Nvidia introduced the Rubin HPC GPU at the Supercomputing 2026 conference. This new addition to the Rubin GPU family is specifically developed to accelerate agentic workflows and simulations. It targets scientists, engineers, and analysts who manage large datasets in their work.
The Rubin HPC GPU features over 50,000 CUDA cores, which Nvidia states is the highest number on any of its GPUs. This configuration suggests a multi-die design, potentially similar to the four-die Rubin Ultra GPU, utilizing NVLink-C2C for inter-die communication. The company did not provide further details on the chip's physical layout.
To facilitate data transfer between Rubin HPC GPUs, Nvidia will implement its NVLink 7 interconnect. While specific bandwidth details for NVLink 7 were not disclosed at the announcement, previous information indicated NVLink 6 offered 3.6 TB/s per-GPU bandwidth, with NVLink 7 expected to maintain this while expanding the scale-up domain.
Nvidia emphasizes the Rubin HPC GPU's suitability for agentic workflows, expecting faster simulation performance and accelerated discovery in scientific and engineering fields. The GPU's design, with high compute resources and faster data movement, aims to minimize idle compute resources and improve utilization for data-intensive tasks in areas such as climate research, genomic analysis, and financial simulation.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Nvidia unveiled the Rubin HPC GPU at Supercomputing 2026, featuring over 50,000 CUDA cores and NVLink 7 interconnect. This new GPU is designed to accelerate agentic workflows and simulations for scientists, engineers, and analysts working with large datasets, aiming to improve performance in fields like climate research and genomic analysis.