GPU Servers(42)

Key Applications

• Artificial Intelligence (AI)
• HPC
• AI / Deep Learning
• Deep Learning/AI/Machine Learning Development

Key Features

1. Dual-Socket, AMD EPYC™ 9004 Series Processors
2. • High density 4U system with NVIDIA® HGX™ H100 8-GPU
   • 8 NVMe for NVIDIA GPUDirect Storage
   • 8 NIC for NVIDIA GPUDirect RDMA (1:1 GPU Ratio)
   • Highest GPU communication using NVIDIA® NVLink®
3. 24 DIMM slots Up to 6TB: 4800 ECC DDR5
4. • 8 PCIe 5.0 x16 LP slots
   • 2 PCIe 5.0 x16 FHHL slots, 2 PCIe 5.0 x16 FHHL slots (optional)
5. 4x 5250W(2+2) Redundant Power Supplies, Titanium Level

Key Applications

• AI / Deep Learning
• High Performance Computing

Key Features

1. • Flexible GPU support: active & passive GPUs
   • Up to 8 direct attached double width, full length GPUs
   • 10 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
2. Dual-Socket, AMD EPYC™ 9004 Series Processors
3. 24 DIMM Slots, up to 6TB DDR5 memory
4. • up to 4x 2.5" Hot-swap NVMe drive bays
   • 1 M.2  Slot

Key Applications

• AI / Deep Learning
• High Performance Computing

Key Features

1. • Flexible GPU support: active & passive GPUs
   • Single Root Configuration with PCIe Switch for up to 10 double width, full length GPUs
   • 10 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
2. Single AMD EPYC™ 9004 Series Processors
3. 12 DIMM Slots, up to 3TB DDR5 memory
4. up to 8x 2.5" Hot-swap NVMe drive bays
5. AIOM / OCP 3.0 Support

Key Applications

• AI / Deep Learning
• High Performance Computing

Key Features

1. • Flexible GPU support: active & passive GPUs
   • Dual Root Configuration with PCIe Switch for up to 10 double width, full length GPUs
   • 10 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
2. Dual-Socket, AMD EPYC™ 9004 Series Processors up to 360W TDP
3. 24 DIMM Slots, up to 6TB DDR5 memory
4. • up to 8x 2.5" Hot-swap NVMe drive bays
   • 1 M.2  Slot
5. AIOM / OCP 3.0 Support

Key Applications

• High Performance Computing
• AI/Deep Learning Training
• Industrial Automation, Retail
• Climate and Weather Modeling

Key Features

1. • High density 8U system with NVIDIA® HGX™ H100 8-GPU
   • Highest GPU communication using NVIDIA® NVLINK™ + NVIDIA® NVSwitch™
   • 8 NIC for GPU direct RDMA (1:1 GPU Ratio)
2. 24 DIMM Slots; Up to 6TB DRAM; 4800 ECC DDR5 LRDIMM;RDIMM;
3. 8 PCIe Gen 5.0 X16 LP, and up to 4 PCIe Gen 5.0 X16 FHFL Slots
4. Flexible networking options
5. • 2x 2.5" Hot-swap  SATA drive bays
   • 1 M.2 NVMe for boot drive only
   • up to 16x 2.5" Hot-swap  NVMe drive bays (12 by default + 4 optional)
6. 10 heavy duty fans with optimal fan speed control
7. 6x 3000W redundant Titanium level power supplies

Key Applications

• High Performance Computing
• AI/Deep Learning Training
• Industrial Automation, Retail
• Climate and Weather Modeling

Key Features

1. • 8 NIC for GPU direct RDMA (1:1 GPU Ratio)
   • High density 8U system with AMD Instinct MI300X 8-GPU
2. 24 DIMM Slots; Up to 6TB DRAM; 4800 ECC DDR5 LRDIMM;RDIMM;
3. 8 PCIe Gen 5.0 X16 LP, and up to 4 PCIe Gen 5.0 X16 FHFL Slots
4. Flexible networking options
5. • 2x 2.5" Hot-swap  SATA drive bays
   • 1 M.2 NVMe for boot drive only
   • up to 16x 2.5" Hot-swap  NVMe drive bays (12 by default + 4 optional)
6. 10 heavy duty fans with optimal fan speed control
7. 6x 3000W redundant Titanium level power supplies

Key Applications

• High Performance Computing
• AI/Deep Learning Training and Inference
• Large Language Model (LLM) and Generative AI

Key Features This system currently supports two E1.S drives direct to the processor and the onboard GPU only. Please consult your Supermicro Salesperson for details. Two nodes in a 1U form factor. Each node supports the following:

1. High density 1U 2-node GPU system with Integrated NVIDIA® H100 GPU (1 per Node)
2. NVIDIA Grace Hopper™ Superchip (Grace CPU and H100 GPU)
3. NVLink® Chip-2-Chip (C2C) high-bandwidth, low-latency interconnect between CPU and GPU at 900GB/s
4. Up to 576GB of coherent memory per node including 480GB LPDDR5X and 96GB of HBM3 for LLM applications
5. 2x PCIe 5.0 x16 slots per node supporting NVIDIA BlueField®-3 or ConnectX®-7
6. 7 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
7. This system supports two E1.S drives directly from the processor only.

Key Applications

• High Performance Computing
• AI/Deep Learning Training and Inference
• Large Language Model (LLM) and Generative AI

Key Features This system currently supports two E1.S drives direct to the processor and the onboard GPU only. Please consult your Supermicro Salesperson for details. 

1. High density 1U GPU system with Integrated NVIDIA® H100 GPU
2. NVIDIA Grace Hopper™ Superchip (Grace CPU and H100 GPU)
3. NVLink® Chip-2-Chip (C2C) high-bandwidth, low-latency interconnect between CPU and GPU at 900GB/s
4. Up to 576GB of coherent memory per node including 480GB LPDDR5X and 96GB of HBM3 for LLM applications
5. 2x PCIe 5.0 x16 slots supporting NVIDIA BlueField®-3 or ConnectX®-7
6. 9 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
7. This system supports two E1.S drives directly from the processor only.

Key Applications

• High Performance Computing
• AI/Deep Learning Training and Inference
• Large Language Model (LLM) and Generative AI

Key Features This system currently supports two E1.S drives direct to the processor and the onboard GPU only. Please consult your Supermicro Salesperson for details. 

1. High density 1U GPU system with Integrated NVIDIA® H100 GPU and liquid cooling
2. NVIDIA Grace Hopper™ Superchip (Grace CPU and H100 GPU)
3. NVLink® Chip-2-Chip (C2C) high-bandwidth, low-latency interconnect between CPU and GPU at 900GB/s
4. Up to 576GB of coherent memory per node including 480GB LPDDR5X and 96GB of HBM3 for LLM applications
5. 2x PCIe 5.0 x16 slots supporting NVIDIA BlueField®-3 or ConnectX®-7
6. 7 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
7. This system supports two E1.S drives directly from the processor only.

Key Applications

• High Performance Computing
• Hyperscale Cloud Applications
• Data Analytics

Key Features Pending a firmware fix, this system currently supports four E1.S drives and two GPUs. Please consult your Supermicro Salesperson for details. Two nodes in a 1U form factor. Each node supports the following:

1. High density 1U 2-node system with NVIDIA Grace™ CPU Superchip per node
2. NVLink® Chip-2-Chip (C2C) high-bandwidth, low-latency interconnect between CPU and CPU at 900GB/s
3. Up to 480GB LPDDR5X onboard memory
4. 2x PCIe 5.0 x16 slots per node supporting NVIDIA BlueField®-3 or ConnectX®-7
5. Up to 4x Hot-swap E1.S drives and 2x M.2 NVMe drives per node
6. 7 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
7. Pending a firmware fix, this system currently supports four E1.S drives and two GPUs. Please consult your Supermicro Salesperson for details.