Featured Articles

TSMC: Volume production of 16nm FinFET in 2H 2015

TSMC: Volume production of 16nm FinFET in 2H 2015

TSMC has announced that it will begin volume production of 16nm FinFET products in the second half of 2015, in late…

More...
AMD misses earnings targets, announces layoffs

AMD misses earnings targets, announces layoffs

AMD has missed earnings targets and is planning a substantial job cuts. The company reported quarterly earnings yesterday and the street is…

More...
Did Google botch the Nexus 6 and Nexus 9?

Did Google botch the Nexus 6 and Nexus 9?

As expected, Google has finally released the eagerly awaited Nexus 6 phablet and its first 64-bit device, the Nexus 9 tablet.

More...
Gainward GTX 970 Phantom previewed

Gainward GTX 970 Phantom previewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
EVGA GTX 970 SC ACX 2.0 reviewed

EVGA GTX 970 SC ACX 2.0 reviewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Thursday, 26 June 2008 13:58

Rambus in talks with GPU makers

Written by test

Image

Doesn’t want to talk about details


At an
event earlier today in Taiwan, Rambus talked a lot about the bandwidth needs of both graphics cards and consoles and it seems like the company is very hopeful about a bright future in this market segment.

One of the people we talked to admitted that Rambus was talking to the various GPU manufacturers and considering that Nvidia already has some experience working with Rambus on the PS3 graphics solution, it’s not too far fetched that the company could be considering a Rambus solution in the future.

Rambus’ XDR technology offers some advantages over GDDR, such as easier PCB tracing and high bandwidth, two things that should be interesting for companies making graphics cards. On top of this, Rambus is working on what they’re calling the Terabyte bandwidth initiative, which should allow for some very fast memory in the future. The demo board didn’t look like much and even today’s fastest XDR memory only runs at 500MHz, which is slow even compared to GDDR5 at 900MHz.

But as GDDR5 has a four times internal multiplier, XDR has an eight times multiplier and the Terabyte bandwidth initiative is going after a 32 times multiplier. That means that if this memory would be clocked at 500MHz when it arrives, it would offer 1.6TB/s in bandwidth, although it’s likely that first generation memory of this type won’t come in at much more than 333MHz.

This could lead to some interesting memory solutions for graphics cards in the future, but time will tell if this is a path that the GPU makers are willing to go down.

Last modified on Friday, 27 June 2008 05:32
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments