The Relative Windows vs. Linux Performance For NVIDIA, Intel & AMD
Written by Michael Larabel in Hardware on 25 June 2016 at 08:23 AM EDT. 46 Comments
HARDWARE --
Following the recent Windows vs. Linux AMDGPU-PRO / RadeonSI testing, GTX 1080 Windows vs. Linux results, and yesterday's Intel Windows vs. Linux benchmarks, here is a look at all three sets of numbers when using some OpenBenchmarking.org magic to merge the data-sets and normalize the results.

For getting a quick and easy look at all of the Intel/AMD/NVIDIA results side-by-side, thanks to OpenBenchmarking.org it's easy to merge and run some analytic passes. From those three earlier articles, here is a look at the comparable data when normalizing the best performance of each vendor/driver. This makes it easy to see the Linux vs. Windows performance overall or for games where the Linux ports are simply rubbish and performing like crap compared to the native Windows game.


So here's some of that merged and normalized data in a multi-way comparison:


As any regular Phoronix reader should know, the Linux version of the Unigine demos generally is quite on-par with Windows... For a number of years, the Unigine Linux tests have performed close to the same on Windows when there aren't Linux GPU driver issues getting in the way.

The poor Xonotic performance on Linux with the Intel driver was one of the biggest surprises from yesterday's article. It's not anything we've seen with the other drivers.


Tomb Raider on Linux performs much worse than the Windows build regardless of your driver / graphics card.

GRID Autosport also gets only around 60% of the performance as the original Windows game.


Valve's Dota 2 / Source 2 Engine is a quality Linux port.


Shadow of Mordor's relative Linux performance is more decent than many other Linux games albeit still isn't running at the same speeds as the Windows games.

F1 2015 also performs much more poorly on Linux than the original Windows games.

It's too bad that so many Linux games perform so poorly compared to the original Windows games, regardless of graphics card brand / driver. Hopefully in due time with the next generation of games making use of Vulkan that we'll see better performance relative to Windows. For more numbers be sure to check out the three Intel / AMD / NVIDIA articles linked at the beginning of the post. If you sign into OpenBenchmarking.org, you can play around more with these normalized numbers and run more analytics via this OpenBenchmarking.org merge. Also a friendly reminder to please consider joining Phoronix if you appreciate all of the work I single-handedly put out each week.

About The Author
Author picture

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 10,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter or contacted via MichaelLarabel.com.

Related Hardware News
Popular News