aboutsummaryrefslogtreecommitdiffstats
path: root/src/amd
Commit message (Expand)AuthorAgeFilesLines
* ac/nir, radv, radeonsi: Switch to using ac_shader_argsConnor Abbott2019-11-256-783/+843
* ac: Add a shared interface between radv, radeonsi, LLVM and ACOConnor Abbott2019-11-256-0/+273
* radv: Rename ac_arg_regfileConnor Abbott2019-11-251-2/+2
* ac/llvm: fix the local invocation index for wave32Samuel Pitoiset2019-11-251-0/+4
* radv: disable subgroup shuffle operations on GFX10Samuel Pitoiset2019-11-251-1/+2
* radv: create a fresh fork for each pipeline compileTimothy Arceri2019-11-252-14/+139
* radv: add a secure_compile_open_fifo_fds() helperTimothy Arceri2019-11-251-0/+43
* radv: add some infrastructure for fresh forks for each secure compileTimothy Arceri2019-11-251-1/+14
* aco: fix waitcnts for barriers at block endsRhys Perry2019-11-221-0/+3
* aco: fix copy+paste errorRhys Perry2019-11-211-2/+2
* aco: improve waitcnt insertion around loopsRhys Perry2019-11-211-45/+108
* radv: Enable Subgroup Arithmetic and Clustered for SIDaniel Schürmann2019-11-201-6/+5
* amd/llvm: Add Subgroup Scan functions for SIDaniel Schürmann2019-11-201-6/+75
* radv: enable VK_KHR_shader_subgroup_extended_types on GFX6-GFX7Samuel Pitoiset2019-11-201-1/+1
* radv: Do not change scratch settings while shaders are active.Bas Nieuwenhuizen2019-11-204-55/+105
* ac: fill num_rings for remaining IPsMarek Olšák2019-11-191-2/+16
* ac: add radeon_info::num_rings and move ring_type to amd_family.hMarek Olšák2019-11-196-20/+23
* nir: move data.image.access to data.accessMarek Olšák2019-11-193-5/+5
* radv/aco: enable VK_KHR_shader_subgroup_extended_typesRhys Perry2019-11-191-1/+1
* aco: implement 64-bit integer reductionsRhys Perry2019-11-193-10/+240
* aco: refactor reduction lowering helpersRhys Perry2019-11-191-174/+115
* radv: advertise VK_KHR_shader_subgroup_extended_types on GFX8-GFX9Samuel Pitoiset2019-11-192-0/+7
* ac: add 16-bit float support to ac_build_alu_op()Samuel Pitoiset2019-11-191-4/+5
* ac: add 8-bit and 16-bit supports to ac_build_optimization_barrier()Samuel Pitoiset2019-11-191-2/+13
* ac: add 8-bit and 16-bit supports to ac_build_wwm()Samuel Pitoiset2019-11-191-3/+18
* ac: add 8-bit and 16-bit supports to get_reduction_identity()Samuel Pitoiset2019-11-191-1/+33
* ac: add 8-bit and 16-bit supports to ac_build_swizzle()Samuel Pitoiset2019-11-191-6/+13
* ac: add 8-bit and 16-bit supports to ac_build_dpp()Samuel Pitoiset2019-11-191-13/+20
* ac: add 8-bit and 16-bit supports to ac_build_set_inactive()Samuel Pitoiset2019-11-191-0/+9
* ac: add 8-bit and 16-bit supports to ac_build_readlane()Samuel Pitoiset2019-11-191-6/+16
* ac: add 8-bit and 16-bit supports to ac_build_shuffle()Samuel Pitoiset2019-11-191-5/+10
* ac: remove useless cast in ac_build_set_inactive()Samuel Pitoiset2019-11-191-1/+2
* radv: implement VK_AMD_device_coherent_memorySamuel Pitoiset2019-11-183-15/+101
* ac: add radeon_info::has_l2_uncachedSamuel Pitoiset2019-11-182-0/+4
* aco: implement VK_KHR_shader_float_controlsRhys Perry2019-11-159-25/+227
* aco: fix 64-bit fsign with 0Rhys Perry2019-11-151-1/+1
* aco: don't combine literals into v_cndmask_b32/v_subb/v_addcRhys Perry2019-11-151-0/+6
* radv: enable FP16/FP64 denormals earlier and only for LLVMRhys Perry2019-11-151-14/+14
* radv: make sure to not clear the ds attachment after resolvesSamuel Pitoiset2019-11-151-0/+3
* radv: remove useless RADV_DEBUG=unsafemath debug optionSamuel Pitoiset2019-11-159-66/+29
* aco: Optimize out trivial code from uniform bools.Timur Kristóf2019-11-141-3/+27
* aco: Treat all booleans as per-lane.Timur Kristóf2019-11-143-287/+184
* aco: use s_and_b64 exec to reduce uniform booleans to one bitDaniel Schürmann2019-11-141-1/+3
* aco: Make sure not to mistakenly propagate 64-bit constants.Timur Kristóf2019-11-141-3/+3
* aco: value number instructions using the execution maskDaniel Schürmann2019-11-141-28/+51
* aco: check if SALU instructions are predeceeded by exec when calculating WQM ...Daniel Schürmann2019-11-143-10/+13
* ac: fix build with recent LLVMSamuel Pitoiset2019-11-141-0/+4
* 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
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-14 14:59:14 +0000