summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* llvmpipe: Fix build.José Fonseca2009-08-292-2/+2
|
* llvmpipe: Merge all pixel format related files.José Fonseca2009-08-296-255/+153
|
* llvmpipe: Factor out and optimize the input interpolation.José Fonseca2009-08-297-169/+521
| | | | | | | Special attention is given to the interpolation of side by side quads. Multiplications are made only for the first quad. Interpolation of inputs for posterior quads are done exclusively with additions, and perspective divide if necessary.
* llvmpipe: Pre-declare fetch_texel.José Fonseca2009-08-295-28/+66
|
* llvmpipe: Pass the alpha ref value and blend color in the jit context.José Fonseca2009-08-298-50/+86
|
* llvmpipe: Pass fragment context to generated function in a single structure.José Fonseca2009-08-298-33/+108
|
* llvmpipe: Structure manipulation helpers.José Fonseca2009-08-294-0/+119
|
* llvmpipe: Centralize the C <-> JIT interfaces in one place.José Fonseca2009-08-297-43/+153
|
* llvmpipe: Drop blend derived state.José Fonseca2009-08-294-161/+6
| | | | Already included in the fragment shader.
* llvmpipe: keep texture stride 16byte alignedKeith Whitwell2009-08-291-1/+1
| | | | Fixes crash when resizing gears window.
* llvmpipe: Squash the quad pipeline.José Fonseca2009-08-2910-351/+120
| | | | It had been reduced to one fixed stage.
* llvmpipe: s/uni/scalar/.José Fonseca2009-08-299-47/+47
| | | | More obvious name.
* llvmpipe: Add a bunch of comments.José Fonseca2009-08-2917-70/+346
| | | | Description/rationale/to-do items, while I still remember them...
* llvmpipe: Split off vs stuff from lp_state_fs.c.José Fonseca2009-08-294-60/+98
| | | | lp_state_fs.c is already too big without it.
* llvmpipe: Avoid duplicate clamping when converting between types.José Fonseca2009-08-291-8/+15
|
* llvmpipe: Generate the fragment pipeline into a single function.José Fonseca2009-08-2913-339/+327
| | | | Still hackish. Will document and optimize later.
* llvmpipe: Get conversions working correctly for all integer types.José Fonseca2009-08-295-83/+389
|
* llvmpipe: Delete the quad polygon stipple stage.José Fonseca2009-08-293-87/+0
| | | | Not used now -- stipple done by the draw module. May code generate later.
* llvmpipe: Early depth testing.José Fonseca2009-08-2911-46/+166
|
* llvmpipe: Disassemble beyond referred code beyond the RET instruction.José Fonseca2009-08-291-2/+32
|
* llvmpipe: Split control flow function declarations and notes.José Fonseca2009-08-2911-38/+91
|
* llvmpipe: Back port recent softpipe-opt improvements from Keith.José Fonseca2009-08-296-142/+466
|
* llvmpipe: Don't limit the number of tiles in the cache.José Fonseca2009-08-293-239/+96
|
* llvmpipe: Clean dead tile cache code.José Fonseca2009-08-292-28/+0
|
* llvmpipe: Simplify tile clears. Use pipe_fill_rect instead of scratch tile.José Fonseca2009-08-293-66/+39
|
* llvmpipe: Start hiding llvmpipe_cached_tile.José Fonseca2009-08-293-8/+8
|
* llvmpipe: Drop depth/stencil support from tile cache.José Fonseca2009-08-292-83/+18
|
* llvmpipe: Code generate the depth test, and include in the shader.José Fonseca2009-08-2914-869/+172
| | | | | Only 32bit depth/stencil surfaces supported for now. Stencil ops not implemented yet.
* llvmpipe: Update texture block from format.José Fonseca2009-08-291-0/+3
|
* llvmpipe: Depth test to LLVM IR translation.José Fonseca2009-08-294-2/+248
|
* llvmpipe: Centralize mask update logic.José Fonseca2009-08-297-34/+43
|
* llvmpipe: Clamped float to unsigned norm via mantissa manipulation.José Fonseca2009-08-293-17/+113
|
* llvmpipe: Several fixes of the conversion test.José Fonseca2009-08-294-34/+55
|
* llvmpipe: Generate instrinsics for integer comparisons.José Fonseca2009-08-291-0/+71
| | | | | It is a little messy, given the available instrucions form SIMD integer comparisons is rather limited.
* llvmpipe: Mention the ability to get microbenchmarks from the unit tests.José Fonseca2009-08-291-0/+4
| | | | Even better would be to have a -h/--help option to the tests...
* llvmpipe: Code generate alpha testing and append to generated fragment shader.José Fonseca2009-08-299-147/+279
|
* util: Dump PIPE_FUNC_x value names.José Fonseca2009-08-292-0/+29
|
* llvmpipe: frag shader commentsBrian Paul2009-08-291-5/+5
|
* llvmpipe: blend commentsBrian Paul2009-08-291-0/+7
|
* llvmpipe: comments about blend generatorBrian Paul2009-08-291-5/+11
|
* llvmpipe: basic commentsBrian Paul2009-08-291-0/+62
|
* llvmpipe: Hack to force the line/point rasterization also fit the blend ↵José Fonseca2009-08-291-16/+42
| | | | function expectations.
* llvmpipe: Refer my udis86 branch which decodes more opcodes.José Fonseca2009-08-291-2/+3
|
* llvmpipe: Code generate the position interpolation.José Fonseca2009-08-294-72/+98
|
* llvmpipe: Simpler variant of lp_build_broadcast_scalar.José Fonseca2009-08-292-0/+25
|
* llvmpipe: Put the position coefficients together with the inputs.José Fonseca2009-08-294-68/+65
| | | | | The automatic search'n'replace leaves lp_setup.c a bit ugly, but this code will be eventually code generated as well.
* llvmpipe: Implement saturation.José Fonseca2009-08-291-2/+7
|
* llvmpipe: Put color/depth directly into the quad structure.José Fonseca2009-08-293-54/+45
|
* llvmpipe: prefix point/line/tri_setup() functions with llvmpipe_Brian Paul2009-08-294-59/+59
| | | | Avoid symbol collisions with softpipe.
* llvmpipe: updated Makefile C_SOURCESBrian Paul2009-08-291-9/+20
|