NVIDIA has announced DGX-1 deep learning supercomputer at the company’s 2016 GPU Technology Conference. The NVIDIA DGX-1 deep learning system is built on NVIDIA Tesla P100 GPUs, based on the new NVIDIA Pascal GPU architecture.
NVIDIA says that the DGX-1 is capable of 170 teraflops of performance which NVIDIA says that is the equivalent of 250 servers relying only on Intel processors. The DGX-1 software includes the NVIDIA Deep Learning GPU Training System (DIGITS) for designing deep neural networks (DNNs). It also includes the newly released NVIDIA CUDA Deep Neural Network library (cuDNN) version 5, a GPU-accelerated library of primitives for designing DNNs. It features optimized versions of several widely used deep learning frameworks — Caffe, Theano and Torch. The DGX-1 additionally provides access to cloud management tools, software updates and a repository for containerized applications.
The NVIDIA DGX-1 system specifications:
- Up to 170 teraflops of half-precision (FP16) peak performance
- Eight Tesla P100 GPU accelerators, 16GB memory per GPU
- NVLink Hybrid Cube Mesh
- 7TB SSD DL Cache
- Dual 10GbE, Quad InfiniBand 100Gb networking
- 3U – 3200W
Jen-Hsun Huang, CEO and co-founder of NVIDIA said,
Artificial intelligence is the most far-reaching technological advancement in our lifetime. It changes every industry, every company, everything. It will open up markets to benefit everyone. Data scientists and AI researchers today spend far too much time on home-brewed high performance computing solutions.
NVIDIA is positioning this machine for serious research purposes. The NVIDIA DGX-1 is available for pre-order and is priced at $129,000. It will be available in the United States is in June, and in other regions beginning in the third quarter direct from NVIDIA and select systems integrators.