Mole Tests Geforce GTX 480, Spills Some Of The Beans
@ 2010/02/21The GTX480 with 512 shaders running at full speed, 600Mhz or 625MHz depending on which source, ran on average 5 percent faster than a Cypress HD5870, plus or minus a little bit. The sources were not allowed to test the GTX470, which is likely an admission that it will be slower than the Cypress HD5870.
Getting back to the selective showings of the GTX480, there is a good reason for it. The performance is too close to the HD5870, so Nvidia will be forced to sell it at HD5870 prices, basically $400. The GPU isn't a money maker at this price point, and at best, Nvidia can price it between the $400 HD5870 and the $600 HD5970. The only tools left to deal with this issue are PR and marketing as the chip is currently in production.
If you give the GTX480 to honest journalists, they will likely say that the two cards, the GTX480 and the HD5870, show equivalent performance, so we hear Nvidia is doing its best to keep the GTX480 out of the hands of the honest.
Getting back to the selective showings of the GTX480, there is a good reason for it. The performance is too close to the HD5870, so Nvidia will be forced to sell it at HD5870 prices, basically $400. The GPU isn't a money maker at this price point, and at best, Nvidia can price it between the $400 HD5870 and the $600 HD5970. The only tools left to deal with this issue are PR and marketing as the chip is currently in production.
If you give the GTX480 to honest journalists, they will likely say that the two cards, the GTX480 and the HD5870, show equivalent performance, so we hear Nvidia is doing its best to keep the GTX480 out of the hands of the honest.
So far increasing the shader counts has worked well for performance with both AMD and NVIDIA cards. Something would have to be physically wrong with the design for 2x GTX 285 shader count to not yield significantly more performance.
Just look at current GTX 295 or GTX 285 SLI results to see the performance against 5870 is there. GTX480 has more shaders and much better memory bandwidth, easy to see that it should do far better than just 5%.