I was talking about the tiny 1u blades similar to this: http://gizmodo.com/270650/nvidias-te...uters-fo-reals
I know you can buy them standalone with the shroud and fan.
Printable View
I was talking about the tiny 1u blades similar to this: http://gizmodo.com/270650/nvidias-te...uters-fo-reals
I know you can buy them standalone with the shroud and fan.
The pic is fake for sure. No way could the light come from UNDER the power connector. Photoshopped.
Superior in which way? FLOPS/mm²? W/mm²? Manufacturing costs? raw performance? Performance/mm²? Performance/W²?
There is one thing which HD5k are superior; early in the market.
Looking at all the pics and replied, I am really starting to believe that it's fake, LOL.
Interesting read from jasoncross.org about this card.
Yes, because by the specs GF100 seems to be far from being superior compared to RV870. It's huge, its slow(GFLOPS wise), it will cost a ton, and there isn't cards out yet. So yeah, thats the "superior product" Nvidia is having. :rolleyes:
The only way I can see GF100 being superior is GPGPU applications. Thats where it's aimed towards. Gaming performance seems to be the secondary priority.
for gaming, its just bigger than ATI, not superior. for tesla, i think its a very nice upgrade, but whos competing with them?
Again, superior in which way? If you care for perf/watt or perf/price, is it really going to be even better?
From companys point of view it's even worse. For consumers GF100 based cards could actually be better deal in perf/price, but for Nvidia such deal is not really good, it just can not compete in price due to (likely to be) more expensive product.
i think we're agreeing, i said its just bigger and NOT superior. i think it will have a very similar perf/watt and perf/$ (like within 10%) of ati. price is fully controllable by nvidia, but i expect the architecture to do well enough to provide a close perf/watt ratio. and given the die size difference, i think it will have a lower perf/mm2, but that is expected with its CUDA background, and shouldnt affect anything except cost.
its not stupid pictures of a card, its pictures of a stupid card :D
if nvidia cant show a gt300 retail card or doesnt want to, fine...
if they decide to show a mock up instead... fine
if they decide to claim the mock up is the real deal... thats pretty lame, but whatever... their call...
but not even getting a propper mock-up done and instead hack-sawing through some old trash pcb and glueing parts to it... ouch... thats the most amateur move ive seen from nvidia in many years...
and you know, if it would have been a propper mockup, who would have cared? nobody would have complained in a couple of months when the card actually comes out, that it looks slightly diferent... if you plan to lie to people about this stuff, you might want to use something a little more sofisitcated than a 20minute hotglue mockup... :D
if they have the superior product, then they wont lose :)
how can they lose if they have the surperior product?
i was a bit bored so i put this together heheh :D
http://img28.imageshack.us/img28/2883/tesafilm.pngQuote:
Originally Posted by jensen huang
as you can see we added some nano-technology plastic tape, which is wrapped around the card, protecting it from super-charged alpha particles from outer space! *audience applauds*
:D
this forum is starting to suck... :rolleyes:
do you know what makes forums like this suck? users like you. :mad:
anti-nvidia sentiment is so stupidly high here, it's nearly forcing me into becoming a nvidia fanboy, even though it's been two years since I last used a nvidia product, and I am probably two weeks away from getting a 5870.
The funny part is, if Jen-Hsung said "We'll totally kick ass gaming performance wise" instead of the CUDA thing, you guys would still mock him.
We do not know the performance of Fermi. Kindly shut the hell up until you DO know that it is NOT performing and it IS expensive. Too much speculation, too much bullcrap talked about Nvidia based on that speculation.
Fermi's launch has been late and it's bad for Nvidia. However, this doesn't mean it's going to be slow or anything.
if perf is right, and the only problem is yield and heat, they can cut down gt300 to compete with 5870... they really HAVE to, i dont see how their strategy can be to only have gt300 and gt200 and nothing else in between...
who? me? :confused:
"LEAVE NVIDIA ALONE! ;_; :mad:"
So yeah. No negative speculation because it could actually imply that Nvidia would have really messed up big time this time?
We know for a fact that bigger chip means bigger costs.
We know for a fact that 384-bit memory controller means more complex PCB and more costs.
We know for a fact that Nvidia's CEO used FAKE card to show the upcoming card.
We know for a fact that Nvidia's product is late to the market, so it has been having some problems already.
Expensive card AND competitive pricing means less profit for the company.
So, based on this, what positive can you say about the upcoming product? If nothing, would you propose people to be quiet for the sake of "being fair"? :)
probably... for the geforce fx they did claim kick-4ss gaming perf and they failed big time... i think anything nvidia can say right now will be criticized by most... they are trying to be a party pooper for ati, so dont you think they deserve at least some of the criticism they get?
if theyd actually show something real then it would be acceptable imo, but yelling hey, hey, look at me! uh! uh! over here, and then all they talk about is gpgpu and physix most people are fed up with, and show a patched together mock-up card and claim its the next gen card when anybody who knows a BIT about vgas can tell its a fake? what do you expect? people cheering for them?
But you don't know that it's not going to be fast as to compensate for its price.
Yeah, you do know all you have listed; but come Fermi, and if its price is in line with its performance, then all of what you've said will be in vain.
There are two sides to the equation - price AND performance. So far we only know that it's going to be a big chip and thus going to cost a lot. This doesn't bode well for Nvidia but still none of the critics for Fermi (aside from the ones complaining for the late launch) know anything about the other side of the equation.
So it's funny that you guys are talking as if you know how the product's performance is going to be. Until then, all such bashing based on pure speculation is funny and stupid.
Can't say I'm sorry. A good joke is a good joke. Also, since the card was not the real deal and still was showed by the CEO I think it deserves some bashing. Had it been ATi that did the same thing we'd be hearing this from some of you instead (well, saaya probably would have been doing the photoshop anyway).
Edit:
Highoctane:
Sure, there are flames in Nvidia threads but equally in the ATI/AMD threads. And as I said, this fake needs to be called out on. It's really lame.
It's come to my attention that every single NV thread ends up with people posting with censor bypasses and inappropriate language.. If you see it, PM me directly and I will handle it, as my email is screwed up presently so I don't receive the notifications right now.
This is a warning, if any of you are guilty edit it now. At 5pm Central I will be sweeping thread by thread, and taking care of things.
If you're feeling froggy, I'll feed you an M-80.
I'm also convinced that Fermi graphics card is fake. I found this pic of PCI Express connector from Chinese website PCpop.com and it says: ""180-11072-1102-A00" (link)
I checked some previous PCB codes:
GeForce GTX 295: 180-10656-0102-B01
GeForce GTX 285: 180-10891-0102-A01
GeForce GTX 9800 GX2: 180-10790-0102-A02
saaya, do you have more detailed info about these codes?