The GPU Development Conference wrapped up last week, and there were several exciting announcements coming from Nvidia. Jen-Hsun Huang, Nvidia CEO, addressed some of the company’s technological breakthroughs in his keynote address to the conference. The company unveiled Nvidia’s Tesla P100 graphics card which uses the new Pascal architecture, as well as some amazing tech for business and research.
The Pascal P100 combines is the first chip build on the company’s newly developed architecture, and combines 5 new Nvidia technologies: The Pascal Architecture, HBM2, NVLink interconnect, AI algotithms, and 16 nm FinFET technology. The new card features 15.3 billion transistors and 16GB of HB2 memory. The new GPU also runs at an incredible clock speed, 1328 MHz.
The product is capable of tremendous computing power and is intended to be used primarily for data centers, rather than high end gaming.
For users who are looking for something a little beefier than just a single P100, the rack-mounted DGX-1 is powered by a set of eight Tesla P100s. It’s specifically engineered for AI and deep learning development, making it first of its kind. Nvidia claims its memory has as much throughput as 250 x86 servers, and it also has 7TB of SSD storage right on board.
What does this mean in terms of performance? DGX-1 is equivalent to 250 servers, according to NVIDIA. DGX-1 has been received well by consumers, as all systems have already been booked. The company aims to launch the product in 1Q17.
Overall, Nvidia has some very exciting developments on the horizon, and it looks like they have begun to take a much more serious look at business applications for their products. With the ability to find patterns in massive pools of data, Nvidia’s new products could lead to research breakthroughs in several industries.