summaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
* intel/compiler: Don't repeat dispatch max fixing conditionKenneth Graunke2019-05-141-2/+5
* intel/compiler: Rename invocation_id_mask to instance_id_maskKenneth Graunke2019-05-141-4/+4
* intel/compiler: Refactor TCS invocation ID setup into a helperKenneth Graunke2019-05-142-14/+23
* i965: Pass compiler to default key populatorsKenneth Graunke2019-05-1413-27/+37
* ac: use 1D GEPs for descriptors and constantsMarek Olšák2019-05-143-13/+12
* mesa: fix _mesa_max_texture_levels for GL_TEXTURE_EXTERNAL_OESMarek Olšák2019-05-141-1/+1
* freedreno: Restore msm_drm.h to a pristine "make headers_install" copy.Eric Anholt2019-05-141-1/+1
* freedreno: Move msm_drm.h to the same spot as other DRM uapi.Eric Anholt2019-05-147-6/+4
* nir/algebraic: Commute 1-fsat(a) to fsat(1-a) for all non-fmul instructionsIan Romanick2019-05-142-5/+24
* nir/algebraic: Eliminate useless fsat() on operand of comparison w/value in (...Ian Romanick2019-05-142-0/+57
* nir/algebraic: Strip double negatives from comparison sourcesIan Romanick2019-05-141-0/+28
* intel/compiler: Repeat nir_opt_algebraic_lateIan Romanick2019-05-142-1/+20
* Revert "nir: add late opt to turn inot/b2f combos back to bcsel"Ian Romanick2019-05-142-19/+0
* nir/algebraic: Eliminate a tautological compareIan Romanick2019-05-141-0/+7
* nir/algebraic: Simplify fsqrt domain guardIan Romanick2019-05-141-0/+1
* nir/search: Don't compare 8-bit or 1-bit constants with floatsIan Romanick2019-05-141-1/+12
* nir/algebraic: Recognize open-coded fsat with modifiersIan Romanick2019-05-141-0/+5
* nir/algebraic: Push unary operations into source operands of fsat sourceIan Romanick2019-05-142-1/+23
* nir/algebraic: Recognize open-coded flrp(a, b, fsat(c))Ian Romanick2019-05-141-3/+12
* intel/fs: Allow cmod propagation to instructions with saturate modifierIan Romanick2019-05-142-9/+528
* nir/algebraic: Add missing ffma(-1, a, b) patternIan Romanick2019-05-141-0/+1
* nir: Mark ffma as 2src_commutativeIan Romanick2019-05-142-17/+15
* nir: Add support for 2src_commutative ops that have 3 sourcesIan Romanick2019-05-143-9/+24
* nir: Rename commutative to 2src_commutativeIan Romanick2019-05-144-48/+60
* intel/fs/ra: Spill without destroying the interference graphJason Ekstrand2019-05-141-13/+96
* intel/fs/ra: Put the VGRFs at the end of the nodesJason Ekstrand2019-05-141-18/+32
* intel/fs/ra: Re-arrange interference setupJason Ekstrand2019-05-141-217/+205
* intel/fs/ra: Do the spill loop inside RAJason Ekstrand2019-05-142-21/+28
* intel/fs/ra: Only add MRF hack interference if we're spillingJason Ekstrand2019-05-141-62/+50
* intel/fs/ra: Pull the guts of RA into its own classJason Ekstrand2019-05-142-76/+103
* intel/fs/ra: Move assign_regs further down in the fileJason Ekstrand2019-05-141-70/+70
* intel/fs/ra: Split building the interference graph into a helperJason Ekstrand2019-05-141-23/+42
* intel/fs/ra: Initialize grf_used with first_non_payload_grfJason Ekstrand2019-05-141-1/+1
* intel/fs/ra: Stop adding RA interference to too many SENDS nodesJason Ekstrand2019-05-141-8/+3
* util/ra: Assert nodes are in-bounds in add_node_interferenceJason Ekstrand2019-05-141-0/+1
* intel/fs/ra: Only add dest interference to sources that existJason Ekstrand2019-05-141-1/+1
* util/ra: Don't destroy the graph in ra_allocate()Jason Ekstrand2019-05-141-76/+102
* util/ra: Add a helper for resetting a node's interferenceJason Ekstrand2019-05-142-0/+37
* util/ra: Add helpers for adding nodes to an interference graphJason Ekstrand2019-05-142-20/+72
* util/ralloc: Add helpers for growing zero-initialized memoryJason Ekstrand2019-05-142-0/+87
* intel/fs: Stop doing extra RA callsJason Ekstrand2019-05-141-19/+27
* util/ra: Improve the performance of ra_simplifyJason Ekstrand2019-05-141-30/+119
* util/ra: Only update q_total if the reg is not assignedJason Ekstrand2019-05-141-1/+1
* util/ra: Only update best_optimistic_node if !progressJason Ekstrand2019-05-141-1/+5
* util/ra: Make in_stack a bitset in the graphJason Ekstrand2019-05-141-18/+15
* util/ra: Get rid of tabsJason Ekstrand2019-05-142-28/+28
* virgl: clean up virgl_res_needs_flushChia-I Wu2019-05-141-2/+34
* virgl: comment on a sync issue in transfersChia-I Wu2019-05-142-0/+20
* virgl: PIPE_TRANSFER_READ does not imply flushChia-I Wu2019-05-141-4/+1
* virgl: do not skip readback because of explicit flushChia-I Wu2019-05-141-3/+0