The release of LLVM 3.4 is imminent and with the major compiler infrastructure upgrade comes update to the Clang C/C++ compiler front-end, LLDB debugger, and other LLVM sub-projects. LLVM 3.4 is a very righteous release and in celebration of its forthcoming release, it's back into compiler benchmarking season at Phoronix.
Our initial file-system testing of EXT4, XFS, Btrfs, and F2FS from the Linux 3.13 kernel appear to reveal that the performance overall is slower than when using the Linux 3.12 kernel on the same software/hardware configuration.
While I'm waiting for development activity on the Linux 3.13 kernel to settle down a bit more before delivering comprehensive benchmarks looking at the Linux 3.13 kernel performance changes across the various covered subsystems, up this morning are some early benchmarks of the Linux 3.13 Git kernel and benchmarking every major release going back to Linux 3.9.
For those that may have some time this holiday weekend and are looking to better enhance the performance of Ubuntu's open-source graphics drivers, one of the easiest ways to do so is by enabling the Oibaf repository for easily downloading and installing newer versions of the Mesa/Gallium3D drivers and other X.Org related components. Here are some more details and current benchmarks of enabling the Oibaf PPA over Ubuntu 13.10.
It's been a while since last putting out any hardware-accelerated video decode benchmarks of NVIDIA's Video Decode and Presentation API for Unix (VDPAU). However, after updating qVDPAUtest to support building on modern platforms, here's a round of thirteen NVIDIA GeForce graphics cards being benchmarked under VDPAU.
How does the Linux kernel performance compare if simply bouncing between some of the recent long-term kernel releases? Well, to try to answer that question on Phoronix today we have benchmarks of the Linux 3.0.101, 3.4.68, 3.10.18, and 3.12.0 kernel releases tested from an AMD Opteron system with Radeon graphics.
With the Fedora 20 beta coming up I decided to see where the latest Fedora 20 packages are now at for their support of Wayland and the GNOME Shell Wayland session. In particular, looking at whether the session is still buggy and how the XWayland performance is for Linux gaming.
While the Ubuntu 13.10 desktop isn't using Mir/XMir by default, the packages are available within the archive for those wanting to test out the next-generation display server for Ubuntu. To see how the 2D/3D performance is when running under XMir with the Unity System Compositor, I ran some new benchmarks using this week's Ubuntu 13.10 release.
It's been several kernel releases since last benchmarking the Liquorix kernel, an optimized version of the Linux kernel that's advertised as "built using the best configuration and kernel sources for desktop, multimedia, and gaming workloads." In Liquorix having out their version of the Linux 3.11 kernel since late September, here are some benchmarks comparing Liquorix to recent mainline versions of the vanilla Linux kernel.
In following the AMD Radeon performance is incredible on Linux 3.12 article that benchmarked ten different AMD graphics cards on the Linux kernel, followed by the reason why AMD Radeon graphics are faster on Linux 3.12, here's now some benchmarks of the open-source NVIDIA driver with GeForce graphics cards. The testing in this article is a few NVIDIA GeForce graphics cards with the Nouveau driver when comparing the Linux 3.11 and 3.12 kernels in a similar fashion to the AMD Linux OpenGL performance testing. Like the AMD results, there are some notable gains to find with the yet-to-be-released 3.12 kernel.
Yesterday I published benchmarks showing the AMD Radeon graphics being much faster on Linux 3.12. Ten graphics cards were benchmarked and many of them were showing rather remarkable OpenGL frame-rate performance improvements when moving from the Linux 3.11 to Linux 3.12 Git kernel. This large comparison came after benchmarks I did this weekend on a single Radeon HD graphics card showed the Linux 3.12 kernel delivering the best performance of any recent kernel release. The only thing was, this AMD Radeon performance improvement baffled the upstream developers. The AMD developers were taken off-guard and didn't have an explanation why the Linux 3.12 kernel performance is faster... Now thanks to automated testing and bisecting by the Phoronix Test Suite, I have an answer.
So far in our testing of the Linux 3.12 kernel we have found that there are some file-system performance improvements and most noticeable is AMD Radeon performance improvements for the open-source driver. We have also found the AMD APU performance hasn't changed much and Ivy Bridge graphics are rather unchanged among other mute workloads, but is there any other worthwhile performance improvements to be discovered? Our latest Linux 3.12 Git tests are from the System76 Galago UltraPro with Core i7 4750HQ "Haswell" processor as we benchmark every major kernel release going back to Linux 3.8.
Our latest Linux benchmarks from the Intel Core i7 4960X Ivy Bridge Extreme Edition processor are compiler tests on this $1000 USD processor. The last two stable releases of GCC and LLVM's Clang C/C++ compilers were compared: GCC 4.7.2, GCC 4.8.1, LLVM Clang 3.2, and LLVM Clang 3.3.
With the Linux 3.12 kernel due for release in several weeks time but all major changes behind us now, here are some file-system tests from this forthcoming kernel update. Tested Linux file-systems for this Phoronix article include EXT4, Btrfs, XFS, and F2FS. From these results, there are multiple instances of these file-systems running measurably faster than Linux 3.11.
After earlier this month delivering new Amazon EC2 cloud benchmarks, several Phoronix readers had requested some reference benchmark results against some "bare metal" hardware systems. For those not running their own performance comparisons against Amazon's Elastic Compute Cloud, here's some more benchmark results showing different EC2 cloud instance types compared to an Intel Ivy Bridge and Haswell system.
Released by VMware earlier this month was VMware Fusion 6.0 and VMware Workstation 10. If you're running a new Haswell-based MacBook with VMware Fusion, you can expect some noticeable performance improvements by upgrading.
The latest interesting Linux test results to share this week for those not at Oktoberfest are 2D and 3D/OpenGL benchmark results when testing XMir and a pure X.Org Server configuration with the Xfce, Unity, and KDE desktops as will be found in next month's Ubuntu 13.10 release.
As it's been nearly one year since we last put out some reference benchmarks of Amazon's EC2 Cloud, or compared the different operating system's in Amazon's cloud, it's time to kick off a new round of cloud performance benchmarks. Coming out today are new benchmarks of Amazon's Elastic Compute Cloud when benchmarking various on-demand instance types.
To end off August we have benchmarks up of five popular desktop environments running on Ubuntu 13.10 as of Friday. With feature freeze passing, we now have a good look at the desktop competition for Ubuntu 13.10 and how each of the desktops perform.
Composition bypass support finally landed this morning into the mainline Mir code-base ahead of the Ubuntu 13.10 feature-freeze. With the feature being merged and packages already being pushed into the 13.10 archive, benchmarks at Phoronix have already been conducted. The benchmarks to share this afternoon are of the Mir/XMir packages from yesterday against the Mir packages today with composite bypass support. Lastly, there are benchmarks of a pure X.Org Server running on the same hardware to look at the performance impact and current (reduced) overhead of Mir.
With the recent release of ZFS On Linux 0.6.2 that provides an open-source native Linux kernel module implementation of the Sun/Oracle ZFS file-system, the performance is faster, there are greater Linux kernel compatibility, and other improvements. Here's a fresh round of ZFS Linux benchmarks against EXT4 and Btrfs.
Phoronix Media is pleased to announce the immediate availability of Phoronix Test Suite 4.8 (codenamed "Sokndal") as its latest offering to advance open-source benchmarking and performance testing on Linux operating systems and also BSD, Solaris, OS X, and Windows platforms scaling from embedded devices to servers and HPC solutions.
On the latest Linux 3.10 stable kernel we have taken ten common Linux file-systems and generated an interesting performance comparisons. The Linux file-systems being tested in this article include XFS, Btrfs, EXT2, EXT3, EXT4, ReiserFS, Reiser4, JFS, F2FS, and ZFS.
With quite some time having passed since we last benchmarked the Reiser4 file-system, to end out July we have some fresh benchmarks of Reiser4 from the newly released patches for the Linux 3.10 kernel. There's fairly good performance out of the experimental file-system when compared to the original ReiserFS as well as EXT4, Btrfs, and XFS.
To complement the LLVM 3.4 SVN compiler benchmarks from yesterday that were looking at the impact of using the SLP Vectorizer that's soon to be enabled by default for some optimization levels, here are some more LLVM Clang compiler development benchmarks. This time around are fresh benchmarks of the open-source C/C++ compiler when trying out the different compiler optimization levels, including -O0, -O1, -O2, -Os, -O3, and -Ofast.
To complement the EXT4, XFS, Btrfs, and F2FS benchmark results that were published yesterday from the Linux 3.11 kernel and its predecessors, here are some Btrfs tuning benchmarks on the Linux 3.11 kernel with various performance-sensitive Btrfs mount options being tried.
Coming out today are our first Linux 3.11 kernel file-system benchmarks. Being benchmarked from a higher-end OCZ Vertex 3 SATA 3.0 SSD connected to an Intel Core i7 "Haswell" system are the EXT4, Btrfs, XFS, and F2FS file-systems.
Along with benchmarking the AMD A10-6800K "Richland" APU on Linux and its Radeon HD 8670D graphics, I provided some GCC compiler tuning benchmarks for this AMD APU with Piledriver cores. The latest Linux testing from the A10-6800K is a comparison of GCC 4.8.1 to LLVM/Clang 3.3 on this latest-generation AMD low-power system.
On Friday I delivered the first benchmarks of Ubuntu's Unity desktop running on XMir -- the X.Org Server compatibility layer for talking to the Mir Display Server. Those benchmarks showered there was noticeable performance overhead to running XMir with Intel's graphics driver. Later benchmarks showed XMir 2D performance was also negatively affected. In this article are benchmarks looking at the XMir performance with the Nouveau driver.
Earlier today I delivered the first benchmarks of Ubuntu's Unity 7 running over XMir to run the current X11 desktop atop the Mir Display Server via this compatibility layer. These benchmarks documented the performance impact of running OpenGL games when having to deal with XMir rather than just a clean X.Org Server running on the hardware. The extra step in the rendering process did result in a measurable performance impact, especially when the performance of the open-source Linux graphics drivers is already lower than their proprietary brethren. The benchmarks to now show illustrate that the 2D rendering performance also takes a hit when running Unity on XMir.
492 software articles published on Phoronix.