← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Nvidia and AMD Detail New CPUs and GPUs at SC26 Supercomputing Conference

🔄 Updated 8h ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Nvidia's Vera CPU can see up to 39% performance optimization with architecture-specific tuning.
  • Nvidia announced Rubin HPC GPU with over 50,000 CUDA cores for agentic workflows.
  • AMD's EPYC Venice CPUs are positioned for agentic workloads.
  • AMD now powers over 40% of new TOP500 supercomputers.

SC26 Conference Highlights

The annual Supercomputing conference (SC26) featured new developments from major hardware manufacturers. Coverage from the event included discussions between Nvidia and AMD regarding their latest CPU and GPU offerings, particularly concerning agentic workloads and high-performance computing.

Nvidia's Vera CPU and Rubin HPC GPU

Nvidia's Vera CPU was a key topic, with the company explaining that existing software requires architecture-specific optimization to fully utilize the processor. Nvidia demonstrated that Vera's performance can be optimized by up to 39% in some workloads when considering its Olympus-based Arm cores. The company also introduced the Rubin HPC GPU, a variant of the Rubin GPU designed for agentic workflows and scientific simulations involving large datasets. The Rubin HPC reportedly features over 50,000 CUDA cores, nearly double the standard Rubin GPU.

AMD's EPYC Venice and TOP500 Presence

AMD asserted that its EPYC Venice CPU lineup is optimized for agentic workloads. The company also significantly increased its representation on the TOP500 list of supercomputers, now featured in over 40% of new systems, marking a 14% boost. This includes the Lux supercomputer, developed in collaboration with another entity.

Industry Implications

The announcements from both Nvidia and AMD at SC26 underscore the ongoing focus on developing specialized hardware for emerging computational demands, particularly in artificial intelligence and scientific research. The emphasis on 'agentic workloads' indicates a growing segment of high-performance computing that both companies are targeting with their latest CPU and GPU architectures.

✨ 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 →

The daily brief

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.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

Nvidia discussed its Vera CPU's optimization potential and announced the Rubin HPC GPU with over 50,000 CUDA cores for agentic workflows. AMD claimed its EPYC Venice CPUs excel at agentic workloads and increased its presence on the TOP500 supercomputer list to over 40%. These announcements highlight ongoing competition and development in high-performance computing hardware for AI and scientific applications.