Age | Commit message (Collapse) | Author | |
---|---|---|---|
2009-08-29 | llvmpipe: Normalize the cycles with the number of channel. | José Fonseca | |
So that we have a comparable number for different formats. | |||
2009-08-29 | llvmpipe: Handle ubyte -> float conversion too. | José Fonseca | |
2009-08-29 | llvmpipe: Make lp_const_offset visible. | José Fonseca | |
2009-08-29 | llvmpipe: Only get the preprocessor flags from llvm-config. | José Fonseca | |
Otherwise we get -O2 optimization flag, preventing proper debugging. | |||
2009-08-29 | llvmpipe: Bootstrap type conversions. | José Fonseca | |
2009-08-29 | llvmpipe: Use same type for reference vectors. | José Fonseca | |
2009-08-29 | llvmpipe: Fix floating point const scale factor. | José Fonseca | |
2009-08-29 | llvmpipe: Factor out shared test code into a separate module. | José Fonseca | |
2009-08-29 | llvmpipe: Cleanup constant helpers. | José Fonseca | |
2009-08-29 | llvmpipe: Move intrinsic helpers to a separate module. | José Fonseca | |
2009-08-29 | llvmpipe: Collect richer blend data. | José Fonseca | |
2009-08-29 | llvmpipe: Some notes about PSHUF. | José Fonseca | |
2009-08-29 | llvmpipe: Optimize blend swizzles by using bitmasks instead of shuffles for ↵ | José Fonseca | |
ubytes. | |||
2009-08-29 | llvmpipe: Write data to a tsv file for posterior analysis. | José Fonseca | |
2009-08-29 | llvmpipe: Move p_build_context to lp_bld_type.h | José Fonseca | |
As it will be shared with more modules. | |||
2009-08-29 | llvmpipe: Don't use llvm.readcyclecounter. | José Fonseca | |
LLVM during optimization reorders the rdtsc instructions next to each other, which makes it pretty useless. | |||
2009-08-29 | llvmpipe: Separate constant building. | José Fonseca | |
2009-08-29 | llvmpipe: Move type support functions into a separate file. | José Fonseca | |
2009-08-29 | llvmpipe: Measure the number of cycles taken for blending. | José Fonseca | |
2009-08-29 | llvmpipe: Minor comments / debug mnemonics. | José Fonseca | |
2009-08-29 | llvmpipe: Optimize away min/max with equal operands. | José Fonseca | |
2009-08-29 | llvmpipe: Improve generated 8bit blending code. | José Fonseca | |
2009-08-29 | llvmpipe: Get blending of normalized 8bit unsigned integers working. | José Fonseca | |
2009-08-29 | llvmpipe: Specialize arithmetic operations. | José Fonseca | |
2009-08-29 | llvmpipe: Introduce a custom typing system. | José Fonseca | |
Straightforward representation of floating-point/fixed-point/integer, normalized/scaled, signed/unsigned SIMD vector types. | |||
2009-08-29 | llvmpipe: Avoid C99-isms. | José Fonseca | |
2009-08-29 | llvmpipe: Factor out intrisic calling code into a reusable function. | José Fonseca | |
2009-08-29 | llvmpipe: Cleanup test programs. | José Fonseca | |
2009-08-29 | llvmpipe: Blending. | José Fonseca | |
The code | |||
2009-08-29 | llvmpipe: Arithmetic helpers. | José Fonseca | |
2009-08-29 | llvmpipe: fastpath for interpolated z16 less depthtesting | Keith Whitwell | |
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. | |||
2009-08-29 | llvmpipe: cope with nr_cbufs == 0 | Keith Whitwell | |
Disable blend code when no color buffer | |||
2009-08-29 | llvmpipe: Translate logicops. | José Fonseca | |
2009-08-29 | llvmpipe: Separate pixel packing/unpacking from loading/storing. | José Fonseca | |
2009-08-29 | llvmpipe: Adjust for pixel layout changes. | José Fonseca | |
2009-08-29 | llvmpipe: Fix typo in copyright. | José Fonseca | |
2009-08-29 | llvmpipe: Add test cases for pixels. | José Fonseca | |
Actually some of this test cases need more testing... | |||
2009-08-29 | llvmpipe: Update SConscript. | José Fonseca | |
2009-08-29 | llvmpipe: Simple shell script to aid port softpipe changes to llvmpipe. | José Fonseca | |
2009-08-29 | llvmpipe: move all depth/stencil/alpha pixel processing into one stage | Keith Whitwell | |
2009-08-29 | llvmpipe: fix error in scissor state dependencies | Keith Whitwell | |
2009-08-29 | llvmpipe: cleanup framebuffer state routine slightly | Keith Whitwell | |
2009-08-29 | llvmpipe: move all color-combine code into lp_quad_blend.c | Keith Whitwell | |
Consolidate the read-modify-write color combining code from the blend, colormask and output stages. | |||
2009-08-29 | llvmpipe: fix typo | Keith Whitwell | |
2009-08-29 | llvmpipe: example fastpaths in blending | Keith Whitwell | |
2009-08-29 | llvmpipe: actually pass >1 quad from triangle routine | Keith Whitwell | |
First attempt | |||
2009-08-29 | llvmpipe: expand quad pipeline to process >1 quad at a time | Keith Whitwell | |
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. | |||
2009-08-29 | llvmpipe: rip out old mulithread support | Keith Whitwell | |
2009-08-29 | llvmpipe: avoid flushing depth buffer cache on swapbuffers | Keith Whitwell | |
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. | |||
2009-08-29 | llvmpipe: also shortcircuit non-texture tile lookups | Keith Whitwell | |