AS-2145GH-TNMR
2U 4-GPU Server, AMD Instinct MI300A Accelerator (liquid-cooled)
- Quad AMD® EPYC™ MI300A processors
- HBM3 Stacks 512GB
- Optional PCIe configurations up to 6 PCIe slots x16 FHHL
- Flexible networking options with 2 AIOM networking slot (OCP NIC 3.0 compatible)
- Default 8x 2.5" Hot-swap NVMe or Optional 8x 2.5" SAS3/SATA3 via storage add-on card;
- 2x internal M.2 NVMe/SATA;
- 3 heavy duty fans w/ Liquid Cooled
- 4x 1600W redundant Titanium level power supplies
Product SKUs | A+ Server AS -2145GH-TNMR (Black) |
Motherboard | Super H13QSH |
Processor | |
CPU | Quad Socket SH5 AMD Instinct™ MI300A Accelerated Processing Units (APUs) |
Note | Supports up to 760W TDP CPUs (Liquid Cooled) |
GPU | |
Max GPU Count | 4 onboard GPU(s) |
Supported GPU | AMD: MI300A |
System Memory | |
Memory | Max Memory (1DPC): Up to 512GB ECC HBM3 |
On-Board Devices | |
Chipset | AMD SH5 |
Network Connectivity | Via AIOM |
Input / Output | |
LAN | 1 RJ45 Dedicated IPMI LAN port |
USB | 2 USB 2.0 port(s) (2 front) 2 USB 3.0 port(s) (2 rear) |
Video | 1 VGA port(s) 1 DisplayPort (s) |
Serial Port | 1 COM Port(s) (1 rear) |
System BIOS | |
BIOS Type | AMI 32MB SPI Flash EEPROM |
Security | |
Hardware | Trusted Platform Module (TPM) 2.0 |
PC Health Monitoring | |
CPU | 4+1 Phase-switching voltage regulator Monitors for CPU Cores, Chipset Voltages, Memory |
FAN | Fans with tachometer monitoring Pulse Width Modulated (PWM) fan connectors Status monitor for speed control |
Temperature | Monitoring for CPU and chassis environment Thermal Control for fan connectors |
Chassis | |
Form Factor | 2U Rackmount |
Model | CSE-218H2TS-R3K2AWP |
Dimensions and Weight | |
Height | 3.5" (87.9mm) |
Width | 17.3" (438.4mm) |
Depth | 32" (812.9mm) |
Package | 9.75" (H) x 26.5" (W) x 43.5" (D) |
Weight | Net Weight: 45.5 lbs (20.64 kg) Gross Weight: 71.5 lbs (32.43 kg) |
Available Color | Black |
Expansion Slots | |
PCI-Express (PCIe) | 4 PCIe 5.0 x16 FHHL slot(s) 2 PCIe 5.0 x16 AIOM slot(s) |
Drive Bays / Storage | |
Hot-swap | 8x 2.5" hot-swap NVMe/SAS3/SATA3 drive bays |
M.2 | 2 M.2 NVMe OR 2 M.2 SATA3 |
System Cooling | |
Fans | 3 Heavy duty counter-rotating 8cm Fan(s) |
Liquid Cooling | Direct to Chip (D2C) Cold Plate (optional) |
Power Supply | 1600W Redundant Titanium Level power supplies |
Dimension (W x H x L) | 73.5 x 40 x 203 mm |
AC Input | 1000W: 100-127Vac / 50-60Hz 1600W: 200-240Vac / 50-60Hz |
+12V | Max: 83.3A / Min: 0A (100Vac-127Vac) Max: 133A / Min: 0A (200Vac-240Vac) |
12V SB | Max: 2.1A / Min: 0A |
Output Type | Backplanes (gold finger) |
Operating Environment | |
RoHS | RoHS Compliant |
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) |
Targeting accelerated HPC workloads, this 2U 4-way multi-APU system with liquid cooling integrates 4 AMD Instinct™ MI300A accelerators. Each APU combines high-performance AMD CPU, GPU and HBM3 memory for a total of 912 AMD CDNA™ 3 GPU compute units and 96 “Zen 4” cores in one system. Supermicro's direct-to-chip custom liquid-cooling technology enables exceptional TCO with over 51% data center energy cost savings. Furthermore, there is a 70% reduction in fans compared to air-cooled solutions. The rack-scale integration optimized with the dual AIOM and 400G networking creates a high-density supercomputing cluster with up to 21 2U systems in a 48U rack.
Quad APU Liquid Cooled Server
Powered by AMD Instinct™ MI300A Accelerators
Targeting accelerated HPC workloads, 2U liquid cooled systems integrate 4 AMD Instinct™ MI300A APU accelerators
- 4 APUs combine high-performance AMD CPU, GPU and HBM3 memory for a total of 912 AMD CDNA™ 3 GPU compute units and 96 “Zen 4” cores, and 512GB of unified HBM3 memory in one system.
- PCIe 5.0 expansion slots for high-speed networking including RDMA to APU memory
- 2 PCIe 5.0 Open Compute Project (OCP) 3.0 AIOM slots
- Fully optimized for the most popular AI & ML frameworks—PyTorch, TensorFlow, JAX, ONYX-RT, Triton
Proven to Perform at Scale
Industry-Proven System Designs
8U high-performance fabric 8-GPU system leveraging industry-standard OCP Accelerator Module (OAM) to support AMD’s MI300X Accelerators. 4U and 2U multi-processor APU systems integrate 4 AMD Instinct™ MI300A accelerators.
Purpose Built for AI & HPC
Feature maximized and power optimized, supporting up to 16x dedicated hot-swap NVMe drives, full-performance GPUs, CPUs, and memory, and high-speed networking for large-scale cluster deployments.
Advanced Cooling Options
Flexible cooling options for air- and liquid-cooled racks, with liquid-cooled solutions delivering exceptional TCO with over 51% data center energy cost savings.
Designed to Scale
Designed with full scalability in mind, supporting 8 high-speed 400G networking cards providing direct connectivity to each GPU for massive AI clusters.