aco: implement some exclusive scans with inclusive scans
[platform/upstream/mesa.git] / src / amd / compiler / aco_instruction_selection.cpp
2023-09-02 Georg Lehmannaco: implement some exclusive scans with inclusive...
2023-09-01 Konstantin Seureraco: Unify demote and demote_if selection
2023-09-01 Konstantin Seureraco: Use bytes() instead of size() in emit_wqm
2023-09-01 Samuel Pitoisetaco: allow separate compilation of NGG shaders
2023-09-01 Samuel Pitoisetaco: flag blocks with long-jump as export_end for separ...
2023-08-31 Qiang Yuaco: add vs prolog instruction selection for radeonsi
2023-08-31 Qiang Yuaco: prepare fix_ls_vgpr_init_bug to be used by gl...
2023-08-31 Qiang Yuaco: pass sw_stage when setup_isel_context
2023-08-29 Samuel Pitoisetaco: fix emitting TCS epilogs end on GFX9+
2023-08-25 Samuel Pitoisetaco: add support for compiling {VS,TES}+GS separately...
2023-08-25 Samuel Pitoisetaco: add support for compiling VS+TCS separately on...
2023-08-25 Samuel Pitoisetaco: disable shared VGPRs for non-monolithic shaders...
2023-08-23 Georg Lehmannaco: fix u2f16 with 32bit input
2023-08-23 Rhys Perryaco: clarify bpermute pseudo opcode names
2023-08-22 Konstantin Seureraco: Do not fixup registers if there are no shader...
2023-08-22 Samuel Pitoisetaco: implement create_tcs_jump_to_epilog()
2023-08-22 Samuel Pitoisetaco: adjust TCS epilogs for RADV
2023-08-22 Samuel Pitoisetaco: fix jumping from main TCS to epilog on GFX9+
2023-08-16 Qiang Yuaco: use semantic location as io temp index
2023-08-16 Qiang Yuaco: skip scratch init when no scratch arg provide
2023-08-16 Qiang Yuaco: don't emit s_endpgm for tcs with epilog
2023-08-16 Qiang Yuaco: add tcs epilog generation for radeonsi
2023-08-16 Qiang Yuaco: allow tcs with epilog to keep nir store output...
2023-08-16 Qiang Yuaco: add tcs end regs for epilog usage
2023-08-16 Qiang Yuaco: move jump to epilog out of ic_merged_wave_info
2023-08-15 Faith Ekstrandnir: Rename nir_instr_type_ssa_undef to nir_instr_type_...
2023-08-15 Konstantin Seurerradv/rt: Rename shader_pc and next_shader
2023-08-14 Faith Ekstrandnir: Drop nir_dest
2023-08-14 Faith Ekstrandnir: Drop nir_alu_dest
2023-08-14 Faith Ekstrandnir: Get rid of nir_dest_is_divergent()
2023-08-12 Alyssa Rosenzweignir: Drop "SSA" from NIR language
2023-08-11 Georg Lehmannaco: always use rtne for fquantize2f16
2023-08-03 Alyssa Rosenzweigaco: Remove is_ssa check
2023-08-02 Samuel Pitoisetradv,aco: move has_epilog to radv_shader_info
2023-08-02 Samuel Pitoisetaco: add infra for compiling TCS epilogs
2023-08-02 Qiang Yuaco: extract aco_compile_shader_part from aco_compile_p...
2023-08-01 Alyssa Rosenzweignir: Rename scoped_barrier -> barrier
2023-08-01 Georg Lehmannaco: fix non constant 16bit bitnz/bitz
2023-08-01 Georg Lehmannaco/gfx11: use v_cmp_class_f16 with opsel for bitnz...
2023-07-28 Timur Kristófaco: Refactor select_program to smaller functions.
2023-07-24 Qiang Yuaco,radv: replace tess_input_vertices shader info param
2023-07-22 Bas Nieuwenhuizenaco: Fix some constant patterns in 16-bit vec4 construc...
2023-07-22 Bas Nieuwenhuizenaco: fix nir_op_vec8/16 with 16-bit elements.
2023-07-14 Timur Kristófaco: Remove subgroup_id and num_subgroups intrinsics.
2023-07-14 Timur Kristófaco: Fix subgroup_id intrinsic on GFX10.3+.
2023-07-03 Rhys Perryaco: remove 64-bit integer conversion opcodes
2023-06-30 Rhys Perryaco,ac/llvm,ac/nir,vtn: unify cube opcodes
2023-06-29 Georg Lehmannaco: implement nir_op_bitz/bitnz
2023-06-27 Rhys Perrynir,aco: add INCLUDE_HELPERS index to reduce intrinsic
2023-06-27 Rhys Perryaco: include helpers in emit_uniform_{reduce,scan}
2023-06-26 Vitaliy Triang3l... aco: Implement fragment shader interlock intrinsics
2023-06-26 Vitaliy Triang3l... aco: Add Primitive Ordered Pixel Shading waitcnt rules
2023-06-23 Timur Kristófaco: Use ac_hw_stage instead of aco-specific HWStage.
2023-06-19 Caio Oliveiracompiler: Move from nir_scope to mesa_scope
2023-06-16 Eric Engestromaco: reformat according to its .clang-format
2023-06-10 Konstantin Seureraco/rt: Do not initialize the next shader addr
2023-06-08 Rhys Perryaco: mask bits source of s_bfe
2023-06-08 Yonggang Luoutil: use uint32_t as the parameter of align function
2023-06-08 Daniel Schürmannaco: adjust RT prolog for shader functions [disables RT]
2023-06-08 Daniel Schürmannradv/rt: set up RT shader args for separate compilation
2023-06-08 Daniel Schürmannaco: implement select_program_rt()
2023-06-08 Daniel Schürmannaco: implement nir_intrinsic_load_resume_shader_address_amd
2023-06-08 Daniel Schürmannnir,amd: add nir_intrinsic_store_[scalar|vector]_arg_am...
2023-06-08 Daniel Schürmannradv: add remaining RT shader args for separate compilation
2023-06-07 Rhys Perryaco: remove memory_barrier_buffer implementation
2023-06-05 Rhys Perryaco: fix has_color_exports=true for mrtz exports
2023-06-02 Qiang Yuaco: use ac_get_image_dim for array check when image...
2023-06-02 Qiang Yuaco: implement nir_bindless_image_fragment_mask_load_amd
2023-06-02 Qiang Yuaco: implement nir_xfb_counter_sub_amd
2023-06-02 Qiang Yuaco: use gds reg when ordered xfb counter add
2023-06-02 Qiang Yuaco: implement load buffer with ACCESS_USES_FORMAT_AMD
2023-06-02 Qiang Yuaco: implement two load lds ngg intrininsic for radeonsi
2023-05-31 Georg Lehmannaco: cleanup v_cmp_class usage
2023-05-31 Samuel Pitoisetaco: remove nir_intrinsic_load_barycentric_at_sample...
2023-05-30 Chia-I Wuaco: fix alignment check in emit_load
2023-05-25 Rhys Perryaco: implement texture samples with strict WQM coordinates
2023-05-25 Rhys Perryaco: implement strict_wqm_coord_amd
2023-05-25 Rhys Perryaco: add MIMG_instruction::strict_wqm
2023-05-25 Rhys Perryradv,radeonsi: use ac_nir_lower_tex
2023-05-25 Rhys Perrynir,vtn,aco,ac/llvm: make cube_face_coord_amd more...
2023-05-16 Georg Lehmannaco: emit_wqm on MIMG dst, not operands
2023-05-12 Marek Olšákaco: don't treat ACCESS_NON_READABLE as ACCESS_COHERENT
2023-05-12 Alyssa Rosenzweigaco,radv: Use unified atomics
2023-05-04 Timur Kristófamd: Cleanup old GS intrinsics code.
2023-05-04 Timur Kristófac/nir: Emit legacy GS DONE signal in NIR.
2023-05-04 Timur Kristófamd: Add and implement gs_wave_id sysval.
2023-05-04 Timur Kristófamd: Add and implement sendmsg_amd intrinsic.
2023-05-04 Marek Olšáknir: rename ACCESS_STREAM_CACHE_POLICY -> ACCESS_NON_TE...
2023-04-28 Qiang Yuaco: get scratch addr from symbol for radeonsi
2023-04-26 Qiang Yuaco,radv: remove unused aco compile options
2023-04-26 Qiang Yuaco,ac/llvm,radv,radeonsi: handle ps bc optimization...
2023-04-26 Qiang Yuaco,radv: lower outputs to exports when nir for monolit...
2023-04-26 Qiang Yuaco: support nir_export_amd with ps targets
2023-04-26 Qiang Yuaco: implement nir_export_dual_src_blend_amd
2023-04-26 Qiang Yuaco: move create_fs_dual_src_export_gfx11 above
2023-04-20 Qiang Yuaco: fix nir_f2u64 translation
2023-04-19 Rhys Perryaco: remove SMEM_instruction::prevent_overflow
2023-04-19 Qiang Yuaco: skip scratch buffer init when its arg is not used
2023-04-19 Qiang Yuaco: implement nir_bindless_image_atomic_inc/dec_wrap
2023-04-19 Qiang Yuaco: support 32bit address in nir_load_smem_amd
next