aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Collapse)AuthorAgeFilesLines
* i915g: Bump texture sizesJakob Bornecrantz2011-05-251-2/+2
| | | | | | Spotted and tested by Christopher Egert. Signed-off-by: Jakob Bornecrantz <[email protected]>
* r600g: remove duplicate opcode in r600_opcodes.hAlex Deucher2011-05-251-1/+0
| | | | | | | | V_SQ_CF_WORD1_SQ_CF_INST_HALT is 0x1f on both evergreen and cayman. Reported-by: Gustaw Smolarczyk <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
* r600g: fix eg/cayman scissor workaroundAlex Deucher2011-05-241-11/+13
| | | | Signed-off-by: Alex Deucher <[email protected]>
* r600g: add workaround for buggy hw scissor on eg/cayman.Dave Airlie2011-05-251-1/+14
| | | | | | This is ported from the same fix to the DDX. Signed-off-by: Dave Airlie <[email protected]>
* r600g: add initial cayman acceleration support.Dave Airlie2011-05-2512-204/+1442
| | | | | | | | | | | | | | | | Cayman is the RadeonHD 69xx series of GPUs. This adds support for 3D acceleration to the r600g driver. Major changes: Some context registers moved around - mainly MSAA and clipping/guardband related. GPR allocation is all dynamic no vertex cache - all unified in texture cache. 5-wide to 4-wide shader engines (no scalar or trans slot) - some changes to how instructions are placed into slots - removal of END_OF_PROGRAM bit in favour of END flow control clause - no vertex fetch clause - TC accepts vertex or texture Signed-off-by: Dave Airlie <[email protected]>
* r600g: don't lookup a vs semantic for position/face.Dave Airlie2011-05-251-0/+4
| | | | | | | These don't need one, and I was seeing 0xff being returned and set in the GPU registers with some tests. Signed-off-by: Dave Airlie <[email protected]>
* r600g: flush the DB dest base as well.Dave Airlie2011-05-251-1/+1
| | | | | | | | If we do this for CB bases then we should do it for DB bases. noticed while adding cayman support. Signed-off-by: Dave Airlie <[email protected]>
* wgl: Don't hold on to user supplied HDC.José Fonseca2011-05-243-23/+22
| | | | | | | | | | | Certain applications (e.g., Bernina My Label, and the Windows implementation of Processing language) destroy the device context used when creating the frame-buffer, causing presents to fail because we were still referring to the old device context internally. This change ensures we always use the same HDC passed to the ICD entry-points when available, or our own HDC when not available (necessary only when flushing on single buffered visuals).
* r600g: fix "Fixed-Point Data Conversions"Christian König2011-05-212-2/+2
| | | | | | According to OpenGL 3.1 chapter 2.1.5 the representation without zero should only be used for vertex attribute values, but not for textures or frame-buffers.
* st/egl: Add support for EGL_DRM_BUFFER_USE_CURSOR_MESABenjamin Franzke2011-05-201-1/+7
|
* st/dri: Support dri2 useflags in dri2_create_imageBenjamin Franzke2011-05-201-0/+9
|
* st/egl/wayland: Deal with wayland visual changesBenjamin Franzke2011-05-201-17/+21
| | | | | | | Since wayland 4bde293ff8109d55eeaee8732f5a6ee0c8cd4bd9 we cant lookup visuals, as we dont receive the visual token events. The format for pixmap-images thus has to default to argb for now.
* gallivm: Fix for dynamically linked LLVM 2.8 library.José Fonseca2011-05-201-2/+12
| | | | | | | | | This prevents the error prog: for the -disable-mmx option: may only occur zero or one times! when creating a new context after XCloseDisplay with DRI drivers linked with a shared LLVM 2.8 library.
* st/glx: define/set new ST_CONTEXT_FLAG_bitsBrian Paul2011-05-192-11/+25
|
* st/glx: pass major, minor, context flags, etc to XMesaCreateContext()Brian Paul2011-05-193-3/+9
|
* st/glx: implement glXCreateContextAttribsARB()Brian Paul2011-05-191-0/+95
|
* st/glx: pass version, context flags, etc to create_context()Brian Paul2011-05-191-4/+9
|
* st/glx: refactor create-context functionsBrian Paul2011-05-191-61/+40
|
* nv50: add support for user clip planesMaxim Levitsky2011-05-194-1/+40
| | | | | | | | | | | | | | | Clip distance is calculated each time vertex position is written which is suboptiomal is some cases but very safe. User clip planes are an obsolete feature anyway. Every time number of clip planes increases, the vertex program is recompiled. That ensures no overhead in normal case (no user clip planes) and reasonable overhead otherwise. Fixes 3D windows in compiz, and reflection effect in neverball. Also fixes compiz expo plugin when windows were dragged and each window shown 3 times.
* gallivm: Tell LLVM to not assume a 16-byte aligned stack on x86.José Fonseca2011-05-181-0/+13
| | | | Fixes fdo 36738.
* r600g: bump domain selection up one layer.Dave Airlie2011-05-183-6/+24
| | | | | | | this is taken from a patch from Mathias Froehlich, just going to stage it in a few pieces. Signed-off-by: Dave Airlie <[email protected]>
* u_vbuf_mgr: fix max_index computation when src_offset is abused as buffer_offsetMarek Olšák2011-05-171-1/+6
|
* gallium: block signals for new thread when spawning threadsDave Airlie2011-05-161-1/+8
| | | | | | | | | | | | | I'm hard pressed to think of any reason a gallium thread would want to receive a signal, especially considering its probably loaded as a library and you don't want the threads interfering with the main threads signal handling. This solves a problem loading llvmpipe into the X server for AIGLX, where the X server relies on the SIGIO signal going to the main thread, but once llvmpipe loads the SIGIO can end up in any of its threads. Signed-off-by: Dave Airlie <[email protected]>
* r600g: reduce flushes so only when texture and CB overlap.Dave Airlie2011-05-152-8/+17
| | | | | | | We only need to do this when the texture and CB are using the same memory area. Signed-off-by: Dave Airlie <[email protected]>
* r300g: HiZ fixesMarek Olšák2011-05-151-24/+24
| | | | | | | Nothing special, just changing conditions for when HiZ can be enabled and when HiZ memory becomes invalid. I was thinking about it again and realized it had not been quite right.
* r300g: don't set other HyperZ states if depth and stencil tests are disabledMarek Olšák2011-05-151-14/+27
| | | | Such as HiZ.
* r300g: dynamically ask for and release Hyper-Z accessMarek Olšák2011-05-1510-95/+225
| | | | | We ask for Hyper-Z access when clearing a zbuffer. We release it if no zbuffer clear has been done for 2 seconds.
* r300g: fix conversion from int to booleanMarek Olšák2011-05-151-2/+2
|
* u_vbuf_mgr: fix max_index computation once againMarek Olšák2011-05-141-15/+47
| | | | | | | | | | | | See how I compute and use the 'unused' variable in the code. It's crucial for getting max_index right. Fixed with the help of apitrace. (bisecting the problematic draw call manually was not fun though) This should fix: https://bugs.freedesktop.org/show_bug.cgi?id=36268 https://bugs.freedesktop.org/show_bug.cgi?id=36609
* nvc0: prevent overlap between load address and destination regsChristoph Bumiller2011-05-131-15/+29
| | | | | | | | For example, an indirect load like "ld b128 $r0q c0[$r0]" seems to overwrite the address register before finishing the load, but only if there are a lot of threads running. Visible as displaced geoemtry in Unigine Heaven.
* util_logbase2 takes and returns unsigned, not intMatt Turner2011-05-121-2/+2
| | | | | Signed-off-by: Matt Turner <[email protected]> Signed-off-by: Brian Paul <[email protected]>
* Remove redundant util_unsigned_logbase2Matt Turner2011-05-125-17/+5
| | | | | | | util_logbase2 is exactly the same function. Signed-off-by: Matt Turner <[email protected]> Signed-off-by: Brian Paul <[email protected]>
* u_math.h: Remove redundant mingw32 ffs definitionMatt Turner2011-05-121-4/+0
| | | | | Signed-off-by: Matt Turner <[email protected]> Signed-off-by: Brian Paul <[email protected]>
* st/egl: Implement EGL_WL_bind_wayland_display for x11,drm,waylandBenjamin Franzke2011-05-1315-0/+495
|
* nvfx: fill some PIPE_CAPsFrancesco Marella2011-05-131-0/+6
| | | | Signed-off-by: Francesco Marella <[email protected]>
* i915g: Fix typos in print messages.Vinson Lee2011-05-121-3/+3
|
* r600g: don't unmap if we haven't mappedDave Airlie2011-05-131-2/+4
| | | | | | should fix https://bugs.freedesktop.org/show_bug.cgi?id=37157 Signed-off-by: Dave Airlie <[email protected]>
* r600g: use a local var to store pointer to which register we are working onDave Airlie2011-05-131-7/+8
| | | | | | this just makes the code a little bit cleaner. Signed-off-by: Dave Airlie <[email protected]>
* r600g: make range/block act more like a page tableDave Airlie2011-05-133-50/+45
| | | | | | | | | | | | | | | | only allocate the blocks ptr in the range if we ever have one, otherwise don't bother wasting the memory. valgrind glxinfo before: ==967== in use at exit: 419,754 bytes in 706 blocks ==967== total heap usage: 3,552 allocs, 2,846 frees, 3,550,131 bytes allocated after: ==5227== in use at exit: 419,754 bytes in 706 blocks ==5227== total heap usage: 3,452 allocs, 2,746 frees, 3,140,531 bytes allocate Signed-off-by: Dave Airlie <[email protected]>
* r600g: reduce r600_reg footprintDave Airlie2011-05-133-788/+785
| | | | | | | | This drops 6k of the text segment, a minor drop in the ocean, however it also makes the code a lot cleaner and removes a lot of duplicated information, hopefully making it more maintainable. Signed-off-by: Dave Airlie <[email protected]>
* r600g: reduce memory usage from range/block hash table.Dave Airlie2011-05-134-28/+39
| | | | | | | | | | | | | | | | | | This table covered a large range unnecessarily, reduce the address range covered, use the fact that the bottom two bits aren't significant, and remove unused fields from the range struct. It also drops the hash_size/shift in context in favour of a define, which should make doing the math a bit less CPU intensive. valgrind glxinfo Before: ==320== in use at exit: 419,754 bytes in 706 blocks ==320== total heap usage: 3,691 allocs, 2,985 frees, 7,272,467 bytes allocated After: ==967== in use at exit: 419,754 bytes in 706 blocks ==967== total heap usage: 3,552 allocs, 2,846 frees, 3,550,131 bytes allocated Signed-off-by: Dave Airlie <[email protected]>
* r600g: delay mapping until first map request. (v2)Dave Airlie2011-05-132-6/+4
| | | | | | | | | | | | | | Currently r600g always maps every bo, this is quite pointless as it wastes VM and on 32-bit with wine running VM space is quite useful. So with this patch we don't create the mappings until first use, without tiling enabled this probably won't make a major difference on its own, but with tiled staged uploads it should avoid keeping maps for most of the textures unnecessarily. v2: add bo data ptr check Signed-off-by: Dave Airlie <[email protected]>
* r600g: fix flushes on rs780/rs880Alex Deucher2011-05-111-1/+3
| | | | | | | | | They need the same hack as rv670. Fixes: https://bugs.freedesktop.org/show_bug.cgi?id=35312 Signed-off-by: Alex Deucher <[email protected]>
* svga/drm: Implement svga_winsys_screen::get_hw_version.José Fonseca2011-05-101-0/+14
|
* st/wgl: Remove buggy assertion.José Fonseca2011-05-101-2/+0
| | | | | The assertion is wrong, now that state tracker can cope with a window with zero width or height.
* nv50: fix mistake in pipe caps for pre-NVA0 cardsMaxim Levitsky2011-05-101-0/+1
| | | | Introduced by 531b12af35a832bcd8928a4919d76f8e9405cde0.
* nv50/nvc0: make transfers aware of PIPE_TRANSFER_MAP_DIRECTLYMarcin Slusarz2011-05-092-0/+6
| | | | | | | | | | If state tracker asked us to map resource directly and we can't do it (because of tiling), return NULL instead of doing full transfer - state tracker should handle it and fallback to some other method or repeat transfer without PIPE_TRANSFER_MAP_DIRECTLY. It greatly improves performance of xorg state tracker on nv50+, because its fallback (DFS/UTS) is much faster than full transfer.
* r300g: unreference a zbuffer surface after decompressionMarek Olšák2011-05-091-0/+2
|
* r300g: remove redundant state variable hyperz_lockedMarek Olšák2011-05-095-14/+12
|
* r600g: anisotropic filtering support for evergreen hwJerome Glisse2011-05-095-23/+31
| | | | Signed-off-by: Jerome Glisse <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-30 10:43:21 +0000