summaryrefslogtreecommitdiff
path: root/src/gallium/drivers/llvmpipe
AgeCommit message (Collapse)Author
2010-01-03llvmpipe: Remove comma at end of enumerator list.Vinson Lee
2010-01-01llvmpipe: Silence uninitialized variable warning.Vinson Lee
2010-01-01llvmpipe: Use C-style comment.Vinson Lee
2009-12-28llvmpipe: Fix assert.Vinson Lee
2009-12-28llvmpipe: Silence compiler warnings.Vinson Lee
2009-12-28llvmpipe: Silence compiler warnings.Vinson Lee
2009-12-08Merge branch 'mesa_7_6_branch' into mesa_7_7_branchAndre Maasikas
2009-12-07llvmpipe: Initialize variables in emit_instruction.Vinson Lee
2009-11-10llvmpipe: Fix derived blend color state.José Fonseca
2009-11-09llvmpipe: Ensure stack variables in unit tests are properly aligned.José Fonseca
2009-11-06llvmpipe: Fix build with llvm 2.6.José Fonseca
Fixes bug 24949.
2009-11-03llvmpipe: Sanitise shader semantic and interpolator handling.Michal Krol
Handle the remaining semantic names and indices. Respect color interpolator when not flatshading. Based on Michal's softpipe commit eb699d64ec7057032139baccedcb0694ca41d706.
2009-11-03llvmpipe: remove old prim_setup draw stageKeith Whitwell
Everything now goes through the draw_vbuf handler, the same as regular drivers. Based on Keith's commit 4fe0fc3eba1f79beda890a5016359d549bab6ad4.
2009-11-03llvmpipe: Respect gl_rasterization_rules in primitive setup.José Fonseca
Based on Michal's identical commit for softpipe (ca9c413647bf9efb5ed770e3a655bc758075aec7).
2009-10-28llvmpipe: Make sure the JIT engine and X86 target are linked on MSVC build.José Fonseca
Basically mimic the llvm 2.6 way of linking execution engines and targets.
2009-10-28llvmpipe: Implement round() for MSVC.José Fonseca
2009-10-25llvmpipe: Human friendlier sampler state dump.José Fonseca
2009-10-25llvmpipe: Dump the sampler state of the shader key.José Fonseca
2009-10-25llvmpipe: Immediate multiplication.José Fonseca
2009-10-25llvmpipe: Fast path for sampling rgba8 textures with linear filtering.José Fonseca
Implement Keith's suggestion of doing most of the sampling with 16x8 and 8x16 AoS, and only doing the conversion to floating point SoA at the very last step. Improves gloss performance by 10%.
2009-10-25llvmpipe: Make lerping work for 8.8 fixed point values.José Fonseca
2009-10-25llvmpipe: New module to help make assertions about formats.José Fonseca
2009-10-25llvmpipe: New function to unpack rgba8 formats into 4 x u8n AoS.José Fonseca
2009-10-25llvmpipe: Split the format swizzling step from the unpacking.José Fonseca
2009-10-25llvmpipe: Allow different signs when unpacking.José Fonseca
2009-10-25llvmpipe: Add inlines to quickly generate types matching the native SIMD ↵José Fonseca
register bitwidth.
2009-10-25llvmpipe: Merge lp_build_load_rgba_soa into lp_build_sample_texel.José Fonseca
2009-10-25llvmpipe: Factor our pixel offset computation.José Fonseca
2009-10-25llvmpipe: Share testing infrastructure with lp_test_format.José Fonseca
2009-10-25llvmpipe: Eliminate lp_build_store_rgba_aos.José Fonseca
2009-10-25llvmpipe: Eliminate lp_build_load_rgba_aos.José Fonseca
2009-10-25llvmpipe: Move a few format/sampling functions into better space.José Fonseca
2009-10-23gallium: remove the swizzling parts of ExtSwizzleKeith Whitwell
These haven't been used by the mesa state tracker since the conversion to tgsi_ureg, and it seems that none of the other state trackers are using it either. This helps simplify one of the biggest suprises when starting off with TGSI shaders.
2009-10-23gallium: remove noise opcodesKeith Whitwell
Provide a dummy implementation in the GL state tracker (move 0.5 to the destination regs). At some point, a motivated person could add a better implementation of noise. Currently not even the nvidia binary drivers do anything more than this. In any case, the place to do this is in the GL state tracker, not the poor driver.
2009-10-22llvmpipe: Avoid yet another variable size array.José Fonseca
2009-10-22llvmpipe: Define rdtsc for MSVC.José Fonseca
2009-10-22llvmpipe: Avoid variable size arrays.José Fonseca
Not really variable size, but MSVC still doesn't like them.
2009-10-22llvmpipe: Use the pack/unpack functions for 8bit unsigned norm multiplication.José Fonseca
2009-10-22llvmpipe: Utility function to double the bit width of a type.José Fonseca
2009-10-22llvmpipe: Factor vector packing/unpacking to a separate source file.José Fonseca
These functions will be needed to implement many of the 8bit operations, and they are quite complex on its own.
2009-10-22llvmpipe: Call util_cpu_detect() from the unit tests.José Fonseca
2009-10-21llvmpipe: Remove extraneous name in lp_type pre-declaration.José Fonseca
2009-10-18llvmpipe: Allocate texture storage for whole quads.José Fonseca
2009-10-14llvmpipe: Use ALIGN_STACK.José Fonseca
2009-10-09llvmpipe: Eliminate constant mapping/unmapping.José Fonseca
2009-10-04llvmpipe: Ensure tile cache transfers are mapped before flushing it.José Fonseca
2009-10-04llvmpipe: Autogenerate lp_tile_soa.c from u_format.csv.José Fonseca
This is just a temporary change until we code generate the tile read/write functions in runtime. The new code avoids an extra memcpy that exists in u_tile.c functions, from which lp_tile_soa.c was originally based. This achieves up to 5% improvement, particularly in frames with little geometry overlap.
2009-10-04llvmpipe: Remove loop testing from format testing.José Fonseca
Loop building will be rewritten.
2009-10-04llvmpipe: Match header's protection macro with filename.José Fonseca
2009-10-04llvmpipe: Adjust format assertion.José Fonseca
We support array layout too -- if it has a single channel.