Supermicro announces an end-to-end systems blueprint for NVIDIA’s Vera Rubin platform, described as an NVL4 design intended for converged high-performance computing (HPC) and AI workloads. The plan is presented as a “total solution” that scales in liquid-cooled racks and supports both AI processing and double-precision (FP64) simulation performance. According to the available reports, configurations can include up to 1,152 NVIDIA Rubin GPUs and 576 NVIDIA Vera CPUs within liquid-cooled racks, packaged for high-density deployment. The PR release also describes a 3.2MW scalable unit and notes that the design uses DLC-2 Direct Liquid Cooling, with a stated cooling capacity of 362 kW per rack. The offerings are framed as research-cluster-ready, with scalability aimed at systems of different sizes. While the details provided focus on the integration approach, the communication does not add independent performance results beyond the claim of native FP64 capability. Other sources provided repeat the same announcement without additional substantiating specifics.
Supermicro unveils NVIDIA Vera Rubin NVL4 blueprint for liquid-cooled HPC and AI systems
Supermicro announces an end-to-end systems blueprint for NVIDIA’s Vera Rubin platform, described as an NVL4 design intended for converged high-performance computing (HPC) and AI workloads. The plan is...
- Supermicro announces an end-to-end blueprint for NVIDIA Vera Rubin platform systems labeled NVL4.
- The solution targets converged HPC and AI workloads and highlights native FP64 performance.
- Configurations are described as up to 1,152 NVIDIA Rubin GPUs and 576 NVIDIA Vera CPUs in liquid-cooled racks.
- The design is said to use DLC-2 Direct Liquid Cooling, with a stated capacity of 362 kW per rack.
- The release describes scaling via 3.2MW units for building research clusters of varying sizes.
Supermicro Delivers NVIDIA Vera Rubin NVL4 End-to-End DCBBS Blueprint with Native FP64 Performance for Converged HPC and AI Infrastructure
16 hours agoSupermicro Delivers NVIDIA Vera Rubin NVL4 End-to-End DCBBS Blueprint with Native FP64 Performance for Converged HPC and AI Infrastructure
16 hours agoTotal solution includes up to 1,152 NVIDIA Rubin GPUs and 576 NVIDIA Vera CPUs in liquid-cooled racks—3.2MW Scalable Unit delivers next-generation performance for AI workloads and FP64 simulation, scalable to research clusters of any size DLC-2 Direct Liquid Cooling supports 362 kW per...
17 hours agoAMD reinstates Memory Guard memory encryption option for consumer Ryzen CPUs
AMD reinstates memory encryption (“Memory Guard”) on certain consumer Ryzen desktop processors after user backlash over...
Apple plans to remove AirPort Utility from App Store in iOS 27, iPadOS 27 and macOS
Apple is planning to stop offering the AirPort Utility app through official app distribution channels, according to rele...
Google invests $75M in A24 to develop AI filmmaking tools with DeepMind
Google makes an approximately $75 million investment in independent film studio A24 as part of an AI research partnershi...