According to AMD, AMD PowerTune technology helps enable higher performance that is optimized to the thermal limits of the GPU by dynamically adjusting the engine clock during runtime based on an internally calculated GPU power assessment. AMD PowerTune technology also helps to improve the mechanism to deal with applications that would otherwise exceed the GPU’s TDP. By dynamically managing the engine clock speeds based on calculations which determine the proximity of the GPU to its TDP limit, AMD PowerTune allows for the GPU to run within its TDP budget at higher nominal clock speeds than otherwise possible.
AMD PowerTune technology can be directly adjusted by the user using the AMD Catalyst Control Center AMD Overdrive tab. AMD PowerTune can be tweaked to allow for a more aggressive power containment (and therefore more aggressively limit power and heat) or be used by enthusiasts to relax the enforcement of factory thermal constraints on their AMD Radeon HD 6900 Series graphics card for more performance.
While NVIDIA’s power consumption has improved going from the GF100 chipset to GF110, AMD Evergreen and Cayman are still a little more frugal. It is impressive considering how much power high-end AMD and NVIDIA GPUs these days draw at full brunt, yet are able to sip nearly next to nothing on idle.
To measure both maximum system power draw and maximum GPU temperature, we used Furmark 1.8.2 with Xtreme Burning Mode enabled. FurMark is a very intensive OpenGL benchmark that uses fur rendering algorithms. Fur rendering is extremely stressful, thus making Furmark a good GPU
toaster stress testing utility.
Over here, we note that the Radeon HD 6970 is drawing 425.2W from the socket, and the Radeon HD 6950 drawing 368.7W. AMD PowerTune’s power control is set at +20% for both cards.
However, we suspect that there is still a power cap on these cards as AMD calls the maximum TDP as ‘PowerTune Maximum Power’. Just to jog your memory, the limits are 250W and 200W for the HD 6970 and HD 6950 respectively.
NVIDIA’s throttling is pretty aggressive when it detects ‘power viruses’ such as Furmark and OCCT stress test utilites. With OCP enabled, the GeForce GTX 580 just draws around 340W from our wall socket. Thus, for NVIDIA’s GeForce GTX 580 and GeForce GTX 570, the power containment mechanism was disabled via GPU-Z.
The GeForce GTX 570 draws 431.1W on full load, just 6W more than the Radeon HD 6970. The GeForce GTX 580 draws 459.5W, but do not forget it is a good 15% to 20% faster than the GTX 570.