Friday, July 16th 2010
ASUS Working on MARS II Dual GTX 480 Graphics Accelerator
After treating the enthusiast community to the Republic of Gamers (ROG) ARES Dual HD 5870 graphics accelerator, ASUS isn't wasting any time is designing its successor, referred to (for now) as "MARS II". This graphics accelerator uses two NVIDIA GeForce GTX 480 (GF100) GPUs on one board, that's right, the first dual-GPU accelerator based on GF100, which is dreaded for its thermal and electrical characteristics so much, that NVIDIA is content with having the second-fastest graphics card in the market (GTX 480), with no immediate plans of working on a dual-GPU accelerator.
ASUS' ambitious attempt is in the design stage deep inside its R&D, where the design is in an evaluation state. The R&D gave us some exclusive pictures of the MARS II PCB to treat you with. To begin with, the card's basic design is consistent with almost every other dual-GPU NVIDIA card in recent past. There are two independent GPU systems, each with its own VRM and memory, which are interconnected by an internal SLI, and connected to the system bus by an nForce 200 bridge chip. On this card, two GF100 GPUs with the same configuration as GeForce GTX 480 (GF100-375-A3) are used, each having 480 CUDA cores, and connecting to 1536 MB of GDDR5 memory across a 384-bit wide memory interface.ASUS' innovations kick in right from the PCB, since it takes a lot of effort to keep such a design electrically stable, as well form an overclockers' product. MARS II uses a PCB with 3 oz copper layers to increase electrical stability, and used a strong VRM. Each GPU system is fed by an 8+2 phase VRM of its own, which use a new Super Alloy choke that reduces core energy loss. The card takes its power input from three 8-pin power inputs, which are fused.The card is quad SLI capable, and can pair with another of its kind (and probably single GTX 480s). To cool this monstrosity, ASUS is coming up with a beefier than ever cooling solution. With the product being still at an evaluation stage, how long it will take to reach production, or whether it will in the first place, remains to be seen.
ASUS' ambitious attempt is in the design stage deep inside its R&D, where the design is in an evaluation state. The R&D gave us some exclusive pictures of the MARS II PCB to treat you with. To begin with, the card's basic design is consistent with almost every other dual-GPU NVIDIA card in recent past. There are two independent GPU systems, each with its own VRM and memory, which are interconnected by an internal SLI, and connected to the system bus by an nForce 200 bridge chip. On this card, two GF100 GPUs with the same configuration as GeForce GTX 480 (GF100-375-A3) are used, each having 480 CUDA cores, and connecting to 1536 MB of GDDR5 memory across a 384-bit wide memory interface.ASUS' innovations kick in right from the PCB, since it takes a lot of effort to keep such a design electrically stable, as well form an overclockers' product. MARS II uses a PCB with 3 oz copper layers to increase electrical stability, and used a strong VRM. Each GPU system is fed by an 8+2 phase VRM of its own, which use a new Super Alloy choke that reduces core energy loss. The card takes its power input from three 8-pin power inputs, which are fused.The card is quad SLI capable, and can pair with another of its kind (and probably single GTX 480s). To cool this monstrosity, ASUS is coming up with a beefier than ever cooling solution. With the product being still at an evaluation stage, how long it will take to reach production, or whether it will in the first place, remains to be seen.
87 Comments on ASUS Working on MARS II Dual GTX 480 Graphics Accelerator
What we really want to know is what he's going to use on "GTX 495" Quad-SLI.
Dual 1500W PSUs?
Then again, i've seen a rig use 4x GTX 480's in 4-Way SLI and a 980x CPU with a Silverstone 1600w that only hit about 60% load(the PSU) running 3Dmark.
i also think that only the h2o crowd should buy this \>][
By the time they release this if they do. ATI will have something to surpass this like 6xxx. Come on nvidia. Just jump to 6xx and get it over with. lol.
And as for speculation on the power supply, maybe it'll come with a big flaming hole you have to occasionally feed small rodents into.
Woah, there's another microwave producing card coming right up, bet it's going to eat more than 600W of power, then in quad SLI it will be 1000w+ of power consumption, and it's goin to weigh 3kg, 'cause it's cooling system is going to be more heavier... ^^ :laugh:
ASUS is really greedy.
For example, and don't take my word just check some benches, the ATI HD 4870X2 is 15% FASTER than HD5870, not HD5850. I'm guessing the same is for HD3870X2...
I mean you could buy 4x normal fermis several weeks ago if you bribed the company so you could have their whole stock that is
Why pay extra for something like this which will be old by the time you can buy it in stores?
Asus at least not like other companies that only think about profit and sales, there's passion and dedication in what they do and these graphics cards is shown.
These cards are just experiments made by true enthusiast people.
Ya, i really don't see how someone could call this card pointless or useless at all. Whats so pointless or useless about it?
Chances are the people who can afford to buy this card can afford to buy a great case with great cooling(perhaps watercooling), and a nice powerful PSU to go with it. Of course the power consumption is gonna be high and chances are it's gonna run hot, where's the mystery?. These cards are for full frontal power, and are meant for those with deep pockets and have the resources for cooling and powering these cards. It maybe pointless and stupid for the majority, but it has it's market, and they're gonna be damn happy to get there hands on one or even two of these if/when they are released.
Those that are able and willing to spend around $1000 for a video card, should be able to have enough to cool and power the damn thing.