HPC/AI Server with NVIDIA HGX™ H100 GPUs and Dual Intel® Xeon® Scalable Processors

Datacenter

HPC/AI Server G593-SD2-AAX1

5U NVIDIA-Certified Server Optimized for AI Training, Inference, and High-Performance Computing

NVIDIA HGX™ H100 with 8 x SXM5 GPUs
900GB/s GPU-to-GPU bandwidth with NVIDIA® NVLink® and NVSwitch™
Dual 5th/4th Gen Intel® Xeon® Scalable Processors
NVIDIA-Certified Systems™ - Data Center Servers
Dual Intel® Xeon® CPU Max Series
4+2 3000W 80 PLUS Titanium redundant power supplies

Enquire Now

Accelerating Artificial Intelligence and Leading Efficiency

Redefine Performance with 4th/5th Gen Intel Xeon Scalable Processors and Intel Xeon CPU Max Series

Engineering richer features in a revolutionary platform, Intel has made an incredible jump in processor performance in the business transformation journey. AI and deep learning performance will benefit from the built-in AI acceleration engines, while networking, storage, and analytics leverage other specialized accelerators in the 4th & 5th Gen Intel Xeon Scalable processors. Adding a host of new features to target a wide range of workloads, the new families of Intel Xeon processors will deliver even better CPU performance and performance per watt, and do so on a PCIe 5.0 platform with 2x the prior gen throughput to greatly speed up data movement to and from GPUs and storage. Intel also created the Intel Xeon CPU Max Series with High Bandwidth Memory (HBM) for improvements in memory bound HPC and AI workloads. For this new platform, GIGABYTE has products ready to get the most out of Intel Xeon CPU-based systems that support fast PCIe Gen5 accelerators and Gen5 NVMe drives, in addition to support for high performant DDR5 memory.

Power Efficiency

Automatic Fan Speed Control

GIGABYTE servers are enabled with Automatic Fan Speed Control to achieve the best cooling and power efficiency. Individual fan speeds will be automatically adjusted according to temperature sensors strategically placed in the servers.

High Performance

Supports NVIDIA HGX™ H100 8-GPU

NVIDIA HGX™ H100 brings together the full power of NVIDIA H100 GPUs and fully optimized NVIDIA AI and NVIDIA HPC software stacks. NVIDIA HGX™ H100 is available as a server building block in the form of integrated baseboards in four or eight H100 GPU configurations. Four GPU HGX H100 offers fully interconnected point to point NVLink™ connections between GPUs while the eight GPU configuration offers full GPU to GPU bandwidth through NVSwitch. Leveraging the power of H100 multi-precision Tensor Cores, an 8-way HGX H100 provides over 32 petaFLOPS of FP8 deep learning compute performance. NVIDIA HGX™ H100 also includes NVIDIA BlueField®-3 data processing units (DPUs) to enable cloud networking, composable storage, zero-trust security, and GPU compute elasticity in hyperscale AI clouds.