==================================================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_002/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(167911:281473202921264,MainProcess):2026-01-29-17:39:15.556.308 [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 = 0.248493, [21] [bootstrap]: 0.00066928 [type_inference]: 0.0152566 [event_method]: 1.625e-05 [auto_monad]: 0.00017721 [graph_reusing]: 6.07001e-06 [inline]: 3.53e-06 [add_attr]: 0.22461, [1] [add_attr_with_inline]: 0.224595, [1] [Cycle 1]: 9.131e-05, [2] [tag_attr]: 1.753e-05 [meta_addattr_fg_expand]: 4.22e-06 [parallel-infer-symbol]: 3.93001e-06 [pre_auto_parallel]: 4.54e-05 [insert-virtual-dataset]: 2.67001e-06 [parallel-infer-symbol-second]: 7.50006e-07 [dataset_repeat_opt]: 2.29001e-06 [pipeline_split]: 1.94e-06 [optimize]: 0.00643289, [53] [py_interpret_to_execute]: 2.011e-05 [rewriter_before_opt_a]: 7.307e-05 [opt_a]: 0.00309101, [2] [Cycle 1]: 0.00211562, [45] [expand_dump_flag]: 3.09001e-06 [switch_simplify]: 2.665e-05 [loop_unroll]: 1.298e-05 [a_1]: 0.00037799 [with_stream_mark]: 2.215e-05 [recompute_prepare]: 1.043e-05 [updatestate_depend_eliminate]: 6.60002e-06 [updatestate_assign_eliminate]: 6.01e-06 [updatestate_loads_eliminate]: 5.22e-06 [parameter_eliminate]: 1.97001e-06 [a_2]: 0.00012327 [accelerated_algorithm]: 9.51e-06 [shard]: 3.75e-06 [meta_shard_fg_expand]: 2.41e-06 [shard_inline]: 8.96998e-06 [merge_send_recv]: 1.018e-05 [auto_parallel]: 8.26002e-06 [parallel]: 4.649e-05 [flash_sp]: 1.003e-05 [merge_comm]: 6.76e-06 [allreduce_fusion]: 5.20999e-06 [matmul_add_comm_reduction]: 1.225e-05 [allreduce_slice_to_reducescatter]: 1.05001e-06 [virtual_shard_identity]: 1.103e-05 [virtual_dataset]: 8.95001e-06 [get_grad_eliminate_]: 8.45001e-06 [virtual_output]: 8.27998e-06 [merge_forward]: 5.55001e-06 [cell_reuse_recompute_pass]: 1.37e-06 [offload_activation]: 1.327e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.789e-05 [merge_recompute_call_nodes]: 1.71998e-06 [before_grad]: 1.57e-05 [set_forward_comm_id_for_comm_node_pass]: 6.17999e-06 [meta_fg_expand]: 3.86001e-06 [flash_sp_send_recv_attached]: 3.08e-06 [receive_attached]: 2.30002e-06 [after_resolve]: 1.328e-05 [a_after_grad]: 1.342e-05 [renormalize]: 0.00082909 [add_forward_monad_depend]: 7.51001e-06 [auto_monad_grad]: 2.62001e-06 [auto_monad_eliminator]: 2.645e-05 [cse]: 5.806e-05 [a_3]: 7.127e-05 [Cycle 2]: 0.00096147, [45] [expand_dump_flag]: 2.04999e-06 [switch_simplify]: 1.148e-05 [loop_unroll]: 8.58001e-06 [a_1]: 0.00021435 [with_stream_mark]: 2.246e-05 [recompute_prepare]: 9.64e-06 [updatestate_depend_eliminate]: 6.61999e-06 [updatestate_assign_eliminate]: 5.54e-06 [updatestate_loads_eliminate]: 5.71998e-06 [parameter_eliminate]: 2.43e-06 [a_2]: 0.00011378 [accelerated_algorithm]: 9.72999e-06 [shard]: 2.37999e-06 [meta_shard_fg_expand]: 2.91e-06 [shard_inline]: 9.17999e-06 [merge_send_recv]: 1.05e-05 [auto_parallel]: 1.159e-05 [parallel]: 1.003e-05 [flash_sp]: 4.08001e-06 [merge_comm]: 5.97001e-06 [allreduce_fusion]: 5.15999e-06 [matmul_add_comm_reduction]: 1.192e-05 [allreduce_slice_to_reducescatter]: 5.59987e-07 [virtual_shard_identity]: 9.26002e-06 [virtual_dataset]: 9.07001e-06 [get_grad_eliminate_]: 7.95998e-06 [virtual_output]: 8.52e-06 [merge_forward]: 5.61998e-06 [cell_reuse_recompute_pass]: 2.60002e-06 [offload_activation]: 1.419e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.807e-05 [merge_recompute_call_nodes]: 1.62001e-06 [before_grad]: 1.489e-05 [set_forward_comm_id_for_comm_node_pass]: 5.58002e-06 [meta_fg_expand]: 3.85e-06 [flash_sp_send_recv_attached]: 2.06998e-06 [receive_attached]: 2.07001e-06 [after_resolve]: 1.417e-05 [a_after_grad]: 1.278e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.26e-06 [auto_monad_grad]: 2.46e-06 [auto_monad_eliminator]: 1.864e-05 [cse]: 3.063e-05 [a_3]: 5.404e-05 [py_interpret_to_execute_after_opt_a]: 2.132e-05 [slice_cell_reuse_recomputed_activation]: 2.71999e-06 [rewriter_after_opt_a]: 0.00020704 [convert_after_rewriter]: 1.386e-05 [order_py_execute_after_rewriter]: 8.02e-06 [mutable_eliminate]: 0.00083535 [opt_b]: 0.0003458, [1] [Cycle 1]: 0.00033427, [7] [b_1]: 0.00020825 [b_2]: 1.257e-05 [updatestate_depend_eliminate]: 1.424e-05 [updatestate_assign_eliminate]: 5.53002e-06 [updatestate_loads_eliminate]: 4.89998e-06 [renormalize]: 1.24e-06 [cse]: 4.329e-05 [optimize_parallel_all_gather_comm]: 2.905e-05 [overlap_param_gather]: 2.24001e-06 [cconv]: 4.084e-05 [loop_unroll]: 0.00069279 [opt_after_cconv]: 0.00017912, [1] [Cycle 1]: 0.00016937, [7] [c_1]: 6.29e-05 [parameter_eliminate]: 6.19001e-06 [updatestate_depend_eliminate]: 1.189e-05 [updatestate_assign_eliminate]: 5.34e-06 [updatestate_loads_eliminate]: 4.62e-06 [cse]: 3.648e-05 [renormalize]: 9.79984e-07 [remove_dup_value]: 1.998e-05 [tuple_transform]: 0.00010297, [1] [Cycle 1]: 9.698e-05, [4] [d_1]: 6.206e-05 [none_parameter_eliminate]: 1.75001e-06 [renormalize]: 2.9002e-07 [switch_simplify]: 1.101e-05 [partial_unused_args_eliminate]: 2.31e-06 [add_recomputation]: 9.452e-05 [cse_after_recomputation]: 2.95e-05, [1] [Cycle 1]: 2.4e-05, [1] [cse]: 1.818e-05 [environ_conv]: 2.306e-05 [swap_dp_allreduce_reducescatter]: 8.15e-06 [bias_add_comm_swap]: 4.48001e-06 [label_micro_interleaved_index]: 6.98e-06 [label_fine_grained_interleaved_index]: 3.23e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.84001e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.42999e-06 [ForceFp32Comm]: 9.39996e-07 [remove_cast_before_assign_add]: 1.25001e-06 [full_micro_interleaved_order_control]: 2.84999e-06 [reorder_send_recv_between_fp_bp]: 2.97002e-06 [comm_op_add_attrs]: 1.59e-06 [add_comm_op_reuse_tag]: 1.39e-06 [interleave_split_concat_branches]: 1.26002e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 3.027e-05 [overlap_opt_shard_grad_in_pipeline]: 1.92999e-06 [control_data_broadcast_order]: 2.314e-05 [grouped_pairwise_exchange_alltoall]: 1.79e-06 [offloading_packed_experts]: 6.19999e-06 [overlap_recompute_and_grad_model_parallel]: 6.84999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22e-06 [overlap_recompute_allgather_and_fa_grad]: 1.62001e-06 [overlap_recompute_comm]: 2.68998e-06 [overlap_grad_ring_attention]: 5.87001e-06 [overlap_grad_flash_sp]: 4.977e-05 [begin_end_overlap_inline]: 6.50005e-07 [split_matmul_comm_elemetwise]: 2.41998e-06 [split_layernorm_comm]: 2.12999e-06 [handle_group_info]: 9.89996e-07 [symbol_engine_optimizer]: 0.00011496, [1] [Cycle 1]: 0.00010869, [6] [build]: 6.46e-06 [elim_shapecalc]: 1.652e-05 [elim_not_effective]: 2.073e-05 [opt_reshape]: 9.80002e-06 [fold_const_symbol]: 1.63e-05 [renormalize]: 7.7e-07 [detach_backward]: 2.71e-06 [pipeline_parallel_scheduler]: 1.72001e-06 [auto_monad_reorder]: 4.363e-05 [get_jit_bprop_graph]: 2.04999e-06 [rewriter_after_jit_bprop_graph]: 6.28e-06 [opt_after_jit_grad]: 0.00089645 [validate]: 8.539e-05 Sums bootstrap : 0.000669s : 2.95% type_inference : 0.015257s : 67.29% event_method : 0.000016s : 0.07% auto_monad : 0.000177s : 0.78% graph_reusing : 0.000006s : 0.03% inline : 0.000004s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.08% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.02% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000045s : 0.20% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000020s : 0.09% optimize.rewriter_before_opt_a : 0.000073s : 0.32% optimize.opt_a.expand_dump_flag : 0.000005s : 0.02% optimize.opt_a.switch_simplify : 0.000038s : 0.17% optimize.opt_a.loop_unroll : 0.000022s : 0.10% optimize.opt_a.a_1 : 0.000592s : 2.61% optimize.opt_a.with_stream_mark : 0.000045s : 0.20% optimize.opt_a.recompute_prepare : 0.000020s : 0.09% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.06% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.05% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.05% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000237s : 1.05% optimize.opt_a.accelerated_algorithm : 0.000019s : 0.08% optimize.opt_a.shard : 0.000006s : 0.03% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.02% optimize.opt_a.shard_inline : 0.000018s : 0.08% optimize.opt_a.merge_send_recv : 0.000021s : 0.09% optimize.opt_a.auto_parallel : 0.000020s : 0.09% optimize.opt_a.parallel : 0.000057s : 0.25% optimize.opt_a.flash_sp : 0.000014s : 0.06% optimize.opt_a.merge_comm : 0.000013s : 0.06% optimize.opt_a.allreduce_fusion : 0.000010s : 0.05% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.11% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000020s : 0.09% optimize.opt_a.virtual_dataset : 0.000018s : 0.08% optimize.opt_a.get_grad_eliminate_ : 0.000016s : 0.07% optimize.opt_a.virtual_output : 0.000017s : 0.07% optimize.opt_a.merge_forward : 0.000011s : 0.05% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.02% optimize.opt_a.offload_activation : 0.000027s : 0.12% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000036s : 0.16% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000031s : 0.13% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 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 : 0.000004s : 0.02% optimize.opt_a.after_resolve : 0.000027s : 0.12% optimize.opt_a.a_after_grad : 0.000026s : 0.12% optimize.opt_a.renormalize : 0.000829s : 3.66% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.04% optimize.opt_a.auto_monad_grad : 0.000005s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000045s : 0.20% optimize.opt_a.cse : 0.000089s : 0.39% optimize.opt_a.a_3 : 0.000125s : 0.55% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.09% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.01% optimize.rewriter_after_opt_a : 0.000207s : 0.91% optimize.convert_after_rewriter : 0.000014s : 0.06% optimize.order_py_execute_after_rewriter : 0.000008s : 0.04% optimize.mutable_eliminate : 0.000835s : 3.68% optimize.opt_b.b_1 : 0.000208s : 0.92% optimize.opt_b.b_2 : 0.000013s : 0.06% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.06% 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 : 0.01% optimize.opt_b.cse : 0.000043s : 0.19% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.13% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000041s : 0.18% optimize.loop_unroll : 0.000693s : 3.06% optimize.opt_after_cconv.c_1 : 0.000063s : 0.28% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.05% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.cse : 0.000036s : 0.16% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000020s : 0.09% optimize.tuple_transform.d_1 : 0.000062s : 0.27% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.05% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000095s : 0.42% optimize.cse_after_recomputation.cse : 0.000018s : 0.08% optimize.environ_conv : 0.000023s : 0.10% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.04% optimize.bias_add_comm_swap : 0.000004s : 0.02% optimize.label_micro_interleaved_index : 0.000007s : 0.03% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% 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 : 0.000002s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000030s : 0.13% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000023s : 0.10% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.03% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.03% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 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 : 0.03% optimize.overlap_grad_flash_sp : 0.000050s : 0.22% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 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 : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.07% optimize.symbol_engine_optimizer.elim_not_effective : 0.000021s : 0.09% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.04% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000016s : 0.07% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000044s : 0.19% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000006s : 0.03% opt_after_jit_grad : 0.000896s : 3.95% validate : 0.000085s : 0.38% Time group info: ------[substitution.] 0.000181 55 5.05% : 0.000009s : 2: substitution.depend_value_elim 2.01% : 0.000004s : 5: substitution.elim_not_effective 1.36% : 0.000002s : 5: substitution.fold_const_symbol 4.27% : 0.000008s : 6: substitution.graph_param_transform 52.14% : 0.000094s : 1: substitution.inline 3.20% : 0.000006s : 10: substitution.j_node_and_user_rematch 4.76% : 0.000009s : 10: substitution.remove_not_recompute_node 3.11% : 0.000006s : 2: substitution.replace_old_param 15.53% : 0.000028s : 6: substitution.updatestate_pure_node_eliminater 8.58% : 0.000016s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.015178 2 96.41% : 0.014633s : 1: type_inference.infer 3.59% : 0.000545s : 1: type_inference.specialize ------[replace.] 0.000016 1 100.00% : 0.000016s : 1: replace.inline ------[match.] 0.000093 1 100.00% : 0.000093s : 1: match.inline ------[predicate.] 0.000261 1419 0.81% : 0.000002s : 13: predicate.accumulaten_eliminater 1.84% : 0.000005s : 6: predicate.ad_related_special_op_eliminate 0.63% : 0.000002s : 12: predicate.addn_check_dump 0.81% : 0.000002s : 13: predicate.addn_zero_filter 0.68% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.95% : 0.000005s : 25: predicate.arithmetic_simplify 0.80% : 0.000002s : 13: predicate.cast_eliminate 0.79% : 0.000002s : 12: predicate.check_bprop_eliminate 0.75% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000001s : 6: predicate.const_output_eliminate 0.77% : 0.000002s : 12: predicate.depend_value_elim 0.91% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.85% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.91% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.81% : 0.000005s : 12: predicate.dumpgradient_eliminate 0.36% : 0.000001s : 6: predicate.elim_not_effective 0.51% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.20% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.09% : 0.000003s : 19: predicate.environ_get_depend_swap 1.85% : 0.000005s : 31: predicate.environ_get_eliminate 1.22% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.76% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.47% : 0.000004s : 14: predicate.float_depend_g_call 0.77% : 0.000002s : 12: predicate.float_environ_get_switch 1.03% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 6: predicate.fold_const_symbol 0.80% : 0.000002s : 12: predicate.get_grad_eliminate 0.35% : 0.000001s : 6: predicate.graph_param_transform 0.77% : 0.000002s : 12: predicate.incorporate_call 0.57% : 0.000001s : 12: predicate.incorporate_call_switch 5.40% : 0.000014s : 63: predicate.inline 0.87% : 0.000002s : 12: predicate.inline_without_move 0.35% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.06% : 0.000003s : 12: predicate.less_batch_normalization 1.79% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.17% : 0.000006s : 38: predicate.load_eliminater 1.66% : 0.000004s : 6: predicate.loop_unroll_after_grad 1.04% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.63% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.75% : 0.000002s : 12: predicate.merge_addn 0.79% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.75% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.63% : 0.000002s : 13: predicate.minmaximum_grad 1.79% : 0.000005s : 6: predicate.mutable_eliminate 0.52% : 0.000001s : 6: predicate.opt_reshape 0.52% : 0.000001s : 6: predicate.parallel_virtual_node 0.93% : 0.000002s : 14: predicate.partial_defer_inline 1.10% : 0.000003s : 19: predicate.partial_eliminate 0.78% : 0.000002s : 13: predicate.print_const_string_wrapper 0.75% : 0.000002s : 12: predicate.reduce_all_const_elim 1.00% : 0.000003s : 13: predicate.reduce_eliminate 2.27% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 12: predicate.remove_not_recompute_node 0.93% : 0.000002s : 25: predicate.replace_applicator 0.54% : 0.000001s : 12: predicate.replace_old_param 0.40% : 0.000001s : 6: predicate.reset_defer_inline 0.77% : 0.000002s : 13: predicate.reshape_eliminate 0.89% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.69% : 0.000002s : 6: predicate.row_tensor_eliminate 0.88% : 0.000002s : 12: predicate.same_eliminate 0.45% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.98% : 0.000003s : 12: predicate.shard_identity_eliminate 1.04% : 0.000003s : 12: predicate.special_op_eliminate 0.81% : 0.000002s : 12: predicate.specialize_transform 1.66% : 0.000004s : 12: predicate.split_environ_get_set_with_tuple_value 1.07% : 0.000003s : 12: predicate.stack_unstack_eliminate 0.49% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.75% : 0.000002s : 14: predicate.switch_defer_inline 1.56% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.38% : 0.000009s : 49: predicate.switch_simplify 0.81% : 0.000002s : 13: predicate.tile_eliminate 0.85% : 0.000002s : 13: predicate.transpose_eliminate 1.95% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.54% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.35% : 0.000009s : 37: predicate.tuple_list_get_item_eliminator 1.55% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.57% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.56% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.19% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.66% : 0.000010s : 50: predicate.updatestate_useless_node_eliminater 0.44% : 0.000001s : 6: predicate.value_based_eliminate 0.80% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.81% : 0.000002s : 12: predicate.virtual_output_eliminate 0.47% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.66% : 0.000002s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000268 4 9.89% : 0.000027s : 1: func_graph_cloner_run.FuncGraphClonerGraph 90.11% : 0.000242s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.481813 192 0.00% : 0.000004s : 1: ForceFp32Comm 46.62% : 0.224616s : 1: add_attr 46.62% : 0.224600s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000100s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000185s : 1: auto_monad 0.01% : 0.000049s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.15% : 0.000729s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000008s : 1: comm_op_add_attrs 0.01% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000020s : 1: convert_after_rewriter 0.01% : 0.000033s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000028s : 1: environ_conv 0.00% : 0.000024s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 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% : 0.000007s : 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% : 0.000010s : 1: label_micro_interleaved_index 0.15% : 0.000713s : 1: loop_unroll 0.00% : 0.000008s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.18% : 0.000854s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000030s : 1: opt.transform.mutable_eliminate 0.24% : 0.001170s : 78: opt.transform.opt_a 0.01% : 0.000061s : 1: opt.transform.opt_after_cconv 0.01% : 0.000048s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000190s : 28: opt.transform.opt_b 0.01% : 0.000071s : 2: opt.transform.opt_trans_graph 0.01% : 0.000059s : 4: opt.transform.symbol_engine_opt 0.64% : 0.003095s : 1: opt_a 0.04% : 0.000184s : 1: opt_after_cconv 0.19% : 0.000920s : 1: opt_after_jit_grad 0.07% : 0.000350s : 1: opt_b 1.34% : 0.006439s : 1: optimize 0.01% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000054s : 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 0.01% : 0.000036s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 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% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000050s : 1: pre_auto_parallel 0.01% : 0.000025s : 1: py_interpret_to_execute 0.01% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000024s : 1: remove_dup_value 0.10% : 0.000505s : 1: renormalize.infer 0.07% : 0.000314s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000218s : 1: rewriter_after_opt_a 0.02% : 0.000078s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000008s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000118s : 1: symbol_engine_optimizer 0.02% : 0.000106s : 1: tuple_transform 3.17% : 0.015281s : 1: type_inference TotalTime = 0.141063, [21] [bootstrap]: 0.00053081 [type_inference]: 0.128624 [event_method]: 1.724e-05 [auto_monad]: 0.00016217 [graph_reusing]: 6.55002e-06 [inline]: 3.36001e-06 [add_attr]: 0.00493415, [1] [add_attr_with_inline]: 0.00492102, [1] [Cycle 1]: 6.875e-05, [2] [tag_attr]: 1.717e-05 [meta_addattr_fg_expand]: 3.68999e-06 [parallel-infer-symbol]: 3.78001e-06 [pre_auto_parallel]: 3.716e-05 [insert-virtual-dataset]: 2.43e-06 [parallel-infer-symbol-second]: 8.00006e-07 [dataset_repeat_opt]: 1.86998e-06 [pipeline_split]: 1.89999e-06 [optimize]: 0.00584947, [53] [py_interpret_to_execute]: 2.377e-05 [rewriter_before_opt_a]: 5.679e-05 [opt_a]: 0.00306312, [2] [Cycle 1]: 0.00210364, [45] [expand_dump_flag]: 3.31001e-06 [switch_simplify]: 2.58e-05 [loop_unroll]: 1.301e-05 [a_1]: 0.00037733 [with_stream_mark]: 1.858e-05 [recompute_prepare]: 1.054e-05 [updatestate_depend_eliminate]: 6.29999e-06 [updatestate_assign_eliminate]: 5.47001e-06 [updatestate_loads_eliminate]: 6.51e-06 [parameter_eliminate]: 1.88002e-06 [a_2]: 0.00012007 [accelerated_algorithm]: 9.37999e-06 [shard]: 2.65002e-06 [meta_shard_fg_expand]: 2.31e-06 [shard_inline]: 8.89998e-06 [merge_send_recv]: 1.062e-05 [auto_parallel]: 8.05999e-06 [parallel]: 3.296e-05 [flash_sp]: 9.69999e-06 [merge_comm]: 5.78002e-06 [allreduce_fusion]: 5.66e-06 [matmul_add_comm_reduction]: 1.24e-05 [allreduce_slice_to_reducescatter]: 6.59988e-07 [virtual_shard_identity]: 1.071e-05 [virtual_dataset]: 8.47998e-06 [get_grad_eliminate_]: 8.37e-06 [virtual_output]: 8.18999e-06 [merge_forward]: 5.78002e-06 [cell_reuse_recompute_pass]: 1.39e-06 [offload_activation]: 1.402e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.93e-05 [merge_recompute_call_nodes]: 1.97001e-06 [before_grad]: 1.625e-05 [set_forward_comm_id_for_comm_node_pass]: 5.62001e-06 [meta_fg_expand]: 3.51999e-06 [flash_sp_send_recv_attached]: 2.56e-06 [receive_attached]: 2.58e-06 [after_resolve]: 1.208e-05 [a_after_grad]: 1.27e-05 [renormalize]: 0.00085148 [add_forward_monad_depend]: 6.69001e-06 [auto_monad_grad]: 2.75997e-06 [auto_monad_eliminator]: 2.428e-05 [cse]: 4.432e-05 [a_3]: 6.54e-05 [Cycle 2]: 0.00094648, [45] [expand_dump_flag]: 1.69e-06 [switch_simplify]: 1.023e-05 [loop_unroll]: 8.41002e-06 [a_1]: 0.00020222 [with_stream_mark]: 1.504e-05 [recompute_prepare]: 9.05001e-06 [updatestate_depend_eliminate]: 6.11998e-06 [updatestate_assign_eliminate]: 4.88001e-06 [updatestate_loads_eliminate]: 5.09e-06 [parameter_eliminate]: 7.89994e-07 [a_2]: 0.00011254 [accelerated_algorithm]: 1.051e-05 [shard]: 1.84e-06 [meta_shard_fg_expand]: 2.33002e-06 [shard_inline]: 8.44998e-06 [merge_send_recv]: 8.95001e-06 [auto_parallel]: 8.63001e-06 [parallel]: 7.14001e-06 [flash_sp]: 3.67002e-06 [merge_comm]: 5.56e-06 [allreduce_fusion]: 5.19e-06 [matmul_add_comm_reduction]: 1.014e-05 [allreduce_slice_to_reducescatter]: 6.10016e-07 [virtual_shard_identity]: 1.002e-05 [virtual_dataset]: 8.73001e-06 [get_grad_eliminate_]: 8.57e-06 [virtual_output]: 8.43001e-06 [merge_forward]: 5.00999e-06 [cell_reuse_recompute_pass]: 1.72999e-06 [offload_activation]: 1.08e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.817e-05 [merge_recompute_call_nodes]: 9.10019e-07 [before_grad]: 1.562e-05 [set_forward_comm_id_for_comm_node_pass]: 6.21e-06 [meta_fg_expand]: 3.69002e-06 [flash_sp_send_recv_attached]: 1.25999e-06 [receive_attached]: 1.43002e-06 [after_resolve]: 1.163e-05 [a_after_grad]: 1.232e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.40999e-06 [auto_monad_grad]: 1.91998e-06 [auto_monad_eliminator]: 1.417e-05 [cse]: 2.233e-05 [a_3]: 5.177e-05 [py_interpret_to_execute_after_opt_a]: 1.448e-05 [slice_cell_reuse_recomputed_activation]: 2.54001e-06 [rewriter_after_opt_a]: 0.00019098 [convert_after_rewriter]: 1.088e-05 [order_py_execute_after_rewriter]: 7.55e-06 [mutable_eliminate]: 0.00072789 [opt_b]: 0.00029779, [1] [Cycle 1]: 0.00028979, [7] [b_1]: 0.00018695 [b_2]: 1.062e-05 [updatestate_depend_eliminate]: 1.054e-05 [updatestate_assign_eliminate]: 5.10001e-06 [updatestate_loads_eliminate]: 5.10001e-06 [renormalize]: 4.7998e-07 [cse]: 2.747e-05 [optimize_parallel_all_gather_comm]: 2.328e-05 [overlap_param_gather]: 6.54001e-06 [cconv]: 3.519e-05 [loop_unroll]: 0.00052355 [opt_after_cconv]: 0.00015177, [1] [Cycle 1]: 0.00014442, [7] [c_1]: 5.303e-05 [parameter_eliminate]: 4.49002e-06 [updatestate_depend_eliminate]: 9.68002e-06 [updatestate_assign_eliminate]: 5.07999e-06 [updatestate_loads_eliminate]: 4.63999e-06 [cse]: 2.548e-05 [renormalize]: 3.89991e-07 [remove_dup_value]: 1.747e-05 [tuple_transform]: 9.554e-05, [1] [Cycle 1]: 9.021e-05, [4] [d_1]: 5.697e-05 [none_parameter_eliminate]: 1.60001e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 9.30001e-06 [partial_unused_args_eliminate]: 2.01998e-06 [add_recomputation]: 7.717e-05 [cse_after_recomputation]: 2.783e-05, [1] [Cycle 1]: 2.263e-05, [1] [cse]: 1.639e-05 [environ_conv]: 7.22002e-06 [swap_dp_allreduce_reducescatter]: 7.77e-06 [bias_add_comm_swap]: 3.19001e-06 [label_micro_interleaved_index]: 4.87e-06 [label_fine_grained_interleaved_index]: 2.86999e-06 [merge_cast_opt]: 1.37e-06 [slice_recompute_activation]: 2.38002e-06 [micro_interleaved_order_control]: 3.04999e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 8.80013e-07 [remove_cast_before_assign_add]: 1.12999e-06 [full_micro_interleaved_order_control]: 2.58e-06 [reorder_send_recv_between_fp_bp]: 3.22002e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.04998e-06 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.22e-06 [overlap_opt_shard_in_pipeline]: 4.68999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.86e-06 [control_data_broadcast_order]: 2.073e-05 [grouped_pairwise_exchange_alltoall]: 2.26e-06 [offloading_packed_experts]: 5.81003e-06 [overlap_recompute_and_grad_model_parallel]: 6.02001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.51002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.45001e-06 [overlap_recompute_comm]: 2.64999e-06 [overlap_grad_ring_attention]: 5.65001e-06 [overlap_grad_flash_sp]: 3.062e-05 [begin_end_overlap_inline]: 5.50004e-07 [split_matmul_comm_elemetwise]: 2.58e-06 [split_layernorm_comm]: 2.11e-06 [handle_group_info]: 9.79984e-07 [symbol_engine_optimizer]: 0.00010055, [1] [Cycle 1]: 9.503e-05, [6] [build]: 4.80001e-06 [elim_shapecalc]: 1.363e-05 [elim_not_effective]: 1.756e-05 [opt_reshape]: 9.79e-06 [fold_const_symbol]: 1.47e-05 [renormalize]: 2.09984e-07 [detach_backward]: 2.22001e-06 [pipeline_parallel_scheduler]: 1.39003e-06 [auto_monad_reorder]: 3.083e-05 [get_jit_bprop_graph]: 2.02999e-06 [rewriter_after_jit_bprop_graph]: 5.38002e-06 [opt_after_jit_grad]: 0.00056834 [validate]: 9.024e-05 Sums bootstrap : 0.000531s : 0.39% type_inference : 0.128624s : 95.31% event_method : 0.000017s : 0.01% auto_monad : 0.000162s : 0.12% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000037s : 0.03% 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 : 0.000024s : 0.02% optimize.rewriter_before_opt_a : 0.000057s : 0.04% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000036s : 0.03% optimize.opt_a.loop_unroll : 0.000021s : 0.02% optimize.opt_a.a_1 : 0.000580s : 0.43% optimize.opt_a.with_stream_mark : 0.000034s : 0.02% optimize.opt_a.recompute_prepare : 0.000020s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000010s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000233s : 0.17% optimize.opt_a.accelerated_algorithm : 0.000020s : 0.01% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000017s : 0.01% optimize.opt_a.merge_send_recv : 0.000020s : 0.01% optimize.opt_a.auto_parallel : 0.000017s : 0.01% optimize.opt_a.parallel : 0.000040s : 0.03% optimize.opt_a.flash_sp : 0.000013s : 0.01% optimize.opt_a.merge_comm : 0.000011s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000021s : 0.02% optimize.opt_a.virtual_dataset : 0.000017s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.01% optimize.opt_a.virtual_output : 0.000017s : 0.01% optimize.opt_a.merge_forward : 0.000011s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000037s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000032s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000024s : 0.02% optimize.opt_a.a_after_grad : 0.000025s : 0.02% optimize.opt_a.renormalize : 0.000852s : 0.63% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000038s : 0.03% optimize.opt_a.cse : 0.000067s : 0.05% optimize.opt_a.a_3 : 0.000117s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000014s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000191s : 0.14% optimize.convert_after_rewriter : 0.000011s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.01% optimize.mutable_eliminate : 0.000728s : 0.54% optimize.opt_b.b_1 : 0.000187s : 0.14% optimize.opt_b.b_2 : 0.000011s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000027s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000023s : 0.02% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000035s : 0.03% optimize.loop_unroll : 0.000524s : 0.39% optimize.opt_after_cconv.c_1 : 0.000053s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000025s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000017s : 0.01% optimize.tuple_transform.d_1 : 0.000057s : 0.04% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000077s : 0.06% optimize.cse_after_recomputation.cse : 0.000016s : 0.01% optimize.environ_conv : 0.000007s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% 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 : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000005s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 0.02% 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 : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000014s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000018s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000031s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000568s : 0.42% validate : 0.000090s : 0.07% Time group info: ------[substitution.] 0.000168 55 4.63% : 0.000008s : 2: substitution.depend_value_elim 1.63% : 0.000003s : 5: substitution.elim_not_effective 1.24% : 0.000002s : 5: substitution.fold_const_symbol 4.51% : 0.000008s : 6: substitution.graph_param_transform 61.57% : 0.000103s : 1: substitution.inline 3.26% : 0.000005s : 10: substitution.j_node_and_user_rematch 4.57% : 0.000008s : 10: substitution.remove_not_recompute_node 2.41% : 0.000004s : 2: substitution.replace_old_param 8.41% : 0.000014s : 6: substitution.updatestate_pure_node_eliminater 7.76% : 0.000013s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.128557 2 99.58% : 0.128022s : 1: type_inference.infer 0.42% : 0.000536s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000102 1 100.00% : 0.000102s : 1: match.inline ------[predicate.] 0.000237 1419 0.79% : 0.000002s : 13: predicate.accumulaten_eliminater 1.35% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.72% : 0.000002s : 12: predicate.addn_check_dump 1.02% : 0.000002s : 13: predicate.addn_zero_filter 1.01% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.98% : 0.000005s : 25: predicate.arithmetic_simplify 0.78% : 0.000002s : 13: predicate.cast_eliminate 0.82% : 0.000002s : 12: predicate.check_bprop_eliminate 0.73% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000001s : 6: predicate.const_output_eliminate 0.75% : 0.000002s : 12: predicate.depend_value_elim 0.82% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.85% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.83% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.26% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.26% : 0.000001s : 6: predicate.elim_not_effective 0.64% : 0.000002s : 6: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.04% : 0.000002s : 19: predicate.environ_get_add_eliminate 1.13% : 0.000003s : 19: predicate.environ_get_depend_swap 1.82% : 0.000004s : 31: predicate.environ_get_eliminate 1.25% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.78% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.40% : 0.000003s : 14: predicate.float_depend_g_call 0.65% : 0.000002s : 12: predicate.float_environ_get_switch 1.09% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 6: predicate.fold_const_symbol 1.12% : 0.000003s : 12: predicate.get_grad_eliminate 0.28% : 0.000001s : 6: predicate.graph_param_transform 0.73% : 0.000002s : 12: predicate.incorporate_call 0.62% : 0.000001s : 12: predicate.incorporate_call_switch 5.62% : 0.000013s : 63: predicate.inline 1.14% : 0.000003s : 12: predicate.inline_without_move 0.44% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.15% : 0.000003s : 12: predicate.less_batch_normalization 1.61% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.26% : 0.000005s : 38: predicate.load_eliminater 1.34% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.07% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.97% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.73% : 0.000002s : 12: predicate.merge_addn 0.74% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 13: predicate.minmaximum_grad 1.28% : 0.000003s : 6: predicate.mutable_eliminate 0.44% : 0.000001s : 6: predicate.opt_reshape 0.63% : 0.000001s : 6: predicate.parallel_virtual_node 1.02% : 0.000002s : 14: predicate.partial_defer_inline 1.17% : 0.000003s : 19: predicate.partial_eliminate 0.77% : 0.000002s : 13: predicate.print_const_string_wrapper 0.75% : 0.000002s : 12: predicate.reduce_all_const_elim 1.01% : 0.000002s : 13: predicate.reduce_eliminate 2.29% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000001s : 12: predicate.remove_not_recompute_node 1.14% : 0.000003s : 25: predicate.replace_applicator 0.60% : 0.000001s : 12: predicate.replace_old_param 0.30% : 0.000001s : 6: predicate.reset_defer_inline 0.83% : 0.000002s : 13: predicate.reshape_eliminate 0.80% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.51% : 0.000001s : 6: predicate.row_tensor_eliminate 1.06% : 0.000003s : 12: predicate.same_eliminate 0.49% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.94% : 0.000002s : 12: predicate.shard_identity_eliminate 1.06% : 0.000003s : 12: predicate.special_op_eliminate 0.89% : 0.000002s : 12: predicate.specialize_transform 1.00% : 0.000002s : 12: predicate.split_environ_get_set_with_tuple_value 0.91% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.87% : 0.000002s : 14: predicate.switch_defer_inline 1.61% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.60% : 0.000009s : 49: predicate.switch_simplify 0.82% : 0.000002s : 13: predicate.tile_eliminate 0.89% : 0.000002s : 13: predicate.transpose_eliminate 1.74% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.82% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.03% : 0.000007s : 37: predicate.tuple_list_get_item_eliminator 1.90% : 0.000005s : 25: predicate.tuple_list_get_set_item_eliminator 2.82% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.49% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.29% : 0.000005s : 38: predicate.updatestate_pure_node_eliminater 3.56% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.42% : 0.000001s : 6: predicate.value_based_eliminate 0.89% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.99% : 0.000002s : 12: predicate.virtual_output_eliminate 0.36% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.54% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000296 4 7.50% : 0.000022s : 1: func_graph_cloner_run.FuncGraphClonerGraph 92.50% : 0.000273s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.154070 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.21% : 0.004941s : 1: add_attr 3.20% : 0.004926s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.05% : 0.000082s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.11% : 0.000171s : 1: auto_monad 0.02% : 0.000036s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.37% : 0.000563s : 1: bootstrap 0.03% : 0.000040s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.02% : 0.000025s : 1: control_data_broadcast_order 0.01% : 0.000016s : 1: convert_after_rewriter 0.02% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000011s : 1: environ_conv 0.02% : 0.000025s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.01% : 0.000008s : 1: label_micro_interleaved_index 0.35% : 0.000533s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.48% : 0.000740s : 1: mutable_eliminate 0.01% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000020s : 1: opt.transform.mutable_eliminate 0.75% : 0.001148s : 78: opt.transform.opt_a 0.03% : 0.000052s : 1: opt.transform.opt_after_cconv 0.02% : 0.000036s : 1: opt.transform.opt_after_jit_grad 0.11% : 0.000170s : 28: opt.transform.opt_b 0.04% : 0.000064s : 2: opt.transform.opt_trans_graph 0.03% : 0.000053s : 4: opt.transform.symbol_engine_opt 1.99% : 0.003067s : 1: opt_a 0.10% : 0.000156s : 1: opt_after_cconv 0.38% : 0.000580s : 1: opt_after_jit_grad 0.20% : 0.000302s : 1: opt_b 3.80% : 0.005856s : 1: optimize 0.02% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 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 0.03% : 0.000041s : 1: pre_auto_parallel 0.02% : 0.000029s : 1: py_interpret_to_execute 0.01% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000022s : 1: remove_dup_value 0.31% : 0.000483s : 1: renormalize.infer 0.23% : 0.000360s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.13% : 0.000198s : 1: rewriter_after_opt_a 0.04% : 0.000062s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000104s : 1: symbol_engine_optimizer 0.06% : 0.000099s : 1: tuple_transform 83.50% : 0.128650s : 1: type_inference TotalTime = 0.380287, [21] [bootstrap]: 0.00052972 [type_inference]: 0.0842829 [event_method]: 7.451e-05 [auto_monad]: 0.00033663 [graph_reusing]: 9.67001e-06 [inline]: 3.21999e-06 [add_attr]: 0.00462285, [1] [add_attr_with_inline]: 0.00460752, [1] [Cycle 1]: 0.00026305, [2] [tag_attr]: 8.87e-05 [meta_addattr_fg_expand]: 1.081e-05 [parallel-infer-symbol]: 4.38999e-06 [pre_auto_parallel]: 7.674e-05 [insert-virtual-dataset]: 2.89999e-06 [parallel-infer-symbol-second]: 8.39995e-07 [dataset_repeat_opt]: 2.06e-06 [pipeline_split]: 1.71e-06 [optimize]: 0.289051, [53] [py_interpret_to_execute]: 6.106e-05 [rewriter_before_opt_a]: 0.00017595 [opt_a]: 0.210214, [3] [Cycle 1]: 0.201803, [45] [expand_dump_flag]: 8.97999e-06 [switch_simplify]: 7.932e-05 [loop_unroll]: 7.15e-05 [a_1]: 0.00232055 [with_stream_mark]: 7.437e-05 [recompute_prepare]: 4.617e-05 [updatestate_depend_eliminate]: 1.657e-05 [updatestate_assign_eliminate]: 1.34e-05 [updatestate_loads_eliminate]: 1.252e-05 [parameter_eliminate]: 4.15999e-06 [a_2]: 0.00035213 [accelerated_algorithm]: 4.991e-05 [shard]: 3.12002e-06 [meta_shard_fg_expand]: 9.02999e-06 [shard_inline]: 2.369e-05 [merge_send_recv]: 2.564e-05 [auto_parallel]: 2.197e-05 [parallel]: 2.582e-05 [flash_sp]: 1.754e-05 [merge_comm]: 1.566e-05 [allreduce_fusion]: 1.634e-05 [matmul_add_comm_reduction]: 4.942e-05 [allreduce_slice_to_reducescatter]: 9.79984e-07 [virtual_shard_identity]: 2.97e-05 [virtual_dataset]: 2.454e-05 [get_grad_eliminate_]: 2.335e-05 [virtual_output]: 2.335e-05 [merge_forward]: 6.686e-05 [cell_reuse_recompute_pass]: 7.61001e-06 [offload_activation]: 4.741e-05 [cell_reuse_handle_not_recompute_node_pass]: 9.611e-05 [merge_recompute_call_nodes]: 3.18e-06 [before_grad]: 6.743e-05 [set_forward_comm_id_for_comm_node_pass]: 2.817e-05 [meta_fg_expand]: 0.137266 [flash_sp_send_recv_attached]: 6.14001e-06 [receive_attached]: 2.56e-06 [after_resolve]: 0.00016911 [a_after_grad]: 0.00022409 [renormalize]: 0.0455292 [add_forward_monad_depend]: 2.899e-05 [auto_monad_grad]: 1.804e-05 [auto_monad_eliminator]: 0.00018176 [cse]: 0.00036067 [a_3]: 0.00191736 [Cycle 2]: 0.00699198, [45] [expand_dump_flag]: 7.08998e-06 [switch_simplify]: 0.0001103 [loop_unroll]: 0.00010207 [a_1]: 0.00320434 [with_stream_mark]: 3.715e-05 [recompute_prepare]: 2.265e-05 [updatestate_depend_eliminate]: 3.915e-05 [updatestate_assign_eliminate]: 6.97002e-06 [updatestate_loads_eliminate]: 6.58e-06 [parameter_eliminate]: 3.53e-06 [a_2]: 0.00016427 [accelerated_algorithm]: 1.941e-05 [shard]: 2.19001e-06 [meta_shard_fg_expand]: 5.90002e-06 [shard_inline]: 3.656e-05 [merge_send_recv]: 1.544e-05 [auto_parallel]: 1.524e-05 [parallel]: 1.214e-05 [flash_sp]: 4.33999e-06 [merge_comm]: 7.23e-06 [allreduce_fusion]: 6.60002e-06 [matmul_add_comm_reduction]: 1.611e-05 [allreduce_slice_to_reducescatter]: 9.5999e-07 [virtual_shard_identity]: 1.606e-05 [virtual_dataset]: 1.206e-05 [get_grad_eliminate_]: 1.129e-05 [virtual_output]: 1.073e-05 [merge_forward]: 7.3e-06 [cell_reuse_recompute_pass]: 2.32999e-06 [offload_activation]: 1.588e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.71e-05 [merge_recompute_call_nodes]: 1.75001e-06 [before_grad]: 2.187e-05 [set_forward_comm_id_for_comm_node_pass]: 8e-06 [meta_fg_expand]: 9.822e-05 [flash_sp_send_recv_attached]: 2.26e-06 [receive_attached]: 2.59001e-06 [after_resolve]: 2.311e-05 [a_after_grad]: 1.877e-05 [renormalize]: 0.0021848 [add_forward_monad_depend]: 1.144e-05 [auto_monad_grad]: 3.07002e-06 [auto_monad_eliminator]: 3.48e-05 [cse]: 0.00015362 [a_3]: 0.00010999 [Cycle 3]: 0.00139323, [45] [expand_dump_flag]: 3.4e-06 [switch_simplify]: 1.594e-05 [loop_unroll]: 1.302e-05 [a_1]: 0.00037328 [with_stream_mark]: 2.572e-05 [recompute_prepare]: 1.475e-05 [updatestate_depend_eliminate]: 8.77e-06 [updatestate_assign_eliminate]: 7.29001e-06 [updatestate_loads_eliminate]: 7.12997e-06 [parameter_eliminate]: 2.06998e-06 [a_2]: 0.00016934 [accelerated_algorithm]: 1.876e-05 [shard]: 2.39999e-06 [meta_shard_fg_expand]: 4.52e-06 [shard_inline]: 1.298e-05 [merge_send_recv]: 1.324e-05 [auto_parallel]: 1.377e-05 [parallel]: 1.217e-05 [flash_sp]: 2.27001e-06 [merge_comm]: 7.83999e-06 [allreduce_fusion]: 6.37001e-06 [matmul_add_comm_reduction]: 1.533e-05 [allreduce_slice_to_reducescatter]: 1.15999e-06 [virtual_shard_identity]: 1.576e-05 [virtual_dataset]: 1.228e-05 [get_grad_eliminate_]: 1.165e-05 [virtual_output]: 1.079e-05 [merge_forward]: 7.46001e-06 [cell_reuse_recompute_pass]: 3.40998e-06 [offload_activation]: 1.674e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.348e-05 [merge_recompute_call_nodes]: 1.95001e-06 [before_grad]: 2.012e-05 [set_forward_comm_id_for_comm_node_pass]: 8.85999e-06 [meta_fg_expand]: 5.44998e-06 [flash_sp_send_recv_attached]: 1.92999e-06 [receive_attached]: 2.54999e-06 [after_resolve]: 1.938e-05 [a_after_grad]: 1.78e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.84999e-06 [auto_monad_grad]: 1.76e-05 [auto_monad_eliminator]: 2.641e-05 [cse]: 4.543e-05 [a_3]: 0.00011722 [py_interpret_to_execute_after_opt_a]: 2.639e-05 [slice_cell_reuse_recomputed_activation]: 2.73e-06 [rewriter_after_opt_a]: 8.39e-05 [convert_after_rewriter]: 1.14e-05 [order_py_execute_after_rewriter]: 9.05999e-06 [mutable_eliminate]: 0.00092113 [opt_b]: 0.00047184, [1] [Cycle 1]: 0.00046054, [7] [b_1]: 0.00029819 [b_2]: 1.377e-05 [updatestate_depend_eliminate]: 1.672e-05 [updatestate_assign_eliminate]: 7.17002e-06 [updatestate_loads_eliminate]: 7.29001e-06 [renormalize]: 8.70001e-07 [cse]: 6.37e-05 [optimize_parallel_all_gather_comm]: 3.199e-05 [overlap_param_gather]: 2.29001e-06 [cconv]: 4.076e-05 [loop_unroll]: 0.00070132 [opt_after_cconv]: 0.00022924, [1] [Cycle 1]: 0.00021867, [7] [c_1]: 8.399e-05 [parameter_eliminate]: 6.84001e-06 [updatestate_depend_eliminate]: 1.376e-05 [updatestate_assign_eliminate]: 6.92002e-06 [updatestate_loads_eliminate]: 6.11998e-06 [cse]: 5.126e-05 [renormalize]: 8.2e-07 [remove_dup_value]: 2.319e-05 [tuple_transform]: 0.00013384, [1] [Cycle 1]: 0.00012786, [4] [d_1]: 8.768e-05 [none_parameter_eliminate]: 1.94999e-06 [renormalize]: 4.10015e-07 [switch_simplify]: 1.287e-05 [partial_unused_args_eliminate]: 2.34001e-06 [add_recomputation]: 0.00011833 [cse_after_recomputation]: 0.0750991, [1] [Cycle 1]: 0.0750896, [1] [cse]: 0.0750449 [environ_conv]: 1.957e-05 [swap_dp_allreduce_reducescatter]: 2.208e-05 [bias_add_comm_swap]: 3.91001e-06 [label_micro_interleaved_index]: 9.60001e-06 [label_fine_grained_interleaved_index]: 2.85998e-06 [merge_cast_opt]: 1.67999e-06 [slice_recompute_activation]: 2.74001e-06 [micro_interleaved_order_control]: 2.81e-06 [assign_add_opt]: 1.63002e-06 [ForceFp32Comm]: 1.24e-06 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.48e-06 [reorder_send_recv_between_fp_bp]: 3.01999e-06 [comm_op_add_attrs]: 1.14e-06 [add_comm_op_reuse_tag]: 1.42999e-06 [interleave_split_concat_branches]: 1.62001e-06 [interleave_parallel_branches]: 1.50001e-06 [overlap_opt_shard_in_pipeline]: 1.71002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.91e-06 [control_data_broadcast_order]: 2.999e-05 [grouped_pairwise_exchange_alltoall]: 1.62999e-06 [offloading_packed_experts]: 6.89999e-06 [overlap_recompute_and_grad_model_parallel]: 7.26001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.76e-06 [overlap_recompute_allgather_and_fa_grad]: 1.68002e-06 [overlap_recompute_comm]: 2.99999e-06 [overlap_grad_ring_attention]: 7.60998e-06 [overlap_grad_flash_sp]: 3.939e-05 [begin_end_overlap_inline]: 6.60017e-07 [split_matmul_comm_elemetwise]: 2.29001e-06 [split_layernorm_comm]: 2.12999e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00019106, [1] [Cycle 1]: 0.00017914, [6] [build]: 1.775e-05 [elim_shapecalc]: 4.019e-05 [elim_not_effective]: 3.584e-05 [opt_reshape]: 1.243e-05 [fold_const_symbol]: 2.175e-05 [renormalize]: 7.79983e-07 [detach_backward]: 2.12001e-06 [pipeline_parallel_scheduler]: 1.52999e-06 [auto_monad_reorder]: 4.899e-05 [get_jit_bprop_graph]: 2.29999e-06 [rewriter_after_jit_bprop_graph]: 9.76e-06 [opt_after_jit_grad]: 0.00090713 [validate]: 7.905e-05 Sums bootstrap : 0.000530s : 0.15% type_inference : 0.084283s : 23.29% event_method : 0.000075s : 0.02% auto_monad : 0.000337s : 0.09% graph_reusing : 0.000010s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000089s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000011s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000077s : 0.02% 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 : 0.000061s : 0.02% optimize.rewriter_before_opt_a : 0.000176s : 0.05% optimize.opt_a.expand_dump_flag : 0.000019s : 0.01% optimize.opt_a.switch_simplify : 0.000206s : 0.06% optimize.opt_a.loop_unroll : 0.000187s : 0.05% optimize.opt_a.a_1 : 0.005898s : 1.63% optimize.opt_a.with_stream_mark : 0.000137s : 0.04% optimize.opt_a.recompute_prepare : 0.000084s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000064s : 0.02% optimize.opt_a.updatestate_assign_eliminate : 0.000028s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000026s : 0.01% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000686s : 0.19% optimize.opt_a.accelerated_algorithm : 0.000088s : 0.02% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000019s : 0.01% optimize.opt_a.shard_inline : 0.000073s : 0.02% optimize.opt_a.merge_send_recv : 0.000054s : 0.02% optimize.opt_a.auto_parallel : 0.000051s : 0.01% optimize.opt_a.parallel : 0.000050s : 0.01% optimize.opt_a.flash_sp : 0.000024s : 0.01% optimize.opt_a.merge_comm : 0.000031s : 0.01% optimize.opt_a.allreduce_fusion : 0.000029s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000081s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000062s : 0.02% optimize.opt_a.virtual_dataset : 0.000049s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.01% optimize.opt_a.virtual_output : 0.000045s : 0.01% optimize.opt_a.merge_forward : 0.000082s : 0.02% optimize.opt_a.cell_reuse_recompute_pass : 0.000013s : 0.00% optimize.opt_a.offload_activation : 0.000080s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000147s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000007s : 0.00% optimize.opt_a.before_grad : 0.000109s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000045s : 0.01% optimize.opt_a.meta_fg_expand : 0.137370s : 37.96% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.00% optimize.opt_a.after_resolve : 0.000212s : 0.06% optimize.opt_a.a_after_grad : 0.000261s : 0.07% optimize.opt_a.renormalize : 0.047714s : 13.19% optimize.opt_a.add_forward_monad_depend : 0.000043s : 0.01% optimize.opt_a.auto_monad_grad : 0.000039s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000243s : 0.07% optimize.opt_a.cse : 0.000560s : 0.15% optimize.opt_a.a_3 : 0.002145s : 0.59% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000084s : 0.02% optimize.convert_after_rewriter : 0.000011s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000921s : 0.25% optimize.opt_b.b_1 : 0.000298s : 0.08% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000064s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000701s : 0.19% optimize.opt_after_cconv.c_1 : 0.000084s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000051s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000023s : 0.01% optimize.tuple_transform.d_1 : 0.000088s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000118s : 0.03% optimize.cse_after_recomputation.cse : 0.075045s : 20.74% optimize.environ_conv : 0.000020s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000022s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000010s : 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000030s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 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 : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000039s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000036s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000049s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.00% opt_after_jit_grad : 0.000907s : 0.25% validate : 0.000079s : 0.02% Time group info: ------[substitution.] 0.002892 310 0.61% : 0.000018s : 4: substitution.depend_value_elim 0.13% : 0.000004s : 7: substitution.elim_not_effective 0.88% : 0.000025s : 7: substitution.float_depend_g_call 0.18% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000003s : 7: substitution.fold_const_symbol 32.77% : 0.000948s : 4: substitution.getattr_setattr_resolve 0.34% : 0.000010s : 9: substitution.graph_param_transform 0.12% : 0.000004s : 2: substitution.incorporate_call 0.08% : 0.000002s : 2: substitution.incorporate_call_switch 43.66% : 0.001263s : 24: substitution.inline 1.83% : 0.000053s : 5: substitution.inline_without_move 1.08% : 0.000031s : 28: substitution.j_node_and_user_rematch 0.86% : 0.000025s : 3: substitution.less_batch_normalization 0.60% : 0.000017s : 9: substitution.minmaximum_grad 0.87% : 0.000025s : 7: substitution.partial_eliminate 0.71% : 0.000021s : 28: substitution.remove_not_recompute_node 4.06% : 0.000117s : 38: substitution.replace_applicator 0.71% : 0.000020s : 19: substitution.replace_old_param 0.14% : 0.000004s : 1: substitution.set_cell_output_no_recompute 1.27% : 0.000037s : 9: substitution.tuple_list_convert_item_index_to_positive 0.54% : 0.000016s : 9: substitution.tuple_list_get_item_const_eliminator 0.74% : 0.000021s : 9: substitution.tuple_list_get_item_depend_reorder 3.71% : 0.000107s : 31: substitution.tuple_list_get_item_eliminator 0.77% : 0.000022s : 9: substitution.tuple_list_get_set_item_eliminator 1.34% : 0.000039s : 16: substitution.updatestate_pure_node_eliminater 1.89% : 0.000055s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.084146 2 97.52% : 0.082055s : 1: type_inference.infer 2.48% : 0.002090s : 1: type_inference.specialize ------[replace.] 0.000793 49 9.67% : 0.000077s : 3: replace.getattr_setattr_resolve 37.34% : 0.000296s : 24: replace.inline 23.66% : 0.000187s : 1: replace.replace_applicator 27.61% : 0.000219s : 20: replace.tuple_list_get_item_eliminator 1.73% : 0.000014s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002238 49 39.91% : 0.000893s : 3: match.getattr_setattr_resolve 55.65% : 0.001246s : 24: match.inline 0.87% : 0.000019s : 1: match.replace_applicator 2.76% : 0.000062s : 20: match.tuple_list_get_item_eliminator 0.82% : 0.000018s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001381 8683 0.86% : 0.000012s : 85: predicate.accumulaten_eliminater 0.30% : 0.000004s : 9: predicate.ad_related_special_op_eliminate 0.38% : 0.000005s : 37: predicate.addn_check_dump 0.84% : 0.000012s : 85: predicate.addn_zero_filter 0.80% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 1.65% : 0.000023s : 122: predicate.arithmetic_simplify 0.86% : 0.000012s : 85: predicate.cast_eliminate 2.44% : 0.000034s : 260: predicate.check_bprop_eliminate 0.39% : 0.000005s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.41% : 0.000006s : 37: predicate.depend_value_elim 0.95% : 0.000013s : 85: predicate.dict_get_item_const_eliminator 0.93% : 0.000013s : 85: predicate.dict_get_item_eliminator 0.88% : 0.000012s : 85: predicate.dict_set_item_eliminator 0.33% : 0.000005s : 18: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 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 0.89% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.91% : 0.000013s : 94: predicate.environ_get_depend_swap 1.31% : 0.000018s : 131: predicate.environ_get_eliminate 0.92% : 0.000013s : 94: predicate.environ_get_set_eliminate 1.31% : 0.000018s : 130: predicate.exchange_switch_depend_value 1.87% : 0.000026s : 130: predicate.float_depend_g_call 0.38% : 0.000005s : 37: predicate.float_environ_get_switch 0.48% : 0.000007s : 46: predicate.float_tuple_getitem_switch 0.05% : 0.000001s : 9: predicate.fold_const_symbol 0.40% : 0.000005s : 37: predicate.get_grad_eliminate 0.57% : 0.000008s : 20: predicate.getattr_setattr_resolve 0.07% : 0.000001s : 9: predicate.graph_param_transform 0.37% : 0.000005s : 37: predicate.incorporate_call 0.34% : 0.000005s : 37: predicate.incorporate_call_switch 4.56% : 0.000063s : 307: predicate.inline 1.58% : 0.000022s : 111: predicate.inline_without_move 0.20% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.60% : 0.000008s : 37: predicate.less_batch_normalization 1.35% : 0.000019s : 123: predicate.list_to_tuple_eliminator_ 2.05% : 0.000028s : 208: predicate.load_eliminater 0.34% : 0.000005s : 9: predicate.loop_unroll_after_grad 1.91% : 0.000026s : 197: predicate.loop_unroll_before_grad 1.12% : 0.000015s : 103: predicate.make_slice_get_slice_eliminator 0.42% : 0.000006s : 37: predicate.merge_addn 2.42% : 0.000033s : 256: predicate.micro_step_allgather_replace 2.47% : 0.000034s : 256: predicate.mini_step_allgather_replace 0.83% : 0.000011s : 85: predicate.minmaximum_grad 0.35% : 0.000005s : 9: predicate.mutable_eliminate 0.11% : 0.000001s : 9: predicate.opt_reshape 0.13% : 0.000002s : 9: predicate.parallel_virtual_node 1.93% : 0.000027s : 130: predicate.partial_defer_inline 1.24% : 0.000017s : 114: predicate.partial_eliminate 0.83% : 0.000011s : 85: predicate.print_const_string_wrapper 0.42% : 0.000006s : 37: predicate.reduce_all_const_elim 1.10% : 0.000015s : 85: predicate.reduce_eliminate 2.03% : 0.000028s : 208: predicate.redundant_stop_gradient_eliminater 0.34% : 0.000005s : 37: predicate.remove_not_recompute_node 8.30% : 0.000115s : 363: predicate.replace_applicator 0.69% : 0.000009s : 111: predicate.replace_old_param 0.11% : 0.000002s : 9: predicate.reset_defer_inline 0.95% : 0.000013s : 85: predicate.reshape_eliminate 2.76% : 0.000038s : 256: predicate.row_tensor_add_zeros_like 0.14% : 0.000002s : 9: predicate.row_tensor_eliminate 2.70% : 0.000037s : 260: predicate.same_eliminate 0.34% : 0.000005s : 39: predicate.set_cell_output_no_recompute 0.51% : 0.000007s : 37: predicate.shard_identity_eliminate 0.23% : 0.000003s : 18: predicate.special_op_eliminate 0.48% : 0.000007s : 37: predicate.specialize_transform 2.63% : 0.000036s : 256: predicate.split_environ_get_set_with_tuple_value 1.44% : 0.000020s : 111: predicate.stack_unstack_eliminate 0.12% : 0.000002s : 9: predicate.switch_call_monad_eliminater 1.45% : 0.000020s : 130: predicate.switch_defer_inline 3.84% : 0.000053s : 390: predicate.switch_layer_defer_inline 4.07% : 0.000056s : 373: predicate.switch_simplify 0.85% : 0.000012s : 85: predicate.tile_eliminate 0.83% : 0.000011s : 85: predicate.transpose_eliminate 1.15% : 0.000016s : 103: predicate.tuple_list_convert_item_index_to_positive 1.20% : 0.000017s : 103: predicate.tuple_list_get_item_const_eliminator 1.07% : 0.000015s : 103: predicate.tuple_list_get_item_depend_reorder 2.44% : 0.000034s : 160: predicate.tuple_list_get_item_eliminator 1.24% : 0.000017s : 103: predicate.tuple_list_get_set_item_eliminator 1.59% : 0.000022s : 140: predicate.tuple_list_set_item_eliminator 1.46% : 0.000020s : 123: predicate.tuple_to_list_eliminator_ 2.12% : 0.000029s : 208: predicate.updatestate_pure_node_eliminater 2.63% : 0.000036s : 246: predicate.updatestate_useless_node_eliminater 0.13% : 0.000002s : 9: predicate.value_based_eliminate 0.42% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.41% : 0.000006s : 37: predicate.virtual_output_eliminate 0.11% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.12% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004706 53 56.02% : 0.002636s : 23: func_graph_cloner_run.FuncGraphClonerGraph 43.98% : 0.002070s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.733238 243 0.00% : 0.000004s : 1: ForceFp32Comm 0.63% : 0.004631s : 1: add_attr 0.63% : 0.004614s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000125s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.05% : 0.000349s : 1: auto_monad 0.01% : 0.000056s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.08% : 0.000569s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000034s : 1: control_data_broadcast_order 0.00% : 0.000015s : 1: convert_after_rewriter 10.24% : 0.075109s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000026s : 1: environ_conv 0.01% : 0.000085s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000015s : 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% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000013s : 1: label_micro_interleaved_index 0.10% : 0.000720s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.13% : 0.000943s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000034s : 1: opt.transform.mutable_eliminate 1.37% : 0.010055s : 125: opt.transform.opt_a 0.01% : 0.000082s : 1: opt.transform.opt_after_cconv 0.01% : 0.000052s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000248s : 28: opt.transform.opt_b 0.15% : 0.001098s : 2: opt.transform.opt_resolve 0.01% : 0.000098s : 2: opt.transform.opt_trans_graph 0.01% : 0.000101s : 4: opt.transform.symbol_engine_opt 28.67% : 0.210218s : 1: opt_a 0.03% : 0.000234s : 1: opt_after_cconv 0.13% : 0.000928s : 1: opt_after_jit_grad 0.07% : 0.000477s : 1: opt_b 39.42% : 0.289059s : 1: optimize 0.00% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000044s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000083s : 1: pre_auto_parallel 0.01% : 0.000067s : 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% : 0.000027s : 1: remove_dup_value 5.74% : 0.042078s : 2: renormalize.infer 0.76% : 0.005603s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000090s : 1: rewriter_after_opt_a 0.02% : 0.000182s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000194s : 1: symbol_engine_optimizer 0.02% : 0.000137s : 1: tuple_transform 11.50% : 0.084322s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__scalar_tensor[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__scalar_tensor[0],max_mem:4.0M [WARNING] ME(167911:281473202921264,MainProcess):2026-01-29-17:39:53.209.985 [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__scalar_tensor[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__scalar_tensor[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 182.92s (0:03:02) ==================