==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/tensor, configfile: ../../../../../../sault/virtual_test/virtualenv_005/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 2 items test_sigmoid_.py [WARNING] ME(168387:281473313443632,MainProcess):2026-01-29-17:39:40.670.017 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 0.616695, [21] [bootstrap]: 0.00070937 [type_inference]: 0.243543 [event_method]: 1.88e-05 [auto_monad]: 0.00021433 [graph_reusing]: 6.66e-06 [inline]: 3.04999e-06 [add_attr]: 0.00937617, [1] [add_attr_with_inline]: 0.00936007, [1] [Cycle 1]: 9.741e-05, [2] [tag_attr]: 1.771e-05 [meta_addattr_fg_expand]: 3.93001e-06 [parallel-infer-symbol]: 3.51001e-06 [pre_auto_parallel]: 5.12e-05 [insert-virtual-dataset]: 2.46e-06 [parallel-infer-symbol-second]: 7.29982e-07 [dataset_repeat_opt]: 2.43e-06 [pipeline_split]: 1.81e-06 [optimize]: 0.0058533, [53] [py_interpret_to_execute]: 2.348e-05 [rewriter_before_opt_a]: 6.851e-05 [opt_a]: 0.00306756, [2] [Cycle 1]: 0.00218279, [45] [expand_dump_flag]: 2.84001e-06 [switch_simplify]: 2.942e-05 [loop_unroll]: 1.311e-05 [a_1]: 0.00038825 [with_stream_mark]: 2.099e-05 [recompute_prepare]: 1.105e-05 [updatestate_depend_eliminate]: 6.26e-06 [updatestate_assign_eliminate]: 7.33e-06 [updatestate_loads_eliminate]: 5.29e-06 [parameter_eliminate]: 2.53e-06 [a_2]: 0.00012468 [accelerated_algorithm]: 9.47001e-06 [shard]: 2.63998e-06 [meta_shard_fg_expand]: 2.62001e-06 [shard_inline]: 9.34e-06 [merge_send_recv]: 1.101e-05 [auto_parallel]: 8.22e-06 [parallel]: 4.677e-05 [flash_sp]: 2.193e-05 [merge_comm]: 5.86e-06 [allreduce_fusion]: 5.14998e-06 [matmul_add_comm_reduction]: 1.265e-05 [allreduce_slice_to_reducescatter]: 7.30011e-07 [virtual_shard_identity]: 1.079e-05 [virtual_dataset]: 8.62e-06 [get_grad_eliminate_]: 8.69e-06 [virtual_output]: 8.55001e-06 [merge_forward]: 5.54e-06 [cell_reuse_recompute_pass]: 1.50999e-06 [offload_activation]: 1.396e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.811e-05 [merge_recompute_call_nodes]: 1.55001e-06 [before_grad]: 1.543e-05 [set_forward_comm_id_for_comm_node_pass]: 5.52001e-06 [meta_fg_expand]: 3.56999e-06 [flash_sp_send_recv_attached]: 2.74999e-06 [receive_attached]: 1.172e-05 [after_resolve]: 1.325e-05 [a_after_grad]: 1.331e-05 [renormalize]: 0.00083572 [add_forward_monad_depend]: 6.38e-06 [auto_monad_grad]: 2.70997e-06 [auto_monad_eliminator]: 2.475e-05 [cse]: 6.88e-05 [a_3]: 6.422e-05 [Cycle 2]: 0.00087065, [45] [expand_dump_flag]: 1.45001e-06 [switch_simplify]: 1.24e-05 [loop_unroll]: 8.67e-06 [a_1]: 0.00019879 [with_stream_mark]: 1.737e-05 [recompute_prepare]: 8.22e-06 [updatestate_depend_eliminate]: 6.53998e-06 [updatestate_assign_eliminate]: 4.60001e-06 [updatestate_loads_eliminate]: 4.57e-06 [parameter_eliminate]: 1.74998e-06 [a_2]: 0.00010889 [accelerated_algorithm]: 8.95001e-06 [shard]: 1.77999e-06 [meta_shard_fg_expand]: 2.03002e-06 [shard_inline]: 8.20999e-06 [merge_send_recv]: 9.36998e-06 [auto_parallel]: 9.98002e-06 [parallel]: 7.30998e-06 [flash_sp]: 4.79e-06 [merge_comm]: 5.57001e-06 [allreduce_fusion]: 5.04998e-06 [matmul_add_comm_reduction]: 1.077e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 9.27001e-06 [virtual_dataset]: 8.05e-06 [get_grad_eliminate_]: 7.85e-06 [virtual_output]: 7.46999e-06 [merge_forward]: 5.29998e-06 [cell_reuse_recompute_pass]: 1.79e-06 [offload_activation]: 1.132e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.743e-05 [merge_recompute_call_nodes]: 1.29998e-06 [before_grad]: 1.398e-05 [set_forward_comm_id_for_comm_node_pass]: 6.23e-06 [meta_fg_expand]: 3.48e-06 [flash_sp_send_recv_attached]: 1.19003e-06 [receive_attached]: 1.63002e-06 [after_resolve]: 1.161e-05 [a_after_grad]: 1.204e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.60999e-06 [auto_monad_grad]: 1.67001e-06 [auto_monad_eliminator]: 1.365e-05 [cse]: 2.214e-05 [a_3]: 5.118e-05 [py_interpret_to_execute_after_opt_a]: 1.715e-05 [slice_cell_reuse_recomputed_activation]: 2.44001e-06 [rewriter_after_opt_a]: 0.0001814 [convert_after_rewriter]: 1.327e-05 [order_py_execute_after_rewriter]: 7.31999e-06 [mutable_eliminate]: 0.00074398 [opt_b]: 0.00029363, [1] [Cycle 1]: 0.00028655, [7] [b_1]: 0.00018847 [b_2]: 1.067e-05 [updatestate_depend_eliminate]: 1.017e-05 [updatestate_assign_eliminate]: 4.47998e-06 [updatestate_loads_eliminate]: 4.52e-06 [renormalize]: 8.99978e-07 [cse]: 3.055e-05 [optimize_parallel_all_gather_comm]: 2.372e-05 [overlap_param_gather]: 1.82001e-06 [cconv]: 3.812e-05 [loop_unroll]: 0.00048124 [opt_after_cconv]: 0.00014263, [1] [Cycle 1]: 0.00013578, [7] [c_1]: 5.275e-05 [parameter_eliminate]: 4.82998e-06 [updatestate_depend_eliminate]: 7.88001e-06 [updatestate_assign_eliminate]: 4.47e-06 [updatestate_loads_eliminate]: 4.79e-06 [cse]: 2.449e-05 [renormalize]: 1.04e-06 [remove_dup_value]: 1.761e-05 [tuple_transform]: 9.204e-05, [1] [Cycle 1]: 8.75e-05, [4] [d_1]: 5.716e-05 [none_parameter_eliminate]: 1.72001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 9.49e-06 [partial_unused_args_eliminate]: 1.84998e-06 [add_recomputation]: 8.429e-05 [cse_after_recomputation]: 2.765e-05, [1] [Cycle 1]: 2.205e-05, [1] [cse]: 1.602e-05 [environ_conv]: 1.98e-05 [swap_dp_allreduce_reducescatter]: 8.66997e-06 [bias_add_comm_swap]: 3.19001e-06 [label_micro_interleaved_index]: 5.05001e-06 [label_fine_grained_interleaved_index]: 3.18e-06 [merge_cast_opt]: 1.83002e-06 [slice_recompute_activation]: 2.66999e-06 [micro_interleaved_order_control]: 2.69999e-06 [assign_add_opt]: 1.23002e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 1.15999e-06 [full_micro_interleaved_order_control]: 2.87002e-06 [reorder_send_recv_between_fp_bp]: 3.38999e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.64e-06 [interleave_parallel_branches]: 1.15001e-06 [overlap_opt_shard_in_pipeline]: 2.347e-05 [overlap_opt_shard_grad_in_pipeline]: 2.17999e-06 [control_data_broadcast_order]: 2.005e-05 [grouped_pairwise_exchange_alltoall]: 1.67001e-06 [offloading_packed_experts]: 5.54e-06 [overlap_recompute_and_grad_model_parallel]: 6.86001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.47001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.69998e-06 [overlap_recompute_comm]: 2.68e-06 [overlap_grad_ring_attention]: 5.64998e-06 [overlap_grad_flash_sp]: 4.401e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.26e-06 [split_layernorm_comm]: 1.72999e-06 [handle_group_info]: 1.05001e-06 [symbol_engine_optimizer]: 9.542e-05, [1] [Cycle 1]: 9.028e-05, [6] [build]: 5.02999e-06 [elim_shapecalc]: 1.296e-05 [elim_not_effective]: 1.863e-05 [opt_reshape]: 9.00999e-06 [fold_const_symbol]: 1.48e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.34999e-06 [pipeline_parallel_scheduler]: 1.67001e-06 [auto_monad_reorder]: 3.989e-05 [get_jit_bprop_graph]: 1.74e-06 [rewriter_after_jit_bprop_graph]: 5.37001e-06 [opt_after_jit_grad]: 0.356531 [validate]: 0.00010083 Sums bootstrap : 0.000709s : 0.12% type_inference : 0.243543s : 40.18% event_method : 0.000019s : 0.00% auto_monad : 0.000214s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000051s : 0.01% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000023s : 0.00% optimize.rewriter_before_opt_a : 0.000069s : 0.01% optimize.opt_a.expand_dump_flag : 0.000004s : 0.00% optimize.opt_a.switch_simplify : 0.000042s : 0.01% optimize.opt_a.loop_unroll : 0.000022s : 0.00% optimize.opt_a.a_1 : 0.000587s : 0.10% optimize.opt_a.with_stream_mark : 0.000038s : 0.01% optimize.opt_a.recompute_prepare : 0.000019s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000234s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000018s : 0.00% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000018s : 0.00% optimize.opt_a.merge_send_recv : 0.000020s : 0.00% optimize.opt_a.auto_parallel : 0.000018s : 0.00% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000027s : 0.00% optimize.opt_a.merge_comm : 0.000011s : 0.00% optimize.opt_a.allreduce_fusion : 0.000010s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000020s : 0.00% optimize.opt_a.virtual_dataset : 0.000017s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.00% optimize.opt_a.virtual_output : 0.000016s : 0.00% optimize.opt_a.merge_forward : 0.000011s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000036s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000029s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.00% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000013s : 0.00% optimize.opt_a.after_resolve : 0.000025s : 0.00% optimize.opt_a.a_after_grad : 0.000025s : 0.00% optimize.opt_a.renormalize : 0.000836s : 0.14% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000038s : 0.01% optimize.opt_a.cse : 0.000091s : 0.02% optimize.opt_a.a_3 : 0.000115s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000017s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000181s : 0.03% optimize.convert_after_rewriter : 0.000013s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000744s : 0.12% optimize.opt_b.b_1 : 0.000188s : 0.03% optimize.opt_b.b_2 : 0.000011s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000031s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.01% optimize.loop_unroll : 0.000481s : 0.08% optimize.opt_after_cconv.c_1 : 0.000053s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000024s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.00% optimize.tuple_transform.d_1 : 0.000057s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000084s : 0.01% optimize.cse_after_recomputation.cse : 0.000016s : 0.00% optimize.environ_conv : 0.000020s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000023s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000020s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000044s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000009s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000040s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.356531s : 58.81% validate : 0.000101s : 0.02% Time group info: ------[substitution.] 0.000180 55 4.94% : 0.000009s : 2: substitution.depend_value_elim 1.58% : 0.000003s : 5: substitution.elim_not_effective 1.25% : 0.000002s : 5: substitution.fold_const_symbol 4.38% : 0.000008s : 6: substitution.graph_param_transform 58.56% : 0.000105s : 1: substitution.inline 3.28% : 0.000006s : 10: substitution.j_node_and_user_rematch 5.05% : 0.000009s : 10: substitution.remove_not_recompute_node 3.05% : 0.000005s : 2: substitution.replace_old_param 9.99% : 0.000018s : 6: substitution.updatestate_pure_node_eliminater 7.92% : 0.000014s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.243471 2 99.79% : 0.242957s : 1: type_inference.infer 0.21% : 0.000514s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000104 1 100.00% : 0.000104s : 1: match.inline ------[predicate.] 0.000240 1419 0.82% : 0.000002s : 13: predicate.accumulaten_eliminater 2.86% : 0.000007s : 6: predicate.ad_related_special_op_eliminate 0.66% : 0.000002s : 12: predicate.addn_check_dump 0.91% : 0.000002s : 13: predicate.addn_zero_filter 0.72% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.94% : 0.000005s : 25: predicate.arithmetic_simplify 0.78% : 0.000002s : 13: predicate.cast_eliminate 0.79% : 0.000002s : 12: predicate.check_bprop_eliminate 0.78% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000001s : 6: predicate.const_output_eliminate 0.89% : 0.000002s : 12: predicate.depend_value_elim 0.83% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.96% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.87% : 0.000002s : 13: predicate.dict_set_item_eliminator 2.03% : 0.000005s : 12: predicate.dumpgradient_eliminate 0.43% : 0.000001s : 6: predicate.elim_not_effective 0.55% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.03% : 0.000002s : 19: predicate.environ_get_add_eliminate 1.06% : 0.000003s : 19: predicate.environ_get_depend_swap 1.84% : 0.000004s : 31: predicate.environ_get_eliminate 1.08% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.80% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.49% : 0.000004s : 14: predicate.float_depend_g_call 0.70% : 0.000002s : 12: predicate.float_environ_get_switch 1.03% : 0.000002s : 18: predicate.float_tuple_getitem_switch 0.20% : 0.000000s : 6: predicate.fold_const_symbol 0.85% : 0.000002s : 12: predicate.get_grad_eliminate 0.23% : 0.000001s : 6: predicate.graph_param_transform 0.74% : 0.000002s : 12: predicate.incorporate_call 0.65% : 0.000002s : 12: predicate.incorporate_call_switch 5.97% : 0.000014s : 63: predicate.inline 1.01% : 0.000002s : 12: predicate.inline_without_move 0.39% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.93% : 0.000002s : 12: predicate.less_batch_normalization 1.82% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.26% : 0.000005s : 38: predicate.load_eliminater 1.11% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.00% : 0.000002s : 17: predicate.loop_unroll_before_grad 1.66% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.80% : 0.000002s : 12: predicate.merge_addn 0.75% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.73% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 13: predicate.minmaximum_grad 1.66% : 0.000004s : 6: predicate.mutable_eliminate 0.46% : 0.000001s : 6: predicate.opt_reshape 0.59% : 0.000001s : 6: predicate.parallel_virtual_node 1.02% : 0.000002s : 14: predicate.partial_defer_inline 1.28% : 0.000003s : 19: predicate.partial_eliminate 0.83% : 0.000002s : 13: predicate.print_const_string_wrapper 0.73% : 0.000002s : 12: predicate.reduce_all_const_elim 0.99% : 0.000002s : 13: predicate.reduce_eliminate 2.12% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.61% : 0.000001s : 12: predicate.remove_not_recompute_node 1.16% : 0.000003s : 25: predicate.replace_applicator 0.56% : 0.000001s : 12: predicate.replace_old_param 0.38% : 0.000001s : 6: predicate.reset_defer_inline 0.85% : 0.000002s : 13: predicate.reshape_eliminate 0.79% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.68% : 0.000002s : 6: predicate.row_tensor_eliminate 0.88% : 0.000002s : 12: predicate.same_eliminate 0.56% : 0.000001s : 12: predicate.set_cell_output_no_recompute 1.02% : 0.000002s : 12: predicate.shard_identity_eliminate 0.97% : 0.000002s : 12: predicate.special_op_eliminate 0.93% : 0.000002s : 12: predicate.specialize_transform 1.01% : 0.000002s : 12: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.82% : 0.000002s : 14: predicate.switch_defer_inline 1.55% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.53% : 0.000008s : 49: predicate.switch_simplify 0.80% : 0.000002s : 13: predicate.tile_eliminate 0.80% : 0.000002s : 13: predicate.transpose_eliminate 1.57% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.48% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.45% : 0.000003s : 25: predicate.tuple_list_get_item_depend_reorder 3.28% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.47% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.71% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.34% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.22% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.54% : 0.000001s : 6: predicate.value_based_eliminate 0.77% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.76% : 0.000002s : 12: predicate.virtual_output_eliminate 0.46% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.50% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000276 4 8.86% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.14% : 0.000251s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.634132 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.48% : 0.009383s : 1: add_attr 1.48% : 0.009365s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000090s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000224s : 1: auto_monad 0.01% : 0.000045s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.12% : 0.000764s : 1: bootstrap 0.01% : 0.000042s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000024s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.00% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.08% : 0.000491s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.12% : 0.000756s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000023s : 1: opt.transform.mutable_eliminate 0.18% : 0.001151s : 78: opt.transform.opt_a 0.01% : 0.000051s : 1: opt.transform.opt_after_cconv 0.01% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000172s : 28: opt.transform.opt_b 0.01% : 0.000064s : 2: opt.transform.opt_trans_graph 0.01% : 0.000052s : 4: opt.transform.symbol_engine_opt 0.48% : 0.003071s : 1: opt_a 0.02% : 0.000146s : 1: opt_after_cconv 56.23% : 0.356555s : 1: opt_after_jit_grad 0.05% : 0.000297s : 1: opt_b 0.92% : 0.005860s : 1: optimize 0.00% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000010s : 1: order_py_execute_after_rewriter 0.01% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000027s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000056s : 1: pre_auto_parallel 0.00% : 0.000027s : 1: py_interpret_to_execute 0.00% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 0.08% : 0.000495s : 1: renormalize.infer 0.05% : 0.000332s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000189s : 1: rewriter_after_opt_a 0.01% : 0.000073s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000098s : 1: symbol_engine_optimizer 0.01% : 0.000095s : 1: tuple_transform 38.41% : 0.243572s : 1: type_inference TotalTime = 0.035066, [21] [bootstrap]: 0.00060542 [type_inference]: 0.00435563 [event_method]: 1.909e-05 [auto_monad]: 0.00016381 [graph_reusing]: 7.23999e-06 [inline]: 4.23999e-06 [add_attr]: 0.00516347, [1] [add_attr_with_inline]: 0.00514798, [1] [Cycle 1]: 7.54e-05, [2] [tag_attr]: 1.876e-05 [meta_addattr_fg_expand]: 3.2e-06 [parallel-infer-symbol]: 3.8e-06 [pre_auto_parallel]: 3.952e-05 [insert-virtual-dataset]: 2.53998e-06 [parallel-infer-symbol-second]: 9.20001e-07 [dataset_repeat_opt]: 2.54999e-06 [pipeline_split]: 1.74e-06 [optimize]: 0.0237745, [53] [py_interpret_to_execute]: 2.588e-05 [rewriter_before_opt_a]: 6.492e-05 [opt_a]: 0.0155739, [2] [Cycle 1]: 0.0145354, [45] [expand_dump_flag]: 3.59002e-06 [switch_simplify]: 2.78e-05 [loop_unroll]: 1.355e-05 [a_1]: 0.00042418 [with_stream_mark]: 2.376e-05 [recompute_prepare]: 1.228e-05 [updatestate_depend_eliminate]: 6.51e-06 [updatestate_assign_eliminate]: 8.81002e-06 [updatestate_loads_eliminate]: 6.69999e-06 [parameter_eliminate]: 1.93002e-06 [a_2]: 0.00012364 [accelerated_algorithm]: 9.84001e-06 [shard]: 3.22002e-06 [meta_shard_fg_expand]: 2.36e-06 [shard_inline]: 8.60999e-06 [merge_send_recv]: 1.174e-05 [auto_parallel]: 9.44e-06 [parallel]: 3.408e-05 [flash_sp]: 1.078e-05 [merge_comm]: 5.86998e-06 [allreduce_fusion]: 5.29e-06 [matmul_add_comm_reduction]: 1.48e-05 [allreduce_slice_to_reducescatter]: 8.99978e-07 [virtual_shard_identity]: 1.205e-05 [virtual_dataset]: 8.59e-06 [get_grad_eliminate_]: 8.07e-06 [virtual_output]: 8.68001e-06 [merge_forward]: 6.91001e-06 [cell_reuse_recompute_pass]: 1.44e-06 [offload_activation]: 1.577e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.019e-05 [merge_recompute_call_nodes]: 1.72999e-06 [before_grad]: 1.798e-05 [set_forward_comm_id_for_comm_node_pass]: 6.21e-06 [meta_fg_expand]: 3.78001e-06 [flash_sp_send_recv_attached]: 2.98003e-06 [receive_attached]: 2.66e-06 [after_resolve]: 1.626e-05 [a_after_grad]: 1.343e-05 [renormalize]: 0.0131315 [add_forward_monad_depend]: 1.013e-05 [auto_monad_grad]: 2.55002e-06 [auto_monad_eliminator]: 2.704e-05 [cse]: 4.352e-05 [a_3]: 7.937e-05 [Cycle 2]: 0.00102243, [45] [expand_dump_flag]: 2.62001e-06 [switch_simplify]: 1.245e-05 [loop_unroll]: 9.05999e-06 [a_1]: 0.0002121 [with_stream_mark]: 2.135e-05 [recompute_prepare]: 9.45001e-06 [updatestate_depend_eliminate]: 7.56001e-06 [updatestate_assign_eliminate]: 5.51e-06 [updatestate_loads_eliminate]: 5.62001e-06 [parameter_eliminate]: 1.76998e-06 [a_2]: 0.00011786 [accelerated_algorithm]: 1.094e-05 [shard]: 2.76999e-06 [meta_shard_fg_expand]: 2.78e-06 [shard_inline]: 9.17001e-06 [merge_send_recv]: 1.094e-05 [auto_parallel]: 1.312e-05 [parallel]: 9.77001e-06 [flash_sp]: 4.67e-06 [merge_comm]: 5.38002e-06 [allreduce_fusion]: 5.44e-06 [matmul_add_comm_reduction]: 1.363e-05 [allreduce_slice_to_reducescatter]: 7.7e-07 [virtual_shard_identity]: 1.127e-05 [virtual_dataset]: 9.37999e-06 [get_grad_eliminate_]: 8.33999e-06 [virtual_output]: 8.57998e-06 [merge_forward]: 6.69999e-06 [cell_reuse_recompute_pass]: 3.25002e-06 [offload_activation]: 1.697e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.91e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 1.611e-05 [set_forward_comm_id_for_comm_node_pass]: 8.28001e-06 [meta_fg_expand]: 4.08001e-06 [flash_sp_send_recv_attached]: 1.99999e-06 [receive_attached]: 2.74999e-06 [after_resolve]: 1.671e-05 [a_after_grad]: 1.271e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.75997e-06 [auto_monad_grad]: 1.56002e-06 [auto_monad_eliminator]: 1.661e-05 [cse]: 2.571e-05 [a_3]: 5.608e-05 [py_interpret_to_execute_after_opt_a]: 2.086e-05 [slice_cell_reuse_recomputed_activation]: 2.68e-06 [rewriter_after_opt_a]: 0.00019742 [convert_after_rewriter]: 1.463e-05 [order_py_execute_after_rewriter]: 6.96001e-06 [mutable_eliminate]: 0.00586549 [opt_b]: 0.00036047, [1] [Cycle 1]: 0.00034769, [7] [b_1]: 0.00021647 [b_2]: 1.112e-05 [updatestate_depend_eliminate]: 1.558e-05 [updatestate_assign_eliminate]: 5.65001e-06 [updatestate_loads_eliminate]: 5.35999e-06 [renormalize]: 1.00999e-06 [cse]: 4.872e-05 [optimize_parallel_all_gather_comm]: 3.675e-05 [overlap_param_gather]: 3.71001e-06 [cconv]: 4.421e-05 [loop_unroll]: 0.00062217 [opt_after_cconv]: 0.00015636, [1] [Cycle 1]: 0.00014822, [7] [c_1]: 5.619e-05 [parameter_eliminate]: 6.22001e-06 [updatestate_depend_eliminate]: 8.57e-06 [updatestate_assign_eliminate]: 4.70999e-06 [updatestate_loads_eliminate]: 4.27e-06 [cse]: 2.709e-05 [renormalize]: 4.90021e-07 [remove_dup_value]: 1.819e-05 [tuple_transform]: 9.643e-05, [1] [Cycle 1]: 9.124e-05, [4] [d_1]: 5.864e-05 [none_parameter_eliminate]: 1.59998e-06 [renormalize]: 2.20025e-07 [switch_simplify]: 9.89999e-06 [partial_unused_args_eliminate]: 2.29001e-06 [add_recomputation]: 8.803e-05 [cse_after_recomputation]: 2.772e-05, [1] [Cycle 1]: 2.249e-05, [1] [cse]: 1.616e-05 [environ_conv]: 8.32998e-06 [swap_dp_allreduce_reducescatter]: 2.538e-05 [bias_add_comm_swap]: 3.36999e-06 [label_micro_interleaved_index]: 6.29999e-06 [label_fine_grained_interleaved_index]: 3.16001e-06 [merge_cast_opt]: 1.53002e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.74001e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 1.14998e-06 [remove_cast_before_assign_add]: 1.22999e-06 [full_micro_interleaved_order_control]: 2.78e-06 [reorder_send_recv_between_fp_bp]: 3.31001e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.14003e-06 [interleave_split_concat_branches]: 1.23002e-06 [interleave_parallel_branches]: 1.40999e-06 [overlap_opt_shard_in_pipeline]: 3.73001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.96e-06 [control_data_broadcast_order]: 2.127e-05 [grouped_pairwise_exchange_alltoall]: 2.07999e-06 [offloading_packed_experts]: 6.16e-06 [overlap_recompute_and_grad_model_parallel]: 6.36998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.75001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.54e-06 [overlap_recompute_comm]: 2.99001e-06 [overlap_grad_ring_attention]: 5.59e-06 [overlap_grad_flash_sp]: 3.401e-05 [begin_end_overlap_inline]: 5.79981e-07 [split_matmul_comm_elemetwise]: 2.74999e-06 [split_layernorm_comm]: 1.74e-06 [handle_group_info]: 1.10001e-06 [symbol_engine_optimizer]: 0.00010616, [1] [Cycle 1]: 0.00010104, [6] [build]: 5.96998e-06 [elim_shapecalc]: 1.596e-05 [elim_not_effective]: 1.883e-05 [opt_reshape]: 1.031e-05 [fold_const_symbol]: 1.515e-05 [renormalize]: 2.69996e-07 [detach_backward]: 2.64001e-06 [pipeline_parallel_scheduler]: 1.64e-06 [auto_monad_reorder]: 3.708e-05 [get_jit_bprop_graph]: 1.86e-06 [rewriter_after_jit_bprop_graph]: 7.71999e-06 [opt_after_jit_grad]: 0.00058048 [validate]: 7.054e-05 Sums bootstrap : 0.000605s : 2.11% type_inference : 0.004356s : 15.22% event_method : 0.000019s : 0.07% auto_monad : 0.000164s : 0.57% graph_reusing : 0.000007s : 0.03% inline : 0.000004s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000019s : 0.07% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000003s : 0.01% parallel-infer-symbol : 0.000004s : 0.01% pre_auto_parallel : 0.000040s : 0.14% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000026s : 0.09% optimize.rewriter_before_opt_a : 0.000065s : 0.23% optimize.opt_a.expand_dump_flag : 0.000006s : 0.02% optimize.opt_a.switch_simplify : 0.000040s : 0.14% optimize.opt_a.loop_unroll : 0.000023s : 0.08% optimize.opt_a.a_1 : 0.000636s : 2.22% optimize.opt_a.with_stream_mark : 0.000045s : 0.16% optimize.opt_a.recompute_prepare : 0.000022s : 0.08% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.05% optimize.opt_a.updatestate_assign_eliminate : 0.000014s : 0.05% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.04% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.000242s : 0.84% optimize.opt_a.accelerated_algorithm : 0.000021s : 0.07% optimize.opt_a.shard : 0.000006s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.02% optimize.opt_a.shard_inline : 0.000018s : 0.06% optimize.opt_a.merge_send_recv : 0.000023s : 0.08% optimize.opt_a.auto_parallel : 0.000023s : 0.08% optimize.opt_a.parallel : 0.000044s : 0.15% optimize.opt_a.flash_sp : 0.000015s : 0.05% optimize.opt_a.merge_comm : 0.000011s : 0.04% optimize.opt_a.allreduce_fusion : 0.000011s : 0.04% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.10% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000023s : 0.08% optimize.opt_a.virtual_dataset : 0.000018s : 0.06% optimize.opt_a.get_grad_eliminate_ : 0.000016s : 0.06% optimize.opt_a.virtual_output : 0.000017s : 0.06% optimize.opt_a.merge_forward : 0.000014s : 0.05% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.02% optimize.opt_a.offload_activation : 0.000033s : 0.11% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000039s : 0.14% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000034s : 0.12% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.05% optimize.opt_a.meta_fg_expand : 0.000008s : 0.03% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.02% optimize.opt_a.receive_attached : 0.000005s : 0.02% optimize.opt_a.after_resolve : 0.000033s : 0.12% optimize.opt_a.a_after_grad : 0.000026s : 0.09% optimize.opt_a.renormalize : 0.013132s : 45.87% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.05% optimize.opt_a.auto_monad_grad : 0.000004s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000044s : 0.15% optimize.opt_a.cse : 0.000069s : 0.24% optimize.opt_a.a_3 : 0.000135s : 0.47% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.07% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.01% optimize.rewriter_after_opt_a : 0.000197s : 0.69% optimize.convert_after_rewriter : 0.000015s : 0.05% optimize.order_py_execute_after_rewriter : 0.000007s : 0.02% optimize.mutable_eliminate : 0.005865s : 20.49% optimize.opt_b.b_1 : 0.000216s : 0.76% optimize.opt_b.b_2 : 0.000011s : 0.04% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 0.05% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000049s : 0.17% optimize.optimize_parallel_all_gather_comm : 0.000037s : 0.13% optimize.overlap_param_gather : 0.000004s : 0.01% optimize.cconv : 0.000044s : 0.15% optimize.loop_unroll : 0.000622s : 2.17% optimize.opt_after_cconv.c_1 : 0.000056s : 0.20% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.02% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.03% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.cse : 0.000027s : 0.09% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000018s : 0.06% optimize.tuple_transform.d_1 : 0.000059s : 0.20% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.03% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000088s : 0.31% optimize.cse_after_recomputation.cse : 0.000016s : 0.06% optimize.environ_conv : 0.000008s : 0.03% optimize.swap_dp_allreduce_reducescatter : 0.000025s : 0.09% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000006s : 0.02% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000004s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000021s : 0.07% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.02% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.01% optimize.overlap_grad_ring_attention : 0.000006s : 0.02% optimize.overlap_grad_flash_sp : 0.000034s : 0.12% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000006s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.06% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.07% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.04% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 0.05% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000037s : 0.13% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000008s : 0.03% opt_after_jit_grad : 0.000580s : 2.03% validate : 0.000071s : 0.25% Time group info: ------[substitution.] 0.000222 55 5.49% : 0.000012s : 2: substitution.depend_value_elim 1.32% : 0.000003s : 5: substitution.elim_not_effective 0.93% : 0.000002s : 5: substitution.fold_const_symbol 3.43% : 0.000008s : 6: substitution.graph_param_transform 62.08% : 0.000138s : 1: substitution.inline 2.98% : 0.000007s : 10: substitution.j_node_and_user_rematch 3.74% : 0.000008s : 10: substitution.remove_not_recompute_node 3.09% : 0.000007s : 2: substitution.replace_old_param 9.11% : 0.000020s : 6: substitution.updatestate_pure_node_eliminater 7.84% : 0.000017s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.004287 2 88.33% : 0.003787s : 1: type_inference.infer 11.67% : 0.000500s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000136 1 100.00% : 0.000136s : 1: match.inline ------[predicate.] 0.000256 1419 1.05% : 0.000003s : 13: predicate.accumulaten_eliminater 1.08% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.77% : 0.000002s : 12: predicate.addn_check_dump 0.75% : 0.000002s : 13: predicate.addn_zero_filter 0.72% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 2.01% : 0.000005s : 25: predicate.arithmetic_simplify 0.95% : 0.000002s : 13: predicate.cast_eliminate 0.75% : 0.000002s : 12: predicate.check_bprop_eliminate 0.71% : 0.000002s : 12: predicate.compare_switch_simplify 0.20% : 0.000001s : 6: predicate.const_output_eliminate 0.81% : 0.000002s : 12: predicate.depend_value_elim 0.74% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.81% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.74% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.63% : 0.000004s : 12: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 6: predicate.elim_not_effective 0.49% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.07% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.15% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.01% : 0.000003s : 19: predicate.environ_get_depend_swap 1.83% : 0.000005s : 31: predicate.environ_get_eliminate 1.03% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.91% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.61% : 0.000004s : 14: predicate.float_depend_g_call 0.71% : 0.000002s : 12: predicate.float_environ_get_switch 1.25% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.39% : 0.000001s : 6: predicate.fold_const_symbol 0.77% : 0.000002s : 12: predicate.get_grad_eliminate 0.24% : 0.000001s : 6: predicate.graph_param_transform 0.70% : 0.000002s : 12: predicate.incorporate_call 0.59% : 0.000001s : 12: predicate.incorporate_call_switch 5.37% : 0.000014s : 63: predicate.inline 0.88% : 0.000002s : 12: predicate.inline_without_move 0.36% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.92% : 0.000002s : 12: predicate.less_batch_normalization 1.68% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.29% : 0.000006s : 38: predicate.load_eliminater 1.42% : 0.000004s : 6: predicate.loop_unroll_after_grad 1.07% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.75% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.77% : 0.000002s : 12: predicate.merge_addn 0.77% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.73% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.82% : 0.000002s : 13: predicate.minmaximum_grad 2.60% : 0.000007s : 6: predicate.mutable_eliminate 0.48% : 0.000001s : 6: predicate.opt_reshape 0.55% : 0.000001s : 6: predicate.parallel_virtual_node 1.21% : 0.000003s : 14: predicate.partial_defer_inline 1.20% : 0.000003s : 19: predicate.partial_eliminate 0.85% : 0.000002s : 13: predicate.print_const_string_wrapper 0.68% : 0.000002s : 12: predicate.reduce_all_const_elim 1.01% : 0.000003s : 13: predicate.reduce_eliminate 2.57% : 0.000007s : 38: predicate.redundant_stop_gradient_eliminater 0.71% : 0.000002s : 12: predicate.remove_not_recompute_node 1.11% : 0.000003s : 25: predicate.replace_applicator 0.70% : 0.000002s : 12: predicate.replace_old_param 0.56% : 0.000001s : 6: predicate.reset_defer_inline 0.80% : 0.000002s : 13: predicate.reshape_eliminate 0.93% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.54% : 0.000001s : 6: predicate.row_tensor_eliminate 1.11% : 0.000003s : 12: predicate.same_eliminate 0.46% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.84% : 0.000002s : 12: predicate.shard_identity_eliminate 0.83% : 0.000002s : 12: predicate.special_op_eliminate 0.89% : 0.000002s : 12: predicate.specialize_transform 1.18% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 0.86% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.86% : 0.000002s : 14: predicate.switch_defer_inline 1.54% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.46% : 0.000009s : 49: predicate.switch_simplify 0.75% : 0.000002s : 13: predicate.tile_eliminate 0.74% : 0.000002s : 13: predicate.transpose_eliminate 1.83% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000005s : 25: predicate.tuple_list_get_item_const_eliminator 1.48% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.21% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.55% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.40% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.63% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.49% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.42% : 0.000009s : 50: predicate.updatestate_useless_node_eliminater 0.53% : 0.000001s : 6: predicate.value_based_eliminate 0.84% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.90% : 0.000002s : 12: predicate.virtual_output_eliminate 0.35% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.49% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000334 4 8.10% : 0.000027s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.90% : 0.000307s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.078652 192 0.01% : 0.000005s : 1: ForceFp32Comm 6.57% : 0.005171s : 1: add_attr 6.55% : 0.005153s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.12% : 0.000093s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.22% : 0.000172s : 1: auto_monad 0.05% : 0.000043s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000007s : 1: bias_add_comm_swap 0.83% : 0.000650s : 1: bootstrap 0.06% : 0.000048s : 1: cconv 0.01% : 0.000005s : 1: comm_op_add_attrs 0.03% : 0.000025s : 1: control_data_broadcast_order 0.03% : 0.000020s : 1: convert_after_rewriter 0.04% : 0.000031s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000006s : 1: detach_backward 0.02% : 0.000012s : 1: environ_conv 0.03% : 0.000026s : 1: event_method 0.01% : 0.000006s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.01% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.01% : 0.000008s : 1: inline 0.01% : 0.000007s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000005s : 1: interleave_split_concat_branches 0.01% : 0.000007s : 1: label_fine_grained_interleaved_index 0.01% : 0.000010s : 1: label_micro_interleaved_index 0.80% : 0.000633s : 1: loop_unroll 0.01% : 0.000006s : 1: merge_cast_opt 0.01% : 0.000006s : 1: micro_interleaved_order_control 7.48% : 0.005887s : 1: mutable_eliminate 0.01% : 0.000011s : 1: offloading_packed_experts 0.03% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.05% : 0.000040s : 1: opt.transform.mutable_eliminate 1.59% : 0.001249s : 78: opt.transform.opt_a 0.07% : 0.000055s : 1: opt.transform.opt_after_cconv 0.05% : 0.000037s : 1: opt.transform.opt_after_jit_grad 0.25% : 0.000196s : 28: opt.transform.opt_b 0.08% : 0.000066s : 2: opt.transform.opt_trans_graph 0.07% : 0.000056s : 4: opt.transform.symbol_engine_opt 19.81% : 0.015578s : 1: opt_a 0.20% : 0.000160s : 1: opt_after_cconv 0.75% : 0.000593s : 1: opt_after_jit_grad 0.46% : 0.000366s : 1: opt_b 30.24% : 0.023782s : 1: optimize 0.05% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000011s : 1: order_py_execute_after_rewriter 0.05% : 0.000038s : 1: overlap_grad_flash_sp 0.01% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000009s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000007s : 1: overlap_param_gather 0.01% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000008s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000006s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.06% : 0.000044s : 1: pre_auto_parallel 0.04% : 0.000030s : 1: py_interpret_to_execute 0.03% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000022s : 1: remove_dup_value 16.13% : 0.012687s : 1: renormalize.infer 0.55% : 0.000429s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.26% : 0.000207s : 1: rewriter_after_opt_a 0.09% : 0.000070s : 1: rewriter_before_opt_a 0.01% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.01% : 0.000005s : 1: split_layernorm_comm 0.01% : 0.000007s : 1: split_matmul_comm_elemetwise 0.04% : 0.000033s : 1: swap_dp_allreduce_reducescatter 0.14% : 0.000109s : 1: symbol_engine_optimizer 0.13% : 0.000100s : 1: tuple_transform 5.57% : 0.004382s : 1: type_inference TotalTime = 1.22158, [21] [bootstrap]: 0.00059309 [type_inference]: 0.606117 [event_method]: 6.982e-05 [auto_monad]: 0.00037579 [graph_reusing]: 1.155e-05 [inline]: 3.39001e-06 [add_attr]: 0.0042298, [1] [add_attr_with_inline]: 0.00421667, [1] [Cycle 1]: 0.00010297, [2] [tag_attr]: 4.499e-05 [meta_addattr_fg_expand]: 1.015e-05 [parallel-infer-symbol]: 4.17e-06 [pre_auto_parallel]: 7.083e-05 [insert-virtual-dataset]: 2.82002e-06 [parallel-infer-symbol-second]: 7.50006e-07 [dataset_repeat_opt]: 2.19001e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.609174, [53] [py_interpret_to_execute]: 5.99e-05 [rewriter_before_opt_a]: 0.00016346 [opt_a]: 0.605907, [3] [Cycle 1]: 0.341823, [45] [expand_dump_flag]: 8.59e-06 [switch_simplify]: 7.504e-05 [loop_unroll]: 7.041e-05 [a_1]: 0.00220818 [with_stream_mark]: 4.769e-05 [recompute_prepare]: 0.0520543 [updatestate_depend_eliminate]: 3.519e-05 [updatestate_assign_eliminate]: 1.327e-05 [updatestate_loads_eliminate]: 1.302e-05 [parameter_eliminate]: 1.226e-05 [a_2]: 0.00037093 [accelerated_algorithm]: 5.305e-05 [shard]: 2.88e-06 [meta_shard_fg_expand]: 1.688e-05 [shard_inline]: 2.097e-05 [merge_send_recv]: 2.888e-05 [auto_parallel]: 2.496e-05 [parallel]: 2.741e-05 [flash_sp]: 1.864e-05 [merge_comm]: 1.388e-05 [allreduce_fusion]: 1.358e-05 [matmul_add_comm_reduction]: 4.844e-05 [allreduce_slice_to_reducescatter]: 1.33002e-06 [virtual_shard_identity]: 3.132e-05 [virtual_dataset]: 2.341e-05 [get_grad_eliminate_]: 2.196e-05 [virtual_output]: 2.324e-05 [merge_forward]: 1.487e-05 [cell_reuse_recompute_pass]: 2.00002e-06 [offload_activation]: 3.225e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.678e-05 [merge_recompute_call_nodes]: 1.89999e-06 [before_grad]: 4.343e-05 [set_forward_comm_id_for_comm_node_pass]: 1.493e-05 [meta_fg_expand]: 0.0486529 [flash_sp_send_recv_attached]: 7.21999e-06 [receive_attached]: 2.56e-06 [after_resolve]: 0.0001604 [a_after_grad]: 0.00021918 [renormalize]: 0.23452 [add_forward_monad_depend]: 2.914e-05 [auto_monad_grad]: 1.668e-05 [auto_monad_eliminator]: 0.00016456 [cse]: 0.0003485 [a_3]: 0.0017233 [Cycle 2]: 0.262814, [45] [expand_dump_flag]: 4.72998e-06 [switch_simplify]: 0.00011218 [loop_unroll]: 0.00010772 [a_1]: 0.0114534 [with_stream_mark]: 4.439e-05 [recompute_prepare]: 2.071e-05 [updatestate_depend_eliminate]: 3.996e-05 [updatestate_assign_eliminate]: 7.11001e-06 [updatestate_loads_eliminate]: 7.13e-06 [parameter_eliminate]: 3.25002e-06 [a_2]: 0.00016351 [accelerated_algorithm]: 1.839e-05 [shard]: 2.16e-06 [meta_shard_fg_expand]: 7.35e-06 [shard_inline]: 1.132e-05 [merge_send_recv]: 1.443e-05 [auto_parallel]: 1.377e-05 [parallel]: 1.353e-05 [flash_sp]: 5.19e-06 [merge_comm]: 6.45002e-06 [allreduce_fusion]: 6.89999e-06 [matmul_add_comm_reduction]: 1.642e-05 [allreduce_slice_to_reducescatter]: 1.04998e-06 [virtual_shard_identity]: 1.312e-05 [virtual_dataset]: 1.077e-05 [get_grad_eliminate_]: 1.039e-05 [virtual_output]: 1.009e-05 [merge_forward]: 6.89999e-06 [cell_reuse_recompute_pass]: 1.88997e-06 [offload_activation]: 1.78e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.414e-05 [merge_recompute_call_nodes]: 2.73e-06 [before_grad]: 2.019e-05 [set_forward_comm_id_for_comm_node_pass]: 7.96001e-06 [meta_fg_expand]: 0.00012002 [flash_sp_send_recv_attached]: 2.41e-06 [receive_attached]: 2.74001e-06 [after_resolve]: 2.346e-05 [a_after_grad]: 1.868e-05 [renormalize]: 0.00279801 [add_forward_monad_depend]: 1.525e-05 [auto_monad_grad]: 4.67e-06 [auto_monad_eliminator]: 4.141e-05 [cse]: 0.247067 [a_3]: 0.00012521 [Cycle 3]: 0.00124725, [45] [expand_dump_flag]: 4.53999e-06 [switch_simplify]: 1.459e-05 [loop_unroll]: 1.131e-05 [a_1]: 0.00032822 [with_stream_mark]: 3.423e-05 [recompute_prepare]: 1.211e-05 [updatestate_depend_eliminate]: 7.82e-06 [updatestate_assign_eliminate]: 6.56e-06 [updatestate_loads_eliminate]: 6.14001e-06 [parameter_eliminate]: 2.96001e-06 [a_2]: 0.00016419 [accelerated_algorithm]: 1.775e-05 [shard]: 2.94999e-06 [meta_shard_fg_expand]: 5.24998e-06 [shard_inline]: 1.295e-05 [merge_send_recv]: 1.483e-05 [auto_parallel]: 1.516e-05 [parallel]: 1.256e-05 [flash_sp]: 1.89e-06 [merge_comm]: 7.88999e-06 [allreduce_fusion]: 6.68e-06 [matmul_add_comm_reduction]: 1.631e-05 [allreduce_slice_to_reducescatter]: 7.60017e-07 [virtual_shard_identity]: 1.397e-05 [virtual_dataset]: 1.157e-05 [get_grad_eliminate_]: 1.046e-05 [virtual_output]: 1.035e-05 [merge_forward]: 7.61999e-06 [cell_reuse_recompute_pass]: 3.82002e-06 [offload_activation]: 1.614e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.386e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 1.927e-05 [set_forward_comm_id_for_comm_node_pass]: 8.00999e-06 [meta_fg_expand]: 5.37001e-06 [flash_sp_send_recv_attached]: 2.41998e-06 [receive_attached]: 3.53999e-06 [after_resolve]: 1.858e-05 [a_after_grad]: 1.755e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.93999e-06 [auto_monad_grad]: 3.21001e-06 [auto_monad_eliminator]: 2.874e-05 [cse]: 3.917e-05 [a_3]: 6.823e-05 [py_interpret_to_execute_after_opt_a]: 2.825e-05 [slice_cell_reuse_recomputed_activation]: 3.26999e-06 [rewriter_after_opt_a]: 7.816e-05 [convert_after_rewriter]: 1.07e-05 [order_py_execute_after_rewriter]: 9.40001e-06 [mutable_eliminate]: 0.00087561 [opt_b]: 0.00039974, [1] [Cycle 1]: 0.00038976, [7] [b_1]: 0.00025614 [b_2]: 1.304e-05 [updatestate_depend_eliminate]: 1.157e-05 [updatestate_assign_eliminate]: 6.60002e-06 [updatestate_loads_eliminate]: 6.35002e-06 [renormalize]: 1.02998e-06 [cse]: 5.059e-05 [optimize_parallel_all_gather_comm]: 3.016e-05 [overlap_param_gather]: 2.13002e-06 [cconv]: 4.167e-05 [loop_unroll]: 0.00053418 [opt_after_cconv]: 0.00018503, [1] [Cycle 1]: 0.00017693, [7] [c_1]: 6.929e-05 [parameter_eliminate]: 4.67e-06 [updatestate_depend_eliminate]: 1.012e-05 [updatestate_assign_eliminate]: 5.92001e-06 [updatestate_loads_eliminate]: 5.76e-06 [cse]: 3.961e-05 [renormalize]: 6.39993e-07 [remove_dup_value]: 2.244e-05 [tuple_transform]: 0.00012259, [1] [Cycle 1]: 0.00011684, [4] [d_1]: 8.282e-05 [none_parameter_eliminate]: 1.89999e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.134e-05 [partial_unused_args_eliminate]: 1.92001e-06 [add_recomputation]: 0.00010764 [cse_after_recomputation]: 4.173e-05, [1] [Cycle 1]: 3.62e-05, [1] [cse]: 2.956e-05 [environ_conv]: 1.398e-05 [swap_dp_allreduce_reducescatter]: 9.75002e-06 [bias_add_comm_swap]: 2.80002e-06 [label_micro_interleaved_index]: 5.79999e-06 [label_fine_grained_interleaved_index]: 3.23e-06 [merge_cast_opt]: 1.79998e-06 [slice_recompute_activation]: 2.68e-06 [micro_interleaved_order_control]: 2.76999e-06 [assign_add_opt]: 1.34998e-06 [ForceFp32Comm]: 9.70002e-07 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.76e-06 [reorder_send_recv_between_fp_bp]: 3.36001e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.35001e-06 [interleave_parallel_branches]: 1.62001e-06 [overlap_opt_shard_in_pipeline]: 1.39e-06 [overlap_opt_shard_grad_in_pipeline]: 2.04e-06 [control_data_broadcast_order]: 2.348e-05 [grouped_pairwise_exchange_alltoall]: 1.97001e-06 [offloading_packed_experts]: 6.29999e-06 [overlap_recompute_and_grad_model_parallel]: 6.76e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.58002e-06 [overlap_recompute_comm]: 2.71e-06 [overlap_grad_ring_attention]: 6.29001e-06 [overlap_grad_flash_sp]: 3.576e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.79001e-06 [split_layernorm_comm]: 1.74e-06 [handle_group_info]: 1.04e-06 [symbol_engine_optimizer]: 0.0001417, [1] [Cycle 1]: 0.00013675, [6] [build]: 3.051e-05 [elim_shapecalc]: 1.734e-05 [elim_not_effective]: 2.203e-05 [opt_reshape]: 1.195e-05 [fold_const_symbol]: 1.88e-05 [renormalize]: 4.39992e-07 [detach_backward]: 2.68e-06 [pipeline_parallel_scheduler]: 1.74998e-06 [auto_monad_reorder]: 3.959e-05 [get_jit_bprop_graph]: 1.94e-06 [rewriter_after_jit_bprop_graph]: 7.41001e-06 [opt_after_jit_grad]: 0.00058679 [validate]: 6.527e-05 Sums bootstrap : 0.000593s : 0.05% type_inference : 0.606117s : 49.86% event_method : 0.000070s : 0.01% auto_monad : 0.000376s : 0.03% graph_reusing : 0.000012s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000045s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000010s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000071s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000060s : 0.00% optimize.rewriter_before_opt_a : 0.000163s : 0.01% optimize.opt_a.expand_dump_flag : 0.000018s : 0.00% optimize.opt_a.switch_simplify : 0.000202s : 0.02% optimize.opt_a.loop_unroll : 0.000189s : 0.02% optimize.opt_a.a_1 : 0.013990s : 1.15% optimize.opt_a.with_stream_mark : 0.000126s : 0.01% optimize.opt_a.recompute_prepare : 0.052087s : 4.28% optimize.opt_a.updatestate_depend_eliminate : 0.000083s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000027s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000026s : 0.00% optimize.opt_a.parameter_eliminate : 0.000018s : 0.00% optimize.opt_a.a_2 : 0.000699s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000089s : 0.01% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000029s : 0.00% optimize.opt_a.shard_inline : 0.000045s : 0.00% optimize.opt_a.merge_send_recv : 0.000058s : 0.00% optimize.opt_a.auto_parallel : 0.000054s : 0.00% optimize.opt_a.parallel : 0.000053s : 0.00% optimize.opt_a.flash_sp : 0.000026s : 0.00% optimize.opt_a.merge_comm : 0.000028s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000081s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000058s : 0.00% optimize.opt_a.virtual_dataset : 0.000046s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000043s : 0.00% optimize.opt_a.virtual_output : 0.000044s : 0.00% optimize.opt_a.merge_forward : 0.000029s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000066s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000095s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000006s : 0.00% optimize.opt_a.before_grad : 0.000083s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.00% optimize.opt_a.meta_fg_expand : 0.048778s : 4.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000012s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000202s : 0.02% optimize.opt_a.a_after_grad : 0.000255s : 0.02% optimize.opt_a.renormalize : 0.237318s : 19.52% optimize.opt_a.add_forward_monad_depend : 0.000048s : 0.00% optimize.opt_a.auto_monad_grad : 0.000025s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000235s : 0.02% optimize.opt_a.cse : 0.247454s : 20.36% optimize.opt_a.a_3 : 0.001917s : 0.16% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000078s : 0.01% optimize.convert_after_rewriter : 0.000011s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000876s : 0.07% optimize.opt_b.b_1 : 0.000256s : 0.02% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000051s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000534s : 0.04% optimize.opt_after_cconv.c_1 : 0.000069s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000040s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.00% optimize.tuple_transform.d_1 : 0.000083s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000108s : 0.01% optimize.cse_after_recomputation.cse : 0.000030s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000031s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000022s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000040s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000587s : 0.05% validate : 0.000065s : 0.01% Time group info: ------[substitution.] 0.002839 310 0.69% : 0.000019s : 4: substitution.depend_value_elim 0.12% : 0.000003s : 7: substitution.elim_not_effective 0.28% : 0.000008s : 7: substitution.float_depend_g_call 0.20% : 0.000006s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000003s : 7: substitution.fold_const_symbol 32.53% : 0.000924s : 4: substitution.getattr_setattr_resolve 0.33% : 0.000009s : 9: substitution.graph_param_transform 0.13% : 0.000004s : 2: substitution.incorporate_call 0.08% : 0.000002s : 2: substitution.incorporate_call_switch 43.57% : 0.001237s : 24: substitution.inline 1.96% : 0.000056s : 5: substitution.inline_without_move 0.55% : 0.000016s : 28: substitution.j_node_and_user_rematch 1.01% : 0.000029s : 3: substitution.less_batch_normalization 0.57% : 0.000016s : 9: substitution.minmaximum_grad 0.34% : 0.000010s : 7: substitution.partial_eliminate 0.67% : 0.000019s : 28: substitution.remove_not_recompute_node 3.88% : 0.000110s : 38: substitution.replace_applicator 0.78% : 0.000022s : 19: substitution.replace_old_param 1.01% : 0.000029s : 1: substitution.set_cell_output_no_recompute 1.20% : 0.000034s : 9: substitution.tuple_list_convert_item_index_to_positive 0.61% : 0.000017s : 9: substitution.tuple_list_get_item_const_eliminator 0.85% : 0.000024s : 9: substitution.tuple_list_get_item_depend_reorder 4.69% : 0.000133s : 31: substitution.tuple_list_get_item_eliminator 0.79% : 0.000022s : 9: substitution.tuple_list_get_set_item_eliminator 1.14% : 0.000032s : 16: substitution.updatestate_pure_node_eliminater 1.93% : 0.000055s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.606004 2 99.66% : 0.603934s : 1: type_inference.infer 0.34% : 0.002070s : 1: type_inference.specialize ------[replace.] 0.000699 49 10.49% : 0.000073s : 3: replace.getattr_setattr_resolve 40.47% : 0.000283s : 24: replace.inline 8.66% : 0.000061s : 1: replace.replace_applicator 38.45% : 0.000269s : 20: replace.tuple_list_get_item_eliminator 1.93% : 0.000013s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002181 49 40.05% : 0.000873s : 3: match.getattr_setattr_resolve 55.11% : 0.001202s : 24: match.inline 0.85% : 0.000018s : 1: match.replace_applicator 3.43% : 0.000075s : 20: match.tuple_list_get_item_eliminator 0.57% : 0.000012s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001319 8683 0.91% : 0.000012s : 85: predicate.accumulaten_eliminater 0.27% : 0.000004s : 9: predicate.ad_related_special_op_eliminate 0.37% : 0.000005s : 37: predicate.addn_check_dump 0.87% : 0.000012s : 85: predicate.addn_zero_filter 0.81% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 1.76% : 0.000023s : 122: predicate.arithmetic_simplify 0.90% : 0.000012s : 85: predicate.cast_eliminate 2.68% : 0.000035s : 260: predicate.check_bprop_eliminate 0.39% : 0.000005s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.40% : 0.000005s : 37: predicate.depend_value_elim 0.90% : 0.000012s : 85: predicate.dict_get_item_const_eliminator 0.97% : 0.000013s : 85: predicate.dict_get_item_eliminator 0.89% : 0.000012s : 85: predicate.dict_set_item_eliminator 0.30% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.06% : 0.000001s : 9: predicate.elim_not_effective 0.16% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 0.95% : 0.000013s : 94: predicate.environ_add_const_eliminate 0.92% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.91% : 0.000012s : 94: predicate.environ_get_depend_swap 1.34% : 0.000018s : 131: predicate.environ_get_eliminate 0.92% : 0.000012s : 94: predicate.environ_get_set_eliminate 1.34% : 0.000018s : 130: predicate.exchange_switch_depend_value 1.93% : 0.000025s : 130: predicate.float_depend_g_call 0.44% : 0.000006s : 37: predicate.float_environ_get_switch 0.48% : 0.000006s : 46: predicate.float_tuple_getitem_switch 0.05% : 0.000001s : 9: predicate.fold_const_symbol 0.45% : 0.000006s : 37: predicate.get_grad_eliminate 0.57% : 0.000007s : 20: predicate.getattr_setattr_resolve 0.08% : 0.000001s : 9: predicate.graph_param_transform 0.40% : 0.000005s : 37: predicate.incorporate_call 0.35% : 0.000005s : 37: predicate.incorporate_call_switch 4.53% : 0.000060s : 307: predicate.inline 1.58% : 0.000021s : 111: predicate.inline_without_move 0.21% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.57% : 0.000007s : 37: predicate.less_batch_normalization 1.44% : 0.000019s : 123: predicate.list_to_tuple_eliminator_ 3.13% : 0.000041s : 208: predicate.load_eliminater 0.27% : 0.000004s : 9: predicate.loop_unroll_after_grad 2.15% : 0.000028s : 197: predicate.loop_unroll_before_grad 1.18% : 0.000016s : 103: predicate.make_slice_get_slice_eliminator 0.43% : 0.000006s : 37: predicate.merge_addn 2.54% : 0.000034s : 256: predicate.micro_step_allgather_replace 2.62% : 0.000035s : 256: predicate.mini_step_allgather_replace 0.85% : 0.000011s : 85: predicate.minmaximum_grad 0.37% : 0.000005s : 9: predicate.mutable_eliminate 0.12% : 0.000002s : 9: predicate.opt_reshape 0.11% : 0.000002s : 9: predicate.parallel_virtual_node 2.39% : 0.000032s : 130: predicate.partial_defer_inline 1.43% : 0.000019s : 114: predicate.partial_eliminate 0.86% : 0.000011s : 85: predicate.print_const_string_wrapper 0.44% : 0.000006s : 37: predicate.reduce_all_const_elim 1.07% : 0.000014s : 85: predicate.reduce_eliminate 2.17% : 0.000029s : 208: predicate.redundant_stop_gradient_eliminater 0.27% : 0.000004s : 37: predicate.remove_not_recompute_node 2.48% : 0.000033s : 363: predicate.replace_applicator 0.74% : 0.000010s : 111: predicate.replace_old_param 0.12% : 0.000002s : 9: predicate.reset_defer_inline 0.88% : 0.000012s : 85: predicate.reshape_eliminate 2.69% : 0.000035s : 256: predicate.row_tensor_add_zeros_like 0.13% : 0.000002s : 9: predicate.row_tensor_eliminate 4.53% : 0.000060s : 260: predicate.same_eliminate 0.36% : 0.000005s : 39: predicate.set_cell_output_no_recompute 0.46% : 0.000006s : 37: predicate.shard_identity_eliminate 0.25% : 0.000003s : 18: predicate.special_op_eliminate 0.49% : 0.000006s : 37: predicate.specialize_transform 2.77% : 0.000036s : 256: predicate.split_environ_get_set_with_tuple_value 1.44% : 0.000019s : 111: predicate.stack_unstack_eliminate 0.11% : 0.000001s : 9: predicate.switch_call_monad_eliminater 1.46% : 0.000019s : 130: predicate.switch_defer_inline 4.05% : 0.000053s : 390: predicate.switch_layer_defer_inline 4.32% : 0.000057s : 373: predicate.switch_simplify 0.90% : 0.000012s : 85: predicate.tile_eliminate 0.89% : 0.000012s : 85: predicate.transpose_eliminate 1.15% : 0.000015s : 103: predicate.tuple_list_convert_item_index_to_positive 1.25% : 0.000017s : 103: predicate.tuple_list_get_item_const_eliminator 1.10% : 0.000014s : 103: predicate.tuple_list_get_item_depend_reorder 2.46% : 0.000032s : 160: predicate.tuple_list_get_item_eliminator 1.25% : 0.000016s : 103: predicate.tuple_list_get_set_item_eliminator 1.76% : 0.000023s : 140: predicate.tuple_list_set_item_eliminator 1.37% : 0.000018s : 123: predicate.tuple_to_list_eliminator_ 2.13% : 0.000028s : 208: predicate.updatestate_pure_node_eliminater 2.71% : 0.000036s : 246: predicate.updatestate_useless_node_eliminater 0.14% : 0.000002s : 9: predicate.value_based_eliminate 0.42% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.42% : 0.000006s : 37: predicate.virtual_output_eliminate 0.10% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.12% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.297698 53 99.32% : 0.295661s : 23: func_graph_cloner_run.FuncGraphClonerGraph 0.68% : 0.002037s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.143539 243 0.00% : 0.000004s : 1: ForceFp32Comm 0.20% : 0.004237s : 1: add_attr 0.20% : 0.004221s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000113s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000389s : 1: auto_monad 0.00% : 0.000044s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.03% : 0.000637s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000014s : 1: convert_after_rewriter 0.00% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000017s : 1: environ_conv 0.00% : 0.000080s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000017s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000545s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000890s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000029s : 1: opt.transform.mutable_eliminate 3.26% : 0.069817s : 125: opt.transform.opt_a 0.00% : 0.000068s : 1: opt.transform.opt_after_cconv 0.00% : 0.000042s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000235s : 28: opt.transform.opt_b 0.05% : 0.001069s : 2: opt.transform.opt_resolve 0.00% : 0.000092s : 2: opt.transform.opt_trans_graph 0.00% : 0.000066s : 4: opt.transform.symbol_engine_opt 28.27% : 0.605911s : 1: opt_a 0.01% : 0.000189s : 1: opt_after_cconv 0.03% : 0.000600s : 1: opt_after_jit_grad 0.02% : 0.000404s : 1: opt_b 28.42% : 0.609181s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000077s : 1: pre_auto_parallel 0.00% : 0.000065s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000026s : 1: remove_dup_value 10.80% : 0.231517s : 2: renormalize.infer 0.27% : 0.005765s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000084s : 1: rewriter_after_opt_a 0.01% : 0.000169s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000145s : 1: symbol_engine_optimizer 0.01% : 0.000126s : 1: tuple_transform 28.28% : 0.606153s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__input_value_range_float[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__input_value_range_float[0],max_mem:4.0M [WARNING] ME(168387:281473313443632,MainProcess):2026-01-29-17:40:32.103.72 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. . [hook] pytest_runtest_teardown:test_sigmoid__input_value_range_float[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__input_value_range_float[1],max_mem:4.0M =============================== warnings summary =============================== ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 2 passed, 25 warnings in 218.87s (0:03:38) ==================