Nvidia will enable cuda support on the arm platform

So far, the benefits of Nvidia graphics cards and ARM processors have not been merged to create any supercomputers. The simple reason is that Nvidia did not support CUDA in ARM, rendering an ARM supercomputer with Nvidia graphics unfeasible, incredible as it appears.

Nvidia did not support CUDA in ARM

Now, Nvidia is committed to offering CUDA support for ARM before the end of the year, with a full stack of AI and HPC software, allowing ARM to be used to create the next generation of supercomputers. With this change, Nvidia will support all three leading CPU architectures, x86, POWER, and ARM.

Visit our guide on the best graphics cards on the market

This announcement comes in the wake of the announcement of two Exascale supercomputers powered by Intel and AMD's combination of silicon CPUs and graphics respectively, each system offering tight integration between its CPU and graphics products. Simply put, Intel knows how to get its CPUs to run on its own graphics chips, and in the same way, AMD knows how to get its Zen CPUs and Radeon graphics to work together optimally.

From the looks of it, Nvidia is expanding its focus on supercomputing in hopes of increasing sales, especially when the European Processor Initiative works to create an ARM-based supercomputer using European processors. In the future, ARM will become a bigger name within the supercomputing space, and Nvidia hopes to take advantage of that slice of the pie.

Overclock3d font