Show Your Support: Did you know that you can get Phoronix Premium for under $4 per month? Try it today to view our site ad-free, multi-page articles on a single page, and more while the proceeds allow us to write more Linux hardware reviews. At the very least, please disable your ad-blocker.
macOS 10.12 Sierra vs. Ubuntu 16.04 Linux Benchmarks
Apple released macOS 10.12 "Sierra" last week as the successor to OS X El Capitan. Given this annual update to macOS / OS X, here are benchmarks of macOS Sierra compared to Ubuntu 16.04 LTS on a MacBook Air and Mac Mini computers.
For those not regularly tracking Apple news, macOS 10.12 integrates Siri, better iCloud Drive integration, optimized storage support, experimental support for the new Apple File System (APFS), cross-device copy/paste, Apple Pay integration in Safari, and various changes to the many programs shipped by default in macOS / OS X.
Curious about performance improvements for macOS Sierra and how Apple's operating system is comparing to Linux distributions, I benchmarked macOS 10.12 and Ubuntu 16.04.1 LTS on my two newest Apple systems available. They are a bit dated but unfortunately they are the only ones I have available for testing: a Haswell-based MacBook Air and a Haswell era Mac Mini.
The MacBook Air is equipped with a Core i5 4250U CPU with HD Graphics 5000, 4GB of DDR3 memory, and a 120GB Apple SSD.
The Mac Mini is equipped with a Core i5 4278U CPU Iris Graphics 5100, 8GB of DDR3 system memory, and a 1000GB HDD.
MacOS Sierra was tested with a clean install of the operating system and its out-of-the-box performance benchmarked. Xcode 8.0 from the App Store was installed as Apple's preferred compiler. Ubuntu 16.04.1 LTS was then installed cleanly on the same systems. In addition to testing the out-of-the-box performance of Ubuntu 16.04 LTS with its GCC 5.4 compiler, a second Ubuntu 16.04.1 LTS run was also done when using LLVM Clang 3.8. This second run was done since Xcode uses LLVM/Clang and thus an Ubuntu LLVM/Clang run rules out some of the performance differences attributed to the compiler, albeit the compiler choice is an important part of the default OS selection made by the software vendor.
With the Haswell Mac Mini, in addition to testing macOS Sierra I had went ahead and also re-tested OS X 10.10.5 and OS X 10.11.6 on the same hardware for additional reference points.
All of the OS X / macOS and Ubuntu Linux benchmarking was carried out in a fully-automated and streamlined manner using the open-source cross-platform Phoronix Test Suite software with open-source test profiles supported both under Mac and Linux.
First up are the Mac Book Air performance results followed by the Mac Mini numbers that also include the OS X 10.10/10.11 benchmarks.