Ubuntu 16.10 Doesn't Change Much With Performance, Clear Linux Still Leads In Most Tests
Written by Michael Larabel in Clear Linux on 29 September 2016 at 07:58 AM EDT. 16 Comments
Given yesterday's Ubuntu 16.10 final beta release ahead of the official "Yakkety Yak" debut in two weeks, I decided to run some benchmarks of Ubuntu 16.10 compared to Ubuntu 16.04.1 LTS on the same system plus also throwing in the Intel Clear Linux distribution given it tends to be one of the most performant.

For those that haven't yet tried out Ubuntu 16.10 nor followed its development, GCC 6.2 is now the default compiler in place of GCC 5.4 from Ubuntu 16.04 LTS. Mesa 12.0.3 provides the stock graphics drivers and Linux 4.8 is the stock kernel.

Tests for this article though are just focused on disk/CPU performance as the graphics unfortunately didn't pan out. The GeForce GTX 770 on this particular test system would have a blank screen when booting Ubuntu 16.10 with its Linux 4.8 kernel. I couldn't figure out any workaround aside from nomodeset, so unfortunately no graphics results for this article. However, with the upgrade to Mesa 12.0 from 11.2, users should see out-of-the-box OpenGL performance improvements particularly for Intel and Radeon open-source users.

All three operating systems were tested on the same Xeon system with clean installs of each OS for this quick comparison. More benchmarks -- including more distributions for the comparison -- will come when Ubuntu 16.10 is officially out in October.

SQLite was about the same speed, Ubuntu was actually slightly faster than Clear Linux in this test.

SciMark2 and some other tests won with Clear Linux, in part due to this Intel distribution shipping with aggressive compiler flags enabled by default.

Clear also ships with the ACPI CPUFreq driver for latest Intel hardware rather than P-State, among other differences.

You can see more of this benchmark data via this OpenBenchmarking.org result file.

For the most part, Clear Linux led Ubuntu still in this latest round of benchmarks. Then from the other purpose of this testing, there isn't much of a performance change in going from Ubuntu 16.04 LTS to 16.10 with Linux 4.8 and GCC 6.2. But the big area where you may see performance improvements and better functionality is with the Mesa 12.0 graphics stack, which is much better than Mesa 11.2 of 16.04 LTS but still a lot more exciting work can be fetched if manually switching to Mesa Git.

I've also been working on some deep learning oriented benchmarks on the CPU for a future comparison. Still going to test more distributions and such, but if you want a teaser of that:

That's from this OpenBenchmarking.org result file while keeping in mind more of those tests are still forthcoming. These real-world-applicable results are very interesting and possess an even greater lead for Clear over Ubuntu.
Related News
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 20,000 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.

Popular News This Week