Today Exxact Corporation announced that the company is the official launch partner of Nvidia for the new DGX-1 deep learning supercomputer. Announced at the GPU Technology Conference, the DGX-1 further expands Exxact’s extensive portfolio of deep learning hardware solutions.
We are thrilled to be at the forefront of this exciting chapter in NVIDIA technology,” said Jason Chen, Vice President of Exxact Corporation. “The DGX-1 has the power to disrupt an already disruptive technology with its unrivaled Pascal GPU architecture. In the future, deep learning will be a part of every possible industry imaginable. Our products will help data scientists and artificial intelligence researchers achieve success faster and more efficiently than ever before.”
The NVIDIA DGX-1 features up to 170 teraflops of half precision (FP16) peak performance, 8 Tesla P100 GPU accelerators with 16GB of memory per GPU, 7TB SSD DL Cache, and a NVLink Hybrid Cube Mesh. Packaged with fully integrated hardware and easily deployed software, it is the world’s first system built specifically for deep learning and with NVIDIA’s revolutionary, Pascal-powered Tesla P100 accelerators, interconnected with NVIDIA’s NVLink. NVIDIA designed the DGX-1 to meet the never-ending computing demands of artificial intelligence and claims it can provide the throughput of 250 CPU-based servers delivered via a single box.
The system features a software stack that includes major deep learning frameworks such as the NVIDIA Deep Learning SDK, the DIGITS GPU training system, drivers and CUDA, meant for rapidly designing deep neural networks (DNN). Additionally, owners of the DGX-1 system will have access to cloud management services for container creation and deployment, system updates, and an application repository. Combining the Pascal-powered Tesla GPUs and the included software stack enables applications to run an estimated 12x faster than with past GPU-accelerated solutions.
Available now, the DGX-1 system is the newest addition to Exxact Corporation’s extensive selection of deep learning solutions such as the Quantum TXR414-1000R, an innovative 10 GPU peer-to-peer 4U solution. The Quantum TXR414-1000R features the latest NVIDIA GPU technology coupled with state-of-the-art PCIe peer-to-peer interconnect technology to enable capacities reaching up to 70 teraflops of single precision (FP32) peak performance.