summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers
Commit message (Collapse)AuthorAgeFilesLines
* softpipe: fix glitch in texel lookups on fastpathsKeith Whitwell2009-08-201-64/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes two issues - firstly for mipmap levels with one or more dimensions smaller than tilesize, the code was sampling off the edge of the texture (but still within the tile). Secondly, in the linear_mipmap_linear case, both the default code and new fastpath were incorrect. This change fixes the fastpath and adds a comment to the default path, which still needs to be fixed. Basically the issue is that the coordinates in the smaller texture level are/were being computed by just dividing thecoordinates from the larger texture level by two, as in: x0[j] /= 2; y0[j] /= 2; x1[j] /= 2; y1[j] /= 2; The issues with this are signficant. Initially x1 is most often equal to x0+1, but after this, it will likely be equal to x0, so we will not actually be performing the linear blend within the smaller mipmap. The fastpath code avoided this (recalculated x1), but was still using the weighting factors from the larger mipmap level (xw, yw), which were incorrect. Change the fastpath code to do two full, independent linear samples of the two mipmap levels before blending. The default code needs to do the same thing.
* softpipe: optimized path for simple mipmap samplingKeith Whitwell2009-08-201-24/+71
| | | | | | | | | linear-mip-linear-repeat-POT sampling faspath, provides a very nice speedup to apps that do this common type of texturing. Test case: demos/terrain, turn fog off, turn texturing on. Without patch: 12 fps With patch: 20 fps.
* softpipe: move flatshade-first check out of loopKeith Whitwell2009-08-181-30/+50
|
* Revert "softpipe: rearrange blend fastpaths"Keith Whitwell2009-08-111-27/+55
| | | | | | | This reverts commit 1295cf423e21dad04a947960782ffa8db2739709. The original formulation was easier to understand & work with. Will revisit this later.
* softpipe: reduce textual differences between exec and sse shader pathsKeith Whitwell2009-08-112-32/+69
| | | | | Unshare one function (setup_pos_vector) as we want to push this code into the generated shader in the SSE case.
* softpipe: remove gallivm fragment shadersKeith Whitwell2009-08-113-211/+2
| | | | | However we do llvm integration, it will be different & more comprehensive than this.
* softpipe: setup quad outputs from with fs->runKeith Whitwell2009-07-303-36/+69
|
* softpipe: rearrange blend fastpathsKeith Whitwell2009-07-301-55/+27
|
* softpipe: add depth-lequal z16 pathKeith Whitwell2009-07-301-7/+100
|
* softpipe: remove unused variable in shade_quadKeith Whitwell2009-07-301-3/+0
|
* softpipe: fix off-by-one in nearest texcoord routinesKeith Whitwell2009-07-271-4/+4
| | | | Stray '- 0.5' copied from linear versions.
* softpipe: example fast paths for simple samplersKeith Whitwell2009-07-273-5/+333
| | | | | All these fastpaths are examples of the types of things we'd code-generate in a more sophisticated version of softpipe.
* softpipe: fastpath for interpolated z16 less depthtestingKeith Whitwell2009-07-271-4/+139
| | | | | | | Because this is interpolated (ie. early) depth, we can build in an assumption about the quads emitted by triangle setup, ie that they are actually linear spans. Interpolate z over those spans in z16 format to save on math & conversion.
* softpipe: cope with nr_cbufs == 0Keith Whitwell2009-07-271-3/+13
| | | | Disable blend code when no color buffer
* softpipe: move all depth/stencil/alpha pixel processing into one stageKeith Whitwell2009-07-2713-957/+580
|
* softpipe: fix error in scissor state dependenciesKeith Whitwell2009-07-251-2/+10
|
* softpipe: cleanup framebuffer state routine slightlyKeith Whitwell2009-07-251-40/+10
|
* softpipe: move all color-combine code into sp_quad_blend.cKeith Whitwell2009-07-2410-972/+727
| | | | | Consolidate the read-modify-write color combining code from the blend, colormask and output stages.
* softpipe: fix typoKeith Whitwell2009-07-241-1/+1
|
* softpipe: example fastpaths in blendingKeith Whitwell2009-07-241-11/+121
|
* softpipe: actually pass >1 quad from triangle routineKeith Whitwell2009-07-248-139/+135
| | | | First attempt
* softpipe: expand quad pipeline to process >1 quad at a timeKeith Whitwell2009-07-2414-633/+745
| | | | | | This is part one -- we still only pass a single quad down, but the code can now cope with more. The quads must all be from the same tile.
* softpipe: rip out old mulithread supportKeith Whitwell2009-07-244-305/+57
|
* softpipe: avoid flushing depth buffer cache on swapbuffersKeith Whitwell2009-07-232-9/+16
| | | | | | | | | There's no need to push out depth buffer contents on swapbuffers. Note that this change doesn't throw away depth buffer changes, it simply holds them in the cache over calls to swapbuffers. The hope is that swapbuffers will be followed by a clear() which means in that case we won't have to write the changes out.
* softpipe: also shortcircuit non-texture tile lookupsKeith Whitwell2009-07-232-18/+31
|
* softpipe: shortcircuit repeated lookups of the same tileKeith Whitwell2009-07-223-97/+156
| | | | | | | | | The sp_tile_cache is often called repeatedly to look up the same tile. Add a cache (to the cache) of the single tile most recently retreived and make a quick inline check to see if this matches the subsequent request. Add a tile_address bitfield struct to make this check easier.
* softpipe: remove unused vars in sp_setup.cKeith Whitwell2009-07-221-5/+0
|
* softpipe: use bitwise logic to setup quad masks in sp_setupKeith Whitwell2009-07-221-25/+40
|
* softpipe: simplify flush_spansKeith Whitwell2009-07-221-53/+19
| | | | No loss of performance, but simpler code.
* softpipe: make some small steps to flush texture cache less frequentlyKeith Whitwell2009-07-226-35/+70
| | | | No performance gain yet, but the code is a bit cleaner.
* softpipe: remove backwards dependency from tilecache to softpipeKeith Whitwell2009-07-2214-65/+62
| | | | | | | | The tile cache is a utility, it shouldn't know anything about the entity which is making use of it (ie softpipe). Remove softpipe parameter to all the tilecache function calls, and also remove the need to keep a softpipe pointer in the sampler structs.
* gallium: simplify tgsi_full_immediate structKeith Whitwell2009-07-2211-35/+34
| | | | | | | | | | | | | Remove the need to have a pointer in this struct by just including the immediate data inline. Having a pointer in the struct introduces complications like needing to alloc/free the data pointed to, uncertainty about who owns the data, etc. There doesn't seem to be a need for it, and it is unlikely to make much difference plus or minus to performance. Added some asserts as we now will trip up on immediates with more than four elements. There were actually already quite a few such asserts, but the >4 case could be used in the future to specify indexable immediate ranges, such as lookup tables.
* gallium/trace: Fix SCons build.Michel Dänzer2009-07-201-0/+1
|
* r300g: Guard R500 register writes by is_r500 check.Michel Dänzer2009-07-201-3/+5
| | | | | Flagged by the DRM command stream checker. This allows the driver to work on non-R500 cards.
* Merge branch 'mesa_7_5_branch'Brian Paul2009-07-171-12/+30
|\ | | | | | | | | | | | | | | | | | | | | Conflicts: Makefile progs/glsl/multitex.c src/mesa/main/enums.c src/mesa/main/state.c src/mesa/main/texenvprogram.c src/mesa/main/version.h
| * softpipe: limit blend results to [0,1]Luca Barbieri2009-07-151-12/+30
| |
* | tgsi: initial texturing support on sse pathKeith Whitwell2009-07-161-0/+1
| | | | | | | | | | Most obvious problem is drawpixels comes out blocky, but this may be an existing issue of KIL on the sse path.
* | tgsi: reduce x86 reg usage in tgsi_sse generated programsKeith Whitwell2009-07-161-18/+5
| | | | | | | | | | | | Pass the tgsi_exec_machine struct in directly and just hold a single pointer to this struct, rather than keeping one for each of its internal members.
* | gallium: proper constructor and destructor for tgsi_exec_machineKeith Whitwell2009-07-161-13/+17
| | | | | | | | | | Centralize the creation, initialization and destruction of this struct. Use align_malloc instead of home-brew alternatives.
* | gallium: Define PIPE_CAP_BLEND_EQUATION_SEPARATE, remove extension from ↵Patrice Mandin2009-07-147-0/+14
| | | | | | | | default extension list
* | r300g: Small compile warning fixes.Nicolai Hähnle2009-07-133-2/+5
| | | | | | | | Signed-off-by: Corbin Simpson <[email protected]>
* | r300g, radeon: Whitespace fixes.Nicolai Hähnle2009-07-131-1/+1
| | | | | | | | Signed-off-by: Corbin Simpson <[email protected]>
* | r300g: Use align() instead of inline maths.Corbin Simpson2009-07-131-4/+7
| |
* | r300g: Remove VAP_CNTL_STATUS from invariant state.Corbin Simpson2009-07-081-6/+1
| | | | | | | | Seriously.
* | r300g: Disable MSPOS registers for glisse's CS security checker.Corbin Simpson2009-07-081-4/+7
| | | | | | | | These will come back in someday, when we can properly use them.
* | r300-gallium: Unify sampler and texture emit.Corbin Simpson2009-07-083-39/+26
| | | | | | | | They have to cross into each other's registers.
* | r300-gallium: Mipmap setup.Corbin Simpson2009-07-082-10/+19
| | | | | | | | (cherry picked from commit 88c01a15da5639dd68a6a0133724994cb66f1316)
* | r300g: Add endian fix to vertex fetcher setup.Corbin Simpson2009-07-081-2/+9
| | | | | | | | As reported and initially tested by MrCooper.
* | Merge branch 'mesa_7_5_branch'Jakob Bornecrantz2009-07-032-15/+13
|\| | | | | | | | | | | Conflicts: src/mesa/main/dlist.c src/mesa/vbo/vbo_save_api.c
| * gallium: fix the front face semanticsZack Rusin2009-07-012-15/+13
| | | | | | | | | | | | | | | | mesa allocates both frontface and pointcoord registers within the fog coordinate register, by using swizzling. to make it cleaner and easier for drivers we want each of them in its own register. so when doing compilation from the mesa IR to tgsi allocate new registers for both and add new semantics to the respective declarations.
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 08:32:45 +0000