NVIDIA Unveils Rubin HPC GPU at SC26, Expected to Launch in 2028
English text is being prepared.
At the Supercomputing 2026 conference, NVIDIA unveiled its new GPU chip Rubin HPC, aimed at accelerating science, engineering, and analytics workloads, with an expected launch in 2028. The chip belongs to the Vera Rubin platform, features more than 50,000 CUDA cores, offers sparse data acceleration capabilities, and adopts seventh-generation NVIDIA NVLink interconnect technology. Ian Buck, NVIDIA's vice president of hyperscale and high-performance computing, said that faster simulation means faster discovery, and that Rubin HPC can accelerate AI agents in testing ideas and guide subsequent simulations.
Why read this
AI score 53
The original text provides the core specifications and launch timeline of Rubin HPC, allowing readers to gauge NVIDIA's product cadence in the convergence of AI and HPC.
Topics
Body
英伟达(NVIDIA)虽深陷管理层变动问题,但持续展现在高速计算技术领域的企图。在Supercomputing 2026(SC26)大会宣布新GPU芯片Rubin HPC,用以加速科学、工程与分析领域,成为帮助科学领域推进的一大利器,展现将AI与传统高性能计算(HPC)整合的企图心,预计2028年上市。
AI大厂持续以芯片和语言模型加速科学进展,Google以TPU和Gemini模型推动对蛋白质结构的计算,英伟达展现在AI芯片的地位,也推出专为科学、工程打造的新品,展现AI技术。
Rubin HPC GPU也是Vera Rubin平台产品,配备超过5万个CUDA核心,创下单颗GPU的CUDA核心数量纪录。它具备稀疏数据加速能力;采用第七代NVIDIA NVLink互联技术加快GPU之间的通讯效率。Rubin HPC加速模拟运算速度,大幅缩短从探索到科学发现与工业设计的时间。
英伟达超大规模与高性能计算副总裁Ian Buck指出,AI代理在科学领域应用,更快的模拟就意味着更快的发现。Rubin HPC加速AI代理测试构想并引导后续步骤的模拟,协助科学家与工程师探索更多可能性,更早突破产品研发瓶颈。
AI Trends