Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
NVidia will be ready to die-shrink before ATI (next month apparently), but die shrinks only tend to give marginal performance increases (maybe 10% at most). The main benifits of smaller die sizes are reduced costs and lower power consumption. Look at the 9800GTX (65nm) vs 9800GTX+ (55nm). Marginal core increases but much lower production and sale costs.Well ATi do have the option, they can bring out a die shrinked 4870, there was an article on it, apparently up to 30% faster than the current one.
What extra SP's ?, the GTX280 so far is just to be shrunk.
How do the ATI cards perform when Physics is enabled?For those that use 8xaa then the 4870 is a lot faster than the 260. In the words of a reviewer they said at 4xaa the cards both are around the same speed but when 8xaa is applied the 4870 leaves it behind. So the 4870 is the faster card overall with all the settings turned up.
http://www.firingsquad.com/hardware/ati_radeon_4850_4870_performance/page15.asp
http://www.firingsquad.com/hardware/ati_radeon_4850_4870_performance/page14.asp
The 4870 bests the gtx260 and 280 in all bar 1 game. From the conclusion : ATI’s really dialed in their 8xMSAA performance also. Whereas GeForce GTX and 9800 boards see a significant performance hit at 8xAA, the Radeon 4800 boards continue to scale well. 8xAA is actually playable in games like Oblivion, Company of Heroes, and Quake Wars. In fact, in our testing the Radeon 4850 was capable of giving the GeForce GTX 260 a run for its money in Oblivion, Quake Wars, and Episode 2, while the 4870 actually outgunned the GTX 280! The GTX cards managed to pull ahead in CoH though.
How do the ATI cards perform when Physics is enabled?![]()
Dropping from 65 to 55nm will not give a 20-30% performance increase. To get that kind of increase BOTH the core and memory would need massive increases in speed. Even if NVidia managed to increase the default core and shader speeds by 20% (10-15% is more likely) overall performance would jump by much less. Look what happened with the 9800GTX+ which has already gone through the shrink process. Many of these overclock no further than the old cards.
Don't get your hpes up. First and foremost the 55nm shrink is aimed at saving production costs.
http://www.evga.com/forums/printable.asp?m=503212
Default shader clock up from 1296 to 1620, thats +25%
This routine from nvidia is really getting stale, was confusing enough last time with the gt and gts varients and now theyre at it again. This gonna be a common trend i wonder?