summaryrefslogtreecommitdiff
path: root/src/amd/compiler/aco_instruction_selection_setup.cpp
Commit message (Expand)AuthorAgeFilesLines
* aco,radv: Use unified atomicsAlyssa Rosenzweig2023-05-121-54/+8
* aco: use apply_nuw_to_ssa() with load_smem_amdRhys Perry2023-04-191-1/+2
* aco: implement nir_bindless_image_atomic_inc/dec_wrapQiang Yu2023-04-191-0/+2
* aco: Remove setup_*_variables and add setup_lds_size instead.Timur Kristóf2023-04-121-77/+8
* ac, aco, radv: Clarify LDS size on GFX6, and NGG shaders.Timur Kristóf2023-04-121-5/+0
* aco: implement load_ray_launch_{id|size}Daniel Schürmann2023-03-161-0/+2
* aco: move rt_dynamic_callable_stack_base_amd to VGPRDaniel Schürmann2023-03-161-0/+1
* aco: add RT stage enumsDaniel Schürmann2023-03-161-1/+15
* aco, radv: Remove VS IO information from ACO.Timur Kristóf2023-03-151-42/+0
* aco: Implement load_typed_buffer_amd.Timur Kristóf2023-03-151-0/+1
* aco: Don't include headers from radv.Timur Kristóf2023-03-081-2/+1
* aco, radv: Don't use radv_shader_args in aco.Timur Kristóf2023-03-081-1/+1
* amd,nir: remove byte_permute_amd intrinsicGeorg Lehmann2023-02-221-1/+0
* nir: add assertions that loops don't have a Continue ConstructDaniel Schürmann2023-02-211-0/+1
* aco: remove early_rast wait insertQiang Yu2023-02-031-8/+0
* radv, aco, ac: Implement pack_half_2x16_rtz_split.Timur Kristóf2023-01-261-0/+1
* aco: add support for fp32 addition atomicsRhys Perry2023-01-171-0/+3
* aco: align scratch size during assemblyRhys Perry2023-01-091-2/+1
* aco/gfx11: reduce scratch allocation alignmentRhys Perry2023-01-091-1/+2
* aco: apply NUW to additions for scratch accessRhys Perry2022-12-061-0/+2
* radv,aco: remove old GS copy shader codeRhys Perry2022-11-291-19/+9
* nir,ac/nir,aco,radv: replace has_input_*_amd with more general intrinsicsRhys Perry2022-10-311-2/+0
* aco: remove invalid assertions for NGG streamoutSamuel Pitoiset2022-10-311-8/+0
* aco: implement NIR intrinsics for NGG streamoutSamuel Pitoiset2022-10-311-1/+2
* aco: Implement signed idot instructions on GFX11.Georg Lehmann2022-10-241-0/+2
* aco: remove unused isel_context::tcs_num_patchesSamuel Pitoiset2022-09-011-3/+0
* radv,aco: use pipe_format for static vertex input stateRhys Perry2022-08-301-22/+11
* aco: use std::vector::reserve() more oftenDaniel Schürmann2022-08-301-0/+4
* radv: stop duplicating radv_vs_output_infoSamuel Pitoiset2022-08-261-7/+8
* radv,aco: Don't lower and vectorize 16bit iabs.Georg Lehmann2022-07-201-0/+1
* aco: Remove dead nir_intrinsic_load_vertex_id caseKonstantin Seurer2022-07-191-1/+0
* aco: add support for compiling PS epilogsSamuel Pitoiset2022-07-181-1/+8
* radv,aco,ac/llvm: use nir_op_f{sin,cos}_amdRhys Perry2022-07-071-2/+2
* radv: vkCmdTraceRaysIndirect2KHRKonstantin Seurer2022-06-081-1/+1
* radv, aco: Packed usub_sat/isub_sat.Georg Lehmann2022-06-011-0/+2
* aco: remove unnecessary intrinsics that are lowered at the ABI levelSamuel Pitoiset2022-05-191-22/+0
* aco/radv: drop radv_nir_compiler_options from aco.Dave Airlie2022-05-171-1/+1
* amd: change chip_class naming to "enum amd_gfx_level gfx_level"Marek Olšák2022-05-131-6/+6
* radv,aco: Use ray_launch_size_addrKonstantin Seurer2022-05-121-1/+1
* aco/radv: convert to aco shader info at the radv level.Dave Airlie2022-05-111-1/+1
* aco: convert vs and so info over to aco structs.Dave Airlie2022-05-111-1/+1
* aco/info: reduce the gs ring info to what is needed.Dave Airlie2022-05-111-1/+1
* aco: move info pointer to a copy.Dave Airlie2022-05-111-19/+19
* aco: implement load_shared2_amd/store_shared2_amdRhys Perry2022-04-131-0/+1
* aco: remove old global access intrinsicsRhys Perry2022-04-131-14/+0
* aco: implement _amd global access intrinsicsRhys Perry2022-04-131-0/+13
* radv, aco: Packed iadd_sat/uadd_sat.Georg Lehmann2022-03-281-0/+2
* aco: Implement scalar iadd_sat.Georg Lehmann2022-03-281-1/+0
* radv: lower load_sample_mask_in in NIRSamuel Pitoiset2022-03-281-1/+0
* radv,aco: lower image descriptor loads in NIRRhys Perry2022-03-221-14/+14