summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2010-01-27llvmpipe: added debug option to disable LLVM optimization passesBrian Paul
2010-01-27llvmpipe: count/report time spent in LLVM compilationsBrian Paul
2010-01-27gallium/util: comments for time-related functionsBrian Paul
2010-01-27gallium/util: print dlerror() info upon dlopen() failureBrian Paul
2010-01-21llvmpipe: use some local vars to index step arraysBrian Paul
Saves a few more cycles.
2010-01-21llvmpipe: s/inline/INLINE/Brian Paul
2010-01-21llvmpipe: consolidate lp_scene_alloc_aligned() callsBrian Paul
Use just one call instead of four. Good for a few more fps.
2010-01-21llvmpipe: re-use a1 var in linear_coef()Brian Paul
2010-01-21llvmpipe: area is an int here, not floatBrian Paul
2010-01-21llvmpipe: manually unroll the inputs.step[] setup codeBrian Paul
Good for a few more fps in some tests.
2010-01-21progs/demos: call glutDestroyWindow() upon exitBrian Paul
2010-01-21llvmpipe: added simple perf/statistics counting facilityBrian Paul
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.
2010-01-20llvmpipe: optimize tile writing codeBrian Paul
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.
2010-01-20llvmpipe: remove tile clipping codeBrian Paul
The surface is always a multiple of the tile size now.
2010-01-20llvmpipe: align display target size to multiple of tile sizeBrian Paul
This will allow us to skip clipping tiles to surface bounds.
2010-01-20llvmpipe: put TILE_SIZE #define in its own headerBrian Paul
To avoid including lp_tile_soa.h in other places.
2010-01-20llvmpipe: add makefile rule for generating .s filesBrian Paul
2010-01-20llvmpipe: updated commentBrian Paul
2010-01-19llvmpipe: asst. task-related clean-upsBrian Paul
2010-01-19llvmpipe: fix-up commentBrian Paul
2010-01-19llvmpipe: re-order file list, fix indentationBrian Paul
2010-01-19llvmpipe: remove unneeded DEBUG checks, use step varBrian Paul
2010-01-19llvmpipe: updated commentsBrian Paul
2010-01-18llvmpipe: tweak a commentBrian Paul
2010-01-18util: fix broken util_ringbuffer_dequeue()Brian Paul
The tests for an empty ring buffer were incorrect. Fixes glxinfo segfaults. Plus, add a new assertion.
2010-01-18llvmpipe: added show_tiles and show_subtiles debug optionsBrian Paul
These options draw lines over the tiles to show the 64x64 tile bounds and 16x16 sub-tile bounds. For debugging/visualization.
2010-01-17llvmpipe: use new u_ringbuffer for scene queueKeith Whitwell
2010-01-16Merge remote branch 'origin/master' into lp-binningJosé Fonseca
Conflicts: src/gallium/drivers/llvmpipe/lp_quad.h src/gallium/drivers/llvmpipe/lp_setup.c
2010-01-16util: add generic ringbuffer utitiltyKeith Whitwell
2010-01-16gallium: Fix uninitialized instance divisor and index.Chia-I Wu
2010-01-16nv50: fix tile flags for scanout tex usageChristoph Bumiller
2010-01-16nv50: handle all and more system valuesChristoph Bumiller
2010-01-16nv50: hook up geometry programsChristoph Bumiller
2010-01-16nv50: support for geometry programs in nv50_programChristoph Bumiller
2010-01-16nv50: get access to primitive input spaceChristoph Bumiller
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].
2010-01-16r600: remove stray END_BATCH in blit codeAlex Deucher
2010-01-16draw: Fix memory leak in gs codeJakob Bornecrantz
2010-01-16i965g: make xorg state tracker build i965g_drv.soDave Airlie
don't make modesetting_drv.so anymore
2010-01-15r600: improve blit supportAlex Deucher
- fill in more src/dst formats - disable depth copies for now - set proper data formats in render target regs - fill in additional default state The swizzles on some of the less used mesa formats are probably wrong.
2010-01-15r600: add initial blit supportAndre Maasikas
2010-01-15r600: add r600_blit.cAlex Deucher
Unfinished.
2010-01-15nouveau: nv30: Remove useless variables fs, txp. Also do not change txf, as ↵Patrice Mandin
bit 13 is in the texture format Signed-off-by: Patrice Mandin <patmandin@gmail.com>
2010-01-15llvmpipe: implement scissor test in triangle setupBrian Paul
2010-01-15llvmpipe: remove lp_rast_triangle::min/max fieldsBrian Paul
These values aren't needed outside the do_triangle_ccw() function.
2010-01-15llvmpipe: skip 4x4 in/out test codeBrian Paul
It's a litte faster to just do the in/out testing in the shader jit code.
2010-01-15llvmpipe: added comment about lookup-tables vs. computationBrian Paul
2010-01-15llvmpipe: change 'in' to boolean, add commentsBrian Paul
2010-01-15llvmpipe: generate two shader varients, one omits triangle in/out testingBrian Paul
When we know that a 4x4 pixel block is entirely inside of a triangle use the jit function which omits the in/out test code. Results in a few percent speedup in many tests.
2010-01-15util: Handle FORMAT_Z32_FLOAT in util_pack_z().Michal Krol
2010-01-15util: Handle the remaining formats in pipe_put_tile_rgba().Michal Krol