After hearing from multiple sources spanning on several continents, we can be fairly certain that the samples of nVidia's first DirectX 11 GPU are going to depart from engineering labs. Just like GT200, GT300 spent several months in the Labs while the drivers were being created.
Given that today's GeForce drivers contain more code than Windows XP core, we aren't surprised that nVidia is taking time to get the product ready for market. Just like some media were suggesting that GT200 taped out in March 2008 [while some developers got the GT200 cards as early as three months before that tape out story], GT300 needs time [and human resources] to finish the development. GT300 is the base graphics architecture not just for the standard desktop or notebook graphics, but also as a future graphics base for the Tegra generation of products. And with recent rumors of nVidia implementing ECC feature into the GPU [which is a given, since GDDR5 comes with ECC], Tesla parts should be quite interesting as well.
But now, we have received words that AIBs are getting time frames forthe demonstrations to their own partners and press, with the firstevents happening in September. The dates are obviously planned to bluntthe katana-sharp market attack from ATI's Radeon 5000 series.
On nVidia's annual gathering of add-in-board manufacturers [happened a while ago], a lot of harsh words were spoken due to renaming policies, OEM positioning and more importantly, how to combat resurgent ATI - it was stated that a lot is expected from the NV70 e.g. GT300 generation.
Now, the only question is how long it will take for nVidia's demo team and software vendors to create traditional launch demos. ATI dropped the practice with the Radeon 4000 series, showing raytraced Ruby in its Cinema 2.0 event, but the demo didn't became available to general public. All in all, computer graphics arena is never boring.
Jeste samo trac, ali nista cudno, cak ocekivano...
[Rumour] Nvidia may rebrand GT 200 parts to 300
ne samo u glavama ljudi nego i u praksi :smackbum:Skroz logicno i uskladu sa njihovom politikom, ako bi sad konacno izbacili 40nm derivate za koje su jos prosle godine rekli da ce biti prvi 40nm cipovi na trzistuwall
i nazvali ih GT2** u glavama ljudi bi zaostajali za ATI-jem koji za deset dana izbacuje novu generaciju.
Opet iako je rumor, izgleda da nije daleko od istine.... možda će izbaciti mainstream proizvode koji će biti rebrandirani, dok će flagship izaći krajem godine.
Ako stvarno to urade i dx10 karte brendiraju kao gt 3xx seriju, bice kao kupovati jeftiniju hranu kojoj rok trajanja istice za par dana :bottle:.
Renaming serije 200 u seriju 300 je veoma moguć.Take note that the D11 parts are only in the bottom three categories, Mainstream A and B, along with Performance A. As we said a few days ago, this is nothing more than a cynical renaming borne from a gross inability to make new parts. It also is quite emblematic of Nvidia's inability to deliver even a G92 class part on 40nm. To bang that drum once again, if Nvidia has huge problems yielding ~100mm^2 and smaller dies on TSMC 40nm, what chance does it have of producing a >500mm^2 part? For the math averse, the answer is less than 1/25th the chance.
To give you an idea of how confident it is of this plan working out, the roadmaps for the Spring 2010 season still list the GTX280 with 1792MB as the lead card. If GT300 doesn't work perfectly and it needs to do a second spin, Nvidia is literally out of the high end graphics game. If that does work out, it gets to promote a card that it can't make at the expense of the products it can produce. Great choices there.
The meat of the market, Performance B, is still served by the venerable G92. Ouch. No, really. Nvidia's inability to make a part is getting painful to watch at this point. Juniper will kill this part at a lower cost.
The bottom three, the GT330/320/310 chips, are simply shrunk versions of their 230/220/210 predecessors. Nvidia is listing the performance gains from the 230 to the 330 as +20%, 220 to 320 as +60%, and 210 to 310 as 30%. For Performance B and Enthusiast, there are no gains listed because the parts don't change at all.
Po meni ovaj roadmap nema smisla.... ako ati u istoj fabrici proizvodi 40nm nevidim razloga da Nvidia nemoze uraditi isto pogotovo u mainstream i low segmentu, a i trenutno koristiti zastarelu memoriju kad se GDDR5 moze naci za slicnoj ceni nema smisla
Slazem se za roadmap, ali je cinjenica da iz nekog razloga ne mogu da urade shrink na 40nm! Zasto ne znam, ali je cinjenica da imaju mnogo vise problema u mainstream i low segmentu nego ATI u high.
Ja neverujem da je to tacno... ako kojim slucajem jesto bice ~6 meseci veoma gadno za NV...
i dalje ovu vest tertiram kao zluradu informaciju AMD ofarbanih terorista![]()
Po meni ovaj roadmap nema smisla.... ako ati u istoj fabrici proizvodi 40nm nevidim razloga da Nvidia nemoze uraditi isto pogotovo u mainstream i low segmentu, a i trenutno koristiti zastarelu memoriju kad se GDDR5 moze naci za slicnoj ceni nema smisla
Meni ovaj pixell-ov post liči na proročanstvo uduvanih AMD/ATI fanova koji vežbaju optimizam. Nestvaran je totalno. :d
Ako stvarno to urade i dx10 karte brendiraju kao gt 3xx seriju, bice kao kupovati jeftiniju hranu kojoj rok trajanja istice za par dana :bottle:.
SAN JOSE, Calif. -- As it solidifies its process roadmap, Taiwan Semiconductor Manufacturing Co. Ltd. (TSMC) continues to see a surge in business.
After a slump in the first quarter, TSMC (Hsinchu, Taiwan) rebounded and recently posted strong results in the second quarter. The company also raised its capital spending to $2.3 billion for 2009. Its capital spending budget is projected to exceed $2 billion in 2010, according to analysts.
And in the meantime, the foundry giant is seeing better-than-expected sales demand in the third quarter of 2009, according to an analyst. ''Checks with TSMC lead us to believe 3Q guidance of plus 20 percent could move to around 25 percent with computing/graphics leading, followed by communications and then consumer,'' said C.J. Muse, an analyst with Barclays Capital, in a new report based on company visits in Taiwan this week.
TSMC reported consolidated revenue of NT$74.21 billion ($2.24 billion) and net income of NT$24.44 billion ($738 million) in the second quarter. Year-over-year, second quarter revenue decreased 15.8 percent, while net income decreased 15 percent. Compared to first quarter of 2009, second quarter results represent an 87.9 percent increase in revenue, and an increase of 1,467.9 percent in net income.
Meanwhile, on the process side, the company continues to make progress on the leading-edge, especially at the 40-nm node. ''40-nm appears now to be ramping well for 4Q after earlier challenges,'' Muse said. ''We believe improved mix may enable firmer 4Q '09 ASPs.''
As reported, TSMC initially experienced low 40-nm yields. Now, the company's 40-nm yields are improving to a large degree, he indicated.
TSMC continues to move full speed ahead on new technology. In an interview with EE Times, Jack Sun, vice president of R&D at TSMC, insisted that the company is on schedule with its upcoming 32- and 28-nm processes.
Follow along with the video below to see how to install our site as a web app on your home screen.
Napomena: this_feature_currently_requires_accessing_site_using_safari