Does MATLAB support NVIDIA Hopper cards for GPU computation?
11 views (last 30 days)
Show older comments
MathWorks Support Team
on 22 Dec 2023
Answered: MathWorks Support Team
on 22 Dec 2023
NVIDIA has released a new GPU architecture called "Hopper". Does MATLAB support using these GPU cards to accelerate deep learning training or other GPU computation?
Example card name: H100
Accepted Answer
MathWorks Support Team
on 22 Dec 2023
For releases R2010b to R2022b support for Hopper will be via NVIDIA's forwards compatibility mode. Optimized device libraries must be compiled at runtime from an unoptimized version. Support can be limited and you might see errors and unexpected behaviour.
Full Hopper built-in binary support within MATLAB is available from R2023a.
For more details please see https://www.mathworks.com/help/parallel-computing/gpu-computing-requirements.html.
Starting in R2020b, forward compatibility for GPU devices is disabled by default. Support can be enabled for the current MATLAB session by executing:
parallel.gpu.enableCUDAForwardCompatibility
Enabling forward compatibility can result in wrong answers and unexpected behaviour during GPU computations. In some cases, forward compatibility does not work as expected and recompilation of the libraries results in errors.
0 Comments
More Answers (0)
See Also
Categories
Find more on GPU Computing in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!