AS-4126GS-NBR-LCC
DP AMD 4U Liquid-Cooled GPU Server with NVIDIA HGX B200 8-GPU
- *Complete liquid-cooled rack integration is required for purchase
- Dual processor(s) AMD EPYC™ 9005/9004 Series Processors up to 500W with Liquid Cooling
- Support for up to 8 onboard SXM GPU accelerator cards with Liquid Cooling
- Up to 24 DIMMs supporting up to 9TB DDR5-6000 in 1DPC
- 2 RJ45 10GbE
- Up to 8 PCIe 5.0 x16 LP + 2 PCIe 5.0 x16 FHHL slots
- Up to 8 front hot-swap 2.5" NVMe
Applications:
- High Performance Computing
- AI/Deep Learning Training
- Industrial Automation, Retail
- Healthcare
- Conversational AI
- Business Intelligence & Analytics
- Drug Discovery
- Climate and Weather Modeling
- Finance & Economics
Datasheet
Product Specification
| Product SKUs | A+ Server AS -4126GS-NBR-LCC |
| Motherboard | Super H14DSG-OD |
| Processor | |
| CPU | Dual processor AMD EPYC™ 9005/9004 Series Processors |
| Core Count | Up to 192C/384T; Up to 384MB Cache per CPU |
| Note | Supports up to 500W TDP CPUs (Liquid Cooled) |
| GPU | |
| Max GPU Count | 8 onboard GPUs |
| Supported GPU | NVIDIA SXM: HGX B200 8-GPU (180GB) |
| CPU-GPU Interconnect | PCIe 5.0 x16 CPU-to-GPU Interconnect |
| GPU-GPU Interconnect | NVIDIA® NVLink® with NVSwitch™ |
| System Memory | |
| Memory | Slot Count: 24 DIMM slots Max Memory (1DPC): Up to 9TB 6000MT/s ECC DDR5 RDIMM |
| Memory Voltage | 1.1V |
| On-Board Devices | |
| Chipset | System on Chip |
| Network Connectivity | 2 RJ45 10GbE with Intel® X710 |
| Input / Output | |
| LAN | 1 RJ45 1 GbE Dedicated BMC LAN port |
| USB | 2 USB 3.0 Type-A ports(Rear) |
| Video | 1 VGA port |
| TPM | 1 TPM header |
| System BIOS | |
| BIOS Type | AMI 64MB SPI Flash EEPROM |
| Management | |
| Software | SuperCloud Composer Supermicro Server Manager (SSM) Supermicro Update Manager (SUM) Supermicro SuperDoctor® 5 (SD5) uper Diagnostics Offline (SDO) Supermicro Thin-Agent Service (TAS) SuperServer Automation Assistant (SAA) New! |
| Security | |
| Hardware | Trusted Platform Module (TPM) 2.0 |
| PC Health Monitoring | |
| CPU | Monitors for CPU Cores, Chipset Voltages, Memory |
| FAN | Fans with tachometer monitoring Status monitor for speed control Pulse Width Modulated (PWM) fan connectors |
| Temperature | Monitoring for CPU and chassis environment Thermal Control for fan connectors |
| Chassis | |
| Form Factor | 4U Rackmount |
| Model | CSE-GP403TS-R000NP |
| Dimensions and Weight | |
| Height | 6.85" (174 mm) |
| Width | 17.6" (449 mm) |
| Depth | 35.25" (895.35 mm) |
| Package | 16.14" (H) x 50.39" (W) x 28.7" (D) |
| Weight | Gross Weight: 140 lbs (63.5 kg) Net Weight: 80 lbs (53 kg) |
| Available Color | Silver |
| Front Panel | |
| LED | Network activity LEDs System information (overheat/UID) UID |
| Buttons | Power On/Off UID/ Reset button |
| Expansion Slots | |
| PCI-Express (PCIe) Configuration | Default 8 PCIe 5.0 x16 LP slots 2 PCIe 5.0 x16 FHHL slots |
| M.2 | 2 M.2 NVMe slots (M-key 22110(default) |
| Drive Bays / Storage | |
| Drive Bays Configuration | Default: Total 8 bays 8 front hot-swap 2.5" PCIe 5.0 x4 NVMe drive bays |
| M.2 | 2 M.2 NVMe slots (M-key) |
| System Cooling | |
| Fans | 5x 6cm heavy duty fans with optimal fan speed control |
| Air Shroud | 1 Air Shroud |
| Liquid Cooling | Direct to Chip (D2C) Cold Plate |
| Power Supply | |
| 4x 6600W | 4x 6600W Redundant Titanium Level (96%) power supplies |
| Operating Environment | |
| Environmental Spec. | Operating Temperature: 10°C ~ 35°C (50°F ~ 95°F) Non-operating Temperature: -40°C to 60°C (-40°F to 140°F) Operating Relative Humidity: 8% to 90% (non-condensing) Non-operating Relative Humidity: 5% to 95% (non-condensing) |
4U
Liquid-Cooled
Rack Configuration
The new liquid-cooled 4U NVIDIA HGX B200 8-GPU system features newly developed cold plates and advanced tubing design paired with the new 250kW coolant distribution unit (CDU) more than doubling the cooling capacity of the previous generation in the same 4U form factor.
The new architecture further enhances efficiency and serviceability of the predecessor that are designed for NVIDIA HGX H100/ H200 8-GPU.l the way up to 12 systems with 96 NVIDIA GPUs in a 52U rack.
Available in 42U, 48U or 52U configuration, the rack scale design with the new vertical coolant distribution manifolds (CDM) means that horizontal manifolds no longer occupy valuable rack units. This enables 8 systems, 64 NVIDIA Blackwell GPUs in a 42U rack and all the way up to 12 systems with 96 NVIDIA GPUs in a 52U rack.
4U 8-GPU System
SYS-422GA-NBRT-LCC / AS-4126GS-NBR-LCC/ SYS-421GE-NBRT-LCC
| Overview | 4U Liquid-cooled System with NVIDIA HGX B200 8-GPU |
|---|---|
| CPU |
|
| Memory |
|
| GPU | NVIDIA HGX B200 8-GPU (180GB HBM3e per GPU) 1.8TB/s NVLink GPU-GPU interconnect with NVSwitch |
| Networking | 8 single-port NVIDIA ConnectX®-7 NICs or NVIDIA BlueField®-3 SuperNICs Up to 400Gbps 2 dual-port NVIDIA BlueField®-3 DPUs |
| Storage | 8 front hot-swap 2.5” NVMe drive bays 2 M.2 NVMe slots |
| Power Supply | 4x 6.6kW redundant Titanium Level power supplies |
