Joss Knight

MathWorks

Last seen: Today | Con actividad desde 2013

Followers: 0 Following: 0

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.

Estadística

CLASIFICACIÓN
84
of 298.247

REPUTACIÓN
1.776

CONTRIBUCIONES
0 Preguntas
610 Respuestas

ACEPTACIÓN DE RESPUESTAS
0.00%

VOTOS RECIBIDOS
325

Ver insignias

Feeds

Respondida
Getting started with cuda in matlab and running into errors
I'm not sure about this one. Since your code only has one kernel, try removing the third argument to |CUDAKernel|. Also try reco...

4 días hace | 0

Respondida
GPU Recommendation for XGBoost with MATLAB R2022b
Yes, MATLAB R2022b supports these GPUs.

4 días hace | 1

Respondida
The adamupdate function in MATLAB R2024b incorrectly uses uint32 with sqrt and exhibits state corruption, causing errors even in minimal test cases."
Well, I admit the error messages aren't very helpful but the basic problem is that passing a trainingOptions object in as an arg...

alrededor de 1 mes hace | 0

| aceptada

Respondida
Load multiple Files from fileDatastore in minibatchqueue
Does the training option PreprocessingEnvironment set to 'background' not work for you? Or is this a custom training loop?

alrededor de 1 mes hace | 0

| aceptada

Respondida
mexcuda Compile CUDA code with child kernels
I think the problem might be that you're trying to do the device binary linking yourself, whereas mexcuda is taking care of that...

alrededor de 2 meses hace | 0

| aceptada

Respondida
How to prepare irregularly spaced time-series data for classification using LSTM
It seems like your observations (batch) are the days, time is the rows and you perhaps have two channels in the first two column...

alrededor de 2 meses hace | 0

| aceptada

Respondida
How to get a dlgradient result for a blackbox function
Hi Fernando. The hardcore solution to your problem (after using Matt's solution) is to implement the sparse matrix multiply func...

3 meses hace | 0

Respondida
Does gather() clear memory
|gather| creates a copy of the array in main memory. Clearing a |gpuArray| variable will release its memory. So if you replace a...

3 meses hace | 1

| aceptada

Respondida
MATLAB R2024b GPU validation device fail for Multi-Instance GPU (MIG) A100
Try running nvidia-smi -L in a terminal to get the UUID of the device, and then set CUDA_VISIBLE_DEVICES to that full UUID inste...

3 meses hace | 0

Respondida
How to use both GPU devices in the laptop
You cannot use your Intel Iris GPU for numerical computation in MATLAB. The best way to use both GPUs is to make sure your integ...

5 meses hace | 1

Respondida
How to perform feval function operation correctly on multiple GPUs
What you have passed to parallel.pool.Constant is a function that returns the captured object; what you wanted was a function th...

5 meses hace | 2

| aceptada

Respondida
slow imwarp with large arrays
I think the documentation is just referring to using the GPU or the ability to process in the background using backgroundPool to...

6 meses hace | 0

| aceptada

Respondida
CUDA seems not to be supported
MATLAB does not use the toolkit that you download, it installs its own version. You cannot change it by downloading the toolkit....

6 meses hace | 1

Respondida
"Maximum variable size allowed on the device is exceeded." when using predict on GPU
Is there a way to force predict to use CPU? Yes. Pass data in as an in-memory array. If your data is on the device, you may nee...

6 meses hace | 0

| aceptada

Respondida
Why is pagemtimes slower than just coding up the matrix multiplication?Especially on GPU.
Your implementation is incorrect I'm afraid, you are using elementwise times rather than mtimes. You are also using timeit inste...

6 meses hace | 4

Respondida
gpuArray size limit is much less than the GPU maximum memory
See https://uk.mathworks.com/matlabcentral/answers/2145604-gpu-array-max-dimensions-size-i-e-int32-of-2e9-not-same-as-other-cud...

6 meses hace | 1

Respondida
For Matlab R2021a, How can Visual Studio be selected as the compiler for C/C++
Using a 2022 compiler with a 2021 MATLAB isn't a supported workflow. Can you upgrade MATLAB?

7 meses hace | 0

| aceptada

Respondida
Retraining YAMNet for audio classification returns channel mismatch error in "deep.internal.train.Trainer/train"
I think the issue will be that your label data is a categorical type with three categories. Run categories(trainLabels) to con...

7 meses hace | 0

| aceptada

Respondida
Retraining YAMNet for audio classification returns channel mismatch error in "deep.internal.train.Trainer/train"
It looks like your network is returning output with three channels instead of two. Could you try running analyzeNetwork(net) to ...

7 meses hace | 0

Respondida
gpu output array wrong dimensions
The outputs of your kernel will be the non-const pointer inputs to your kernel in the order they appear in your function signatu...

7 meses hace | 0

| aceptada

Respondida
Error in index returned by max() in the second dimension in obscure case
Thank you! You have found a bug in MATLAB's GPU support. The computation of the indices is wrong when reducing along the rows an...

7 meses hace | 1

| aceptada

Respondida
Matlab Support for float32/single and float16/half datatypes in GPU Sparse Matrix Multiplication
Half support is not currently planned for sparse.

8 meses hace | 3

Respondida
Error: "Incorrect type of 'Z' for 'predict' in Layer 'samplelayer'. Expected 'gpuArray', but instead was 'single'." This error is shown during using a custom deep layer.
Hello. You need to return an array of the same data type and storage type as the input. Somehow your data is no longer on the GP...

8 meses hace | 0

| aceptada

Respondida
Speeding up matrix expotentials by using GPU
Your GTX 1650 is designed for single precision computing. In single precision it has a peak performance of about 3 teraflops, wh...

8 meses hace | 3

| aceptada

Respondida
GPU Array Max Dimensions/Size (i.e., int32 of ~2e9) Not Same as Other CUDA-Enabled Languages (i.e., Python 3.9 - Tensorflow 2.11)
In CUDA 12 NVIDIA introduced a limited set of 64-bit integer APIs in cublas and other libraries, allowing arrays with more eleme...

8 meses hace | 2

| aceptada

Respondida
Multilayer Perceptron with More Than One Output and Data Interpretation?
You can continue to use trainNetwork if you don't want to use dlnetwork. dlnetwork obviously provides much more flexibility as w...

9 meses hace | 0

Respondida
Matlab continuously launching on GPU
Using the NVIDIA Control Panel, disable hardware acceleration for MATLAB. Alternatively, type |opengl software| on startup.

9 meses hace | 0

9 meses hace | 0

| aceptada

Respondida
I get the illegal instruction error while running Matlab code with GPU
On the face of it it does seem like you've hit some kind of bug in CUDA 11. If you can upgrade your MATLAB to a more recent vers...

9 meses hace | 0

| aceptada

Respondida
GPU memory usage for Hadamard product
I can't reproduce this. You say you have 48Gb of GPU memory available...have you checked this? Try running gpuDevice and lookin...

9 meses hace | 0

Cargar más