NVIDIA ampere architecture-based GPU line expanded
Super Micro Computer has a broad Tier 1 portfolio of systems that integrate capabilities achieving 5 petaFLOPS of AI performance in a 4U form factor with the latest NVIDIA A100, NVIDIA A40, NVIDIA RTX A6000, and the new NVIDIA A30, NVIDIA A10, and NVIDIA A16 GPUs.
"Our collaboration with NVIDIA enables us to design a complete portfolio of GPU systems and platforms empowering maximum customer choice. Customers can exactly match their workload requirements to system architecture to achieve superior scale, performance, efficiency, and cost," said Charles Liang, President and CEO, Supermicro.
"Supermicro offers multi-GPU optimised systems that deliver advanced solutions to AI, Deep Learning, HPC, and video streaming applications. Leveraging our building block solutions and our time-to-market advantage, we continue developing and releasing application-optimised solutions. Our flexible 2U 2-node GPU system with PCIe 4.0 is tuned for cloud gaming and social media and leads the industry with support for up to three double-width or six single-width GPUs per node."
The breadth of Supermicro's systems includes the flagship Intel-based SYS-420GP-TNAR or the AMD-based AS -4124GO-NART(+), featuring the 4U Server powered by the NVIDIA HGX A100 8-GPU board, with the option of either 40GB (HBM2) or 80GB (HBM2e) of memory on each GPU. These systems are currently shipping worldwide.
"From AI-powered drug discovery to designing advanced, efficient factories, accelerated computing is essential to powering the most innovative work in the world today," added Justin Boitano, Vice President and General Manager, Enterprise and Edge Computing at NVIDIA. "Supermicro's NVIDIA-Certified Systems provide customers with a broad range of servers built to deliver top performance for AI, graphics and simulation workloads across the data centre, to the cloud, to the edge."
The new systems can run various advanced application workloads, including the NVIDIA AI Enterprise software suite, which is optimised and certified by NVIDIA to run on VMware vSphere, and NVIDIA Omniverse Enterprise an end-to-end real-time simulation and collaboration platform bringing transformative 3D workflows to organisations of every scale. Supermicro is showcasing these performance-leading solutions at the NVIDIA GTC21 conference this week.
From the Edge to the Cloud, AI, ML, HPC, and 3D visualisation are becoming critical technologies necessary for all organisations and industries to embrace. Developing systems and delivering platforms that incorporate the latest hardware and software allows a range of enterprises to quickly get productive and implement their latest solutions, with a range of form factors. Supermicro is a leading participant in the NVIDIA-Certified Systems program, which validates the hardware and software configurations needed for maximum productivity.
These systems can handle massive amounts of data with advanced networking, allowing for complex models to be developed and incorporate new AI and other advanced algorithms. 3D visualisation enables better comprehension of physical reality, while graphics virtualisation enables IT administrators to consolidate systems infrastructure and centralise and secure their data. NVIDIA-Certified Systems allow for easy and fast deployment in the data centre. Supermicro also leads the industry with NEBS Level 3-certified GPU servers for 5G and telco customers.
Supermicro supports the latest hardware and software solutions from NVIDIA. The range of supported GPUs includes the NVIDIA A100 80GB, A100 40GB, A40, RTX A6000, A30, A10, and A16 GPUs, aiming at AI Inference and mainstream computing, mainstream graphics and video, and virtual desktops, all with AI technologies. All NVIDIA products are available across a wide range of Supermicro systems that use 3rd Gen Intel Xeon Scalable Processors or 3rd Gen AMD EPYC CPUs.
With Supermicro's design excellence, more GPUs are packaged into less space (higher density) than other system suppliers. All of these new GPU systems are NVIDIA-Certified or are currently undergoing certification.
Supermicro systems with NVIDIA HGX A100 modules (choice of 40GB HBM or 80GB HBMe memory) include:
- AS -4124GO-NART/+ – Dual 3rd Gen AMD EPYC processors with NVIDIA HGX A100 8-GPU.
- SYS-420GP-TNAR/+ – Dual 3rd Gen Intel Xeon Scalable processors with NVIDIA HGX A100 8-GPU.
- AS -2124GQ-NART/+ – Dual 3rd Gen AMD EPYC processors with NVIDIA HGX A100 4-GPU.
Supermicro systems with PCIe 4.0, supporting NVIDIA A100/PCIe, A30, A16, A10, and RTX A6000 include:
- AS -4124GS-TNR – Dual 3rd Gen AMD EPYC processors supporting up to 8 double-width GPUs.
- SYS-420GP-TNR – Dual 3rd Gen Intel Xeon Scalable processors supporting up to 10 double-width GPUs.
- Multi-node AS -2114GT-DNR – Single 3rd Gen AMD EPYC processor supporting up to 6 single-width or 3 double-width GPUs per node.
- SuperBlade SBA-4119SG – Single 3rd Gen AMD EPYC processor supporting 1 double-width GPU or 2 single-width GPUs per blade, with up to 20 blades in an 8U enclosure.
- Workstation class SYS-740GP-TNRT – Dual 3rd Gen Intel Xeon Scalable processors supporting up to 4 double-width GPUs.
Omniverse Enterprise will be available starting this summer from Supermicro.