What We Showcased

At GTC 2017, visitors explored and gained the knowledge needed to transform the future of artificial intelligence and deep learning, virtual reality, self-driving cars, and more. GTC 2017 attracted developers, researchers, and technologists from some of the top companies, universities, research firms, and government agencies from around the world. The event showcased some of the most vital work in the computing industry today and displayed some of the technological advancements that will pave the way for our future.

During GTC, Exxact exhibited some of our newest NVIDIA® GPU-based developments for HPC, Life Sciences, Deep Learning, Visualization, and more. As an NVIDIA NPN Elite Partner, we pride ourselves in developing some of the most robust, affordable, and efficient NVIDIA GPU-powered systems that are strictly catered to each one of our customers.

In case you missed us, here are some of our new product highlights from the show:

• The World's First NVLink Workstation
• Exxact Quadro Visualing Computing Appliance (VCA)
• Our latest Deep Learning Solutions Featuring Docker
• Life Science Solutions Featuring NVIDIA Pascal Technology

NVIDIA's Announcements

GTC 2017 also showcased a whole new chapter in the AI revolution with new NVIDIA product announcements. At GTC 2017, we witnessed the unveiling of the Tesla® V100 GPU powered by the new NVIDIA Volta architecture. Built with 21 billion transistors, the Volta-powered V100 is said to deliver deep learning performance equal to 100 CPUs. The V100 is based on the new NVIDIA Volta GV100 GPU and offers a platform for HPC systems to excel at both computational sciences for scientific simulation and data science for finding insights in data. The V100 is said to deliver considerably more compute performance and adds many new features compared to its previous Pascal GP100 GPU and its architecture family.

Following the V100 announcement, NVIDIA introduced the DGX Station™ and DGX-1™ featuring Tesla V100 GPU accelerators based on the new NVIDIA Volta™ architecture. Introduced last year, DGX-1 systems now power a wide range of AI deployments at research organizations, leading enterprises, and cloud service providers worldwide. The new Volta-based DGX-1 delivers the computing capacity of 800 CPUs in a single, small server footprint.

The new DGX Station was introduced as the world's first personal supercomputer for AI development. It features the computing capacity of 400 CPUs, consuming nearly 40x less power, in a water-cooled and whisper-quiet chassis that fits at your desk side. NVIDIA claimed the DGX Station is the world's quietest workstation and that it draws one-tenth the noise as other deep learning workstations. Researchers and data scientists can use the DGX Station for compute-intensive AI exploration, including training deep neural networks, inferencing, and advanced analytics.

NVIDIA Tesla V100 and DGX System Availability

The first NVIDIA Tesla V100 GPUs will only be available in the DGX-1 for now. There is no expected ship date for the GPUs alone, however, they can be pre-ordered through Exxact here:

• Tesla V100 for PCIe: www.exxactcorp.com/tesla-v100-pcie
• Tesla V100 for SXM2: www.exxactcorp.com/tesla-v100-sxm2

Volta-based DGX Station and DGX-1 servers are now available for order through Exxact and are expected to ship in the third quarter of this year. Further information including support options and detailed technical specifications can be found here:

• DGX-1: www.exxactcorp.com/dgx-1
• DGX Station: www.exxactcorp.com/dgx-station