summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers
Commit message (Collapse)AuthorAgeFilesLines
* llvmpipe: count/report time spent in LLVM compilationsBrian Paul2010-01-273-4/+24
|
* llvmpipe: use some local vars to index step arraysBrian Paul2010-01-211-4/+6
| | | | Saves a few more cycles.
* llvmpipe: s/inline/INLINE/Brian Paul2010-01-211-1/+1
|
* llvmpipe: consolidate lp_scene_alloc_aligned() callsBrian Paul2010-01-211-13/+41
| | | | Use just one call instead of four. Good for a few more fps.
* llvmpipe: re-use a1 var in linear_coef()Brian Paul2010-01-211-1/+1
|
* llvmpipe: area is an int here, not floatBrian Paul2010-01-211-4/+4
|
* llvmpipe: manually unroll the inputs.step[] setup codeBrian Paul2010-01-211-18/+31
| | | | Good for a few more fps in some tests.
* llvmpipe: added simple perf/statistics counting facilityBrian Paul2010-01-2111-6/+189
| | | | | | | | Currently counting number of tris, how many tiles of each size are fully covered, partially covered or empty, etc. Set LP_DEBUG=counters to enable. Results are printed upon context destruction.
* llvmpipe: optimize tile writing codeBrian Paul2010-01-201-18/+109
| | | | | | | The code which converts/copies color tiles to the linear layout has been rewritten. There's less arithmetic and better loop unrolling, and possibly a better memory access pattern. Some demos, like gears, are about 20% faster now.
* llvmpipe: remove tile clipping codeBrian Paul2010-01-201-20/+0
| | | | The surface is always a multiple of the tile size now.
* llvmpipe: align display target size to multiple of tile sizeBrian Paul2010-01-201-7/+13
| | | | This will allow us to skip clipping tiles to surface bounds.
* llvmpipe: put TILE_SIZE #define in its own headerBrian Paul2010-01-202-11/+43
| | | | To avoid including lp_tile_soa.h in other places.
* llvmpipe: add makefile rule for generating .s filesBrian Paul2010-01-201-0/+5
|
* llvmpipe: updated commentBrian Paul2010-01-201-0/+2
|
* llvmpipe: asst. task-related clean-upsBrian Paul2010-01-191-22/+29
|
* llvmpipe: fix-up commentBrian Paul2010-01-191-1/+2
|
* llvmpipe: re-order file list, fix indentationBrian Paul2010-01-192-9/+9
|
* llvmpipe: remove unneeded DEBUG checks, use step varBrian Paul2010-01-191-5/+1
|
* llvmpipe: updated commentsBrian Paul2010-01-191-2/+4
|
* llvmpipe: tweak a commentBrian Paul2010-01-181-1/+1
|
* llvmpipe: added show_tiles and show_subtiles debug optionsBrian Paul2010-01-183-0/+65
| | | | | These options draw lines over the tiles to show the 64x64 tile bounds and 16x16 sub-tile bounds. For debugging/visualization.
* llvmpipe: use new u_ringbuffer for scene queueKeith Whitwell2010-01-174-89/+46
|
* Merge remote branch 'origin/master' into lp-binningJosé Fonseca2010-01-1674-838/+1822
|\ | | | | | | | | | | Conflicts: src/gallium/drivers/llvmpipe/lp_quad.h src/gallium/drivers/llvmpipe/lp_setup.c
| * nv50: fix tile flags for scanout tex usageChristoph Bumiller2010-01-161-1/+12
| |
| * nv50: handle all and more system valuesChristoph Bumiller2010-01-162-12/+110
| |
| * nv50: hook up geometry programsChristoph Bumiller2010-01-167-27/+103
| |
| * nv50: support for geometry programs in nv50_programChristoph Bumiller2010-01-165-119/+341
| |
| * nv50: get access to primitive input spaceChristoph Bumiller2010-01-161-88/+197
| | | | | | | | | | | | | | | | | | | | | | Vertex data in geometry programs is located in p[] space. The base address in p[] for vertex i is located in vertex attribute space, i.e. a[i << 2]. This means p[] is always accessed with an address register, and I had to to mess with their allocation once again. Also fixes negative offsets e.g. CONST[ADDR[0].x - 3].
| * nouveau: nv30: Remove useless variables fs, txp. Also do not change txf, as ↵Patrice Mandin2010-01-151-9/+1
| | | | | | | | | | | | bit 13 is in the texture format Signed-off-by: Patrice Mandin <[email protected]>
| * Merge branch 'gallium-noconstbuf'Roland Scheidegger2010-01-1530-98/+98
| |\ | | | | | | | | | | | | | | | Conflicts: src/gallium/drivers/softpipe/sp_draw_arrays.c src/mesa/state_tracker/st_draw_feedback.c
| | * gallium: remove const qualifier from pipe_buffer argument in set_constant_bufferRoland Scheidegger2010-01-1119-19/+19
| | |
| | * gallium: adapt drivers to pipe_constant_buffer removalRoland Scheidegger2009-12-2430-96/+96
| | |
| * | Merge branch 'mesa_7_7_branch'Jakob Bornecrantz2010-01-143-3/+8
| |\ \ | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: src/gallium/auxiliary/pipebuffer/pb_buffer_fenced.c src/gallium/auxiliary/util/Makefile src/gallium/drivers/r300/r300_state_derived.c
| | * | svga: Fix compile_vs error code.José Fonseca2010-01-132-3/+7
| | | | | | | | | | | | | | | | | | | | | | | | It could erroneously return PIPE_OK in some circumstances. Make compile_fs code identical.
| | * | r300g: Silence unused variable warnings.Vinson Lee2010-01-082-1/+2
| | | |
| * | | Merge branch 'instanced-arrays'Michal Krol2010-01-144-44/+162
| |\ \ \ | | | | | | | | | | | | | | | | | | | | Conflicts: src/gallium/drivers/softpipe/sp_draw_arrays.c
| | * | | svga: Fix call to translate::run().Michal Krol2010-01-131-1/+1
| | | | |
| | * | | gallium: draw_arrays/elements_instanced() are of type void.Michal Krol2010-01-122-24/+24
| | | | |
| | * | | Merge branch 'master' into instanced-arraysMichal Krol2010-01-05117-871/+1654
| | |\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: src/gallium/auxiliary/tgsi/tgsi_dump.c src/gallium/include/pipe/p_shader_tokens.h
| | * | | | Add lame support for instanceID to draw module.Michal Krol2009-12-301-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | It's all screaming for integer support -- fake it with float for now.
| | * | | | sp: Generalise drawing code to remove dupes.Michal Krol2009-12-301-81/+84
| | | | | | | | | | | | | | | | | | | | | | | | Also, avoid nested draw calls from simpler versions.
| | * | | | sp: Implement draw_elements_instanced().Michal Krol2009-12-303-2/+55
| | | | | |
| | * | | | Implement draw_arrays_instanced() in softpipe.Michal Krol2009-12-294-0/+61
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Modify the translate module to respect instance divisors and accept instance id as a parameter to calculate input vertex offset.
| * | | | | r300g: Cleanup from last few commits.Corbin Simpson2010-01-141-5/+1
| | | | | | | | | | | | | | | | | | | | | | | | Strangely enough, the code solidified pretty quickly.
| * | | | | r300g: Really destroy translated buffer at the end.Łukasz Krotowski2010-01-141-3/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Note that indexSize is changed by r300_translate_elts(). Also make sure it's destroyed on errors.
| * | | | | r300g: Use indices to translate index buffers of ubytes.Corbin Simpson2010-01-131-7/+58
| | | | | | | | | | | | | | | | | | | | | | | | progs/redbook/aapoly, among others, works fine now.
| * | | | | r300g: Disable immediate mode rendering for now.Corbin Simpson2010-01-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | Will re-enable when the bugs are ironed out.
| * | | | | r300g: Account for CS space used per atom.Corbin Simpson2010-01-134-18/+55
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Oh yeah, those atoms are startin' to pay off. The main obstacle now for OA playability is the absurdly low default mouse sensitivity, IMO. Not totally smooth yet, but getting there.
| * | | | | r300g: Two dirty state optimizations.Corbin Simpson2010-01-131-8/+6
| | | | | |
| * | | | | r300g: DCE in emit.Corbin Simpson2010-01-131-26/+0
| | | | | |
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-13 23:53:41 +0000