Nvidia finally reveals new Rubin GPU with almost 3X more CUDA cores than the Nvidia RTX 5090 — but you will have to wait till 2028 to grab it
Nvidia's Rubin HPC GPU packs over 50,000 CUDA cores, targets scientific simulations, and is expected to reach systems in 2028.
Nvidia has revealed a new processor designed for scientific computing needs, dubbed the Rubin HPC. This GPU packs in over 50,000 CUDA cores, nearly three times the 21,760 CUDA cores found in the GeForce RTX 5090. The Rubin HPC is part of Nvidia's Vera Rubin platform and is intended for complex scientific simulations, data analysis, and other demanding workloads.
The chip is expected to become available in 2028, leaving organizations several years to assess its performance before deployment. Rubin HPC features a balance of processing cores and faster data movement between components to prevent idle time, a common issue with data-intensive scientific calculations. The GPU also incorporates sparse data acceleration for improved operations with limited information in large datasets, common in simulation, analytics, and engineering software.
Nvidia links the development of Rubin HPC to the growing use of AI agents in scientific and engineering research. Faster simulations can help researchers test more possibilities before committing to physical experiments. The GPU supports Nvidia's CUDA-X libraries, which provide optimized software implementations for algorithms used in simulation, scientific research, and data analysis.
However, independent testing is needed to verify how much faster specific workloads will run on the new GPU.
Rewritten by urgent.news; may contain errors — check the original.