Featured Articles

Nvidia Shield 2 shows up in AnTuTu

Nvidia Shield 2 shows up in AnTuTu

Nvidia’s original Shield console launched last summer to mixed reviews. It went on sale in the US and so far Nvidia…

More...
AMD CSO John Byrne talks ARM

AMD CSO John Byrne talks ARM

We had a chance to talk about AMD’s upcoming products with John Byrne, Chief Sales Officer, AMD. We covered a number…

More...
AMD Chief Sales Officer thinks GPU leadership is critical

AMD Chief Sales Officer thinks GPU leadership is critical

We had a chance to talk to John Byrne who spent the last two years as Senior Vice President and Chief…

More...
OpenPlus One $299 5.5-inch Full HD phone

OpenPlus One $299 5.5-inch Full HD phone

OnePlus is one of the few small companies that might disrupt the Android phone market, dominated by giant outfits like Samsung.…

More...
KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 gained a lot of overclocking experience with the GTX 780 Hall of Fame (HOF), which we had a chance to…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Tuesday, 26 April 2011 10:12

AMD plans to ship three million Llanos in Q3

Written by Fudzilla staff


28nm APUs reportedly taped out
AMD is preparing to start shipping Llano APUs in June or July and the company seems to have rather big plans for the new Fusion part.

According to Digitimes, citing motherboard makers, AMD is expecting to ship as many as three million units by the end of the third quarter. This would make up a whopping 40 percent of all AMD CPU shipments in said quarter, which is a rather optimistic scenario.

However, bear in mind that AMD managed to ship a million Brazos platforms by the end of 2010, despite the fact that they were not even on sale back then. Many of them ended up with OEMs and we assume the same will happen with initial batches of Llano APUs. Asus, MSI and Gigabyte already have several Llano motherboard models ready to go.

In related news, 28nm Krishna and Wichita APUs, as well as Southern Islands GPUs are currently in the tape-out phase. However, this should be taken with a grain of salt.

More here.

 

blog comments powered by Disqus

Comments  

 
+37 #1 Nerdmaster 2011-04-26 10:39
Those are very good news.
 
 
+32 #2 pogsnet 2011-04-26 11:46
Where is Fuad, I think he should announce this with meanwhile Nvidia has no news about upcoming next gen GPU. =p
 
 
+14 #3 Nubstick 2011-04-26 16:05
Quote:
AMD is preparing to start shipping Llano APUs in June or July



Llano has been shipping for weeks.
http://m.foxbusiness.com/quickPage.html?page=32811&external=831847.proteus.fma

And Krishna taped out weeks ago.
http://semiaccurate.com/2011/04/11/guess-what-taped-out-at-amd/
 
 
-22 #4 techno 2011-04-26 16:42
AMD need to broaden their road map.
Fusion APU's are great for the low to mid range use but they are going to be left way behind in terms of high power gpu compute performance.

Nvidia's Denver project products are going to unleash the full memory bandwidth available on discrete gpu cards which are just not available to APU's which use system rescources and remove the pcie bottleneck as these product have a an integrated cpu onboard for local calculation....
 
 
+5 #5 techno 2011-04-26 16:43
AMD should not put all their eggs in the fusion basket, they need to maintain production of a traditional cpu as with Zambezie for the high end and develop a hybrid cpu/gpu discrete card similar to Nvidias Denver project as combination of these types of discrete cards with traditional cpu's are going to dominate the enthusiast and hpc market as OpenCL and Direct Compute type applications come to the fore.
 
 
+6 #6 redisnidma 2011-04-26 17:42
Quoting pogsnet:
Where is Fuad, I think he should announce this with meanwhile Nvidia has no news about upcoming next gen GPU. =p

Don't expect any positive comments from Fuad on this one. As of now, he must be grinding his teeth due to this. 8)
 
 
+2 #7 PorscheRacer14 2011-04-26 23:48
Define "CPU" inside Denver. Surely it couldn't be a useful x86 design or Intel and AMD would stop that. So any CPU in Denver would have to emulate unless when they say CPU they mean a dedicated graphics engine which is hardly revolutionary...
 
 
-2 #8 techno 2011-04-27 08:45
Quoting PorscheRacer14:
Define "CPU" inside Denver. Surely it couldn't be a useful x86 design or Intel and AMD would stop that. So any CPU in Denver would have to emulate unless when they say CPU they mean a dedicated graphics engine which is hardly revolutionary...


I'm not a programmer or anything but I thought that such a project Denver combination would work through the OpenCl API......does the cpu still have to be X86 compatible to be of "much use" in such a scenario?
 
 
+2 #9 Bl0bb3r 2011-04-27 18:47
Quoting techno:
does the cpu still have to be X86 compatible to be of "much use" in such a scenario?



Yes, the base of the OpenCL API in this case is exactly x86, so the CPU would still need to be x86.

But the talk is about denver and that is pretty much like tegra, probably overworked. It's based on ARM.
 

To be able to post comments please log-in with Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments