NVIDIA GT200 Rumours & Speculation Thread
- Thread starter Arun
- Start date
- Status
Look how much more densly packed the GT200 is though.. wow, cant say margins will be good, especially with a die that large.
Actually, what I'm more amazed is how leaky the GT200 release is compared to how RV770 hasn't even had a legit die shot yet. Very uncharacteristic of both Nvidia and ATI.
Actually, what I'm more amazed is how leaky the GT200 release is compared to how RV770 hasn't even had a legit die shot yet. Very uncharacteristic of both Nvidia and ATI.
If TDP is over or near 225W 6+8 is required and atm it looks like it will be the case.
What's this - 9900GTX in Tom's Device Manager ? Scroll to last pic on the page.
http://www.tomshardware.co.uk/hdmi-dvi-usb,news-28242.html
http://www.tomshardware.co.uk/hdmi-dvi-usb,news-28242.html
Jawed
Legend
I'm just wondering if it'll be like HD2900XT where 2x 6-pin worked, or if it'll be a hard limit. I know it's too early to tell, just curious what sort of reception this configuration is going to get.
Jawed
Jawed
Legend
Oh completely forgot about G92b....so yeah guess it could be that.
I wonder what pricepoint will 9900GTX will launch at. Since 98GTX will get EOLed in July, will 9900GTX take over that price point or will they push the price point up? If they don't push it up, it looks like there will be a big gap in price between the GT200 and 9900GTX cards.
These are going to be $600-ish cards I think?
You'll have the "affordable" 55nm G92's and RV770 down in the 200-349 range, then with way higher performance and price GT200.
I actually sort of doubt GT200 will sell that well given that scenario. Pie in the sky performance is nice, but not if nobody can afford it, especially in this economy.
You would not say it is not on purpose?
That Nvidia is perhaps telegraphing a message of their new baby monster they are about to unleash. AMD delayed the r700 a bit. Perhaps to bump their clocks in response?
From my view point, AMD is uncharacteristically quiet and Nvidia is unusually giddy with their own apparent success; surprising as Nvidia attempts to take on a much bigger company and AMD at the same time. You'd think they have several secret weapons they are still holding back. i do.
i am guessing at $650 for Nvidia's GT200 top performer. AMD will counter with price [and x2/x3] imo.
-What did that link i quoted say, about $110 for a GT200 chip? That IS a decent margin!
EDIT, Yes
http://www.tgdaily.com/content/view/37554/135/
Last edited by a moderator:
MulciberXP
Regular
Yet again, you can't calculate margins based on an guesstimated retail price less the price of the chip.
apoppin;1165086 -What did that link i quoted say said:
Decent? Maybe, if they can sell enoungh (isn't that easy since GT200 is hi-end). And ofcourse nv also must cover the R&D and employee cost. I don't work in the industry to have an ideea if a $600-650 revenue per part will be ok in this case.
Well in the bizarro universe that the rest of us live in AMD is usually quiet and Nvidia is usually giddy
I'm pretty sure GT200 will have good margins for both Nvidia and AIB's if speculated performance comes to pass. Assuming decent yields margins should be better than the GX2 at least.
Well in the bizarro universe that the rest of us live in AMD is usually quiet and Nvidia is usually giddy
I'm pretty sure GT200 will have good margins for both Nvidia and AIB's if speculated performance comes to pass. Assuming decent yields margins should be better than the GX2 at least.
i live partly in your universe too ..
i did qualify my statements with "uncharacteristically" .. Nvidia is usually very tight-lipped about their future releases - including G80. Unlike GT200, now! ATi was known - in the distant past, 2 years ago - as loose with their NDA, or did you not read theInq?; i admit to it, as a curiosity. Do you still disagree with my view?
i didn't; i gave you a link to a very raw estimate that does not include R&D [to name one important variable]. Of course, i am sure that $110 is a little high - but not for such a complex GPU. Does anyone remember the raw estimate for the G80; there isn't much difference, is there; adjusting for inflation and transportations costs?
Now, if GT 200 turns out to be long life for Tesla architecture - 2 years or better - then the margins will be very good. If it turns out to be a short-lived turkey and we see GT300 in 6 months, then it is probably a very bad margin. These are extreme scenarios.
Simple prediction based on what we appear to know, looks like a decent margin for GT200. Of course, this also depeds on their competition and if Nvidia has to drop prices on their flagship product. Does anyone remember a Flagship, Like Gx2 this year, dropping $100 off their MSRP of $600 within the first month of launch? i would say nvidia is looking to EOL it ASAP! UNlikely to happen with GT200 imo.
I know what you're referring to but I still disagree. Nvidia has made promises regarding GT200 but that's part of a strategic push into the HPC GPGPU area. They have to get people excited and talking about that stuff and can't just spring it on them as a surprise. What they're pushing there is new ideas and new markets and not one specific chip or product. The only specific reference to upcoming products that I can recall is the promise of 1Tflop at the end of 07.
With respect to AMD, RV770 was outed a long time ago so things haven't been particularly tight this time around either.
you are quite correct! Nvidia's CUDA-related innovations demand creating excitement for their upcoming products. Only AMD might still have a possible surprise, but i doubt it; so things DO appear to be changing away from the strict NDAs of just last year. My very minor point, not disagreeing with you at all. And since it also appears that GT200 is long-lived architecture, i speculate that their margins will be very good!
Last edited by a moderator:
I just wonder, how long NV will stand on the GDDR3 node for their SKUs?
If this G200 line is likely to repeat the G80 path, I would see the next die shrinkage (55/40 nm ?) replacement of the bulky GTX-280 to scale down the memory bus in half, wiring some uber-megahertz GDDR5 chippery.
If this G200 line is likely to repeat the G80 path, I would see the next die shrinkage (55/40 nm ?) replacement of the bulky GTX-280 to scale down the memory bus in half, wiring some uber-megahertz GDDR5 chippery.
- Status
