Nor-Tech at the Leading Edge
NVIDIA Volta Deep Learning System
NVIDIA DGX-1 fast-tracks AI, data science, and other high performance computing-dependent initiatives with an easy-to-deploy solution—delivering insights in hours rather than months. DGX-1 allows Nor-Tech clients to simply plug in, power up, and start deep learning training in as little as a day. This is made possible by the integrated NVIDIA deep learning software stack and DGX-1 Cloud management services. The Volta GV100 GPU powers three systems designed by NVIDIA: the DGX-1V, HGX-1V, and the DGX Station. All three systems make use of multiple Tesla® V100 graphics cards and carry enormous power.
Part Number DGX-1 Volta:
920-22787-2510-000
3 Year Support: 718-22787-2510-003
Product Class/Type:
Deep Learning System with 3 Year Support
GPU Memory:
16GB per GPU
TFLOPS/CPU:
960/ Dual 20-core Intel Xeon E5-2698 v4 2.2 GHz
NVIDIA CUDA Cores:
40960
System Memory:
512 GB 2133 MHz DDR4 LRDIMM
Storage:
4x 1.92 TB SSD RAID 0
Network:
Dual 10Gbe, 4 IB EDR
Software:
Ubuntu Server Linux OS
DGX-1 Recommended GPU Driver
System Weight:
134 lbs
System Dimensions:
866 D x 444 W x 131 H (mm)
Packing Dimensions:
1180 D x 730 W x 284 H (mm)
Max Power Requirements:
3200W
Operating Temperature Range:
10-35C
IBM POWER8
Nor-Tech’s price competitive system will be available in the fall of 2017.
IBM and NVIDIA announced the results of their first collaboration with the release of the Power System S822LC for High-Performance Computing. One major international internet service provider reported that a cluster integrated with the new chip can run workloads three times faster when compared with the previous x86-based setup, while using only one-third the number of servers. The system contains two updated Power8 CPUs between eight and ten cores each, and four NVIDIA Tesla P100 GPUs. NVIDIA’s NVLink interconnect moves the data between those devices. IBM through its open source agreements with NVIDIA, integrated the NVLink into the POWER8. The NVLink offers vastly higher bandwidth for the NVIDIA GPU to communicate with the Power8 versus the PCIe 3.0 bus where data must travel in an Intel based CPU/GPU server.
Nor-Tech’s Innovative HPC Solutions
Nor-Tech’s groundbreaking HPC Solutions have been at the forefront of innovation for more than a decade. Nor-Tech offers a variety of HPC clusters, including standard 42U rackmount clusters, GPU clusters and visualization clusters, as well as the award-winning Portable Cluster. Nor-Tech has developed… Read more »
Intel® HPC Orchestrator
Intel® HPC Orchestrator HPC Orchestrator is Intel’s version of the OpenHPC platform, which is an open source framework for operating HPC clusters. HPC Orchestrator is a licensed, value-added version of OpenHPC and is supported by Intel and Nor-Tech. We worked with Intel on testing and development for several months prior to the release. HPC Orchestrator… Read more »
Nor-Tech HPC Clusters and Intel Omni-Path for Seamless Performance
Intel Omni-Path: The Next-Generation Fabric Nor-Tech’s Demo Cluster Intel Omni-Path, along with Intel Orchestrator will be integrated into our innovative demo cluster. As a widely acknowledged pioneer and leading expert in the HPC space, Nor-Tech has the hardware, software, and expertise to demonstrate the immediate ROI of running your applications on a Nor-Tech cluster. This… Read more »