Nor-Tech’s 4 GPU Servers and 8 GPU Servers
Nor-Tech has been building and integrating 4 and 8 GPU servers for Fortune 500 companies and leading research institutes for over 2 decades.
Take advantage of our Demo Cluster to Test your code on AMD and NVIDIA GPUs
Expect uncompromising quality, best performance per-watt, per square-foot, per-dollar; lowest total cost of ownership and highest quality components and materials. Nor-Tech’s 4 and 8 GPU servers support up to 8 active/passive GPUs and come with GPU health monitoring and fan speed control.
All of Nor-Tech’s HPC technology is backed by our industry-leading NT-EZ HPC Cluster Support Solutions Portfolio
SOFTWARE INTEGRATION EXPERTISE
Nor-Tech has a well-deserved reputation as one of the most qualified software integrators in the industry. We work hard to ensure that all software is properly integrated when it leaves our manufacturing facility. This allows clients to begin work within hours of cluster delivery.
Nor-Tech is also widely acknowledged as one of the leading experts on Linux high-performance solutions, offering a full range of open source, Linux-based technology from servers to turn-key HPC clusters. This is a key qualifier for system builders and integrators since 99.6% of the fastest supercomputers now run Linux.
Open source software is significantly less expensive. However, without expertise; complexity, troubleshooting, and maintenance are issues. This is where Nor-Tech comes in. Nor-Tech’s engineering team, which averages 10+ years of Linux experience, excels at provisioning, scheduling and resource management of cluster hardware; maximizing compilers and accelerators; and configuring the low latency fabric that connects nodes together.
NVIDIA H100 GPUs
The NVIDIA® H100 Tensor Core GPU delivers unprecedented acceleration to power the world’s highest-performing elastic data centers for AI, data analytics, and high-performance computing (HPC) applications. NVIDIA H100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA H100 PCIe supports double precision (FP64), single-precision (FP32), half precision (FP16), and integer (INT8) compute tasks.
NVIDIA A100 GPUs
NVIDIA A100 Tensor Cores with Tensor Float (TF32) provide up to 20X higher performance over the NVIDIA Volta with zero code changes and an additional 2X boost with automatic mixed precision and FP16. When combined with NVIDIA® NVLink®, NVIDIA NVSwitch™, PCI Gen4, NVIDIA® Mellanox® InfiniBand®, and the NVIDIA Magnum IO™ SDK, it’s possible to scale to thousands of A100 GPUs.
The AMD Instinct series accelerators are the newest data center GPUs from AMD, designed to power discoveries in mainstream servers and supercomputers, including some of the largest exascale systems, enabling scientists to tackle our most pressing challenges from climate change to vaccine research. AMD Instinct supercharge AI and HPC workloads with their purpose-built AMD CDNA architecture, delivering powerful compute, high bandwidth memory and I/O offering expanded topology capabilities. The ROCm™ open ecosystem environment gives developers the choice to code once and use it everywhere, paving an open path to exascale.
Universal GPU Servers
With multi-architecture flexibility and future-proof open-standards based design, our Universal GPU Server is the industry’s most advanced and flexible GPU server platform. Designed for large-scale AI deep learning and HPC workloads, this modular, standards-based platform supports the best available GPU technologies in a variety of form factors and combinations both today and into the future.
- 4U and 5U Universal GPU systems
- Dual 3rd Gen Intel® Xeon® Scalable or AMD EPYC™ 7003 Series processors
- Supports a range of industry-standard GPU form factors
- Modular design for maximum flexibility
- 4U chassis supports up to 10x 2.5” NVMe/SATA drives
- Optional 1U expansion module for improved thermal capacity up to 700W GPUs and 2 additional AIOM/PCIe slots
Take advantage of our Demo Cluster to Test your code on AMD INSTINCT and NVIDIA GPUs