- Rugged 4U 19” rack enclosure for high-performance GPU server applications
- Dual-socket Intel® Xeon® scalable processor
- 8x PCIe x16 Gen3 slots for GPUs, AI accelerators and expansion cards
- 2x 10 Gigabit Ethernet ports with Intel® X550-AT2 controller for fast network connections
- Up to 14x 2.5” hot-swap SATA for flexible storage options
FEATURES
Description
SHARK A.I. 8-Slot GPU server – High-performance AI and HPC platform for maximum GPU density
The SHARK A.I. 8-slot GPU server is a universal carrier-grade platform designed for demanding AI, deep learning and high-performance computing (HPC) applications. By combining a powerful server node with PCIe expansion and PCIe switch technology, the system supports up to eight NVIDIA® GPUs, providing maximum computing power for data-intensive workloads. Thanks to the scalable architecture, topologies and bandwidths between GPUs and CPUs can be flexibly adapted. InfiniBand support enables easy scaling across multiple GPU clusters and ensures maximum efficiency for parallel computing.
Maximum GPU performance with flexible architecture
With eight PCIe slots for dual-slot GPUs, the SHARK A.I. offers exceptional computing performance for deep learning, neural networks and HPC applications. The system supports both single-root and dual-root complexes, allowing the resource allocation to be optimally adapted to the respective application. Single-root setups pool all GPU resources for intensive AI training, while dual-root configurations improve CPU utilization and enable more efficient parallel processing.
Dynamic PCIe allocation for optimized workloads
The SHARK A.I. 8-slot GPU server offers intelligent PCIe lane allocation that assigns GPUs to specific I/O interfaces or CPU cores. This improves the data flow between CPUs and GPUs and optimizes performance for virtualized AI and HPC workloads. Thanks to the modular architecture, the need for additional server systems is reduced, which minimizes energy consumption, cooling and space requirements.
Edge High Performance Computing (EHPC) for maximum scalability
As a powerful Edge High Performance Computing (EHPC) solution, the SHARK A.I. significantly increases the flexibility of cloud and data center infrastructures. It enables the free allocation of GPUs per virtual machine (VM) and allows the implementation of different head nodes to efficiently manage compute-intensive applications. This makes it the ideal platform for GPU-supported simulations, remote virtualization and AI-supported analyses.
Specifications
| Product: SHARK A.I. 8-Slot GPU server | |
|---|---|
| SYSTEM | |
| CPU | Dual-socket Intel® Xeon® scalable processor, max up to 205W TDP |
| Chipset | Intel® C621 |
| GPU | Supports Single & Dual Root Complex Design 8x PCIe x16 Gen3 graphics card slots |
| RAM | Up to 3TB DDR4 2666MHz (24x DIMM slots) |
| Storage | 14x 2.5″ SATA 6Gbit/s (hot swap) |
| Expansion | 1x PCIe x16 Gen3 slot (low profile) 1x PCIe x8 Gen3 storage (mezzanine slot) |
| TPM | Optional |
| INTERFACE | |
| Ethernet | 2x 10-Gigabit Ethernet ports 1x Gigabit Ethernet ports (for IPMI) Intel® X550-AT2 controller |
| USB | 2x USB 3.0 (front) |
| COM | 1x COM (2×5-pin header) |
| Video | 1x VGA port |
| ENVIRONMENTAL | |
| Chassis | 4U 19″ rack enclosure |
| Cooling | 6x 12cm fan (hot-swap) |
| Power Supply | 3200W AC/DC Platinum power adapter; 2+1 redundancy Input: 2000W: 100~270V AC / 12.9A 3200W: 220 ~ 240V AC/ 9.5A |
| Operating Temperature | 10°C ~ 35°C |
| Storage Temperature | -40° ~ 70°C |
| Humidity | 90% @ 35° C non-condensing |
| Dimensions (W x H x D) | 438 x 176 x 770mm |
| Certifications | FCC (DoC), CE (DoC), CB/LVD, RCM, VCCI RoHS 6/6 conform |
