |parallel.gpu.GPUDevice.getDevice|. So, for instance, you can find th...

10 years ago | 2

| accepted

Answered
MATLAB doesn't recognize GPU NVIDIA GeForce 310M?
Your GPU does not appear to be on the <https://developer.nvidia.com/cuda-gpus CUDA-enabled GPU list>, so it would appear not to ...

10 years ago | 0

Answered
Matlab GPU use with functions that take arguments of different dimensions
<http://www.mathworks.com/help/distcomp/pagefun.html |pagefun|> is what you're looking for. With it you can batch vector and mat...

10 years ago | 2

Answered
How to compile a MEX file containing CUDA code, without using "mexcuda"
|mexcuda| was released in R2015b. Before this compiling GPU |mex| code was perfectly possible, but you needed to follow the proc...

10 years ago | 4

10 years ago | 0

Answered
Iterative solver with gpuArray
If you download the R2015b release of MATLAB (released on 3rd September) you will find that |gmres| is now supported for sparse ...

10 years ago | 0

Answered
Concurrent write to gpuArray
In short, no, not in MATLAB code. |arrayfun| has to write one value per thread to a separate output address. Write a CUDAKernel ...

10 years ago | 0

Answered
Solving Ax=b on Multiple GPUs
There are some mistakes in your timing here. |tic| and |toc| don't work in a nested way, |toc| just times from the most recent |...

10 years ago | 0

Answered
Many small Eigenvalue Decompositions in parallel on GPU?
Have you tried just concatenating your matrices in block-diagonal form and calling |eig|? You may then be limited by memory, but...

10 years ago | 3

Answered
"Partial" matrix multiplication
If you're running this on a GPU using Parallel Computing Toolbox, as you say, then you can use |pagefun|: rows = size(A,1);...

10 years ago | 0

Answered
solving Ax=b in parallel using GPU cores
If you can form a dense |A| then do so. Then call x = gpuArray(A) \ b; If you need A to remain a function (perhaps it is...

11 years ago | 1

11 years ago | 1

Answered
Not able to Compile a GPU MEX-File
Hi, you need to install the CUDA toolkit matching your version of MATLAB. gpu = gpuDevice; gpu.ToolkitVersion At the ...

11 years ago | 0

Answered
Is it possible to locally distribute an array for GPU processing?
If you have multiple GPUs you can perform independent computation on each one using a parallel pool, see here for instance: http...

11 years ago | 0

Answered
Running scripts in parallel on the GPU
Short answer: You can't, |arrayfun| is for functions with elementwise operations only. Long answer: If you pass |x| and |y| a...

11 years ago | 0

Answered
.cu file not execute in command window
Please follow the documented instructions for authoring and compiling MEX functions in MATLAB: <http://www.mathworks.com/help...

11 years ago | 0

Answered
Is there a way to test gpu functions on a computer without a gpu card?
No, I'm afraid not. The only thing you can really do is to run the code on the CPU and check that works. Ideally your MATLAB cod...

11 years ago | 0

Answered
Any way to configure GPU-based FFT library (fft/ifft) to free memory after call?
What version of MATLAB are we talking about here? And how are you determining whether memory was freed or not? R2014a and ear...

11 years ago | 1

| accepted