MATLAB: Is Matlab/ Simulink supporting Nvidia external GPU Systems/Thunderbold 3 for Machine Learning and Deep Learning projects including embedded systems like Jetson TX2

egpuexternal gpugpu coding

Hi there,

we are planning some research projects on machine learning (big data approaches, creating predictive models, deep learning with object recognition). We plan to use GPU computing for this.

To make the GPU easily available for different users (with their laptops) we thought of buying an "external GPU" case (equiped with i.e. Nvidia Geforce 1080Ti) in combination with Thunderbold 3 interfaces. Different users could prepare their tasks and alternately connect the eGPU only for training of their networks.

Does MATLAB/Simulink support this setup?

Does anybody use this hardware setup? (-in combination with the "GPU-Coder Add-on" and Nvidia Jetson TX2 embedded hardware?)

How are your experiences?

Thank you!

Marcus

Best Answer

Yes, it's supported. This isn't really a question of MATLAB's system requirements; if the CUDA driver can interact with your card then so can MATLAB. You will notice a considerable increase in latency due to the dramatically reduced bandwidth to get data on and off the card, so you need to minimize the amount of CPU/GPU communication.

Related Solutions

MATLAB: GPU programming on Matlab (Mac/Window): What are the options

Others may have a longer answer to your question, but certainly it is possible to get an NVIDIA GPU for a desktop PC with a PCI bus. You can even get something that will work with your Mac or Windows laptop, you just need to buy a caddy to put the card in, for instance the Razer Core. Getting this working with a Mac is a bit more complicated than with Windows, you can find instructions online.

Once you have your GPU installed, check out the MATLAB GPU product page to get started.

The GTX 1060 is adequate to get started with image processing, computer vision and deep learning because it has good single precision performance. For simulation, solvers, and other problems where high accuracy double precision is essential, you may need to look at a more expensive card in the Quadro or Tesla range. There is also the Titan V.

MATLAB: CPU vs GPU – Is it reasonable

While I can't comment exactly on the CPU/GPU comparison for your specific setup, I can say that the general rule of thumb in GPU computing is that operating on as much data as possible in a single call by vectorizing your code will provide the best performance. With that said, since you are already using the bsxfun function I would go a step further and use the following code to avoid the for loop and operate on all of your data in a single call.

Also, the timeit/gputimeit functions are the best choice for comparing CPU and GPU execution as they each provide an average time over multiple runs. Furthermore, gputimeit takes into account the fact that GPU operations perform asynchronously, while tic/toc does not.

x1GPU=gpuArray.randn(3,1,10000);
x2GPU=gpuArray.randn(3,5000);
gputimeit(@()bsxfun(@minus, x1GPU, x2GPU))
x1CPU=randn(3,1,10000);
x2CPU=randn(3,5000);
timeit(@()bsxfun(@minus, x1CPU, x2CPU))

I can confirm that when I run the code you provided, it takes about 4 seconds on the GPU and 1.5 seconds on the CPU. For the code that I have provided, gputimeit reports an average time of 0.0855 seconds on the GPU while timeit reports (again) an average of 1.5 seconds on the CPU.

The bottom line is that CPU for loops combined with GPU computing in the loop body generally does not provide the best performance. You should always try to replace code like this with a vectorized version if possible.

Best Answer

Related Solutions

MATLAB: GPU programming on Matlab (Mac/Window): What are the options

MATLAB: CPU vs GPU – Is it reasonable

Related Question