I went overboard on the sarcasm, I admit. I won't be doing that again. However, I definitely would like a feasible explanation of what's going on though - if SLI really is better than single GPU, hey great. I made the right choice.
Maybe toms and pcper just screwed the testing method up. I have no idea. Again: just a reasonable and logical explanation to put the chips in their place. What's going on?
With this chart from
Toms:
We continue to see tiny gaps between frames from our single-GPU cards, though the GeForce GTX 690 consecutive frame time difference more than triples, on average. However, the latencies are still so small, and the frame rates so high, that we would still consider this a good result.
Well, judging from this chart (using the same data as the above bar chart) below:
Where GTX 690 is in fact averaging over 80fps, or less than 12.5ms.
The "average" (median) consecutive frame time difference is 14.1ms (from the first chart), which translates to 70.9 fps if taken by itself. (Actual average is a little over 80fps according to the blue line above.) So, with the ideal frame being only 12.5ms long (80fps), that means each frame would have to be alternating somewhere in between 25 (2 x 12.5) ms long and 0 ms long (or else it would be less than 80fps, period).
Somebody who graduated at the top of Algebra 2++, who isn't so rusty, please calculate the consecutive max and minimum frametimes for the two frames, if the consecutive frame time difference is 14.1ms, in order for the total to average 80fps! Show your work!
That's the ATF challenge (no, not AnandTechForum, but AlaskaThunder*uck)! :biggrin: