Question on die shrinks, GT200b specifically..

Hauk

Platinum Member
Nov 22, 2001
2,806
0
0
I don't know much about architecture stuff so these may be dumb questions..

With the rumored GT200b, could nVidia do anything besides increase clock speeds to counter R700? Could they add more shaders or something? Or does the architecture have to stay the same?
 

SergeC

Senior member
May 7, 2005
484
0
71
It would drop power consumption (and therefore heat), and allow for higher clock speeds. All good things.
The next obvious step would be to take advantage of the lower thermal output per transistor...and start adding functionality. So yeah, it's possible.
 

HurleyBird

Platinum Member
Apr 22, 2003
2,757
1,443
136
Well, 9800GTX+ didn't really drop temps at all, so whether or not G200b gets getter temps is up in the air.

Going to a 256-bit GDDR5 MC would lower temps though, and at the very least costs will decrease, yields will increase, and it will be less painful to bin higher speed grades.
 

taltamir

Lifer
Mar 21, 2004
13,576
6
76
it dropped temps if clocked at 9800GTX+, they simply increased the clockrate so much that the temps went back up beyond the original point.
 

Cookie Monster

Diamond Member
May 7, 2005
5,161
32
86
It really depends on what kind of approach nVIDIA took. If the rumours are correct 55nm G200's have already been taped out and has probably already entered the volume production stage to go retail in next month.

IHMO the move to 55nm has probably been made half a year ago. With rumours of it being taped out and soon to be released, this is only possible if such a decision was made roughly 5~6months ago. (Since even the easiest of transitions to a smaller process takes months). I think this makes perfect sense seeing as that would coincide with them missing their next gen launch around nov~dec timeframe in 2007 because they went with the 55nm route and we all know the reason why.

What does this mean? i think the initial wave of the GTX200 series based on 65nm process was just a strategic move to see what kind of product AMD had in store. Since performance figures are already out, i think nVIDIA can easily counter those products with its 55nm process based products. The GTX260 and 280 severely lack in the shader clock frequency. I can see this part of the architecture being healthy boosted to around 1400~1500MHz.

Im not sure what kind of approach nVIDIA took when transitioning its G200 GPU to the 55nm process. It could be a simple die shrink, i.e the same architecture (since theres no need to change the layout of the architecture when going to a half node process). It could be something along the lines of G70 to G71 i.e to making the G200 much more economical than a simple die shrink (removal of the unnecessary fat/transistors, re-structuring/layout of its architecture to decrease GPU die size since G200 isnt densely laid out like RV770). Or the last one is highly unlikely but some major reworking has been done to provide new features such as DX10.1, or the architecture is based around a 256bit+GDDR5 combination. Personally the first two sounds more likely.
 

Keysplayr

Elite Member
Jan 16, 2003
21,209
50
91
Originally posted by: taltamir
it dropped temps if clocked at 9800GTX+, they simply increased the clockrate so much that the temps went back up beyond the original point.

This 9800GTX+ seems to reside around 64C under load. Is that beyond the original point?
 

Genx87

Lifer
Apr 8, 2002
41,091
513
126
I wouldnt expect much difference in the die shrink. Maybe a few changes to optimize the core. The thing you will see the most is the ability to clock higher due to reduced power and heat.
 

Keysplayr

Elite Member
Jan 16, 2003
21,209
50
91
Originally posted by: BFG10K
Originally posted by: keysplayr2003

This 9800GTX+ seems to reside around 64C under load. Is that beyond the original point?
Yep, according to these figures:

http://techreport.com/articles.x/15105/7

The bottom graph shows the 9800 GTX+ having a higher load temp than the 9800 GTX.

Not bad at all. +1C difference with much higher clocks and same exact cooler.

And, I made an error. 64C at load was my temp when overclocked to 821/2xxx/2354 ( I forget linked shader clock at the moment, but was over 2000MHz).

Those same graphs also show slightly lower power consumption and slightly less noise for the GTX+ over the GTX. So, apparently, the die shrink had some effect.
 

isandu

Member
Oct 15, 2007
41
0
0
9800GTX+ performs very close to an overclocked 9800GTX at the same frequencies, both in terms of power draw and in terms of temps. ATI was able to reduce the power draw A LOT by going to 55nm (though the die size wasn't the only change, but still), I would have expected the G92b to have less power draw than it has. I kind of suspect that the 9800GTX+ most review sites received are not G92b because maybe they weren't ready yet, so they simply sent them with the overclocked G92 chips because they would perform exactly the same as G92b in terms of performance.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |