• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

More bad news for nvidia if true.

Soldato
Joined
28 May 2007
Posts
10,222
http://www.semiaccurate.com/2010/04/05/new-nvidia-code-names-pop/

GTX480 MAY HAVE 'LAUNCHED' but the story is far from over. The first derivative part, GF104, is coming, and there is a mysterious new code name on the far horizon.

SemiAccurate has confirmed that the GF104 did tape out a few months ago. If all goes well, there is about a six month lag between tapeout and chips to sell. With its big brother, the ill-fated GF100, Nvidia is at 10 months and slipping, so don't count on GF104 to be on time. GTX480 might have been 'launched', but cards are still not for sale.

For GF104, likely called the GTS450 or GTS460, word on the street is that it will be cut in half from 512 theoretical shaders to 256. The real open question is what will the 'uncore' or non-shader section of the chip end up as, half of GF100 or the full uncore? GF100 is horribly weak in pixel ops. It has only 64 ROPs (Render Output Units), and that lack of pixel power shows up at higher resolutions.

If Nvidia cuts GF100 cleanly in half to get GF104, it will also suffer from the same handicap. If the GF104 has more than half the GF100's uncore, the price is paid in die area and power instead of performance. The GF104 looks to be about the size of AMD's Cypress HD5870, consume around the same power, and sit between the HD5770 and HD5830 in performance.

The short story is that when you have a chip that is too large, too hot, and badly underperforming, cutting it in half will still put you at the same ratio disadvantage against your competition's 'half' chip. GF104 is unlikely to change the game, either in performance or revenues. Nvidia will likely suffer from more than its current 60 percent die size disadvantage compared to the analogous ATI GPU. The more things change....

Getting back to the GF100, sources at Nvidia are confirming that the yields are far less than 20 percent on both of the variants, GTX480 and GTX470, combined. This means that the silicon for the GPU, before packaging and testing, costs at least $250 for each part. Once you add all the components and make the card, there is no way the GTX470 and GTX480 can make a profit, given what they are being sold for.

If you are queued up for the second batch, don't expect there to be one. If Nvidia is losing money on each board it sells, trying to make it up in volume is not a sane way to proceed. Expect Nvidia to once again pretend that the cards are not EOL'd and trickle the stock it puts aside out over the next few months. If this sounds eerily familiar, that is because Nvidia is doing the exact same thing with the GTX285. It is keeping up appearances while its partners get no stock and suffer the financial consequences.

Last up is a new code name for the far future, GF119. It is likely a next gen 'Fermi II' part, and if Nvidia keeps its naming conventions, a low end one at that. There hasn't been an x9 part in the last three generations of GPUs, so this might be an attempt to do something altogether new. People briefed on Nvidia's long term plans say that this is one to keep an eye on, so SemiAccurate will do exactly that. Stay tuned.S|A
 
Expect Nvidia to once again pretend that the cards are not EOL'd and trickle the stock it puts aside out over the next few months.

This will probably work as people unfamiliar with the graphics world, usually only think of Nvidia anyway.
And im sure all the packaging still says its the fastest GPU :p
 
Also you could probably disconnect your gas when buying a gtx480.

Strap a frying pan to the heatsink :o
You got yourself a full english!

there a youtube video that trys to fry a egg on the 480 card but the tin foil they used to crack the egg in wont go higher than 65c
so egg didnt even start to cook

so sorry no cooking on gfx cards just yet
 
I must admit old Charlie is starting to grow on me. It's fast becoming clear he is one of the very few proper journalists out there and clearly knows his stuff. Obviously he has an axe to grind against Nvidia but it's frightening how accurate he is most of the time.
 
So the GF104 will cost the same as a HD5850 but perform like 5770, awesome. I hope the GF119 is something new and improved of the GTX480.
 
There are a lot of 'if's' in the story though.

If they cut the shaders in half, maybe that will allow a much higher clockspeed?
 
there a youtube video that trys to fry a egg on the 480 card but the tin foil they used to crack the egg in wont go higher than 65c
so egg didnt even start to cook

so sorry no cooking on gfx cards just yet

They had the fan speed on auto and could have overclocked. Setting the fan speed down would have helped a LOT.

Also, someone suggested putting some thermal paste between the foil and the heatsink.

Would be interesting to see more tests done on this... :)
 
They had the fan speed on auto and could have overclocked. Setting the fan speed down would have helped a LOT.

Also, someone suggested putting some thermal paste between the foil and the heatsink.

Would be interesting to see more tests done on this... :)

tbh we just need someone to crack the egg straight onto it :p
 
give it a rest nivek. while he does use a lot of what-if's, what else can he do? the difference is, he's never been far from the truth. A lot closer to it, i might add, than anybody else has been.

You can laugh at semi accurate all you like.
 
I must admit old Charlie is starting to grow on me. It's fast becoming clear he is one of the very few proper journalists out there and clearly knows his stuff. Obviously he has an axe to grind against Nvidia but it's frightening how accurate he is most of the time.

to put this coment about charlie in a post sais it all, and is a mockery of all journalists out there

you clearly have no idea about charlie or his so called 'stuff'heres a quote from another site,

the guy doesnt even have a semi accurate understanding of GPU's

How is it possible to blog about GPUs for a living and not know the difference between a ROP and a TMU? And even if he were to get that right, texture cache efficiency increases with resolution, not the other way around. I wonder how he feels about Cypress' 32 ROPs

/boggle

and here is two quotes from charlie himself,conradicting each other,

17 march

Quote:
SemiAccurate moles are saying that plans are in the works to tape out a GF104 and a GF106 in short order as well, but they haven't left Dear Leader's workers' paradise yet.

5 april


Quote:
SemiAccurate has confirmed that the GF104 did tape out a few months ago.

so please dont make charlie out to be some kind of info insider, that speaks the truth, when it is obvious to many that he talks pure nonsense, and most likely makes it up as he goes along.

as for accuracy, even a blind man can hit a chicken in a barn fullof them.

semi accurate indeed
 
April comes after March..
Making it accurate?

Did you know we used to think the world was flat?
I personally don't care for the guy, but he's been right about Fermi.
 
give it a rest nivek. while he does use a lot of what-if's, what else can he do? the difference is, he's never been far from the truth. A lot closer to it, i might add, than anybody else has been.

You can laugh at semi accurate all you like.

He's a journalist, he doesnt know anything unless his contacts tell him. A classic has to be, the 480 is rated at 300W, oh wait, we were wrong its 295W the engineers changed it at the last minute lol, ends up being 250W. If your going to fail like that, at least fail with a little more dignity than.. 'We'll guess at 300W, and when were wrong, we will say they changed it at the last min, so were covered'

Now add that reasoning to every article he writes and there you have it. I'll give it a rest when he gives it a rest.
 
Back
Top Bottom