Nvidia GF100 "Fermi" Thread

Autor Bukva

Ovo nisam očekivao od guru3Da.

Inače, ATI Stream je brži od CUDA. Di je kvaka? Stream je lijep primjer kako se nešto radi za benchanje. Naime, kvaliteta video je puno lošija nego kada se obrada napravi na nV karticama.

Imaš pravo, ja mislim da Intel najbolje kodira nešto sa istim postavkama kao i AMD. ATi je odmah iza po kvaliteti slike sa istim postavkama kao i ovo dvoje, ali zato nVidia najlijepše to radi. Mora da je zbog boje grafičke kartice, bolje se prenosi na iste operacije. Daje im onaj movie look

[Bukva]

Amaterski se bavim video glupiranjem...
Radio sam i sa ATI Streamom i sa CUDAom...
Možda je do boje grafičke kartice, ali na full HD razlika se i te kako osijeti.

Ovo nisu moje slike, već pokupljene sa neta.

CUDA


Stream



EDIT: Slike pokupljene iz ovog reviewa - http://www.pcper.com/article.php?aid...e=expert&pid=1

[Jelc]

Bulšit

Kao prvo puno ovisi koji se soft koristi a drugo-i jedni i drugi nemaju rezultate kakvi se postižu kad se ide preko proca.

Probao sam u Power Directoru sa ATI-jem i sa Envidiom i ne ispadne kao kad se ide preko proca (ako budemo baš picanili i uspoređivali isti frame)

[Wolverine]

Sljedeći post koji ne bude konkretno vezan za GT300 ili u bilo kojem vidu bio orijentiran na spam, flame i ostale oblike hranjenja trolova rezultirati će kartonom i lockanjem teme do datuma izlaska GT300 na tržište.

Držite se teme i provjerenih informacija a ne rekla-kazala i ostalih čitanja iz kristalne kugle.

[Matth€w]

[Rumour] Nvidia GF100 to launch in "early December";

http://vr-zone.com/articles/-rumour-....html?doc=7955

[Gjurovski]

Cek WTF kaj su promijenili ime iz GT300 u GF100?

[Matth€w]

Očito, to je i mene bunilo malo. Ili sam pak skroz u krivu.

[Wolverine]

Ja b' reko da je GT300 kodno ime čipa a GF100 naziv serije kartica (GeForce 100)
npr GT200 i GTX200 (GF GTX200) -> GT200 je naziv čipa a GTX200 je naziv serije kartica

Ali opet GeForce 100 serija već postoji (kao OEM) pa možda pak pretaču iz šupljeg i prazno

[Gjurovski]

Ili tek toliko da se prica o njima malo, nekuzim no dobro....
No pak sa druge strane: http://www.fudzilla.com/content/view/16170/1/

[the_ghost]

Mogu se kladiti da je opet renaming u igri. gt300 jos nije izasao a ovo su kakti mobilne varijante? how yes no.

[Gjurovski]

Info:
http://www.electronista.com/articles...etails.escape/

I onda ovo:
http://forums.cgsociety.org/showthre..._source=cgtalk

[Majo]

LOL

Epic Fail

[greg SE]

tako to ide kada se vijesti rade od baljezganja s foruma

[Jelc]

I spoke with some industry insiders an hour ago and we have been told that Nvidia plan on having some Fermi cards ready for CES (2nd week of Jan). If you are an Nvidia lover this is good news indeed.

The big question however is will they have them working? or will it be several showcase models in glass presentation cases with prepared video footage running behind them?

Ako je info točan-najvjerovatnije ništa od masovnije prodaje do ožujka/travnja...

[Halos]

Autor Jelc

Ako je info točan-najvjerovatnije ništa od masovnije prodaje do ožujka/travnja...

e ako je tako, mislim da ce se vecina koja nešto čeka ispucat na 5850/70/5970/50 verzijama

[Mast3r Chi3f]

ti komentari s cekanjem vise stvarno nemaju smisla nije ati nedavno bezveze dignuo cijene
vec mjesec dana nema niceg novaga(a ni nece tako skoro)o gt300 tako da su svi daljnji komentari u ovoj temi nisu nista drugo doli offtopic

[Gjurovski]

Dok su god konzole u igri za nove naslove igara ja se nemoram bojati sa svojom 8800GTX i hitno trcati u ducan po 5xxx seriju

Polako se bozja kola voze

[the_ghost]

Autor Jelc

I spoke with some industry insiders an hour ago and we have been told that Nvidia plan on having some Fermi cards ready for CES (2nd week of Jan). If you are an Nvidia lover this is good news indeed.

good news? fudo pise da ce biti predstavljene pocetkom 12. ovo znaci da ce nvidia opako popusiti love na bozicnom shopingu...

[Jelc]

Autor the_ghost

good news? fudo pise...

Pa, za sad su sve to glasine i rekla-kazala.
Makar-čisto sumnjam da Endivijini partneri ne bi već na sva zvona oglašavali prodaju GT300 za Žićbo

Za sad šute svi do jednog.

[the_ghost]

Autor Jelc

Pa, za sad su sve to glasine i rekla-kazala.
Makar-čisto sumnjam da Endivijini partneri ne bi već na sva zvona oglašavali prodaju GT300 za Žićbo

Za sad šute svi do jednog.

Pokazati ce se da je charlie kojeg svi pljuju da je AMD propaganda u pravu sto se tice GT300.

[Matth€w]

Today's reports claim Nvidia are likely to have working samples not before 2nd week of January 2010. Xbitlabs speculates an actual release for February 2010. HardOCP is less optimistic, suggesting any "real availability" is unlikely even for March 2010, in a best case scenario.

http://vr-zone.com/articles/-rumour-....html?doc=7983

[greg SE]

ne znam sto se toliko oko toga zivcirate kao da ste dionicari nvidie. Znam da ste se nadali da ce nesto izaci kako bi pale cijene HD5xxx modela oko bozica ali nista od toga. Ili kupite danas ili poslusajte Gjurovskog....ponekad kao danas izbaci koju pametnu

[dart_tom]

odgođeno za prvi kvartal 2011.
http://www.xbitlabs.com/news/video/d...y_in_2010.html
a tko zna možda to nije ni kraj odgode,a njima je prvi kvartal mslim do travnja!


http://vr-zone.com/forums/505017/nvi...d-to-2010.html

http://icrontic.com/news/nvidia-admi...yed-until-1q10

[Doink the Clown]

U svakom slučaju je bolje da odgode nego da izbace nekakav rebrandirani poluproizvod opet.

[Matth€w]

VR-Zone.com

[Rino]

Autor dart_tom

odgođeno za prvi kvartal 2011.

NVIDIA's first fiscal quarter for 2011 begins on January 26th, 2010 and ends on April 26th, 2010.

[Majo]

Super,izmedu 1. i 4.mj mozemo ocekivat grafe,nije to nimalo lose!

[McG]

Fermi in trouble?

We all know it is constantly being delayed - but at the end of all those delays, what we were expecting was a stellar product from nVidia. However, with today's press release, certain inconvenient details are revealed. Let's forget about the delays for now, and just consider the product itself. The first Fermi GPU - GF100 - as we know for a while now, is a 3 billion transistor giant, taking a die size of around 500 mm2. Compare this with the 2.15 billion transistor, 330 mm2 Cypress on the same 40nm TSMC process, and you would be expecting a different class of product. Unfortunately, the details revealed today about cast an uncertain shadow over this basic assumption.

The first thing worth noticing is a complete and total absence of Single Precision performance figures or any comparison to direct competition - i.e. ATi's GPGPUs. It is clear that Fermi's real performance advantage would be Double Precision performance - had it hit the right clock speeds. However, today's press release suggests nVidia have missed target speeds by a lot. To be fair, Tesla products do clock lower, though not by much. In fact, GTX 280 and Tesla C1060 were clocked the same. Even taking a generous increase for Geforce products, things are still uncertain. As a result, DP performance is rated at between 520 GFlops and 630 GFlops. Suddenly, ATi Radeon HD 5870 - which wasn't even supposed to be a direct competitor - is performing right on par with 544 GFlops against Fermi's supposed strong point.

Consider Single Precision - far more important for gaming graphics, and things turn rather ugly. GF100's target speeds were reported to be 1.5 GHz for the shaders. Based on the 520 / 630 GFlops figures, the shader clocks can only be estimated at 1015 MHz and 1230 MHz respectively. The SP theoretical performance from 512 CUDA cores? Between 1.05 TFlops and 1.26 TFlops. Even less than 1.05 TFlops, considering the lesser part is likely to have units disabled. Now, no amount of overclock can bridge the enormous gap to the smaller, already available HD 5870, which stands pretty at 2.72 TFlops. Even the mainstream HD 5770 clocks in at 1.36 TFlops! Barring a different clock speed for SP units, or other technology we are unaware of, this is a dismal performance from the Fermi shaders. Sure, Nvidia's shaders are much more efficient, but this is just too massive a gap to claw back.

Then comes the price. A previous-gen C1060 released at $1699, falling to $1199. Compare this with fellow Geforce model, GTX 280, released at $649, falling quick to $500, and finally $300. The price of a next-gen C2070 is a whopping $3999. Nearly double the price as the previous generation C1060. Clearly, these are expensive products to make, so how much can Nvidia sell a Geforce version of Fermi for? Even the cheapest Tesla 20 variant, the C2050 costs $2499, nearly 50% more than the GT200 based C1060 flagship. Can nVidia sell the $3999 Tesla product at $399 as a Geforce product? So far, we are comparing GF100 to Cypress. Where, in reality, GF100 should be compared to Hemlock. 4.64 TFlops vs. 1.26 TFlops is not much of a comparison at all, however, CF limitations, ATi's less efficient shaders aside. The other, much less common rumour is the possibility of a dual-GPU Fermi product. Well, considering "Typical" power of Tesla 20 is 190W, this will be highly unlikely, at least for a while. Not to mention, GeForce products might end up clocked higher. A HD 5870s peak TDP is 188W, lower than GF100's "typical" power! TDP is expected to be 220W, at least, and that is just too hot for a dual GPU product. And we have not factored in the fact that GF100 is nowhere to be seen, and are unlikely to be on shelves in quantity for at least 4-5 months. Any further delays, and we will be looking at new products from AMD.

In the end, AMD have a solid product already available that is efficient, economical, scalable. nVidia have ink on paper - and even that is not looking as promising as we may have hoped for.
At this moment, we can only hope for "hidden" or "magical" gaming features which might bring about a revolution in how GPUs work. Short of that, all signs point to Fermi being in real trouble.

Izvor: VR-Zone, nVidia

[Gjurovski]

Burek ili ne?
http://www.fudzilla.com/content/view/16470/1/

[Jerry]

Autor Gjurovski

Burek ili ne?
http://www.fudzilla.com/content/view/16470/1/

Fake!