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.
87 Comments on ASUS Working on MARS II Dual GTX 480 Graphics Accelerator
Let's see history of mainstream beating pefromence kings:
7800GX2 = 8800GTS
9800GX2 = GTX260
HD3870X2 = HD4850
HD4870X2 = HD5850
BT the last two pics would not load for me.
Given the ARES I intolerable noise levels at load, expect this to be one noisy piece of hardware.
3 8-pin connectors will be needed to power this monster......:roll:
though I think the naming scheme is meaning "we are using 2x"most-powerful-GPU@the-moment" or just SLI/CF on a single PCB :D
though I would really like to see 2xGF104 instead of 2xGF100... should be much better card - gaming I mean... ;)
7800GX2 = 8800GTS - couldn't really find anything on this but the original gx2's were pretty slow due to driver issues so I'd more compare it to a 7900GTX actually.
9800GX2 = GTX275
www.techpowerup.com/reviews/Zotac/GeForce_GTX_275_Amp_Edition/29.html
HD3870X2 = HD4870
www.techpowerup.com/reviews/MSI/HD_4850/23.html
HD4870X2 = HD5870
www.techpowerup.com/reviews/ATI/Radeon_HD_5870/30.html
being that those are upper mid or lower highend you've got more than 1 generation if you go dual. If you throw in the gtx295 it competes with the 480 quite nicely.
www.techpowerup.com/reviews/NVIDIA/GeForce_GTX_480_Fermi/32.html
my ftw edition being faster still.
so last gen dual gpu highend = current gen single gpu highend for the most part these days.
the draw backs are of course higher heat and power requirements than the newer cards, but that won't matter to someone who already has the dual gpu.
so this card will likely last a bit, it's just going to be expensive as hell and of course only be available in limited quantities.
And even with a design like that, ASUS would probably be forced to put the most powerful Delta fans in that cooler.
Guess that thing will be able to get as loud as a Jumbo-jet taking off.
Even the thought of putting two of these in SLI is enough for my mind to explode. The cooling soultion is probably gonna be godlike.(unless they just go with water cooling)
I know damn well i won't be able to afford this nor be able to power it. I'll just stick with picking up a second 470.:)
"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. "
Besides, this isn't NV's solution, it is Asus - and they are nutters. I'm sure they can make it but the cooling solution will be a single plane ticket to alaska and a hole in the frozen ground to put it in.
They'll call it 'Mars to Fermi - Baked Alaska done right'
Qudos to Asus for being mental enough to try anything!
To be fair though (or not so fair) most product reviews for the Mars and the Ares aren't very appreciative.
Cause it's gonna take them forever to find a sufficent enough air cooler to keep that card within reasonable temps.