7900 GTX is old. What's Next?

[loveamd]

Ok, so the 7900 has been out for a while now. I'm sure we all have one and are tired of the slow FPS.

So any ideas on what the next generation of Nvidia and ATI cards will look like, what type of power they will have and when they will be available to buy.

 

[sackynut]

LOL! dx10.

 

[dorion]

I keep on hearing this wierd mumbo jumbo about combining pixel shaders with something... I guess I didn't pay much attention.

 

[tenaciousleydead]

like sacky said dx10! something out of the xbox 360 maybe... they already have dx10 built in. i hope nvidia chooses another number system i think 8000 whatver sounds kind of stupid.

 

[a1ien]

nah man, dx10 is old... geeshhh... get with the program. (dx)^2 is the way to go 8)

 

[Hitokiri777]

G80, dx 10 card, still using ununified pixel/shader, going to be 512 and duel card that is 1 GB, launch is due in june. This is all rumor....but atlest it didnt come from the inquirer

 

[bront]

I keep on hearing this wierd mumbo jumbo about combining pixel shaders with something... I guess I didn't pay much attention.

Pixel and Vertex shaders are supposed to merge. The XBox 360 already has the unified shaders, and DX10 supports it. However, the rumor is that DX10 will only be on Vista.

Nvidia meanwhile, is refusing to do the unified shader thing, but will build a driver work around for it in their next gen card.

ATI, meanwhile, already has it from their XBox setup, and it should be in their new cards.

I'm guessing my 7800 GT will last me a year or two, depending on if I keep playing 3D games or not. I can only hope it lasts as long as my Radeon 8500 (Still going, but not on my main machine, replaced it with the 7800 GT), but that realy depends on how much newer games will push the cards.

 

[TabrisDarkPeace]

Ok, so the 7900 has been out for a while now. I'm sure we all have one and are tired of the slow FPS.

So any ideas on what the next generation of Nvidia and ATI cards will look like, what type of power they will have and when they will be available to buy.

- They'll look similar and be PCI Express Graphics x16 slot cards

- They'll use 65 - 75 watts from the PCIe x16 slot, and likely up to 150 watts or so from the PCIe 6-pin power connector, or connectors from the PSU. (Similar to now, however some may require the 75 watt varient of the PCIe x16 slot).

- They'll be available around October - November this year

- Using the the 80nm process performance is only expected to be +30% higher.

- Come March / April 2007 the next batch will be twice as fast as the existing top end cards (GeForce 7900 GTX / Radeon X1900 XTX) as likely based on a 65nm manufacturing process.

Does that answer your questions ?

 

[bront]

- They'll be available around October - November this year

I believe the current timelines have them coming out around June/July.

 

[TabrisDarkPeace]

Any card coming out within 6 months won't be using 65nm, and thus one can conclude the 80nm manufacturing process will be used.

Current cards are using 90nm, going to 80nm will gain them +25% to +30% in transistor count, (As in 90^2 divided by 80^2), and a little in clock speed, say another 10% or so.

If the 7900 GTX got (+(1.25 x 1.1)) 38% faster would anyone really care ?, I think not (as it is under a doubling of the performance which is what people want).

So it makes sense to wait (unless your current setup is too slow) for 65nm GPU/VPUs around March 2007. (As 90nm^2 divided by 65nm^2 = at least +91% increase, or twice the number of transistors as the current 7900 GTX), and then another +33% in clock speed, for a total performance leap of around 2.54 times as power than the existing 7900 GTX.

Chances are they'll add another layer to the GPU / VPU construction when moving to 65nm, so it will be more like a +105% (2.05 times) the number of transistors when compared to the existing 7900 GTX, and thus provide 2.75 times the performance in the final version (eg: Likely called the GeForce 8800 to 8950 GTX with Direct X 10 support in March 2007).

The only alternative if die shrinks are not available is to make 'larger' GPUs, with lower yields, which would give the parts a very high price... or designing a new interconnect on the video cards themselves and running two (or more) GPUs with low power usage on one card (and I am not talking about SLI or Crossfire on one card which is just a basic hack), this would be far more efficient than existing SLI / Crossfire solutions.

Have a look at: http://www.es.com for some ideas.