Réponse apportée
FFT spread to multiple GPU's ?
I'm guessing you have a Quadro K120 GPU driving your graphics attached to your machine, or elsewhere on the PCI bus, is that pos...

presque 10 ans il y a | 0

Réponse apportée
Appropriate GPU card for FEM Simulation
For double precision computation you should use one of NVIDIA's Tesla series of cards intended for high performance compute. The...

presque 10 ans il y a | 1

| A accepté

Réponse apportée
Which version of Visual Studio is fully supported by Matlab with Cuda Coding?
Visual Studio 2012 and 2013 are supported in MATLAB R2016a and R2016b. These are the compilers that are supported by the CUDA co...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
CUDA 8.0, Pascal, in Ubuntu
It's not because of the toolkit you have installed, it's because you're using a Pascal card, which isn't supported by CUDA 7.5. ...

presque 10 ans il y a | 1

Réponse apportée
error LNK2019: unresolved external symbol when trying to MEX a C++ file containing CUDA
|mex| on its own does not automatically link in the CUDA libraries, so you will have to do that manually using |-lcublas| or sim...

presque 10 ans il y a | 0

Réponse apportée
Many function evaluation with GPU
The GPU can be used to run the same function simultaneously on a lot of data. If you wish to run different functions simultaneou...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
Compiling CUDA files with mexcuda - why wont Matlab accept my compiler?!
Hello Petter, CUDA 8.0 was only released last week! |mexcuda| doesn't yet support it, and consequently does not yet support V...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
error in working with SVD using GPUArray: GPU failed with CUDA error status: out of memory.
Your GPU doesn't have enough memory for this calculation. You need to reduce the size of your problem, do some algebra to divide...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
Issues with cnngpu.dll in NN toolbox
This is the unfortunate error message you get when you do not have Parallel Computing Toolbox and therefore cannot use the ConvN...

presque 10 ans il y a | 0

Réponse apportée
CUDA_ERROR_ILLEGAL_ADDRESS
Both these issues stem from the fact that Pascal architecture cards are not fully supported by the current CUDA toolkit. This me...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
pagefun makes an error
The corrected code is ans = sqrt(sum(b.*b, 1));

presque 10 ans il y a | 1

Réponse apportée
The trainNetwork does not work with Pascal GPU. What's the next step?
We have asked for a compatible version of cuDNN from NVIDIA with a backported fix. If they can provide that then we will provide...

presque 10 ans il y a | 4

| A accepté

Réponse apportée
Parallel matrix operations on GPU using arrayfun: why is it slower than looping, and/or is there a better method for coding this?
|arrayfun| IS just a loop, unless the inputs are |gpuArrays|. Your input isn't a |gpuArray|, because you've passed all your |gpu...

presque 10 ans il y a | 1

| A accepté

Réponse apportée
The training accuracy of "trainNetwork" decreases a lot when I used another computer
_NVIDIA_ doesn't support the latest NVIDIA GPU: <https://www.mathworks.com/support/bugreports/1439741> Sorry :-(

presque 10 ans il y a | 1

| A accepté

Réponse apportée
How do I estimate the memory usage of a calculation on the GPU?
Hi. |mldivide| is a very complicated calculation, so it's using a considerable amount of working memory. The code is complicated...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
[bug?]DeepLearningImageClassificationExample not getting the expected classification accuracy
Do you have a new Pascal GPU like the GeForce GTX 1080? If so, this is your issue: <https://www.mathworks.com/support/bugrepo...

presque 10 ans il y a | 0

| A accepté

Réponse apportée
Can I use gpuArrays inside spmd blocks
Have you tried? ;-) Yes, you can and it is advised. But if you only have one GPU and it's doing all the computation, you may not...

presque 10 ans il y a | 0

Réponse apportée
How I can solve this (error using gpuArray/gather occured during CUDA execution.TheCUDA error was:CUDA_ERROR_UNKNOWN).
It looks like you might be running out of GPU memory but it's not being reported properly. This sort of thing can happen on mobi...

environ 10 ans il y a | 0

Réponse apportée
MATLAB CUDA 8.0 compatibility
CUDA 8.0 hasn't been released yet, so your question is really one for NVIDIA! Past history says that a version of MATLAB will su...

environ 10 ans il y a | 1

Réponse apportée
Help with efficient collection of sub-matrices on GPU
You need to vectorize your indexing, then it will be efficient on the GPU. [offsetX, offsetY] = meshgrid(1:(2*halfPatch+1))...

environ 10 ans il y a | 0

Réponse apportée
Is it Possible to create a DLL from a .m-file containing GPU-Code (R2015a)
The answer is no, sorry. See <http://www.mathworks.com/matlabcentral/answers/290084-does-the-matlab-coder-support-gpuarray>.

environ 10 ans il y a | 0

Réponse apportée
cuda programming compiling and running the code in a remote machine
Do you mean a MEX function? If so you can compile your function on your laptop using |mex| <http://www.mathworks.com/help/releas...

environ 10 ans il y a | 0

Réponse apportée
Does the Matlab Coder support gpuArray?
No, sorry. Our GPU code is highly optimized for the devices we support and there isn't yet any such thing as a language that gen...

environ 10 ans il y a | 1

Réponse apportée
I need to insert multiple 32x32 arrays into 1024x1024 array at predetermined random locations. How to do this efficiently?
Use |accumarray| (and |randi|): N = 1024; Nx = randi([1 (N-32)], 1e5, 1); Ny = randi([1 (N-32)], 1e5, 1); linIndSt...

environ 10 ans il y a | 1

| A accepté

Réponse apportée
How to use arrayfun with a function that has different dimensions inputs
You need an |@| symbol in front of |GradientDescentLinear| to pass it as a function handle. At the moment it's trying to invoke ...

environ 10 ans il y a | 0

Réponse apportée
Poor performance in mex-files created using mexcuda
I implemented your code and got the same results as you. Then I added |gpu = gpuDevice| at the top and |wait(gpu)| before each c...

environ 10 ans il y a | 0

Réponse apportée
Preconditioning algorithm on GPU for solution of sparse matrices
MATLAB's preconditioning for sparse iterative solvers on the GPU is currently implemented using ILU and sparse triangular solves...

environ 10 ans il y a | 2

| A accepté

Réponse apportée
Limited GPU capabilities with 2 graphic cards on a laptop
For Windows, follow the instructions on <https://msdn.microsoft.com/en-us/library/windows/hardware/ff569918(v=vs.85).aspx changi...

environ 10 ans il y a | 0

Réponse apportée
ConvNN train in CPU mode
You cannot train CNNs built using Neural Network Toolbox using only the CPU. You may want to look at <http://www.vlfeat.org/matc...

environ 10 ans il y a | 1

| A accepté

Réponse apportée
strange running time behavior when calculating on the gpu (CUDA)
The problem is asynchronous execution - you're missing a |wait(gpuDevice)|. I got these timings: tgpu = 0.0204 0....

plus de 10 ans il y a | 1

Charger plus