==================================================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_008/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(168506:281472966807344,MainProcess):2026-01-29-17:37:25.846.713 [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 = 0.0276072, [21] [bootstrap]: 0.00063001 [type_inference]: 0.0112782 [event_method]: 1.641e-05 [auto_monad]: 0.00015132 [graph_reusing]: 6.12001e-06 [inline]: 2.43998e-06 [add_attr]: 0.00853341, [1] [add_attr_with_inline]: 0.00851846, [1] [Cycle 1]: 9.608e-05, [2] [tag_attr]: 1.727e-05 [meta_addattr_fg_expand]: 3.43e-06 [parallel-infer-symbol]: 3.98999e-06 [pre_auto_parallel]: 4.865e-05 [insert-virtual-dataset]: 2.29001e-06 [parallel-infer-symbol-second]: 9.80013e-07 [dataset_repeat_opt]: 1.91e-06 [pipeline_split]: 1.62001e-06 [optimize]: 0.00602124, [53] [py_interpret_to_execute]: 2.44e-05 [rewriter_before_opt_a]: 6.466e-05 [opt_a]: 0.00310575, [2] [Cycle 1]: 0.00218742, [45] [expand_dump_flag]: 2.51e-06 [switch_simplify]: 2.735e-05 [loop_unroll]: 1.252e-05 [a_1]: 0.0004159 [with_stream_mark]: 2.418e-05 [recompute_prepare]: 1.196e-05 [updatestate_depend_eliminate]: 6.93e-06 [updatestate_assign_eliminate]: 5.30999e-06 [updatestate_loads_eliminate]: 5.13002e-06 [parameter_eliminate]: 2.27999e-06 [a_2]: 0.00013213 [accelerated_algorithm]: 1.063e-05 [shard]: 4.23999e-06 [meta_shard_fg_expand]: 1.96998e-06 [shard_inline]: 8.85999e-06 [merge_send_recv]: 1.062e-05 [auto_parallel]: 9.85002e-06 [parallel]: 5.321e-05 [flash_sp]: 1.254e-05 [merge_comm]: 7.05e-06 [allreduce_fusion]: 5.19e-06 [matmul_add_comm_reduction]: 1.283e-05 [allreduce_slice_to_reducescatter]: 1.14e-06 [virtual_shard_identity]: 1.352e-05 [virtual_dataset]: 8.68001e-06 [get_grad_eliminate_]: 9.18002e-06 [virtual_output]: 9.41e-06 [merge_forward]: 7.93001e-06 [cell_reuse_recompute_pass]: 2.06e-06 [offload_activation]: 1.407e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.19e-05 [merge_recompute_call_nodes]: 1.84e-06 [before_grad]: 1.669e-05 [set_forward_comm_id_for_comm_node_pass]: 6.38e-06 [meta_fg_expand]: 4.03001e-06 [flash_sp_send_recv_attached]: 2.97002e-06 [receive_attached]: 1.179e-05 [after_resolve]: 1.556e-05 [a_after_grad]: 1.38e-05 [renormalize]: 0.00081801 [add_forward_monad_depend]: 7.92998e-06 [auto_monad_grad]: 2.22999e-06 [auto_monad_eliminator]: 2.634e-05 [cse]: 5.236e-05 [a_3]: 6.999e-05 [Cycle 2]: 0.00090461, [45] [expand_dump_flag]: 2.81e-06 [switch_simplify]: 1.151e-05 [loop_unroll]: 8.47998e-06 [a_1]: 0.00020406 [with_stream_mark]: 2.195e-05 [recompute_prepare]: 9.18002e-06 [updatestate_depend_eliminate]: 6.28e-06 [updatestate_assign_eliminate]: 5.30999e-06 [updatestate_loads_eliminate]: 5.44e-06 [parameter_eliminate]: 1.62001e-06 [a_2]: 0.00011362 [accelerated_algorithm]: 9.51e-06 [shard]: 2.43002e-06 [meta_shard_fg_expand]: 2.22999e-06 [shard_inline]: 8.55001e-06 [merge_send_recv]: 1.03e-05 [auto_parallel]: 1.071e-05 [parallel]: 7.8e-06 [flash_sp]: 3.97002e-06 [merge_comm]: 5.62999e-06 [allreduce_fusion]: 5.09e-06 [matmul_add_comm_reduction]: 1.067e-05 [allreduce_slice_to_reducescatter]: 6.59988e-07 [virtual_shard_identity]: 1.003e-05 [virtual_dataset]: 8.28001e-06 [get_grad_eliminate_]: 8.19002e-06 [virtual_output]: 7.88001e-06 [merge_forward]: 6.28e-06 [cell_reuse_recompute_pass]: 2.26e-06 [offload_activation]: 1.26e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.771e-05 [merge_recompute_call_nodes]: 1.73002e-06 [before_grad]: 1.453e-05 [set_forward_comm_id_for_comm_node_pass]: 6.22001e-06 [meta_fg_expand]: 3.23e-06 [flash_sp_send_recv_attached]: 1.74e-06 [receive_attached]: 1.99999e-06 [after_resolve]: 1.356e-05 [a_after_grad]: 1.283e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 1.50999e-06 [auto_monad_grad]: 2.14e-06 [auto_monad_eliminator]: 1.543e-05 [cse]: 2.47e-05 [a_3]: 5.14e-05 [py_interpret_to_execute_after_opt_a]: 1.877e-05 [slice_cell_reuse_recomputed_activation]: 1.87001e-06 [rewriter_after_opt_a]: 0.00020217 [convert_after_rewriter]: 1.283e-05 [order_py_execute_after_rewriter]: 6.39999e-06 [mutable_eliminate]: 0.00070989 [opt_b]: 0.0003023, [1] [Cycle 1]: 0.00029422, [7] [b_1]: 0.00019077 [b_2]: 1.065e-05 [updatestate_depend_eliminate]: 1.149e-05 [updatestate_assign_eliminate]: 4.72e-06 [updatestate_loads_eliminate]: 5.22999e-06 [renormalize]: 7.50006e-07 [cse]: 3.346e-05 [optimize_parallel_all_gather_comm]: 2.4e-05 [overlap_param_gather]: 2.29999e-06 [cconv]: 3.498e-05 [loop_unroll]: 0.00054161 [opt_after_cconv]: 0.00015325, [1] [Cycle 1]: 0.00014559, [7] [c_1]: 5.578e-05 [parameter_eliminate]: 5.05001e-06 [updatestate_depend_eliminate]: 9.32001e-06 [updatestate_assign_eliminate]: 4.38001e-06 [updatestate_loads_eliminate]: 4.84003e-06 [cse]: 2.93e-05 [renormalize]: 9.30013e-07 [remove_dup_value]: 1.599e-05 [tuple_transform]: 0.00010633, [1] [Cycle 1]: 0.00010179, [4] [d_1]: 7.166e-05 [none_parameter_eliminate]: 1.79e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 9.46998e-06 [partial_unused_args_eliminate]: 1.99e-06 [add_recomputation]: 8.158e-05 [cse_after_recomputation]: 2.697e-05, [1] [Cycle 1]: 2.216e-05, [1] [cse]: 1.593e-05 [environ_conv]: 1.653e-05 [swap_dp_allreduce_reducescatter]: 8.13999e-06 [bias_add_comm_swap]: 2.84001e-06 [label_micro_interleaved_index]: 5.92999e-06 [label_fine_grained_interleaved_index]: 3.01001e-06 [merge_cast_opt]: 1.40001e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.78e-06 [assign_add_opt]: 1.47999e-06 [ForceFp32Comm]: 1.70001e-06 [remove_cast_before_assign_add]: 8.00006e-07 [full_micro_interleaved_order_control]: 2.09e-06 [reorder_send_recv_between_fp_bp]: 3.01001e-06 [comm_op_add_attrs]: 1.00999e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.11002e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 2.328e-05 [overlap_opt_shard_grad_in_pipeline]: 1.92999e-06 [control_data_broadcast_order]: 2.111e-05 [grouped_pairwise_exchange_alltoall]: 1.56002e-06 [offloading_packed_experts]: 5.71e-06 [overlap_recompute_and_grad_model_parallel]: 7.41001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.25001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.27999e-06 [overlap_grad_ring_attention]: 6.49001e-06 [overlap_grad_flash_sp]: 4.131e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.41e-06 [split_layernorm_comm]: 2.06998e-06 [handle_group_info]: 9.70002e-07 [symbol_engine_optimizer]: 0.00010018, [1] [Cycle 1]: 9.5e-05, [6] [build]: 5.51e-06 [elim_shapecalc]: 1.514e-05 [elim_not_effective]: 1.76e-05 [opt_reshape]: 9.12001e-06 [fold_const_symbol]: 1.435e-05 [renormalize]: 4.00003e-07 [detach_backward]: 2.54001e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 3.617e-05 [get_jit_bprop_graph]: 1.89e-06 [rewriter_after_jit_bprop_graph]: 6.44999e-06 [opt_after_jit_grad]: 0.00060679 [validate]: 7.033e-05 Sums bootstrap : 0.000630s : 3.51% type_inference : 0.011278s : 62.83% event_method : 0.000016s : 0.09% auto_monad : 0.000151s : 0.84% graph_reusing : 0.000006s : 0.03% inline : 0.000002s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 0.10% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000003s : 0.02% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000049s : 0.27% insert-virtual-dataset : 0.000002s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000024s : 0.14% optimize.rewriter_before_opt_a : 0.000065s : 0.36% optimize.opt_a.expand_dump_flag : 0.000005s : 0.03% optimize.opt_a.switch_simplify : 0.000039s : 0.22% optimize.opt_a.loop_unroll : 0.000021s : 0.12% optimize.opt_a.a_1 : 0.000620s : 3.45% optimize.opt_a.with_stream_mark : 0.000046s : 0.26% optimize.opt_a.recompute_prepare : 0.000021s : 0.12% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.07% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.06% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.06% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000246s : 1.37% optimize.opt_a.accelerated_algorithm : 0.000020s : 0.11% optimize.opt_a.shard : 0.000007s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.02% optimize.opt_a.shard_inline : 0.000017s : 0.10% optimize.opt_a.merge_send_recv : 0.000021s : 0.12% optimize.opt_a.auto_parallel : 0.000021s : 0.11% optimize.opt_a.parallel : 0.000061s : 0.34% optimize.opt_a.flash_sp : 0.000017s : 0.09% optimize.opt_a.merge_comm : 0.000013s : 0.07% optimize.opt_a.allreduce_fusion : 0.000010s : 0.06% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.13% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000024s : 0.13% optimize.opt_a.virtual_dataset : 0.000017s : 0.09% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.10% optimize.opt_a.virtual_output : 0.000017s : 0.10% optimize.opt_a.merge_forward : 0.000014s : 0.08% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.02% optimize.opt_a.offload_activation : 0.000027s : 0.15% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.22% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.02% optimize.opt_a.before_grad : 0.000031s : 0.17% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.07% optimize.opt_a.meta_fg_expand : 0.000007s : 0.04% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.03% optimize.opt_a.receive_attached : 0.000014s : 0.08% optimize.opt_a.after_resolve : 0.000029s : 0.16% optimize.opt_a.a_after_grad : 0.000027s : 0.15% optimize.opt_a.renormalize : 0.000818s : 4.56% optimize.opt_a.add_forward_monad_depend : 0.000009s : 0.05% optimize.opt_a.auto_monad_grad : 0.000004s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.23% optimize.opt_a.cse : 0.000077s : 0.43% optimize.opt_a.a_3 : 0.000121s : 0.68% optimize.py_interpret_to_execute_after_opt_a : 0.000019s : 0.10% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000202s : 1.13% optimize.convert_after_rewriter : 0.000013s : 0.07% optimize.order_py_execute_after_rewriter : 0.000006s : 0.04% optimize.mutable_eliminate : 0.000710s : 3.95% optimize.opt_b.b_1 : 0.000191s : 1.06% optimize.opt_b.b_2 : 0.000011s : 0.06% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.06% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000033s : 0.19% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.13% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000035s : 0.19% optimize.loop_unroll : 0.000542s : 3.02% optimize.opt_after_cconv.c_1 : 0.000056s : 0.31% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.05% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.cse : 0.000029s : 0.16% optimize.opt_after_cconv.renormalize : 0.000001s : 0.01% optimize.remove_dup_value : 0.000016s : 0.09% optimize.tuple_transform.d_1 : 0.000072s : 0.40% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.05% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000082s : 0.45% optimize.cse_after_recomputation.cse : 0.000016s : 0.09% optimize.environ_conv : 0.000017s : 0.09% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.05% optimize.bias_add_comm_swap : 0.000003s : 0.02% optimize.label_micro_interleaved_index : 0.000006s : 0.03% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000002s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 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 : 0.000023s : 0.13% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000021s : 0.12% 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 : 0.04% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.01% optimize.overlap_grad_ring_attention : 0.000006s : 0.04% optimize.overlap_grad_flash_sp : 0.000041s : 0.23% 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 : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.08% optimize.symbol_engine_optimizer.elim_not_effective : 0.000018s : 0.10% optimize.symbol_engine_optimizer.opt_reshape : 0.000009s : 0.05% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000014s : 0.08% 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 : 0.000036s : 0.20% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000006s : 0.04% opt_after_jit_grad : 0.000607s : 3.38% validate : 0.000070s : 0.39% Time group info: ------[substitution.] 0.000195 55 5.70% : 0.000011s : 2: substitution.depend_value_elim 1.35% : 0.000003s : 5: substitution.elim_not_effective 1.12% : 0.000002s : 5: substitution.fold_const_symbol 11.09% : 0.000022s : 6: substitution.graph_param_transform 52.22% : 0.000102s : 1: substitution.inline 3.35% : 0.000007s : 10: substitution.j_node_and_user_rematch 4.49% : 0.000009s : 10: substitution.remove_not_recompute_node 3.25% : 0.000006s : 2: substitution.replace_old_param 9.68% : 0.000019s : 6: substitution.updatestate_pure_node_eliminater 7.75% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.011217 2 95.94% : 0.010762s : 1: type_inference.infer 4.06% : 0.000456s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000101 1 100.00% : 0.000101s : 1: match.inline ------[predicate.] 0.000246 1419 0.91% : 0.000002s : 13: predicate.accumulaten_eliminater 1.07% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 12: predicate.addn_check_dump 1.16% : 0.000003s : 13: predicate.addn_zero_filter 0.69% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 2.07% : 0.000005s : 25: predicate.arithmetic_simplify 0.89% : 0.000002s : 13: predicate.cast_eliminate 0.78% : 0.000002s : 12: predicate.check_bprop_eliminate 0.76% : 0.000002s : 12: predicate.compare_switch_simplify 0.19% : 0.000000s : 6: predicate.const_output_eliminate 0.87% : 0.000002s : 12: predicate.depend_value_elim 0.75% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.88% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.99% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.71% : 0.000004s : 12: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 6: predicate.elim_not_effective 0.67% : 0.000002s : 6: predicate.elim_shapecalc_of_broadcastargs 1.10% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.14% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.10% : 0.000003s : 19: predicate.environ_get_depend_swap 1.87% : 0.000005s : 31: predicate.environ_get_eliminate 1.04% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.88% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.62% : 0.000004s : 14: predicate.float_depend_g_call 0.71% : 0.000002s : 12: predicate.float_environ_get_switch 1.12% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.20% : 0.000000s : 6: predicate.fold_const_symbol 0.97% : 0.000002s : 12: predicate.get_grad_eliminate 0.29% : 0.000001s : 6: predicate.graph_param_transform 0.73% : 0.000002s : 12: predicate.incorporate_call 0.62% : 0.000002s : 12: predicate.incorporate_call_switch 5.30% : 0.000013s : 63: predicate.inline 1.04% : 0.000003s : 12: predicate.inline_without_move 0.35% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.29% : 0.000003s : 12: predicate.less_batch_normalization 1.79% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.27% : 0.000006s : 38: predicate.load_eliminater 1.53% : 0.000004s : 6: predicate.loop_unroll_after_grad 1.13% : 0.000003s : 17: predicate.loop_unroll_before_grad 2.07% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.80% : 0.000002s : 12: predicate.merge_addn 0.71% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.84% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.69% : 0.000002s : 13: predicate.minmaximum_grad 1.47% : 0.000004s : 6: predicate.mutable_eliminate 0.42% : 0.000001s : 6: predicate.opt_reshape 0.53% : 0.000001s : 6: predicate.parallel_virtual_node 1.15% : 0.000003s : 14: predicate.partial_defer_inline 1.14% : 0.000003s : 19: predicate.partial_eliminate 0.73% : 0.000002s : 13: predicate.print_const_string_wrapper 0.86% : 0.000002s : 12: predicate.reduce_all_const_elim 0.93% : 0.000002s : 13: predicate.reduce_eliminate 2.29% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.77% : 0.000002s : 12: predicate.remove_not_recompute_node 0.95% : 0.000002s : 25: predicate.replace_applicator 0.65% : 0.000002s : 12: predicate.replace_old_param 0.40% : 0.000001s : 6: predicate.reset_defer_inline 0.83% : 0.000002s : 13: predicate.reshape_eliminate 0.84% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.49% : 0.000001s : 6: predicate.row_tensor_eliminate 1.02% : 0.000003s : 12: predicate.same_eliminate 0.54% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.91% : 0.000002s : 12: predicate.shard_identity_eliminate 0.83% : 0.000002s : 12: predicate.special_op_eliminate 0.82% : 0.000002s : 12: predicate.specialize_transform 1.16% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 1.00% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.48% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.88% : 0.000002s : 14: predicate.switch_defer_inline 1.56% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.78% : 0.000009s : 49: predicate.switch_simplify 0.84% : 0.000002s : 13: predicate.tile_eliminate 0.79% : 0.000002s : 13: predicate.transpose_eliminate 1.61% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.59% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.73% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.10% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.45% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.66% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.61% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.25% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.26% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.46% : 0.000001s : 6: predicate.value_based_eliminate 0.82% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.89% : 0.000002s : 12: predicate.virtual_output_eliminate 0.39% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.48% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000260 4 8.44% : 0.000022s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.56% : 0.000238s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.044455 192 0.01% : 0.000004s : 1: ForceFp32Comm 19.21% : 0.008539s : 1: add_attr 19.17% : 0.008523s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.19% : 0.000086s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.36% : 0.000159s : 1: auto_monad 0.09% : 0.000041s : 1: auto_monad_reorder 0.01% : 0.000003s : 1: begin_end_overlap_inline 0.01% : 0.000006s : 1: bias_add_comm_swap 1.51% : 0.000671s : 1: bootstrap 0.09% : 0.000039s : 1: cconv 0.01% : 0.000005s : 1: comm_op_add_attrs 0.06% : 0.000025s : 1: control_data_broadcast_order 0.04% : 0.000017s : 1: convert_after_rewriter 0.07% : 0.000030s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000006s : 1: detach_backward 0.05% : 0.000020s : 1: environ_conv 0.05% : 0.000023s : 1: event_method 0.01% : 0.000005s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.02% : 0.000010s : 1: graph_reusing 0.01% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000004s : 1: interleave_split_concat_branches 0.01% : 0.000006s : 1: label_fine_grained_interleaved_index 0.02% : 0.000009s : 1: label_micro_interleaved_index 1.26% : 0.000561s : 1: loop_unroll 0.01% : 0.000006s : 1: merge_cast_opt 0.01% : 0.000006s : 1: micro_interleaved_order_control 1.62% : 0.000720s : 1: mutable_eliminate 0.02% : 0.000010s : 1: offloading_packed_experts 0.05% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.05% : 0.000024s : 1: opt.transform.mutable_eliminate 2.73% : 0.001214s : 78: opt.transform.opt_a 0.12% : 0.000054s : 1: opt.transform.opt_after_cconv 0.09% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.39% : 0.000174s : 28: opt.transform.opt_b 0.18% : 0.000079s : 2: opt.transform.opt_trans_graph 0.12% : 0.000052s : 4: opt.transform.symbol_engine_opt 7.00% : 0.003110s : 1: opt_a 0.35% : 0.000157s : 1: opt_after_cconv 1.40% : 0.000620s : 1: opt_after_jit_grad 0.69% : 0.000306s : 1: opt_b 13.56% : 0.006028s : 1: optimize 0.16% : 0.000072s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000009s : 1: order_py_execute_after_rewriter 0.10% : 0.000045s : 1: overlap_grad_flash_sp 0.01% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.02% : 0.000009s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.06% : 0.000027s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000006s : 1: overlap_param_gather 0.01% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.02% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000005s : 1: overlap_recompute_comm 0.02% : 0.000008s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000005s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.12% : 0.000053s : 1: pre_auto_parallel 0.06% : 0.000028s : 1: py_interpret_to_execute 0.05% : 0.000023s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000003s : 1: remove_cast_before_assign_add 0.04% : 0.000020s : 1: remove_dup_value 1.11% : 0.000495s : 1: renormalize.infer 0.70% : 0.000311s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.02% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.48% : 0.000211s : 1: rewriter_after_opt_a 0.16% : 0.000069s : 1: rewriter_before_opt_a 0.01% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.01% : 0.000005s : 1: split_layernorm_comm 0.02% : 0.000007s : 1: split_matmul_comm_elemetwise 0.03% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.23% : 0.000103s : 1: symbol_engine_optimizer 0.25% : 0.000109s : 1: tuple_transform 25.42% : 0.011300s : 1: type_inference TotalTime = 0.0154313, [21] [bootstrap]: 0.00048355 [type_inference]: 0.0036839 [event_method]: 1.465e-05 [auto_monad]: 0.00013378 [graph_reusing]: 5.66003e-06 [inline]: 2.43998e-06 [add_attr]: 0.00420525, [1] [add_attr_with_inline]: 0.00419404, [1] [Cycle 1]: 6.655e-05, [2] [tag_attr]: 1.645e-05 [meta_addattr_fg_expand]: 3.12002e-06 [parallel-infer-symbol]: 3.46001e-06 [pre_auto_parallel]: 3.578e-05 [insert-virtual-dataset]: 2.54999e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 1.92001e-06 [pipeline_split]: 1.55001e-06 [optimize]: 0.00605766, [53] [py_interpret_to_execute]: 2.226e-05 [rewriter_before_opt_a]: 5.577e-05 [opt_a]: 0.00341883, [2] [Cycle 1]: 0.00251919, [45] [expand_dump_flag]: 2.54999e-06 [switch_simplify]: 2.66e-05 [loop_unroll]: 1.322e-05 [a_1]: 0.00038798 [with_stream_mark]: 1.906e-05 [recompute_prepare]: 1.046e-05 [updatestate_depend_eliminate]: 6.04999e-06 [updatestate_assign_eliminate]: 5.24e-06 [updatestate_loads_eliminate]: 6.17999e-06 [parameter_eliminate]: 1.97001e-06 [a_2]: 0.0001195 [accelerated_algorithm]: 9.81998e-06 [shard]: 2.81999e-06 [meta_shard_fg_expand]: 2.20002e-06 [shard_inline]: 8.23999e-06 [merge_send_recv]: 1.243e-05 [auto_parallel]: 9.27001e-06 [parallel]: 3.216e-05 [flash_sp]: 9.18002e-06 [merge_comm]: 5.40001e-06 [allreduce_fusion]: 5.49e-06 [matmul_add_comm_reduction]: 1.209e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.103e-05 [virtual_dataset]: 8.40001e-06 [get_grad_eliminate_]: 7.94002e-06 [virtual_output]: 8.22e-06 [merge_forward]: 5.66003e-06 [cell_reuse_recompute_pass]: 1.30001e-06 [offload_activation]: 1.447e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.849e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 1.675e-05 [set_forward_comm_id_for_comm_node_pass]: 5.39998e-06 [meta_fg_expand]: 3.81001e-06 [flash_sp_send_recv_attached]: 2.84999e-06 [receive_attached]: 2.62001e-06 [after_resolve]: 1.196e-05 [a_after_grad]: 1.256e-05 [renormalize]: 0.00126284 [add_forward_monad_depend]: 6.06e-06 [auto_monad_grad]: 2.53998e-06 [auto_monad_eliminator]: 2.352e-05 [cse]: 3.897e-05 [a_3]: 6.839e-05 [Cycle 2]: 0.00088616, [45] [expand_dump_flag]: 1.54e-06 [switch_simplify]: 1.114e-05 [loop_unroll]: 8.68001e-06 [a_1]: 0.00020147 [with_stream_mark]: 1.576e-05 [recompute_prepare]: 8.83001e-06 [updatestate_depend_eliminate]: 5.57999e-06 [updatestate_assign_eliminate]: 4.58001e-06 [updatestate_loads_eliminate]: 5.10999e-06 [parameter_eliminate]: 1.33002e-06 [a_2]: 0.00011145 [accelerated_algorithm]: 8.28999e-06 [shard]: 1.33002e-06 [meta_shard_fg_expand]: 2.04999e-06 [shard_inline]: 8.23001e-06 [merge_send_recv]: 7.36001e-06 [auto_parallel]: 8.59e-06 [parallel]: 5.67999e-06 [flash_sp]: 3.63999e-06 [merge_comm]: 4.89e-06 [allreduce_fusion]: 4.82e-06 [matmul_add_comm_reduction]: 1.03e-05 [allreduce_slice_to_reducescatter]: 3.89991e-07 [virtual_shard_identity]: 9.44e-06 [virtual_dataset]: 8.13001e-06 [get_grad_eliminate_]: 7.72998e-06 [virtual_output]: 8.12e-06 [merge_forward]: 5.21998e-06 [cell_reuse_recompute_pass]: 1.79e-06 [offload_activation]: 1.156e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.801e-05 [merge_recompute_call_nodes]: 1.04e-06 [before_grad]: 1.475e-05 [set_forward_comm_id_for_comm_node_pass]: 5.23002e-06 [meta_fg_expand]: 3.18998e-06 [flash_sp_send_recv_attached]: 1.00001e-06 [receive_attached]: 2.08998e-06 [after_resolve]: 1.16e-05 [a_after_grad]: 1.196e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.32999e-06 [auto_monad_grad]: 1.18001e-06 [auto_monad_eliminator]: 1.213e-05 [cse]: 1.918e-05 [a_3]: 5.131e-05 [py_interpret_to_execute_after_opt_a]: 1.531e-05 [slice_cell_reuse_recomputed_activation]: 1.91998e-06 [rewriter_after_opt_a]: 0.00017745 [convert_after_rewriter]: 1.044e-05 [order_py_execute_after_rewriter]: 6.44001e-06 [mutable_eliminate]: 0.00069705 [opt_b]: 0.00029015, [1] [Cycle 1]: 0.00028254, [7] [b_1]: 0.00018813 [b_2]: 1.03e-05 [updatestate_depend_eliminate]: 8.99e-06 [updatestate_assign_eliminate]: 4.57998e-06 [updatestate_loads_eliminate]: 4.28001e-06 [renormalize]: 5.69999e-07 [cse]: 2.358e-05 [optimize_parallel_all_gather_comm]: 2.07e-05 [overlap_param_gather]: 6.75002e-06 [cconv]: 2.998e-05 [loop_unroll]: 0.00048314 [opt_after_cconv]: 0.00014141, [1] [Cycle 1]: 0.00013497, [7] [c_1]: 5.415e-05 [parameter_eliminate]: 3.56001e-06 [updatestate_depend_eliminate]: 7.36999e-06 [updatestate_assign_eliminate]: 4.39998e-06 [updatestate_loads_eliminate]: 4.03001e-06 [cse]: 2.246e-05 [renormalize]: 2.50002e-07 [remove_dup_value]: 1.625e-05 [tuple_transform]: 9.448e-05, [1] [Cycle 1]: 8.871e-05, [4] [d_1]: 5.709e-05 [none_parameter_eliminate]: 1.47001e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 9.37999e-06 [partial_unused_args_eliminate]: 1.60999e-06 [add_recomputation]: 7.298e-05 [cse_after_recomputation]: 2.601e-05, [1] [Cycle 1]: 2.112e-05, [1] [cse]: 1.534e-05 [environ_conv]: 7.23e-06 [swap_dp_allreduce_reducescatter]: 7.95998e-06 [bias_add_comm_swap]: 2.83003e-06 [label_micro_interleaved_index]: 4.38001e-06 [label_fine_grained_interleaved_index]: 2.77002e-06 [merge_cast_opt]: 1.32999e-06 [slice_recompute_activation]: 2.34001e-06 [micro_interleaved_order_control]: 2.54001e-06 [assign_add_opt]: 1.31998e-06 [ForceFp32Comm]: 1.17e-06 [remove_cast_before_assign_add]: 1.09e-06 [full_micro_interleaved_order_control]: 2.19001e-06 [reorder_send_recv_between_fp_bp]: 3.03e-06 [comm_op_add_attrs]: 1.00999e-06 [add_comm_op_reuse_tag]: 1.22e-06 [interleave_split_concat_branches]: 1.30999e-06 [interleave_parallel_branches]: 1.17999e-06 [overlap_opt_shard_in_pipeline]: 4.18001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.00002e-06 [control_data_broadcast_order]: 1.821e-05 [grouped_pairwise_exchange_alltoall]: 1.64e-06 [offloading_packed_experts]: 5.05999e-06 [overlap_recompute_and_grad_model_parallel]: 6.27001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.44999e-06 [overlap_grad_ring_attention]: 5.01002e-06 [overlap_grad_flash_sp]: 2.778e-05 [begin_end_overlap_inline]: 4.99975e-07 [split_matmul_comm_elemetwise]: 2.07999e-06 [split_layernorm_comm]: 2.09e-06 [handle_group_info]: 9.89996e-07 [symbol_engine_optimizer]: 9.932e-05, [1] [Cycle 1]: 9.456e-05, [6] [build]: 5.59e-06 [elim_shapecalc]: 1.341e-05 [elim_not_effective]: 1.73e-05 [opt_reshape]: 1.064e-05 [fold_const_symbol]: 1.529e-05 [renormalize]: 2.09984e-07 [detach_backward]: 2.25002e-06 [pipeline_parallel_scheduler]: 1.55001e-06 [auto_monad_reorder]: 2.788e-05 [get_jit_bprop_graph]: 1.81998e-06 [rewriter_after_jit_bprop_graph]: 4.89e-06 [opt_after_jit_grad]: 0.00053474 [validate]: 5.811e-05 Sums bootstrap : 0.000484s : 4.77% type_inference : 0.003684s : 36.34% event_method : 0.000015s : 0.14% auto_monad : 0.000134s : 1.32% graph_reusing : 0.000006s : 0.06% inline : 0.000002s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000016s : 0.16% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000003s : 0.03% parallel-infer-symbol : 0.000003s : 0.03% pre_auto_parallel : 0.000036s : 0.35% insert-virtual-dataset : 0.000003s : 0.03% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.02% pipeline_split : 0.000002s : 0.02% optimize.py_interpret_to_execute : 0.000022s : 0.22% optimize.rewriter_before_opt_a : 0.000056s : 0.55% optimize.opt_a.expand_dump_flag : 0.000004s : 0.04% optimize.opt_a.switch_simplify : 0.000038s : 0.37% optimize.opt_a.loop_unroll : 0.000022s : 0.22% optimize.opt_a.a_1 : 0.000589s : 5.81% optimize.opt_a.with_stream_mark : 0.000035s : 0.34% optimize.opt_a.recompute_prepare : 0.000019s : 0.19% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.11% optimize.opt_a.updatestate_assign_eliminate : 0.000010s : 0.10% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.11% optimize.opt_a.parameter_eliminate : 0.000003s : 0.03% optimize.opt_a.a_2 : 0.000231s : 2.28% optimize.opt_a.accelerated_algorithm : 0.000018s : 0.18% optimize.opt_a.shard : 0.000004s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.04% optimize.opt_a.shard_inline : 0.000016s : 0.16% optimize.opt_a.merge_send_recv : 0.000020s : 0.20% optimize.opt_a.auto_parallel : 0.000018s : 0.18% optimize.opt_a.parallel : 0.000038s : 0.37% optimize.opt_a.flash_sp : 0.000013s : 0.13% optimize.opt_a.merge_comm : 0.000010s : 0.10% optimize.opt_a.allreduce_fusion : 0.000010s : 0.10% optimize.opt_a.matmul_add_comm_reduction : 0.000022s : 0.22% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000020s : 0.20% optimize.opt_a.virtual_dataset : 0.000017s : 0.16% optimize.opt_a.get_grad_eliminate_ : 0.000016s : 0.15% optimize.opt_a.virtual_output : 0.000016s : 0.16% optimize.opt_a.merge_forward : 0.000011s : 0.11% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.03% optimize.opt_a.offload_activation : 0.000026s : 0.26% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000036s : 0.36% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.03% optimize.opt_a.before_grad : 0.000032s : 0.31% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.10% optimize.opt_a.meta_fg_expand : 0.000007s : 0.07% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.04% optimize.opt_a.receive_attached : 0.000005s : 0.05% optimize.opt_a.after_resolve : 0.000024s : 0.23% optimize.opt_a.a_after_grad : 0.000025s : 0.24% optimize.opt_a.renormalize : 0.001263s : 12.46% optimize.opt_a.add_forward_monad_depend : 0.000007s : 0.07% optimize.opt_a.auto_monad_grad : 0.000004s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000036s : 0.35% optimize.opt_a.cse : 0.000058s : 0.57% optimize.opt_a.a_3 : 0.000120s : 1.18% optimize.py_interpret_to_execute_after_opt_a : 0.000015s : 0.15% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.02% optimize.rewriter_after_opt_a : 0.000177s : 1.75% optimize.convert_after_rewriter : 0.000010s : 0.10% optimize.order_py_execute_after_rewriter : 0.000006s : 0.06% optimize.mutable_eliminate : 0.000697s : 6.88% optimize.opt_b.b_1 : 0.000188s : 1.86% optimize.opt_b.b_2 : 0.000010s : 0.10% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.05% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.04% optimize.opt_b.renormalize : 0.000001s : 0.01% optimize.opt_b.cse : 0.000024s : 0.23% optimize.optimize_parallel_all_gather_comm : 0.000021s : 0.20% optimize.overlap_param_gather : 0.000007s : 0.07% optimize.cconv : 0.000030s : 0.30% optimize.loop_unroll : 0.000483s : 4.77% optimize.opt_after_cconv.c_1 : 0.000054s : 0.53% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.07% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.cse : 0.000022s : 0.22% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000016s : 0.16% optimize.tuple_transform.d_1 : 0.000057s : 0.56% optimize.tuple_transform.none_parameter_eliminate : 0.000001s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.09% optimize.partial_unused_args_eliminate : 0.000002s : 0.02% optimize.add_recomputation : 0.000073s : 0.72% optimize.cse_after_recomputation.cse : 0.000015s : 0.15% optimize.environ_conv : 0.000007s : 0.07% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.08% optimize.bias_add_comm_swap : 0.000003s : 0.03% optimize.label_micro_interleaved_index : 0.000004s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.03% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 0.03% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000002s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.03% optimize.comm_op_add_attrs : 0.000001s : 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 : 0.000004s : 0.04% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.02% optimize.control_data_broadcast_order : 0.000018s : 0.18% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.02% optimize.offloading_packed_experts : 0.000005s : 0.05% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.06% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.02% optimize.overlap_grad_ring_attention : 0.000005s : 0.05% optimize.overlap_grad_flash_sp : 0.000028s : 0.27% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.02% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.06% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.13% optimize.symbol_engine_optimizer.elim_not_effective : 0.000017s : 0.17% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.10% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 0.15% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.02% auto_monad_reorder : 0.000028s : 0.27% get_jit_bprop_graph : 0.000002s : 0.02% rewriter_after_jit_bprop_graph : 0.000005s : 0.05% opt_after_jit_grad : 0.000535s : 5.27% validate : 0.000058s : 0.57% Time group info: ------[substitution.] 0.000164 55 5.20% : 0.000009s : 2: substitution.depend_value_elim 1.53% : 0.000003s : 5: substitution.elim_not_effective 1.35% : 0.000002s : 5: substitution.fold_const_symbol 4.29% : 0.000007s : 6: substitution.graph_param_transform 59.68% : 0.000098s : 1: substitution.inline 3.12% : 0.000005s : 10: substitution.j_node_and_user_rematch 4.70% : 0.000008s : 10: substitution.remove_not_recompute_node 2.52% : 0.000004s : 2: substitution.replace_old_param 9.60% : 0.000016s : 6: substitution.updatestate_pure_node_eliminater 8.02% : 0.000013s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.003627 2 88.19% : 0.003199s : 1: type_inference.infer 11.81% : 0.000428s : 1: type_inference.specialize ------[replace.] 0.000015 1 100.00% : 0.000015s : 1: replace.inline ------[match.] 0.000097 1 100.00% : 0.000097s : 1: match.inline ------[predicate.] 0.000230 1419 0.96% : 0.000002s : 13: predicate.accumulaten_eliminater 0.99% : 0.000002s : 6: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 12: predicate.addn_check_dump 0.83% : 0.000002s : 13: predicate.addn_zero_filter 0.75% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.97% : 0.000005s : 25: predicate.arithmetic_simplify 0.92% : 0.000002s : 13: predicate.cast_eliminate 0.81% : 0.000002s : 12: predicate.check_bprop_eliminate 0.70% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000000s : 6: predicate.const_output_eliminate 0.76% : 0.000002s : 12: predicate.depend_value_elim 0.90% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 1.02% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.82% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.36% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.30% : 0.000001s : 6: predicate.elim_not_effective 0.48% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.18% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.08% : 0.000002s : 19: predicate.environ_get_depend_swap 2.02% : 0.000005s : 31: predicate.environ_get_eliminate 1.16% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.92% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.37% : 0.000003s : 14: predicate.float_depend_g_call 0.66% : 0.000002s : 12: predicate.float_environ_get_switch 1.01% : 0.000002s : 18: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 6: predicate.fold_const_symbol 0.81% : 0.000002s : 12: predicate.get_grad_eliminate 0.39% : 0.000001s : 6: predicate.graph_param_transform 0.72% : 0.000002s : 12: predicate.incorporate_call 0.65% : 0.000002s : 12: predicate.incorporate_call_switch 5.35% : 0.000012s : 63: predicate.inline 0.86% : 0.000002s : 12: predicate.inline_without_move 0.40% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.03% : 0.000002s : 12: predicate.less_batch_normalization 1.81% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.30% : 0.000005s : 38: predicate.load_eliminater 1.21% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.15% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.85% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.78% : 0.000002s : 12: predicate.merge_addn 0.85% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.79% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.76% : 0.000002s : 13: predicate.minmaximum_grad 1.53% : 0.000004s : 6: predicate.mutable_eliminate 0.48% : 0.000001s : 6: predicate.opt_reshape 0.60% : 0.000001s : 6: predicate.parallel_virtual_node 1.04% : 0.000002s : 14: predicate.partial_defer_inline 1.29% : 0.000003s : 19: predicate.partial_eliminate 0.86% : 0.000002s : 13: predicate.print_const_string_wrapper 0.72% : 0.000002s : 12: predicate.reduce_all_const_elim 0.96% : 0.000002s : 13: predicate.reduce_eliminate 2.29% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.65% : 0.000001s : 12: predicate.remove_not_recompute_node 1.11% : 0.000003s : 25: predicate.replace_applicator 0.66% : 0.000002s : 12: predicate.replace_old_param 0.30% : 0.000001s : 6: predicate.reset_defer_inline 0.84% : 0.000002s : 13: predicate.reshape_eliminate 0.86% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.52% : 0.000001s : 6: predicate.row_tensor_eliminate 1.16% : 0.000003s : 12: predicate.same_eliminate 0.49% : 0.000001s : 12: predicate.set_cell_output_no_recompute 1.06% : 0.000002s : 12: predicate.shard_identity_eliminate 0.99% : 0.000002s : 12: predicate.special_op_eliminate 0.82% : 0.000002s : 12: predicate.specialize_transform 1.06% : 0.000002s : 12: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.89% : 0.000002s : 14: predicate.switch_defer_inline 1.67% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.62% : 0.000008s : 49: predicate.switch_simplify 1.05% : 0.000002s : 13: predicate.tile_eliminate 0.80% : 0.000002s : 13: predicate.transpose_eliminate 1.80% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.91% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000007s : 37: predicate.tuple_list_get_item_eliminator 1.59% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.65% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.62% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.49% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.28% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.46% : 0.000001s : 6: predicate.value_based_eliminate 0.79% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.89% : 0.000002s : 12: predicate.virtual_output_eliminate 0.43% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.67% : 0.000002s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000269 4 7.36% : 0.000020s : 1: func_graph_cloner_run.FuncGraphClonerGraph 92.64% : 0.000249s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.028396 192 0.02% : 0.000004s : 1: ForceFp32Comm 14.83% : 0.004211s : 1: add_attr 14.78% : 0.004198s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.27% : 0.000077s : 1: add_recomputation 0.02% : 0.000004s : 1: assign_add_opt 0.50% : 0.000141s : 1: auto_monad 0.11% : 0.000032s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.02% : 0.000006s : 1: bias_add_comm_swap 1.81% : 0.000515s : 1: bootstrap 0.12% : 0.000034s : 1: cconv 0.02% : 0.000005s : 1: comm_op_add_attrs 0.08% : 0.000022s : 1: control_data_broadcast_order 0.05% : 0.000015s : 1: convert_after_rewriter 0.10% : 0.000029s : 1: cse_after_recomputation 0.02% : 0.000005s : 1: dataset_repeat_opt 0.02% : 0.000006s : 1: detach_backward 0.04% : 0.000011s : 1: environ_conv 0.07% : 0.000021s : 1: event_method 0.02% : 0.000005s : 1: full_micro_interleaved_order_control 0.02% : 0.000005s : 1: get_jit_bprop_graph 0.03% : 0.000010s : 1: graph_reusing 0.02% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.02% : 0.000006s : 1: inline 0.02% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.02% : 0.000005s : 1: interleave_split_concat_branches 0.02% : 0.000006s : 1: label_fine_grained_interleaved_index 0.03% : 0.000008s : 1: label_micro_interleaved_index 1.73% : 0.000492s : 1: loop_unroll 0.02% : 0.000006s : 1: merge_cast_opt 0.02% : 0.000006s : 1: micro_interleaved_order_control 2.49% : 0.000707s : 1: mutable_eliminate 0.03% : 0.000009s : 1: offloading_packed_experts 0.06% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.14% : 0.000040s : 1: opt.transform.mutable_eliminate 4.07% : 0.001157s : 78: opt.transform.opt_a 0.19% : 0.000053s : 1: opt.transform.opt_after_cconv 0.12% : 0.000035s : 1: opt.transform.opt_after_jit_grad 0.60% : 0.000171s : 28: opt.transform.opt_b 0.23% : 0.000064s : 2: opt.transform.opt_trans_graph 0.19% : 0.000054s : 4: opt.transform.symbol_engine_opt 12.05% : 0.003423s : 1: opt_a 0.51% : 0.000145s : 1: opt_after_cconv 1.92% : 0.000546s : 1: opt_after_jit_grad 1.04% : 0.000294s : 1: opt_b 21.35% : 0.006064s : 1: optimize 0.09% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.04% : 0.000010s : 1: order_py_execute_after_rewriter 0.11% : 0.000031s : 1: overlap_grad_flash_sp 0.01% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.03% : 0.000008s : 1: overlap_grad_ring_attention 0.02% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.03% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.04% : 0.000011s : 1: overlap_param_gather 0.02% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.03% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.02% : 0.000005s : 1: overlap_recompute_comm 0.03% : 0.000007s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.02% : 0.000005s : 1: partial_unused_args_eliminate 0.02% : 0.000005s : 1: pipeline_parallel_scheduler 0.02% : 0.000005s : 1: pipeline_split 0.14% : 0.000040s : 1: pre_auto_parallel 0.09% : 0.000026s : 1: py_interpret_to_execute 0.07% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.07% : 0.000020s : 1: remove_dup_value 1.65% : 0.000469s : 1: renormalize.infer 2.76% : 0.000785s : 1: renormalize.specialize 0.02% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.03% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.65% : 0.000184s : 1: rewriter_after_opt_a 0.21% : 0.000060s : 1: rewriter_before_opt_a 0.02% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.02% : 0.000005s : 1: slice_recompute_activation 0.02% : 0.000005s : 1: split_layernorm_comm 0.02% : 0.000006s : 1: split_matmul_comm_elemetwise 0.04% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.36% : 0.000102s : 1: symbol_engine_optimizer 0.34% : 0.000098s : 1: tuple_transform 13.05% : 0.003705s : 1: type_inference TotalTime = 0.0729872, [21] [bootstrap]: 0.0004315 [type_inference]: 0.0196557 [event_method]: 6.414e-05 [auto_monad]: 0.00027155 [graph_reusing]: 1.008e-05 [inline]: 2.90002e-06 [add_attr]: 0.00371871, [1] [add_attr_with_inline]: 0.00370669, [1] [Cycle 1]: 9.364e-05, [2] [tag_attr]: 4.169e-05 [meta_addattr_fg_expand]: 9.71e-06 [parallel-infer-symbol]: 3.5e-06 [pre_auto_parallel]: 5.95e-05 [insert-virtual-dataset]: 2.68e-06 [parallel-infer-symbol-second]: 8.30012e-07 [dataset_repeat_opt]: 2.04e-06 [pipeline_split]: 1.97001e-06 [optimize]: 0.0478951, [53] [py_interpret_to_execute]: 4.982e-05 [rewriter_before_opt_a]: 0.00015855 [opt_a]: 0.0447705, [3] [Cycle 1]: 0.0378405, [45] [expand_dump_flag]: 6.96001e-06 [switch_simplify]: 7.47e-05 [loop_unroll]: 7.165e-05 [a_1]: 0.00207457 [with_stream_mark]: 3.952e-05 [recompute_prepare]: 3.54e-05 [updatestate_depend_eliminate]: 1.385e-05 [updatestate_assign_eliminate]: 1.218e-05 [updatestate_loads_eliminate]: 1.162e-05 [parameter_eliminate]: 3.46001e-06 [a_2]: 0.00033079 [accelerated_algorithm]: 4.22e-05 [shard]: 2.46e-06 [meta_shard_fg_expand]: 6.13998e-06 [shard_inline]: 2.005e-05 [merge_send_recv]: 2.197e-05 [auto_parallel]: 1.57e-05 [parallel]: 2.219e-05 [flash_sp]: 1.466e-05 [merge_comm]: 1.368e-05 [allreduce_fusion]: 1.227e-05 [matmul_add_comm_reduction]: 4.029e-05 [allreduce_slice_to_reducescatter]: 1.07e-06 [virtual_shard_identity]: 2.507e-05 [virtual_dataset]: 2.233e-05 [get_grad_eliminate_]: 2.286e-05 [virtual_output]: 2.174e-05 [merge_forward]: 1.301e-05 [cell_reuse_recompute_pass]: 1.44e-06 [offload_activation]: 2.758e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.589e-05 [merge_recompute_call_nodes]: 1.69e-06 [before_grad]: 4.06e-05 [set_forward_comm_id_for_comm_node_pass]: 1.398e-05 [meta_fg_expand]: 0.021261 [flash_sp_send_recv_attached]: 6.33998e-06 [receive_attached]: 2.45002e-06 [after_resolve]: 0.00014459 [a_after_grad]: 0.00021731 [renormalize]: 0.010516 [add_forward_monad_depend]: 2.476e-05 [auto_monad_grad]: 1.545e-05 [auto_monad_eliminator]: 0.00015238 [cse]: 0.00033124 [a_3]: 0.00164722 [Cycle 2]: 0.00578597, [45] [expand_dump_flag]: 4.15e-06 [switch_simplify]: 0.00010606 [loop_unroll]: 0.00010089 [a_1]: 0.00274578 [with_stream_mark]: 3.188e-05 [recompute_prepare]: 1.777e-05 [updatestate_depend_eliminate]: 3.062e-05 [updatestate_assign_eliminate]: 1.956e-05 [updatestate_loads_eliminate]: 6.43998e-06 [parameter_eliminate]: 2.56e-06 [a_2]: 0.00015731 [accelerated_algorithm]: 1.732e-05 [shard]: 2.17999e-06 [meta_shard_fg_expand]: 4.32e-06 [shard_inline]: 1.2e-05 [merge_send_recv]: 1.263e-05 [auto_parallel]: 1.487e-05 [parallel]: 1.08e-05 [flash_sp]: 4.28001e-06 [merge_comm]: 6.57002e-06 [allreduce_fusion]: 5.99e-06 [matmul_add_comm_reduction]: 1.301e-05 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 1.389e-05 [virtual_dataset]: 1.092e-05 [get_grad_eliminate_]: 1.05e-05 [virtual_output]: 1.057e-05 [merge_forward]: 6.40002e-06 [cell_reuse_recompute_pass]: 1.96998e-06 [offload_activation]: 1.582e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.188e-05 [merge_recompute_call_nodes]: 1.46998e-06 [before_grad]: 1.889e-05 [set_forward_comm_id_for_comm_node_pass]: 6.71e-06 [meta_fg_expand]: 8.019e-05 [flash_sp_send_recv_attached]: 1.49998e-06 [receive_attached]: 3.26001e-06 [after_resolve]: 1.827e-05 [a_after_grad]: 1.718e-05 [renormalize]: 0.00166762 [add_forward_monad_depend]: 8.86002e-06 [auto_monad_grad]: 2.81e-06 [auto_monad_eliminator]: 2.773e-05 [cse]: 0.00013286 [a_3]: 8.869e-05 [Cycle 3]: 0.00112298, [45] [expand_dump_flag]: 2.27001e-06 [switch_simplify]: 1.312e-05 [loop_unroll]: 1.136e-05 [a_1]: 0.00030696 [with_stream_mark]: 1.933e-05 [recompute_prepare]: 1.169e-05 [updatestate_depend_eliminate]: 7.38999e-06 [updatestate_assign_eliminate]: 5.76998e-06 [updatestate_loads_eliminate]: 5.61998e-06 [parameter_eliminate]: 1.63002e-06 [a_2]: 0.00015173 [accelerated_algorithm]: 1.641e-05 [shard]: 2.23998e-06 [meta_shard_fg_expand]: 3.18998e-06 [shard_inline]: 1.111e-05 [merge_send_recv]: 1.137e-05 [auto_parallel]: 1.134e-05 [parallel]: 8.31002e-06 [flash_sp]: 1.57001e-06 [merge_comm]: 7.42998e-06 [allreduce_fusion]: 5.99e-06 [matmul_add_comm_reduction]: 1.319e-05 [allreduce_slice_to_reducescatter]: 5.99975e-07 [virtual_shard_identity]: 1.274e-05 [virtual_dataset]: 1.145e-05 [get_grad_eliminate_]: 1.057e-05 [virtual_output]: 1.051e-05 [merge_forward]: 7e-06 [cell_reuse_recompute_pass]: 2.31e-06 [offload_activation]: 1.302e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.277e-05 [merge_recompute_call_nodes]: 1.14998e-06 [before_grad]: 1.921e-05 [set_forward_comm_id_for_comm_node_pass]: 7.38e-06 [meta_fg_expand]: 4.74998e-06 [flash_sp_send_recv_attached]: 1.89999e-06 [receive_attached]: 2.69999e-06 [after_resolve]: 1.756e-05 [a_after_grad]: 1.662e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 1.79e-06 [auto_monad_grad]: 2.10002e-06 [auto_monad_eliminator]: 1.888e-05 [cse]: 3.227e-05 [a_3]: 6.813e-05 [py_interpret_to_execute_after_opt_a]: 2.416e-05 [slice_cell_reuse_recomputed_activation]: 2.61e-06 [rewriter_after_opt_a]: 6.881e-05 [convert_after_rewriter]: 1.074e-05 [order_py_execute_after_rewriter]: 7.43999e-06 [mutable_eliminate]: 0.00081092 [opt_b]: 0.00039906, [1] [Cycle 1]: 0.00038956, [7] [b_1]: 0.00024925 [b_2]: 1.301e-05 [updatestate_depend_eliminate]: 1.442e-05 [updatestate_assign_eliminate]: 6.54999e-06 [updatestate_loads_eliminate]: 6.33e-06 [renormalize]: 1.20001e-06 [cse]: 5.269e-05 [optimize_parallel_all_gather_comm]: 2.731e-05 [overlap_param_gather]: 2.04e-06 [cconv]: 3.767e-05 [loop_unroll]: 0.00051603 [opt_after_cconv]: 0.00018595, [1] [Cycle 1]: 0.000179, [7] [c_1]: 6.908e-05 [parameter_eliminate]: 4.4e-06 [updatestate_depend_eliminate]: 1.07e-05 [updatestate_assign_eliminate]: 6.11e-06 [updatestate_loads_eliminate]: 5.48997e-06 [cse]: 4.078e-05 [renormalize]: 7.39994e-07 [remove_dup_value]: 2.012e-05 [tuple_transform]: 0.0001239, [1] [Cycle 1]: 0.00011867, [4] [d_1]: 8.233e-05 [none_parameter_eliminate]: 2.07999e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.188e-05 [partial_unused_args_eliminate]: 1.93997e-06 [add_recomputation]: 0.00010636 [cse_after_recomputation]: 4.419e-05, [1] [Cycle 1]: 3.887e-05, [1] [cse]: 3.154e-05 [environ_conv]: 1.279e-05 [swap_dp_allreduce_reducescatter]: 9.75002e-06 [bias_add_comm_swap]: 3.3e-06 [label_micro_interleaved_index]: 5.14e-06 [label_fine_grained_interleaved_index]: 2.71e-06 [merge_cast_opt]: 1.43002e-06 [slice_recompute_activation]: 2.21998e-06 [micro_interleaved_order_control]: 2.29001e-06 [assign_add_opt]: 1.32e-06 [ForceFp32Comm]: 1.15999e-06 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.62001e-06 [reorder_send_recv_between_fp_bp]: 2.84999e-06 [comm_op_add_attrs]: 1.02998e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.39e-06 [interleave_parallel_branches]: 1.24e-06 [overlap_opt_shard_in_pipeline]: 1.60999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.76e-06 [control_data_broadcast_order]: 2.336e-05 [grouped_pairwise_exchange_alltoall]: 1.89e-06 [offloading_packed_experts]: 6.28e-06 [overlap_recompute_and_grad_model_parallel]: 8.16002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.33002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.39001e-06 [overlap_grad_ring_attention]: 7.45998e-06 [overlap_grad_flash_sp]: 3.563e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.30002e-06 [split_layernorm_comm]: 2.20002e-06 [handle_group_info]: 1.00999e-06 [symbol_engine_optimizer]: 0.00012905, [1] [Cycle 1]: 0.00012365, [6] [build]: 1.563e-05 [elim_shapecalc]: 1.727e-05 [elim_not_effective]: 2.416e-05 [opt_reshape]: 1.217e-05 [fold_const_symbol]: 2.014e-05 [renormalize]: 1.59984e-07 [detach_backward]: 2.42001e-06 [pipeline_parallel_scheduler]: 1.38002e-06 [auto_monad_reorder]: 3.626e-05 [get_jit_bprop_graph]: 1.77001e-06 [rewriter_after_jit_bprop_graph]: 7.08e-06 [opt_after_jit_grad]: 0.00057125 [validate]: 7.05e-05 Sums bootstrap : 0.000431s : 0.64% type_inference : 0.019656s : 28.99% event_method : 0.000064s : 0.09% auto_monad : 0.000272s : 0.40% graph_reusing : 0.000010s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000042s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000010s : 0.01% parallel-infer-symbol : 0.000003s : 0.01% pre_auto_parallel : 0.000059s : 0.09% 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 : 0.000050s : 0.07% optimize.rewriter_before_opt_a : 0.000159s : 0.23% optimize.opt_a.expand_dump_flag : 0.000013s : 0.02% optimize.opt_a.switch_simplify : 0.000194s : 0.29% optimize.opt_a.loop_unroll : 0.000184s : 0.27% optimize.opt_a.a_1 : 0.005127s : 7.56% optimize.opt_a.with_stream_mark : 0.000091s : 0.13% optimize.opt_a.recompute_prepare : 0.000065s : 0.10% optimize.opt_a.updatestate_depend_eliminate : 0.000052s : 0.08% optimize.opt_a.updatestate_assign_eliminate : 0.000038s : 0.06% optimize.opt_a.updatestate_loads_eliminate : 0.000024s : 0.03% optimize.opt_a.parameter_eliminate : 0.000008s : 0.01% optimize.opt_a.a_2 : 0.000640s : 0.94% optimize.opt_a.accelerated_algorithm : 0.000076s : 0.11% optimize.opt_a.shard : 0.000007s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000014s : 0.02% optimize.opt_a.shard_inline : 0.000043s : 0.06% optimize.opt_a.merge_send_recv : 0.000046s : 0.07% optimize.opt_a.auto_parallel : 0.000042s : 0.06% optimize.opt_a.parallel : 0.000041s : 0.06% optimize.opt_a.flash_sp : 0.000021s : 0.03% optimize.opt_a.merge_comm : 0.000028s : 0.04% optimize.opt_a.allreduce_fusion : 0.000024s : 0.04% optimize.opt_a.matmul_add_comm_reduction : 0.000066s : 0.10% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.08% optimize.opt_a.virtual_dataset : 0.000045s : 0.07% optimize.opt_a.get_grad_eliminate_ : 0.000044s : 0.06% optimize.opt_a.virtual_output : 0.000043s : 0.06% optimize.opt_a.merge_forward : 0.000026s : 0.04% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.01% optimize.opt_a.offload_activation : 0.000056s : 0.08% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000091s : 0.13% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.01% optimize.opt_a.before_grad : 0.000079s : 0.12% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.04% optimize.opt_a.meta_fg_expand : 0.021346s : 31.49% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.01% optimize.opt_a.receive_attached : 0.000008s : 0.01% optimize.opt_a.after_resolve : 0.000180s : 0.27% optimize.opt_a.a_after_grad : 0.000251s : 0.37% optimize.opt_a.renormalize : 0.012184s : 17.97% optimize.opt_a.add_forward_monad_depend : 0.000035s : 0.05% optimize.opt_a.auto_monad_grad : 0.000020s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000199s : 0.29% optimize.opt_a.cse : 0.000496s : 0.73% optimize.opt_a.a_3 : 0.001804s : 2.66% optimize.py_interpret_to_execute_after_opt_a : 0.000024s : 0.04% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000069s : 0.10% optimize.convert_after_rewriter : 0.000011s : 0.02% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.000811s : 1.20% optimize.opt_b.b_1 : 0.000249s : 0.37% optimize.opt_b.b_2 : 0.000013s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.02% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000053s : 0.08% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.04% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.06% optimize.loop_unroll : 0.000516s : 0.76% optimize.opt_after_cconv.c_1 : 0.000069s : 0.10% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.02% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.cse : 0.000041s : 0.06% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000020s : 0.03% optimize.tuple_transform.d_1 : 0.000082s : 0.12% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.02% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000106s : 0.16% optimize.cse_after_recomputation.cse : 0.000032s : 0.05% optimize.environ_conv : 0.000013s : 0.02% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.01% 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 : 0.000002s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.03% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.01% optimize.overlap_grad_flash_sp : 0.000036s : 0.05% 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 : 0.000016s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000024s : 0.04% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.03% 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 : 0.000036s : 0.05% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.01% opt_after_jit_grad : 0.000571s : 0.84% validate : 0.000070s : 0.10% Time group info: ------[substitution.] 0.002228 310 0.70% : 0.000016s : 4: substitution.depend_value_elim 0.16% : 0.000004s : 7: substitution.elim_not_effective 0.29% : 0.000006s : 7: substitution.float_depend_g_call 0.19% : 0.000004s : 2: substitution.float_tuple_getitem_switch 0.12% : 0.000003s : 7: substitution.fold_const_symbol 34.29% : 0.000764s : 4: substitution.getattr_setattr_resolve 0.41% : 0.000009s : 9: substitution.graph_param_transform 0.13% : 0.000003s : 2: substitution.incorporate_call 0.09% : 0.000002s : 2: substitution.incorporate_call_switch 41.63% : 0.000928s : 24: substitution.inline 2.10% : 0.000047s : 5: substitution.inline_without_move 0.62% : 0.000014s : 28: substitution.j_node_and_user_rematch 0.94% : 0.000021s : 3: substitution.less_batch_normalization 0.66% : 0.000015s : 9: substitution.minmaximum_grad 0.39% : 0.000009s : 7: substitution.partial_eliminate 0.84% : 0.000019s : 28: substitution.remove_not_recompute_node 4.33% : 0.000097s : 38: substitution.replace_applicator 0.87% : 0.000019s : 19: substitution.replace_old_param 0.14% : 0.000003s : 1: substitution.set_cell_output_no_recompute 1.40% : 0.000031s : 9: substitution.tuple_list_convert_item_index_to_positive 0.62% : 0.000014s : 9: substitution.tuple_list_get_item_const_eliminator 0.86% : 0.000019s : 9: substitution.tuple_list_get_item_depend_reorder 4.08% : 0.000091s : 31: substitution.tuple_list_get_item_eliminator 0.88% : 0.000020s : 9: substitution.tuple_list_get_set_item_eliminator 1.37% : 0.000030s : 16: substitution.updatestate_pure_node_eliminater 1.88% : 0.000042s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.019566 2 92.58% : 0.018114s : 1: type_inference.infer 7.42% : 0.001452s : 1: type_inference.specialize ------[replace.] 0.000521 49 13.05% : 0.000068s : 3: replace.getattr_setattr_resolve 41.48% : 0.000216s : 24: replace.inline 10.12% : 0.000053s : 1: replace.replace_applicator 33.37% : 0.000174s : 20: replace.tuple_list_get_item_eliminator 1.97% : 0.000010s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.001703 49 41.80% : 0.000712s : 3: match.getattr_setattr_resolve 53.59% : 0.000913s : 24: match.inline 0.97% : 0.000016s : 1: match.replace_applicator 2.99% : 0.000051s : 20: match.tuple_list_get_item_eliminator 0.66% : 0.000011s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001249 8683 0.90% : 0.000011s : 85: predicate.accumulaten_eliminater 0.24% : 0.000003s : 9: predicate.ad_related_special_op_eliminate 0.39% : 0.000005s : 37: predicate.addn_check_dump 0.88% : 0.000011s : 85: predicate.addn_zero_filter 0.88% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 1.64% : 0.000020s : 122: predicate.arithmetic_simplify 0.92% : 0.000012s : 85: predicate.cast_eliminate 2.67% : 0.000033s : 260: predicate.check_bprop_eliminate 0.42% : 0.000005s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.45% : 0.000006s : 37: predicate.depend_value_elim 0.96% : 0.000012s : 85: predicate.dict_get_item_const_eliminator 1.01% : 0.000013s : 85: predicate.dict_get_item_eliminator 0.90% : 0.000011s : 85: predicate.dict_set_item_eliminator 0.30% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.07% : 0.000001s : 9: predicate.elim_not_effective 0.12% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 1.00% : 0.000012s : 94: predicate.environ_add_const_eliminate 0.98% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.99% : 0.000012s : 94: predicate.environ_get_depend_swap 1.39% : 0.000017s : 131: predicate.environ_get_eliminate 0.96% : 0.000012s : 94: predicate.environ_get_set_eliminate 1.46% : 0.000018s : 130: predicate.exchange_switch_depend_value 1.99% : 0.000025s : 130: predicate.float_depend_g_call 0.40% : 0.000005s : 37: predicate.float_environ_get_switch 0.50% : 0.000006s : 46: predicate.float_tuple_getitem_switch 0.07% : 0.000001s : 9: predicate.fold_const_symbol 0.44% : 0.000005s : 37: predicate.get_grad_eliminate 0.54% : 0.000007s : 20: predicate.getattr_setattr_resolve 0.08% : 0.000001s : 9: predicate.graph_param_transform 0.44% : 0.000005s : 37: predicate.incorporate_call 0.37% : 0.000005s : 37: predicate.incorporate_call_switch 4.51% : 0.000056s : 307: predicate.inline 1.57% : 0.000020s : 111: predicate.inline_without_move 0.22% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.59% : 0.000007s : 37: predicate.less_batch_normalization 1.47% : 0.000018s : 123: predicate.list_to_tuple_eliminator_ 2.17% : 0.000027s : 208: predicate.load_eliminater 0.29% : 0.000004s : 9: predicate.loop_unroll_after_grad 2.18% : 0.000027s : 197: predicate.loop_unroll_before_grad 1.20% : 0.000015s : 103: predicate.make_slice_get_slice_eliminator 0.41% : 0.000005s : 37: predicate.merge_addn 2.69% : 0.000034s : 256: predicate.micro_step_allgather_replace 2.64% : 0.000033s : 256: predicate.mini_step_allgather_replace 0.89% : 0.000011s : 85: predicate.minmaximum_grad 0.33% : 0.000004s : 9: predicate.mutable_eliminate 0.14% : 0.000002s : 9: predicate.opt_reshape 0.12% : 0.000001s : 9: predicate.parallel_virtual_node 1.93% : 0.000024s : 130: predicate.partial_defer_inline 2.96% : 0.000037s : 114: predicate.partial_eliminate 0.95% : 0.000012s : 85: predicate.print_const_string_wrapper 0.41% : 0.000005s : 37: predicate.reduce_all_const_elim 1.14% : 0.000014s : 85: predicate.reduce_eliminate 2.18% : 0.000027s : 208: predicate.redundant_stop_gradient_eliminater 0.26% : 0.000003s : 37: predicate.remove_not_recompute_node 2.56% : 0.000032s : 363: predicate.replace_applicator 0.74% : 0.000009s : 111: predicate.replace_old_param 0.11% : 0.000001s : 9: predicate.reset_defer_inline 0.93% : 0.000012s : 85: predicate.reshape_eliminate 2.72% : 0.000034s : 256: predicate.row_tensor_add_zeros_like 0.13% : 0.000002s : 9: predicate.row_tensor_eliminate 2.85% : 0.000036s : 260: predicate.same_eliminate 0.28% : 0.000004s : 39: predicate.set_cell_output_no_recompute 0.47% : 0.000006s : 37: predicate.shard_identity_eliminate 0.24% : 0.000003s : 18: predicate.special_op_eliminate 0.44% : 0.000006s : 37: predicate.specialize_transform 2.87% : 0.000036s : 256: predicate.split_environ_get_set_with_tuple_value 1.42% : 0.000018s : 111: predicate.stack_unstack_eliminate 0.11% : 0.000001s : 9: predicate.switch_call_monad_eliminater 1.55% : 0.000019s : 130: predicate.switch_defer_inline 4.20% : 0.000052s : 390: predicate.switch_layer_defer_inline 4.30% : 0.000054s : 373: predicate.switch_simplify 0.89% : 0.000011s : 85: predicate.tile_eliminate 0.92% : 0.000011s : 85: predicate.transpose_eliminate 1.19% : 0.000015s : 103: predicate.tuple_list_convert_item_index_to_positive 1.30% : 0.000016s : 103: predicate.tuple_list_get_item_const_eliminator 1.20% : 0.000015s : 103: predicate.tuple_list_get_item_depend_reorder 2.37% : 0.000030s : 160: predicate.tuple_list_get_item_eliminator 1.30% : 0.000016s : 103: predicate.tuple_list_get_set_item_eliminator 1.69% : 0.000021s : 140: predicate.tuple_list_set_item_eliminator 1.38% : 0.000017s : 123: predicate.tuple_to_list_eliminator_ 2.20% : 0.000027s : 208: predicate.updatestate_pure_node_eliminater 2.74% : 0.000034s : 246: predicate.updatestate_useless_node_eliminater 0.14% : 0.000002s : 9: predicate.value_based_eliminate 0.42% : 0.000005s : 37: predicate.virtual_dataset_eliminate 0.45% : 0.000006s : 37: predicate.virtual_output_eliminate 0.09% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.13% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003674 53 56.81% : 0.002087s : 23: func_graph_cloner_run.FuncGraphClonerGraph 43.19% : 0.001587s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.146792 243 0.00% : 0.000004s : 1: ForceFp32Comm 2.54% : 0.003726s : 1: add_attr 2.53% : 0.003711s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.08% : 0.000111s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.19% : 0.000281s : 1: auto_monad 0.03% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.31% : 0.000461s : 1: bootstrap 0.03% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.02% : 0.000027s : 1: control_data_broadcast_order 0.01% : 0.000014s : 1: convert_after_rewriter 0.03% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000016s : 1: environ_conv 0.05% : 0.000073s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000014s : 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% : 0.000007s : 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 0.36% : 0.000526s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.56% : 0.000823s : 1: mutable_eliminate 0.01% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000026s : 1: opt.transform.mutable_eliminate 5.96% : 0.008743s : 125: opt.transform.opt_a 0.05% : 0.000068s : 1: opt.transform.opt_after_cconv 0.03% : 0.000043s : 1: opt.transform.opt_after_jit_grad 0.16% : 0.000231s : 28: opt.transform.opt_b 0.62% : 0.000904s : 2: opt.transform.opt_resolve 0.06% : 0.000092s : 2: opt.transform.opt_trans_graph 0.05% : 0.000069s : 4: opt.transform.symbol_engine_opt 30.50% : 0.044775s : 1: opt_a 0.13% : 0.000190s : 1: opt_after_cconv 0.40% : 0.000582s : 1: opt_after_jit_grad 0.27% : 0.000403s : 1: opt_b 32.63% : 0.047902s : 1: optimize 0.02% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.03% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000010s : 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% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.01% : 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 0.04% : 0.000064s : 1: pre_auto_parallel 0.04% : 0.000054s : 1: py_interpret_to_execute 0.02% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000024s : 1: remove_dup_value 5.12% : 0.007518s : 2: renormalize.infer 3.16% : 0.004640s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000075s : 1: rewriter_after_opt_a 0.11% : 0.000163s : 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% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.09% : 0.000132s : 1: symbol_engine_optimizer 0.09% : 0.000127s : 1: tuple_transform 13.40% : 0.019675s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__inf_nan[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__inf_nan[0],max_mem:4.0M [WARNING] ME(168506:281472966807344,MainProcess):2026-01-29-17:37:40.923.693 [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__inf_nan[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__inf_nan[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 44.77s ========================