Age | Commit message (Collapse) | Author | |
---|---|---|---|
2009-12-16 | llvmpipe: do final the pixel in/out triangle test in the fragment shader | Brian Paul | |
The test to determine which of the pixels in a 2x2 quad is now done in the fragment shader rather than in the calling C code. This is a little faster but there's a few more things to do. Note that the step[] array elements are in a different order now. Rather than being in row-major order for the 4x4 grid, they're in "quad-major" order. The setup of the step arrays is a little more complicated now. So is the course/intermediate tile test code, but some lookup tables help with that. Next steps: - early-cull 2x2 quads which are totally outside the triangle. - skip the in/out test for fully contained quads - make the in/out comparison code tighter/faster. | |||
2009-12-16 | llvmpipe: added lp_build_int32_vec4_type() | Brian Paul | |
2009-12-16 | llvmpipe: refactor lp_build_cmp() to use lp_build_compare() | Brian Paul | |
2009-12-15 | llvmpipe: tighten up an assertion | Brian Paul | |
2009-12-15 | llvmpipe: use 1ULL to be ready for 64-bit arithmetic someday | Brian Paul | |
2009-12-14 | llvmpipe: fix broken TGSI_OPCODE_FRC codegen | Brian Paul | |
2009-12-14 | llvmpipe: fix broken lp_build_abs() | Brian Paul | |
2009-12-14 | llvmpipe: update file list in Makefile | Brian Paul | |
2009-12-13 | llvmpipe: rename bins to scene | Keith Whitwell | |
It was pretty confusing having an entity named "bin" and another named "bins", not least because sometimes there was a need to talk about >1 of the "bins" objects, which couldn't be pluralized any further... Scene is a term used in a bunch of places to talk about what a binner operates on, so it's a decent choice here. | |||
2009-12-12 | llvmpipe: rename queue size to count | Keith Whitwell | |
2009-12-12 | llvmpipe: rename one of the two rasterize_bins functions | Keith Whitwell | |
2009-12-11 | llvmpipe: checkpoint: plug in the new fencing code | Brian Paul | |
This has only been very lightly tested. More work to come. | |||
2009-12-11 | llvmpipe: added lp_rast_fence() bin function | Brian Paul | |
2009-12-11 | llvmpipe: added lp_rast_get_num_threads() | Brian Paul | |
2009-12-11 | llvmpipe: added lp_bin_get_num_bins() | Brian Paul | |
2009-12-11 | llvmpipe: remove old fence code, compile new lp_fence.c file | Brian Paul | |
2009-12-11 | llvmpipe: initial fence implementation | Brian Paul | |
2009-12-11 | llvmpipe: implement lp_rast_load_color() | Brian Paul | |
2009-12-11 | llvmpipe: checkpoint: more thread/queuing changes | Brian Paul | |
Now mapping/unmapping the framebuffer is done by a rasteizer thread rather than the main calling thread. | |||
2009-12-11 | gallium: comments and minor re-org in p_thread.h | Brian Paul | |
There's more work to do in this file: 1. Implement condvars for Windows via Win32 CONDITION_VARIABLE type. 2. Implement barriers for Windows 3. Try to get rid of PIPE_THREAD_HAVE_CONDVAR (only used in trace driver) 4. Why the 2 in _P_THREAD2_H_? | |||
2009-12-11 | gallium: added pipe_barrier type and functions | Brian Paul | |
2009-12-11 | llvmpipe: remove unused lp_rasterizer::fb field | Brian Paul | |
2009-12-11 | llvmpipe: improve framebuffer/surface code | Brian Paul | |
2009-12-11 | llvmpipe: fix-up #includes | Brian Paul | |
2009-12-11 | llvmpipe: fix inverted util_framebuffer_state_equal() result | Brian Paul | |
2009-12-11 | gallium/util: added util_unreference_framebuffer_state() | Brian Paul | |
2009-12-11 | gallium/util: simplify util_framebuffer_state_equal() | Brian Paul | |
And copy width, height in util_copy_framebuffer_state(). | |||
2009-12-11 | llvmpipe: remove unused fb parameter | Brian Paul | |
2009-12-11 | llvmpipe: minor comment fix | Brian Paul | |
2009-12-10 | llvmpipe: checkpoint: use empty/full bin queues | Brian Paul | |
2009-12-10 | llvmpipe: updated comment | Brian Paul | |
2009-12-10 | llvmpipe: simplify llvmpipe_set_framebuffer_state() | Brian Paul | |
2009-12-10 | gallium/util: added framebuffer compare, copy util funcs | Brian Paul | |
2009-12-10 | llvmpipe: added some bin queue debug code | Brian Paul | |
2009-12-10 | llvmpipe: updated comments | Brian Paul | |
2009-12-09 | llvmpipe: added some debug/info code | Brian Paul | |
2009-12-09 | llvmpipe: simplify the tiles_x, tiles_y code a bit | Brian Paul | |
2009-12-09 | llvmpipe: use the empty_bins queue now | Brian Paul | |
2009-12-09 | llvmpipe: checkpoint: begin plugging in bin queue code | Brian Paul | |
2009-12-09 | llvmpipe: added new lp_bin_queue.[ch] files | Brian Paul | |
The queues will be used for keeping track of full and empty bins so we can overlap setup with the rasterization threads. | |||
2009-12-09 | llvmpipe: use new lp_setup_get_current_bins() function | Brian Paul | |
This stub function will interface to the queue system... | |||
2009-12-09 | llvmpipe: more bin functions for create/destroy/queries | Brian Paul | |
2009-12-08 | llvmpipe: Use number of CPUs as default number of threads. | José Fonseca | |
Also bump MAX_THREADS to 8. | |||
2009-12-07 | llvmpipe: remove some left-over debug code | Brian Paul | |
2009-12-07 | llvmpipe: implement threaded rasterization | Brian Paul | |
The LP_NUM_THREADS env var controls how many threads are created. The default (and max) is 4, for now. If LP_NUM_THREADS = 0, threading is not used. | |||
2009-12-07 | gallium: added pipe_semaphore and related code | Brian Paul | |
2009-12-07 | llvmpipe: repartition lp_rasterizer state for threading | Brian Paul | |
Some of the state is per-thread. Put that state in new lp_rasterizer_task struct. | |||
2009-12-07 | llvmpipe: use bin iteration functions when rasterizing bins | Brian Paul | |
2009-12-07 | llvmpipe: introduce mutex and bin iteration functions | Brian Paul | |
2009-12-04 | llvmpipe: still more bin code reorganization | Brian Paul | |
Move tiles_x,y fields from setup state into bin state. Move more bin-adding commands into lp_bin.[ch]. |