Taman da posluzi samo kao demo :d
ako je yield kakav pricaju da jeste, ocas posla oni naprave mainstream klasu od felericnih fermijaZadavanje domacih ne donosi pare
Trenutno stanje dozvoljava atiju da iza zavesa na miru razvija novu arhitekturu...i to ako je mozda tako nVidiji ce zadati dosta problema, kolko god fermi bio superioran... Ipak kasnjenje od 4meseca nije malo, pogotovo ako se zna da ce tek za 5-6 biti dostupna srednja klasa....
Ne kasne oni. Pustili i Ati-ju da zarade nesto. Dogovor kucu gradi.
Zanimljivo, verovatno će se poklopiti sa pojavom Crysis 2, ako on bude u martu kao što se očekuje.
Svi se sećamo one pomame kad se pojavio 8800gt (g92) par nedelja posle izlaska prvog Crysis-a.
Nvidia has now released a new picture of the next generation graphics cards. It shows Tom Petersen, Nvidia head of Marketing, presenting a water cooled PC with two graphics cards in SLI setup. The cards pictured are quite similar to the one presented as GF100 with Fermi chip - so apparently Nvidia has at least two working devices. ;-)
Nvidia has furthermore confirmed that the GF100 which has been pictured while rendering the Unigine Engine benchmark, is 10.5 inches long and thus has the same size as the graphics cards of the Geforce GTX 200 series. This piece of information has been published on Facebook.
In metrical system this means the card is 26.7 centimeters long which would exactly be as long as a Geforce GTX 285 with the default layout. Thus the GF100 Fermi would be shorter than Nvida's current dual GPU flagship Geforce GTX 295, which is 27 centimeters long, and also shorter than AMD's current single GPU top dog Radeon HD 5870 which is 28 centimeters long.
Paaaa....moglo je i gore![]()
Za koju nedelju ce izbaciti sliku sa tri kartice...pa onda sa ceeeet'ri...zrno po zrno, pogaca![]()
Nvidia needs zero defects from its foundry partners, particularly in the vias on its leading-edge graphics processors, said John Chen, vice president of technology and foundry operations at the GPU powerhouse. With 3.2 billion transistors on its 40 nm graphics processor now coming on the market, the 7.2 billion vias have become a source of problems that the industry must learn to deal with, Chen said in a keynote speech at IEDM.
Chen's speech included a call to "my friends at TSMC to give me more 40 nm parts," and a plea for improved via defectivity. :banana::banana::banana::banana: James, a technology analyst at Chipworks (Ottowa, Canada), said via defects have shown up on ICs manufactured by TSMC. Chipworks has inspected products from graphics vendor ATI, now part of Advanced Micro Devices (AMD, Sunnyvale, Calif.). "The problem appears to be that when they cut a via, a residue of photoresist gets on the edge of the via, which creates a ring-shaped discontinuity in the metal," James said. "The discontinuity could create electromigration issues. We've seen the same problem on the upper metal levels on the ATI chips we've studied. It creates a reliability failure mode."
A marketing manager at Chartered Semiconductor Ltd. (Singapore) said Nvidia is investigating silicon-on-insulator (SOI) technology, which Chartered and GlobalFoundries both provide. Nvidia joined the SOI Consortium (Boston) last summer. James of Chipworks said the buried oxide layer in an SOI substrate could reduce current leakage by blocking leakage from an active area to the bulk silicon. "SOI could take out a whole leakage mechanism," James said.
Nvidia also needs through-silicon vias (TSVs) so that it can connect its logic transistors to DRAMs on a separate die. With 3-D interconnects, it can vertically connect two much smaller die. Graphics performance depends in part on the bandwidth for uploading from a buffer to a DRAM. "If we could put the DRAM on top of the GPU, that would be wonderful," Chen said. "Instead of by-32 or by-64 bandwidth, we could increase the bandwidth to more than a thousand and load the buffer in one shot."
Variation is hurting the company's business, which depends on binning. The normal practice is to bin the best chips to the ultrahigh-performance accounts, devices that hit the mean performance and operating voltage metrics to the notebook market, and slightly underperforming chips to desktops. "The problem if the mean of the variation shifts day to day, we lose all of our ultra and some of our mobile bin," Chen said. "It creates a huge inventory of desktop chips, some of which we have to discard. This is really going to be a major problem at 28/22 and beyond. Even 1 nm variation in a CD can affect our products in a very significant way."
meni se cini da ce nakon ovog iskustva sa Fermijem i skolom koju su naucili, NV za sledecu generaciju preci u GloFo-ove fabrikeOvu priču su već prošli jednom sa NV40 kojeg je prozvodio IBM upravo iz razloga što TSMC tada nije bio sposoban napraviti tako veliki čip na 130nm procesu. Bez obzira na to, škarta je bilo ko pljeve (u vidu 6800LE, 6800, 6800GS).
pod debelom pretpostavkom da je tabela tacna, zasto mislis da bi tzv. GTX 360 mogao da utice na smanjenej cene HD5870? Mislis da ce GTX360, koji ce nastajati od harvestovanog "full size" Fermija, kostati manje od HD5870? Mislis da ce ga biti vise u ponudi? Ja ne mogu da naslutim ni jedan realni ekonomski faktor po kom bi HighEnd Fermi uticao na cenu HD 5870.... naravno mozemo spekulisati i nadati se da ce a) biti brzi b) biti jeftiniji c)ponudjen u vecim kolicinama, tek ako se sve to ostvari, stvorice se uslovi cenovnog pritiska na HD5870... pricnaces da je to mnogo akoPrema ovoj tabeli, na oko bi se reklo da ce gtx360 biti kao 5870 ili za nijansu brzi, sto je super za obaranje cena 5870 karti, dok ce 5850 ostati sa slicnom cenom do sredine 2010, a mozda i duze.Sve ovo pod uslovom da shaderi ostanu na klokovima sa tabele!
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