Farraguter Nvidia Places Bet on Artificial Intelligence With New Chip

Each of those SMs also contains 32 FP64 CUDA cores, giving us the 1/2 rate for FP64 and new to the Pascal architecture is the ability to pack 2 FP16 operations inside a single FP32 CUDA core, when under the right conditions.Nvidia has just announced a new GPU platform called the Tesla P100. NVIDIA NVLink for maximum application scalability – The NVIDIA NVLink high-speed GPU interconnect scales applications across multiple GPUs, delivering a 5x acceleration in bandwidth compared to today's best-in-class solution.Specifically, the DGX-1 can pump out 170 teraflops – that's 170,000 floating operations per second – with its eight 16GB Tesla P100 graphics chips.The hype for the upcoming next generation NVIDIA GeForce Pascal graphics processing units is now at an all-time high as majority of the reports are claiming that the GPUs might be making their way into the market in the coming months. The GPU is meant for data centers, scientific and technical research, or churning statistics. It features NVIDIA's new Pascal GPU architecture, the latest memory and semiconductor process, and packaging technology – all to create the densest compute platform to date.Other technologies employed in the DGX-1 include 16nm FinFET fabrication technology, for improved energy efficiency; Chip on Wafer on Substrate with HBM2, for maximizing big data workloads; and new half-precision instructions to deliver more than 21 teraflops of peak performance for deep learning.Nvidia's new GPU is the first to be based on its Pascal architecture. It provides the throughput of 250 CPU-based servers, networking, cables and racks – all in a single box. This core is clocked at 1,328 MHz with boost clocks up to 1,480 MHz.