Warning: long post. Theoretical calculations. Train of thought textual vomit ahead. This is an analysis looking at heat in this system.
First things first:
Heat is not temperature is not thermal energy.
Heat is a process: the flow of thermal energy from one location to another. As humans, this is what we sense.
Temperature is a physical measure of thermal energy present, although correlated, it depends heavily on the properties of the material.
Thermal energy is what causes temperature, and is a byproduct of any use (degradation) of high grade energy.
Video cards produce thermal energy in direct proportion to their power consumption. This thermal energy manifests as an elevated temperature, which causes heating. "Heatsinks" are thermal energy reservoirs, which cause a transfer of thermal energy to themselves, they "heat" up.
Secondly, it should be noted that in the two pictures being compared in this thread by Seero, that the HD 6990 is running on "Standard" mode; from all the reviews I've seen, the HD 6990 consumes less power than the GTX 590. I've seen anywhere from 15-100W less in terms of total system pwoer; unfortunately, xbit labs hasn't come out with their power consumption numbers for the video cards themselves (yet). It is my suspicion that the HD 6990 in O/C mode runs about the same power consumption as the GTX 590 at stock. I can't say for sure, as reviews vary with sites like Anandtech pegging the 6990 OC at higher system consumption than the 590, while other sites like Tom's, Tweaktown, TechReport, etc. as showing 6990OC using less or the same amount of power as the 590. I feel 6990OC wattage~=590 wattage is a reasonable position to take. Thus, in the picture being compared, the HD 6990 is dissipating rather less thermal energy that the gtx. The correct comparison is the 6990 OC vs 590. I will be comparing these two pictures.
Thirdly, assuming an equal airflow (big assumption; feel free to disagree, but please explain why), the 6990 is exhausting up to twice as much air outside the case as the 590 gtx is. The physics of why a 590 will exhaust less air (given similar "free air" CFM fan ratings) has been discussed in the last few pages. The assumption of equal CFM I make on the fact that the 6990 card itself runs cooler than the 590. This indicates that even under similar power situations, the 6990OC is still dissipating more thermal energy away from the video card itself. Given that the biggest indicator of cooling performance in this situation would be CFM (combined with exhaust temperature, which is equal), I would say that the CFM numbers would be comparable, if not greater in the 6990.
Fourthly, if you might notice, the HD 6990 OC pic shows that the area above the video card is warmer than the 590 pic. There is extra thermal energy above the 6990 than the 590.
Finally, to put it together. The 6990 OC exhausts up to twice as much air as the 590. Their power consumption is the same. Airflow is unknown, but assumed to be comparable.
Note: I am saying energy but referring to watts as a unit. This is technically incorrect. Let us say I am working off of a unit time, ie 1 second.
Therefore, given the same thermal energy to dissipate, the 6990 right off the bat dumps ~50% of its energy (~190-225W remains) outside the case. Let us be generous to the 590 and say it manages to dump 33% of its energy outside the case through the rear vent (251-300W remains). At nomial 375 W rating, that's an extra 64 W of energy. At 450W, that's 76W extra energy dumped into the case.
It is also known that there is more thermal energy above the 6990 OC than the 590 (temperatures are higher on the mobo and HD cage). Therefore, there is more thermal energy above the 6990 than the 590.
Thus, my conclusion. The absolute numbers don't mean very much, just the relative numbers here. Assume that the 590 dissipates 170W of thermal energy above the video card. Assume that the 6990 dissipates 200W of thermal energy above the case. Where does the rest of the energy go? Below the card, of course. For the 6990, ~20-55 watts of energy below; for the 590, 80-130 watts below.
Are my numbers right? Fat chance. But it is a reasonable analysis of thermal energy tracking? I would say yes. This analysis, in and of itself, does not explain the cold spot. But it shows that it is definitely possible for the 6990 to leave that cold spot there, based on quantities of thermal energy alone. There does not need to be an intake fan. (it would have to be an intake fan based on that image; if it were an exhaust fan, that area would show up as much warmer) My personal theory for that cold spot is that the cables directed the interior 6990 exhaust slightly upwards, resulting in a stagnant air bubble there, which also explains why there is more thermal energy above the 6990.