Joss Knight

Last seen: Today

MathWorks

397 total contributions since 2013

Although I cannot be contacted directly, if you would like to ask me a question all you have to do is mention "GPU" somewhere in your MATLAB Answers question.

Joss Knight's Badges

View details...

Answered
Using CUDA mex files interoperably with gpuArray
A third party CUDA MEX file could be built with a different version of the CUDA toolkit, and thus a different version of the CUD...

5 days ago | 0

Answered
GPU arrays support only fundamental numeric or logical data types
It looks distinctly like one of your custom functions, preprocessData or augmentData, is doing something illegal with gpuArray o...

5 days ago | 1

| accepted

Answered
Code optimization with GPU
I = reshape(gpuArray.eye(q),q,1,q); U = I.*my_line_vector;

5 days ago | 0

Answered
GPU GTX 1650 TI support
MathWorks does not list every single supported device, instead the documentation shows which device compute capabilities are sup...

5 days ago | 0

| accepted

Answered
Runing code with matlab on the GPU restarts the PC
Almost always the only way the GPU can cause your PC to restart is a power supply issue. You should check that your PC's power s...

11 days ago | 1

| accepted

Answered
deeplearning Matlab is not compatible with graphics card
As explained in the documentation, both for CUDA support and for the enableForwardCompatibility function, "Enabling forward comp...

11 days ago | 0

Answered
The CUDA driver must recompile the GPU libraries
There isn't really much to say. This 'forward compatibility' is explained in the CUDA support by release documentation. As it sa...

11 days ago | 0

| accepted

Answered
gpuArray/imresize Input array has too many elements
There is a size limitation for gpuArray/imresize of <= 2^27 elements which is only documented in help text. >> help gpuArray/im...

13 days ago | 0

| accepted

Answered
GPU vs. CPU in training time
Use the DispatchInBackground training option to improve throughput when your data access and preprocessing is costly.

1 month ago | 0

| accepted

Answered
Background Data Dispatch with Custom Training Loop
Use a minibatchqueue with the DispatchInBackground option.

2 months ago | 0

| accepted

Answered
The function trainNetwork is slow during startup - what is the cause?
Your validation set is huge. I suspect that what's taking time is the computation of the first validation accuracy metric. If fi...

2 months ago | 0

| accepted

Answered
GPU error + Working with total XTrain data in custom training loop
The error is telling you you can't process all your data at once because you don't have enough GPU memory. You either have to us...

3 months ago | 1

Answered
Is there any work around the error "Array concatenation is not supported"?
Yeah, you can't do anything with arrays in GPU arrayfun, only scalars. You have some options: Reimplement with a loop instead o...

3 months ago | 0

Answered
Error using gpuArray Maximum variable size allowed on the device is exceeded.
The NVIDIA libraries that MATLAB uses to do GPU computation store array lengths as 32-bit integers and therefore MATLAB cannot u...

3 months ago | 1

Answered
I have problem with clear GPU memory
MATLAB does not clear all GPU memory unless all variables are released because allocating memory is a performance bottleneck. So...

3 months ago | 1

Answered
RTX 3080 recompiling issue in Matlab 2020a
Does MATLAB support NVIDIA Ampere cards for GPU computation? You should follow the advice on the GPU support by release page ca...

3 months ago | 0

Answered
How to execute several backslash operations in parallel on GPU?
Try using gpuArray/pagefun before you resort to code generation.

3 months ago | 0

Answered
Where does the file"mex_CUDA_win64.xml " exist in Matlab2020a?
The correct method for compiling GPU MEX functions for many years now has been to use the utility mexcuda, which does not requir...

6 months ago | 0

Answered
How do I substitute all the activation functions of a neural network?
It looks as though you've replaced every relu layer with multiple other layers. This will make your network deeper. The deeper t...

6 months ago | 0

Answered
Using mex with CUDA
Hi Jack. I expect the answer to this question is that you have installed a more recent version of the CUDA toolkit, specifically...

6 months ago | 0

Answered
How to run a custom function to gpu?
I guess the basic problem is that the gctest function doesn't support gpuArray data. You could try taking a copy of it and fixin...

6 months ago | 0

Answered
How do I take poisson draws with poissrnd() using GPU resources via arrayfun?
As you can see from the documentation, poissrnd is not a function that is support by the FUN argument of gpuArray/arrayfun. You ...

7 months ago | 0

Answered
Same gpu operation in loop but two speeds
MATLAB will do some optimisations when it sees you are doing the same thing repeatedly. In your case, the optimisation that appl...

9 months ago | 0

| accepted

Answered
Parallrl calculations for Deep learning Toolbox
Sorry about this not-very-good error, which should be fixed in the current release. What it means is that 'Shuffle', 'never' is ...

9 months ago | 1

Answered
Error using parpool (line 113)
This is a very unusual error and indicates a problem with your installation. I suspect your MATLAB path is mixed up with previou...

9 months ago | 2

Answered
CPU/GPU Architecture Recommendation
For Deep Learning the RTX 2080 is a good choice.

9 months ago | 0

Answered
Using external GPU with MatLab 2020a
There may be nothing you can do. Data transfer times to an external GPU are much higher. It might help to increase the MiniBatch...

10 months ago | 0

Answered
Arrayfun GPU in "Game of Life" works slower than CPU
Check out this Answer. The arrayfun version is rather dependent on good memory performance since the kernel is accessing global ...

10 months ago | 0

| accepted

Answered
Deep Learning - Distributed GPU Memory
No, there is nothing like what you are after, to distribute the weights of a fully connected layer across multiple GPUs. You cou...

10 months ago | 0

Answered
Multiple GPUs perform slower than single GPU to train a semantic segmentation network
On Windows, due to GPU communication issues on that platform, it is difficult to get any benefit from multi-GPU training. This w...

11 months ago | 0

| accepted