summaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Expand)AuthorAgeFilesLines
* aco: combine read_invocation and shuffle implementationsRhys Perry2019-11-121-29/+7
* aco: don't propagate vgprs into v_readlane/v_writelaneRhys Perry2019-11-121-1/+8
* aco: fix read_invocation with VGPR lane indexRhys Perry2019-11-121-2/+1
* aco: fix shuffle with uniform operandsRhys Perry2019-11-121-6/+6
* aco: use DPP instead of exec modification when lowering GFX10 shufflesRhys Perry2019-11-121-15/+7
* aco: rematerialize s_movk instructionsDaniel Schürmann2019-11-121-2/+7
* aco: preserve kill flag on moved operands during RADaniel Schürmann2019-11-121-1/+1
* aco: fix invalid access on Pseudo_instructionsDaniel Schürmann2019-11-122-2/+10
* ac: handle pointer types to LDS in ac_get_elem_bits()Samuel Pitoiset2019-11-121-0/+5
* radv: fix radv secure compile feature breaks compilation on armhf EABI and aa...Luis Mendes2019-11-121-0/+8
* radv: fix radv_nir_get_max_workgroup_size when nir=NULLRhys Perry2019-11-111-1/+4
* ac: Handle invalid GFX10 format correctly in ac_get_tbuffer_format.Timur Kristóf2019-11-082-0/+6
* aco: add Instruction::usesModifiers() and add more checks in the optimizerRhys Perry2019-11-082-7/+23
* radv: adjust loop unrolling heuristics for int64Rhys Perry2019-11-072-7/+16
* radv/gfx10: fix primitive indices orientation for NGG GSSamuel Pitoiset2019-11-072-9/+45
* aco: workaround Tonga/Iceland hardware bugDaniel Schürmann2019-11-071-5/+5
* radv: implement VK_EXT_subgroup_size_controlSamuel Pitoiset2019-11-065-3/+59
* radv: rely on shader's wavesize when computing NGG infoSamuel Pitoiset2019-11-061-1/+10
* radv: determine shaders wavesize at pipeline levelSamuel Pitoiset2019-11-066-19/+28
* radv: hardcode the number of waves for the GFX6 LS-HS bugSamuel Pitoiset2019-11-061-1/+1
* radv/gfx10: enable wave32 for compute based on shader's wavesizeSamuel Pitoiset2019-11-063-3/+7
* radv: fix 32-bit compiler warningsSamuel Pitoiset2019-11-061-3/+3
* radv: add a note about perftest/debug optionsSamuel Pitoiset2019-11-061-0/+1
* meson: move the generic symbols check arguments to a common variableEric Engestrom2019-11-051-1/+1
* meson: add variable to control the symbols checksEric Engestrom2019-11-051-1/+1
* util: rename PIPE_ARCH_*_ENDIAN to UTIL_ARCH_*_ENDIANDylan Baker2019-11-054-7/+7
* util/u_endian: set PIPE_ARCH_*_ENDIAN to 1Dylan Baker2019-11-054-7/+7
* ac: add missing Arcturus to the info of pc linesLeo Liu2019-11-041-0/+2
* aco: fix accidential reordering of instructions when schedulingDaniel Schürmann2019-11-041-10/+47
* aco: only use single-dword loads/stores for spillingDaniel Schürmann2019-11-041-41/+10
* aco: fix immediate offset for spills if scratch is usedDaniel Schürmann2019-11-041-6/+6
* radv: fix compute pipeline keys when optimizations are disabledSamuel Pitoiset2019-11-041-2/+18
* radv: Close all unnecessary fds in secure compile.Bas Nieuwenhuizen2019-11-011-29/+64
* radv: drop unnecessary xmlpool_options_hEric Engestrom2019-10-311-1/+1
* radv: Fix disk_cache_get size argument.Bas Nieuwenhuizen2019-10-311-2/+2
* radv: Remove _mesa_locale_init/fini calls.Bas Nieuwenhuizen2019-10-311-3/+0
* android: aco: fix Lower to CSSAMauro Rossi2019-10-311-0/+1
* radv: declare NGG scratch for VS or TES and only on GFX10Samuel Pitoiset2019-10-311-5/+3
* radv: Fix timeout handling in syncobj wait.Bas Nieuwenhuizen2019-10-311-1/+1
* radv: Allocate space for temp. semaphore parts.Bas Nieuwenhuizen2019-10-301-0/+1
* aco: implement VGPR spillingDaniel Schürmann2019-10-301-7/+162
* aco: always set scratch_offset in startpgmDaniel Schürmann2019-10-303-23/+22
* aco: omit linear VGPRs as spill variablesDaniel Schürmann2019-10-301-4/+8
* aco: ensure that spilled VGPR reloads are done after p_logical_startDaniel Schürmann2019-10-301-34/+43
* aco: simplify calculation of target register pressure when spillingDaniel Schürmann2019-10-301-39/+12
* aco: fix new_demand calculation for first instructionsRhys Perry2019-10-301-4/+7
* aco: don't add interferences between spilled phi operandsDaniel Schürmann2019-10-301-8/+8
* aco: consider loop_exit blocks like merge blocks, even if they have only one ...Daniel Schürmann2019-10-301-2/+2
* aco: don't insert the exec mask into set of live-out variables when spillingDaniel Schürmann2019-10-301-14/+6
* aco: fix transitive affinities of spilled variablesDaniel Schürmann2019-10-301-25/+79
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 07:15:50 +0000