It is time for another round of compiler benchmarks on AMD's latest FX-8150 Bulldozer processor. In this article is comparing the GCC 4.6.1, GCC 4.7 development, Open64 4.2.4, and AMD Open64 184.108.40.206 compilers in their stock configuration, when the binaries are built again but with the march/mtune flags set to "bdver1", and a third when being built with the "bdver1" architecture and tuning flags along with "-Ofast" for the highest-level of compiler optimizations.
At long last, it looks like there is an adequate solution to the Active State Power Management (ASPM) problem in the Linux kernel , a.k.a. the well-known and wide-spread power regression in the Linux 2.6.38 kernel, which has been causing many laptops to go through significantly more power than they should. This is not another workaround, but rather a behavioral change in the kernel to better decide when the PCI Express ASPM support should be toggled.
For those interested by last week's articles on the AMD Bulldozer benchmarks of the GCC, Open64, and LLVM/Clang compilers and the FX-8150 compiler tuning, but curious to know how the new LLVM/Clang 3.0 and other compilers perform on other processors, here's some new test results. These tests are looking at GCC 4.6, LLVM/Clang 3.0-RC1, and AMD Open64 compilers on Intel Sandy Bridge and AMD Shanghai hardware.
The "AMD F15h cache aliasing issue" fixes have landed, which address cache aliasing penalties for AMD Bulldozer (Family 15h) processors. This can lead to performance improvements for some workloads.
After recently comparing the AMD Bulldozer with the GCC, Open64, and LLVM/Clang compilers, in this article is a look at the performance of AMD's Open64 compiler when using their recommended compiler tuning options for Bulldozer when building software.
While last week I showed how Ubuntu's performance has evolved as a KVM guest from Ubuntu 8.04 through Ubuntu 11.10, in today's article is a Linux virtualization showdown between VirtualBox, Xen, and KVM while using Ubuntu 11.10 on the Linux 3.0 kernel.
A few days ago I shared the first one thousand comments about the GNOME desktop from the 2011 GNOME User Survey. Here's now the next set of one thousand comments concerning the state of GNOME in the eyes of end-users.
Last week the 2011 GNOME User Survey began, which is an independent survey that was devised by members of the GNOME community to collect feedback on their desktop platform. With the GNOME Foundation not interested in hosting the survey, these survey creators came to Phoronix to host the survey. Some of the initial GNOME comments were shared shortly after the survey went live. This survey will be running for one month, but there were already more than 8,000 submissions in the first few days. Here's the first 1,000 comments provided by participants of the GNOME survey.
In continuing from yesterday's AMD FX-4100 "Bulldozer" Linux benchmarks, here are more Ubuntu test results from this system comparing the stock GCC 4.5.2 and GCC 4.6.1 compilers for the new Bulldozer platform.
Last week I published benchmark results of using Intel AES-NI for Ubuntu home directory encryption, but the benefits of using this new x86 instruction set found on the latest Intel and AMD (as of today's Bulldozer launch) processors was minimal for this eCryptfs-based solution. Continuing in the AES-NI investigation under Linux, today are benchmark results when using AES-NI for full-disk encryption with dmcrypt.
While I was away for three weeks, there was an update on LP bug #760131, the infamous bug report on the power consumption being raised significantly higher in Ubuntu Natty. This bug report of high importance now indicates a fix being committed to Natty and a fix being released for Oneiric, but what has changed? Here is an update.
Supported by modern Intel processors is the AES instruction set, which is designed to improve the speed of encryption and decryption on the CPU for AES, the Advanced Encryption Standard. Under Ubuntu Linux, even for supported hardware, the Intel AES-NI capability is not taken advantage of when enabling its data encryption feature. The Intel AES-NI support can be easily enabled, but what is the impact on performance? Here are some benchmarks.
Recently I published benchmarks of Btrfs from a Serial ATA 3.0 SSD (the excellent OCZ Vertex 3 SSD) and those results were interesting, but most people aren't running 6Gb/s solid-state drives, so how does this next-generation file-system perform on the opposite end of the spectrum? In this article are EXT4 and Btrfs benchmarks from an old Core Duo notebook with a 5400RPM mobile hard drive.
On Tuesday at XDC2011 Chicago I hosted a question and answer panel about contributing to X.Org, Mesa, and the Linux kernel. Much of the information presented, however, is relevant to any open-source / free software project. The panel participants were largely graphics driver developers that started off contributing to open-source when at university and some of them have since moved on to working for major Linux companies, i.e. Intel and Red Hat. The talk was very interesting and Chicago computer science students were free to ask questions of them.
With more and more of one's personal and professional lives being on the computer, encrypting and properly securing those computers -- particularly mobile devices -- is incredibly important. Sadly, it's not often thought about until it's too late. It has become relatively easy to protect your personal data on Ubuntu Linux with home directory encryption support being just a checkbox-away within the installer or even full-disk LVM encryption when using Ubuntu's alternate installer. Previous tests of Ubuntu disk encryption performance have shown there is some penalty in disk-centric workloads, but the benefits are certainly worth it. In this article is a look at the Ubuntu home encryption performance under Ubuntu 11.10 with both old and new laptops.
Next Tuesday at XDC2011 Chicago I am hosting a Q&A panel about contributing to X.Org and open-source projects, where the panel participants are largely comprised of well known X.Org and Mesa developers that began contributing while at university. In hopes of sparking new contributors to these key open-source projects, computer science students from the major Chicago universities have been invited to attend this panel discussion and anyone else wishing to learn more about open-source development. In preparation for this panel, I have been collecting some new development statistics on Mesa and X.Org.
It's approaching the one-year anniversary of when Mark Shuttleworth announced Ubuntu is going to deploy Wayland with Unity, eventually. As those know that pay attention to the continual flow of information from Phoronix regarding the next-generation Wayland Display Server and Linux graphics drivers in general, it's being developed at a brisk pace and with several key open-source projects now betting big on its adoption, but how's it playing in the soon-to-be-released Ubuntu 11.10?
If you were hoping that the Linux 3.1 kernel would fix the big power regression problem that's caused by PCI Express Active State Power Management (ASPM) being disabled on more systems since the release of the Linux 2.6.38 kernel, you're not in luck. There has not been any active work in this area. Making things worse though for mobile Linux users interested in a long lasting battery is another new regression in the Linux 3.1 kernel. Affected systems can easily see a 30% increase in power consumption simply when comparing the Linux 3.0 kernel to the current code being assembled for Linux 3.1. For an Intel Sandy Bridge notebook, the power consumption is up by 76% just over the course of this year from Linux kernel regressions.
This month marks the two-year anniversary of the release of BFS, the Brain Fuck Scheduler, for the Linux kernel. While BFS has not been merged into the mainline Linux kernel, the scheduler is still actively maintained by Con Kolivas and patches are updated for new kernel releases. The BFS scheduler has also reached mild success and adoption over the past two years. In this article is a fresh look at the Brain Fuck Scheduler along with a fresh round of benchmarks from the Linux 3.0 kernel.
With my recent work in tracking down Linux power regressions and looking at other areas of Linux power consumption, there's been a number of emails sent in by Phoronix readers concerning the power consumption of web-browsers. In particular, some users seem to think that Google's Chrome/Chromium web-browser causes the system to go through noticeably more power than Mozilla Firefox and other web-browsers. But how much is this really the case? Here's some benchmarks.
In the middle of July, Adobe released the first Flash Player 11 beta, which had updated the Linux version too. The Flash Player 11 release notably incorporated native 64-bit support, once again, after the earlier "Square" 64-bit beta had lagged behind in terms of updates. Shortly following the Flash Player 11 Beta 1 release I had carried out some Linux benchmarks, but those results never seemed to make it out the door. Here are those results for anyone interested in seeing how the CPU usage and system power consumption differ between Flash 11 with and without VDPAU rendering and then against the open-source Gnash Flash Player.
This weekend at the Desktop Summit in Berlin, plans were presented by Martin Gräßlin, the maintainer of the KWin compositing window manager, for supporting the Wayland Display Server as an alternative to KDE being limited to X11. For early adopters and those using Plasma Active, KDE on Wayland should become a reality in the 2012 calendar year.
With Phoronix Test Suite 3.4-Lillesand and the new MATISK support, over one thousand revisions of the Mesa graphics library were benchmarked. Two small performance optimizations were also noted.
While S3 Texture Compression (S3TC) is widely used by many games and applications since its inclusion into OpenGL 1.3 and Microsoft DirectX 6.0, these lossy texture compression algorithms have not been implemented in the open-source Linux graphics drivers. This lack of open-source support is due to S3 Graphics holding the patent rights to this technology that they actively license to major hardware vendors. There long has been an external library that can be loaded and will work with most Mesa / Gallium3D drivers for advertising S3TC support, but it's not found by default and it's not included in leading Linux distributions due to these legal fears. There may now be a new solution for the S3TC Linux problem thanks to the advent of a new (and simpler) texture compression algorithm that can serve as a drop-in replacement.
Last month when publishing Fedora 15 vs. Ubuntu 11.04 benchmarks in some of the disk workloads the Fedora Linux release was behind that of Ubuntu Natty Narwhal. Some users speculated in our forums that SELinux was to blame, but later tests show SELinux does not cause a huge performance impact. With Security Enhanced Linux not to blame, some wondered if Fedora's use of LVM, the Logical Volume Manager, by default was the cause.
"Mobile users are urged to seriously consider these results, and possibly even avoid the Natty Narwhal...I hate to say it, especially in an Ubuntu review, but the mobile edge goes to Windows for now...There are also compelling reasons for folks to avoid [Ubuntu 11.04] at all costs. Linux gamers should see substantial improvements, while mobile users suffer a dramatic loss in battery life," were among the critical comments that Tom's Hardware had in their Ubuntu 11.04 review as they were referencing the power regressions I discovered nearly two months ago within the mainline Linux kernel. As I mentioned on Sunday, the Phoronix Test Suite stack and I have now nailed this major power regression in the Linux 2.6.38 kernel that is affecting a significant number of mobile Linux users. Here is what is happening and a way that you should be able to workaround the serious regression should it affect your computer system(s).
With the Linux 3.0 kernel carrying CleanCache support along with various improvements to the EXT4 and Btrfs file-system modules, it is time for another Phoronix file-system comparison. This time around the EXT4 vs. Btrfs performance is particularly important with Fedora 16 possibly switching to Btrfs by default. Due to this level of interest, for our Linux 3.0 kernel benchmarks of the EXT4 and Btrfs file-systems, an Intel SSD was tested as well as an old 5400RPM IDE notebook hard drive to represent two ends of the spectrum.
As mentioned last week, a plethora of Linux power tests are on the way now that we have found an AC power meter with USB interface that works under Linux and we've been able to integrate nicely into the Phoronix Test Suite and its sensor monitoring framework. In this article is one of the first tests that have been completed using this power-measuring device as we monitored the Linux kernel power consumption for an old Intel Pentium 4 and ATI Radeon 9200 system for the past several kernel releases. Even this very old desktop system looks to be affected by the kernel power problems.
Phoronix Media has announced the immediate release of Phoronix Test Suite 3.2 (codenamed "Grimstad") as the planned quarterly update to their open-source Phoronix Test Suite software. The Phoronix Test Suite provides a framework for conducting qualitative and quantitative tests in a manner that is reproducible, easy-to-use, and fully automated.
Within the free software world, GCC has long been the dominant compiler with it being backed by the Free Software Foundation, it being the most well developed free compiler suite, and is a feature rich offering that is put out under the GNU GPLv3. As of late, LLVM has also been hitting the nail on the head. The Low-Level Virtual Machine with its C/C++ Clang compiler front-end offers great performance, is successful in building code-bases like the Linux kernel, its modular design allows the compiler infrastructure to be used in areas like graphics drivers, is under a BSD-style license, and carries numerous other advantages. Other open-source compilers have advanced too, including the release of PCC 1.0. Now there is a new and extremely interesting option to shake the open-source compiler world: PathScale is freely releasing the source to the EKOPath 4 Compiler Suite. EKOPath 4 is a high-performance compiler that up until now has been proprietary and costs nearly $2000 USD per license, but now it's open-source and can sharply outperform GCC in many computationally-intense workloads.
477 software articles published on Phoronix.