Fermi 480 heaven benchmark video

[losttheplot]

NVIDIA is still keeping the Fermi to themselves. I don't think AMD knows how it will really perform. Fermi will either perform or fail. For Fermi to be profitable for NVIDIA Fermi would need to be at least 50-75% faster than ATI's 5000 series and right now I don't see this happening at all

I just hope ATI drops prices just to keep pressure on NVIDIA on Fermi's launch date.

Even if its 10-20% faster its a success, though the figures emmerging, it looks as if its a big FAIL, not that I care for NVIDIA but that means the ATI 5 series prices wont have to drop anytime soon either if thats the case

 

[F430]

Guys show some love for nvidia....
The card would be very good if launched with the 5870

it will be nice for physics lol

 

[KainXS]

its kinda funny though its like nvidia is gonna hand the consumer market to AMD and AMD is gonna hand the professional market to nvidia, lol

 

[nt300]

I think hd 3800, 4800 and the 5800 were test designs and the real stuff comes out with 6800 and 7800 I think this is where ATi wil gain a lot of market share and keep performance crown.

 

[3volvedcombat]

Whats with all these Little Kid sort of comments (no offense) You have to realize that maybe the version 1.0 of the benchmark is utilized for ATI cards, and maybe the 1.1 uniengine
benchmark is even optimized for both cards or more of ATI. They finally have the card running and i believe they gave strait out scores on the fps in the uniengine benchmark. I mean you also have to think about the need they have to market and that they could be strait out honest about what they are saying. I mean give them a break, and to all you flamers watch out when the card finally comes out and its fast fast fast and cheap.


*Note* If you were paying attention to the PCB design of the 470 and 480 they have gone to there lengths to keep it as low cost to make as possible. The 470 PCB is so dam simple its not even funny if it was a working model, like 6 transistors and a couple of mosfets and such to deliver power to the gpu, and on-top of that maybe they have gotten there yields to the sky because i have not herd much in 2 months from TMSC.

And the Power hog Mith really doesn't con-cretely seem true looking at the 480-470 pcb's because they dont have that many power regs to suggest high power usages. We will see how this card stacks up and on top of that the cooling for the cards are DTH heatpipe coolers that are nickle plated and have a mirror finish, but that contradicts the statement i made about low power ussage, because for that kind of cooling the gpu needs to have ALOT of power pumping threw it. I have faith in nvidia though.

 

[nt300]

Well we shal see when released. One more week and another one bites the dust or not

 

[shevanel]

i find it hilarious that when i play the Just Cause 2 demo I see all these badges like Powered by Nvidia CUDA but the game uses havok

this game releases 3 days prior to the nv release i think.

 

[Lionheart]

The only reason I would buy one or 2 of these cards would be 3D, but then again thats an expensive investment

 

[Super XP]

3D, no thank you. I think its a waist of money right now. If and when it becomes mainstream and the price is right then maybe I might buy into this 3D. But for now its expensive nonesense

 

[bobzilla2009]

aye, plus 3d tv makers are trying to sort out an open standard. They can make native 3d monitors and tv's (i.e. no glasses, Phillips made a prototype in 2008 that worked well and ran at ~3840x2160), they just want to make the content standard so that when they start making them it'll all work on every set. AMD, ever being the ones to notice such things, noticed this and have let any 3d maker use their cards.

Nvidia are being nvidia and being arrogant enough to think they, as one company, can beat a group of several dozens of richer companies. Still, at least they have some 3d out early, like they did with physX, it just won't be mainstream until open standards. At that point the nvidia solutions become pointless in the eyes of the consumer.

 

[HalfAHertz]

http://forums.techpowerup.com/showthread.php?p=1807139#post1807139 The next Heaven benchmark wil be 2.0 and not 1.1. And if you look at the screenshots, you can see the blimp from nvidia's fermi presentation.

 

[nt300]

Oh no, look like Fermi is in big heat trouble. :shadedshu

GDC 2010 Officially raised 50W, OEMs livid
http://www.semiaccurate.com/2010/03/12/semiaccurate-wrong-about-nvidia-480gtx-power-use/

IF YOU WANT to learn about Nvidia's Tesla and GTX480 cards at GDC, don't ask Nvidia, it has problems with the truth. The real story is found with the users, and they have interesting things to say about the upcoming card's upward bound TDP.

If you recall, the official story is that the card, in it's cut down and underclocked version, pulls 225W. That number, along with stunningly poor performance, has lead to some notable backpedaling. If that isn't bad enough, some sources at GDC told SemiAccurate that Nvidia jacked up the TDP by 50W last week without warning.

There are two problems here, one internal and one external. The internal one is that this is a big flag saying Nvidia admits defeat and has no hope of fixing the problems that plague the chip. Nvidia can't get the power to a reasonable level, and that is the end of it. :shadedshu The only way to get numbers of chips to salable quantities is to jack power through the roof to mask the broken architecture, so that is what it is doing.

More problematic is what about the OEMs? Officially raising the TDP three weeks before launch by a very substantial 50W is massively stupid. Nvidia just can't do this to OEMs without causing them lots of pain. For high end desktops with lots of space, that can be worked around, but if the system is a little closer to the edge, 20+ percent more TDP can have a profound and negative effect on cooling.

Even worse, think about all the companies that make Fermi based Tesla cards. If you put four in a system, and Nvidia jacks TDP 50W per card, that is 200W more you have to dissipate. Three weeks before launch, your cases are built and in a warehouse, your cooling system is finished, and you don't have time to change things, much less test them. 200W is a lot in a 2U server case. 21 of these in a 42U rack is an added 4.2kW that you need to dissipate, roughly 3 hair dryers on full blast.

Then there are the laptops. I feel bad for those guys, first Bumpgate, now this. There is no way you can redesign a laptop cooling system in six months, much less three weeks. Silly ODMs, no cookie, but you will probably be blamed by Nvidia PR for 'screwing up' so badly.

In the end, Fermi is turning into a running bad joke. You have to wonder about how many high margin orders will be shown the door when word of this leaks out. Nvidia might be "Oak Ridged" a few more times yet.S|A

Why don't Nvidia admit defete and move on with a Fermi 2 or something

 

[Kenshai]

Oh no, look like Fermi is in big heat trouble. :shadedshu

GDC 2010 Officially raised 50W, OEMs livid
http://www.semiaccurate.com/2010/03/12/semiaccurate-wrong-about-nvidia-480gtx-power-use/

Why don't Nvidia admit defete and move on with a Fermi 2 or something

More Semiaccurate don't believe everything.

 

[Fourstaff]

I think the push to GPGPU has caused Nvidia a lot of problems. However, I believe "Fermi 2" will be a killer product.

 

[a_ump]

I think the push to GPGPU has caused Nvidia a lot of problems. However, I believe "Fermi 2" will be a killer product.

i agree, i think that fermi "accidentally" turned out to be the testing silicon on 40nm for nvidia's new architecture, but with all these mistakes you can bet they've gained a lot of knowledge on how to do things and the next gen based on fermi will probly be bomb. imo

 

[nt300]

Lets hope so for Nvidia sake. I don't see this happeng with ATI though.

 

[Zubasa]

Lets hope so for Nvidia sake. I don't see this happeng with ATI though.

ATi did the smarter move of releasing the HD 4770 months before nVidia released their GT 240,
so they got the upper hand in dealing with the 40nm yield issues.

The classical nVidia releases the "arse whooping big ass monster chip" also back fires on them.

 

[fritoking]

http://www.shanebaxtor.com/2010/03/16/gtx-400-series-date-pushed-back/

retail release delayed

 

[Marineborn]

http://www.shanebaxtor.com/2010/03/16/gtx-400-series-date-pushed-back/

retail release delayed

LOLZ!!! SO HARD IT HURTS!!!! omg...hey chaulk another month on your calendar, HAHAHAH. thats so funny

 

[a_ump]

hey, we'll all still know performance on the 26th thou. *opptimistic moment* and we'll all be surprised to nvidia pulling with fermi what ATI did with the RV770 and have shocker performance!

 

[bobzilla2009]

well, nvidia just look like they have only improved their cards less than AMD without AMD having an architecture change (if the gtx480 is 5-15% better than a hd5870, compare that to the ~20% or so the gtx280 was ahead of the hd4870).

So if nvidia are just going to improve their architecture and amd bring out a (gaming orientated as opposed to pure gpgpu i would assume) new killer architecture nvidia could be in trouble. Still the next gen is going to very very interesting nvidia have just brought a series of disappointments this time round, the best they can do is salvage some reputation and money and bring out some affordable mid range dx11 cards (especially laptops!) before september (student laptop/desktop buying season, probably the next large computer sales time).

 

[nt300]

http://www.shanebaxtor.com/2010/03/16/gtx-400-series-date-pushed-back/

retail release delayed

You think thats bad, I hear Fermi might be delayed up into middle of May. I hear from co-workers, will ask for proof

 

[Binge]

You think thats bad, I hear Fermi will be delayed up into middle of May now

State sources on delays or don't post. Rumors are not a great basis for technical discussion.

 

[nt300]

State sources on delays or don't post. Rumors are not a great basis for technical discussion.

Here is the link I got,
Fermi delayed till Q2 2011
http://www.xbitlabs.com/news/video/...e_Pull_Stride_Next_Quarter_CEO_of_Nvidia.html

second quarter of FY 2011 for them is from may-July 2010

 

[erocker]

Here is the link I got,
Fermi delayed till Q2 2011
http://www.xbitlabs.com/news/video/...e_Pull_Stride_Next_Quarter_CEO_of_Nvidia.html

Just remember, if you are going to quote others, you need to include the source. Otherwise, it's just making up stuff and that is punishable by virtual flogging.