http://img223.imageshack.us/img223/3123/picture48h.png
close one
Printable View
With a launch at Q1 that let's a lots of time for AMD to make a move.
Why are people hyping up ECC so much, the ATi's cards also support something similar if not same "EDC" even that is great tech for some GPU-CPU action.
Blah, didn't we go through this last year and the year before? Rumor mill never ceases...
Btw, good to see you around diltech :)
no it isnt. what would they do except lower price point?Quote:
Originally Posted by AbelJemka
Sell a lot of DX11 cards while preparing something special for G300 launch?Quote:
Originally Posted by Chumbucket843
http://www.anandtech.com/video/showdoc.aspx?i=3651&p=6Quote:
Originally Posted by ajaidev
so whats the clock speed
it was officially announced so we have some specs its not all rumorsQuote:
Originally Posted by EternityZX9
probably due to ECC?Quote:
Originally Posted by SamHughe
Please argument!Quote:
Originally Posted by Chumbucket843
If you're point is 4 months is nothing, i laugh in advance :rofl:
what move will they make then? 5890? please tell me.Quote:
Originally Posted by AbelJemka
Lower price point and raise clock speeds to make HD5890? Not much you can do... unless you're expecting some kind of a miracle new architecture in 4 months. :ROTF:Quote:
Originally Posted by AbelJemka
Watching the Nvidia GTC, I have a good feeling that GF100 will be special... much faster and better than the competition in every aspect except price.
I think the performance is totally a mystery to every everyone at this point so they don't know whether to jump or stay put. And even if they were to make a move, it couldn't be much more than a clock jump as i doubt AMD would think r8xx was only going to last 6 months.Quote:
Originally Posted by AbelJemka
Knowing AMD they might just completely forfeit the high end and fight at 250 and below for the next year if this card turns out to be 50-60% percent faster than the 5870, like they did against intel lately or 88xx generation to an extent. If the gtx 380 is able to somehow beat r800, it might just completely abandon it altogether, as I doubt it would sell well at all, as 3870x2 bombed and it was still beating the 8800 ultra. This was lots to do with NV just being a stronger brand due to marketing.
This is all talk at this point until NV atleast shows the card.
There's 2 things they can do, 5890 with maybe another 100-150 mhz, and a 5870x2.Quote:
Originally Posted by AbelJemka
This card should still be faster than a 5890, and a GTX-395 will likely walk all over the 5870x2 with ease.
2x+ the speed of a GTX 285(not sli, literally double or more performance) will put a single GTX-380 far above the 5870(40 to 60%, if not more), and a simple overclock of the 5870(5890) is NOT going to catch it.
There's no way ATi can launch another architecture in 4 months, so those are their only 2 options.
Complete Nvidia brigade jump on me:p:
No, you're just making assumptions that doesn't make sense. Seriously, what do you expect in 4 months? A new architecture? I really want to know your answer.Quote:
Originally Posted by AbelJemka
I have no preference over certain brands as I have two HD5870s in my desktop but you on the other hand. :rolleyes:
Bigger die = more expensive card. Lets see who wins price / performance wise.
The way I -feel- about it, AMD solution will offer better price / performance ratio for games, while Nvidia will offer additional computing features.
Exactly, the true ECC won't happen with GDDR5, expect the Telsa cards to have DDR3 on them.Quote:
Originally Posted by ajaidev
Umm... have other cards out? Have a die shrink being prepped and released shortly after? Ever thought on why Cypress and Juniper are so large for their bus sizes?Quote:
Originally Posted by Chumbucket843
750mhz core is supposedly the targeted core clocks.Quote:
Originally Posted by zanzabar
Yep, seems that way now that certain people are back posting...Quote:
Originally Posted by AbelJemka
Edit- If anyone is expecting these cards to have a massive performance lead over 5870 is sadly going to be very disappointed.
Details on ECC ---> http://www.anandtech.com/video/showdoc.aspx?i=3651&p=6Quote:
Originally Posted by ajaidev
Ok i give you what i thinking.Quote:
Originally Posted by Clairvoyant129
I will quote Anandtech article about Fermi :
http://anandtech.com/video/showdoc.aspx?i=3651&p=7
AMD launch it card before this time, what AMD is doing now : extrapolate GT300 performance and cost.Quote:
Ujesh is wiling to take total blame for GT200. As manager of GeForce at the time, Ujesh admitted that he priced GT200 wrong. NVIDIA looked at RV670 (Radeon HD 3870) and extrapolated from that to predict what RV770's performance would be. Obviously, RV770 caught NVIDIA off guard and GT200 was priced much too high.
Performance? GTX285 SLI is like 30% faster than 5870 in average. GTX380 may be more like 50% to 60% faster than 5870 in average. Maybe even less.
Cost? 40% more transistors than RV870 and 384bits istead of 256bits. 600$? More?
Diltech speaks about GTX395 but in Nvidia history multigpu cards were launched very late (More than 6 months in average).
Basically AMD have 3 months to sell DX11 card with the help of Windows 7.
Read above...Quote:
Originally Posted by ubuntu83
Wow, its like an 8800GTX but with more RAM, and 4x the shaders... :p:
The 8800GTX was awesome so this probably will be too. :)
I doubt it'll be $600, NVidia said they realized they launched the GTX-280 too high and they won't be making that mistake again. I'm thinking probably around $400 at launch, which will put a VERY tight squeeze on ATi.Quote:
Originally Posted by AbelJemka
Of course, that's all theoretical as no one can know for sure how NVidia will price this thing. We'll find out soon enough though. Considering NVidia is aiming to market for tesla, where the profit margins are much higher, they can afford lower prices on the desktop cards and make the difference off tesla kits. Just a little something to keep in mind. ;)
those will only compete at price point. i am suprised to see you not excited about this card. 2 kernels,new ISA and a new mem hierarchy... yayQuote:
Originally Posted by LordEC911
are you referring to a 28nm shrink?:confused:i thought the die was big because they doubled everything.
Quote:
Originally Posted by ajaidev
amd's cards can detect errors on the memory BUS only and not do a thing to correct them. If there is an error on the bus connecting the controller to the chip, amd's card can try to adjust the signal to maintain a stable connection to the memory chip.AMD did this to maintain higher memory clocks without having to change traces on the pcb. ECC on fermi is for more than just the memory bus.