We chose not to rely on the typical computing tests this time around, since we're specifically trying to isolate and compare single- and double-precision math performance. After all, like GeForce GTX Titan, the 780 is a descendant of the powerful Tesla cards. So, we're using metrics that let us test both levels of precision.
Financial Analysis Performance (Float/FP32)
Remarkably, the GeForce GTX 780 ends up closer to the 680 than the Titan.
The Folding@Home benchmark puts Nvidia's GeForce GTX 780 exactly halfway between the GeForce GTX Titan and GeForce GTX 680.
Looking at these results, two things become clear. First, Nvidia regrettably still appears to treat OpenCL as a second-class API. Second, the F@H benchmark proves that porting a CUDA application to OpenCL is not as trivial as it may sound. While the GeForce cards dominate when it comes to protein folding with the explicit solvent, AMD’s Radeon HD 7970 GHz Edition comes out on top in financial analysis performance.
Of course, it’s easy to find other benchmarks that show either one or the other company in the lead, but that’s not what we're after. Rather, we want to show how our field performs in these same tests switching to double-precision.
Of course, one could argue that as we get closer to higher-end products, the performance increase is always minimal and price to performance ratio starts to increase, however, for the past 3-4 years (or so I guess), never has it been that the 2nd highest-end GPU having such low performance difference with the highest-end GPU. It's usually significant enough that the highest end GPU (GTX x80) still has it's place.
The GTX Titan was released to make the GTX 780 look incredibly good, and people (especially on the internet), will spread the news fast enough claiming the $650 release price for the GTX 780 is good and reasonable, and people who didn't even bother reading reviews and benchmarks, will take their word and pay the premium for GTX 780.
Nvidia is taking a different route to compete with AMD or one could say that they're not even trying to compete with AMD in terms of price/performance (at least for the high-end products).
Thats apretty bad analogy. A gpu is still smooth even with some of the cores/vram/etc turned off, it doesn't increase latency/frametimes/etc.
I must've missed something. Why wait a week?