Featured Articles

Hands on: Nvidia Shield Tablet with Android 5.0

Hands on: Nvidia Shield Tablet with Android 5.0

We broke the news of Nvidia's ambitious gaming tablet plans back in May and now the Shield tablet got a bit…

More...
Nokia N1 Android tablet ships in Q1 2015

Nokia N1 Android tablet ships in Q1 2015

Nokia has announced its first Android tablet and when we say Nokia, we don’t mean Microsoft. The Nokia N1 was designed…

More...
Marvell launches octa-core 64-bit PXA1936

Marvell launches octa-core 64-bit PXA1936

Marvell is better known for its storage controllers, but the company doesn’t want to give up on the smartphone and…

More...
TSMC 16nm FinFET Plus in risk production

TSMC 16nm FinFET Plus in risk production

TSMC’s next generation 16nm process has reached an important milestone – 16nm FinFET Plus (16FF+) is now in risk production.

More...
Nvidia GTX 970 SLI tested

Nvidia GTX 970 SLI tested

Nvidia recently released two new graphics cards based on its latest Maxwell GPU architecture, with exceptional performance-per-watt. The Geforce GTX 970…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Tuesday, 25 March 2014 18:43

Nvidia announces Pascal, its 2016 chip

Written by Fuad Abazovic



3D stacked chip

Nvidia just announced a new 2016 chip and it's called Pascal. This is the successor to the Maxwell DirectX 12 architecture and it will bring a few unique features to the market.

The first interesting feature is NVLink, a bandwidth improving inter-chip communication solution that should solve the bandwidth problem faced by multi GPU platforms. It is based on PCIe 3.0 but it can make things significantly faster, 5 to 12 times faster according to Nvidia. This is a huge gain and it should bring communication between the CPU and GPU to a whole new level.

Pascal also packs 3D stacked memory that is in the same chip packaging and it is about a third of the size of a PCIe card. It will launch in 2016, it will follow Moore's Law and deliver 20 Teraflops per second. Just for comparison, the original Tesla launched back in in 2008 was a 1TFLOPS unit, while Maxwell maxes out at 12TFLOPS.

Nvidia CEO Jen-Hsun Huang showed off the Pascal test module on stage, but we still have to see the demo. 

We will ask around and try to find out what happened to Volta, that is either renamed to Pascal, or it got scrapped, but Nvidia's roadmaps placed Volta right after Maxwell.

nvidia GTC2014Pascal-1

nvidia GTC2014Pascal-2

nvidia GTC2014Pascal-3 

 

Last modified on Tuesday, 25 March 2014 18:59
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments