If you have been curious how the performance of the GNU/Linux stack has evolved over 2016, I ran some benchmarks of the rolling-release Clear Linux from the start of 2016 compared to this week to see how gains in the upstream software have evolved as well as their aggressive out-of-the-box optimizations for this operating system out of Intel's Open-Source Technology Center.
Clear Linux was used for this 2016 before/after comparison due to Intel's aggressive performance optimizations made this year and that it's a rolling-release distribution but with publishing new installer images for each release, which is on a near-daily basis, it's easy to get the system back to its state far back in the past. This makes it much easier to run fresh benchmarks on an older state of Clear Linux compared to today, rather than using Arch Linux or another rolling-release where it's less easy to get the system to a prior state long ago.
For representing Clear Linux at the start of the year I used Clear Linux 6030, which is their build from nearly the beginning of the year. Their first releases of 2016 unfortunately weren't working on my Haswell test system used due to some UEFI issues, while Clear Linux 6030's installer had no troubles. Clear Linux 6030 shipped with the Linux 4.4 kernel, Xfce 4.12, X.Org Server 1.18.0, xf86-video-intel 2.99.917, GCC 5.3.0, and Mesa 11.0.
The "end of 2016" release used was Clear Linux 12140, which was the latest build this week as of testing time. Clear Linux 12140 has the Linux 4.8 kernel, Xfce 4.12, X.Org Server 1.19.0, xf86-video-modesetting 1.19, GCC 6.2 and LLVM Clang 3.9, and Mesa 13.1-dev. Clear Linux continues to use the EXT4 file-system by default. All year Clear Linux has also been using the ACPI CPUFreq driver with performance governor rather than the Intel P-State CPU scaling driver.
These benchmarks were done out-of-the-box and serve as nice complementary benchmarks to the daily Clear Linux benchmarking done at LinuxBenchmarking.com. All of these Clear Linux benchmarks were done in a fully-automated and reproducible manner using the open-source Phoronix Test Suite benchmarking software. All tests were done from the same Intel Core i7 4790K Haswell system with 16GB of RAM, OCZ TRION 100 SSD, and the integrated HD Graphics 4600.