==================================================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/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_001/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 1 item test_transpose_bmm_transpose.py [WARNING] ME(155445:281473409142576,MainProcess):2026-01-29-17:37:20.218.975 [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 = 0.314098, [21] [bootstrap]: 0.00072906 [type_inference]: 0.269366 [event_method]: 2.615e-05 [auto_monad]: 0.00037938 [graph_reusing]: 8.37e-06 [inline]: 3.24001e-06 [add_attr]: 0.00806444, [1] [add_attr_with_inline]: 0.00804969, [1] [Cycle 1]: 0.00012755, [2] [tag_attr]: 4.045e-05 [meta_addattr_fg_expand]: 9.06002e-06 [parallel-infer-symbol]: 3.70998e-06 [pre_auto_parallel]: 7.418e-05 [insert-virtual-dataset]: 2.65997e-06 [parallel-infer-symbol-second]: 1.05999e-06 [dataset_repeat_opt]: 2.24001e-06 [pipeline_split]: 2.06e-06 [optimize]: 0.0343556, [53] [py_interpret_to_execute]: 4.428e-05 [rewriter_before_opt_a]: 0.00015637 [opt_a]: 0.030544, [2] [Cycle 1]: 0.0290347, [45] [expand_dump_flag]: 4.28001e-06 [switch_simplify]: 6.467e-05 [loop_unroll]: 4.837e-05 [a_1]: 0.025669 [with_stream_mark]: 4.248e-05 [recompute_prepare]: 3.068e-05 [updatestate_depend_eliminate]: 0.00010453 [updatestate_assign_eliminate]: 1.444e-05 [updatestate_loads_eliminate]: 1.234e-05 [parameter_eliminate]: 2.73e-06 [a_2]: 0.00022513 [accelerated_algorithm]: 1.618e-05 [shard]: 2.81e-06 [meta_shard_fg_expand]: 6.80998e-06 [shard_inline]: 1.424e-05 [merge_send_recv]: 1.639e-05 [auto_parallel]: 1.689e-05 [parallel]: 4.365e-05 [flash_sp]: 1.586e-05 [merge_comm]: 9.89999e-06 [allreduce_fusion]: 8.78001e-06 [matmul_add_comm_reduction]: 1.791e-05 [allreduce_slice_to_reducescatter]: 1.07e-06 [virtual_shard_identity]: 1.908e-05 [virtual_dataset]: 1.464e-05 [get_grad_eliminate_]: 1.448e-05 [virtual_output]: 1.344e-05 [merge_forward]: 1.048e-05 [cell_reuse_recompute_pass]: 2.46e-06 [offload_activation]: 1.686e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.37e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 2.531e-05 [set_forward_comm_id_for_comm_node_pass]: 1.067e-05 [meta_fg_expand]: 7.42998e-06 [flash_sp_send_recv_attached]: 3.35e-06 [receive_attached]: 1.508e-05 [after_resolve]: 2.295e-05 [a_after_grad]: 2.262e-05 [renormalize]: 0.00174002 [add_forward_monad_depend]: 1.001e-05 [auto_monad_grad]: 2.44999e-06 [auto_monad_eliminator]: 3.92e-05 [cse]: 0.00012197 [a_3]: 0.00014117 [Cycle 2]: 0.00149304, [45] [expand_dump_flag]: 2.78e-06 [switch_simplify]: 1.755e-05 [loop_unroll]: 1.362e-05 [a_1]: 0.00037402 [with_stream_mark]: 2.909e-05 [recompute_prepare]: 1.778e-05 [updatestate_depend_eliminate]: 1.099e-05 [updatestate_assign_eliminate]: 9.12001e-06 [updatestate_loads_eliminate]: 1.243e-05 [parameter_eliminate]: 2.84001e-06 [a_2]: 0.00019857 [accelerated_algorithm]: 1.776e-05 [shard]: 3.7e-06 [meta_shard_fg_expand]: 4.70001e-06 [shard_inline]: 1.5e-05 [merge_send_recv]: 1.666e-05 [auto_parallel]: 1.69e-05 [parallel]: 1.034e-05 [flash_sp]: 4.89998e-06 [merge_comm]: 9.66e-06 [allreduce_fusion]: 8.40001e-06 [matmul_add_comm_reduction]: 1.792e-05 [allreduce_slice_to_reducescatter]: 7.30011e-07 [virtual_shard_identity]: 2.042e-05 [virtual_dataset]: 1.318e-05 [get_grad_eliminate_]: 1.371e-05 [virtual_output]: 1.356e-05 [merge_forward]: 8.96998e-06 [cell_reuse_recompute_pass]: 3.26999e-06 [offload_activation]: 1.83e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.275e-05 [merge_recompute_call_nodes]: 1.48002e-06 [before_grad]: 2.581e-05 [set_forward_comm_id_for_comm_node_pass]: 1.129e-05 [meta_fg_expand]: 6.27001e-06 [flash_sp_send_recv_attached]: 2.06e-06 [receive_attached]: 2.56998e-06 [after_resolve]: 2.316e-05 [a_after_grad]: 2.196e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 4.62e-06 [auto_monad_grad]: 3.28998e-06 [auto_monad_eliminator]: 3.188e-05 [cse]: 5.452e-05 [a_3]: 9.361e-05 [py_interpret_to_execute_after_opt_a]: 2.645e-05 [slice_cell_reuse_recomputed_activation]: 2.76e-06 [rewriter_after_opt_a]: 0.00023039 [convert_after_rewriter]: 1.812e-05 [order_py_execute_after_rewriter]: 1.002e-05 [mutable_eliminate]: 0.00079024 [opt_b]: 0.00052459, [1] [Cycle 1]: 0.00051438, [7] [b_1]: 0.0003364 [b_2]: 1.877e-05 [updatestate_depend_eliminate]: 1.972e-05 [updatestate_assign_eliminate]: 8.80001e-06 [updatestate_loads_eliminate]: 1.219e-05 [renormalize]: 7.60017e-07 [cse]: 6.594e-05 [optimize_parallel_all_gather_comm]: 3.584e-05 [overlap_param_gather]: 2.11e-06 [cconv]: 4.242e-05 [loop_unroll]: 0.00061503 [opt_after_cconv]: 0.00028126, [1] [Cycle 1]: 0.00027166, [7] [c_1]: 0.00013291 [parameter_eliminate]: 6.22001e-06 [updatestate_depend_eliminate]: 1.749e-05 [updatestate_assign_eliminate]: 9.07001e-06 [updatestate_loads_eliminate]: 1.07e-05 [cse]: 5.136e-05 [renormalize]: 1.65001e-06 [remove_dup_value]: 6.335e-05 [tuple_transform]: 0.00014383, [1] [Cycle 1]: 0.0001369, [4] [d_1]: 9.857e-05 [none_parameter_eliminate]: 2.44999e-06 [renormalize]: 2.29978e-07 [switch_simplify]: 1.499e-05 [partial_unused_args_eliminate]: 2.63e-06 [add_recomputation]: 0.00011754 [cse_after_recomputation]: 4.269e-05, [1] [Cycle 1]: 3.719e-05, [1] [cse]: 3.091e-05 [environ_conv]: 2.5e-05 [swap_dp_allreduce_reducescatter]: 1.256e-05 [bias_add_comm_swap]: 3.55e-06 [label_micro_interleaved_index]: 7.06001e-06 [label_fine_grained_interleaved_index]: 2.61e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.04999e-06 [micro_interleaved_order_control]: 2.50002e-06 [assign_add_opt]: 1.28002e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.04e-06 [reorder_send_recv_between_fp_bp]: 2.79001e-06 [comm_op_add_attrs]: 1.03001e-06 [add_comm_op_reuse_tag]: 1.39998e-06 [interleave_split_concat_branches]: 1.57001e-06 [interleave_parallel_branches]: 1.57001e-06 [overlap_opt_shard_in_pipeline]: 2.576e-05 [overlap_opt_shard_grad_in_pipeline]: 1.77999e-06 [control_data_broadcast_order]: 3.03e-05 [grouped_pairwise_exchange_alltoall]: 1.73002e-06 [offloading_packed_experts]: 7.83999e-06 [overlap_recompute_and_grad_model_parallel]: 8.22e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.60001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37e-06 [overlap_recompute_comm]: 2.37001e-06 [overlap_grad_ring_attention]: 7.38999e-06 [overlap_grad_flash_sp]: 5.539e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.36e-06 [split_layernorm_comm]: 1.87001e-06 [handle_group_info]: 1.00001e-06 [symbol_engine_optimizer]: 0.000142, [1] [Cycle 1]: 0.00013582, [6] [build]: 6.61999e-06 [elim_shapecalc]: 2.461e-05 [elim_not_effective]: 2.783e-05 [opt_reshape]: 1.559e-05 [fold_const_symbol]: 2.396e-05 [renormalize]: 1.69995e-07 [detach_backward]: 2.06e-06 [pipeline_parallel_scheduler]: 1.64e-06 [auto_monad_reorder]: 5.857e-05 [get_jit_bprop_graph]: 2.34001e-06 [rewriter_after_jit_bprop_graph]: 6.94999e-06 [opt_after_jit_grad]: 0.00072001 [validate]: 8.992e-05 Sums bootstrap : 0.000729s : 0.24% type_inference : 0.269366s : 88.39% event_method : 0.000026s : 0.01% auto_monad : 0.000379s : 0.12% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000040s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000074s : 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 : 0.000044s : 0.01% optimize.rewriter_before_opt_a : 0.000156s : 0.05% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000082s : 0.03% optimize.opt_a.loop_unroll : 0.000062s : 0.02% optimize.opt_a.a_1 : 0.026043s : 8.55% optimize.opt_a.with_stream_mark : 0.000072s : 0.02% optimize.opt_a.recompute_prepare : 0.000048s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000116s : 0.04% optimize.opt_a.updatestate_assign_eliminate : 0.000024s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000025s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000424s : 0.14% optimize.opt_a.accelerated_algorithm : 0.000034s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.00% optimize.opt_a.shard_inline : 0.000029s : 0.01% optimize.opt_a.merge_send_recv : 0.000033s : 0.01% optimize.opt_a.auto_parallel : 0.000034s : 0.01% optimize.opt_a.parallel : 0.000054s : 0.02% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000020s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000040s : 0.01% optimize.opt_a.virtual_dataset : 0.000028s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.01% optimize.opt_a.virtual_output : 0.000027s : 0.01% optimize.opt_a.merge_forward : 0.000019s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000035s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000066s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000051s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.01% optimize.opt_a.meta_fg_expand : 0.000014s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000018s : 0.01% optimize.opt_a.after_resolve : 0.000046s : 0.02% optimize.opt_a.a_after_grad : 0.000045s : 0.01% optimize.opt_a.renormalize : 0.001740s : 0.57% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000071s : 0.02% optimize.opt_a.cse : 0.000176s : 0.06% optimize.opt_a.a_3 : 0.000235s : 0.08% 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 : 0.000230s : 0.08% optimize.convert_after_rewriter : 0.000018s : 0.01% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000790s : 0.26% optimize.opt_b.b_1 : 0.000336s : 0.11% optimize.opt_b.b_2 : 0.000019s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000066s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.01% optimize.loop_unroll : 0.000615s : 0.20% optimize.opt_after_cconv.c_1 : 0.000133s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000051s : 0.02% optimize.opt_after_cconv.renormalize : 0.000002s : 0.00% optimize.remove_dup_value : 0.000063s : 0.02% optimize.tuple_transform.d_1 : 0.000099s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000118s : 0.04% optimize.cse_after_recomputation.cse : 0.000031s : 0.01% optimize.environ_conv : 0.000025s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 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 : 0.000002s : 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 : 0.000026s : 0.01% 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 : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000055s : 0.02% 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 : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000059s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000720s : 0.24% validate : 0.000090s : 0.03% Time group info: ------[substitution.] 0.000592 158 1.77% : 0.000010s : 2: substitution.depend_value_elim 0.73% : 0.000004s : 9: substitution.elim_not_effective 0.60% : 0.000004s : 9: substitution.fold_const_symbol 1.90% : 0.000011s : 11: substitution.graph_param_transform 70.32% : 0.000417s : 7: substitution.inline 1.53% : 0.000009s : 18: substitution.j_node_and_user_rematch 1.20% : 0.000007s : 6: substitution.load_eliminater 2.25% : 0.000013s : 18: substitution.remove_not_recompute_node 1.18% : 0.000007s : 4: substitution.replace_old_param 9.30% : 0.000055s : 34: substitution.updatestate_pure_node_eliminater 9.22% : 0.000055s : 40: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.269269 2 99.43% : 0.267732s : 1: type_inference.infer 0.57% : 0.001537s : 1: type_inference.specialize ------[replace.] 0.000087 7 100.00% : 0.000087s : 7: replace.inline ------[match.] 0.000411 7 100.00% : 0.000411s : 7: match.inline ------[predicate.] 0.000563 3413 1.06% : 0.000006s : 39: predicate.accumulaten_eliminater 0.72% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.56% : 0.000003s : 22: predicate.addn_check_dump 1.00% : 0.000006s : 39: predicate.addn_zero_filter 0.91% : 0.000005s : 39: predicate.adjust_all_reduce_mul_add 2.26% : 0.000013s : 61: predicate.arithmetic_simplify 1.10% : 0.000006s : 39: predicate.cast_eliminate 0.56% : 0.000003s : 22: predicate.check_bprop_eliminate 0.55% : 0.000003s : 22: predicate.compare_switch_simplify 0.15% : 0.000001s : 11: predicate.const_output_eliminate 0.58% : 0.000003s : 22: predicate.depend_value_elim 1.03% : 0.000006s : 39: predicate.dict_get_item_const_eliminator 1.07% : 0.000006s : 39: predicate.dict_get_item_eliminator 1.01% : 0.000006s : 39: predicate.dict_set_item_eliminator 0.86% : 0.000005s : 22: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 11: predicate.elim_not_effective 0.48% : 0.000003s : 11: predicate.elim_shapecalc_of_broadcastargs 1.29% : 0.000007s : 50: predicate.environ_add_const_eliminate 1.23% : 0.000007s : 50: predicate.environ_get_add_eliminate 1.30% : 0.000007s : 50: predicate.environ_get_depend_swap 1.81% : 0.000010s : 72: predicate.environ_get_eliminate 1.24% : 0.000007s : 50: predicate.environ_get_set_eliminate 1.17% : 0.000007s : 46: predicate.exchange_switch_depend_value 1.73% : 0.000010s : 46: predicate.float_depend_g_call 0.53% : 0.000003s : 22: predicate.float_environ_get_switch 0.91% : 0.000005s : 33: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 11: predicate.fold_const_symbol 0.73% : 0.000004s : 22: predicate.get_grad_eliminate 0.20% : 0.000001s : 11: predicate.graph_param_transform 0.55% : 0.000003s : 22: predicate.incorporate_call 0.50% : 0.000003s : 22: predicate.incorporate_call_switch 5.64% : 0.000032s : 151: predicate.inline 0.79% : 0.000004s : 22: predicate.inline_without_move 0.29% : 0.000002s : 22: predicate.j_node_and_user_rematch 0.88% : 0.000005s : 22: predicate.less_batch_normalization 1.83% : 0.000010s : 61: predicate.list_to_tuple_eliminator_ 2.52% : 0.000014s : 100: predicate.load_eliminater 0.77% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.65% : 0.000009s : 66: predicate.loop_unroll_before_grad 1.77% : 0.000010s : 61: predicate.make_slice_get_slice_eliminator 0.59% : 0.000003s : 22: predicate.merge_addn 0.56% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.56% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.92% : 0.000005s : 39: predicate.minmaximum_grad 0.92% : 0.000005s : 11: predicate.mutable_eliminate 0.36% : 0.000002s : 11: predicate.opt_reshape 0.34% : 0.000002s : 11: predicate.parallel_virtual_node 1.82% : 0.000010s : 46: predicate.partial_defer_inline 1.83% : 0.000010s : 50: predicate.partial_eliminate 1.00% : 0.000006s : 39: predicate.print_const_string_wrapper 0.57% : 0.000003s : 22: predicate.reduce_all_const_elim 1.35% : 0.000008s : 39: predicate.reduce_eliminate 2.57% : 0.000014s : 100: predicate.redundant_stop_gradient_eliminater 0.41% : 0.000002s : 22: predicate.remove_not_recompute_node 1.24% : 0.000007s : 61: predicate.replace_applicator 0.42% : 0.000002s : 22: predicate.replace_old_param 0.24% : 0.000001s : 11: predicate.reset_defer_inline 1.11% : 0.000006s : 39: predicate.reshape_eliminate 0.61% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.39% : 0.000002s : 11: predicate.row_tensor_eliminate 0.72% : 0.000004s : 22: predicate.same_eliminate 0.48% : 0.000003s : 30: predicate.set_cell_output_no_recompute 0.91% : 0.000005s : 22: predicate.shard_identity_eliminate 0.72% : 0.000004s : 22: predicate.special_op_eliminate 0.70% : 0.000004s : 22: predicate.specialize_transform 1.04% : 0.000006s : 22: predicate.split_environ_get_set_with_tuple_value 0.73% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.36% : 0.000002s : 11: predicate.switch_call_monad_eliminater 1.20% : 0.000007s : 46: predicate.switch_defer_inline 1.81% : 0.000010s : 68: predicate.switch_layer_defer_inline 4.00% : 0.000023s : 145: predicate.switch_simplify 1.00% : 0.000006s : 39: predicate.tile_eliminate 1.00% : 0.000006s : 39: predicate.transpose_eliminate 1.74% : 0.000010s : 61: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000010s : 61: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000009s : 61: predicate.tuple_list_get_item_depend_reorder 2.84% : 0.000016s : 83: predicate.tuple_list_get_item_eliminator 1.72% : 0.000010s : 61: predicate.tuple_list_get_set_item_eliminator 2.55% : 0.000014s : 83: predicate.tuple_list_set_item_eliminator 1.57% : 0.000009s : 61: predicate.tuple_to_list_eliminator_ 2.85% : 0.000016s : 100: predicate.updatestate_pure_node_eliminater 5.12% : 0.000029s : 122: predicate.updatestate_useless_node_eliminater 0.34% : 0.000002s : 11: predicate.value_based_eliminate 0.62% : 0.000004s : 22: predicate.virtual_dataset_eliminate 0.59% : 0.000003s : 22: predicate.virtual_output_eliminate 0.29% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.36% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000562 10 4.78% : 0.000027s : 1: func_graph_cloner_run.FuncGraphClonerGraph 95.22% : 0.000535s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.385970 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.09% : 0.008071s : 1: add_attr 2.09% : 0.008054s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000123s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.10% : 0.000391s : 1: auto_monad 0.02% : 0.000065s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.20% : 0.000767s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000035s : 1: control_data_broadcast_order 0.01% : 0.000023s : 1: convert_after_rewriter 0.01% : 0.000046s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000030s : 1: environ_conv 0.01% : 0.000034s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000004s : 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% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.16% : 0.000630s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.21% : 0.000809s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000035s : 1: opt.transform.mutable_eliminate 7.04% : 0.027160s : 78: opt.transform.opt_a 0.03% : 0.000131s : 1: opt.transform.opt_after_cconv 0.01% : 0.000057s : 1: opt.transform.opt_after_jit_grad 0.08% : 0.000321s : 28: opt.transform.opt_b 0.03% : 0.000110s : 2: opt.transform.opt_trans_graph 0.02% : 0.000086s : 4: opt.transform.symbol_engine_opt 7.91% : 0.030548s : 1: opt_a 0.07% : 0.000286s : 1: opt_after_cconv 0.19% : 0.000737s : 1: opt_after_jit_grad 0.14% : 0.000530s : 1: opt_b 8.90% : 0.034361s : 1: optimize 0.01% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.02% : 0.000061s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000031s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 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 0.02% : 0.000079s : 1: pre_auto_parallel 0.01% : 0.000050s : 1: py_interpret_to_execute 0.01% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000069s : 1: remove_dup_value 0.26% : 0.001004s : 1: renormalize.infer 0.19% : 0.000722s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000243s : 1: rewriter_after_opt_a 0.04% : 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% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000145s : 1: symbol_engine_optimizer 0.04% : 0.000147s : 1: tuple_transform 69.80% : 0.269389s : 1: type_inference [WARNING] ME(155445:281473409142576,MainProcess):2026-01-29-17:37:46.250.359 [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 = 0.333619, [21] [bootstrap]: 0.00050609 [type_inference]: 0.316896 [event_method]: 2.568e-05 [auto_monad]: 0.00033402 [graph_reusing]: 8.31002e-06 [inline]: 2.85002e-06 [add_attr]: 0.00428538, [1] [add_attr_with_inline]: 0.00427057, [1] [Cycle 1]: 0.00010113, [2] [tag_attr]: 4.227e-05 [meta_addattr_fg_expand]: 1.012e-05 [parallel-infer-symbol]: 4.15999e-06 [pre_auto_parallel]: 6.094e-05 [insert-virtual-dataset]: 2.41e-06 [parallel-infer-symbol-second]: 2.11e-06 [dataset_repeat_opt]: 2.21e-06 [pipeline_split]: 1.72999e-06 [optimize]: 0.0106028, [53] [py_interpret_to_execute]: 5.943e-05 [rewriter_before_opt_a]: 0.00016017 [opt_a]: 0.00712918, [2] [Cycle 1]: 0.00571098, [45] [expand_dump_flag]: 4.92e-06 [switch_simplify]: 6.983e-05 [loop_unroll]: 5.382e-05 [a_1]: 0.00186175 [with_stream_mark]: 3.364e-05 [recompute_prepare]: 3.177e-05 [updatestate_depend_eliminate]: 0.0001012 [updatestate_assign_eliminate]: 9.72999e-06 [updatestate_loads_eliminate]: 1.235e-05 [parameter_eliminate]: 2.37001e-06 [a_2]: 0.00025347 [accelerated_algorithm]: 1.908e-05 [shard]: 2.59999e-06 [meta_shard_fg_expand]: 4.67998e-06 [shard_inline]: 1.536e-05 [merge_send_recv]: 1.72e-05 [auto_parallel]: 1.663e-05 [parallel]: 3.175e-05 [flash_sp]: 1.386e-05 [merge_comm]: 9.24e-06 [allreduce_fusion]: 8.74e-06 [matmul_add_comm_reduction]: 1.752e-05 [allreduce_slice_to_reducescatter]: 1.02998e-06 [virtual_shard_identity]: 1.849e-05 [virtual_dataset]: 2.33e-05 [get_grad_eliminate_]: 1.708e-05 [virtual_output]: 1.7e-05 [merge_forward]: 1.107e-05 [cell_reuse_recompute_pass]: 2.22999e-06 [offload_activation]: 1.914e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.559e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 2.73e-05 [set_forward_comm_id_for_comm_node_pass]: 1.041e-05 [meta_fg_expand]: 7.36999e-06 [flash_sp_send_recv_attached]: 3.57002e-06 [receive_attached]: 2.71e-06 [after_resolve]: 2.399e-05 [a_after_grad]: 2.743e-05 [renormalize]: 0.00209636 [add_forward_monad_depend]: 8.87e-06 [auto_monad_grad]: 2.91999e-06 [auto_monad_eliminator]: 3.583e-05 [cse]: 0.00012383 [a_3]: 0.0001219 [Cycle 2]: 0.00140368, [45] [expand_dump_flag]: 2.16998e-06 [switch_simplify]: 1.719e-05 [loop_unroll]: 1.453e-05 [a_1]: 0.00039328 [with_stream_mark]: 2.639e-05 [recompute_prepare]: 1.547e-05 [updatestate_depend_eliminate]: 9.58002e-06 [updatestate_assign_eliminate]: 8.43999e-06 [updatestate_loads_eliminate]: 1.16e-05 [parameter_eliminate]: 2.12001e-06 [a_2]: 0.00020061 [accelerated_algorithm]: 1.429e-05 [shard]: 2.61e-06 [meta_shard_fg_expand]: 3.63999e-06 [shard_inline]: 1.648e-05 [merge_send_recv]: 1.448e-05 [auto_parallel]: 1.556e-05 [parallel]: 9.36998e-06 [flash_sp]: 4.49998e-06 [merge_comm]: 8.54998e-06 [allreduce_fusion]: 7.91001e-06 [matmul_add_comm_reduction]: 1.532e-05 [allreduce_slice_to_reducescatter]: 8.10018e-07 [virtual_shard_identity]: 1.627e-05 [virtual_dataset]: 1.435e-05 [get_grad_eliminate_]: 1.323e-05 [virtual_output]: 1.349e-05 [merge_forward]: 9.02e-06 [cell_reuse_recompute_pass]: 3.30003e-06 [offload_activation]: 1.615e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.867e-05 [merge_recompute_call_nodes]: 1.22e-06 [before_grad]: 2.434e-05 [set_forward_comm_id_for_comm_node_pass]: 8.72e-06 [meta_fg_expand]: 5.66e-06 [flash_sp_send_recv_attached]: 1.55999e-06 [receive_attached]: 2.79999e-06 [after_resolve]: 2.164e-05 [a_after_grad]: 2.177e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.06e-06 [auto_monad_grad]: 1.94e-06 [auto_monad_eliminator]: 2.309e-05 [cse]: 4.061e-05 [a_3]: 9.237e-05 [py_interpret_to_execute_after_opt_a]: 2.322e-05 [slice_cell_reuse_recomputed_activation]: 2.32999e-06 [rewriter_after_opt_a]: 0.00018049 [convert_after_rewriter]: 1.384e-05 [order_py_execute_after_rewriter]: 9.62999e-06 [mutable_eliminate]: 0.0007633 [opt_b]: 0.0005458, [1] [Cycle 1]: 0.00053653, [7] [b_1]: 0.00037446 [b_2]: 1.802e-05 [updatestate_depend_eliminate]: 1.515e-05 [updatestate_assign_eliminate]: 8.80999e-06 [updatestate_loads_eliminate]: 1.193e-05 [renormalize]: 9.60019e-07 [cse]: 6.345e-05 [optimize_parallel_all_gather_comm]: 2.988e-05 [overlap_param_gather]: 2.31e-06 [cconv]: 3.605e-05 [loop_unroll]: 0.00049559 [opt_after_cconv]: 0.00022648, [1] [Cycle 1]: 0.00021967, [7] [c_1]: 0.00010629 [parameter_eliminate]: 3.66001e-06 [updatestate_depend_eliminate]: 1.146e-05 [updatestate_assign_eliminate]: 7.85e-06 [updatestate_loads_eliminate]: 9.36e-06 [cse]: 4.327e-05 [renormalize]: 3.69997e-07 [remove_dup_value]: 5.695e-05 [tuple_transform]: 0.00015422, [1] [Cycle 1]: 0.00014901, [4] [d_1]: 0.00011102 [none_parameter_eliminate]: 1.74e-06 [renormalize]: 2.30008e-07 [switch_simplify]: 1.554e-05 [partial_unused_args_eliminate]: 1.80001e-06 [add_recomputation]: 0.00011847 [cse_after_recomputation]: 4.368e-05, [1] [Cycle 1]: 3.811e-05, [1] [cse]: 3.166e-05 [environ_conv]: 9.32999e-06 [swap_dp_allreduce_reducescatter]: 1.121e-05 [bias_add_comm_swap]: 2.74001e-06 [label_micro_interleaved_index]: 4.68999e-06 [label_fine_grained_interleaved_index]: 2.73e-06 [merge_cast_opt]: 1.42e-06 [slice_recompute_activation]: 1.96003e-06 [micro_interleaved_order_control]: 2.37999e-06 [assign_add_opt]: 1.24e-06 [ForceFp32Comm]: 1.18001e-06 [remove_cast_before_assign_add]: 1.14998e-06 [full_micro_interleaved_order_control]: 1.99999e-06 [reorder_send_recv_between_fp_bp]: 2.76e-06 [comm_op_add_attrs]: 1.10001e-06 [add_comm_op_reuse_tag]: 1.54e-06 [interleave_split_concat_branches]: 1.18001e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 1.35001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.93002e-06 [control_data_broadcast_order]: 2.856e-05 [grouped_pairwise_exchange_alltoall]: 1.60001e-06 [offloading_packed_experts]: 7.52002e-06 [overlap_recompute_and_grad_model_parallel]: 8.37e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.14998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.71e-06 [overlap_recompute_comm]: 1.98997e-06 [overlap_grad_ring_attention]: 8.08001e-06 [overlap_grad_flash_sp]: 3.948e-05 [begin_end_overlap_inline]: 6.10016e-07 [split_matmul_comm_elemetwise]: 2.46e-06 [split_layernorm_comm]: 2.02999e-06 [handle_group_info]: 1.36002e-06 [symbol_engine_optimizer]: 0.00014042, [1] [Cycle 1]: 0.00013346, [6] [build]: 7.46001e-06 [elim_shapecalc]: 2.322e-05 [elim_not_effective]: 2.769e-05 [opt_reshape]: 1.639e-05 [fold_const_symbol]: 2.619e-05 [renormalize]: 3.60014e-07 [detach_backward]: 2.16e-06 [pipeline_parallel_scheduler]: 1.56998e-06 [auto_monad_reorder]: 5.112e-05 [get_jit_bprop_graph]: 2.01003e-06 [rewriter_after_jit_bprop_graph]: 5.46e-06 [opt_after_jit_grad]: 0.00056167 [validate]: 7.486e-05 Sums bootstrap : 0.000506s : 0.15% type_inference : 0.316896s : 96.60% event_method : 0.000026s : 0.01% auto_monad : 0.000334s : 0.10% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000042s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000010s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000061s : 0.02% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000059s : 0.02% optimize.rewriter_before_opt_a : 0.000160s : 0.05% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000087s : 0.03% optimize.opt_a.loop_unroll : 0.000068s : 0.02% optimize.opt_a.a_1 : 0.002255s : 0.69% optimize.opt_a.with_stream_mark : 0.000060s : 0.02% optimize.opt_a.recompute_prepare : 0.000047s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000111s : 0.03% optimize.opt_a.updatestate_assign_eliminate : 0.000018s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000024s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000454s : 0.14% optimize.opt_a.accelerated_algorithm : 0.000033s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.01% optimize.opt_a.merge_send_recv : 0.000032s : 0.01% optimize.opt_a.auto_parallel : 0.000032s : 0.01% optimize.opt_a.parallel : 0.000041s : 0.01% optimize.opt_a.flash_sp : 0.000018s : 0.01% optimize.opt_a.merge_comm : 0.000018s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000035s : 0.01% optimize.opt_a.virtual_dataset : 0.000038s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000030s : 0.01% optimize.opt_a.virtual_output : 0.000030s : 0.01% optimize.opt_a.merge_forward : 0.000020s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000035s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000064s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000052s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000046s : 0.01% optimize.opt_a.a_after_grad : 0.000049s : 0.01% optimize.opt_a.renormalize : 0.002096s : 0.64% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000059s : 0.02% optimize.opt_a.cse : 0.000164s : 0.05% optimize.opt_a.a_3 : 0.000214s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000180s : 0.06% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000763s : 0.23% optimize.opt_b.b_1 : 0.000374s : 0.11% optimize.opt_b.b_2 : 0.000018s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000063s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000036s : 0.01% optimize.loop_unroll : 0.000496s : 0.15% optimize.opt_after_cconv.c_1 : 0.000106s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000043s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000057s : 0.02% optimize.tuple_transform.d_1 : 0.000111s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000118s : 0.04% optimize.cse_after_recomputation.cse : 0.000032s : 0.01% optimize.environ_conv : 0.000009s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 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 : 0.000002s : 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 : 0.000002s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 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 : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000026s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000051s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000562s : 0.17% validate : 0.000075s : 0.02% Time group info: ------[substitution.] 0.000538 158 1.80% : 0.000010s : 2: substitution.depend_value_elim 0.68% : 0.000004s : 9: substitution.elim_not_effective 0.63% : 0.000003s : 9: substitution.fold_const_symbol 1.88% : 0.000010s : 11: substitution.graph_param_transform 70.20% : 0.000378s : 7: substitution.inline 1.61% : 0.000009s : 18: substitution.j_node_and_user_rematch 1.22% : 0.000007s : 6: substitution.load_eliminater 2.66% : 0.000014s : 18: substitution.remove_not_recompute_node 1.31% : 0.000007s : 4: substitution.replace_old_param 8.33% : 0.000045s : 34: substitution.updatestate_pure_node_eliminater 9.68% : 0.000052s : 40: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.316808 2 99.42% : 0.314970s : 1: type_inference.infer 0.58% : 0.001838s : 1: type_inference.specialize ------[replace.] 0.000086 7 100.00% : 0.000086s : 7: replace.inline ------[match.] 0.000373 7 100.00% : 0.000373s : 7: match.inline ------[predicate.] 0.000566 3413 1.05% : 0.000006s : 39: predicate.accumulaten_eliminater 0.65% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.53% : 0.000003s : 22: predicate.addn_check_dump 1.02% : 0.000006s : 39: predicate.addn_zero_filter 1.00% : 0.000006s : 39: predicate.adjust_all_reduce_mul_add 2.13% : 0.000012s : 61: predicate.arithmetic_simplify 1.05% : 0.000006s : 39: predicate.cast_eliminate 0.57% : 0.000003s : 22: predicate.check_bprop_eliminate 0.54% : 0.000003s : 22: predicate.compare_switch_simplify 0.15% : 0.000001s : 11: predicate.const_output_eliminate 0.60% : 0.000003s : 22: predicate.depend_value_elim 1.10% : 0.000006s : 39: predicate.dict_get_item_const_eliminator 1.24% : 0.000007s : 39: predicate.dict_get_item_eliminator 1.00% : 0.000006s : 39: predicate.dict_set_item_eliminator 0.71% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 11: predicate.elim_not_effective 0.38% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.31% : 0.000007s : 50: predicate.environ_add_const_eliminate 1.25% : 0.000007s : 50: predicate.environ_get_add_eliminate 1.28% : 0.000007s : 50: predicate.environ_get_depend_swap 1.86% : 0.000011s : 72: predicate.environ_get_eliminate 1.28% : 0.000007s : 50: predicate.environ_get_set_eliminate 1.20% : 0.000007s : 46: predicate.exchange_switch_depend_value 1.99% : 0.000011s : 46: predicate.float_depend_g_call 0.52% : 0.000003s : 22: predicate.float_environ_get_switch 0.78% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 11: predicate.fold_const_symbol 0.62% : 0.000003s : 22: predicate.get_grad_eliminate 0.18% : 0.000001s : 11: predicate.graph_param_transform 0.62% : 0.000003s : 22: predicate.incorporate_call 0.58% : 0.000003s : 22: predicate.incorporate_call_switch 5.66% : 0.000032s : 151: predicate.inline 0.84% : 0.000005s : 22: predicate.inline_without_move 0.28% : 0.000002s : 22: predicate.j_node_and_user_rematch 0.80% : 0.000005s : 22: predicate.less_batch_normalization 1.70% : 0.000010s : 61: predicate.list_to_tuple_eliminator_ 2.54% : 0.000014s : 100: predicate.load_eliminater 0.74% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.78% : 0.000010s : 66: predicate.loop_unroll_before_grad 1.67% : 0.000009s : 61: predicate.make_slice_get_slice_eliminator 0.56% : 0.000003s : 22: predicate.merge_addn 0.56% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.53% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.98% : 0.000006s : 39: predicate.minmaximum_grad 0.90% : 0.000005s : 11: predicate.mutable_eliminate 0.34% : 0.000002s : 11: predicate.opt_reshape 0.39% : 0.000002s : 11: predicate.parallel_virtual_node 1.68% : 0.000010s : 46: predicate.partial_defer_inline 1.43% : 0.000008s : 50: predicate.partial_eliminate 0.99% : 0.000006s : 39: predicate.print_const_string_wrapper 3.18% : 0.000018s : 22: predicate.reduce_all_const_elim 1.33% : 0.000008s : 39: predicate.reduce_eliminate 2.54% : 0.000014s : 100: predicate.redundant_stop_gradient_eliminater 0.43% : 0.000002s : 22: predicate.remove_not_recompute_node 1.13% : 0.000006s : 61: predicate.replace_applicator 0.41% : 0.000002s : 22: predicate.replace_old_param 0.25% : 0.000001s : 11: predicate.reset_defer_inline 1.13% : 0.000006s : 39: predicate.reshape_eliminate 0.61% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.33% : 0.000002s : 11: predicate.row_tensor_eliminate 0.70% : 0.000004s : 22: predicate.same_eliminate 0.50% : 0.000003s : 30: predicate.set_cell_output_no_recompute 0.72% : 0.000004s : 22: predicate.shard_identity_eliminate 0.67% : 0.000004s : 22: predicate.special_op_eliminate 0.73% : 0.000004s : 22: predicate.specialize_transform 0.77% : 0.000004s : 22: predicate.split_environ_get_set_with_tuple_value 0.65% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.34% : 0.000002s : 11: predicate.switch_call_monad_eliminater 1.23% : 0.000007s : 46: predicate.switch_defer_inline 1.83% : 0.000010s : 68: predicate.switch_layer_defer_inline 4.11% : 0.000023s : 145: predicate.switch_simplify 1.04% : 0.000006s : 39: predicate.tile_eliminate 0.99% : 0.000006s : 39: predicate.transpose_eliminate 1.69% : 0.000010s : 61: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000010s : 61: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000009s : 61: predicate.tuple_list_get_item_depend_reorder 2.68% : 0.000015s : 83: predicate.tuple_list_get_item_eliminator 1.79% : 0.000010s : 61: predicate.tuple_list_get_set_item_eliminator 2.38% : 0.000013s : 83: predicate.tuple_list_set_item_eliminator 1.60% : 0.000009s : 61: predicate.tuple_to_list_eliminator_ 2.79% : 0.000016s : 100: predicate.updatestate_pure_node_eliminater 3.65% : 0.000021s : 122: predicate.updatestate_useless_node_eliminater 0.39% : 0.000002s : 11: predicate.value_based_eliminate 0.85% : 0.000005s : 22: predicate.virtual_dataset_eliminate 0.59% : 0.000003s : 22: predicate.virtual_output_eliminate 0.29% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.37% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000858 10 2.77% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 97.23% : 0.000834s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.354625 192 0.00% : 0.000005s : 1: ForceFp32Comm 1.21% : 0.004292s : 1: add_attr 1.21% : 0.004277s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000123s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.10% : 0.000345s : 1: auto_monad 0.02% : 0.000056s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.15% : 0.000533s : 1: bootstrap 0.01% : 0.000040s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000032s : 1: control_data_broadcast_order 0.01% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000047s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000013s : 1: environ_conv 0.01% : 0.000033s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 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% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.14% : 0.000505s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.22% : 0.000776s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000031s : 1: opt.transform.mutable_eliminate 0.97% : 0.003427s : 78: opt.transform.opt_a 0.03% : 0.000105s : 1: opt.transform.opt_after_cconv 0.02% : 0.000054s : 1: opt.transform.opt_after_jit_grad 0.10% : 0.000357s : 28: opt.transform.opt_b 0.03% : 0.000124s : 2: opt.transform.opt_trans_graph 0.02% : 0.000088s : 4: opt.transform.symbol_engine_opt 2.01% : 0.007134s : 1: opt_a 0.06% : 0.000230s : 1: opt_after_cconv 0.16% : 0.000572s : 1: opt_after_jit_grad 0.16% : 0.000550s : 1: opt_b 2.99% : 0.010609s : 1: optimize 0.01% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.01% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000006s : 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 0.02% : 0.000067s : 1: pre_auto_parallel 0.02% : 0.000065s : 1: py_interpret_to_execute 0.01% : 0.000027s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000061s : 1: remove_dup_value 0.29% : 0.001042s : 1: renormalize.infer 0.29% : 0.001040s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000187s : 1: rewriter_after_opt_a 0.05% : 0.000166s : 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% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000143s : 1: symbol_engine_optimizer 0.04% : 0.000157s : 1: tuple_transform 89.37% : 0.316921s : 1: type_inference [WARNING] ME(155445:281473409142576,MainProcess):2026-01-29-17:37:51.857.481 [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 = 0.691225, [21] [bootstrap]: 0.00052655 [type_inference]: 0.509659 [event_method]: 0.00025771 [auto_monad]: 0.00053456 [graph_reusing]: 8.99998e-06 [inline]: 3.05998e-06 [add_attr]: 0.0366459, [1] [add_attr_with_inline]: 0.0366307, [1] [Cycle 1]: 0.00011621, [2] [tag_attr]: 5.359e-05 [meta_addattr_fg_expand]: 1.227e-05 [parallel-infer-symbol]: 4.26001e-06 [pre_auto_parallel]: 7.546e-05 [insert-virtual-dataset]: 2.89999e-06 [parallel-infer-symbol-second]: 1.77999e-06 [dataset_repeat_opt]: 2.55002e-06 [pipeline_split]: 1.66002e-06 [optimize]: 0.142191, [53] [py_interpret_to_execute]: 7.446e-05 [rewriter_before_opt_a]: 0.00018468 [opt_a]: 0.0827225, [2] [Cycle 1]: 0.0809379, [45] [expand_dump_flag]: 6.23e-06 [switch_simplify]: 8.818e-05 [loop_unroll]: 7.325e-05 [a_1]: 0.00225798 [with_stream_mark]: 5.088e-05 [recompute_prepare]: 4.64e-05 [updatestate_depend_eliminate]: 0.0001781 [updatestate_assign_eliminate]: 1.658e-05 [updatestate_loads_eliminate]: 2.017e-05 [parameter_eliminate]: 4.22998e-06 [a_2]: 0.00033981 [accelerated_algorithm]: 5.742e-05 [shard]: 2.78e-06 [meta_shard_fg_expand]: 8.67e-06 [shard_inline]: 2.151e-05 [merge_send_recv]: 1.91e-05 [auto_parallel]: 2.081e-05 [parallel]: 2.552e-05 [flash_sp]: 1.735e-05 [merge_comm]: 1.429e-05 [allreduce_fusion]: 1.277e-05 [matmul_add_comm_reduction]: 2.169e-05 [allreduce_slice_to_reducescatter]: 1.17999e-06 [virtual_shard_identity]: 2.496e-05 [virtual_dataset]: 2.3e-05 [get_grad_eliminate_]: 2.451e-05 [virtual_output]: 2.244e-05 [merge_forward]: 1.201e-05 [cell_reuse_recompute_pass]: 3.12002e-06 [offload_activation]: 2.408e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.137e-05 [merge_recompute_call_nodes]: 1.82999e-06 [before_grad]: 3.788e-05 [set_forward_comm_id_for_comm_node_pass]: 1.502e-05 [meta_fg_expand]: 1.019e-05 [flash_sp_send_recv_attached]: 6.51e-06 [receive_attached]: 2.40002e-06 [after_resolve]: 3.021e-05 [a_after_grad]: 3.66e-05 [renormalize]: 0.0764823 [add_forward_monad_depend]: 1.29e-05 [auto_monad_grad]: 2.81999e-06 [auto_monad_eliminator]: 4.466e-05 [cse]: 0.00018833 [a_3]: 0.00015281 [Cycle 2]: 0.00176787, [45] [expand_dump_flag]: 1.91e-06 [switch_simplify]: 2.168e-05 [loop_unroll]: 1.801e-05 [a_1]: 0.00053872 [with_stream_mark]: 2.661e-05 [recompute_prepare]: 1.922e-05 [updatestate_depend_eliminate]: 1.256e-05 [updatestate_assign_eliminate]: 1.369e-05 [updatestate_loads_eliminate]: 1.776e-05 [parameter_eliminate]: 2.44001e-06 [a_2]: 0.00026977 [accelerated_algorithm]: 2.567e-05 [shard]: 2.21e-06 [meta_shard_fg_expand]: 4.87e-06 [shard_inline]: 1.873e-05 [merge_send_recv]: 1.824e-05 [auto_parallel]: 1.699e-05 [parallel]: 9.77001e-06 [flash_sp]: 4.50999e-06 [merge_comm]: 1.168e-05 [allreduce_fusion]: 1.13e-05 [matmul_add_comm_reduction]: 2.013e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 1.947e-05 [virtual_dataset]: 1.763e-05 [get_grad_eliminate_]: 1.701e-05 [virtual_output]: 1.737e-05 [merge_forward]: 1.119e-05 [cell_reuse_recompute_pass]: 2.93e-06 [offload_activation]: 2.035e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.682e-05 [merge_recompute_call_nodes]: 1.42e-06 [before_grad]: 3.142e-05 [set_forward_comm_id_for_comm_node_pass]: 1.196e-05 [meta_fg_expand]: 7.75998e-06 [flash_sp_send_recv_attached]: 1.87999e-06 [receive_attached]: 2.59001e-06 [after_resolve]: 2.519e-05 [a_after_grad]: 3.335e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.05002e-06 [auto_monad_grad]: 1.69998e-06 [auto_monad_eliminator]: 2.582e-05 [cse]: 5.207e-05 [a_3]: 0.0001193 [py_interpret_to_execute_after_opt_a]: 2.943e-05 [slice_cell_reuse_recomputed_activation]: 2.12999e-06 [rewriter_after_opt_a]: 0.000262 [convert_after_rewriter]: 1.806e-05 [order_py_execute_after_rewriter]: 1.25e-05 [mutable_eliminate]: 0.0392399 [opt_b]: 0.00080796, [1] [Cycle 1]: 0.0007954, [7] [b_1]: 0.00054816 [b_2]: 2.458e-05 [updatestate_depend_eliminate]: 2.429e-05 [updatestate_assign_eliminate]: 1.403e-05 [updatestate_loads_eliminate]: 1.825e-05 [renormalize]: 9.10019e-07 [cse]: 0.00011423 [optimize_parallel_all_gather_comm]: 4.454e-05 [overlap_param_gather]: 3.24001e-06 [cconv]: 4.117e-05 [loop_unroll]: 0.0006323 [opt_after_cconv]: 0.00033834, [1] [Cycle 1]: 0.00033006, [7] [c_1]: 0.00017203 [parameter_eliminate]: 6.50002e-06 [updatestate_depend_eliminate]: 1.783e-05 [updatestate_assign_eliminate]: 1.143e-05 [updatestate_loads_eliminate]: 1.443e-05 [cse]: 6.683e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 8.378e-05 [tuple_transform]: 0.00020475, [1] [Cycle 1]: 0.00019901, [4] [d_1]: 0.00015283 [none_parameter_eliminate]: 2.16e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 2.309e-05 [partial_unused_args_eliminate]: 2.17999e-06 [add_recomputation]: 0.00015934 [cse_after_recomputation]: 6.098e-05, [1] [Cycle 1]: 5.17e-05, [1] [cse]: 4.426e-05 [environ_conv]: 1.79e-05 [swap_dp_allreduce_reducescatter]: 1.476e-05 [bias_add_comm_swap]: 3.53e-06 [label_micro_interleaved_index]: 6.71e-06 [label_fine_grained_interleaved_index]: 3.04001e-06 [merge_cast_opt]: 1.91e-06 [slice_recompute_activation]: 2.36e-06 [micro_interleaved_order_control]: 2.78998e-06 [assign_add_opt]: 1.35999e-06 [ForceFp32Comm]: 8.60018e-07 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 0.0164043 [reorder_send_recv_between_fp_bp]: 1.116e-05 [comm_op_add_attrs]: 1.69998e-06 [add_comm_op_reuse_tag]: 1.17999e-06 [interleave_split_concat_branches]: 1.77001e-06 [interleave_parallel_branches]: 1.19e-06 [overlap_opt_shard_in_pipeline]: 1.55999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.74e-06 [control_data_broadcast_order]: 7.406e-05 [grouped_pairwise_exchange_alltoall]: 2.22999e-06 [offloading_packed_experts]: 1.043e-05 [overlap_recompute_and_grad_model_parallel]: 1.33e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.25001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.04e-06 [overlap_grad_ring_attention]: 8.97e-06 [overlap_grad_flash_sp]: 6.169e-05 [begin_end_overlap_inline]: 5.49975e-07 [split_matmul_comm_elemetwise]: 2.26998e-06 [split_layernorm_comm]: 2.00002e-06 [handle_group_info]: 9.5999e-07 [symbol_engine_optimizer]: 0.00024066, [1] [Cycle 1]: 0.00022862, [6] [build]: 2.866e-05 [elim_shapecalc]: 4.969e-05 [elim_not_effective]: 4.742e-05 [opt_reshape]: 2.01e-05 [fold_const_symbol]: 3.397e-05 [renormalize]: 2.69996e-07 [detach_backward]: 3.2e-06 [pipeline_parallel_scheduler]: 1.45001e-06 [auto_monad_reorder]: 0.00010954 [get_jit_bprop_graph]: 2.16e-06 [rewriter_after_jit_bprop_graph]: 9.44e-06 [opt_after_jit_grad]: 0.0008734 [validate]: 9.096e-05 Sums bootstrap : 0.000527s : 0.08% type_inference : 0.509659s : 78.03% event_method : 0.000258s : 0.04% auto_monad : 0.000535s : 0.08% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000054s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000012s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000075s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000074s : 0.01% optimize.rewriter_before_opt_a : 0.000185s : 0.03% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000110s : 0.02% optimize.opt_a.loop_unroll : 0.000091s : 0.01% optimize.opt_a.a_1 : 0.002797s : 0.43% optimize.opt_a.with_stream_mark : 0.000077s : 0.01% optimize.opt_a.recompute_prepare : 0.000066s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000191s : 0.03% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000038s : 0.01% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.000610s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000083s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000014s : 0.00% optimize.opt_a.shard_inline : 0.000040s : 0.01% optimize.opt_a.merge_send_recv : 0.000037s : 0.01% optimize.opt_a.auto_parallel : 0.000038s : 0.01% optimize.opt_a.parallel : 0.000035s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000026s : 0.00% optimize.opt_a.allreduce_fusion : 0.000024s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000042s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000044s : 0.01% optimize.opt_a.virtual_dataset : 0.000041s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.01% optimize.opt_a.virtual_output : 0.000040s : 0.01% optimize.opt_a.merge_forward : 0.000023s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000044s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000088s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000069s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000018s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000055s : 0.01% optimize.opt_a.a_after_grad : 0.000070s : 0.01% optimize.opt_a.renormalize : 0.076482s : 11.71% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000070s : 0.01% optimize.opt_a.cse : 0.000240s : 0.04% optimize.opt_a.a_3 : 0.000272s : 0.04% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000262s : 0.04% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000013s : 0.00% optimize.mutable_eliminate : 0.039240s : 6.01% optimize.opt_b.b_1 : 0.000548s : 0.08% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000114s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000045s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000632s : 0.10% optimize.opt_after_cconv.c_1 : 0.000172s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000067s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000084s : 0.01% optimize.tuple_transform.d_1 : 0.000153s : 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 : 0.000023s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000159s : 0.02% optimize.cse_after_recomputation.cse : 0.000044s : 0.01% optimize.environ_conv : 0.000018s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000015s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 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 : 0.016404s : 2.51% optimize.reorder_send_recv_between_fp_bp : 0.000011s : 0.00% optimize.comm_op_add_attrs : 0.000002s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000074s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.00% 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 : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000062s : 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 : 0.000029s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000050s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000047s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000020s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000034s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000110s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000873s : 0.13% validate : 0.000091s : 0.01% Time group info: ------[substitution.] 0.000912 213 1.14% : 0.000010s : 2: substitution.depend_value_elim 0.71% : 0.000006s : 13: substitution.elim_not_effective 0.49% : 0.000004s : 13: substitution.fold_const_symbol 1.46% : 0.000013s : 15: substitution.graph_param_transform 62.64% : 0.000571s : 8: substitution.inline 1.32% : 0.000012s : 26: substitution.j_node_and_user_rematch 3.10% : 0.000028s : 2: substitution.less_batch_normalization 1.12% : 0.000010s : 12: substitution.load_eliminater 2.00% : 0.000018s : 26: substitution.remove_not_recompute_node 0.74% : 0.000007s : 4: substitution.replace_old_param 6.68% : 0.000061s : 42: substitution.updatestate_pure_node_eliminater 18.60% : 0.000170s : 50: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.509548 2 99.55% : 0.507267s : 1: type_inference.infer 0.45% : 0.002281s : 1: type_inference.specialize ------[replace.] 0.000112 8 100.00% : 0.000112s : 8: replace.inline ------[match.] 0.000563 8 100.00% : 0.000563s : 8: match.inline ------[predicate.] 0.000720 4487 1.00% : 0.000007s : 50: predicate.accumulaten_eliminater 0.71% : 0.000005s : 15: predicate.ad_related_special_op_eliminate 0.58% : 0.000004s : 30: predicate.addn_check_dump 1.00% : 0.000007s : 50: predicate.addn_zero_filter 0.95% : 0.000007s : 50: predicate.adjust_all_reduce_mul_add 2.26% : 0.000016s : 80: predicate.arithmetic_simplify 0.99% : 0.000007s : 50: predicate.cast_eliminate 0.59% : 0.000004s : 30: predicate.check_bprop_eliminate 0.60% : 0.000004s : 30: predicate.compare_switch_simplify 0.16% : 0.000001s : 15: predicate.const_output_eliminate 0.63% : 0.000005s : 30: predicate.depend_value_elim 1.04% : 0.000008s : 50: predicate.dict_get_item_const_eliminator 1.11% : 0.000008s : 50: predicate.dict_get_item_eliminator 0.98% : 0.000007s : 50: predicate.dict_set_item_eliminator 0.80% : 0.000006s : 30: predicate.dumpgradient_eliminate 0.27% : 0.000002s : 15: predicate.elim_not_effective 0.48% : 0.000003s : 15: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000009s : 65: predicate.environ_add_const_eliminate 1.24% : 0.000009s : 65: predicate.environ_get_add_eliminate 1.29% : 0.000009s : 65: predicate.environ_get_depend_swap 1.91% : 0.000014s : 95: predicate.environ_get_eliminate 1.25% : 0.000009s : 65: predicate.environ_get_set_eliminate 1.13% : 0.000008s : 58: predicate.exchange_switch_depend_value 1.97% : 0.000014s : 58: predicate.float_depend_g_call 0.58% : 0.000004s : 30: predicate.float_environ_get_switch 0.90% : 0.000007s : 45: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 15: predicate.fold_const_symbol 0.64% : 0.000005s : 30: predicate.get_grad_eliminate 0.22% : 0.000002s : 15: predicate.graph_param_transform 0.70% : 0.000005s : 30: predicate.incorporate_call 0.62% : 0.000004s : 30: predicate.incorporate_call_switch 5.84% : 0.000042s : 198: predicate.inline 0.97% : 0.000007s : 30: predicate.inline_without_move 0.30% : 0.000002s : 30: predicate.j_node_and_user_rematch 0.98% : 0.000007s : 33: predicate.less_batch_normalization 1.79% : 0.000013s : 80: predicate.list_to_tuple_eliminator_ 2.59% : 0.000019s : 130: predicate.load_eliminater 0.84% : 0.000006s : 15: predicate.loop_unroll_after_grad 1.62% : 0.000012s : 83: predicate.loop_unroll_before_grad 1.66% : 0.000012s : 80: predicate.make_slice_get_slice_eliminator 0.65% : 0.000005s : 30: predicate.merge_addn 0.59% : 0.000004s : 30: predicate.micro_step_allgather_replace 0.59% : 0.000004s : 30: predicate.mini_step_allgather_replace 0.93% : 0.000007s : 50: predicate.minmaximum_grad 1.63% : 0.000012s : 15: predicate.mutable_eliminate 0.35% : 0.000002s : 15: predicate.opt_reshape 0.35% : 0.000003s : 15: predicate.parallel_virtual_node 1.72% : 0.000012s : 58: predicate.partial_defer_inline 1.52% : 0.000011s : 65: predicate.partial_eliminate 0.98% : 0.000007s : 50: predicate.print_const_string_wrapper 0.69% : 0.000005s : 30: predicate.reduce_all_const_elim 1.42% : 0.000010s : 50: predicate.reduce_eliminate 2.49% : 0.000018s : 130: predicate.redundant_stop_gradient_eliminater 0.42% : 0.000003s : 30: predicate.remove_not_recompute_node 1.10% : 0.000008s : 80: predicate.replace_applicator 0.45% : 0.000003s : 30: predicate.replace_old_param 0.25% : 0.000002s : 15: predicate.reset_defer_inline 1.00% : 0.000007s : 50: predicate.reshape_eliminate 0.66% : 0.000005s : 30: predicate.row_tensor_add_zeros_like 0.38% : 0.000003s : 15: predicate.row_tensor_eliminate 0.79% : 0.000006s : 30: predicate.same_eliminate 0.58% : 0.000004s : 42: predicate.set_cell_output_no_recompute 0.70% : 0.000005s : 30: predicate.shard_identity_eliminate 0.71% : 0.000005s : 30: predicate.special_op_eliminate 0.79% : 0.000006s : 30: predicate.specialize_transform 0.79% : 0.000006s : 30: predicate.split_environ_get_set_with_tuple_value 0.77% : 0.000006s : 30: predicate.stack_unstack_eliminate 0.37% : 0.000003s : 15: predicate.switch_call_monad_eliminater 1.18% : 0.000008s : 58: predicate.switch_defer_inline 1.84% : 0.000013s : 88: predicate.switch_layer_defer_inline 3.96% : 0.000029s : 186: predicate.switch_simplify 0.96% : 0.000007s : 50: predicate.tile_eliminate 0.95% : 0.000007s : 50: predicate.transpose_eliminate 1.76% : 0.000013s : 80: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000013s : 80: predicate.tuple_list_get_item_const_eliminator 1.74% : 0.000012s : 80: predicate.tuple_list_get_item_depend_reorder 2.75% : 0.000020s : 110: predicate.tuple_list_get_item_eliminator 1.75% : 0.000013s : 80: predicate.tuple_list_get_set_item_eliminator 2.35% : 0.000017s : 110: predicate.tuple_list_set_item_eliminator 1.75% : 0.000013s : 80: predicate.tuple_to_list_eliminator_ 2.80% : 0.000020s : 130: predicate.updatestate_pure_node_eliminater 3.68% : 0.000027s : 160: predicate.updatestate_useless_node_eliminater 0.36% : 0.000003s : 15: predicate.value_based_eliminate 0.65% : 0.000005s : 30: predicate.virtual_dataset_eliminate 0.64% : 0.000005s : 30: predicate.virtual_output_eliminate 0.31% : 0.000002s : 15: predicate.virtual_view_grad_eliminate 0.41% : 0.000003s : 15: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001266 13 17.79% : 0.000225s : 3: func_graph_cloner_run.FuncGraphClonerGraph 82.21% : 0.001041s : 10: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.951894 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.85% : 0.036653s : 1: add_attr 3.85% : 0.036636s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000165s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.06% : 0.000553s : 1: auto_monad 0.01% : 0.000115s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000010s : 1: bias_add_comm_swap 0.06% : 0.000556s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000078s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.01% : 0.000064s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000021s : 1: environ_conv 0.03% : 0.000276s : 1: event_method 1.73% : 0.016443s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 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% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.07% : 0.000645s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 4.12% : 0.039261s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000059s : 1: opt.transform.mutable_eliminate 0.46% : 0.004392s : 78: opt.transform.opt_a 0.02% : 0.000170s : 1: opt.transform.opt_after_cconv 0.01% : 0.000104s : 1: opt.transform.opt_after_jit_grad 0.06% : 0.000529s : 28: opt.transform.opt_b 0.02% : 0.000173s : 2: opt.transform.opt_trans_graph 0.01% : 0.000142s : 4: opt.transform.symbol_engine_opt 8.69% : 0.082727s : 1: opt_a 0.04% : 0.000342s : 1: opt_after_cconv 0.09% : 0.000887s : 1: opt_after_jit_grad 0.09% : 0.000813s : 1: opt_b 14.94% : 0.142199s : 1: optimize 0.01% : 0.000049s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.01% : 0.000065s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 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% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000017s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000080s : 1: pre_auto_parallel 0.01% : 0.000080s : 1: py_interpret_to_execute 0.00% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000089s : 1: remove_dup_value 7.89% : 0.075102s : 1: renormalize.infer 0.14% : 0.001358s : 1: renormalize.specialize 0.00% : 0.000019s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000269s : 1: rewriter_after_opt_a 0.02% : 0.000192s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000244s : 1: symbol_engine_optimizer 0.02% : 0.000208s : 1: tuple_transform 53.54% : 0.509690s : 1: type_inference . [hook] pytest_runtest_teardown:test_transpose_batch_matmul_transpose_mint tests/st/infer/ops/test_internal_ops/test_transpose_bmm_transpose.py::test_transpose_batch_matmul_transpose_mint,max_mem:108.0M =============================== 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 ================== 1 passed, 25 warnings in 79.14s (0:01:19) ===================