https://github.com/halide/Halide
- HEAD
- refs/heads/Halide_unsharp
- refs/heads/abadams/align_strided_const_loads
- refs/heads/abadams/alloca
- refs/heads/abadams/atomic_parallel_compiled_in
- refs/heads/abadams/atomic_vector_non_recursive
- refs/heads/abadams/averaging_tree
- refs/heads/abadams/avoid_name_mangling_in_cross_module_dependencies
- refs/heads/abadams/better_absd
- refs/heads/abadams/better_codegen_for_non_const_ramps
- refs/heads/abadams/bgu_cholesky
- refs/heads/abadams/braces_around_statements
- refs/heads/abadams/cache_tighten_producer_consumer_nodes
- refs/heads/abadams/check_reorder_dups
- refs/heads/abadams/clarify_broadcast_shuffle
- refs/heads/abadams/compositing_app
- refs/heads/abadams/cond_wait_spin
- refs/heads/abadams/cse_in_unroll_split_tuples
- refs/heads/abadams/custom_cuda_context
- refs/heads/abadams/custom_cuda_context_2
- refs/heads/abadams/custom_cuda_context_3
- refs/heads/abadams/d3d12abi
- refs/heads/abadams/deflake_mullapudi_reorder
- refs/heads/abadams/delete_prepare_for_early_exit
- refs/heads/abadams/depthwise_separable_conv
- refs/heads/abadams/diagnose_boundary_condition_failure
- refs/heads/abadams/disable_onnx_app_on_mac
- refs/heads/abadams/divide_using_pavgw
- refs/heads/abadams/dont_link_to_cudart
- refs/heads/abadams/dont_reinterpret_concat
- refs/heads/abadams/early_out
- refs/heads/abadams/enable_f16c
- refs/heads/abadams/extract_concat_bits
- refs/heads/abadams/fast_integer_divide_round_to_zero
- refs/heads/abadams/faster_runtime_integer_division
- refs/heads/abadams/faster_unroll
- refs/heads/abadams/fix-arm-seg2
- refs/heads/abadams/fix_4211
- refs/heads/abadams/fix_5323
- refs/heads/abadams/fix_5329
- refs/heads/abadams/fix_5889
- refs/heads/abadams/fix_6984
- refs/heads/abadams/fix_7229
- refs/heads/abadams/fix_7260
- refs/heads/abadams/fix_7365
- refs/heads/abadams/fix_7374
- refs/heads/abadams/fix_7504
- refs/heads/abadams/fix_7514
- refs/heads/abadams/fix_7531
- refs/heads/abadams/fix_7584
- refs/heads/abadams/fix_7584_v2
- refs/heads/abadams/fix_7742
- refs/heads/abadams/fix_7756
- refs/heads/abadams/fix_7761
- refs/heads/abadams/fix_7768
- refs/heads/abadams/fix_7786
- refs/heads/abadams/fix_7810
- refs/heads/abadams/fix_7811
- refs/heads/abadams/fix_7815
- refs/heads/abadams/fix_7867
- refs/heads/abadams/fix_7871
- refs/heads/abadams/fix_7872
- refs/heads/abadams/fix_7873
- refs/heads/abadams/fix_7888
- refs/heads/abadams/fix_7890
- refs/heads/abadams/fix_7891
- refs/heads/abadams/fix_7892
- refs/heads/abadams/fix_7893
- refs/heads/abadams/fix_7906
- refs/heads/abadams/fix_7909
- refs/heads/abadams/fix_7968
- refs/heads/abadams/fix_8038
- refs/heads/abadams/fix_8054
- refs/heads/abadams/fix_arm_fcvtmp
- refs/heads/abadams/fix_autoschedule_feature_transposition
- refs/heads/abadams/fix_cse_name_collisions
- refs/heads/abadams/fix_cuda_mat_mul_assert
- refs/heads/abadams/fix_deinterleave_bug
- refs/heads/abadams/fix_deinterleave_for_reinterpret
- refs/heads/abadams/fix_div_round_to_zero
- refs/heads/abadams/fix_fft_compile_time_regression
- refs/heads/abadams/fix_generate_output_snippets
- refs/heads/abadams/fix_if_nesting_condition
- refs/heads/abadams/fix_leaks_in_memoize_test
- refs/heads/abadams/fix_lgtm_warnings
- refs/heads/abadams/fix_links_to_master
- refs/heads/abadams/fix_load_of_broadcast
- refs/heads/abadams/fix_lossless_cast_of_sub
- refs/heads/abadams/fix_onnx_app
- refs/heads/abadams/fix_pointless_lower_condition
- refs/heads/abadams/fix_potential_gpu_deadlock
- refs/heads/abadams/fix_realize_condition_depends_on_tuple
- refs/heads/abadams/fix_reduce_expr_modulo_of_vector
- refs/heads/abadams/fix_riscv_vx_vi
- refs/heads/abadams/fix_round
- refs/heads/abadams/fix_stencil_chain_gpu_schedule
- refs/heads/abadams/fix_track_bounds_intervals
- refs/heads/abadams/fix_tutorial_2
- refs/heads/abadams/forward_partition_methods
- refs/heads/abadams/fully_fused_depthwise_separable_conv
- refs/heads/abadams/fuzz_sliding_window
- refs/heads/abadams/gaussian_blur_app
- refs/heads/abadams/generator_infinite_default_timeout
- refs/heads/abadams/gpu_autoscheduler_parallel_random_probes
- refs/heads/abadams/include_riscv_in_readme
- refs/heads/abadams/interleave_nested_vector
- refs/heads/abadams/ir_match_by_ref
- refs/heads/abadams/lerp_plus_cast
- refs/heads/abadams/local_laplacian_code_size
- refs/heads/abadams/lower_halving_sub
- refs/heads/abadams/lower_rounding_shift_right
- refs/heads/abadams/mac-arm-fixes
- refs/heads/abadams/make_fast_inverse_test_throughput_limited
- refs/heads/abadams/makefile_serialization_support
- refs/heads/abadams/mismatched_new_delete
- refs/heads/abadams/mixed_sign_mul_shift_right
- refs/heads/abadams/mixed_width_mul_shift_right
- refs/heads/abadams/multiple_scatter
- refs/heads/abadams/mux_intrinsic
- refs/heads/abadams/name_helpers
- refs/heads/abadams/narrow_predicates
- refs/heads/abadams/nested_vectorization_compile_time_regression_fix
- refs/heads/abadams/nested_vectorization_tweaks
- refs/heads/abadams/parallel_simd_op_check
- refs/heads/abadams/per_instance_profiling
- refs/heads/abadams/precompute_shared_mem_size
- refs/heads/abadams/prefer_no_gather
- refs/heads/abadams/print_uncaught_exception
- refs/heads/abadams/promote_fixed_point_intrinsics
- refs/heads/abadams/psabdw
- refs/heads/abadams/random_pipelines
- refs/heads/abadams/rationalize_gpu_for_loop_names
- refs/heads/abadams/reenable_unscheduled_stage_warning
- refs/heads/abadams/reinterpret_vector
- refs/heads/abadams/remove_arch_os_for_shaders
- refs/heads/abadams/remove_bad_pruning
- refs/heads/abadams/remove_parameter_self_references
- refs/heads/abadams/remove_readnone_on_functions
- refs/heads/abadams/remove_use_of_python_config_in_onnx_makefile
- refs/heads/abadams/reschedule_bgu
- refs/heads/abadams/reschedule_bilateral_grid
- refs/heads/abadams/rewrite_atomic_pass
- refs/heads/abadams/rounding_shift_right_use_average
- refs/heads/abadams/rungenmain_error
- refs/heads/abadams/sampling_profiler_overhead_v2
- refs/heads/abadams/scope_improvements
- refs/heads/abadams/simpler_broadcasts
- refs/heads/abadams/simplify_correlated_pyramid
- refs/heads/abadams/siotas_20
- refs/heads/abadams/sioutas_20
- refs/heads/abadams/slide_over_split_loop
- refs/heads/abadams/sorting_network_working_branch
- refs/heads/abadams/stable_topological_order
- refs/heads/abadams/string_view
- refs/heads/abadams/strip_asserts_last
- refs/heads/abadams/switch_stmt
- refs/heads/abadams/target_specific_lerp
- refs/heads/abadams/time_lowering_passes
- refs/heads/abadams/track_failedness_through_solver_lets
- refs/heads/abadams/turn_off_slp_vectorization_for_avx512
- refs/heads/abadams/tweak_unpack_buffers
- refs/heads/abadams/undo_pointless_widening
- refs/heads/abadams/unordered_blocks
- refs/heads/abadams/unsigned_demosaic
- refs/heads/abadams/update_makefile_for_llvm_19
- refs/heads/abadams/use_arm_for_runtime_triple
- refs/heads/abadams/use_pmaddubsw_for_downsample
- refs/heads/abadams/validate_gpu_schedules
- refs/heads/abadams/vector_reduce_hexagon_predicate
- refs/heads/abadams/vector_scan
- refs/heads/abadams/vst_type_fix
- refs/heads/abadams/widening_let_bug
- refs/heads/abadams/x86_avg
- refs/heads/abadams/zen4
- refs/heads/adadams/profile_allocator
- refs/heads/add_image_checks_after_bounds_inference_plus_new_rules
- refs/heads/add_outermost_to_extern
- refs/heads/add_vectorization_to_search_space
- refs/heads/aelphy/feature_cadence_changes
- refs/heads/aelphy/float_extracts
- refs/heads/align_loads_comment_fix
- refs/heads/alina-strided-store
- refs/heads/another_buffer_copy_fix
- refs/heads/arm_sve_redux
- refs/heads/ataei-block_asserts-codegen
- refs/heads/ataei-debug_info
- refs/heads/ataei-fix-pow
- refs/heads/ataei-gen_str_param
- refs/heads/ataei-implicit_lhs_vars
- refs/heads/ataei-onnx
- refs/heads/ataei-onnx_converter_update
- refs/heads/ataei-onnx_pybind
- refs/heads/ataei-resnet50_benchmarks
- refs/heads/ataei-standalone_autoscheduler
- refs/heads/ataei_lots_of_inputs
- refs/heads/auto_sched_benchmarks
- refs/heads/auto_sched_estimates
- refs/heads/auto_sched_inline
- refs/heads/auto_sched_test_notparallel
- refs/heads/autoschedule_top_down
- refs/heads/autoschedule_with_convnet
- refs/heads/autoscheduler_scalar_imageparam_fix
- refs/heads/backports/10.x
- refs/heads/backports/11.x
- refs/heads/backports/12.x
- refs/heads/backports/13.x
- refs/heads/balance_expressions
- refs/heads/bazel
- refs/heads/benchmarks
- refs/heads/blaze
- refs/heads/bounds_buffer_lets_fix
- refs/heads/bounds_correct_vs_bounds_loaded_reduced
- refs/heads/buffer_device_api_target
- refs/heads/bug_device_free
- refs/heads/bug_inline_unbounded
- refs/heads/build/fix-xcode-2
- refs/heads/build/manylinux-fixes
- refs/heads/circ_buffer
- refs/heads/cmake-no-runtime-debug-symbols
- refs/heads/cmake/asan
- refs/heads/cmake/deps-cleanup
- refs/heads/cmake/find-modules
- refs/heads/cmake/spirv
- refs/heads/cmake_wasm_features
- refs/heads/compute_at_guard_with_if_goes_on_stack
- refs/heads/compute_with_at
- refs/heads/compute_with_check
- refs/heads/compute_with_excessive_bounds
- refs/heads/compute_with_inlined
- refs/heads/compute_with_remove_is_right_level
- refs/heads/cpack/nuget
- refs/heads/ctest/wrappers
- refs/heads/cuda-constant
- refs/heads/d3d12-allocation-cache
- refs/heads/deferred_cse_after_inlining
- refs/heads/destructor_calls_deinit
- refs/heads/dg/deserialize_unmapped_objects
- refs/heads/dg/fix_vulkan_codegen_bool_conversion
- refs/heads/dg/vulkan_conform_api
- refs/heads/dg/vulkan_region_allocator_fixes
- refs/heads/dgerstmann/fix-vulkan-memory-config-init
- refs/heads/disable_acquire_release_test_vulkan
- refs/heads/distinct_wrapper_names
- refs/heads/dkg/6863_asan_fixes
- refs/heads/dkg/vulkan
- refs/heads/dpalermo_dmabuf
- refs/heads/dpalermo_dmabuf_libion
- refs/heads/dpalermo_hexagon_remote_202003
- refs/heads/dpalermo_sdk4_2_0_2
- refs/heads/ds/buffer-get-pure
- refs/heads/ds/opt-tile-size
- refs/heads/ds/tail-none
- refs/heads/ds/while
- refs/heads/dsharletg/bitwise-intrinsics
- refs/heads/dsharletg/find-vector-reduce
- refs/heads/dsharletg/jit-optimization
- refs/heads/dsharletg/memcpy-copy_from
- refs/heads/dsharletg/pattern-headroom
- refs/heads/dsharletg/refactor-host-alignment
- refs/heads/dsharletg/runtime-size
- refs/heads/dsharletg/simplify-abs
- refs/heads/dsharletg/simplify-type-bounds
- refs/heads/dsharletg/specialize-bounds
- refs/heads/dsharletg/upsample-channels
- refs/heads/empty_prefetch
- refs/heads/emscripten_vector_fix
- refs/heads/export_all-wsmoses
- refs/heads/expr_auto_sched
- refs/heads/extern_bugs
- refs/heads/extern_host_alloc
- refs/heads/factor_parallel_codegen_hack
- refs/heads/fast_sync_tsan
- refs/heads/faster_integer_division
- refs/heads/feature/apps-external
- refs/heads/feature/cmake-presets
- refs/heads/feature/convert
- refs/heads/feature/f16_interleave
- refs/heads/feature/gather_load_q7
- refs/heads/feature/llvm-codemodel
- refs/heads/feature/load_predicated
- refs/heads/feature/luma_regression
- refs/heads/feature/maintanence
- refs/heads/feature/reinterprets
- refs/heads/feature/tcm_bump_allocator
- refs/heads/feature/xtensa_fix_interleave_q8
- refs/heads/feature/xtensa_q8_tests
- refs/heads/find_intrinsics_issue
- refs/heads/find_intrinsics_widening_lets
- refs/heads/fix-floated-pure-stage
- refs/heads/fix-race-condition
- refs/heads/fix_hexagon_alignment
- refs/heads/fix_hvx_intrinsics
- refs/heads/fix_prefetch_test
- refs/heads/fix_windows_vs15_build
- refs/heads/fixed_length_vectors
- refs/heads/fixed_point_local_laplac
- refs/heads/gemmlowp
- refs/heads/generate
- refs/heads/gha/pip
- refs/heads/gpu_canon_fix
- refs/heads/halide_ir_flatbuffer
- refs/heads/hex_dma2_async
- refs/heads/hexagon_le_runtime
- refs/heads/hexagon_priority
- refs/heads/hexagon_setpriority
- refs/heads/hexagon_strided_pred_load
- refs/heads/hexagon_sysmon_markers
- refs/heads/imaging-synthesis
- refs/heads/includes_fix
- refs/heads/ios_fast_sync_fix
- refs/heads/jia-kai-fix-runtime-cuda-init
- refs/heads/kamil-openglcompute-infinity
- refs/heads/kamil/name_pthread_workers
- refs/heads/kp_bit_shift
- refs/heads/line_buffer
- refs/heads/loop_carry_not_working
- refs/heads/lower_on_huge_stack
- refs/heads/main
- refs/heads/master
- refs/heads/memoize_with_extents
- refs/heads/metal_float16
- refs/heads/metaprogrammed_simplifier_mod
- refs/heads/mohamedadaly-vmlal
- refs/heads/more_powerful_sliding
- refs/heads/new_autoschedule_with_new_simplifier_arm_worker_branch
- refs/heads/new_autoscheduler
- refs/heads/new_simplifier_rule_testing
- refs/heads/newer_ion_ioctl
- refs/heads/no_bounds_query_when_bounds_used
- refs/heads/opengl_compute_buffer_types_fix
- refs/heads/openglcompute_reuse_shared_allocations
- refs/heads/optmize_reorder
- refs/heads/par_for_opt
- refs/heads/pdb/fix_7806
- refs/heads/pdb/hexagon_remote_cmake
- refs/heads/pdb_add_libcpp_makefile_inc
- refs/heads/pdb_eliminate_interleaves_test
- refs/heads/pdb_fix_clang_build
- refs/heads/pdb_fix_install_qc
- refs/heads/pdb_fix_loop_carry
- refs/heads/pdb_fix_simd_op_check_hvx
- refs/heads/pdb_mul_div_mod_multi_thread
- refs/heads/pdb_remove_hvx_v64
- refs/heads/perform_inline_with_order
- refs/heads/pr/2572
- refs/heads/pr/2676
- refs/heads/pr/2975
- refs/heads/pr/3017
- refs/heads/pr/3081
- refs/heads/pr/3387
- refs/heads/pr/3939
- refs/heads/pr/3960
- refs/heads/pr/4380
- refs/heads/pr/4414
- refs/heads/pr/5331
- refs/heads/pr/5438
- refs/heads/pr/5455
- refs/heads/pr/5758_2
- refs/heads/predicated_vector
- refs/heads/prefetch_specialize
- refs/heads/print_schedule
- refs/heads/profile_hardware_counters
- refs/heads/random-pipelines
- refs/heads/rdom_with_pure_vars
- refs/heads/readme-fix-gcd
- refs/heads/realization_order
- refs/heads/refactor_module
- refs/heads/register_promotion
- refs/heads/release/10.x
- refs/heads/release/11.x
- refs/heads/release/12.x
- refs/heads/release/13.x
- refs/heads/release/14.x
- refs/heads/release/15.x
- refs/heads/release/16.x
- refs/heads/release/17.x
- refs/heads/release/8.x
- refs/heads/remove_max_on_fuse_factor
- refs/heads/reorder_rvar
- refs/heads/reset_unique_counter
- refs/heads/revert-3612-ataei-speedup_compiletime
- refs/heads/revert-7009-rootjalex/distribute-w_shl
- refs/heads/revert-7601-compile_hexagon_remote
- refs/heads/riscv_update
- refs/heads/rl_simplifier_rules
- refs/heads/rootjalex/add_simpl_rules
- refs/heads/rootjalex/arm-optimize
- refs/heads/rootjalex/autoscheduler_mcts
- refs/heads/rootjalex/bounds-rewriter
- refs/heads/rootjalex/bounds_synthesis
- refs/heads/rootjalex/cbounds
- refs/heads/rootjalex/cbounds_predicated
- refs/heads/rootjalex/fix-sat-overflow
- refs/heads/rootjalex/fix_estimate_issue
- refs/heads/rootjalex/fix_failed_unrolls
- refs/heads/rootjalex/gsoc_codegen
- refs/heads/rootjalex/improve_cbounds_fixed
- refs/heads/rootjalex/improve_constant_bounds
- refs/heads/rootjalex/pitchfork-arm
- refs/heads/rootjalex/reinterpret-simplify
- refs/heads/rootjalex/rts
- refs/heads/rootjalex/super_simplify_bounds
- refs/heads/rootjalex/test_cbounds_fixed
- refs/heads/rootjalex/test_constant_bounds
- refs/heads/rootjalex/trs-codegen
- refs/heads/rootjalex/trs-codegen-cross
- refs/heads/rootjalex/trs-merge
- refs/heads/rootjalex/uint32-int32-cast
- refs/heads/rootjalex/x86-hadds
- refs/heads/rootjalex/x86-optimize
- refs/heads/rootjalex/x86-optimize-test
- refs/heads/rootjalex/x86-sat
- refs/heads/rootjalex/x86-test
- refs/heads/rule_removal_experiments
- refs/heads/schedule-output-storage
- refs/heads/separate_bounds_query_entrypoint
- refs/heads/shallow
- refs/heads/shift_amount_type_change
- refs/heads/shoaibkamil/cmake-without-arm
- refs/heads/shoaibkamil/correct_memory_fences
- refs/heads/shoaibkamil/d3d-fixes
- refs/heads/shoaibkamil/deprecate_openglcompute
- refs/heads/shoaibkamil/json
- refs/heads/shoaibkamil/llvm_clone_tag
- refs/heads/shoaibkamil/minor-vcpkg-doc-change
- refs/heads/shoaibkamil/opengl_compute_tests
- refs/heads/shoaibkamil/performance_tests_as_generators
- refs/heads/shoaibkamil/rule_removal_experiments
- refs/heads/shoaibkamil/super_simplify_with_interpreter
- refs/heads/shoaibkamil/windows-arm-fix-attributes
- refs/heads/sim_shlib_addr_print
- refs/heads/simplify-nested-broadcasts
- refs/heads/simplify-vectorreduce-shuffles2
- refs/heads/simplify_mod
- refs/heads/sioutas_2020
- refs/heads/sioutas_2020_autoscheduler
- refs/heads/slomp/gpu-codegen-profiling
- refs/heads/slomp/msvc-static-analysis
- refs/heads/solve_div
- refs/heads/solve_div_master
- refs/heads/solve_div_simplifier_test
- refs/heads/sr/python-late-binding-defaults
- refs/heads/srj-aaa
- refs/heads/srj-alloc
- refs/heads/srj-alloca
- refs/heads/srj-appmake2
- refs/heads/srj-armv83a
- refs/heads/srj-aslog
- refs/heads/srj-assert
- refs/heads/srj-assoc
- refs/heads/srj-auto-multi
- refs/heads/srj-auto-multi2
- refs/heads/srj-auto_schedule_mat_mul
- refs/heads/srj-autosched
- refs/heads/srj-b2cpphide
- refs/heads/srj-barr
- refs/heads/srj-bits
- refs/heads/srj-blacklist
- refs/heads/srj-bounds
- refs/heads/srj-bufcalltype
- refs/heads/srj-bufcallwrap
- refs/heads/srj-bufcallwrap2
- refs/heads/srj-buffer
- refs/heads/srj-bv
- refs/heads/srj-classic-autotune
- refs/heads/srj-clean
- refs/heads/srj-constcall
- refs/heads/srj-crosscompile
- refs/heads/srj-ctlz
- refs/heads/srj-cvec-patch
- refs/heads/srj-dag
- refs/heads/srj-debug-to-file
- refs/heads/srj-deir
- refs/heads/srj-f16
- refs/heads/srj-fp16
- refs/heads/srj-fsch
- refs/heads/srj-fthru
- refs/heads/srj-g2
- refs/heads/srj-g3
- refs/heads/srj-gha-test-fixes
- refs/heads/srj-hidden
- refs/heads/srj-hide2
- refs/heads/srj-hvx
- refs/heads/srj-hvx-bug
- refs/heads/srj-hvx-codegen-bug
- refs/heads/srj-hvx-nocopy
- refs/heads/srj-hvxshift
- refs/heads/srj-iib
- refs/heads/srj-initshape
- refs/heads/srj-inv
- refs/heads/srj-ir
- refs/heads/srj-irmut2
- refs/heads/srj-iwyu
- refs/heads/srj-iwyu3
- refs/heads/srj-javascript_work_in_progress
- refs/heads/srj-lensblur
- refs/heads/srj-lessinc
- refs/heads/srj-llvm-loop-opt
- refs/heads/srj-mak
- refs/heads/srj-maxthreads
- refs/heads/srj-mod
- refs/heads/srj-msan
- refs/heads/srj-msan-call
- refs/heads/srj-muldivmod
- refs/heads/srj-mut
- refs/heads/srj-outputs-2
- refs/heads/srj-parse
- refs/heads/srj-pch
- refs/heads/srj-printfunc
- refs/heads/srj-pygp
- refs/heads/srj-revertbits
- refs/heads/srj-schedule-storage
- refs/heads/srj-shl-shr-2
- refs/heads/srj-sio
- refs/heads/srj-static-const
- refs/heads/srj-strided-store
- refs/heads/srj-tidyh
- refs/heads/srj-tiff
- refs/heads/srj-trace
- refs/heads/srj-tutorial
- refs/heads/srj-using
- refs/heads/srj-wasmfix
- refs/heads/srj-xor2
- refs/heads/srj/abstract-gen-without-get-output-func-KEEP
- refs/heads/srj/aligned-alloc
- refs/heads/srj/aligned-alloc-2
- refs/heads/srj/aligned-malloc-with-aligned-alloc
- refs/heads/srj/all-explicit-ctor
- refs/heads/srj/anderson-thread-info-ptr
- refs/heads/srj/aot-perf
- refs/heads/srj/argv-signatures
- refs/heads/srj/argv-types
- refs/heads/srj/async-test
- refs/heads/srj/b2cpp-const-data
- refs/heads/srj/better-xt-dispatch
- refs/heads/srj/bfloat1
- refs/heads/srj/bp
- refs/heads/srj/build_halide_h
- refs/heads/srj/c-bool
- refs/heads/srj/cache-clear
- refs/heads/srj/clang-fmt-ignore
- refs/heads/srj/clang-tidy
- refs/heads/srj/clear-c-cache
- refs/heads/srj/cmake-asan
- refs/heads/srj/cmake-asan2
- refs/heads/srj/cmake-jit-generators
- refs/heads/srj/configure-cmake
- refs/heads/srj/cpp-generator-v2-experiment-KEEP
- refs/heads/srj/crosscompile
- refs/heads/srj/ctad
- refs/heads/srj/depr
- refs/heads/srj/deprecation
- refs/heads/srj/device-copy
- refs/heads/srj/example
- refs/heads/srj/experiment
- refs/heads/srj/experiment-6967
- refs/heads/srj/exporting
- refs/heads/srj/expr_t
- refs/heads/srj/external-tensors
- refs/heads/srj/fix-pytorch
- refs/heads/srj/fixed-rollback
- refs/heads/srj/fopen-fix
- refs/heads/srj/forward
- refs/heads/srj/forward-name
- refs/heads/srj/gen-func
- refs/heads/srj/gen-func-2
- refs/heads/srj/gen-func-3
- refs/heads/srj/gen2-1
- refs/heads/srj/gen_closure
- refs/heads/srj/generator_aot_gpu_multi_context_threaded
- refs/heads/srj/globals
- refs/heads/srj/halide-buffer-crop
- refs/heads/srj/halide-malloc-alignment
- refs/heads/srj/halide-must-use
- refs/heads/srj/halide-runtime-must-use-result
- refs/heads/srj/hang-repro
- refs/heads/srj/hannk
- refs/heads/srj/hannk-aliasing
- refs/heads/srj/hannk-error-checking
- refs/heads/srj/hannk-errors
- refs/heads/srj/hannk-inplace
- refs/heads/srj/hannk-mmap
- refs/heads/srj/hannk-tflite-27
- refs/heads/srj/hannk-verbosity
- refs/heads/srj/hdrs
- refs/heads/srj/html-becomes-viz
- refs/heads/srj/implicit-mult-widening
- refs/heads/srj/issue-7076
- refs/heads/srj/iwyu
- refs/heads/srj/iwyu-2
- refs/heads/srj/iwyu-6
- refs/heads/srj/libHANNK
- refs/heads/srj/llvm_type_of
- refs/heads/srj/maybe-unused
- refs/heads/srj/meanop
- refs/heads/srj/metadata-calling-convention
- refs/heads/srj/more-tidy
- refs/heads/srj/msan-dtf
- refs/heads/srj/multimeta
- refs/heads/srj/nanobind
- refs/heads/srj/new-rt-1
- refs/heads/srj/no-threadpool
- refs/heads/srj/no-timeout-thread
- refs/heads/srj/oglc-mutexed
- refs/heads/srj/param-map
- refs/heads/srj/pip-15.x
- refs/heads/srj/pip-cron
- refs/heads/srj/possible-uninited
- refs/heads/srj/pr-7566
- refs/heads/srj/printer-size
- refs/heads/srj/profiler-data-race
- refs/heads/srj/ptr-int-cast
- refs/heads/srj/pyapps
- refs/heads/srj/pyext-fix
- refs/heads/srj/pygen-class
- refs/heads/srj/pygen-deux
- refs/heads/srj/pygen-func
- refs/heads/srj/pygen-native-types
- refs/heads/srj/pyinstall
- refs/heads/srj/pypi-try
- refs/heads/srj/pystuff
- refs/heads/srj/python-buffer-unpack
- refs/heads/srj/python-tutorial
- refs/heads/srj/reshape
- refs/heads/srj/rt-error-smallify
- refs/heads/srj/rt-return-types
- refs/heads/srj/runtime-error-handling
- refs/heads/srj/sat-fixes-exp
- refs/heads/srj/sat-fixes-exp-2
- refs/heads/srj/shadow-field
- refs/heads/srj/snprintf
- refs/heads/srj/spirv-license
- refs/heads/srj/stat-buf-deprecations
- refs/heads/srj/static-buffer-generators
- refs/heads/srj/stmt-html
- refs/heads/srj/stringify
- refs/heads/srj/synth-gen-params
- refs/heads/srj/synth-params-python
- refs/heads/srj/test-arm_sve_redux
- refs/heads/srj/test-intrinsics-bounds
- refs/heads/srj/test8076
- refs/heads/srj/test8078
- refs/heads/srj/test8094
- refs/heads/srj/test8105a
- refs/heads/srj/test8115
- refs/heads/srj/test_tmpdir_fix
- refs/heads/srj/tidy
- refs/heads/srj/tidy-format-14
- refs/heads/srj/tidymore
- refs/heads/srj/tidymore2
- refs/heads/srj/tls
- refs/heads/srj/tls-3
- refs/heads/srj/tls-4
- refs/heads/srj/tls-ucon
- refs/heads/srj/tmp-unschedule-experiment
- refs/heads/srj/tot-fix
- refs/heads/srj/try-revert-sat
- refs/heads/srj/type-traits
- refs/heads/srj/typed-func
- refs/heads/srj/ucon-all-const
- refs/heads/srj/ucon-non-const
- refs/heads/srj/visit-warnings
- refs/heads/srj/wasm-atomic2
- refs/heads/srj/wasm-simd
- refs/heads/srj/wasm-stuff
- refs/heads/srj/wasm-threads
- refs/heads/srj/wasm-updates
- refs/heads/srj/wasm-work
- refs/heads/srj/wip
- refs/heads/srj/x-rounding
- refs/heads/srj/xbuf
- refs/heads/srj/xc+plus+size+tmp
- refs/heads/srj/xc-types
- refs/heads/srj/xt-uint-cast-test
- refs/heads/srj/xtensa-arch
- refs/heads/srj/xtensa-merge
- refs/heads/srj/xvc-experimetn
- refs/heads/srj/zlib-embed
- refs/heads/standalone_autoscheduler
- refs/heads/standalone_autoscheduler_arm_worker
- refs/heads/standalone_autoscheduler_arm_worker_amazon
- refs/heads/standalone_autoscheduler_gpu
- refs/heads/standalone_autoscheduler_hexagon
- refs/heads/sticky_task_assignments
- refs/heads/store_with
- refs/heads/store_with_solver_for_super_simplify
- refs/heads/strict_float_cse_fix
- refs/heads/super_simplify
- refs/heads/super_simplify_v2
- refs/heads/super_simplify_v3
- refs/heads/transitive_wrapper
- refs/heads/trigger-release-v16
- refs/heads/tzumao-autodiff-boundarycond
- refs/heads/tzumao-gradient-autoscheduler-bug
- refs/heads/tzumao-predicate-store-load
- refs/heads/tzumao-python-buffer
- refs/heads/tzumao_autodiff_unbounded
- refs/heads/tzumao_improve_gradient_autoscheduler
- refs/heads/tzumao_issue_4297
- refs/heads/tzumao_licm_before_BI
- refs/heads/unbounded_bugs
- refs/heads/undo_async_copy_chain_black_list
- refs/heads/use_string_literals_for_blobs
- refs/heads/users/lukas/python-pip
- refs/heads/validate_sched_error_msg
- refs/heads/var_ir_fix
- refs/heads/vksnk/async-experiment
- refs/heads/vksnk/async-multiple-producers
- refs/heads/vksnk/async-order
- refs/heads/vksnk/better-loop-carry
- refs/heads/vksnk/better-message
- refs/heads/vksnk/bound-storage
- refs/heads/vksnk/bounds-widen-right
- refs/heads/vksnk/c-print-type
- refs/heads/vksnk/c-round
- refs/heads/vksnk/check-return-result
- refs/heads/vksnk/compute-with-bug
- refs/heads/vksnk/compute_with_async
- refs/heads/vksnk/dma-limit-channels
- refs/heads/vksnk/dma-min-max
- refs/heads/vksnk/expr-match-shuffle
- refs/heads/vksnk/extract-from-scalar
- refs/heads/vksnk/f16-load
- refs/heads/vksnk/fix-packvr
- refs/heads/vksnk/fix_halide_xtensa_narrow_with_rounding_shift_i16
- refs/heads/vksnk/fused-compute-with
- refs/heads/vksnk/hoist-storage-bug
- refs/heads/vksnk/lerp-intrinsics
- refs/heads/vksnk/lower-signed-shifts
- refs/heads/vksnk/missing-exception
- refs/heads/vksnk/non-widening-halves
- refs/heads/vksnk/optimize-shuffles
- refs/heads/vksnk/replace-all
- refs/heads/vksnk/restrict
- refs/heads/vksnk/roll-buffer
- refs/heads/vksnk/roundeven-arm
- refs/heads/vksnk/rvar-bounds
- refs/heads/vksnk/simplify-slice
- refs/heads/vksnk/skip-semaphores
- refs/heads/vksnk/storage-folding
- refs/heads/vksnk/strided-load-of-4_2
- refs/heads/vksnk/typed-scope
- refs/heads/vksnk/update-simd-driver
- refs/heads/vksnk/vectorize-bug
- refs/heads/vksnk/vectorize-scalarize
- refs/heads/vksnk/widening_absd
- refs/heads/vksnk/xtensa-codegen-fp16
- refs/heads/vksnk/xtensa-dma-improvements
- refs/heads/vksnk/xtensa-regroup-pass
- refs/heads/vksnk/xtensa/lift-allocs
- refs/heads/vulkan
- refs/heads/vulkan-diagnose-alloc-failures
- refs/heads/vulkan-phase0-adts
- refs/heads/vulkan-phase1-spirv
- refs/heads/vulkan-phase2-runtime
- refs/heads/vulkan2
- refs/heads/vulkan_fix_gpu_dynamic_shared_test
- refs/heads/vulkan_fix_subregion_memory_offsets
- refs/heads/webassembly-old
- refs/heads/winograd
- refs/heads/wording_fix
- refs/heads/xtensa-codegen
- refs/heads/xtensa-codegen-parallel
- refs/heads/xuanda/fix-serialize-bad-partition-always
- refs/remotes/origin/rootjalex/add_autosched_caching
- refs/tags/release_2018_02_15
- refs/tags/release_2019_08_27
- refs/tags/release_8.0.0
- refs/tags/v10.0.0
- refs/tags/v10.0.1
- refs/tags/v11.0.0
- refs/tags/v11.0.1
- refs/tags/v12.0.0
- refs/tags/v12.0.1
- refs/tags/v13.0.0
- refs/tags/v13.0.1
- refs/tags/v13.0.2
- refs/tags/v13.0.3
- refs/tags/v13.0.4
- refs/tags/v14.0.0
- refs/tags/v15.0.0
- refs/tags/v15.0.1
- refs/tags/v16.0.0
- refs/tags/v17.0.0
- refs/tags/v17.0.1
- refs/tags/v8.0.0
Take a new snapshot of a software origin
If the archived software origin currently browsed is not synchronized with its upstream version (for instance when new commits have been issued), you can explicitly request Software Heritage to take a new snapshot of it.
Use the form below to proceed. Once a request has been submitted and accepted, it will be processed as soon as possible. You can then check its processing state by visiting this dedicated page.Processing "take a new snapshot" request ...
Permalinks
To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.
Revision | Author | Date | Message | Commit Date |
---|---|---|---|---|
64bb90e | Volodymyr Kysenko | 11 November 2021, 17:11:32 UTC | Change implementation of round_f* in CodeGen_C to use nearbyint to match CodeGen_LLVM | 11 November 2021, 17:11:32 UTC |
8e34a35 | Steven Johnson | 09 November 2021, 23:10:40 UTC | Remove halide_abort_if_false() usage in runtime/metal (#6398) * Remove halide_abort_if_false() usage in runtime/metal This converts all the usage of `halide_abort_if_false()` in runtime/metal into either an explicit runtime check-and-return-error-code (if the check looks plausible), or `halide_debug_assert()` (if the check seems to be stating an invariant that shouldn't be possible in well-structured code). These changes are admittedly subjective, so feedback is especially welcome. Also, driveby change to sync-common.h to use `halide_debug_assert()` rather than a local equivalent. * nits | 09 November 2021, 23:10:40 UTC |
4f70271 | Steven Johnson | 09 November 2021, 22:51:05 UTC | Add defensive checks to halide_buffer_copy_already_locked (#6401) Found while debugging crashes with performance_async_gpu for OpenGLCompute: the 'if' tree wasn't robust enough for malformed buffers being passed, and could attempt to deref and use a null src->device_interface or dst->device_interface in some cases. This patch just improves this function to return an error in these cases (rather than crashing); the fact that we are getting malformed buffers passed to us is likely a separate bug. | 09 November 2021, 22:51:05 UTC |
b189722 | Steven Johnson | 09 November 2021, 21:35:24 UTC | [hannk] Upgrade hannk to use TFLite 2.7.0 by default (#6393) * [hannk] Upgrade hannk to use TFLite 2.7.0 by default * Fix unused-vars warnings | 09 November 2021, 21:35:24 UTC |
b021f87 | Steven Johnson | 09 November 2021, 21:25:26 UTC | Move PyTorch test into standalone tests (#6397) * Move PyTorch test into standalone tests It doesn't need to be internal. Also simplified to use only public API, updated the expected correctness, and avoided the need to have cuda present on the system to test for cuda output (since we can cross-compile to generate the C++ output anywhere). * fixes * Fix Windows text file endings * Update pytorch.cpp * Update pytorch.cpp | 09 November 2021, 21:25:26 UTC |
4286c78 | Steven Johnson | 09 November 2021, 17:13:09 UTC | Drop support for LLVM11 (#6396) * Drop support for LLVM11 With Halide 13 released, we should drop support for LLVM11 in Halide trunk, since we only promise to support LLVM trunk + two releases. * Update packaging.yml * Update config.cmake * Update CMakeLists.txt | 09 November 2021, 17:13:09 UTC |
d3ea755 | Steven Johnson | 09 November 2021, 17:03:17 UTC | Fix OGLC debug builds (#6399) If you try to build and run something with `openglcompute` and `debug`, you may crash with a div-by-zero, because the openglcompute runtime never calls `halide_start_clock()`, and all implementations of `halide_current_time_ns()` assume that it has been called. On (e.g.) OSX, this results in div by zero. This fixes it by inserting the correct call into openglruntime.cpp, and also adding debug-only asserts to all the `halide_current_time_ns()` implementations. (I was tempted to fix this by removing `halide_start_clock()` entirely and just lazily initing the initial value in `halide_current_time_ns()`, but I figured that would likely get pushback...) | 09 November 2021, 17:03:17 UTC |
d6f1345 | Steven Johnson | 08 November 2021, 23:13:13 UTC | Rename halide_assert -> halide_abort_if_false (#6382) * Rename halide_assert -> HALIDDE_CHECK A crashing bug got mistakenly inserted because a new contributor (reasonably) assumed that the `halide_assert()` macro in our runtime code was like a C `assert()` (i.e., something that would vanish in optimized builds). This is not the case; it is a check that happens in all build modes and always triggers an `abort()` if it fires. We should remove any ambiguity about it, so this proposes to rename it to somethingmore like the Google/Abseil-style CHECK() macro, to make it stand out more. (We may want to do a followup to verify that all of the uses really are unrecoverable errors that aren't better handled by returning an error.) * clang-format * Fix for top-of-tree LLVM * Fix for older versions * HALIDE_CHECK -> halide_abort_if_false * Update runtime_internal.h | 08 November 2021, 23:13:13 UTC |
1312817 | Steven Johnson | 08 November 2021, 22:01:29 UTC | Clean up CodeGen_LLVM names to match ASAN nomenclature changes (#6395) | 08 November 2021, 22:01:29 UTC |
6071cf6 | Steven Johnson | 08 November 2021, 20:13:44 UTC | Check results of all runtime function calls (#6389) * Check results of all runtime function calls This cherry-picks just the changes to callsites internal to Halide (and tests) from #6388. (It doesn't attempt to annotate runtime functions to enforce checking the results.) * Update write_debug_image.cpp * Add checks + comment to buffer_copy_aottest * Add comment to gpu_object_lifetime_aottest * Update memory_profiler_mandelbrot_aottest.cpp * Update user_context_insanity_aottest.cpp * Update process.cpp | 08 November 2021, 20:13:44 UTC |
a798909 | Steven Johnson | 08 November 2021, 20:13:28 UTC | Add halide_debug_assert() macro (#6390) * Add halide_debug_assert() macro Also convert usage of halide_assert()/HALIDE_CHECK() in hashmap.h and gpu_context_common.h to halide_debug_assert(), as all the usages looked to be appropriate for debug-mode only. (Rebased version of #6385, which this replaces) * appease clang-format | 08 November 2021, 20:13:28 UTC |
656c6b5 | Steven Johnson | 04 November 2021, 23:00:28 UTC | [hannk] Have CMake emit .s, .stmt, .ll files (#6392) | 04 November 2021, 23:00:28 UTC |
26ccb54 | Omar Emara | 04 November 2021, 00:35:13 UTC | Support vectorized Select in OpenGLCompute backend (#6371) The ternary operator in GLSL does not work with vector types. While the mix function have overloads to boolean vectors, it is only supported in version 4.5, so it is not exactly portable. To work around this, we use the ternary operator on all elements of the vector type. Necessary for #6348. | 04 November 2021, 00:35:13 UTC |
c005b9f | Omar Emara | 04 November 2021, 00:32:20 UTC | Support vectorization in OpenGLCompute backend (#6348) * Support vectorization in OpenGLCompute backend This patch adds support for vector load and store operations. First, a pass identifies the buffers whose loads and stores are all dense, aligned, and have the same number of lanes. Such buffers are declared with a vector base type and accessed accordingly. Loads and stores that do not satisfy those criteria are implemented as gathers and scatters from buffers whose base type is scalar. Resolves #4976. Partially resolves #1687. * Move buffer name instead of copy (clang-tidy) | 04 November 2021, 00:32:20 UTC |
657bb03 | Steven Johnson | 03 November 2021, 23:29:38 UTC | Fix for top-of-tree LLVM (#6386) * Fix for top-of-tree LLVM * Fix for older versions | 03 November 2021, 23:29:38 UTC |
76315a2 | Omar Emara | 03 November 2021, 22:54:44 UTC | Vectorize Ramp in OpenGLCompute backend (#6372) Currently, ramps are generated as a number of independent scalar expressions that are finally gathered into a vector. For instance, indexing in vectorized code is filled with ramps like the following: ``` int _11 = int(1) * int(1); int _12 = _10 + _11; int _13 = int(2) * int(1); int _14 = _10 + _13; int _15 = int(3) * int(1); int _16 = _10 + _15; ivec4 _17 = ivec4(_10, _12, _14, _16); ``` This patch simplifies the generated code using a multiply add expression on a vector containing an arithmetic expression, such that the code is as follows: ``` ivec4 _11 = ivec4(0, 1, 2, 3) * int(1) + _10; ``` This is more performant due to vectorization, more compact, and more readable because the base and the stride are easily identifiable. | 03 November 2021, 22:54:44 UTC |
2cf3afb | Steven Johnson | 03 November 2021, 22:47:03 UTC | [hannk] Fix MeanOp (#6336) * [hannk] Fix MeanOp The `reducing()` method didn't handle negative values for indices, and didn't reverse the value of the axis as we do elsewhere, so results were incorrect. Also, we now parse and save the value of `keep_dims`, though I can't find evidence that it does much of anything: test cases pass different values for it but none of them fail (even though we ignore it), and at least one reference implementation I see doesn't seem to do anything with it. * Remove keep_dims handling for MeanOp | 03 November 2021, 22:47:03 UTC |
7ec8d70 | Steven Johnson | 03 November 2021, 22:19:15 UTC | Convert various halide_assert -> static_assert (#6383) The type-size checks in d3d12compute.cpp don't need to be runtime checks. | 03 November 2021, 22:19:15 UTC |
a227440 | Steven Johnson | 03 November 2021, 20:55:28 UTC | Remove halide_assert() from halide_default_device_wrap_native (#6381) This was inserted in https://github.com/halide/Halide/pull/6310, probably mistakenly, since `halide_assert()` in the Halide runtime is *not* a debug-only assertion). Instead of a controlled runtime failure, we just abort, which is not OK. | 03 November 2021, 20:55:28 UTC |
415ce0c | Alex Reinking | 03 November 2021, 20:27:46 UTC | Fix empty INSTALL_COMMAND in hannk super-build (#6387) * Fix empty INSTALL_COMMAND in hannk super-build * Fix 3.16 missing command * Fix the fix... | 03 November 2021, 20:27:46 UTC |
0d6b0f5 | Steven Johnson | 03 November 2021, 16:18:45 UTC | Fix for top-of-tree LLVM (#6380) | 03 November 2021, 16:18:45 UTC |
ac2673b | Alex Reinking | 03 November 2021, 00:57:12 UTC | Add super-build for cross-compiling HANNK (#6374) * Add super-build for cross-compiling HANNK * Relax CMake version | 03 November 2021, 00:57:12 UTC |
6070821 | Alex Reinking | 02 November 2021, 19:42:02 UTC | Update README for Halide 13. (#6378) | 02 November 2021, 19:42:02 UTC |
5b8f473 | Volodymyr Kysenko | 02 November 2021, 15:36:19 UTC | Fix for the crash from #6367 (#6375) * Skip empty boxes * Address the comments | 02 November 2021, 15:36:19 UTC |
4225eba | Alex Reinking | 01 November 2021, 23:03:09 UTC | Add helper for cross-compiling Halide generators. (#6366) * Add helper for cross-compiling Halide generators. Created a new function, `add_halide_generator`, that helps users write correct cross-compiling builds by establishing the following convention for creating a generator named `TARGET`: 1. Define Halide generators and libraries in the same project 2. Assume two builds: a host build and a cross build. 3. When creating a generator, check to see if we can load a pre-built version of the target. 4. If so, just use it. 5. If not, make sure the full Halide package is loaded and create a target for the generator. a. If `CMAKE_CROSSCOMPILING` is set, then _warn_ the user (the variable is unreliable on macOS) that something seems fishy. b. Create export rules for the generator. It creates a package `PACKAGE_NAME` and appends to its `EXPORT_FILE`. c. Create a custom target also named `PACKAGE_NAME` for building the generators. d. Create an alias `${PACKAGE_NAMESPACE}${TARGET}`. 6. Users are expected to use the alias in conjunction `add_halide_library`. Users can test the existence of `TARGET` to determine whether a pre-built one was loaded (and set additional properties if not). 7. Setting `${PACKAGE_NAME}_ROOT` is enough to load pre-built generators. `PACKAGE_NAME` is `${PROJECT_NAME}-halide_generators` by default. `PACKAGE_NAMESPACE` is `${PROJECT_NAME}::halide_generators::` by default. `EXPORT_FILE` is `${PROJECT_BINARY_DIR}/cmake/${PACKAGE_NAME}-config.cmake` by default. Users are free to avoid the helper if it would not fit their workflow. * Make HANNK use the new add_halide_generator helper | 01 November 2021, 23:03:09 UTC |
f5ce5f3 | Steven Johnson | 01 November 2021, 20:40:36 UTC | [hannk] Clean up aliasing (v2) (#6364) * wip * [hannk] Clean up aliasing (v2) The code for aliasing tensors was janky. This cleans it up and makes a clear distinction between aliasing done to overlay buffers with crop-and-translate, vs the aliasing done when we reshape tensors. We no longer allow a given tensor to do both of these, and we give preference to Reshape aliasing first. (Cherry-picked from #6321) * Move alias_type into shared ptr | 01 November 2021, 20:40:36 UTC |
1a1c97f | Steven Johnson | 01 November 2021, 20:28:50 UTC | [hannk] Add support for building/running for wasm (#6361) * [hannk] Allow disabling TFLite+Delegate build in CMake Preparatory work for allowing building of hannk with Emscripten; TFLite (and its dependees) problematic to build in that environment, but this will allow us to build a tflite-parser-only environment. (Note that more work is needed to get this working for wasm, as crosscompiling in CMake is still pretty painful; this work was split out to make subsequent reviews simpler) * [hannk] Add support for building/running for wasm * HANNK_BUILD_TFLITE_DELEGATE -> HANNK_BUILD_TFLITE * Use explicit host build strategy for cross compiling HANNK (#6365) * Ignore local emsdk clone * Fix usage of CMAKE_BUILD_TYPE * Only print the Halide target info once per CMake run * Fix Halide "cmake" target detection for Emscripten * Prefer target_link_options to _link_libraries when applicable * Validate, rather than find, NODE_JS_EXECUTABLE (set by emsdk) * Emscripten already wraps tests with node. * Add dependency on Android logging library. * For cross-compiling, find host tools instead of recursive call. Rather than shelling out via execute_process and potentially guessing the toolchain options wrong, expect to find our host tools (i.e. generators) in a package called "hannk_tools". The package is created by the host build via the CMake export() command. Importing this package in the cross build creates IMPORTED targets with the same names as our generators. We then use these generators rather than creating generators for the target build. * Rework cross-compiling script. * Respond to (easy) reviewer comments. * Add HANNK_AOT_HOST_ONLY option. Use in script. * [hannk] tests should only process .tflite files (#6368) currently, random dotfiles (e.g. .DS_Store on OSX) can creep in, causing bogus failures * Add comment about node wrapping. * Rename hannk_tools to hannk-halide_generators * Add comment about exporting targets. * Bump version to Halide 14.0.0 (#6369) Co-authored-by: Steven Johnson <srj@google.com> Co-authored-by: Alex Reinking <alex_reinking@berkeley.edu> | 01 November 2021, 20:28:50 UTC |
69d8ef0 | Alex Reinking | 30 October 2021, 01:33:50 UTC | Bump version to Halide 14.0.0 (#6369) | 30 October 2021, 01:33:50 UTC |
3c52df1 | Steven Johnson | 29 October 2021, 23:46:50 UTC | [hannk] tests should only process .tflite files (#6368) currently, random dotfiles (e.g. .DS_Store on OSX) can creep in, causing bogus failures | 29 October 2021, 23:46:50 UTC |
541bc37 | Steven Johnson | 28 October 2021, 21:14:42 UTC | [hannk] Allow disabling TFLite+Delegate build in CMake (#6360) * [hannk] Allow disabling TFLite+Delegate build in CMake Preparatory work for allowing building of hannk with Emscripten; TFLite (and its dependees) problematic to build in that environment, but this will allow us to build a tflite-parser-only environment. (Note that more work is needed to get this working for wasm, as crosscompiling in CMake is still pretty painful; this work was split out to make subsequent reviews simpler) * Update hannk_delegate.h * HANNK_BUILD_TFLITE_DELEGATE -> HANNK_BUILD_TFLITE | 28 October 2021, 21:14:42 UTC |
e10f104 | Steven Johnson | 28 October 2021, 17:34:27 UTC | Update Emscripten settings (#6362) The settings we use to build C++ in wasm were slightly out of date now that we've updated our runtime to Node instead of d8. Also drive-by gitignore fix. | 28 October 2021, 17:34:27 UTC |
1c7388a | Andrew Adams | 28 October 2021, 17:25:58 UTC | Allow users to use their own cuda contexts and streams in JIT mode (#6345) * Deprecate JIT runtime override methods that take void * * Make it possible to use custom cuda contexts and streams in JIT mode * Clean up comments * Tolerate null handlers in the JITUserContext These can come up if a JITUserContext is passed to something like copy_to_device before getting fully populated by passing it to a call to realize. * Remove reliance on dlsym in test and reuse the runtime's name resolution mechanism instead * Handle case where cuda and cuda-debug runtime modules both exist This change means we'll only ever create one built-in cuda context in this circumstance. * Slight simplification * Improve comments | 28 October 2021, 17:25:58 UTC |
4f573bf | Volodymyr Kysenko | 28 October 2021, 02:05:29 UTC | Add missing widening_absd patterns (#6359) * Add missing widening_absd patterns * Add a comment | 28 October 2021, 02:05:29 UTC |
8f1ae2a | Steven Johnson | 27 October 2021, 20:37:00 UTC | Use Node instead of d8 for Wasm AOT testing (#6356) * Use Node instead of d8 for Wasm AOT testing This requires the right version of Node is installed on your system. Since EMSDK often puts a too-old version of Node in the path, allow overriding via an env var. * wip | 27 October 2021, 20:37:00 UTC |
34534f5 | Steven Johnson | 27 October 2021, 20:35:39 UTC | [hannk] Add missing call to Interpreter::prepare in benchmark app (#6358) | 27 October 2021, 20:35:39 UTC |
a15ffda | Volodymyr Kysenko | 27 October 2021, 01:33:39 UTC | Add include for size_t in constants.h (#6353) * Add include for size_t in constants.h * Change to int | 27 October 2021, 01:33:39 UTC |
86cb6c7 | Andrew Adams | 26 October 2021, 23:12:52 UTC | Deprecate JIT runtime override methods that take void * (#6344) * Deprecate JIT runtime override methods that take void * * Clean up comments | 26 October 2021, 23:12:52 UTC |
6211da9 | Andrew Adams | 26 October 2021, 23:12:34 UTC | Add --help flag to rungenmain, fixing #5323 (#6354) | 26 October 2021, 23:12:34 UTC |
06a37ca | Steven Johnson | 26 October 2021, 17:23:23 UTC | Add to various OpVisitors to avoid overload warnings for some compilers (#6337) | 26 October 2021, 17:23:23 UTC |
47fa87f | Steven Johnson | 26 October 2021, 17:22:49 UTC | [hannk] Add a prepare() method for ops and interp (#6338) * [hannk] Add a prepare() method for ops and interp This adds a new method to the Interpreter, and to all ops, which allows the interpreter (and each op) to do any one-time preparation for future executions. Previously this was lumped into either the Interpreter's ctor, or the Ops various other methods, but this has some nice advantages at minimal cost: - Since the new prepare() returns an error value, it allows the Interpreter to do sanity checking at startup and return an error to the caller (rather than simply crashing); this makes using it in some runtime environments less painful. - Ops can use this to prep and cache information for multiple subsequent runs; initially, Conv and DepthwiseConv use this to calculate and cache the alignment requirements they need later on. This is unlikely to be a huge performance hit, but it is likely nonzero, and As an added bonus, this means that e.g. the map_bounds() method is no longer susceptible to runtime failures from Halide bounds queries. * Update interpreter.cpp * Update transforms.cpp * Update transforms.cpp | 26 October 2021, 17:22:49 UTC |
667836d | Steven Johnson | 26 October 2021, 17:16:35 UTC | Harvest IWYU changes for LLVM, WABT (#6341) A couple of minor hygiene changes, extracted from https://github.com/halide/Halide/pull/6251: - Clean up LLVM_Headers.h to uniformly use <> instead of "" and to alphabetize properly - Clean up WABT includes to reflect what we need more accurately | 26 October 2021, 17:16:35 UTC |
b34919f | Omar Emara | 26 October 2021, 17:09:48 UTC | Fix wrong type in Ramp CodeGen for OpenGLCompute (#6349) The variable type of the Ramp in OpenGLCompute is assigned the type of the base member of the ramp, which is a scalar, while the ramp is a vector. Instead, we should use the type of the ramp instead to take vectorization into account. Partially resolves #1687. | 26 October 2021, 17:09:48 UTC |
ab57ab1 | Steven Johnson | 26 October 2021, 17:07:44 UTC | [hannk] augment SoftmaxOp to allow specifying axis (#6351) (basically equivalent to #6335 but for softmax) | 26 October 2021, 17:07:44 UTC |
50517cb | Steven Johnson | 26 October 2021, 17:07:00 UTC | [hannk] requantize() should never skip the operation (#6350) * [hannk] requantize() should never skip the operation Even if inq == outq, the incoming buffer can contain out-of-range values; we shouldn't try to optimize the op away, since it's cheap. * Update ops.cpp * Update ops.cpp | 26 October 2021, 17:07:00 UTC |
d6d7bbc | Steven Johnson | 26 October 2021, 17:05:48 UTC | Make halide_type_t and halide_type_of constexpr (#6340) * Make halide_type_t and halide_type_of constexpr This allows us to do a bit more at compile time in some cases; e.g., we can more reliably collapse things like `t == halide_type_t(int, 8)` into `t.as_u32() == literal-integer`, avoiding temporaries. It also makes it tractable to to do a `switch` on a series of `halide_type_t`, since we can now use halide_type_t::as_u32() as a constexpr. There were a number of places that did this in an ad-hoc manner previously; I updated those, and also converted at least one more repeated-if clause into a switch. (TBH, I'm not sure if I'm wild about the syntax, though; it is a bit weedy to scan. Suggestions welcome.) * Ensure there are no uninited vars in constexpr funcs * Update HalideRuntime.h | 26 October 2021, 17:05:48 UTC |
334e27a | Volodymyr Kysenko | 26 October 2021, 05:10:41 UTC | Specify template parameter of ScopedValue (#6352) | 26 October 2021, 05:10:41 UTC |
5e374bc | Omar Emara | 25 October 2021, 20:34:07 UTC | Fix default device wrap native function (#6310) * Fix default device wrap native function Currently, an attempt to call device_wrap_native on a target that uses the default device wrap native function will result in an error of type halide_error_device_interface_no_device, namely in the OpenGLCompute and the Hexagon targets. This happens because the default wrap native function calls debug_log_and_validate_buf after the device_interface is set in halide_device_wrap_native but before the device handle is set, which is validated as a bad state. This patch removes the validation call and adds an assert for the handle much like the other wrap_native implementations in other targets. * Use approperiate error code | 25 October 2021, 20:34:07 UTC |
6d9737d | Xuanda Yang | 25 October 2021, 20:12:24 UTC | Fix cuda-debug logging: fix incorrect threads_per_core when SM >= 8.0. fix device memory smaller than acutal size. (#6346) | 25 October 2021, 20:12:24 UTC |
ba81a06 | Volodymyr Kysenko | 25 October 2021, 16:22:38 UTC | Scheduling directive to set an explicit storage bound (#6327) * bound_allocation scheduling directive * Add a more specific error and test * Add a correctness test for bound_allocation * Remove debug output from test * Move expression * Per dim bound_storage * Update CMakeLists.txt * how hard can it be * Rename the error code * More detailed error message | 25 October 2021, 16:22:38 UTC |
297c30a | Steven Johnson | 22 October 2021, 16:30:56 UTC | Fix Makefile for LLVM11 (#6343) | 22 October 2021, 16:30:56 UTC |
6c9224a | Steven Johnson | 21 October 2021, 23:16:36 UTC | Fix HelloWasm (#6342) - Add workaround for Cross-origin isolation requirements - Add CXXFLAGS to allow benchmarks to compile | 21 October 2021, 23:16:36 UTC |
0078880 | Thales Sabino | 21 October 2021, 17:52:39 UTC | Add support for AMX instructions (#5818) * Add support for AMX tile instructions * Make AMX transform opt-in with memory type * Clean up tiled_matmul test * Handle AMX intrinsic attributes better * Format * Fix test to behave like other tests * Add doc and missing load check * Format * Throw error if user requests AMX for invalid operation * Add Tile lowering pass to makefile * Use spaces in Makefile * Place AMX instrinsics into a separate module (x86_amx.ll) This will only be included if LLVM >= 12 is used to build Halide * Fix CreateAlignedLoad() call in CodeGen_X86 Recent changes in LLVM trunk made the previous calling convention deprecated (and thus compiling with warning/error) * fix exporting to module * add llvm funcs for su, us, uu amx variants * add other amx intrinsics to intrinsic_defs * match with unsigned 8 bit integers This matching happens for the left and right side, each determining whether that side is unsigned or signed. In the end the proper 1024 byte buffer is created with (un)signed. * match for 32 bit integer and guard unsigned amx on llvm 13 * adjust test to cover unsigned tile operations * guard properly with llvm 12 * create explicit error if failed to use tile operations * pass types as template params rather than boolean This makes the intention clearer * clang-format patch * add x86_amx to makefile's runtime components * make tiled_matmul compatible with c++11 * add mattrs required for amx * fix formatting issues * remove outdated FIXME comments * add bf16 tile operations to the runtime * create a schedule that should map to amx * create full amx-bf16 schedule * allow amx operations to yield f32s * accept 32 bit float stores * add support for bf16 * add missing bf16 intrinsics * fix striding error when loading matrix * add checks to verify bf16 result * fix scaling of col_bytes on matmul call * move brace to previous line * derive result type using a function rather than lambda * run clang tidy and format * have tile_store return i32 * make is_3d_tile_index robust to indexing changes * apply formatting suggestions * both first and second can be const qualified * remove trailing whitespace in unformatted section * make requested style changes * rename NewMatmul -> Matmul * fix warning about missing return value * use get_1d_tile_index to handle special case When using `Buffer` instead of `ImageParam` the `Ramp` expression generated is 1D instead of 2D, therefore we recognize this with a special case. The lanes are still matched against the dimensions of the LHS 3d tile lanes. * add correctness test for AMX instructions * correctness part has been separated out * remove unused variables Co-authored-by: John Lawson <john@codeplay.com> Co-authored-by: Thales Sabino <thales@codeplay.com> Co-authored-by: Steven Johnson <srj@google.com> Co-authored-by: Frederik Engels <frederik.engels@codeplay.com> | 21 October 2021, 17:52:39 UTC |
05107ca | Steven Johnson | 21 October 2021, 17:23:31 UTC | Fix WASM datalayout for top-of-tree LLVM (#6339) | 21 October 2021, 17:23:31 UTC |
ecf69b0 | Xuanda Yang | 21 October 2021, 04:16:55 UTC | Add support for CUDA capability 8.6 (#6334) * Add support for CUDA capability 8.6 * add assertion to guard LLVM version * fallback to sm80 if LLVM < 13.0 | 21 October 2021, 04:16:55 UTC |
27f975f | Andrew Adams | 20 October 2021, 22:32:08 UTC | Add ability to pass a user context in JIT mode (#6313) * Change type of first arg to all JITHandlers and expose struct to users * Make it possible to pass a custom JITUserContext per realize call * More comments * Fix type in python bindings * Fix type in python bindings * Fix more types in python bindings * Add user_context-accepting variants of other realize-like functions * Revert tests back to the way they are on master but with comments explaining why they are the way they are * Add example of passing a custom context to copy_to_host * Revert test to be closer to master. It was that way for a reason * The first arg to get_library_symbol isn't actually a user_context * Add copy_to_device example too * Fix python * Make bad_buf even worse * Comment clarifications | 20 October 2021, 22:32:08 UTC |
c3641b6 | Steven Johnson | 20 October 2021, 00:16:04 UTC | [hannk] augment L2NormOp to allow specifying axis (#6335) | 20 October 2021, 00:16:04 UTC |
d80bb23 | Andrew Adams | 19 October 2021, 16:43:07 UTC | Add a new unsigned division method (#6322) * Add a new unsigned division method It uses averages rounding up instead of averages rounding down, to reduce instruction count on x86. Division by 7 before: vpmulhuw .LCPI0_1(%rip), %ymm0, %ymm1 vpsubw %ymm1, %ymm0, %ymm0 vpsrlw $1, %ymm0, %ymm0 vpaddw %ymm1, %ymm0, %ymm0 vpsrlw $2, %ymm0, %ymm0 Division by 7 after: vpmulhuw .LCPI0_1(%rip), %ymm0, %ymm1 vpavgw %ymm0, %ymm1, %ymm0 vpsrlw $2, %ymm0, %ymm0 * Remove debugging code * Add comment elaborating on why this is a good idea | 19 October 2021, 16:43:07 UTC |
deeb6bc | Steve Suzuki | 19 October 2021, 16:40:16 UTC | Rewrite double/triple narrowing from float on ARM (#6305) * Rewrite double/triple narrowing from float on ARM | 19 October 2021, 16:40:16 UTC |
7613f9d | Steven Johnson | 18 October 2021, 16:55:35 UTC | [hannk] Improve GatherOp (#6328) We (mostly) implemented GatherOp for TFLite's Gather op, but missed some things: - There's a batch_dim param for Gather that we were ignoring. I added code to fill it in, but we punt for values != 0, because I haven't yet found a test case that handles it. Should be easy to fill in when we do. - TFLite's GatherNd op (and NNAPI's GATHER op) allow for the indices arg to be multidimensional; I rewrote the code to handle this and it's passing the acceptance tests for NNAPI's cases. (It doesn't yet handle the GatherNd op because, again, I haven't found a good test case. Should be simple to do when we do.) | 18 October 2021, 16:55:35 UTC |
8d098de | Steven Johnson | 18 October 2021, 16:52:49 UTC | [hannk] Restructure BinaryOp to allow adding more temporary types (#6326) Change is a no-op as written, but I'd like to land it so this change doesn't get lost -- it's handy for debugging pipelines that happen to use op/type variants we don't yet support (eg arithmetic on floats), which can unblock the ability to run more tests (albeit not efficiently). | 18 October 2021, 16:52:49 UTC |
cd8146d | Steven Johnson | 18 October 2021, 16:47:48 UTC | [hannk] Fix override annotation in hannk (#6315) Minor hygiene: add explicit override annotations and enable the compiler warnings. (I was about to tweak some of the virtual functions and this has been bothering me for a while.) | 18 October 2021, 16:47:48 UTC |
923025a | Steven Johnson | 14 October 2021, 20:27:00 UTC | [hannk] Fix assert in dconv (#6320) | 14 October 2021, 20:27:00 UTC |
071f5f7 | Steven Johnson | 13 October 2021, 18:23:34 UTC | [hannk] Improve Op::dump() (#6314) * [hannk] Improve Op::dump() Rewrite the Op::dump() methods to be more verbose, so that we can determine all the details of the tensors used, and the hierarchy of OpGroups; also add a post-transform dump when verbosity >= 2. (I'm using this to track down a subtle bug, but landing this separate from other fixes seems appropriate) * Fixes | 13 October 2021, 18:23:34 UTC |
63cfd9d | Andrew Adams | 12 October 2021, 20:52:24 UTC | Substitute in all widening lets prior to find_intrinsics (#6307) * Look through lets in find_intrinsics If an Expr like: narrow((widen(x) + y + 1)/2) gets lifted into a let, the simplifier will then substitute things in like so: let foo = widen(x) + y in narrow(foo + 1)/2, potentially breaking a pattern. This is a general problem for patterns that widen, do some math, and then narrow. They will always get cut at the widening operation, so this PR just substitutes in all widening operations. This can't cause combinatorial blow-up, because each substitution has a wider type than the values that it depends on, so the chains can be at most 2-3 lets deep. * Make substituting in widening lets a prepass instead * Move find_intrinsics a little earlier in lowering * Handle impure subexpressions by leaving them behind at the original let site * FindIntrinsics must be after the last simplification pass | 12 October 2021, 20:52:24 UTC |
a351021 | Andrew Adams | 12 October 2021, 19:20:33 UTC | Demosaic should be done unsigned (#6308) So that we can use pavgw instructions and the like. Speeds it up slightly on x86 (5% or so) | 12 October 2021, 19:20:33 UTC |
3931213 | Steven Johnson | 12 October 2021, 18:57:02 UTC | [hannk] SpaceDepthOp isn't limited to u8 Tensors (#6311) The code as written should work on all Tensor types; we just need to require the input and output types match. | 12 October 2021, 18:57:02 UTC |
d4e45bd | Steven Johnson | 12 October 2021, 18:56:43 UTC | [hannk] Fix > and >= op implementations (#6312) a>b should be b<=a (not b <a) a>=b should be b<a (not b<=a) | 12 October 2021, 18:56:43 UTC |
89b36b4 | Steven Johnson | 12 October 2021, 18:00:09 UTC | [hannk] Fix faulty 'shallow' logic in dconv2d (#6309) * [hannk] Fix faulty 'shallow' logic in dconv2d | 12 October 2021, 18:00:09 UTC |
e058532 | Andrew Adams | 11 October 2021, 21:56:51 UTC | store_in(MemoryType::Stack) should use alloca if the size is small (#6289) * Test using a real alloca call instead of the pseudostack * Improve test and remove debugging prints * Fix test * Switch to heap based on cumulative size rather than current size and add a test case that illustrates why this matters. * Fix test that requires actual heap allocations * Make test actually test more than one trip through the loop * Fix alignment of stack allocation * Branching is cheaper than alloca(0) * Tweak test pass condition * Move shared constant to a single locations * Namespace shuffling * Fix comment location | 11 October 2021, 21:56:51 UTC |
1e40a71 | Steven Johnson | 11 October 2021, 20:48:35 UTC | Fix for top-of-tree LLVM (#6306) * Fix for top-of-tree LLVM * drive-by fix for other bad LLVM_VERSION checks | 11 October 2021, 20:48:35 UTC |
2a2c4b0 | Andrew Adams | 10 October 2021, 21:06:57 UTC | At some point llvm re-added pavgw intrinsics (#6302) * At some point llvm re-added pavgw intrinsics This is a good thing, because these do not reliably trigger from the pattern in runtime/x86.ll * Delete more dead code | 10 October 2021, 21:06:57 UTC |
2bfa567 | Alex Reinking | 08 October 2021, 18:52:29 UTC | Add ClampUnsafeAccesses pass. (#6294) * Add ClampUnsafeAccesses pass. Fixes #6131 Inject clamps around func calls h(...) when all the following conditions hold: 1. The call flows into an indexing context, such as: `f(x) = g(h(x))` or `let y = h(x) in f(x) = g(y)` 2. The FuncValueBounds of h are smaller than those of its type 3. h's allocation bounds might be wider than its compute bounds Condition (3) is not yet implemented see #6297. | 08 October 2021, 18:52:29 UTC |
c6529ed | Steven Johnson | 08 October 2021, 01:21:42 UTC | Modernize loops, part 4/final (#6296) * Modernize loops, part 4/final Final part getting code ready for clang-tidy's modernize-loop check, plus enabling the check * Update Module.cpp | 08 October 2021, 01:21:42 UTC |
0b297f2 | Steven Johnson | 07 October 2021, 20:04:57 UTC | Modernize loops, part 3 (#6295) * Modernize loops, part 3 Part 3 of getting code ready for clang-tidy's modernize-loop check * Update Func.cpp * Address review comments | 07 October 2021, 20:04:57 UTC |
e27db6f | Zalman Stern | 07 October 2021, 16:26:52 UTC | Don't set environment for RISCV Linux as apparently it is not (#6282) used. Should not change anything. Per issue: https://github.com/halide/Halide/issues/6281 | 07 October 2021, 16:26:52 UTC |
ed87acb | Steven Johnson | 07 October 2021, 00:50:51 UTC | Modernize loops, part 2 (#6293) Part 2 of getting code ready for clang-tidy's modernize-loop check | 07 October 2021, 00:50:51 UTC |
9169734 | Steven Johnson | 06 October 2021, 20:51:06 UTC | [hannk] Add specialization for broadcast of input 0 (#6291) * [hannk] Add specialization for broadcast of input 0 Alternate fix for https://github.com/halide/Halide/pull/6290 that is Halide-only. * Update elementwise_generator.cpp * Oops, do Mul as well | 06 October 2021, 20:51:06 UTC |
71c47b3 | Steven Johnson | 06 October 2021, 20:37:26 UTC | Modernize loops, part 1 (#6292) Part 1 of getting code ready for clang-tidy's modernize-loop check: src/autoschedulers and src/runtime | 06 October 2021, 20:37:26 UTC |
81b34e2 | Basile Clement | 05 October 2021, 16:32:59 UTC | Remove unbound variable in documentation (#6287) In the example for RDom::where, the simplified case contains a free occurence of `r.x`, which should be replaced with `10` since we are in the case `r.x == 10`. | 05 October 2021, 16:32:59 UTC |
da7c66e | Steven Johnson | 04 October 2021, 16:33:15 UTC | Make parking_control (etc) use vtables (#6275) * Make parking_control (etc) use vtables This class hierarchy is clearly best modeled with virtual methods (rather than fn ptrs), but was not; we *think* this was due to COMDAT issues that have been resolved by other means. I refactored this to use virtual methods instead (and removed the unused unpark_all function); it seems to work locally. * Add -fno-rtti to runtime compile flags (needed to allow vtables in runtime code) * make all overrides 'final' * Make virtual methods protected * Make structs final too * pacify clang-tidy | 04 October 2021, 16:33:15 UTC |
2495bcc | Zalman Stern | 02 October 2021, 17:38:40 UTC | Remove hopefully dead code. (#6280) | 02 October 2021, 17:38:40 UTC |
81ad45e | Andrew Adams | 01 October 2021, 21:41:29 UTC | compiler stack usage improvements (#6239) * Reduce compiler stack usage, and grant more control over stack usage I found some code in the wild that needs 9mb of stack to lower. It's a pain to even diagnose the problem definitively, because it requires plumbing platform-specific linker flags to grant more stack. This commit: - Reduces peak stack usage of similar code in the repo (the FFT) - Increases the stack size for lowering and codegen to 32mb on all platforms, using stack switching techniques. We started doing this on Windows a while ago and it hasn't bitten us, so let's try on more platforms. - Gives user control over the amount of stack used for lowering and codegen. It shouldn't be necessary except when diagnosing problems like this in future. Using the control I was able to determine that the correctness tests all pass with 500k of stack, and the apps all pass with 1MB, so 32MB ought to be enough for anybody. I found a never-checked-in test for the mux helper which uses 10MB of stack and really shouldn't need to, so I added that (and opened an issue) as an example of how to grant more stack when necessary, even though 10MB is less than our default now. Also fixed an incorrect comment on the Block node. * Fixes for macos * Add test to cmake * Fix type of temporary * Reduce number of exprs in the mux * Fix quadratic memory usage in new test * Better comment * Variable name fix * Try giving windows a little more stack * Clarify why we want a live Stmt in scope * Review comments * Check some return values * tickle buildbots * Fixes for arm macos * Remove stray character * clang-tidy had some reasonable concerns * Comment fix * Maybe windows needs yet more stack Co-authored-by: Steven Johnson <srj@google.com> | 01 October 2021, 21:41:29 UTC |
4b9f728 | Steven Johnson | 30 September 2021, 17:16:12 UTC | Remove more obsolete MachO/COMDAT workarounds (#6274) * Remove more obsolete MachO/COMDAT workarounds (Followup to #6272) * Update metal.cpp * A few more fixes | 30 September 2021, 17:16:12 UTC |
ef387ad | Steven Johnson | 30 September 2021, 17:03:07 UTC | Minor cleanups in thread_pool_common.h (#6276) Minor hygiene noticed when doing other patches: - prefer `constexpr int` over `#define`, since we can now use C++17 in runtime code - remove redundant def of MAX_THREADS - use `do .. while (0)` idiom for functional macros | 30 September 2021, 17:03:07 UTC |
a8d7013 | Steven Johnson | 30 September 2021, 02:09:12 UTC | Remove the runtime/ssp module (#6277) * Remove the runtime/ssp module It doesn't get included via *any* path in the runtime linker, and removing it doesn't seem to affect any tests. (I haven't looked at the revision history to see when it was added and/or when inclusion of it was removed.) * Update LLVM_Runtime_Linker.cpp * Update LLVM_Runtime_Linker.cpp | 30 September 2021, 02:09:12 UTC |
e092c01 | Steven Johnson | 29 September 2021, 23:08:38 UTC | Fix alignment issues in synchronization_common.h (#6272) * Fix alignment issues in synchronization_common.h To work around old COMDAT issues, we allocated the table as a char array and cast it to what we want; unfortunately this doesn't guarantee the right alignment for the table and in some environments (eg wasm) we can get unaligned-access failures. We could fix this by forcing the right alignment, but since we fixed COMDAT issues in another way a while back (adding smarts to LLVM_Runtime_Linker), let's just remove the hack and declare it normally. Also added some drive-by changes to ensure that the hashtable size and HASH_TABLE_BITS were safe (this happened to be the case before but wasn't enforced), and also to init all the fields in hash_bucket. (Q: do we really need `check_hash()` to exist? With the mods in place above, is it possible for addr_hash() to return a bad index?) * Always use HASH_TABLE_BITS in addr_hash() * Only use check_hash() in DEBUG_RUNTIME builds | 29 September 2021, 23:08:38 UTC |
4307645 | aankit-ca | 29 September 2021, 16:56:34 UTC | [Hexagon] Remove qurt_init_fini (#6271) Including qurt_init_fini generates the below error: dlopenbuf failed: undefined symbol #140 __DTOR_LIST__ Including qurt_init_fini was needed when the pipeline was loaded using mmap. This is not needed now. Co-authored-by: Ankit Aggarwal <aankit@quicinc.com> | 29 September 2021, 16:56:34 UTC |
e836ea6 | Roman Lebedev | 28 September 2021, 08:36:38 UTC | CMake: install docs into halide subdirectory of doc dir (#6267) | 28 September 2021, 08:36:38 UTC |
8fbc788 | Steven Johnson | 27 September 2021, 17:12:25 UTC | [hannk] Add Make target to rebuild just the Halide-generated code. (#6265) * [hannk] Add Make target to rebuild just the Halide-generated code. Also, drive-by comment fix about disabling Fortran (!) when building for Android. * More changes | 27 September 2021, 17:12:25 UTC |
ebb9f19 | Roman Lebedev | 24 September 2021, 16:13:58 UTC | Usage of C++ `<thread>` header requires linking to threading library (#6257) * Usage of C++ `<thread>` header requires linking to threading library `Generator.cpp` and `ThreadPool.h` both `#include <thread>`, but don't link to the threading implementation. This fixes build for me on debian sid, which is failing otherwise with: ``` $ ninja [ 0% 2/1480][ 0% 0:00:00 + 0:33:06] Linking CXX executable src/autoschedulers/adams2019/get_host_target FAILED: src/autoschedulers/adams2019/get_host_target : && /usr/local/bin/clang++ -pipe -O3 -DNDEBUG src/autoschedulers/adams2019/CMakeFiles/get_host_target.dir/get_host_target.cpp.o -o src/autoschedulers/adams2019/get_host_target -Wl,-rpath,/repositories/halide/build/src: src/libHalide.so.13.0.0 && : ld: error: /usr/lib/gcc/x86_64-linux-gnu/11/libstdc++.so: undefined reference to pthread_create [--no-allow-shlib-undefined] clang: error: linker command failed with exit code 1 (use -v to see invocation) [ 0% 5/1480][ 0% 0:00:00 + 0:12:47] Linking CXX executable src/autoschedulers/adams2019/test_apps_autoscheduler FAILED: src/autoschedulers/adams2019/test_apps_autoscheduler : && /usr/local/bin/clang++ -pipe -O3 -DNDEBUG src/autoschedulers/adams2019/CMakeFiles/test_apps_autoscheduler.dir/test.cpp.o -o src/autoschedulers/adams2019/test_apps_autoscheduler -Wl,-rpath,/repositories/halide/build/src src/libHalide.so.13.0.0 -ldl && : ld: error: /usr/lib/gcc/x86_64-linux-gnu/11/libstdc++.so: undefined reference to pthread_create [--no-allow-shlib-undefined] clang: error: linker command failed with exit code 1 (use -v to see invocation) [ 0% 7/1480][ 0% 0:00:00 + 0:08:53] Linking CXX executable src/autoschedulers/adams2019/test_function_dag FAILED: src/autoschedulers/adams2019/test_function_dag : && /usr/local/bin/clang++ -pipe -O3 -DNDEBUG src/autoschedulers/adams2019/CMakeFiles/test_function_dag.dir/test_function_dag.cpp.o src/autoschedulers/adams2019/CMakeFiles/test_function_dag.dir/FunctionDAG.cpp.o src/autoschedulers/adams2019/CMakeFiles/test_function_dag.dir/ASLog.cpp.o -o src/autoschedulers/adams2019/test_function_dag -Wl,-rpath,/repositories/halide/build/src src/libHalide.so.13.0.0 && : ld: error: /usr/lib/gcc/x86_64-linux-gnu/11/libstdc++.so: undefined reference to pthread_create [--no-allow-shlib-undefined] clang: error: linker command failed with exit code 1 (use -v to see invocation) [ 0% 9/1480][ 0% 0:00:00 + 0:06:41] Linking CXX executable src/autoschedulers/li2018/gradient_autoscheduler_test_cpp FAILED: src/autoschedulers/li2018/gradient_autoscheduler_test_cpp : && /usr/local/bin/clang++ -pipe -O3 -DNDEBUG src/autoschedulers/li2018/CMakeFiles/gradient_autoscheduler_test_cpp.dir/test.cpp.o -o src/autoschedulers/li2018/gradient_autoscheduler_test_cpp -Wl,-rpath,/repositories/halide/build/src src/libHalide.so.13.0.0 && : ld: error: /usr/lib/gcc/x86_64-linux-gnu/11/libstdc++.so: undefined reference to pthread_create [--no-allow-shlib-undefined] clang: error: linker command failed with exit code 1 (use -v to see invocation) [ 2% 35/1480][ 0% 0:00:00 + 0:05:09] Generating included_schedule_file.runtime.o ninja: build stopped: subcommand failed. ``` * Dommy commit to retrigger bots | 24 September 2021, 16:13:58 UTC |
11ec1dc | Steven Johnson | 17 September 2021, 21:14:21 UTC | Remove remaining bits of LLVM10 support (#6245) Update various parts of the source that still assume LLVM10 is supported. (We probably need to update the buildbots as well before this lands.) | 17 September 2021, 21:14:21 UTC |
95198a7 | Michael Gharbi | 15 September 2021, 21:47:31 UTC | Remove torch/extension dependency and fix PyTorch example, adding the correct (GPU) autoscheduler (#6234) * fix static op warning * add backward * removes "torch/extension.h" dependency * suppress grad check warnings * simplifies CUDA PyTorch bindings, remove HL_PT_CUDA define * fix gradient for scalar parameter * fix style issues * Update CodeGen_PyTorch.cpp | 15 September 2021, 21:47:31 UTC |
2d0ac72 | Steven Johnson | 14 September 2021, 23:41:33 UTC | Modify hexagon_remote/Makefile to allow defining C++ #defines on the command line (#6243) * Modify hexagon_remote/Makefile to allow defining C++ #defines on the command line * Update Makefile | 14 September 2021, 23:41:33 UTC |
fdcf140 | Dillon Sharlet | 14 September 2021, 20:27:54 UTC | Improve the code quality of scalarized code (#6218) * Improve the quality of scalarized predicated loads. * Add assert * clang-format * We can't assume this assert won't be hit. * Fix implementation of single lane shuffles in deinterleave. | 14 September 2021, 20:27:54 UTC |
10e4e8e | Dillon Sharlet | 13 September 2021, 18:27:59 UTC | Fall through to LLVM for unknown shuffles on Hexagon (#6237) * Fall through to LLVM for unknown shuffles on Hexagon. * Don't fall back to LLVM, use vdelta instead. * Fix vdelta patterns | 13 September 2021, 18:27:59 UTC |
d80e5d8 | Andrew Adams | 10 September 2021, 19:31:17 UTC | Join generator watchdog timer if exception thrown (#6240) Make sure to join the generator watchdog timer when an exception is thrown. Otherwise the error message gets swallowed entirely and you just get "terminate called without an active exception" Also rejiggered the watchdog to do a timed wait on a condition variable instead of polling every 100ms. | 10 September 2021, 19:31:17 UTC |
b78b205 | Steven Johnson | 02 September 2021, 17:58:52 UTC | Upgrade clang-format and clang-tidy to LLVM-12 (#6233) | 02 September 2021, 17:58:52 UTC |
24d6bd6 | Steven Johnson | 29 August 2021, 20:02:34 UTC | Hoist unrolled prefetches to top of the block (#6230) * Hoist unrolled prefetches to top of the block When a loop with prefetch is unrolled, the prefetch instructions getting scattered through the loop can cause LLVM codegen issues in some cases (see https://bugs.llvm.org/show_bug.cgi?id=51172). As a partial mitigation for that issue, this PR adds a pass to hoist all prefetch instructions to the top of their loop. This is still a bit experimental; it definitely addresses the codegen issues we see, but makes the use of prefetch potentially less effective (since the hoisted prefetch may be too far from the eventual use to be effective). * appease clang-tidy * Avoid quadratic behavior * Use template instead of std::function * Require prefetch offset to be pure | 29 August 2021, 20:02:34 UTC |
085e11e | Andrew Adams | 27 August 2021, 21:00:14 UTC | Rename inner version of bounds_of_expr_in_scope (#6232) It's not in the explicit namespace that it's requested in (Halide::Internal), so turning on that debugging code results in compile failures. I just gave it a different name to disambiguate. | 27 August 2021, 21:00:14 UTC |
c860cab | Steven Johnson | 25 August 2021, 17:36:14 UTC | Add modernize-make-shared and modernize-make-unique to .clang-tidy and fix warnings (#6222) * Add modernize-make-shared and modernize-make-unique to .clang-tidy and fix warnings * std::initializer_list instead of std::vector * Update Pipeline.h | 25 August 2021, 17:36:14 UTC |