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 July 2007 11:14

AMD G3MX memory socket for Opteron

Written by test
Image

Ready in 2009

AMD has revealed that it's working on a new socket for memory expansion for its Opteron processors called G3MX or G3 Memory Extender. AMD is working together with IDT and Inphi to develop this new technology which is based on DDR3 memory.

The G3MX technology allows AMD to use 16 memory modules per CPU socket instead of the current limitation of eight. This might not seem like a big deal right now, but with larger databaes and virtulization technology, this could be a crucial feature for AMD's Opteron servers.

G3MX is only expected to appear in quad socket systems and beyond, so don't expect to see this appear on workstation motherboards or AMD's FX platform, at least not initially.

The trick here is that G3MX works similarly to the buffer on a FB-DIMM, but it's a single buffer instead of separate buffers on each memory module, which should allow for much lower latency.

By using standard DDR3 memory modules, the cost of adding 16 memory modules would be far cheaper than using FB-DIMM's as well.

You can read the AMD press release here
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments