Called "Maximus", the technology combines Quadro workstation graphics cards with Tesla C2075 companion cards to provide hardware-accelerated computing environments. Nvidia said that applications that support Maximus are offered by Adobe, ANSYS, Autodesk, Bunkspeed, Dassault Systèmes and MathWorks. Prices start at about $200 for an entry-level Quadro 600 card and $2500 for the Tesla board.
According to Nvidia, the C2075 comes with 448 processing cores and 6 GB of GDDR5 memory, which are good for 515 double-precision GFlops. A Quadro 600 card leverages 96 cores, while the high-end $3500 6000 model, which closely matches the specs of the C2075, runs 448.
Maximus appears to be the most aggressive attempt by Nvidia to drive Tesla deeper into workstation computing since the launch of the original Tesla products and the D870 deskside accelerator in 2007. Back then, Nvidia offered two Tesla GPUs that offered 1 TFlops of single precision floating point performance. Prices then started at $7500.
I don't see how this is new technology at all, since it has already existed for years. And the Quadros have been proven time and time again to be a complete waste of money. I love Nvidia graphics cards as much as the next nerd, but the Quadros and FireGLs are utter bullshit.
And this latest Tesla iteration is in effect a Geforce 590 with more RAM, only it costs five times as much?
http://www.anandtech.com/show/5094/nvidias-maximus-technology-quadro-tesla-launching-todaylordstormdragonAnd this latest Tesla iteration is in effect a Geforce 590 with more RAM, only it costs five times as much?...seriously?
Please try to not be a total douche. Nothing posted in that article stated anything different than what I've stated. I'm in the 3D rendering industry and use GPUs to their fullest, and have vast experience with Quadros and FireGLs.
I understand the Tesla is meant as a workhorse not necessarily relating to graphics at all. I also stated and stand by the Quadro and FireGL lines being a total marketing scam, and have massive amounts of field data to back that claim.
"So what is Maximus Technology? As NVIDIA likes to reiterate to their customers it’s not a new product, it’s a new technology – a new way to use NVIDIA’s existing Quadro and Tesla products together. There’s no new hardware involved, just new features in NVIDIAs drivers and new hooks exposed to application developers. Or put more succinctly, in the same vein that Optimus was a driver technology to allow the transparent combination of NVIDIA mobile GPUs with Intel IGPs, Maximus is a driver technology to allow the transparent combination of NVIDIA’s Quadro and Tesla products."
So it's a driver similar to SLI that lets the Quadro work with the Tesla? They already did that anyway, in all the applications I've used.
My POINT here, which you dullards obviously missed, is that Nvidia didn't need to come up with another marketing ploy. They just need to keep making kickass components.
And yes, the Tesla they're discussing here is identical to the Geforce 590, save (as I stated) it simply has more RAM.
Since you offered no opinion or data at all here except to try to insult me, your post has been thus nullified.
As for the Quadro cards.....you're right. They are little more than a marketing scam. They use the same GPU as their GeForce counterparts, though in most cases they do have more memory than their GeForce counterparts. There is absolutely nothing that the Quadro or GeForce cards can do...that their counterparts can't to the same extent. Sadly, this is nothing new nor is it exactly a secret. Anyone else remember the Quadro "softmods" that were so popular with older cards? The FireGL series is done the same way....and as long as "professionals" continue buying the cards...AMD and nVidia will continue making them the same way they always have.
The stinker is, the Quadros (for example) often perform pretty well in say, Maya, right out of the box. Whereas the Geforce counterparts often require tweaking a few settings to match the Quadros. So many, many studios simply believe the Quadros are better, and companies like Autodesk (who I work closely with and love, actually) perpetuate the notion for Nvidia and AMD. I guess at least AMD offers competition, but it doesn't appear to affect either company's pricing, so that's also not helpful to the prosumer.
I guess what's obnoxious is that there's no way that the extra RAM justifies the extra pricing. One could purchase four GTX580s or more for the price, and come out way, way ahead.
I don't see the Tesla in this configuration as being cost-effective at all, especially with a POS Quadro. And yet, Nvidia will likely lock their gaming cards out of such a config, again reinforcing their higher-priced cards for yet another sucker-punch.
with amd 5770 i have a driver issue with acdsee, and i contacted them with the issue, and got a response back along the lines of, we will not help you, you cant know if they know there is an error, go f yourself and roll back drivers.
but with a pro seriese they listen to you and in some cases get you custom drivers.
at least thats what i have been told the difference is. you arent paying a few k for for that card, but the support that comes allong with it.
Pro cards like this have their applications, however, my bet is that only the most hard core of pro users need something like this - especially since consumer-grade graphics cards outperform Teslas.
IMHO, beware marketing departments.
Just in case you are wondering -