Release 2.20.6 (2012-09-02) =========================== A serious bug that caused a crash on SandyBridge and IvyBridge when mixing CPU and GPU operations on the same buffer, and an annoyance from bad scheduling of windowed swapbuffer updates causing low framerates and jitter. Plus the usual smattering of assertion fixes and a long standing issue with incoherent page access to a streaming buffer. * Low frame rates in Blobby Valley when "fullscreen" https://bugs.freedesktop.org/show_bug.cgi?id=54274 * Incoherent concurrent access with the CPU and GPU https://bugs.freedesktop.org/show_bug.cgi?id=51422 https://bugs.freedesktop.org/show_bug.cgi?id=52299 * Add Option "Backlight" to override automatic selection of the backlight interface. * Avoid overwriting the composite operation info when testing if we can transfer the operation to the BLT. Release 2.20.5 (2012-08-26) =========================== Another silly bug found, another small bugfix release. The goal was for the driver to bind to all Intel devices supported by the kernel. Unfortunately we were too successful and started claiming Pouslbo, Medfield and Cedarview devices which are still encumbered by propietary IP and not supported by this driver. Bugs fixed since 2.20.4: * Only bind to Intel devices using the i915 kernel module * Regression in the bitmap-to-region code, e.g. icewm window buttons https://bugs.freedesktop.org/show_bug.cgi?id=53699 Release 2.20.4 (2012-08-18) =========================== Continuing the small bugfix releases, the only real feature is initial enabling for Haswell for the purpose of rendering verification and validation - by no means is it complete! Bugs fixed since 2.20.3: * Some potential errors along failure paths found by a static analyser with the help of Zdenek Kablac. * Eliminate zero-sized rectangles from PolyFillRectangles as the code assumes that they did not exist and so caused corruption. * Remove the UXA warning for failing to tile the front buffer if it is disallowed by hardware, and so expected. * Fix the validation of the XV pipe parameter. * Fix 8x8 tiled pattern fills https://bugs.freedesktop.org/show_bug.cgi?id=53353 * Fix compile failure when using --with-builderstring * Restore w/a flush for gen4 fill/copy/video, fortunately rare operations as at least for fill/copy we prefer to use the BLT. https://bugs.freedesktop.org/show_bug.cgi?id=53119 * Restore preferred use of the RENDER ring for SNB+ DRI copies. Release 2.20.3 (2012-08-04) =========================== Just a minor bugfix for gen4 chipsets (965gm, gm45 and friends) that crept into 2.20.2. As an added bonus, the pessimistic workaround for a GPU hang on gen4 has been relaxed and the shaders have been overhauled which should pave the way to eliminating the last of the uncommon CPU operations, along with immediately realising a small perforamnce improvement. Bugs fixed since 2.20.2: * Update DPMS bookkeeping after modeset https://bugs.freedesktop.org/show_bug.cgi?id=52142 * Avoid overlapping gpu/cpu damage after ignoring cpu damage in the consideration of placement for the operation. * Enable acceleration by default on 830gm/845g. The GMCH on this pair of chipsets is notoriously incoherent, so the GPU is almost certainly going to hang at some point, though unlikely to hang the system and should automatically disable acceleration (and thence behave identically as if the acceleration was disabled from the start). Option "NoAccel" can be used to disable all 2D acceleration and Option "DRI" can be used to disable all 3D acceleration. https://bugs.freedesktop.org/show_bug.cgi?id=52624 * Fix vertex bookkeeping for gen4 that was causing corruption in the command stream. Release 2.20.2 (2012-07-27) =========================== For the last 9 months, since 2.16.901, we have been shipping a driver that does not work on IvyBridge GT1 systems (HD2500 graphics); we were telling the GPU to use an invalid number of threads for the pixel shader and this in turned caused the GPU to hang. Also fixed since the last release just a few days ago: * Support for the gmux backlight controller on Apple laptops https://bugs.freedesktop.org/show_bug.cgi?id=52423 * Fix X -configure not to list this driver as matching any Intel device, just the VGA class devices will do! * A crash in SNA when repeatedly switching xrandr rotations * Corruption in SNA observed in kwin on IvyBridge https://bugs.freedesktop.org/show_bug.cgi?id=52473 Release 2.20.1 (2012-07-22) =========================== A week in, grab the brown paper bags, for it is time to reveal a couple of critical bugs that spoilt the 2.20.0 release. Firstly we have the restoration of DRI for i810. I am sure that the solitary user will be overjoyed in a couple of years when a new xserver is forced upon him. That enjoyment will be short-lived when as no actual acceleration remains, not even shadow, for the chipset. Perhaps a little more wildly felt, I hope!, will be that the SNA fallbacks were broken on 64-bit machines if they required clipping. One little misplaced cast of a pointer, and the screen is filled with corruption. Among the other tweaks this week: * A bug affecting gen4 handling of trapezoids was fixed, and CPU overhead reduced. https://bugs.freedesktop.org/show_bug.cgi?id=52158 * A fix for a bug causing corruption of a DRI2 unredirected client window that was resized whilst under a compositor. * Support for snoopable buffers on non-LLC architectures, coming to a future kernel. The aim to accelerate transfers between the CPU and the GPU, in particular to dramatically improve readback performance, and to further minimise clflushes. * Improvement to the composite performance on GT2 SandyBridge and IvyBridge devices, in particular the render copy is significantly improved. * Improved handling for when acceleration is disabled, including permitting DRI2 to remain supported even if the X server believes the GPU wedged. * Shadow support was dropped from UXA as it was neither complete nor correct, use SNA instead. Release 2.20.0 (2012-07-15) =========================== First the big news, a new acceleration method that aims to be faster and consume far less CPU than UXA is now available for selection at runtime. This snazzy new architecture can be selected through use of Option "AccelMethod" "sna" in your xorg.conf. Whilst it has been under development for some time, it has not yet had the same degree of widespread testing of UXA, so tread lightly. Try it and if you spot anything that can be improved, please do report a bug. Otherwise we have the usual smattering of bug fixes for UXA: * Use a white source whilst adding glyphs to the glyph mask (This fixes blank glyphs if using a font that mixes ARGB and A glyphs.) * Avoid fallbacks for glyph-to-dst in e.g. gnome-terminal https://bugs.freedesktop.org/show_bug.cgi?id=50508 * Force unused outputs off when VT switching https://bugs.freedesktop.org/show_bug.cgi?id=50772 * Copy the fbcon across to the Screen pixmap at startup. (This patch has been kicking around in the distributions for years.) * Many missed malloc failures checks and forgotten frees found by a static analyzer. Thanks Zdenek Kabelac! * Leak of the back buffer when terminating an application after pageflipping https://bugs.freedesktop.org/show_bug.cgi?id=50670 * Double check that the pipe is on before emitting a WAIT_ON_EVENT. In conjunction with an uptodate kernel, this should eliminate any hangs when changing resolutions or adding/removing displays. https://bugs.freedesktop.org/show_bug.cgi?id=50668 * Update to new Xorg APIs. Future proofing for the next generation of hotplug Xorg display servers. Many thanks to everyone who has reported a bug and otherwise helped to improve the driver. Release 2.19.0 (2012-04-29) =========================== More stability fixes for UXA and support for another variant of IvyBridge. Given the severity of the stability fixes, I strongly recommend everybody to upgrade to 2.19.0. * Prevent waiting on scanlines whilst not in control of the VT and therefore whilst referencing foreign CRTC configurations. * Pixmap (and bo leak) during fallback glyph composition * Remove broken acceleration for rendering glyphs directly upon the destination pixmap, exposed by cairo-1.12.0 (and coincidentally fix another Pixmap leak upon fallback handling). * Add support for Ivy Bridge GT2 Server chipset [PCI id 0x016a] * Remove broken damage flushing with CompositeRectangles https://bugs.freedesktop.org/show_bug.cgi?id=32547 * Fix crash upon server start with multiple monitors https://bugs.freedesktop.org/show_bug.cgi?id=47395 * Fix composition issues resulting from overly aggressive Pixmap reuse https://bugs.freedesktop.org/show_bug.cgi?id=47345 Release 2.18.0 (2012-02-24) =========================== Time passes, a few more bugs have crept out of the woodwork that are a compelling reason to update. Bugs fixed in this release (compared to 2.17.0) ----------------------------------------------- * Limit maximum object size so that all of the source, mask and destination can be mapped into the aperture simultaneously by basing the limit on the mappable aperture size rather than the size of the total GATT. * Incorrect clipping of polygons https://bugs.freedesktop.org/show_bug.cgi?id=43649 Regression from 2.15.901 * Limit number of VMA cached to avoid hitting the per-process VMA limit There still is a residual bug in that we seem to have so many objects floating around in the first place and that still leads to exhaustion of system limits. https://bugs.freedesktop.org/show_bug.cgi?id=43075 https://bugs.freedesktop.org/show_bug.cgi?id=40066 * Latency in processing user-input during continuous rendering Release 2.17.0 (2011-11-16) ============================== A few months have passed, and we have accumulated a surprising number of bug fixes. Oops! We would strongly encourage everyone to upgrade. Bugs fixed in this snapshot (compared to 2.16.902) -------------------------------------------------- * Video clobbering composite batch state http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=635953 Snapshot 2.16.902 (2011-11-13) ============================== This is the second release candidate in preparation for the upcoming 2.17.0 release. We will appreciate any feedback we can get from testing of this snapshot, and thanks to everyone who tested and reported upon issues in the last snapshot. A very old bug demonstrating that nobody has ever used alpha maps, and a couple of more recent mistakes were found. Bugs fixed in this snapshot (compared to 2.16.901) -------------------------------------------------- * Incorrect reuse of surface bindings within a batch for multiple formats https://bugs.freedesktop.org/show_bug.cgi?id=40926 * Nothing was rendered for text with procedural sources https://bugs.freedesktop.org/show_bug.cgi?id=31819 * Handle fallbacks involving alpha maps Snapshot 2.16.901 (2011-10-30) ============================== This is the first release candidate in preparation for the upcoming 2.17.0 release. We will appreciate any feedback we can get from testing of this snapshot. The basis of this release are to push out a couple of critical stability fixes for SandyBridge and IvyBridge. There is very little else to see here. Those 200+ other commits do not exist... Bugs fixed in this snapshot (compared to 2.16.0) -------------------------------------------------- * Workaround blitter hang on SandyBridge and IvyBridge https://bugzilla.kernel.org/show_bug.cgi?id=27892 https://bugs.freedesktop.org/show_bug.cgi * Workaround pipe control issues on SandyBridge * Use correct maximum PS thread count on IvyBridge * Protect against failed pixmap allocation for XV https://bugs.freedesktop.org/show_bug.cgi?id=40439 Release 2.16.0 (2011-08-09) ============================== A new quarter, a new release! The key feature of this release, looking past the bug fixes, is the enabling of IvyBridge acceleration. We have also fixed many bugs and graphical glitches and would encourage everyone to upgrade. Bugs fixed in this snapshot (compared to 2.15.901) -------------------------------------------------- * Build fix for xserver-1.7.7 Snapshot 2.15.901 (2011-07-30) ============================== This is the first release candidate in preparation for the upcoming 2.16.0 release. We will appreciate any feedback we can get from testing of this snapshot. The highlight of this snapshot is the full enabling of IvyBridge with acceleration for Render and Xv, along with handling of the shared render buffer allocations required for Mesa. Also of note is that deep-color support is enabled (for all chipsets), which allows you to drive your 30-bit monitor at its native colour depth. Bugs fixed in this snapshot (compared to 2.15.0) -------------------------------------------------- * Misuse of the Resource database causing crashes after DRI clients close https://bugs.freedesktop.org/show_bug.cgi?id=37700 * Crash on large strings https://bugs.freedesktop.org/show_bug.cgi?id=36860 * Incorrect rendering for some core drawing operations http://bugs.freedesktop.org/show_bug.cgi?id=28768 http://bugs.freedesktop.org/show_bug.cgi?id=28798 http://bugs.freedesktop.org/show_bug.cgi?id=28908 http://bugs.freedesktop.org/show_bug.cgi?id=29401 * Crash in Xv due to insufficient checks on batch space https://bugs.freedesktop.org/show_bug.cgi?id=36319 Release 2.15.0 (2011-04-14) ============================== We are pleased to announce this major release of the xf86-video-intel driver, roughly on schedule at 3 months since 2.14.0. With the many bug fixes in this release, we encourage everyone to upgrade to 2.15. The priority for this quarter has been simply to be unexciting and stabilise the driver further, seeking to capitalise upon the improvements elsewhere in the stack. Bugs fixed in this snapshot (compared to 2.14.903) -------------------------------------------------- * Turn off relaxed fencing by default for older chipsets This was continuing to destabilize those system, so for the release we disabled the feature. If you wish to help us debug this, you can re-enable the optimisation with Option "RelaxedFencing" "True". Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=36147 * Build fix for xserver-1.7.7 * KDE glitches on SNB [Technically fixed in the previous snapshot, but I'm really pleased that this got fixed in time for the release!] https://bugs.freedesktop.org/show_bug.cgi?id=35808 Snapshot 2.14.903 (2011-04-11) ============================== This is the third release candidate in preparation for the upcoming 2.15.0 release. We will appreciate any feedback we can get from testing of this snapshot. There was a bit of churn since 2.14.902 as a potential fix for a performance regression was tried but had to reverted when it was found to cause glitches running Compiz on SandyBridge. Otherwise, there were just a couple of fixes for building against old xservers and running on an obscure chipset. Bugs fixed in this snapshot (compared to 2.14.902) -------------------------------------------------- * Prevent issuing an invalid scanline wait command https://bugs.freedesktop.org/show_bug.cgi?id=35576 * The 946GZ in not a 945, but a 965. https://bugs.freedesktop.org/show_bug.cgi?id=35854 * Fix tile sizes for gen2 (finally). * Allow building of recent dri2 changes against old xservers. Snapshot 2.14.902 (2011-03-29) ============================== This is the second release candidate in preparation for the upcoming 2.15.0 release. We will appreciate any feedback we can get from testing of this snapshot. As befits testing of release candidates, no major regression was found and a couple more bugs have been fixed. Bugs fixed in this snapshot (compared to 2.14.901) -------------------------------------------------- * Clients disappearing with pending swaps * Incorrect clipping of Xv output on i915 across extended desktops https://bugs.freedesktop.org/show_bug.cgi?id=35346 * Introduction of a LinearFramebuffer option. (Defaults to tiled for performance and power saving.) Snapshot 2.14.901 (2011-03-02) ============================== This is the first release candidate in preparation for the upcoming 2.15.0 release. We will appreciate any feedback we can get from testing of this snapshot. Still no further along my grandiose plans to improve Render performance, aside from the performance tuning lower in the stack, instead we have had a steady stream of bug fixes. Bugs fixed in this snapshot (compared to 2.14.0) ------------------------------------------------ * Green pixels within partially off-screen video playback https://bugs.freedesktop.org/show_bug.cgi?id=24767 * Defer creation of the glyph cache to generation startup https://bugs.freedesktop.org/show_bug.cgi?id=33412 * Incorrect maximum addresses for video decoder state https://bugs.freedesktop.org/show_bug.cgi?id=34017 * Failure to handle oversized temporary surfaces https://bugs.freedesktop.org/show_bug.cgi?id=34399 * Relaxed tiling corruption on gen2 * Crash when destroying a foreign DRI drawable https://bugs.freedesktop.org/show_bug.cgi?id=34787 Release 2.14.0 (2011-01-07) =========================== We are pleased to announce this major release of the xf86-video-intel driver, on schedule at 3 months since 2.13.0. With the many bug fixes in this release, we encourage everyone to upgrade to 2.14. The most notable feature of this release is the inclusion of acceleration support, both RENDER and XVIDEO, for Sandy Bridge; note that this requires a 2.6.37 kernel. In improving the acceleration code paths to support Sandy Bridge, we were also able to improve the performance of the general i965+ RENDER acceleration. For example on i3, glyph (aa10 and rgb10) performance is about 3x faster, as is performing small copies between windows, with the improvement becoming negligible once you hit around 100 pixels square. Snapshot 2.13.903 (2010-01-04) ============================== This is the second release candidate in preparation for the upcoming 2.14.0 release, and if no showstoppers turn up in wider testing will become the next release. Besides the usual bug fixes, we've included patches by Mario Kleiner to improve vblank handing which both improve the timing accuracy and remove a few potential races -- provided you also have the corresponding fixes in the kernel. Bug fixes --------- * Crash on hot-unpluging with an active fullscreen GL application, e.g. a compositing WM or video player https://bugs.freedesktop.org/show_bug.cgi?id=32770 * Freeze upon maximising client-side software renderers, e.g. flash. https://bugs.freedesktop.org/show_bug.cgi?id=31367 * Fix confusion over G35 generation https://bugs.freedesktop.org/show_bug.cgi?id=32478 Snapshot 2.13.902 (2010-12-10) ============================== This is the first release candidate in preparation for the upcoming 2.14.0 release. Sandybridge support should be now be ready for use, and we will appreciate any feedback we can get from this snapshot. Improving the code base for Sandybridge should also have had knock on effects for earlier chips as well, in particular Ironlake and to a lesser extent i965. New requirements compared to 2.13 --------------------------------- * Librdrm >= 2.4.23 Bug fixes --------- * Crash after failing to allocate memory https://bugs.freedesktop.org/show_bug.cgi?id=31487 * EFAULT during pwrite https://bugs.freedesktop.org/show_bug.cgi?id=29752 * Mark outputs as on and restore backlight after mode-set * A hang with i965+ with newer kernels. Snapshot 2.13.901 (2010-11-05) ============================== This is an intermediate snapshot of ongoing driver development. The primary purpose of this snapshot is to capture some recent improvements, (particularly in Sandybridge support), for further testing. Release 2.13.0 (2010-09-30) =========================== We are pleased to announce this major release of the xf86-video-intel driver, on schedule at 3 months since 2.12.0. With the many bug fixes in this release, we encourage everyone using 2.12 to upgrade to 2.13. [This release is functionally identical to the earlier 2.12.902 release candidate.] New requirements compared to 2.12 --------------------------------- * Librdrm >= 2.4.22 Bug fixes --------- * Attempt to fix infinite MI_WAIT_FOR_EVENT while watching video https://bugs.freedesktop.org/show_bug.cgi?id=28964 [Various new checks have been added to the video code here, but the bug fix hasn't yet been verified by the original reporter.] * Fix buffer-object leak https://bugs.freedesktop.org/show_bug.cgi?id=26946 * Fix memory leak on server reset * Fix crash due to unchecked pixmap allocation https://bugs.freedesktop.org/show_bug.cgi?id=29187 * Fix for video artifacts when using dualscreen https://bugs.freedesktop.org/show_bug.cgi?id=29213 * Fix for incorrect characters in gnome-terminal when using compiz https://bugs.freedesktop.org/show_bug.cgi?id=28438 * Fix for hanging, full-screen applications, (flash, compiz, etc.) https://bugs.freedesktop.org/show_bug.cgi?id=29584 * Fix selection of backlight device on multi-GPU systems https://bugs.freedesktop.org/show_bug.cgi?id=29273 * Fix to avoid crash with extremely large glyphs https://bugs.freedesktop.org/show_bug.cgi?id=29430 * Fix for eDP panels incorrectly being given only a single, valid mode https://bugs.freedesktop.org/show_bug.cgi?id=30069 * Fix GPU hang involving clipped SRC copies https://bugs.freedesktop.org/show_bug.cgi?id=30120 * Fix to compile for 1.6 series X server. * Fix to retry framebuffer allocation after an initial failure. * Fix to disable dri2 after fallbacks are forced on. Snapshot 2.12.902 (2010-09-28) ============================== This is the second release candidate in preparation for the upcoming 2.13.0 release. The comes exactly one week after 2.12.902 and includes only a handful of changes. One significant change is that the drive now requires libdrm 2.4.22 (or newer), as several people reported compilation failures of xf86-video-intel 2.12.901 with libdrm 2.4.21. Other changes include a fix to compile for the 1.6 series X server, a fix to retry framebuffer allocation after an initial failure, and a fix to disable dri2 after fallbacks are forced on. Snapshot 2.12.901 (2010-09-21) ============================== This is the first release candidate in preparation for the upcoming 2.13.0 release. We will appreciate any feedback we can get from testing of this snapshot. Bugs fixed in this snapshot (compared to 2.12.0) ------------------------------------------------ * Attempt to fix infinite MI_WAIT_FOR_EVENT while watching video https://bugs.freedesktop.org/show_bug.cgi?id=28964 [Various new checks have been added to the video code here, but the bug fix hasn't yet been verified by the original reporter.] * Fix buffer-object leak https://bugs.freedesktop.org/show_bug.cgi?id=26946 * Fix memory leak on server reset * Fix crash due to unchecked pixmap allocation https://bugs.freedesktop.org/show_bug.cgi?id=29187 * Fix for video artifacts when using dualscreen https://bugs.freedesktop.org/show_bug.cgi?id=29213 * Fix for incorrect characters in gnome-terminal when using compiz https://bugs.freedesktop.org/show_bug.cgi?id=28438 * Fix for hanging, full-screen applications, (flash, compiz, etc.) https://bugs.freedesktop.org/show_bug.cgi?id=29584 * Fix selection of backlight device on multi-GPU systems https://bugs.freedesktop.org/show_bug.cgi?id=29273 * Fix to avoid crash with extremely large glyphs https://bugs.freedesktop.org/show_bug.cgi?id=29430 * Fix for eDP panels incorrectly being given only a single, valid mode https://bugs.freedesktop.org/show_bug.cgi?id=30069 * Fix GPU hang involving clipped SRC copies https://bugs.freedesktop.org/show_bug.cgi?id=30120 Release 2.12.0 (2010-06-24) =========================== We are pleased to announce this major release of the xf86-video-intel 2D driver. It contains many correctness and performance improvements compared to the 2.11 releases. We encourage everyone using 2.11 to upgrade to 2.12. [This release contains several bug fixes since the earlier 2.11.901 release candidate---see below for details.] New requirements compared to 2.11 --------------------------------- * Libdrm >= 2.4.21 Major performance improvements ------------------------------ There have been many performance improvements targeting the 915G/945G/Pineview graphics chipsets (thank to Chris Wilson!). Areas improved include: * Major improvements to glyph rendering * Avoid software fallback when using extended desktops, (for example, video playback) * Better performance when using large windows, (for example with firefox scrolling) * Avoiding migration ping-pong with gigantic drawing The following speedups (measured with cairo-perf-trace/cairo-traces) capture some of the improvements. These were measured on a Pineview system with X server 1.8.1. This compares how this 2.12 release improves performance compared to 2.11.0: Trace Speedup ----- ------- ocitysmap 5.41x speedup firefox-talos-gfx 2.41x speedup gnome-terminal-vim 2.15x speedup poppler 1.86x speedup firefox-planet-gnome 1.43x speedup midori-zoomed 1.39x speedup swfdec-giant-steps 1.36x speedup xfce4-terminal-a1 1.17x speedup evolution 1.09x speedup swfdec-youtube 1.06x speedup Other improvements ------------------ Daniel Vetter improved Xvmc and overlay, adding GEM support. Bug fixes --------- There have been many conformance improvements targeting the 915G/945G/Pineview graphics chipsets. The rendercheck test suite passes once again and there has been a significant reduction in the number of errors detected by the cairo test suite (notably center sampling and EXTEND_NONE behaviors are fixed). Other notable bug fixes include: * Fix for bug 28446 Garbled fonts with Mathematica https://bugs.freedesktop.org/show_bug.cgi?id=28446 * Fixes for page-flipping and other DRI2-handling bugs, (Thanks Jesse Barnes, and Kristian Høgsberg) * Avoid corruption when using extended desktops, (for example, video playback) (The bug fixes below are new since the 2.11.901 release candidate) * Fix corrupted output when screen rotated https://bugs.freedesktop.org/show_bug.cgi?id=28461 * Fix corrupted rendering in KDE due to missing flush. * Fixes i830_uxa_put_image for the following issues: Bug 28569 - [i965] IGN's flash-based video player crashes X https://bugs.freedesktop.org/show_bug.cgi?id=28569 Bug 28573 - [i965] Fullscreen flash and windowed SDL games fail to update the screen https://bugs.freedesktop.org/show_bug.cgi?id=28573 * Fix visual corruption of scrollbar in Chromium * Fix tiling limits to resolve this issue: Bug 28497 - Graphics corruption after opening a specific website https://bugs.freedesktop.org/show_bug.cgi?id=28497 Snapshot 2.11.901 (2010-06-14) ============================== This is the first release candidate in preparation for the upcoming 2.12.0 release. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.12.0 release. New requirements compared to 2.10 --------------------------------- * Libdrm >= 2.4.19 Major performance improvements ------------------------------ There have been many performance improvements targeting the 915G/945G/Pineview graphics chipsets (thank to Chris Wilson!). Areas improved include: * Major improvements to glyph rendering * Avoid software fallback when using extended desktops, (for example, video playback) * Better performance when using large windows, (for example with firefox scrolling) * Avoiding migration ping-pong with gigantic drawing The following speedups (measured with cairo-perf-trace/cairo-traces) capture some of the improvements. These were measured on a Pineview system with a very recent X server, (from git just before 1.8.1). This compares how this 2.12 release candidate improves performance compared to 2.11.0: Trace Speedup ----- ------- ocitysmap 5.41x speedup firefox-talos-gfx 2.41x speedup gnome-terminal-vim 2.15x speedup poppler 1.86x speedup firefox-planet-gnome 1.43x speedup midori-zoomed 1.39x speedup swfdec-giant-steps 1.36x speedup xfce4-terminal-a1 1.17x speedup evolution 1.09x speedup swfdec-youtube 1.06x speedup Other improvements ------------------ Daniel Vetter improved Xvmc and overlay, adding GEM support. Bug fixes --------- There have been many conformance improvements targeting the 915G/945G/Pineview graphics chipsets. The rendercheck test suite passes once again and there has been a significant reduction in the number of errors detected by the cairo test suite (notably center sampling and EXTEND_NONE behaviors are fixed). Other notable bug fixes include: * Fix for bug 28446 Garbled fonts with Mathematica https://bugs.freedesktop.org/show_bug.cgi?id=28446 * Fixes for page-flipping and other DRI2-handling bugs, (Thanks Jesse Barnes, and Kristian Høgsberg) * Avoid corruption when using extended desktops, (for example, video playback) Release 2.11.0 (2010-03-29) =========================== New in 2.11: DRI2 and page flipping ----------------------------------- The most significant new feature of this release is support for new DRI2 APIs, allowing page flipping to occur for swaps that are full-screen and not rotated. Performance improvements in 2.11 compared to 2.10 ------------------------------------------------- Dramatically improved performance of large pixmaps on memory-constrained hardware, (such as 945), by using tiling. Note that this fix is new since the most recent release candidate for this release (2.10.903). https://bugs.freedesktop.org/show_bug.cgi?id=25375 Elimination of software fallback with alpha-only pixmap (a fix which eliminated a full second from the Moblin boot time): https://bugs.freedesktop.org/show_bug.cgi?id=26189 Notable bug fixes in 2.11 compared to 2.10 ------------------------------------------ Fix for undesired black borders on some images, (caued several problems with firefox): http://bugs.freedesktop.org/show_bug.cgi?id=17933 And other fixes to provide more conformance with existing software-rendering, (as measures by the cairo test suite), such as the sampling location for nearest-neighbor sampling. Other changes ------------- Eric Anholt and Daniel Vetter both removed large piles of old and useless code now that the driver requires kernel modesetting (KMS). This continues to reduce the mainteance burden of the driver, making it easier to isolate and fix bugs. Snapshot 2.10.903 (2010-03-22) ============================== Some notable bug fixes ---------------------- * Fix unpredictable results in page-flipping code due to access of an uninitialized variable. * Two fixes that address a number of long-outstanding failures in the cairo test suite: Remove coord-adjust for nearest centre-sampling. Fill alpha on xrgb images. Closes: Bug 17933 - x8r8g8b8 doesn't sample alpha=0 outside surface bounds http://bugs.freedesktop.org/show_bug.cgi?id=17933 * Fix a regression introduced in 2.10.902: Fatal server error: i915_emit_composite_setup: ADVANCE_BATCH: under-used allocation 100/104 Bug 21723 [i915 bisected] rendering makes X crash http://bugs.freedesktop.org/show_bug.cgi?id=27123 Other minor fixes (avoid trying to print an error message with a freed string, set a variable to NULL after freeing), and documentation updates are also included. Snapshot 2.10.902 (2010-03-15) ============================== Some significant bug fixes -------------------------- Fix video color problems due to YUV plane ordering issue. This fixed a regression that showed up recently (only in these release candidates). Fix recent regression leading to corruption under compiz: https://bugs.freedesktop.org/show_bug.cgi?id=26814 Further DRI2 improvements/fixes from Mario Kleiner and Jesse Barnes, (including support for SwapBuffers request with divisor != 0). Fix build against X server 1.6 branch. Avoid flooding logs after an error occurs. And dramatic code cleanups -------------------------- Eric Anholt removed several cases of old, useless code, (conditions that could not occur now that we require KMS, etc.). Daniel Vetter eliminated piles of code by modernizing the XvMC memory-management and completely removing the old i830_memory allocator (i830_allocate_memory, i830_free_memory), etc. Snapshot 2.10.901 (2010-02-26) ============================== The most significant new feature of this release is support for new DRI2 APIs, allowing page flipping to occur for swaps that are full-screen and not rotated. Some significant bug fixes -------------------------- * Avoid fallback due to failing to extract pixel value from an alpha-only solid, (this fix eliminated 1 second from Mobilin boot time). https://bugs.freedesktop.org/show_bug.cgi?id=26189 * Handle full-height blits without tearing in CopyRegion https://bugs.freedesktop.org/show_bug.cgi?id=22475 Several other fixes and cleanups are included as well, (including the removal of stale utility code that is now maintained in the separate intel-gpu-tools module). Release 2.10.0 (2010-01-04) =========================== New requirements of 2.10 compared to 2.9 ---------------------------------------- * Linux kernel with kernel-modesetting (KMS) All user-modesetting code has now been removed from the driver. We highly recommend kernel version 2.6.32 or later. * Libdrm >= 2.4.16 New features in 2.10 compared to 2.9 ------------------------------------ * New driver debugging options available in xorg.conf (DebugFlushBatches, DebugFlushCaches, DebugWait). See "man intel" for more details. * Video overlay support with KMS. This currently requires Linux 2.6.33, but a backport to 2.6.32 is available here: http://gitorious.org/daniel-s-linux-stuff/linux-kernel/commits/intel-kms-overlay-for-2.6.32 Notable fixes in 2.10 compared to 2.9 ----------------------------------- * Fix crash when XRenderComposite is called with a -1 value for width/height, (crash at login when using compiz). http://bugs.freedesktop.org/show_bug.cgi?id=24724 * Fix to support larger extended desktops, (such as a 2560x1600 plus a 1920x1200 monitor). * Fix glyph corruption due to insufficient cache flushing: https://bugs.freedesktop.org/show_bug.cgi?id=24315 Several other correctness and performance fixes are also included. Note: The driver code of the 2.10.0 release is identical to that of the 2.9.99.901 release candidate. The only changes in 2.10.0 compared to 2.9.99.902 are a minor change to the configure script, and some small updates to the documentation. Snapshot 2.9.99.902 (2009-12-10) ================================ This is the second release candidate in preparation for the upcoming 2.10.0 release. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.10.0 release. Compared to the previous snapshot, this snapshot now correctly verifies that libdrm 2.4.16 (or newer) is available. The previous snapshot also required libdrm 2.4.16 for correct functionality, but neglected to notify the user of this at configure, compile, or install time and would instead simply fail to run. Snapshot 2.9.99.901 (2009-11-30) ================================ This is the first release candidate in preparation for the upcoming 2.10.0 release. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.10.0 release. With this snapshot, the xf86-video-intel driver requires kernel modesetting (KMS) as all of the user modesetting (UMS) support has been removed from the driver. Release 2.9.0 (2009-09-28) ========================== We are pleased to announce the 2.9.0 release of the xf86-video-intel driver. (If you have been following along at home, this release is identical to the 2.8.99.902 release candidate other than the version number). New features in 2.9 compared to 2.8 ----------------------------------- * Support for the B43 chipset. Major fixes in 2.9.0 compared to 2.8.0 -------------------------------------- * Multiple fixes to make the driver stable for 8xx chipsets, (855GM, 865G, etc.). The 2.8 driver series was extremely unstable with many of these chipsets. https://bugs.freedesktop.org/show_bug.cgi?id=22904 (and many duplicates) https://bugs.freedesktop.org/show_bug.cgi?id=22947 * Add support for BACKLIGHT property when using kernel modesetting (KMS). This allows backlight adjustment with programs such as "xbacklight -set " or "xrandr --set BACKLIGHT ". https://bugs.freedesktop.org/show_bug.cgi?id=20963 * Fix so that "xrandr --scale" works when using KMS. https://bugs.freedesktop.org/show_bug.cgi?id=22893 * Fix segfaults of X server when logging out. https://bugs.freedesktop.org/show_bug.cgi?id=20516 * Avoid falling back to software for 1-bit alpha-only masks. https://bugs.freedesktop.org/show_bug.cgi?id=23184 * Fix pixel sampling position for 8xx chipsets, (fixes some cairo-test suite failures). Snapshot 2.8.99.901 (2009-09-09) ================================ This is the first release candidate in preparation for the upcoming 2.9.0 release. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.9.0 release. See the commit log for changes in this release, and developers, please provide me summaries for any major features in this release that you think should appear in NEWS and in the 2.9.0 release notes. Note: We are still investigating failures with 865G chipsets, (these failures existed in the 2.8 series as well). We are hoping to fix these failures before the 2.9.0 release. Release 2.8.0 (2009-07-20) ========================== We are pleased to present this major release of the xf86-video-intel driver. This release is very similar to the 2.7.99.902 release candidate but includes a couple of additional bug fixes, (for bugs #22760 and @22483). Compared to the 2.7 releases this driver contains several new features and many bug fixes. The driver now depends on X server 1.6 or later, and eliminates several obsolete code paths, (XAA and EXA removed in favor of UXA, DRI1 support eliminated). The driver certainly will work best with an i915 module from a recent kernel (2.6.31) and with kernel-modesetting (KMS, specified by loading i915 with the option "modeset=1"). New features in 2.8.0 compared to 2.7 ------------------------------------- * Remove XAA/EXA/DRI1 and NoAccel, and only support UXA/DRI2 now (requiring xserver 1.6). * VLD support added into XvMC for Mpeg2, which decreases CPU usage when playing video. Major fixes in 2.8.0 compared to 2.7 ------------------------------------ * Fix broken front-buffer rendering https://bugs.freedesktop.org/show_bug.cgi?id=19174 * Fix disabling of XvMC disabled https://bugs.freedesktop.org/show_bug.cgi?id=20790 * Fix broken VT switch on some machines https://bugs.freedesktop.org/show_bug.cgi?id=19578 * Improve performance of trapezoid rendering for UXA https://bugs.freedesktop.org/show_bug.cgi?id=21376 * Vblank sync'd GL buffer swap (fixing video tearing under composite) https://bugs.freedesktop.org/show_bug.cgi?id=20664 * Fix G41 DRM support https://bugs.freedesktop.org/show_bug.cgi?id=21095 * Fix crash on some 8xx https://bugs.freedesktop.org/show_bug.cgi?id=18974 Various fixes for GPU hangs, and more... Snapshot 2.7.99.902 (2009-07-13) -------------------------------- This is the first release candidate in preparation for the upcoming 2.8.0 release. Most major and critical bugs should be fixed, but some minor bugs may still be present. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.8.0 release. Snapshot 2.7.99.901 (2009-06-10) -------------------------------- This is the first release candidate in preparation for the upcoming 2.8.0 release. Most critical bugs should be fixed, but some major bugs may still be present. We will appreciate any feedback we can get from testing of this snapshot to improve the 2.8.0 release. Some of the major fixes in this snapshot include: * Several fixes for intermittent GPU hangs/crashes, (some of which already appeared in the 2.7.1 release) * Fix to avoid X crash when viewing large images in browser * Fix X server failure when running old (non-GEM) kernel * Fixes for SDVO LVDS mode detection * Fix major performance regression of trapezoid rendering compared to XAA/EXA * New support for tear-free video when using KMS * New support for tear-free DRI2 CopyRegion Snapshot 2.7.99.1 (2009-04-28) ------------------------------ This is a development snapshot very early in the process toward developing 2.8. There have been some big changes to the code, and we're anxious to get feedback on these changes as early as possible. Here is a summary of the biggest changes: * Driver now depends on X server 1.6 or later * Eliminate XAA and EXA support (in favor of UXA) * Eliminate DRI1 support * Fixes for running without DRI at all These code removals represent a deletion of a substantial amount of code, (and hopefully piles of bugs), as well as reduce the maintenance effort going forward as the number of combinatorial configurations for the driver are greatly reduced. This means that users are much more likely to be running code that has actually been tested, and it will be much easy for developers to replicate bugs that users experience. One of the things that would be most useful in testing this release is to revisit any outstanding bugs that you have previously reported. If the buggy behavior is gone, (or the bug is no longer relevant---such as a bug that's specific to XAA only), please feel free to indicate so in bugzilla or even just close the bug. If you confirm that the bug is still present, please indicate so in the bug report. (I was going to ask that you select a 1.7.99 version, but it looks like bugzilla only has versions for products not compoenents, while we use a "xorg" product and a "driver/intel" component.) We definitely want to make any such confirmed bugs a priority, so it would be nice to have a consistent mechanism to search for these bugs. Suggestions are welcome on the best approach. Thanks in advance for any testing or feedback on this snapshot. Release 2.7.0 (2009-04-15) -------------------------- Compared to the 2.6 series, 2.7.0 has a large number of bug fixes, but also a few significant features, such as: SDVO-TV support, available on ADD2 card (bug#9992) and D945GCLF2 board (bug#17776). Basic SDVO-LVDS support XV video display without tearing [Though this isn't working for all users yet, see https://bugs.freedesktop.org/show_bug.cgi?id=21076 ] Various fixes for UXA, DRI2, and Kernel modesetting. We encourage users to use kernel modesetting and UXA acceleration with this release, which should give the best performance and robustness. When KMS is available, UXA is the default acceleration used by the driver, (EXA is the default otherwise). Known issue: Some Linux kernel versions (such as 2.6.29) are known to have broken PAT code that causes recent versions of this driver to fail, (which can manifest as the X server simply not starting). This can be verified by adding the "nopat" option to the kernel command-line and seeing the failure go away. We hope that newer kernels in the 2.6.29.x as well as 2.6.30 and above will have working PAT code. Some of the most notable bugs fixed in 2.7.0 include: [GM45 965GM] bad htotal causes panel startup failure https://bugs.freedesktop.org/show_bug.cgi?id=17292 [xrandr TV] need TV output property control https://bugs.freedesktop.org/show_bug.cgi?id=12763 [TV] "xrandr --set TV_FORMAT" gets BadMatch error https://bugs.freedesktop.org/show_bug.cgi?id=16566 [945 tiling] Low performance due to no A17 workaround https://bugs.freedesktop.org/show_bug.cgi?id=16835 [TV]Flicker when launching applications in the 2.4-branch https://bugs.freedesktop.org/show_bug.cgi?id=17405 [945GM FBC] FBC causes underruns & flicker https://bugs.freedesktop.org/show_bug.cgi?id=18651 [xv] Textured video suffers from tearing https://bugs.freedesktop.org/show_bug.cgi?id=19635 [G45] Random hangs with UXA https://bugs.freedesktop.org/show_bug.cgi?id=19734 [945GM] Any 3D app is slow in resolution higher than 800x600 with UXA+DRI2, due to tiling https://bugs.freedesktop.org/show_bug.cgi?id=19738 [i915 UXA,EXA] rotation messes display with tiling on https://bugs.freedesktop.org/show_bug.cgi?id=20265 [G45] DRI2/UXA gives solid white instead of transparency https://bugs.freedesktop.org/show_bug.cgi?id=20321 LVDS output not detected https://bugs.freedesktop.org/show_bug.cgi?id=20517 xf86-video-intel-2.6.3: Xv crashes X server https://bugs.freedesktop.org/show_bug.cgi?id=20525 [G965 non-GEM] systray in KDE 4 completely broken https://bugs.freedesktop.org/show_bug.cgi?id=20527 [SDVO-TV]the desktop is teared in four sections on the screen https://bugs.freedesktop.org/show_bug.cgi?id=20550 Intel video driver 2.6.3 crashes with XVideo https://bugs.freedesktop.org/show_bug.cgi?id=20563 [855GM] Xv crash with non-KMS https://bugs.freedesktop.org/show_bug.cgi?id=20585 2.6.99.902 breaks native 1680x1050 mode on TMDS -- EDID miss https://bugs.freedesktop.org/show_bug.cgi?id=20594 [945GM TV] 2.6.99.902 sets a too high CONTRAST-value https://bugs.freedesktop.org/show_bug.cgi?id=20670 [915GM] fail to detect LVDS with new VBT code https://bugs.freedesktop.org/show_bug.cgi?id=20752 [regression i965]tiled output when start X https://bugs.freedesktop.org/show_bug.cgi?id=20803 2.6.99.902: LVDS wrongly detected as disconnected https://bugs.freedesktop.org/show_bug.cgi?id=20826 vt switching fails and crashes X https://bugs.freedesktop.org/show_bug.cgi?id=20863 [HDMI] The screen will flicker when some application runs on G45-64 https://bugs.freedesktop.org/show_bug.cgi?id=20875 TexturedVideo is offsetted wrongly on dualhead https://bugs.freedesktop.org/show_bug.cgi?id=20980 [EXA] xvideo hang X https://bugs.freedesktop.org/show_bug.cgi?id=21027 [EXA] x11perf performance regression https://bugs.freedesktop.org/show_bug.cgi?id=21029 And many others...