NVIDIA TITAN X Review: The Pascal Beast Unleashed


Titan X Overclocking, Power Consumption, Noise, and Temps

We also spent a little time overlcocking the new GP102-based TITAN X, to see what kind of additional performance we could squeeze out of it. Before we get to our results, though, we'd like to cover an update to GPU Boost and some new overclocking related features that were introduced alongside the GTX 1080, because they apply here as well.

gpu boost 2

gpu boost 3

Pascal-based GPUs feature GPU Boost 3.0. Similar to how it behaved on previous-gen GeForce and TITAN cards, GPU Boost scales frequencies and voltages upwards, power and temperature permitting, based on the GPU's workload at the time. With GPU Boost 2.0, which is available on Maxwell, you could overclock using a fixed frequency offset and bump up the GPU voltage curve manually, but that leaves some performance on the table because it doesn't offer the kind of granular control necessary to massage every last MHz out of a given chip.

With GPU Boost 3.0, however, you can now manually set the frequency offset on a per voltage point basis. In addition, a new feature coming to overclocking / monitoring utilities like EVGA's Precision X gives users the ability to run a tool that automatically finds a GPU's peak frequency at each available voltage point. The tool basically runs Furmark and tests for stability, while incrementally upping the GPU frequency per voltage point. When instability or image anomalies are detected, the tool logs the peak "good" frequency and moves on to the next voltage step. You eventually end up with a customized overclocking profile, optimized for your particular GPU.

titanx oc
TITAN X Overclocking Details

EVGA's Precision utility doesn't support the TITAN X just yet, so we kept things simple, and used the frequency offset and power / temperature target sliders available in MSI's Afterburner Utility. First we cranked up the power target to 120% and also kicked up the temperature target to 91 degrees.  Then we bumped up the GPU and memory clocks until the test system was no longer stable.

Ultimately, we saw a peak GPU clock of over 1,866MHz with a 5,054MHz memory clock (effective speed 10.1Gbps). Those clocks are not in the same league as the GTX 1080, but the GP102 GPU employed here is a much larger, more complex chip, that requires more power.
oc1

oc2

While we had the card overclocked, we re-ran a couple of tests and saw some moderate improvements in performance in the games / settings we tested. Thief showed a nice jump in performance of about 10%, while 3DMark showed an approximate 5% gain.

Total System Power Consumption
Tested at the Outlet
Before bringing this article to a close, we'd like to cover a couple of final data points -- namely, power consumption and noise. Throughout all of our benchmarking and testing, we monitored acoustics and tracked how much power our test system was consuming using a power meter. Our goal was to give you an idea of how much power each configuration used while idling and also while under a heavy workload. Please keep in mind that we were testing total system power consumption at the outlet here, not the power being drawn by the graphics cards alone.

power

Despite offering the best performance across the board in our tests, the TITAN X wasn't the most power hungry card. Our test machine consumed 15 fewer watts under load with the new TITAN X versus the previous-gen version and significantly less than a 980 Ti or Fury X.

We should also mention that temperatures on the TITAN X are a non-issue as well. At idle, the card's GPU hovered in the upper-30s. And under sustained load the GPU temp shot right up to the default 84'C target. While overclocked though, the GPU temperature peaked at around 85'C when running an actual game.

moise

In terms of its noise output, the TITAN X is very quiet, but not as quiet at the GTX 1080. When idling and under load, it was slightly louder than the 1080, but quieter than the Fury X. We should note, however, that much of the additional noise under load in this graph can be attributed to our test system's PSU and CPU cooler. All of these graphics cards are relatively quiet under load, especially if you test inside a chassis like we do.

Related content