Universal GPU システム

Universal GPU システム

大規模AIトレーニングやHPCアプリケーションなどに最適な、モジュラー型ビルディング・ブロック設計の、4U、5Uまたは8Uと次世代への拡張性を備えたオープンスタンダード・プラットフォーム

  • GPU: NVIDIA HGX H100/A100 4-GPU/8-GPU, AMD Instinct MI250 OAM Accelerator
  • CPU: Intel® Xeon® or AMD EPYC™
  • Memory: Up to 32 DIMMs, 8TB
  • Drives: Up to 24 Hot-swap U.2 or 2.5" NVMe/SATA drives
Show Models
4U, 5U GPU 製品ライン

4U, 5U GPU 製品ライン

AI/深層学習、HPCアプリケーションに最適な、最大級のアクセラレーション能力と柔軟性を実現

  • GPU: Up to 10 NVIDIA H100 PCIe GPUs, or up to 10 double-width PCIe GPUs
  • CPU: Intel® Xeon® or AMD EPYC™
  • Memory: Up to 32 DIMMs, 8TB DRAM or 12TB DRAM + PMem
  • Drives: Up to 24 Hot-swap 2.5" SATA/SAS/NVMe
Show Models
NVIDIA MGX™ Systems

NVIDIA MGX™ Systems

Modular Building Block Platform Supporting Today's and Future GPUs, CPUs, and DPUs

  • GPU: Up to 4 NVIDIA PCIe GPUs including H100, H100 NVL, and L40S
  • CPU: Intel® Xeon® or NVIDIA Grace Superchip
  • Memory: Up to 16 DIMMs, 4TB DRAM or 960GB on-chip memory
  • Drives: Up to 8 E1.S + 2 M.2 drives
Show Models
4U GPU Lines with PCIe 4.0

4U GPU Lines with PCIe 4.0

Flexible Design for AI and Graphically Intensive Workloads, Supporting Up to 10 GPUs

  • GPU: NVIDIA HGX A100 8-GPU with NVLink, or up to 10 double-width PCIe GPUs
  • CPU: Intel® Xeon® or AMD EPYC™
  • Memory: Up to 32 DIMMs, 8TB DRAM or 12TB DRAM + PMem
  • Drives: Up to 24 Hot-swap 2.5" SATA/SAS/NVMe
Show Models
2U 2ノード マルチGPU

2U 2ノード マルチGPU

クラウドスケールのデータセンターアプリケーションに最適な、高密度、リソースセービング・マルチGPUアーキテクチャ

  • GPU: Up to 3 double-width PCIe GPUs per node
  • CPU: Intel® Xeon® or AMD EPYC™
  • Memory: Up to 8 DIMMs, 2TB per node
  • Drives: Up to 2 front hot-swap 2.5” U.2 per node
Show Models
2U GPU 製品ライン

2U GPU 製品ライン

高い演算能力を必要とするアプリケーションに最適な、高性能と搭載密度のバランスの取れたソリューション

  • GPU: NVIDIA HGX A100 4-GPU with NVLink, or up to 6 double-width PCIe GPUs
  • CPU: Intel® Xeon® or AMD EPYC™
  • Memory: Up to 32 DIMMs, 8TB
  • Drives: Up to 10 Hot-swap 2.5" SATA/SAS/NVMe
Show Models
1U GPU 製品ライン

1U GPU 製品ライン

データセンターからエッジ用途まで対応可能な、高密度GPUプラットフォーム

  • GPU: Up to 4 double-width PCIe GPUs
  • CPU: Intel® Xeon®
  • Memory: Up to 16 DIMMs, 4TB
  • Drives: Up to 6 x 2.5" Hot-swap SAS/SATA, or 2 x 2.5" Hot-swap NVMe SATA/SAS/NVMe
Show Models
GPU ワークステーション

GPU ワークステーション

ハイエンドグラフィックス、設計、デザイン、VR、AIアプリケーション開発まで、様々な用途に対応可能なワークステーション

  • GPU: Up to 4 double-width PCIe GPUs
  • CPU: Intel® Xeon®
  • Memory: Up to 16 DIMMs, 6TB
  • Drives: Up to 8 hot-swap 2.5” SATA/NVMe
Show Models
リソース

Options For Accessing PCIe GPUs in a High Performance Server Architecture

Understanding Configuration Options for Supermicro GPU Servers Delivers Maximum Performance for Workloads

View the product brief

Petrobras Acquires Supermicro Servers Integrated by Atos To Reduce Costs and Increase Exploration Accuracy

Supermicro Systems Power Petrobras to the #33 Position in the Top500, November 2022 Rankings

View the success story

Supermicro Servers Increase GPU Offerings For SEEWEB, Giving Demanding Customers Faster Results For AI and HPC Workloads

Seeweb Selects Supermicro GPU Servers to Meet Customer Demands of HPC and AI Workloads

View the success story

H12 Universal GPU Server

Open Standards-Based Server Design for Architectural Flexibility

View the datasheet

3000W AMD Epyc Server Tear-Down, ft. Wendell of Level1Techs

By Gamers Nexus -

We are looking at a server optimized for AI and machine learning. Supermicro has done a lot of work to cram as much as possible into 2114GT-DNR (2U2N) - a density optimized server. This is a really cool construction: there are two systems in this 2U chassis. The two redundant power supplies are 2,600W each and we'll see why we need so much power. It hosts six AMD MI210 Instinct GPUs and the dual Epyc processors. See the level of engineering Supermicro put into the design of this server.

See the product review

H12 4U GPU Server

Flexible, High-Density GPU Server for AI, ML, and HPC

View the datasheet

H12 2U 2-Node Multi-GPU

Multi-Node Design for Compute and GPU-Acceleration Density

View the datasheet

NEC Advances AI Research With Advanced GPU Systems From Supermicro

NEC uses Supermicro GPU servers with NVIDIA® A100s for Building a Supercomputer for AI Research (In Japanese)

View the success story

Hybrid 2U2N GPU Workstation-Server Platform Supermicro SYS-210GP-DNR Hands-on

By Will Taillac -

Today we are finishing our latest series by taking a look at the Supermicro SYS-210GP-DNR, a 2U, 2-node 6 GPU system that Patrick recently got some hands-on time with at Supermicro headquarters.

See the product review

Supermicro SYS-220GQ-TNAR+ a NVIDIA Redstone 2U Server

By Will Taillac -

Today we are looking at the Supermicro SYS-220GQ-TNAR+ that Patrick recently got some hands-on time with at Supermicro headquarters.

See the product review

Unveiling GPU System Design Leap - Supermicro SC21 TECHTalk with IDC

Presented by Josh Grossman, Principal Product Manager, Supermicro and Peter Rutten, Research Director, Infrastructure Systems, IDC

Play the video

Supermicro TECHTalk: High-Density AI Training/Deep Learning Server

Our newest data center system packs the highest density of advanced NVIDIA Ampere GPUs with fast GPU-GPU interconnect and 3rd Gen Intel® Xeon® Scalable processors. In this TECHTalk, we will show how we enable unparalleled AI performance in a 4U rack height package.

Play the video

Mission Critical Server Solutions

Supermicro's Comprehensive Server, Storage and Networking product lines Optimized for IT, Data Center, Embedded, HPC and Cloud Computing and Supporting 3rd Gen Intel Xeon Scalable Processors (Ice Lake)
View the brochure

Maximizing AI Development & Delivery with Virtualized NVIDIA A100 GPUs

Supermicro systems with NVIDIA HGX A100 offer a flexible set of solutions to support NVIDIA Virtual Compute Server (vCS) and NVIDIA A100 GPUs, enabling AI developments and delivery to run small and large AI models.

View the solution brief

Supermicro SuperMinute: 2U 2-Node Server

Supermicro's breakthrough multi-node GPU/CPU platform is unlike any existing product in the market. With our advanced Building Block Solutions® design and resource-saving architecture, this system leverages the most advanced CPU and GPU engines along with advanced high-density storage in a space-saving form factor, delivering unrivaled energy-efficiency and flexibility.

Play the video

SuperMinute: 4U System with HGX A100 8-GPU

For the most demanding AI workloads, Supermicro builds the highest-performance, fastest-to-market servers based on NVIDIA A100™ Tensor Core GPUs. With the newest version of NVIDIA® NVLink™ and NVIDIA NVSwitch™ technologies, these servers can deliver up to 5 PetaFLOPS of AI performance in a single 4U system.

Play the video

SuperMinute: 2U System with HGX A100 4-GPU

The new AS -2124GQ-NART server features the power of NVIDIA A100 Tensor Core GPUs and the HGX A100 4-GPU baseboard. The system supports PCI-E Gen 4 for fast CPU-GPU connection and high-speed networking expansion cards.

Play the video

Supermicro Ultra SuperServer による、高性能GPUを使用した仮想デスクトップ・インフラストラクチャ・ソリューション

Supermicroは、急速に成長する仮想デスクトップ・インフラストラクチャ（VDI）市場に対応するため、NVIDIAの仮想GPU（vGPU）ソフトウェアと、NVIDIAの高性能GPUを搭載した、完全に検証されたサーバーソリューションを開発しました。
View the white paper

1U 4 GPU サーバーのホワイトペーパー

1U 4 GPU ソリューションは、スーパーコンピューティング・サーバー分野におけるリーダーシップを発揮しています。
View the white paper
モデル
Card View List View
8U Universal GPU Systems1(2)
Loading Data
4U/5U GPU Lines with PCIe 5.02(6)
Loading Data
4U/5U Universal GPU systems2(6)
Loading Data
4U GPU with NVLink2(1)
Loading Data
NVIDIA MGX™ Systems3(2)
Loading Data
4U GPU Lines3(4)
Loading Data
4U GPU Lines with PCIe 4.04(2)
Loading Data
4U GPU with NVLink and PCIe 4.04(5)
Loading Data
2U 2-Node Multi-GPU with PCIe 4.05(3)
Loading Data
2U GPU Lines6(6)
Loading Data
1U GPU Lines7(6)
Loading Data
GPU Workstation8(5)
Loading Data
1U GPU with NVLink11(2)
Loading Data
10U 16-GPU with NVLink13(1)
Loading Data
System List
Product GroupHiddenOrderSKUDescriptionLinkImageGenerationComingNewGlobalGPUGPU-GPUCPUCPU TypeDIMM SlotsDrive SizeDrivesNetworkingForm FactorTotal PCI-E Slots#Total PowerGPU TypeInterfaceRedundant PowerApplications

お問合せ / サービス

追加リソース

製品マトリクス