For this test, we first let the card sit in idle to reach thermal equilibrium. Next, we start a constant 100% gaming load, recording several important parameters while the test is running. This shows you the thermal behavior of the card and how the fans ramp up as temperatures increase. Once temperatures are stable (no increase for two minutes), we stop the load and record how the card cools down over time.
Pay attention to the second part of the blue curve, above "Frequency". Note how the clocks suddenly start fluctuating wildly. It seems the card encounters some kind of "throttling" condition, which is probably related to heat, and tries to keep heat output in check. Besides the obvious implications of the clock swings, what's surprising here is that the voltage gets dialed up all the way to 1.2 V from time to time—higher than when the card is running cool. Higher voltage means more heat output, which of course amplifies whatever the clocking mechanism is trying to avoid.. not a good solution.
Voltage-Frequency Analysis
For the graph below, we recorded all GPU clock and GPU voltage combinations of our 1920x1080 resolution benchmarking suite. The plotted points are transparent, which allows them to add up to indicate more often used values. A light color means the clock/voltage combination is rarely used and a dark color means it's active more often.
Clock Profiles
Modern graphics cards have several clock profiles that are selected to balance power draw and performance requirements.
The following table lists the clock settings for important performance scenarios and the GPU voltage that is used in those states.