path: root/src/mesa/drivers/dri/i965/brw_fs.cpp
AgeCommit message (Expand)AuthorFilesLines
2017-03-13i965: Move the back-end compiler to src/intel/compilerJason Ekstrand1-6805/+0
2017-03-13i965: remove unused brw_program.h includeEmil Velikov1-1/+0
2017-03-13i965: remove unused brw_cs.h includeEmil Velikov1-1/+0
2017-03-01i965: Move intel_debug.h to intel/common/gen_debug.hJason Ekstrand1-1/+1
2017-03-01i965: Reduce cross-pollination between the DRI driver and compilerJason Ekstrand1-1/+1
2017-03-01i965: Move brw_register_blocks to brw_fs.cppJason Ekstrand1-0/+11
2017-03-01i965: Move SHADER_TIME_STRIDE to brw_compiler.hJason Ekstrand1-1/+1
2017-03-01i965/fs: detect different bit size accesses to uniforms to push them in prope...Samuel Iglesias Gonsálvez1-16/+34
2017-03-01i965/fs: mark last DF uniform array element as 64 bit live oneSamuel Iglesias Gonsálvez1-0/+3
2017-01-20i965: Avoid int64 induced warningsDave Airlie1-0/+2
2017-01-13i965: Move Gen4-5 interpolation stuff to brw_wm_prog_data.Kenneth Graunke1-1/+8
2017-01-10compiler: Merge shader_info's tcs and tes structs.Kenneth Graunke1-3/+3
2017-01-09nir/i965: use two slots from inputs_read for dvec3/dvec4 vertex input attributesJuan A. Suarez Romero1-13/+0
2016-12-23nir: pass compiler rather than devinfo to functions that call nir_optimizeTimothy Arceri1-6/+4
2016-12-14i965/fs: Fetch one cacheline of pull constants at a time.Francisco Jerez1-12/+9
2016-12-14i965/fs: Expose arbitrary pull constant load sizes to the IR.Francisco Jerez1-1/+1
2016-12-14i965/fs: Switch to the constant cache for uniform pull constants.Francisco Jerez1-34/+8
2016-12-12treewide: s/comparitor/comparator/Ilia Mirkin1-2/+2
2016-12-12i965/fs: Rename opt_copy_propagate -> opt_copy_propagation.Matt Turner1-5/+5
2016-12-07i965: enable INTEL_conservative_rasterization on Gen9+Lionel Landwerlin1-0/+1
2016-12-07i965: Add i965 plumbing for ARB_post_depth_coverage for i965 (gen9+).Plamena Manolova1-0/+1
2016-11-29i965/fs: Refactor handling of constant tg4 offsetsJason Ekstrand1-10/+9
2016-11-08i965: Fix GPU hang related to multiple render targets and alpha testingAnuj Phogat1-0/+6
2016-10-26i965: rewrite brw_setup_vue_interpolation()Timothy Arceri1-2/+2
2016-10-26nir/i965/anv/radv/gallium: make shader info a pointerTimothy Arceri1-42/+43
2016-10-24i965: Don't use nir_assign_var_locations for VS/TES/GS outputs.Kenneth Graunke1-13/+0
2016-10-24i965: Make split_virtual_grfs() call compact_virtual_grfs().Kenneth Graunke1-0/+6
2016-10-05i965: Introduce downcast helpers for prog_data structures.Kenneth Graunke1-24/+19
2016-10-05i965: add MAYBE_UNUSED to assert paramTimothy Arceri1-1/+1
2016-10-02i965: Drop pointless stage == MESA_SHADER_FRAGMENT checks.Kenneth Graunke1-5/+1
2016-09-21i965/ir: Test thread dispatch packing assumptions.Francisco Jerez1-0/+30
2016-09-21i965/ir: Skip eliminate_find_live_channel() for stages with sparse thread dis...Francisco Jerez1-0/+8
2016-09-21i965/reg: Make brw_sr0_reg take a subnr and return a vec1 regJason Ekstrand1-1/+1
2016-09-15i965/nir: Roll set_default_interpolation into lower_fs_inputsJason Ekstrand1-39/+1
2016-09-15i965/fs: Use NIR for handling forced per-sample interpolationJason Ekstrand1-37/+3
2016-09-15i965/fs: Use sample interpolation for interpolateAtCentroid in persample modeJason Ekstrand1-0/+26
2016-09-14i965/ir: Update several stale comments.Francisco Jerez1-11/+7
2016-09-14i965/ir: Don't print ARF subnr values twice.Francisco Jerez1-4/+0
2016-09-14i965/fs: Print fs_reg::offset field consistently for all register files.Francisco Jerez1-16/+22
2016-09-14i965/fs: Get rid of fs_inst::set_smear().Francisco Jerez1-26/+12
2016-09-14i965/fs: Use region_contained_in() in compute-to-mrf coalescing pass.Francisco Jerez1-3/+2
2016-09-14i965/fs: Simplify a bunch of fs_inst::size_written calculations by using comp...Francisco Jerez1-1/+1
2016-09-14i965/fs: Simplify and fix buggy stride/offset calculations using subscript().Francisco Jerez1-50/+15
2016-09-14i965/fs: Simplify get_fpu_lowered_simd_width() by using inequalities instead ...Francisco Jerez1-2/+2
2016-09-14i965/fs: Fix signedness of the return value of fs_inst::size_read().Francisco Jerez1-1/+1
2016-09-14i965/fs: Switch mask_relative_to() used in compute-to-mrf to byte units.Francisco Jerez1-10/+10
2016-09-14i965/fs: Fix bogus sub-MRF offset calculation in compute-to-mrf.Francisco Jerez1-6/+6
2016-09-14i965/fs: Take into account copy register offset during compute-to-mrf.Francisco Jerez1-1/+1
2016-09-14i965/fs: Drop fs_inst::overwrites_reg() in favor of regions_overlap().Francisco Jerez1-6/+0
2016-09-14i965/fs: Don't consider LOAD_PAYLOAD with stride > 1 source to behave like a ...Francisco Jerez1-1/+1