As we have outlined before and shared benchmarks of in the past, the Intel graphics driver stack has been going through some significant changes. The Intel graphics driver now has a proper memory manager in the form of the Graphics Execution Manager, there is upstream kernel mode-setting support, and a new 3D component is coming soon in the form of Gallium3D. With all of this invasive work going on, regressions are currently prevalent from stability problems to graphical corruption to slower 2D performance. While these are problems users will face with the new distribution updates in H1'09, some have been trying out different driver configurations in order to circumvent the situation. Canonical, for example, had been toying with the idea of enabling greedy migration heuristics by default.
While the Catalyst driver for Windows was released a number of days ago, the Catalyst Linux driver was missing. It has, however, been released today. AMD's Linux engineers ended up delaying the Catalyst 9.3 release so they could spend additional time tuning this driver, since it will be the last release that supports the R300 through R500 series as the support is being dropped. The significant feature that was pushed back into the Catalyst 9.3 Linux driver is improved Composite support.
Ubuntu 9.04 will be released towards the end of next month and it is picking up the Linux 2.6.28 kernel, GNOME 2.26, and other improvements like install-time support for the EXT4 file-system and some subtle improvements. When it comes to the X.Org side it is shipping with X Server 1.6 and the stabilized version of Mesa 7.3. Specifically in regards to the ATI Linux graphics, it will be shipping with an updated xf86-video-ati driver by default and Catalyst 9.4 will be an option for the user. With Ubuntu 9.04 Alpha 6 having been released last week, we have run a few benchmarks comparing the open-source ATI performance in Ubuntu 8.10 and Ubuntu 9.04 Alpha 6.
In this edition of the Nouveau Companion, covered is the status of this open-source NVIDIA display driver and what went on at FOSDEM with the Nouveau project status and combining LLVM with Gallium3D. Recently the Nouveau developers have been successful in using EXA acceleration on newer GeForce 9 graphics cards, backlight controls working on more NVIDIA graphics cards, and a port of the Nouveau driver to FreeBSD. Work on kernel mode-setting and proper kernel memory management is also underway.
This afternoon AMD has released the Catalyst 9.3 driver for Windows along with ADL, or the AMD Display Library. The AMD Display Library is a cross-platform library that provides a single SDK to access graphics hardware information. In the past AMD has provided a few SDKs for obtaining this information on Windows, but this is the first time we are seeing such support on Linux.
This year NVIDIA has been following the "release early, release often" mantra with it seeming like two weeks can't even go by without seeing a new Linux driver -- whether it's a beta driver, an official driver update, or one of their legacy drivers picking up a few fixes (at times they have even released four drivers at once). On the opposite spectrum, AMD continues with monthly Catalyst driver updates on both Linux and windows. Rather than a continual stream of new public driver releases, AMD maintains a private beta program for their Catalyst Linux driver. This private program is made up of AMD developers, hardware vendors, users of different Linux distributions, other Linux vendors, and end-users. Phoronix has been apart of this program for years, but those testing this driver are under a strict Non-Disclosure Agreement with AMD regarding pre-releases of their Linux software. Today, however, AMD has decided to declassify some information pertaining to its Linux Graphics Driver Beta Program.
Yesterday we broke the news that AMD will stop supporting the R300-500 GPUs in the Catalyst driver. There have been well over one hundred posts in the Phoronix Forums from ATI customers upset with this decision, but fortunately, there is first-rate open-source support available. AMD continues to release documentation and code while the X.Org development community has been hard at work on the xf86-video-ati and xf86-video-radeonhd drivers along with Mesa and Gallium3D components. The main problem though is the open-source stack -- at this time -- providing poor gaming performance, but power management can also be a problem. In yesterday's article we provided some R500 comparative 2D and OpenGL benchmarks, but in this article are some power management results comparing the Catalyst 9.2 driver to the xf86-video-ati driver.
Beginning next month with the Catalyst 9.4 release, support for the R300/400/500 generations of graphics processors will be dropped from AMD's mainline ATI driver. In a move they hope will allow them to focus their efforts on newer and upcoming graphics processors, the mainline Catalyst driver on both Linux and Windows will stop supporting cards older than the Radeon HD 2000 series. Linux customers affected will be encouraged to use their open-source driver stack (xf86-video-ati or xf86-video-radeonhd and Mesa) or stay with the Catalyst 9.3 driver.
For months we have seen S3 Graphics advertise a magical Linux driver in their press releases that promised to offer OpenGL 3.0 support and advanced video functionality. They had reported to us the driver would be released in December, but that deadline had passed and they continued to announce Linux support when launching the Chrome 540 GTX, but still there was nothing. However, S3 Graphics has now actually delivered such a driver! They have delivered a Chrome 500 series Linux driver that not only provides OpenGL 3.0 support but also H.264, VC-1, and MPEG-2 hardware decoding on the GPU. While it may appear to be good, this driver is still far from perfect.
During the X.Org meetings at FOSDEM, Stephane Marchesin had discussed what he and other open-source developers are doing by using a code compiler (LLVM) and interweaving it with the Gallium3D driver architecture. By strapping the Low-Level Virtual Machine to Gallium3D, developers are hoping they can use the power of this relatively new compiler infrastructure to provide advanced GPU shader optimizations. This is not exactly an easy task, but it is believed it can be accomplished with beneficial results and they are making progress.
At FOSDEM 2009 in Keith Packard's talk on the rebuilt Linux desktop, he shared the progress made in composited 3D, monitor auto-plugging, 2D/3D/media shared objects, kernel mode-setting, and kernel-based 2D drawing. Allowing these problems to be addressed was the Graphics Execution Manager for kernel memory management. The Graphics Execution Manager was used instead of TTM (which we talked about several times before at Phoron
The first X.Org talk at FOSDEM 2009 was on version 1.3 of the Resize and Rotate extension. Matthias Hopf talked about RandR 1.3 and then Keith Packard demonstrated the transformations and panning operations using this soon-to-be-released version of RandR. Among the features for RandR 1.3 are querying state without output probing, multi-monitor panning, display transformations (translation, scaling, rotation, projection), and support for standard outputs.
Just over a month ago we shared that patches had emerged to support Intel's VA-API in MPlayer and FFmpeg. VA-API supports popular video formats such as MPEG-4 and VC-1 and is able to accelerate IDCT, Motion Compensation, LVC, bit-stream processing, and other functions, but this video API has not picked up much speed yet. The only display driver to have implemented support for VA-API in the hardware is Intel's closed-source driver (the one that's a bloody mess) for the Poulsbo chipset, which is found in a few select netbooks/nettops. However, it is now possible to use Intel's VA-API with NVIDIA hardware (the GeForce 8 series and later) and soon will be possible to use this video API on ATI/AMD hardware too.
AMD has just released its first official Catalyst driver update for the new year. AMD had delivered several key improvements to their proprietary Linux driver stack last year as we shared in our AMD Linux 2008 Year in Review, but what's there to get excited about in Catalyst 9.1? Well, first and foremost there is improved Composite support during video playback, Hybrid CrossFire support, and a number of fixes. Oh, and there's also OpenGL 3.0 support!
The NVIDIA 180.22 Linux driver was released less than three weeks ago, but today NVIDIA has released a new 180.xx display driver update. In addition, NVIDIA has updated all three of their legacy display drivers.
A month ago we compared Intel's graphics performance between Ubuntu 8.10 and the latest Ubuntu 9.04 daily snapshot at the time. With those tests we found Intel's performance had degraded significantly. However, with many new graphics packages having been released since then, we have carried out some additional tests this morning to look at where the Intel Linux graphics performance stands today.
Earlier this week we delivered results from a comparison between the Catalyst and X.Org Radeon drivers looking at the R500 2D performance. With a lot of interest having been generated from that, we have now carried out the same set of tests again but this time using an ATI Radeon HD 4850 (RV770) graphics card and the experimental EXA support.
Four months after Mesa 7.2 was released, Mesa 7.3 has now officially surfaced. Mesa 7.3 has been in testing since earlier this month with it having gone through three release candidates. The new features found in this latest version of the standard Open-Source OpenGL stack is proper support for GLSL 1.20 and the Intel DRI driver now supports the Graphics Execution Manager and Direct Rendering Infrastructure 2.
The 42nd edition of the Nouveau Companion is now available to provide an update on the status of this community project to provide an open-source 2D/3D driver for all of NVIDIA's graphics hardware. Covered in this developer update is the status of the Nouveau driver on newer NVIDIA hardware, work underway on NV20 Gallium3D code, the LLVM back-end for Gallium3D progressing, the work that's left on kernel mode-setting support, and the GEM / TTM memory management work. The lack of a stabilized memory manager for the Nouveau kernel mode-setting driver is what's postponing a stable 2D driver release.
One of the common complaints about the ATI Catalyst Linux driver is slow 2D performance, but is this really the case? Does AMD's binary-only Linux driver have 2D performance issues that could actually make it run slower than the open-source driver developed by the X.Org community through specifications released by AMD? In this article we have run a total of 28 benchmarks looking squarely at the 2D performance between the Catalyst (fglrx) driver and the xf86-video-ati (Radeon) drivers on Ubuntu Linux.
Just a little more than a week after AMD openly released R600/700 GPU code to begin development of an open-source 3D driver for their ATI Radeon HD 2000/3000/4000 hardware, a disassembler and table dumper for their video BIOS abstraction layer has been released to developers. This tool called AtomDis was used early on in the development of the RadeonHD driver by Novell and is now being released under the GNU GPLv2 license to assist interested open-source developers or act as an instrument to those learning about graphics processor programming.
On Monday AMD released the open-source R600/700 3D code to begin fostering the development of an open-source 3D driver for their newer ATI hardware while the related programming documentation still on the way. This code that's finally out in the public domain brings basic EXA acceleration and X-Video support, but on the 3D side there isn't any usable OpenGL support. It is expected that there will be a modest level of open-source 3D support for the ATI R600 and R700 series in the first half of 2008 for end-users, but for now there is just the DRM code and an r600_demo program. In this article we are taking a brief look at this r600_demo debugging utility on the RV770 hardware.
Since earlier this year we have been waiting for AMD to release documentation and/or code on the ATI R600 series concerning 3D acceleration so that the open-source Linux drivers can begin to support the newer ATI graphics processors. It has taken longer than expected for AMD to complete and release this information, but it's now available. AMD has released the fundamental Linux code needed to begin fostering the development of an open-source R600 3D driver. Furthermore, this code also concerns the latest R700 series of graphics processors! The microcode for the newest GPUs has also been released.
Subsequent to the introduction of the Graphics Execution Manager earlier this year, Intel had introduced a new acceleration architecture. UXA, or the UMA Acceleration Architecture, was developed as a temporary solution based upon the EXA architecture but with support for the kernel-driven GEM memory management. How though does the UXA performance compare to that of EXA? In this article we have ran some benchmarking looking at the Intel graphics performance.
The past year has brought several invasive changes to the Intel Linux graphics stack with the introduction of the Graphics Execution Manager for GPU memory management within the kernel, support for the Direct Rendering Infrastructure 2, and kernel mode-setting finally getting ready to enter the limelight. How though has the work this year affected the overall performance of Intel integrated graphics on Linux? In this article we have run a few benchmarks that show where the driver was at a few months ago and where it is today.
Last week our annual Linux Graphics Survey ended. There were over 14,000 submissions this year to the eleven questions we asked pertaining to X.Org, Linux desktop usage, and graphics hardware. In this article are all of the results from this year's survey.
Yesterday we had published our AMD Linux 2008 Year in Review where we had provided a recap of all major features introduced in their Linux driver over the past year as well as taking the time to re-benchmark every Catalyst driver released this year. We have been doing this process annually going back to 2005, and now it's time to look at the NVIDIA Linux driver releases from this year.
Last year when publishing our AMD Year in Review article there were numerous new features to account for, including but not limited to the new OpenGL driver, support for Compiz, and the AMD Catalyst Control Center Linux Edition. This year has been another interesting year for AMD's Linux efforts on both the open and closed fronts. We are focusing on their Catalyst driver efforts in this article, which has picked up support for CrossFire, is now capable of being overclocked with OverDrive, and AMD is now delivering same-day Linux product support. In this article we will recap some of the highlights from the Catalyst driver releases this year as well as set out on a benchmarking extravaganza.
It was just eleven days ago that NVIDIA had released the 180.11 Beta Linux Driver, but in the wee hours of Saturday morning NVIDIA has pushed out a new beta driver. This driver contains a few fixes, support for new GPUs, and an updated implementation of the Video Decode and Presentation API for Unix.
Just in time for the holidays is a new Nouveau Companion newsletter to update the community on the status of this open-source 2D/3D NVIDIA driver that is written by clean room reverse-engineering of NVIDIA's binary driver. It has been a while since Nouveau Companion 40, but there is still active work going into this X.Org driver. Among the topics covered in the 41st edition of the Nouveau Companion is kernel mode-setting, Gallium3D, layering GEM on top of TTM (similar to the GEM-ified TTM Radeon driver), and thermal monitoring code for the Nouveau driver.
764 display drivers articles published on Phoronix.