NVIDIA to Counter Radeon HD 6970 ''Cayman'' with GeForce GTX 580

[caleb]

Goodie more releases = better prices on decent "older" cards.

 

[bear jesus]

The new GPU is speculated to have 512 CUDA cores, 128 TMUs, and a 512-bit wide GDDR5 memory interface holding 2 GB of memory, with a TDP of close to that of the GeForce GTX 480.

they must have done something impressive with the 40nm process to enable a full 512 set of cuda cores, over double the TMUs and add a third more memory with a one third bigger bus and it sill be close to the 480.
By close i assume they do mean over 300w? whats that a minimum of two 8 pin pci-e connectors?

But still i hope nvidia get going on these fast, more cards from both sides can only mean good things for the consumers (me ).

 

[Tatty_Two]

they must have done something impressive with the 40nm process to enable a full 512 set of cuda cores, over double the TMUs and add a third more memory with a one third bigger bus and it sill be close to the 480.
By close i assume they do mean over 300w? whats that a minimum of two 8 pin pci-e connectors?

But still i hope nvidia get going on these fast, more cards from both sides can only mean good things for the consumers (me ).

Motherboard - 75W
8 Pin PCI-E - 150W
6 pin PCI-E - 75W

total 300W And that won't be enuff I think so yeah, 2 8 pins!

 

[buggalugs]

Hardly more realistic lol, that bench was ran in DX9 and not DX11 where the 480 owns the 5870.

So 480 50% quicker at 1080p

http://img149.imageshack.us/img149/909/555ux.jpg

http://www.xbitlabs.com/articles/video/display/asus-matrix-5870_9.html#sect1

If you look through all the games and 3D benchmarks its no where near 50%, average is 10-20%.You were selective in picking the only game with a decent gap, just like the other guy. For the extra 10-20% you have a blast furnace in your comp and paid an extra $100-$200.

Nvidia is still trying to appeal to the lowest common denominator by making the fastest card any cost. Sales of the 5XXX series should have taught them that most people are a bit more discerning and will weigh up heat/temps/computer noise and cost.

This thing with a 512 bit bus is going to cost more than the 480 and will most likely be over $800 outside the US. Looks like another fail.

 

[the54thvoid]

Oh ffs.

Look it's all, the GTX 480 is so good this and so good that. This new GTX 5blah will so own AMD's next 6series.

Let the adults know when the school yard spat is over and we can talk about realities of performance. Of course the 480 kicks the 5870's ass, it gobbles up much more power to do so.

AMD's task is and has been to deliver more fps per watt. Nvidia has went for all out power.

It'll be the same again. When this mystical card gets released it will probably be very compromised in some areas to allow it to actually work and it'll still be more power hungry.

The reason Nvidia hasn't got the single card performance crown is bacause to date, nobody has got a hold of the power issues. Don't hold your breath for this card.

And my final prediction. AMD 6970 will topple gtx 480 as single fastest chip. Then some time down the line NV will release their next puppy and it will become king, and on and on and on.

 

[HossHuge]

In the immediate future

I find this term very subjective...

 

[stupido]

Oh ffs.

Look it's all, the GTX 480 is so good this and so good that. This new GTX 5blah will so own AMD's next 6series.

Let the adults know when the school yard spat is over and we can talk about realities of performance. Of course the 480 kicks the 5870's ass, it gobbles up much more power to do so.

AMD's task is and has been to deliver more fps per watt. Nvidia has went for all out power.

It'll be the same again. When this mystical card gets released it will probably be very compromised in some areas to allow it to actually work and it'll still be more power hungry.

The reason Nvidia hasn't got the single card performance crown is bacause to date, nobody has got a hold of the power issues. Don't hold your breath for this card.

And my final prediction. AMD 6970 will topple gtx 480 as single fastest chip. Then some time down the line NV will release their next puppy and it will become king, and on and on and on.

quite right... I'm personally curious if the GTX 580 will still be 40nm process? If it is not, than all those power issues could be overcome?

 

[CDdude55]

hmm, It seems when it's Nvidia news, everybody complains..:shadedshu

This is good news and i hope for the best so we can get some solid competition going, lets get some of these prices down!!!!

 

[arnoo1]

wil there be a new gtx470 something like 475 or 570?
and i want prive drops,

and that new speculated gtx580 will be damn fast

 

[DanTheMan]

I guess W1zzard better get that second air condition ready for these upcoming video card reviews, it looks like it gonna be a HOT winter!! Might have to add that nuclear power plant reactor to help juice these babies!

 

[Mr McC]

hmm, It seems when it's Nvidia news, everybody complains..:shadedshu

I don't think it's that, it's just that it isn't really news: AMD are on the verge of launching 68XX series and Nvidia hopes to divert some attention away from the launch by stating that they will be releasing faster cards with better features in the future. We already assumed that.

 

[Benetanegia]

I don't know from where did they take those specs, but Nvidia will not release those things. They are absurd. 512 bit? If GF104 has taught anything, that is that performance on Fermi cards depends mostly/only on shaders and is not by any means based on ROPs/bandwidth.

The only probable GF110 specs are one of these (in order of probability):

1 - 3/2 (three halves) of a GF104, that is 3 GPC (clusters)

specs: 576 SP, 96 TMU, 384 bit, core 750 mhz, < 500 mm^2

performance: GTX480 + 25%

Posibility of a dual GF104 card.

2- GF104 with 4 SIMDs per SM instead of 3 (64 SPs instead of 48), 2 GPC

specs: 512 SP, 64 TMU, 256 bit (it would accompanied with 6 gbps memory for about the same bandwidth as GF100), core 750-800 Mhz, << 400 mm^2

performance: ~ GTX480 +/- 5%

There would be a dual gpu card based on this one.

3- Combination of both, #2 but with 3 GPC or #1 with 4 SIMD.

specs: 768 SP, 96 TMU, 384 bit, core 650-700 Mhz, ~550 mm^2

performance: GTX480 + 50%

#3 becomes posible thanks to the fact that TSMC 40nm is said to have exceeded 55nm yields, and Nvidia not fecking up the fabric like they did with GF100.

Also #2 and #3 can easily exist at the same time, as well as a dual card based on #2, and a card based on the same but with 1 GPC only and 128 bit. That way:

GF110#2 (512 SP part) >>> Bart at a higher cost
GF110#3 (768 SP part) >>> Cayman at a higher cost
2xGF110#2 (2x512 SP) == Antilles at similar cost

I don't think it's that, it's just that it isn't really news: AMD are on the verge of launching 68XX series and Nvidia hopes to divert some attention away from the launch by stating that they will be releasing faster cards with better features in the future. We already assumed that.

I don't see Nvidia saying anything anywhere, all I see is a pair of websites speculating, based on the fact that speaking about a posible Nvidia response now that AMD is releasing HD6000 is going to be inflamatory and obtain them a lot of clicks.

 

[wahdangun]

wow, i hope nvdia won't take another 7 month to release these card and make wood screw version before it

 

[Mr McC]

I don't see Nvidia saying anything anywhere, all I see is a pair of websites speculating, based on the fact that speaking about a posible Nvidia response now that AMD is releasing HD6000 is going to be inflamatory and obtain them a lot of clicks.

I see marketing.

 

[beautyless]

I don't know from where did they take those specs, but Nvidia will not release those things. They are absurd. 512 bit? If GF104 has taught anything, that is that performance on Fermi cards depends mostly/only on shaders and is not by any means based on ROPs/bandwidth.

The only probable GF110 specs are one of these (in order of probability):

1 - 3/2 (three halves) of a GF104, that is 3 GPC (clusters)

specs: 576 SP, 96 TMU, 384 bit, core 750 mhz, < 500 mm^2

performance: GTX480 + 25%

Posibility of a dual GF104 card.

2- GF104 with 4 SIMDs per SM instead of 3 (64 SPs instead of 48), 2 GPC

specs: 512 SP, 64 TMU, 256 bit (it would accompanied with 6 gbps memory for about the same bandwidth as GF100), core 750-800 Mhz, << 400 mm^2

performance: ~ GTX480 +/- 5%

There would be a dual gpu card based on this one.

3- Combination of both, #2 but with 3 GPC or #1 with 4 SIMD.

specs: 768 SP, 96 TMU, 384 bit, core 650-700 Mhz, ~550 mm^2

performance: GTX480 + 50%

#3 becomes posible thanks to the fact that TSMC 40nm is said to have exceeded 55nm yields, and Nvidia not fecking up the fabric like they did with GF100.

Also #2 and #3 can easily exist at the same time, as well as a dual card based on #2. That way:

GF110#2 (512 SP part) >>> Bart at a higher cost
GF110#3 (768 SP part) >>> Cayman at a higher cost
2xGF110#2 (2x512 SP) == Antilles at similar cost



I don't see Nvidia saying anything anywhere, all I see is a pair of websites speculating, based on the fact that speaking about a posible Nvidia response now that AMD is releasing HD6000 is going to be inflamatory and obtain them a lot of clicks.

But, I don't think they can make 768 SP part because it was too big.
And 1x512 SP part should be faster and higher power than Bart so 2x512 SP is hard to make.

 

[HalfAHertz]

If they just release unlocked gts460s(as in all cores enabled) and gtx480s, lower the voltage a bit so that they are in the same tdp and name them 466 and 485, Nvidia will be in a pretty good position imo.

 

[CDdude55]

I don't think it's that, it's just that it isn't really news: AMD are on the verge of launching 68XX series and Nvidia hopes to divert some attention away from the launch by stating that they will be releasing faster cards with better features in the future. We already assumed that.

I'm just saying:

nVidia:
http://i55.tinypic.com/wjjtvr.jpg
How on Earth can they chop the GTX480 then put out the original GTX480 as a GTX580? What a move of desperation!
Just when I was annoyed with AMD acting like nVidia with the rebranding/renaming/repricing/whatever, nVidia proved themselves truly unique!

512bit bus. We can assume it will be a 4 digit price tag...

A TDP close to the 480GTX???? I can see where this is heading....:shadedshu

The reason Nvidia hasn't got the single card performance crown is bacause to date, nobody has got a hold of the power issues. Don't hold your breath for this card.

wow, i hope nvdia won't take another 7 month to release these card and make wood screw version before it

 

[btarunr]

I find this term very subjective...

The next 3 months.

 

[derwin75]

Nvidia GeForce GTX 580

That's terrific news about the new GF110 Fermi card. But I read somewhere online stated that GeForce GTX 580 will have 580 Cuda cores not 512 Cuda cores. Here is a statement below:

( NVIDIA announced a next-generation GeForce GTX 500 series , the first high-end models named GeForce GTX 580 based on the Fermi architecture.

The GeForce GTX 580 features 580 CUDA cores to go along with its "580" moniker and have a whopping 2560MB of 384-bit GDDR5 memory

"Although we're very proud of the GTX 480," NVIDIA President and CEO Jen-Hsun Huang said, "the 400 series is merely a tease for what Fermi can really accomplish. When we release the 500 series later this year, I think everyone will be pleasantly surprised. ) By Softpedia News.

Anyone care to explain this....In my opinion I would rather buy a 580 cuda cores card instead of 512 cuda cores card.

 

[Red_Machine]

Later THIS year? Good god...

 

[Benetanegia]

But, I don't think they can make 768 SP part because it was too big.
And 1x512 SP part should be faster and higher power than Bart so 2x512 SP is hard to make.

No because you are not understanding how those 512 and 768 SP parts would be achieved. You are only adding a SIMD into every SM and that does not add much die area to the SM, as can be seen from the fact that GF104 has 3/4 of the shaders, same TMU and SFU number, crammed into less than 2/3 the die area of GF100:

GF100: 512 SP, 64 TMU, 64 SFU, 382 bit ==> 530 mm^2
GF104: 384 SP, 64 TMU, 64 SFU, 256 bit ==> 332 mm^2

GF110#2: 512 SP, 64 TMU, 64 SFU, 256 bit ==> (?) 375 mm^2
GF110#3: 768 SP, 96 TMU, 64 SFU, 384 bit ==> (?) 375/2 * 3 = 560 mm^2*

* GT200 was 576 mm^2 and both AMD and Nvidia, as well as TSMC are saying that TSMC's 40nm node is finally as good as 55nm or 65 nm.

 

[mdm-adph]

The next 3 months.

Oh, I don't doubt that in the next 3 months Nvidia will release either A) another press release B) nothing, because the card will be delayed, or C) a card that was supposed to be called the GTX 495, but rebranded as a GTX 580.

 

[beautyless]

No because you are not understanding how those 512 and 768 SP parts would be achieved. You are only adding a SIMD into every SM and that does not add much die area to the SM, as can be seen from the fact that GF104 has 3/4 of the shaders, same TMU and SFU number, crammed into less than 2/3 the die area of GF100:

GF100: 512 SP, 64 TMU, 64 SFU, 382 bit ==> 530 mm^2
GF104: 384 SP, 64 TMU, 64 SFU, 256 bit ==> 332 mm^2

GF110#2: 512 SP, 64 TMU, 64 SFU, 256 bit ==> (?) 375 mm^2
GF110#3: 768 SP, 96 TMU, 64 SFU, 384 bit ==> (?) 375/2 * 3 = 560 mm^2

Ahh! I see. I agreed with you now. So GF100 is the fail config design, I think. GF104 is much better.

 

[Benetanegia]

Oh, I don't doubt that in the next 3 months Nvidia will release either A) another press release B) nothing, because the card will be delayed, or C) a card that was supposed to be called the GTX 495, but rebranded as a GTX 580.

Yeah because Nvidia has always been late and has dissapointed, unlike AMD/Ati...

 

[iamverysmart]

Maybe they can use the shaders of the GTX460/GTS450 to make the power consumption acceptable?