Age | Commit message (Collapse) | Author | |
---|---|---|---|
2010-06-09 | intel: Use the blitter to upload TexSubImage data to busy textures. | Eric Anholt | |
This avoids many pipeline stalls in cairo-gl. [ # ] backend test min(s) median(s) stddev. count Before: [ 0] gl firefox-talos-gfx 36.799 36.851 2.34% 3/3 [ 0] gl firefox-talos-svg 33.429 35.360 3.46% 3/3 After: [ 0] gl firefox-talos-gfx 35.895 36.250 0.48% 3/3 [ 0] gl firefox-talos-svg 26.669 29.888 5.34% 3/3 This doesn't avoid all the pipeline stalls because the kernel reports !busy for buffers on the flushing list. That should be fixed in .36. | |||
2010-06-09 | i965: Avoid calloc/free in the CURBE upload process. | Eric Anholt | |
In exchange we end up with an extra memcpy, but that seems better than calloc/free. Each buffer is 4k maximum, and on the i965-streaming branch this allocation was showing up as the top entry in brw_validate_state profiling for cairo-gl. | |||
2010-06-09 | r300g: try harder to create a transfer object | Marek Olšák | |
I was told this wouldn't help to fix the FDO bug #28443, but still, it's a harmless last resort. Also, linear textures safely fallback to an unpipelined transfer here. | |||
2010-06-09 | draw: make sure geometry shader correctly iterates the output buffer | Zack Rusin | |
2010-06-09 | r300g: debug output texture size | Marek Olšák | |
2010-06-09 | r300g: return NULL texture early if buffer_create fails | Marek Olšák | |
2010-06-09 | draw: make sure the buffer is big enough to fit everything emitted by the gs | Zack Rusin | |
2010-06-09 | llvmpipe: fix copy & paste bug in clear logic | Roland Scheidegger | |
fixes bug 28450. | |||
2010-06-09 | draw: fix geometry shader which emit multiplie primitives | Zack Rusin | |
2010-06-09 | graw: add a multiple primitive geometry shader test | Zack Rusin | |
2010-06-09 | nv: fix compile after the latest gs changes | Zack Rusin | |
2010-06-09 | geometry shaders: make gs work with changable primitives and variable number ↵ | Zack Rusin | |
of vertices lots and lots of fixes for geometry shaders. in particular now we work when the gs emits a different primitive than the one the pipeline was started with and also we work when gs emits more vertices than would fit in the original buffer. | |||
2010-06-09 | xorg/vmwgfx: Disable 3D by default. | Thomas Hellstrom | |
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> | |||
2010-06-09 | st/xorg: Add a customizable option to disable 3D. | Thomas Hellstrom | |
If no customizer is present, 3D will be enabled by default. Otherwise the option will default to the customizer value. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> | |||
2010-06-09 | nvfx: fix typo from gallium-msaa merge | Ben Skeggs | |
2010-06-09 | nv50: fix typo from gallium-msaa merge | Ben Skeggs | |
2010-06-09 | nv50: use MARK_RING correctly | Ben Skeggs | |
2010-06-08 | draw: Remove unnecessary headers. | Vinson Lee | |
2010-06-09 | r600g: save vertex buffers in blitter | Marek Olšák | |
2010-06-09 | r300g: save vertex buffers in blitter | Marek Olšák | |
2010-06-09 | util: reference vertex buffers in blitter | Marek Olšák | |
2010-06-09 | r300g: report that transfers are always supported | Marek Olšák | |
2010-06-09 | r300g: fix loading compressed textures | Marek Olšák | |
2010-06-08 | r300g: skip rendering for unsupported vertex formats instead of aborting | Marek Olšák | |
The next step is to replace skipping by an actual fallback. | |||
2010-06-08 | intel: Flag NEW_BUFFERS when changing draw buffers. | Eric Anholt | |
There were entries to this function (most imporantly, prepare_render -> update_renderbuffers) that wouldn't have had NEW_BUFFERS set, but brw_wm_surface_state (the i965 state tracking the drawing regions) expected this to change. | |||
2010-06-08 | intel: Convert remaining dri_bo_emit_reloc to drm_intel_bo_emit_reloc. | Eric Anholt | |
The new API makes so much more sense, I'd like to forget how the old one worked. | |||
2010-06-08 | intel: Change dri_bo_* to drm_intel_bo* to consistently use new API. | Eric Anholt | |
The slightly less mechanical change of converting the emit_reloc calls will follow. | |||
2010-06-08 | intel: Clean up stale comments in intel_batchbuffer.c. | Eric Anholt | |
2010-06-08 | intel: Remove the non-gem paths for batchbuffer upload. | Eric Anholt | |
2010-06-08 | intel: Update comment in intel_tex_copy from before miptree x/y rework. | Eric Anholt | |
2010-06-08 | softpipe: make sure we don't fallback to assert on so stats query | Zack Rusin | |
spotted by Vinson | |||
2010-06-08 | softpipe: make sure that invalid calls to sosettargets don't crash us | Zack Rusin | |
2010-06-08 | r600: Make next_inst() static. | Henri Verbeet | |
2010-06-08 | r600: Assert output registers have a valid export index. | Henri Verbeet | |
2010-06-08 | r600: Process exports for all written fragment outputs. | Henri Verbeet | |
2010-06-08 | r600: Fill uiFP_OutputMap for all written fragment outputs. | Henri Verbeet | |
2010-06-08 | SConscript: don't build mesa components if mesa not in state trackers | Keith Whitwell | |
2010-06-08 | softpipe: added sp_state_so.c to file list | Brian Paul | |
2010-06-08 | gallium: scream when one of two unimplemented features in draw is used | Zack Rusin | |
plus used the correctly specified stride | |||
2010-06-08 | gallium: add basic support for stream output queries | Zack Rusin | |
2010-06-08 | gallium: adjust the query interface to support custom types | Zack Rusin | |
we need to change it to support composite types | |||
2010-06-08 | gallium: rename draw_auto to draw_stream_output, plus fix a comment | Zack Rusin | |
Brian spotted those | |||
2010-06-08 | gallium: make draw auto work and add relevant caps and docs | Zack Rusin | |
2010-06-08 | gallium: add interface for DrawAuto and implement it in softpipe | Zack Rusin | |
2010-06-08 | gallium: a lot more complete implementation of stream output | Zack Rusin | |
interface wise we have everything needed by d3d10 and gl transform feedback. the draw module misses implementation of some corner cases (e.g. when stream output wants different number of components per output than normal rendering paths) | |||
2010-06-08 | gallium: basic and initial implementation of the stream output interface | Zack Rusin | |
aka transform feedback | |||
2010-06-08 | st/mesa: attempt to fix TFP by using sampler views (v1) | Dave Airlie | |
Okay I think this is good enough for now, I can't see any other reason for mesa to want to use a sampler view so lets just leave it at all the A->X conversions for now. I've been running gnome-shell under r300g with this for day or so and it seems fine. Signed-off-by: Dave Airlie <airlied@redhat.com> | |||
2010-06-08 | llvmpipe: Add geom shader file to make build | Jakob Bornecrantz | |
2010-06-07 | graw: Fix file handle leaks. | Vinson Lee | |
2010-06-07 | graw: Remove unnecessary headers. | Vinson Lee | |