GPU Boost 2.0
For anyone who has ever tried overclocking a graphics card, you know that it’s a bit hit and miss, trying to find the right combination core and memory clocks, voltages, and fan speeds to achieve stability. You’ll also know that trying to match the card’s power consumption to suit your needs is nearly impossible. Nvidia’s GPU Boost technology completely changed the rules when Kepler was released, and it’s continued here with version 2.0 in an evolution of that with the GTX 780 launch.
The original GPU Boost was designed to achieve the highest possible clocks while remaining within a power target. However, clock speeds are only part of the equation of the overall performance of a card. This time around, GPU Boost 2.0 focuses far more heavily on temperature, which is generally more restrictive in terms of performance boost, not to mention noise and heat output. As a result, GPU Boost 2.0 is temperature-driven, not power-driven like its predecessor.
GPU Boost 2.0 is still hardwired right in and cannot be disabled. It is not a driver or software feature; it is a function of the product itself. You can’t change it, you can’t turn it off. What this also means is that the Kepler GPU has two separate core clocks: Base Block (think of this as the traditional core clock) and a Boost Clock (think of this as the automatic Turbo clock).
Also realize that GPU Boost doesn’t negate overclocking; it merely supplements it in a sense. Overclocking a Kepler card will simply increase the Base and Boost clocks. Since they’re not static speeds, think of overclocking on Kepler as just shifting the overhead targets on the card. You’re not achieving particular clocks; you’ll be achieving a range of potential clocks.
To help illustrate GPU Boost 2.0 in action, below is a screenshot from EVGA’s Precision utility software.
As you can see, the temp target is 80°C here, so the card will automatically adjust the power, voltages, and clock speeds to match that. This is a significant change from all previous generation cards where the clocks were set, and all power, all the time, was maintained regardless of user needs.
So, with Kepler and GPU Boost 2.0, users can simply install the card and let it do its thing, optimizing your card’s speeds, power consumption, performance, and temperatures automatically, and just call it a day. Or you can customize the temperature target to suit your needs.
The GPU’s fan curve is fully adjustable, as shown below.
The result of this dynamically adjusting fan speed is that the temperature fluctuations are moderated, and kept more stable, as shown below. The dark green line represents previous fan control, with large peaks and valley of fluctuations, whereas the light green line is the new fan control result, with a much more smooth horizontal line, illustrating a more constant temperature.
This also means that traditional temperature testing in reviews will be a bit skewed because custom coolers will still automatically top out at the same 79°C, when in fact they should be capable of much lower temperatures at load. According to Nvidia, this results in a significant drop in noise levels as well.