Supermicro Brings Enterprise-Class AI Performance to the Client, Edge, and Consumer Markets
Expands edge portfolios with NVIDIA, Intel, and AMD-powered platforms
More
Supermicro Announces Support for Upcoming NVIDIA Vera Rubin NVL72, HGX Rubin NVL8 and Expanded Rack-Scale Manufacturing Capacity for Liquid-Cooled AI Solutions
Data Center Building Block Solutions® (DCBBS) and Advanced Direct Liquid Cooling
(DLC) Technology with Supermicro US Based In-House Design/Manufacturing
Accelerate Time to Deployment of Next Generation Liquid-cooled AI Infrastructure
More
How Supermicro Boosts Density in AI Data Centre Environments
Supermicro has launched a new 6U SuperBlade platform designed to increase compute density and efficiency for modern data centre environments
More
Supermicro Unveils High-Density, Liquid-Cooled and Air-Cooled 6U SuperBlade® Powered by Intel® Xeon® 6900 Series Processors for Maximum Performance and Efficiency
- 6U SuperBlade's innovative design delivers up to 93% cable reduction and 50% space savings compared to traditional 1U servers
- 32-inch depth enclosure fits in a standard 19-inch rack, eliminating the need for a deep rack
- Supports both air cooling (6U 5 nodes) and liquid cooling (6U 10 nodes)
- Powered by dual Intel Xeon 6900 Series Processors with P-cores, the 6U SuperBlade delivers high compute density, supporting up to 100 servers per rack
- Optimized for demanding HPC and AI workloads including manufacturing, financial services, scientific research, energy and climate & weather modeling
More
HPC and AI converging infrastructures
Vik Malyala, Managing Director & President for EMEA from Supermicro shares the boundaries between HPC and AI workloads becoming increasingly blurred
More
Ethernet is a full-fledged alternative for AI networks
Dan Hanson, Director of AI Fabric Product Management at Supermicro talks about how training large AI models requires GPU interconnects with extremely low latency and high throughput.
More
Supermicro擴大NVIDIA Blackwell產品系列，推出全新4U與2-OU（OCP）液冷NVIDIA HGX B300解決方案，現可大量出貨
- 本次推出的4U與2-OU（OCP）液冷NVIDIA HGX B300系統，適用於高密度超大規模設施與AI工廠的部署。這兩款機型基於Supermicro Data Center Building Block Solutions®架構，並分別採用DLC-2與DLC散熱技術
- 4U液冷NVIDIA HGX B300系統可適用於標準的19吋EIA機架，可在每機架內支援最高64個GPU，並能透過DLC-2（直接液冷）技術為最高98%的系統熱能進行冷卻
- 緊湊、高能效的2-OU（OCP）NVIDIA HGX B300 8-GPU系統針對21吋OCP Open Rack V3（ORV3）規格所設計，可在單一機架內支援最高144個GPU
More
Storage priorities in the AI age
Wendell Wenjen from Supermicro highlights four current developments shaping storage strategies in AI-driven enterprise environments.
More
Supermicro JumpStart Review: A Week With an NVIDIA HGX B200
Supermicro’s JumpStart program takes a very different approach to hardware evaluation. Instead of a short, scripted demo in a shared lab environment, JumpStart gives qualified customers free, time-boxed, bare-metal access to a catalog of real production servers.
More
Supermicro JumpStart Review: A Week With an NVIDIA HGX B200
Supermicro is already offering access to HGX B200- and B300-class systems for AI training and inference, and it uses JumpStart to give early, NDA-based looks at next-generation platforms that are not yet broadly shipping.
More