With the imminent release of Mesa 9.2, out this morning are Radeon "R600" Gallium3D driver benchmarks comparing Mesa Git master (9.3-devel) to Mesa 9.2 Git, Mesa 9.1.6, Mesa 9.0.3, Mesa 8.0.5, and Mesa 7.11.2. These are the past two years worth of Mesa releases and testing occurred on an ATI Radeon HD 4890 (RV790XT) graphics card.
With it looking like the R600 SB shader optimization back-end might be enabled for AMD's popular Radeon Gallium3D graphics driver, here are fresh benchmarks looking at the performance impact of enabling this shader optimization code-path that has the ability to dramatically increase the performance out of GLSL-using OpenGL games.
Earlier this week I delivered results showing the AMD Radeon HD 6000 open-source driver becoming more competitive against the proprietary AMD Catalyst driver. The Gallium3D driver is still far from reigning supreme in most aspects that concern desktop Linux users, but much progress has been made in recent months. For those HD 5000 series graphics card owners, here are similar open-source driver vs. AMD Catalyst OpenGL Linux performance tests.
The "R600" Gallium3D driver that provides open-source 3D/OpenGL Linux graphics support for AMD GPUs up through the Radeon HD 6000 graphics cards is becoming increasingly competitive. The open-source AMD stack isn't yet ready to overtake the proprietary AMD Catalyst driver in terms of raw performance or OpenGL compliance, but a lot of ground has been made up in recent months.
Now that Mir is living in the Ubuntu 13.10 archive, new Phoronix benchmarks have been conducted to look at the current performance impact of routing the graphics through XMir rather than running an X.Org Server directly on Ubuntu Linux. For this latest XMir testing, the System76 Gazelle Professional laptop with an Intel Core i7 "Haswell" CPU sporting Intel HD Graphics was benchmarked for 2D and 3D environments.
While the Linux 3.11 kernel hasn't even been officially released yet, on Phoronix we have already published a number of Radeon DPM benchmarks, the new dynamic power management code coming to the open-source driver. Early Phoronix tests of Radeon DPM have yielded performance improvements and great improvements for power/thermal use. In this article are new Linux 3.11 + Mesa Git benchmarks from a variety of AMD/ATI Radeon graphics cards.
Phoronix benchmarks have already shown that Mesa 9.2 dramatically improves the Intel Haswell Linux experience and that there's even some performance gains for other intel GPUs. On the AMD Radeon side, Mesa 9.2 also improves the performance for AMD hardware. How does Mesa 9.2 change the game for the Nouveau driver with NVIDIA graphics hardware? Here's some new results looking at the Mesa 9.1 vs. Mesa 9.2 performance for Nouveau, the reverse-engineered open-source NVIDIA graphics driver.
The performance of the open-source AMD Radeon Linux graphics driver for AMD Fusion APUs has improved a lot, but the Gallium3D driver performance still isn't yet on par with the AMD Catalyst binary driver. In this article are a variety of tests from an AMD APU including with the Linux 3.11 dynamic power management support, Mesa Git, and when using the R600 SB shader optimization back-end.
While this week we published benchmarks that showed how NVIDIA's Linux driver can compete with Windows 8 -- when using the closed-source drivers and not the open-source Nouveau solution -- and that even the FreeBSD NVIDIA performance is competitive, this isn't the case for AMD's drivers. From the same Core i7 Haswell system as used for the NVIDIA testing, AMD Radeon graphics cards were tested on Windows 8 and Linux. It wasn't a surprise that the open-source Radeon Gallium3D was much slower than Catalyst, but took us off guard a bit was that the Linux Catalyst driver does take some noticeable performance hits over the Microsoft Windows driver in some OpenGL workloads.
One of the most exciting features of the upcoming Linux 3.11 kernel is the open-source Radeon driver's support for dynamic power management (DPM). We have already done preliminary benchmarks and found that Radeon DPM can boost the GPU's performance in cases where the boot clock speeds are slower than their rated frequencies (as in the case of AMD APUs and modern high-end GPUs). For other GPUs, Radeon DPM can lead to lower power consumption and better operating temperatures. Here's looking at the Linux Radeon DPM performance with the Linux 3.11 Git kernel.
For those ATI/AMD customers with graphics cards of the Radeon HD 2000/3000/4000 generations, they are supported by the "Catalyst Legacy" driver but this older proprietary driver branch is seldom updated for new Linux kernel and X.Org Server releases. Thus, the only real option for those with these older Radeon GPUs is to use the open-source Radeon Gallium3D graphics driver. But how does this driver compare to the still-maintained Catalyst Legacy driver for Windows 8? Here are some benchmarks.
Yesterday I shared open-source Linux graphics benchmarks showing the Intel Ivy Bridge performance improving on Mesa 9.2 over the earlier releases of this important open-source Linux graphics driver component. However, for the latest-generation Intel "Haswell" graphics, Mesa 9.2 is an even more important upgrade. Here's a look at the performance benefits in moving from Mesa 9.1 to the soon-to-be-released Mesa 9.2.
With Mesa 9.2 due to be released next month, here's the very latest Git benchmarks of Mesa 9.2-devel on an Intel Core i5 Ultrabook with HD 4000 "Ivy Bridge" graphics compared to the stable Mesa release versions going back to Mesa 8.0.
As promised, now that Linux 3.11-rc1 has been released, it's time for the new dynamic power management support of the Linux 3.11 kernel for AMD Radeon graphics. This first article previews the possible OpenGL performance gains for an AMD APU when enabling "DPM" for allowing the graphics core to properly re-clock based upon its workload.
For those with older generations of AMD/ATI Radeon graphics processors that may not be running the very latest Mesa Gallium3D driver release, here are benchmarks comparing every major Mesa release between Mesa 7.11 and Mesa 9.2.
From the AMD A10-6800K "Richland" APU I've delivered OpenGL Linux benchmarks of the Radeon HD 8670D graphics and also compared the open-source Gallium3D performance to that of Catalyst. Catalyst still reigns supreme, but in this article are some benchmarks showing the performance between Mesa 9.1 and 9.2 Git and also when deploying the experimental R600 SB shader optimization back-end.
After recently delivering a 15-way open-source Intel/AMD/NVIDIA GPU comparison, here are the benchmarks when tossing in the proprietary AMD Catalyst and NVIDIA graphics drivers too. Besides comparing a diverse selection of graphics processors from the three main desktop GPU vendors, this comparison also shows how the current open-source Linux graphics drivers compare to the official proprietary drivers.
With the Linux 3.10 kernel having been pulled recently into the Ubuntu 13.10 archive, new benchmarks have been conducted comparing the open-source Nouveau driver against the binary NVIDIA 319.32 Linux graphics driver on a NVIDIA-powered laptop.
This morning there were the RadeonSI Gallium3D vs. AMD Catalyst Linux benchmarks for the high-end Radeon HD 7850/7950 "Southern Islands" graphics cards. While the new Southern Islands GPUs understandingly have a long way to catch up on their new open-source Linux Gallium3D driver compared to Catalyst, how is the AMD Radeon HD 8670D "Richland" APU performance between the open and closed-source drivers? Here are some benchmarks.
Towards the end of June I published AMD RadeonSI Gallium3D benchmarks, the open-source Linux graphics driver supporting the Radeon HD 7000/8000 series hardware on Linux. While the alternative to the Catalyst driver can accelerate OpenGL, it's very slow. Open-source driver benchmarks were shown in that article compared to older generations of AMD Radeon hardware backed by the mature R600 Gallium3D driver. In this article are benchmarks comparing the open-source "RadeonSI" driver to the proprietary AMD Catalyst GPU driver on the Radeon HD 7850/7950 graphics cards. As an additional driver reference point were also Radeon HD 7950 Cayman results; all testing happened from Fedora 19 Linux.
With Fedora 19 presenting a nice "out of the box" experience for AMD Radeon HD 7000 series graphics using the open-source RadeonSI Gallium3D driver, benchmarks of the open-source driver were done and compared to previous generations of AMD hardware. Sadly, there's still much work ahead for the Radeon HD 7000 series driver in being able to catch up with the hardware supported under the mature R600 Gallium3D driver.
With Thursday's announcement that Mir will ship by default in Ubuntu 13.10 on the desktop, many Ubuntu users were caught by surprise that this experimental display server will be ready by October. Up to now, Ubuntu 13.10 was expected to continue using an X.Org Server by default on the desktop (with only an experimental option for Mir) while the new Ubuntu Touch project would be using Mir on mobile devices, until next year. With the pressed timeline for the migration to Mir, at Phoronix we have already carried out our first Mir benchmarks. In this article are the first benchmarks of Intel graphics when running on Ubuntu 13.10 with a native X.Org Server (as done now on current Ubuntu Linux releases) and then when deploying the same Unity desktop environment atop XMir with the Mir unity-system-compositor.
To complement the Intel Haswell Linux OpenGL benchmarks that we have been publishing on Phoronix for the past week, up today are some Intel Linux 2D performance benchmarks of Haswell with the Intel Core i7 4770K CPU. The 2D performance is comparing Intel's default UXA accelerated code-paths against the experimental SNA acceleration back-end.
With the continued speculation and FUD about the future of Wayland at a time when Canonical is investing heavily into their own Mir Display Server alternative, Eric Griffith with input from Daniel Stone have written an article for Phoronix where they lay out all the facts. The "Wayland Situation" is explained with first going over the failings of X, the fixings of Wayland, common misconceptions about X and Wayland, and then a few other advantages to Wayland. For anyone interested in X/Wayland or the Linux desktop at a technical level, it's an article certainly worth reading!
After yesterday's Intel Sandy Bridge and Ivy Bridge Linux graphics comparison using the very latest Intel Linux graphics driver, here are new benchmarks using the latest Windows and Linux Intel OpenGL graphics driver. Facing competition this morning is Microsoft Windows 7 Pro x64 and Ubuntu 13.04 with its updated open-source stack.
In revisiting the OpenGL graphics and gaming performance for an older Intel Core i5 "Sandy Bridge" Apple system, the Ubuntu 13.04 performance with Intel's open-source graphics driver is now easily surpassing Apple's OpenGL driver found in OS X 10.8.3.
Curious to see how the performance of the open-source ATI/AMD Linux graphics driver is evolving for aging hardware, a new round of OpenGL benchmarks were carried out on the once-popular ATI Radeon HD 4870 "RV770" graphics card. The performance was compared between the Mesa 7.11, 8.0, 9.0, 9.1, and 9.2-devel Git releases from an Ubuntu Linux system to see how the performance has changed for this driver in the past two years.
One of the exciting features of LLVM 3.3 that is due out next month is the final integration of the AMD R600 GPU LLVM back-end. This LLVM back-end is needed for supporting Gallium3D OpenCL on AMD Radeon graphics hardware, "RadeonSI" HD 7000/8000 series support, and can optionally be used as the Radeon Gallium3D driver's shader compiler. In this article are some benchmarks of the AMD R600 GPU LLVM back-end from LLVM 3.3-rc1 when using several different AMD Radeon HD graphics cards and seeing how the LLVM compiler back-end affects the OpenGL graphics performance.
With the AMD R600 Gallium3D shader optimizing back-end having been merged last week, new benchmarks were carried out at Phoronix to see the impact of the experimental shader optimizations on multiple AMD Radeon HD graphics cards.
Yesterday after publishing the 15-way open-source vs. closed-source NVIDIA/AMD Linux graphics comparison there were some requests by Phoronix readers to also show how the LLVMpipe software rasterizer performance is in reference. For this article to end out the month are the OpenGL performance results from nine lower-end AMD Radeon and NVIDIA GeForce graphics cards running with their respective Mesa/Gallium3D drivers compared to the LLVMpipe software driver in two configurations.
814 display drivers articles published on Phoronix.