NVIDIA has this week unveiled something extremely interesting, called the NVIDIA DGX-1, it is what NVIDIA claims to be the “world’s first deep-learning supercomputer”, which has been designed to offer solutions for artificial intelligence applications.
It will come integrated with its own development tools and hardware fo this, and according to NVIDIA, it can deliver the equivalent throughput of 250 x86 servers.
To do this, it has been equipped with the new NVIDIA Pascal GPU which is based on NVIDIA’s P100 GPUs and comes in a single box that features 250 CPU-based servers, some networking, cables and racks, all for around $129,000.
NVIDIA explains more about the supercomputer :
The DGX-1 deep learning system enables researchers and data scientists to easily harness the power of GPU-accelerated computing to create a new class of intelligent machines that learn, see and perceive the world as humans do. It delivers unprecedented levels of computing power to drive next-generation AI applications, allowing researchers to dramatically reduce the time to train larger, more sophisticated deep neural networks.
NVIDIA designed the DGX-1 for a new computing model to power the AI revolution that is sweeping across science, enterprises and increasingly all aspects of daily life. Powerful deep neural networks are driving a new kind of software created with massive amounts of data, which require considerably higher levels of computational performance.
You can read more about the supercomputer at the source link below.