AMD is undertaking its product development cycle at a breakneck pace, NVIDIA trailed it in the DirectX 11 and performance leadership race by months. This November, AMD will release the "Cayman" GPU, its newest high end GPU, the expectations are that it will outperform the NVIDIA GF100, that is a serious cause for concern, for the green team. It's back to its old tactics of talking about GPUs that haven't even taken shape, to try and water down AMD's launch. Enter, the GF110, NVIDIA's new high-end GPU under design, on which is based the GeForce GTX 580.
The new GPU is speculated to have 512 CUDA cores, 128 TMUs, and a 512-bit wide GDDR5 memory interface holding 2 GB of memory, with a TDP of close to that of the GeForce GTX 480. In the immediate future, there are prospects of a more realistic-sounding GF100b "brute force" which is basically GF100 with all its 512 CUDA cores enabled, while retaining its 384-bit GDDR5 memory interface, 64 TMUs, and slightly higher TDP than that of the GTX 480.
New rumors GF110 bring yet another conversation, this should already be in production and ergo to the frequencies must be final. It is obvious that Nvidia Cayman counter XT - in whatever form, is unclear. The colleagues of the 3DC have a supportive statements usually reliable source with the potential data employed on, PHK has Expreview forum also details alleged scattered. Apparently goes Nvidia as with GT200 (b) the "brute force" way and relies on massive ROP Power: A monstrous 512-bit memory interface with 64 grid amplifiers are to it, this would primarily the memory bandwidth up pulling in ( the pixel fill GF10x hangs on to the shader multi-processors, no more of the ROPs!) and especially when using anti-aliasing processing power increase before. Even memory is the use of 2 GiByte GDDR5 so no problem, if Nvidia had thus bandwidth and VRAM monsters in the market dismisses one is questionable.
http://translate.google.com/transla...e-GTX-580-unterwegs/Grafikkarte/News/&act=url
"brute force"
The new GPU is speculated to have 512 CUDA cores, 128 TMUs, and a 512-bit wide GDDR5 memory interface holding 2 GB of memory, with a TDP of close to that of the GeForce GTX 480. In the immediate future, there are prospects of a more realistic-sounding GF100b "brute force" which is basically GF100 with all its 512 CUDA cores enabled, while retaining its 384-bit GDDR5 memory interface, 64 TMUs, and slightly higher TDP than that of the GTX 480.
New rumors GF110 bring yet another conversation, this should already be in production and ergo to the frequencies must be final. It is obvious that Nvidia Cayman counter XT - in whatever form, is unclear. The colleagues of the 3DC have a supportive statements usually reliable source with the potential data employed on, PHK has Expreview forum also details alleged scattered. Apparently goes Nvidia as with GT200 (b) the "brute force" way and relies on massive ROP Power: A monstrous 512-bit memory interface with 64 grid amplifiers are to it, this would primarily the memory bandwidth up pulling in ( the pixel fill GF10x hangs on to the shader multi-processors, no more of the ROPs!) and especially when using anti-aliasing processing power increase before. Even memory is the use of 2 GiByte GDDR5 so no problem, if Nvidia had thus bandwidth and VRAM monsters in the market dismisses one is questionable.
http://translate.google.com/transla...e-GTX-580-unterwegs/Grafikkarte/News/&act=url
"brute force"
, and cost of 1000 $ if they going make it 512 bit
It would be what a GTX480 was supposed to be, or at least closer. A 512SP Fermi core should not be called a GTX580.