Yesterday I posted some performance results of a Radeon R9 290 tested on Ubuntu 15.04 and Ubuntu 15.10 out-of-the-box. In this article are some numbers when upgrading the Ubuntu 15.10 installation to use the non-standard Linux 4.3 Git kernel as well as Mesa 11.1-devel Git that's built against LLVM 3.8 SVN for the newest open-source AMD Linux experience.
The overall system-level processor utilization between AIX and Linux on Power for identical workload and Power hardware configurations in multicore SMT systems can't be compared because the calculations are completely different. The overall system-level processor utilization reported in Linux on Power is derived from /proc/stat, which is purely time based. Whereas, AIX is based on PURR and SPURR, which is more towards CAPEX planning and also projects more realistic and accurate processor utilization for the latest evolution of processors which has SMP and SMT environment. Actual performance difference between single threaded and SMT8 on POWER8 is 2.2 times. In time-based calculations, processor utilization report for a single thread projects as if each SMT thread and execution unit is independent of the other. This gives a notion that users can achieve eight times better performance in the SMT8 mode, which is not true in real world. The realistic 2.2 times processor utilization factor that is not accounted in the calculation is one of the reasons for the low processor utilization reported in Linux on Power system for certain workloads that do not utilize 100% core, when compared to the AIX on Power platform.
Recently there were a number of requests about testing the latest state of Liquorix, the self-prcolaimed "better distro kernel" that is an optimized version of the Linux kernel with extra patches that makes it optimal for desktop, multimedia, and gaming workloads. Here's some fresh Liquorix vs. mainline Linux kernel performance benchmarks.
Wayland has been ported to DragonFlyBSD along with its Weston compositor!
In the past we've seen some minor experiments by BSD developers with Wayland/Weston, but for the most part all of the BSDs are still focused on X.Org Server support -- need I remind Phoronix readers that DRM/KMS support is in varying stages across the BSD distributions too as one of the support stepping stones. Just a few days ago I ran into the DragonFly Radeon kernel module failing to properly mode-set with a several year old (pre-GCN) graphics card while meanwhile FreeBSD's Radeon KMS port worked. It's still rather a mine field when it comes to open-source graphics acceleration and support on the BSDs while slowly but surely their catching up with the kernel code.
Alexandre Courbot, a developer at NVIDIA who has been working on the Tegra open-source graphics support a lot for Nouveau, presented last week at LinuxCon Europe 2015.
Thanks to the work by Courbot and others at NVIDIA, the Tegra K1 with its Kepler GPU has mainline Nouveau graphics support while the open-source graphics enablement for the Tegra X1 with Maxwell GPU continues to be upstreamed.
It's been a while since last running any BSD vs. Linux benchmarks, so I've started some fresh comparisons using the latest releases of various BSDs and Linux distributions. First up, as for what's completed so far, is using the FreeBSD-based PC-BSD 10.2 compared to Ubuntu 15.04 stable and the latest development release of Ubuntu 15.10.