NVIDIA Makes First 4GB Graphics Card

Frogger writes to tell us NVIDIA has released what they are calling the most powerful graphics card in history. With 4GB of graphics memory and 240 CUDA-programmable parallel cores, this monster sure packs a punch, although, with a $3,500 price tag, it certainly should. Big-spenders can rejoice at a new shiny, and the rest of us can be happy with the inevitable price shift in the more reasonable models.

Comments

Power != memory

[unity100]

excuse me but this is total bullshit. oldest trick in the book. if you are behind in technology, pop out a card with huge ram and try to get some sales.

lets face it. nvidia has fallen behind ati in the chip race. you can place any number of 4870s in a setup as much as you like to equate the power of any monolithic nvidia card and they always kick the living daylights out of that nvidia card in terms of cost/performance per unit of processing power.

Re:Power != memory

[Anonymous Coward]

This is not a gaming card, this is CAD/CPU card. what I mean to say is, this card in is basically a super computer that fits in a slot and you can put more than 1 on a machine. The idea, being that you can use these GPU's to do more than just graphics. This card's shader is horrible and would not play any graphics intensive game well. it would be a waste of money for a gamer.

Re:Power != memory

[GNUPublicLicense]

Moreover ATI/AMD specs are opened... meaning you can code directly the hardware. That's times more powerfull and flexible than CUDA. And there are frameworks in the works in order to have easy access to GPU lowlevel interfaces (see Intel/AMD GEM work in the mesa project).
Basically, nvidia behavior is generating a lot of hate in coders community...

Re:Power != memory

[Grey_14]

Coder Hate like that brought by the shitty, bug filled drivers that ATI has a long history with?

I think ATI/AMD is on the right path, but they have a long history of being on the wrong path, while NVIDIA has always been more towards the middle (Not completely right, but not too badly wrong). It'll take some time before I jump to the ATI Bandwagon as completely as you obviously have.

Re:Power != memory

[mikael]

There is no upper limit on the amount of memory required for tasks like volume visualisation, where you have a nice big 3D cube of data in 16-bit format. A cube 1024 voxels in each dimension with a single channel of 16-bit data (2 bytes) is going to be 2 Gigabytes. You will need at least two such cubes to do any sort of image processing work.

Even a digital movie can be considered to be a cube if you consider time as the 3rd dimension.

Rather than having cards with a fixed amount of VRAM, which can't manufacturers just put a bunch of memory card sockets on the card and allow users to add memory when they want?

Re:Power != memory

[thtrgremlin]

I was under the impression this is a card for broadcasting. The 4GB allows for many streams to be buffered simultaneously for smooth real-time mixing / crossovers. The biggest thing driving these cards is sports broadcasting due to the demand for a large number of layers.

Re:cool

[loufoque]

Not gonna happen, RenderMan is CPU-only.

How did this retarded comment get upmodded?

[Nimey]

Really, people. If you're going to buy such an expensive professional card, you're going to go with a professional-grade operating system, which will of course be 64-bit.