==================================================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_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 6 items test_matmul_split.py [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:37:14.375.667 [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 = 0.396457, [21] [bootstrap]: 0.0006479 [type_inference]: 0.353487 [event_method]: 0.00023511 [auto_monad]: 0.00086617 [graph_reusing]: 5.791e-05 [inline]: 3.54002e-06 [add_attr]: 0.00902645, [1] [add_attr_with_inline]: 0.00900961, [1] [Cycle 1]: 0.00034494, [2] [tag_attr]: 0.00019957 [meta_addattr_fg_expand]: 5.635e-05 [parallel-infer-symbol]: 3.86999e-06 [pre_auto_parallel]: 0.00027365 [insert-virtual-dataset]: 2.83e-06 [parallel-infer-symbol-second]: 1.30999e-06 [dataset_repeat_opt]: 2.66e-06 [pipeline_split]: 2.04999e-06 [optimize]: 0.0305366, [53] [py_interpret_to_execute]: 0.0002369 [rewriter_before_opt_a]: 0.00078736 [opt_a]: 0.0239656, [2] [Cycle 1]: 0.0218165, [45] [expand_dump_flag]: 2.87e-05 [switch_simplify]: 0.00073664 [loop_unroll]: 0.00025628 [a_1]: 0.00782029 [with_stream_mark]: 5.825e-05 [recompute_prepare]: 4.052e-05 [updatestate_depend_eliminate]: 1.99e-05 [updatestate_assign_eliminate]: 1.964e-05 [updatestate_loads_eliminate]: 1.827e-05 [parameter_eliminate]: 2.84999e-06 [a_2]: 0.00080657 [accelerated_algorithm]: 5.977e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 2.366e-05 [shard_inline]: 2.302e-05 [merge_send_recv]: 2.023e-05 [auto_parallel]: 2.046e-05 [parallel]: 4.351e-05 [flash_sp]: 1.536e-05 [merge_comm]: 1.444e-05 [allreduce_fusion]: 1.247e-05 [matmul_add_comm_reduction]: 2.119e-05 [allreduce_slice_to_reducescatter]: 5.90022e-07 [virtual_shard_identity]: 2.703e-05 [virtual_dataset]: 2.221e-05 [get_grad_eliminate_]: 2.092e-05 [virtual_output]: 2.181e-05 [merge_forward]: 1.306e-05 [cell_reuse_recompute_pass]: 2.43e-06 [offload_activation]: 2.317e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.545e-05 [merge_recompute_call_nodes]: 1.40999e-06 [before_grad]: 3.741e-05 [set_forward_comm_id_for_comm_node_pass]: 1.379e-05 [meta_fg_expand]: 1.712e-05 [flash_sp_send_recv_attached]: 5.09e-06 [receive_attached]: 1.523e-05 [after_resolve]: 2.915e-05 [a_after_grad]: 3.426e-05 [renormalize]: 0.00974846 [add_forward_monad_depend]: 1.35e-05 [auto_monad_grad]: 3.31001e-06 [auto_monad_eliminator]: 8.96e-05 [cse]: 0.00097339 [a_3]: 0.00016917 [Cycle 2]: 0.00213054, [45] [expand_dump_flag]: 2.93e-06 [switch_simplify]: 2.575e-05 [loop_unroll]: 1.995e-05 [a_1]: 0.00063007 [with_stream_mark]: 3.83e-05 [recompute_prepare]: 2.118e-05 [updatestate_depend_eliminate]: 1.662e-05 [updatestate_assign_eliminate]: 1.188e-05 [updatestate_loads_eliminate]: 1.412e-05 [parameter_eliminate]: 2.73e-06 [a_2]: 0.0003049 [accelerated_algorithm]: 3.068e-05 [shard]: 2.63e-06 [meta_shard_fg_expand]: 7.48e-06 [shard_inline]: 3.94e-05 [merge_send_recv]: 2.256e-05 [auto_parallel]: 2.111e-05 [parallel]: 1.089e-05 [flash_sp]: 4.58999e-06 [merge_comm]: 1.32e-05 [allreduce_fusion]: 1.255e-05 [matmul_add_comm_reduction]: 2.265e-05 [allreduce_slice_to_reducescatter]: 1.08001e-06 [virtual_shard_identity]: 2.4e-05 [virtual_dataset]: 2.02e-05 [get_grad_eliminate_]: 2.071e-05 [virtual_output]: 1.908e-05 [merge_forward]: 1.257e-05 [cell_reuse_recompute_pass]: 3.28e-06 [offload_activation]: 2.504e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.164e-05 [merge_recompute_call_nodes]: 1.55001e-06 [before_grad]: 3.606e-05 [set_forward_comm_id_for_comm_node_pass]: 1.442e-05 [meta_fg_expand]: 9.96998e-06 [flash_sp_send_recv_attached]: 1.96998e-06 [receive_attached]: 2.35002e-06 [after_resolve]: 2.959e-05 [a_after_grad]: 3.08e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.97002e-06 [auto_monad_grad]: 2.59001e-06 [auto_monad_eliminator]: 7.275e-05 [cse]: 9.356e-05 [a_3]: 0.00014287 [py_interpret_to_execute_after_opt_a]: 3.556e-05 [slice_cell_reuse_recomputed_activation]: 2.76e-06 [rewriter_after_opt_a]: 0.00092219 [convert_after_rewriter]: 2.879e-05 [order_py_execute_after_rewriter]: 1.534e-05 [mutable_eliminate]: 0.00084436 [opt_b]: 0.00081016, [1] [Cycle 1]: 0.00079956, [7] [b_1]: 0.00054219 [b_2]: 2.478e-05 [updatestate_depend_eliminate]: 2.173e-05 [updatestate_assign_eliminate]: 1.227e-05 [updatestate_loads_eliminate]: 1.496e-05 [renormalize]: 8.00006e-07 [cse]: 0.00013648 [optimize_parallel_all_gather_comm]: 4.256e-05 [overlap_param_gather]: 7.36001e-06 [cconv]: 4.084e-05 [loop_unroll]: 0.00067783 [opt_after_cconv]: 0.00034782, [1] [Cycle 1]: 0.00033971, [7] [c_1]: 0.00014005 [parameter_eliminate]: 5.19e-06 [updatestate_depend_eliminate]: 2.28e-05 [updatestate_assign_eliminate]: 1.578e-05 [updatestate_loads_eliminate]: 1.669e-05 [cse]: 9.795e-05 [renormalize]: 7.59988e-07 [remove_dup_value]: 0.00010284 [tuple_transform]: 0.00027433, [1] [Cycle 1]: 0.00026706, [4] [d_1]: 0.00021339 [none_parameter_eliminate]: 3.52997e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 2.509e-05 [partial_unused_args_eliminate]: 2.22999e-06 [add_recomputation]: 0.00016909 [cse_after_recomputation]: 7.785e-05, [1] [Cycle 1]: 7.168e-05, [1] [cse]: 6.367e-05 [environ_conv]: 3.865e-05 [swap_dp_allreduce_reducescatter]: 1.928e-05 [bias_add_comm_swap]: 3.13e-06 [label_micro_interleaved_index]: 7.15e-06 [label_fine_grained_interleaved_index]: 2.58e-06 [merge_cast_opt]: 1.62999e-06 [slice_recompute_activation]: 2.44999e-06 [micro_interleaved_order_control]: 2.64001e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 1.18001e-06 [remove_cast_before_assign_add]: 1.70001e-06 [full_micro_interleaved_order_control]: 2.14e-06 [reorder_send_recv_between_fp_bp]: 2.66999e-06 [comm_op_add_attrs]: 1.20001e-06 [add_comm_op_reuse_tag]: 1.10999e-06 [interleave_split_concat_branches]: 1.12999e-06 [interleave_parallel_branches]: 1.05999e-06 [overlap_opt_shard_in_pipeline]: 2.537e-05 [overlap_opt_shard_grad_in_pipeline]: 1.64998e-06 [control_data_broadcast_order]: 4.099e-05 [grouped_pairwise_exchange_alltoall]: 1.57999e-06 [offloading_packed_experts]: 1.029e-05 [overlap_recompute_and_grad_model_parallel]: 1.029e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.25999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47999e-06 [overlap_recompute_comm]: 2.61999e-06 [overlap_grad_ring_attention]: 9.62001e-06 [overlap_grad_flash_sp]: 8.026e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.52001e-06 [split_layernorm_comm]: 1.99e-06 [handle_group_info]: 1.46002e-06 [symbol_engine_optimizer]: 0.00056212, [1] [Cycle 1]: 0.00055539, [6] [build]: 0.00030971 [elim_shapecalc]: 4.132e-05 [elim_not_effective]: 6.085e-05 [opt_reshape]: 3.236e-05 [fold_const_symbol]: 5.937e-05 [renormalize]: 2.80008e-07 [detach_backward]: 2.92002e-06 [pipeline_parallel_scheduler]: 2.27001e-06 [auto_monad_reorder]: 7.306e-05 [get_jit_bprop_graph]: 1.72999e-06 [rewriter_after_jit_bprop_graph]: 6.39999e-06 [opt_after_jit_grad]: 0.00084786 [validate]: 0.00012828 Sums bootstrap : 0.000648s : 0.17% type_inference : 0.353487s : 91.52% event_method : 0.000235s : 0.06% auto_monad : 0.000866s : 0.22% graph_reusing : 0.000058s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000200s : 0.05% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000056s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000274s : 0.07% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000237s : 0.06% optimize.rewriter_before_opt_a : 0.000787s : 0.20% optimize.opt_a.expand_dump_flag : 0.000032s : 0.01% optimize.opt_a.switch_simplify : 0.000762s : 0.20% optimize.opt_a.loop_unroll : 0.000276s : 0.07% optimize.opt_a.a_1 : 0.008450s : 2.19% optimize.opt_a.with_stream_mark : 0.000097s : 0.02% optimize.opt_a.recompute_prepare : 0.000062s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000032s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000032s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001111s : 0.29% optimize.opt_a.accelerated_algorithm : 0.000090s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000031s : 0.01% optimize.opt_a.shard_inline : 0.000062s : 0.02% optimize.opt_a.merge_send_recv : 0.000043s : 0.01% optimize.opt_a.auto_parallel : 0.000042s : 0.01% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000028s : 0.01% optimize.opt_a.allreduce_fusion : 0.000025s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000044s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000051s : 0.01% optimize.opt_a.virtual_dataset : 0.000042s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.01% optimize.opt_a.virtual_output : 0.000041s : 0.01% optimize.opt_a.merge_forward : 0.000026s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000087s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000073s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.01% optimize.opt_a.meta_fg_expand : 0.000027s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000018s : 0.00% optimize.opt_a.after_resolve : 0.000059s : 0.02% optimize.opt_a.a_after_grad : 0.000065s : 0.02% optimize.opt_a.renormalize : 0.009749s : 2.52% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000162s : 0.04% optimize.opt_a.cse : 0.001067s : 0.28% optimize.opt_a.a_3 : 0.000312s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000036s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000922s : 0.24% optimize.convert_after_rewriter : 0.000029s : 0.01% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000844s : 0.22% optimize.opt_b.b_1 : 0.000542s : 0.14% optimize.opt_b.b_2 : 0.000025s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000136s : 0.04% optimize.optimize_parallel_all_gather_comm : 0.000043s : 0.01% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000678s : 0.18% optimize.opt_after_cconv.c_1 : 0.000140s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000023s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.cse : 0.000098s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000103s : 0.03% optimize.tuple_transform.d_1 : 0.000213s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000004s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000169s : 0.04% optimize.cse_after_recomputation.cse : 0.000064s : 0.02% optimize.environ_conv : 0.000039s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 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 : 0.000002s : 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 : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000025s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000041s : 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 : 0.000010s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000080s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000310s : 0.08% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000061s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000032s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000059s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000073s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000848s : 0.22% validate : 0.000128s : 0.03% Time group info: ------[substitution.] 0.002978 569 0.54% : 0.000016s : 8: substitution.depend_value_elim 0.74% : 0.000022s : 14: substitution.elim_not_effective 0.59% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.97% : 0.000029s : 14: substitution.fold_const_symbol 0.55% : 0.000016s : 17: substitution.graph_param_transform 66.81% : 0.001990s : 71: substitution.inline 0.43% : 0.000013s : 29: substitution.j_node_and_user_rematch 1.04% : 0.000031s : 6: substitution.less_batch_normalization 1.68% : 0.000050s : 2: substitution.list_to_tuple_eliminator_ 0.19% : 0.000006s : 6: substitution.load_eliminater 1.15% : 0.000034s : 21: substitution.minmaximum_grad 0.24% : 0.000007s : 2: substitution.opt_reshape 0.67% : 0.000020s : 29: substitution.remove_not_recompute_node 0.26% : 0.000008s : 4: substitution.replace_old_param 1.93% : 0.000058s : 18: substitution.reshape_eliminate 1.77% : 0.000053s : 24: substitution.switch_simplify 4.47% : 0.000133s : 51: substitution.tuple_list_convert_item_index_to_positive 2.17% : 0.000065s : 51: substitution.tuple_list_get_item_const_eliminator 2.96% : 0.000088s : 51: substitution.tuple_list_get_item_depend_reorder 6.41% : 0.000191s : 73: substitution.tuple_list_get_item_eliminator 2.87% : 0.000085s : 51: substitution.tuple_list_get_set_item_eliminator 0.92% : 0.000027s : 6: substitution.updatestate_pure_node_eliminater 0.66% : 0.000020s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.353029 2 94.74% : 0.334461s : 1: type_inference.infer 5.26% : 0.018568s : 1: type_inference.specialize ------[replace.] 0.001153 115 4.53% : 0.000052s : 5: replace.depend_value_elim 57.75% : 0.000666s : 71: replace.inline 3.44% : 0.000040s : 2: replace.list_to_tuple_eliminator_ 25.39% : 0.000293s : 24: replace.switch_simplify 8.89% : 0.000102s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002068 115 0.10% : 0.000002s : 5: match.depend_value_elim 94.20% : 0.001948s : 71: match.inline 2.26% : 0.000047s : 2: match.list_to_tuple_eliminator_ 1.94% : 0.000040s : 24: match.switch_simplify 1.49% : 0.000031s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001522 9701 1.15% : 0.000017s : 123: predicate.accumulaten_eliminater 0.38% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.51% : 0.000008s : 58: predicate.addn_check_dump 1.20% : 0.000018s : 123: predicate.addn_zero_filter 1.08% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.22% : 0.000034s : 181: predicate.arithmetic_simplify 1.19% : 0.000018s : 123: predicate.cast_eliminate 0.32% : 0.000005s : 34: predicate.check_bprop_eliminate 0.50% : 0.000008s : 58: predicate.compare_switch_simplify 0.09% : 0.000001s : 17: predicate.const_output_eliminate 0.61% : 0.000009s : 61: predicate.depend_value_elim 1.24% : 0.000019s : 123: predicate.dict_get_item_const_eliminator 1.27% : 0.000019s : 123: predicate.dict_get_item_eliminator 1.11% : 0.000017s : 123: predicate.dict_set_item_eliminator 0.42% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.13% : 0.000002s : 17: predicate.elim_not_effective 0.24% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.26% : 0.000019s : 140: predicate.environ_add_const_eliminate 1.23% : 0.000019s : 140: predicate.environ_get_add_eliminate 1.24% : 0.000019s : 140: predicate.environ_get_depend_swap 1.77% : 0.000027s : 198: predicate.environ_get_eliminate 1.31% : 0.000020s : 140: predicate.environ_get_set_eliminate 1.93% : 0.000029s : 209: predicate.exchange_switch_depend_value 2.87% : 0.000044s : 209: predicate.float_depend_g_call 0.53% : 0.000008s : 58: predicate.float_environ_get_switch 0.75% : 0.000011s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.34% : 0.000005s : 35: predicate.get_grad_eliminate 0.11% : 0.000002s : 17: predicate.graph_param_transform 0.55% : 0.000008s : 58: predicate.incorporate_call 0.49% : 0.000007s : 58: predicate.incorporate_call_switch 6.00% : 0.000091s : 459: predicate.inline 0.42% : 0.000006s : 35: predicate.inline_without_move 0.17% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.46% : 0.000007s : 36: predicate.less_batch_normalization 1.65% : 0.000025s : 172: predicate.list_to_tuple_eliminator_ 2.64% : 0.000040s : 295: predicate.load_eliminater 0.47% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.24% : 0.000049s : 314: predicate.loop_unroll_before_grad 1.61% : 0.000025s : 157: predicate.make_slice_get_slice_eliminator 0.53% : 0.000008s : 58: predicate.merge_addn 0.30% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.31% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.13% : 0.000017s : 123: predicate.minmaximum_grad 0.47% : 0.000007s : 17: predicate.mutable_eliminate 0.20% : 0.000003s : 17: predicate.opt_reshape 0.19% : 0.000003s : 17: predicate.parallel_virtual_node 3.40% : 0.000052s : 209: predicate.partial_defer_inline 1.63% : 0.000025s : 155: predicate.partial_eliminate 1.09% : 0.000017s : 123: predicate.print_const_string_wrapper 0.49% : 0.000007s : 53: predicate.reduce_all_const_elim 1.49% : 0.000023s : 123: predicate.reduce_eliminate 2.65% : 0.000040s : 295: predicate.redundant_stop_gradient_eliminater 0.16% : 0.000002s : 35: predicate.remove_not_recompute_node 1.19% : 0.000018s : 172: predicate.replace_applicator 0.23% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.26% : 0.000019s : 123: predicate.reshape_eliminate 0.32% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.19% : 0.000003s : 17: predicate.row_tensor_eliminate 0.48% : 0.000007s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.37% : 0.000006s : 35: predicate.shard_identity_eliminate 0.35% : 0.000005s : 34: predicate.special_op_eliminate 0.61% : 0.000009s : 58: predicate.specialize_transform 0.45% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.16% : 0.000033s : 209: predicate.switch_defer_inline 2.41% : 0.000037s : 243: predicate.switch_layer_defer_inline 6.88% : 0.000105s : 646: predicate.switch_simplify 1.14% : 0.000017s : 123: predicate.tile_eliminate 1.17% : 0.000018s : 123: predicate.transpose_eliminate 1.82% : 0.000028s : 157: predicate.tuple_list_convert_item_index_to_positive 1.85% : 0.000028s : 157: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000026s : 157: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000048s : 228: predicate.tuple_list_get_item_eliminator 1.66% : 0.000025s : 157: predicate.tuple_list_get_set_item_eliminator 2.27% : 0.000035s : 215: predicate.tuple_list_set_item_eliminator 1.59% : 0.000024s : 170: predicate.tuple_to_list_eliminator_ 2.63% : 0.000040s : 295: predicate.updatestate_pure_node_eliminater 3.24% : 0.000049s : 353: predicate.updatestate_useless_node_eliminater 0.18% : 0.000003s : 17: predicate.value_based_eliminate 0.37% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.34% : 0.000005s : 35: predicate.virtual_output_eliminate 0.16% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.20% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.013206 133 61.36% : 0.008103s : 53: func_graph_cloner_run.FuncGraphClonerGraph 38.64% : 0.005103s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.458191 209 0.00% : 0.000004s : 1: ForceFp32Comm 1.97% : 0.009033s : 1: add_attr 1.97% : 0.009014s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000175s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.19% : 0.000889s : 1: auto_monad 0.02% : 0.000080s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.15% : 0.000689s : 1: bootstrap 0.01% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000045s : 1: control_data_broadcast_order 0.01% : 0.000035s : 1: convert_after_rewriter 0.02% : 0.000081s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000044s : 1: environ_conv 0.05% : 0.000249s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000065s : 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% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.15% : 0.000690s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.19% : 0.000856s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.01% : 0.000041s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000048s : 1: opt.transform.mutable_eliminate 2.50% : 0.011437s : 95: opt.transform.opt_a 0.03% : 0.000139s : 1: opt.transform.opt_after_cconv 0.02% : 0.000078s : 1: opt.transform.opt_after_jit_grad 0.12% : 0.000533s : 28: opt.transform.opt_b 0.05% : 0.000234s : 2: opt.transform.opt_trans_graph 0.04% : 0.000187s : 4: opt.transform.symbol_engine_opt 5.23% : 0.023971s : 1: opt_a 0.08% : 0.000352s : 1: opt_after_cconv 0.19% : 0.000860s : 1: opt_after_jit_grad 0.18% : 0.000815s : 1: opt_b 6.67% : 0.030543s : 1: optimize 0.01% : 0.000048s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.02% : 0.000085s : 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% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000030s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.06% : 0.000283s : 1: pre_auto_parallel 0.05% : 0.000247s : 1: py_interpret_to_execute 0.01% : 0.000039s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000110s : 1: remove_dup_value 1.14% : 0.005213s : 1: renormalize.infer 0.99% : 0.004518s : 1: renormalize.specialize 0.00% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.20% : 0.000935s : 1: rewriter_after_opt_a 0.17% : 0.000801s : 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 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.12% : 0.000566s : 1: symbol_engine_optimizer 0.06% : 0.000277s : 1: tuple_transform 77.16% : 0.353526s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape0-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape0-1],max_mem:272.0M [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:37:46.794.434 [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 = 0.350332, [21] [bootstrap]: 0.00075621 [type_inference]: 0.306089 [event_method]: 0.00021439 [auto_monad]: 0.00072657 [graph_reusing]: 4.616e-05 [inline]: 4.90999e-06 [add_attr]: 0.00551627, [1] [add_attr_with_inline]: 0.00549934, [1] [Cycle 1]: 0.0003255, [2] [tag_attr]: 0.00020925 [meta_addattr_fg_expand]: 5.998e-05 [parallel-infer-symbol]: 3.65e-06 [pre_auto_parallel]: 0.00025043 [insert-virtual-dataset]: 2.66e-06 [parallel-infer-symbol-second]: 9.50007e-07 [dataset_repeat_opt]: 2.29001e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.0352098, [53] [py_interpret_to_execute]: 0.0002613 [rewriter_before_opt_a]: 0.00079259 [opt_a]: 0.0281342, [2] [Cycle 1]: 0.025852, [45] [expand_dump_flag]: 3.493e-05 [switch_simplify]: 0.00072511 [loop_unroll]: 0.00026183 [a_1]: 0.00795511 [with_stream_mark]: 7.193e-05 [recompute_prepare]: 4.678e-05 [updatestate_depend_eliminate]: 2.166e-05 [updatestate_assign_eliminate]: 1.781e-05 [updatestate_loads_eliminate]: 1.918e-05 [parameter_eliminate]: 3.15998e-06 [a_2]: 0.00081519 [accelerated_algorithm]: 0.00011226 [shard]: 2.53e-06 [meta_shard_fg_expand]: 3.745e-05 [shard_inline]: 2.866e-05 [merge_send_recv]: 2.146e-05 [auto_parallel]: 2.324e-05 [parallel]: 4.002e-05 [flash_sp]: 1.654e-05 [merge_comm]: 1.699e-05 [allreduce_fusion]: 1.288e-05 [matmul_add_comm_reduction]: 2.387e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 3.012e-05 [virtual_dataset]: 2.163e-05 [get_grad_eliminate_]: 2.149e-05 [virtual_output]: 2.239e-05 [merge_forward]: 1.287e-05 [cell_reuse_recompute_pass]: 2.69001e-06 [offload_activation]: 2.466e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.877e-05 [merge_recompute_call_nodes]: 1.47001e-06 [before_grad]: 4.025e-05 [set_forward_comm_id_for_comm_node_pass]: 1.408e-05 [meta_fg_expand]: 1.986e-05 [flash_sp_send_recv_attached]: 6.61e-06 [receive_attached]: 2.06e-06 [after_resolve]: 2.864e-05 [a_after_grad]: 3.645e-05 [renormalize]: 0.012752 [add_forward_monad_depend]: 1.381e-05 [auto_monad_grad]: 3.80998e-06 [auto_monad_eliminator]: 9.075e-05 [cse]: 0.00169717 [a_3]: 0.0001816 [Cycle 2]: 0.00223875, [45] [expand_dump_flag]: 3.36999e-06 [switch_simplify]: 2.751e-05 [loop_unroll]: 2.141e-05 [a_1]: 0.00071511 [with_stream_mark]: 4.416e-05 [recompute_prepare]: 2.426e-05 [updatestate_depend_eliminate]: 1.454e-05 [updatestate_assign_eliminate]: 1.469e-05 [updatestate_loads_eliminate]: 1.421e-05 [parameter_eliminate]: 2.56e-06 [a_2]: 0.00031557 [accelerated_algorithm]: 3.438e-05 [shard]: 2.40002e-06 [meta_shard_fg_expand]: 1.072e-05 [shard_inline]: 2.131e-05 [merge_send_recv]: 2.064e-05 [auto_parallel]: 2.022e-05 [parallel]: 1.044e-05 [flash_sp]: 4.50001e-06 [merge_comm]: 1.265e-05 [allreduce_fusion]: 1.256e-05 [matmul_add_comm_reduction]: 2.487e-05 [allreduce_slice_to_reducescatter]: 1.24e-06 [virtual_shard_identity]: 2.356e-05 [virtual_dataset]: 2.081e-05 [get_grad_eliminate_]: 2.078e-05 [virtual_output]: 1.933e-05 [merge_forward]: 1.32e-05 [cell_reuse_recompute_pass]: 3.52002e-06 [offload_activation]: 2.323e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.159e-05 [merge_recompute_call_nodes]: 1.39e-06 [before_grad]: 3.664e-05 [set_forward_comm_id_for_comm_node_pass]: 1.363e-05 [meta_fg_expand]: 9.89001e-06 [flash_sp_send_recv_attached]: 2.26e-06 [receive_attached]: 2.31e-06 [after_resolve]: 2.935e-05 [a_after_grad]: 3.298e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.52e-06 [auto_monad_grad]: 2.48e-06 [auto_monad_eliminator]: 7.459e-05 [cse]: 9.013e-05 [a_3]: 0.00014262 [py_interpret_to_execute_after_opt_a]: 3.725e-05 [slice_cell_reuse_recomputed_activation]: 2.07999e-06 [rewriter_after_opt_a]: 0.00091424 [convert_after_rewriter]: 3.215e-05 [order_py_execute_after_rewriter]: 1.593e-05 [mutable_eliminate]: 0.00090619 [opt_b]: 0.00088225, [1] [Cycle 1]: 0.00087225, [7] [b_1]: 0.00062905 [b_2]: 2.703e-05 [updatestate_depend_eliminate]: 2.327e-05 [updatestate_assign_eliminate]: 1.254e-05 [updatestate_loads_eliminate]: 1.602e-05 [renormalize]: 6.89994e-07 [cse]: 0.00011183 [optimize_parallel_all_gather_comm]: 5.28e-05 [overlap_param_gather]: 2.84999e-06 [cconv]: 4.566e-05 [loop_unroll]: 0.00086877 [opt_after_cconv]: 0.0003881, [1] [Cycle 1]: 0.00037619, [7] [c_1]: 0.00015592 [parameter_eliminate]: 7.26999e-06 [updatestate_depend_eliminate]: 2.482e-05 [updatestate_assign_eliminate]: 1.274e-05 [updatestate_loads_eliminate]: 1.537e-05 [cse]: 0.00010881 [renormalize]: 1.01002e-06 [remove_dup_value]: 0.00011772 [tuple_transform]: 0.00030473, [1] [Cycle 1]: 0.00029753, [4] [d_1]: 0.00023956 [none_parameter_eliminate]: 2.68e-06 [renormalize]: 2.40019e-07 [switch_simplify]: 2.71e-05 [partial_unused_args_eliminate]: 2.37999e-06 [add_recomputation]: 0.00019494 [cse_after_recomputation]: 8.622e-05, [1] [Cycle 1]: 7.929e-05, [1] [cse]: 7.019e-05 [environ_conv]: 3.335e-05 [swap_dp_allreduce_reducescatter]: 2.004e-05 [bias_add_comm_swap]: 3.55998e-06 [label_micro_interleaved_index]: 8.47e-06 [label_fine_grained_interleaved_index]: 2.88003e-06 [merge_cast_opt]: 2.05002e-06 [slice_recompute_activation]: 2.20002e-06 [micro_interleaved_order_control]: 3.45998e-06 [assign_add_opt]: 1.87999e-06 [ForceFp32Comm]: 1.03001e-06 [remove_cast_before_assign_add]: 1.47001e-06 [full_micro_interleaved_order_control]: 2.38998e-06 [reorder_send_recv_between_fp_bp]: 2.80002e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.67001e-06 [interleave_split_concat_branches]: 1.29998e-06 [interleave_parallel_branches]: 1.37999e-06 [overlap_opt_shard_in_pipeline]: 3.23e-06 [overlap_opt_shard_grad_in_pipeline]: 2.11998e-06 [control_data_broadcast_order]: 4.507e-05 [grouped_pairwise_exchange_alltoall]: 1.64e-06 [offloading_packed_experts]: 1.176e-05 [overlap_recompute_and_grad_model_parallel]: 1.137e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.29e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49998e-06 [overlap_recompute_comm]: 2.41e-06 [overlap_grad_ring_attention]: 1.18e-05 [overlap_grad_flash_sp]: 5.942e-05 [begin_end_overlap_inline]: 8.39995e-07 [split_matmul_comm_elemetwise]: 2.84999e-06 [split_layernorm_comm]: 2.01e-06 [handle_group_info]: 1.12999e-06 [symbol_engine_optimizer]: 0.00057907, [1] [Cycle 1]: 0.00057148, [6] [build]: 0.00032285 [elim_shapecalc]: 3.981e-05 [elim_not_effective]: 5.624e-05 [opt_reshape]: 3.474e-05 [fold_const_symbol]: 6.223e-05 [renormalize]: 3.09985e-07 [detach_backward]: 4.12e-06 [pipeline_parallel_scheduler]: 1.47999e-06 [auto_monad_reorder]: 9.69e-05 [get_jit_bprop_graph]: 2.41e-06 [rewriter_after_jit_bprop_graph]: 6.81999e-06 [opt_after_jit_grad]: 0.00099198 [validate]: 0.00014505 Sums bootstrap : 0.000756s : 0.22% type_inference : 0.306089s : 89.11% event_method : 0.000214s : 0.06% auto_monad : 0.000727s : 0.21% graph_reusing : 0.000046s : 0.01% inline : 0.000005s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000209s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000060s : 0.02% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000250s : 0.07% 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 : 0.000261s : 0.08% optimize.rewriter_before_opt_a : 0.000793s : 0.23% optimize.opt_a.expand_dump_flag : 0.000038s : 0.01% optimize.opt_a.switch_simplify : 0.000753s : 0.22% optimize.opt_a.loop_unroll : 0.000283s : 0.08% optimize.opt_a.a_1 : 0.008670s : 2.52% optimize.opt_a.with_stream_mark : 0.000116s : 0.03% optimize.opt_a.recompute_prepare : 0.000071s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000036s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000033s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000033s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001131s : 0.33% optimize.opt_a.accelerated_algorithm : 0.000147s : 0.04% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000048s : 0.01% optimize.opt_a.shard_inline : 0.000050s : 0.01% optimize.opt_a.merge_send_recv : 0.000042s : 0.01% optimize.opt_a.auto_parallel : 0.000043s : 0.01% optimize.opt_a.parallel : 0.000050s : 0.01% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000030s : 0.01% optimize.opt_a.allreduce_fusion : 0.000025s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000049s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000054s : 0.02% optimize.opt_a.virtual_dataset : 0.000042s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.01% optimize.opt_a.virtual_output : 0.000042s : 0.01% optimize.opt_a.merge_forward : 0.000026s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000090s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000077s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.01% optimize.opt_a.meta_fg_expand : 0.000030s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000058s : 0.02% optimize.opt_a.a_after_grad : 0.000069s : 0.02% optimize.opt_a.renormalize : 0.012752s : 3.71% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000165s : 0.05% optimize.opt_a.cse : 0.001787s : 0.52% optimize.opt_a.a_3 : 0.000324s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000914s : 0.27% optimize.convert_after_rewriter : 0.000032s : 0.01% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.000906s : 0.26% optimize.opt_b.b_1 : 0.000629s : 0.18% optimize.opt_b.b_2 : 0.000027s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000112s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000053s : 0.02% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000046s : 0.01% optimize.loop_unroll : 0.000869s : 0.25% optimize.opt_after_cconv.c_1 : 0.000156s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000025s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.cse : 0.000109s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000118s : 0.03% optimize.tuple_transform.d_1 : 0.000240s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000027s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000195s : 0.06% optimize.cse_after_recomputation.cse : 0.000070s : 0.02% optimize.environ_conv : 0.000033s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000002s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000045s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 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 : 0.000012s : 0.00% optimize.overlap_grad_flash_sp : 0.000059s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000323s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000056s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000035s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000062s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000097s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000992s : 0.29% validate : 0.000145s : 0.04% Time group info: ------[substitution.] 0.003043 569 0.58% : 0.000018s : 8: substitution.depend_value_elim 0.54% : 0.000017s : 14: substitution.elim_not_effective 0.64% : 0.000019s : 12: substitution.float_tuple_getitem_switch 0.95% : 0.000029s : 14: substitution.fold_const_symbol 0.57% : 0.000017s : 17: substitution.graph_param_transform 66.22% : 0.002015s : 71: substitution.inline 0.49% : 0.000015s : 29: substitution.j_node_and_user_rematch 1.34% : 0.000041s : 6: substitution.less_batch_normalization 2.01% : 0.000061s : 2: substitution.list_to_tuple_eliminator_ 0.24% : 0.000007s : 6: substitution.load_eliminater 1.07% : 0.000033s : 21: substitution.minmaximum_grad 0.24% : 0.000007s : 2: substitution.opt_reshape 0.66% : 0.000020s : 29: substitution.remove_not_recompute_node 0.29% : 0.000009s : 4: substitution.replace_old_param 1.61% : 0.000049s : 18: substitution.reshape_eliminate 1.55% : 0.000047s : 24: substitution.switch_simplify 4.95% : 0.000151s : 51: substitution.tuple_list_convert_item_index_to_positive 2.10% : 0.000064s : 51: substitution.tuple_list_get_item_const_eliminator 2.98% : 0.000091s : 51: substitution.tuple_list_get_item_depend_reorder 6.34% : 0.000193s : 73: substitution.tuple_list_get_item_eliminator 2.90% : 0.000088s : 51: substitution.tuple_list_get_set_item_eliminator 0.94% : 0.000029s : 6: substitution.updatestate_pure_node_eliminater 0.79% : 0.000024s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.305690 2 93.07% : 0.284518s : 1: type_inference.infer 6.93% : 0.021171s : 1: type_inference.specialize ------[replace.] 0.001145 115 5.09% : 0.000058s : 5: replace.depend_value_elim 57.08% : 0.000653s : 71: replace.inline 3.92% : 0.000045s : 2: replace.list_to_tuple_eliminator_ 24.77% : 0.000284s : 24: replace.switch_simplify 9.15% : 0.000105s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002104 115 0.11% : 0.000002s : 5: match.depend_value_elim 93.86% : 0.001975s : 71: match.inline 2.78% : 0.000058s : 2: match.list_to_tuple_eliminator_ 1.81% : 0.000038s : 24: match.switch_simplify 1.45% : 0.000030s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001587 9701 1.10% : 0.000017s : 123: predicate.accumulaten_eliminater 0.44% : 0.000007s : 17: predicate.ad_related_special_op_eliminate 0.51% : 0.000008s : 58: predicate.addn_check_dump 1.23% : 0.000020s : 123: predicate.addn_zero_filter 1.08% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.25% : 0.000036s : 181: predicate.arithmetic_simplify 1.13% : 0.000018s : 123: predicate.cast_eliminate 0.32% : 0.000005s : 34: predicate.check_bprop_eliminate 0.50% : 0.000008s : 58: predicate.compare_switch_simplify 0.09% : 0.000001s : 17: predicate.const_output_eliminate 0.62% : 0.000010s : 61: predicate.depend_value_elim 1.21% : 0.000019s : 123: predicate.dict_get_item_const_eliminator 1.28% : 0.000020s : 123: predicate.dict_get_item_eliminator 1.09% : 0.000017s : 123: predicate.dict_set_item_eliminator 0.50% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.21% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.25% : 0.000020s : 140: predicate.environ_add_const_eliminate 1.23% : 0.000020s : 140: predicate.environ_get_add_eliminate 1.20% : 0.000019s : 140: predicate.environ_get_depend_swap 1.77% : 0.000028s : 198: predicate.environ_get_eliminate 1.21% : 0.000019s : 140: predicate.environ_get_set_eliminate 1.88% : 0.000030s : 209: predicate.exchange_switch_depend_value 2.65% : 0.000042s : 209: predicate.float_depend_g_call 0.50% : 0.000008s : 58: predicate.float_environ_get_switch 0.76% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.10% : 0.000002s : 17: predicate.fold_const_symbol 0.38% : 0.000006s : 35: predicate.get_grad_eliminate 0.12% : 0.000002s : 17: predicate.graph_param_transform 0.52% : 0.000008s : 58: predicate.incorporate_call 0.47% : 0.000007s : 58: predicate.incorporate_call_switch 5.93% : 0.000094s : 459: predicate.inline 0.44% : 0.000007s : 35: predicate.inline_without_move 0.16% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.54% : 0.000009s : 36: predicate.less_batch_normalization 1.71% : 0.000027s : 172: predicate.list_to_tuple_eliminator_ 2.60% : 0.000041s : 295: predicate.load_eliminater 0.67% : 0.000011s : 17: predicate.loop_unroll_after_grad 3.33% : 0.000053s : 314: predicate.loop_unroll_before_grad 1.60% : 0.000025s : 157: predicate.make_slice_get_slice_eliminator 0.55% : 0.000009s : 58: predicate.merge_addn 0.30% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.30% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.13% : 0.000018s : 123: predicate.minmaximum_grad 0.44% : 0.000007s : 17: predicate.mutable_eliminate 0.18% : 0.000003s : 17: predicate.opt_reshape 0.21% : 0.000003s : 17: predicate.parallel_virtual_node 3.37% : 0.000053s : 209: predicate.partial_defer_inline 1.55% : 0.000025s : 155: predicate.partial_eliminate 1.15% : 0.000018s : 123: predicate.print_const_string_wrapper 0.47% : 0.000008s : 53: predicate.reduce_all_const_elim 1.45% : 0.000023s : 123: predicate.reduce_eliminate 2.56% : 0.000041s : 295: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 35: predicate.remove_not_recompute_node 1.10% : 0.000018s : 172: predicate.replace_applicator 0.20% : 0.000003s : 35: predicate.replace_old_param 0.11% : 0.000002s : 17: predicate.reset_defer_inline 1.31% : 0.000021s : 123: predicate.reshape_eliminate 0.33% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.22% : 0.000003s : 17: predicate.row_tensor_eliminate 0.55% : 0.000009s : 34: predicate.same_eliminate 0.24% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.39% : 0.000006s : 35: predicate.shard_identity_eliminate 0.44% : 0.000007s : 34: predicate.special_op_eliminate 0.63% : 0.000010s : 58: predicate.specialize_transform 0.41% : 0.000006s : 34: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.19% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.17% : 0.000034s : 209: predicate.switch_defer_inline 2.37% : 0.000038s : 243: predicate.switch_layer_defer_inline 6.89% : 0.000109s : 646: predicate.switch_simplify 1.23% : 0.000020s : 123: predicate.tile_eliminate 1.17% : 0.000019s : 123: predicate.transpose_eliminate 1.76% : 0.000028s : 157: predicate.tuple_list_convert_item_index_to_positive 1.79% : 0.000028s : 157: predicate.tuple_list_get_item_const_eliminator 1.76% : 0.000028s : 157: predicate.tuple_list_get_item_depend_reorder 3.19% : 0.000051s : 228: predicate.tuple_list_get_item_eliminator 1.66% : 0.000026s : 157: predicate.tuple_list_get_set_item_eliminator 2.33% : 0.000037s : 215: predicate.tuple_list_set_item_eliminator 1.56% : 0.000025s : 170: predicate.tuple_to_list_eliminator_ 2.56% : 0.000041s : 295: predicate.updatestate_pure_node_eliminater 3.27% : 0.000052s : 353: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 17: predicate.value_based_eliminate 0.38% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.35% : 0.000005s : 35: predicate.virtual_output_eliminate 0.19% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.20% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.017474 133 62.94% : 0.010997s : 53: func_graph_cloner_run.FuncGraphClonerGraph 37.06% : 0.006476s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.416652 209 0.00% : 0.000006s : 1: ForceFp32Comm 1.33% : 0.005523s : 1: add_attr 1.32% : 0.005504s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.05% : 0.000203s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.18% : 0.000741s : 1: auto_monad 0.02% : 0.000103s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.19% : 0.000812s : 1: bootstrap 0.01% : 0.000051s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.01% : 0.000049s : 1: control_data_broadcast_order 0.01% : 0.000039s : 1: convert_after_rewriter 0.02% : 0.000091s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.01% : 0.000040s : 1: environ_conv 0.05% : 0.000227s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000053s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000009s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 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% : 0.000014s : 1: label_micro_interleaved_index 0.21% : 0.000883s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.22% : 0.000920s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.01% : 0.000057s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000048s : 1: opt.transform.mutable_eliminate 2.82% : 0.011740s : 95: opt.transform.opt_a 0.04% : 0.000154s : 1: opt.transform.opt_after_cconv 0.02% : 0.000098s : 1: opt.transform.opt_after_jit_grad 0.15% : 0.000613s : 28: opt.transform.opt_b 0.06% : 0.000263s : 2: opt.transform.opt_trans_graph 0.04% : 0.000185s : 4: opt.transform.symbol_engine_opt 6.75% : 0.028139s : 1: opt_a 0.09% : 0.000393s : 1: opt_after_cconv 0.24% : 0.001009s : 1: opt_after_jit_grad 0.21% : 0.000887s : 1: opt_b 8.45% : 0.035219s : 1: optimize 0.01% : 0.000058s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.02% : 0.000065s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 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 0.06% : 0.000260s : 1: pre_auto_parallel 0.06% : 0.000270s : 1: py_interpret_to_execute 0.01% : 0.000041s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000124s : 1: remove_dup_value 1.60% : 0.006657s : 1: renormalize.infer 1.46% : 0.006072s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.22% : 0.000928s : 1: rewriter_after_opt_a 0.19% : 0.000805s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000007s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.14% : 0.000583s : 1: symbol_engine_optimizer 0.07% : 0.000309s : 1: tuple_transform 73.47% : 0.306121s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape0-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape0-16],max_mem:274.0M [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:38:01.329.299 [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 = 0.338633, [21] [bootstrap]: 0.00082081 [type_inference]: 0.291387 [event_method]: 0.00022759 [auto_monad]: 0.00084663 [graph_reusing]: 5.134e-05 [inline]: 3.23998e-06 [add_attr]: 0.00589507, [1] [add_attr_with_inline]: 0.00587346, [1] [Cycle 1]: 0.00036954, [2] [tag_attr]: 0.00024318 [meta_addattr_fg_expand]: 6.121e-05 [parallel-infer-symbol]: 4e-06 [pre_auto_parallel]: 0.00028383 [insert-virtual-dataset]: 3.75998e-06 [parallel-infer-symbol-second]: 1.24e-06 [dataset_repeat_opt]: 2.96001e-06 [pipeline_split]: 2.11e-06 [optimize]: 0.0379842, [53] [py_interpret_to_execute]: 0.0003505 [rewriter_before_opt_a]: 0.00092782 [opt_a]: 0.0315829, [2] [Cycle 1]: 0.0292905, [45] [expand_dump_flag]: 5.098e-05 [switch_simplify]: 0.00101495 [loop_unroll]: 0.00032659 [a_1]: 0.0103962 [with_stream_mark]: 6.032e-05 [recompute_prepare]: 4.3e-05 [updatestate_depend_eliminate]: 2.252e-05 [updatestate_assign_eliminate]: 1.605e-05 [updatestate_loads_eliminate]: 1.847e-05 [parameter_eliminate]: 2.59001e-06 [a_2]: 0.00080453 [accelerated_algorithm]: 7.063e-05 [shard]: 2.58e-06 [meta_shard_fg_expand]: 2.37e-05 [shard_inline]: 2.309e-05 [merge_send_recv]: 2.177e-05 [auto_parallel]: 2.178e-05 [parallel]: 3.415e-05 [flash_sp]: 1.664e-05 [merge_comm]: 1.523e-05 [allreduce_fusion]: 1.308e-05 [matmul_add_comm_reduction]: 2.269e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 2.967e-05 [virtual_dataset]: 2.202e-05 [get_grad_eliminate_]: 2.176e-05 [virtual_output]: 2.186e-05 [merge_forward]: 1.384e-05 [cell_reuse_recompute_pass]: 2.46e-06 [offload_activation]: 2.539e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.007e-05 [merge_recompute_call_nodes]: 1.42999e-06 [before_grad]: 4.031e-05 [set_forward_comm_id_for_comm_node_pass]: 1.706e-05 [meta_fg_expand]: 1.637e-05 [flash_sp_send_recv_attached]: 7.13e-06 [receive_attached]: 2.34999e-06 [after_resolve]: 3.401e-05 [a_after_grad]: 3.702e-05 [renormalize]: 0.0130309 [add_forward_monad_depend]: 1.3e-05 [auto_monad_grad]: 3.2e-06 [auto_monad_eliminator]: 8.542e-05 [cse]: 0.00215825 [a_3]: 0.00018082 [Cycle 2]: 0.00227001, [45] [expand_dump_flag]: 3.85e-06 [switch_simplify]: 2.682e-05 [loop_unroll]: 2.242e-05 [a_1]: 0.00067156 [with_stream_mark]: 4.062e-05 [recompute_prepare]: 2.646e-05 [updatestate_depend_eliminate]: 1.573e-05 [updatestate_assign_eliminate]: 1.376e-05 [updatestate_loads_eliminate]: 1.513e-05 [parameter_eliminate]: 2.92002e-06 [a_2]: 0.00031971 [accelerated_algorithm]: 3.554e-05 [shard]: 2.41998e-06 [meta_shard_fg_expand]: 9.10999e-06 [shard_inline]: 2.22e-05 [merge_send_recv]: 2.242e-05 [auto_parallel]: 1.964e-05 [parallel]: 1.159e-05 [flash_sp]: 4.57998e-06 [merge_comm]: 1.358e-05 [allreduce_fusion]: 1.253e-05 [matmul_add_comm_reduction]: 2.378e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 2.663e-05 [virtual_dataset]: 2.002e-05 [get_grad_eliminate_]: 2.03e-05 [virtual_output]: 2e-05 [merge_forward]: 1.425e-05 [cell_reuse_recompute_pass]: 2.61e-06 [offload_activation]: 2.419e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.259e-05 [merge_recompute_call_nodes]: 1.55999e-06 [before_grad]: 3.683e-05 [set_forward_comm_id_for_comm_node_pass]: 1.534e-05 [meta_fg_expand]: 1.021e-05 [flash_sp_send_recv_attached]: 2.07001e-06 [receive_attached]: 2.96001e-06 [after_resolve]: 2.809e-05 [a_after_grad]: 3.211e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 4.70001e-06 [auto_monad_grad]: 3.08e-06 [auto_monad_eliminator]: 0.00010264 [cse]: 8.58e-05 [a_3]: 0.00014393 [py_interpret_to_execute_after_opt_a]: 3.327e-05 [slice_cell_reuse_recomputed_activation]: 2.99999e-06 [rewriter_after_opt_a]: 0.00088154 [convert_after_rewriter]: 2.614e-05 [order_py_execute_after_rewriter]: 1.479e-05 [mutable_eliminate]: 0.0008524 [opt_b]: 0.0007556, [1] [Cycle 1]: 0.00074699, [7] [b_1]: 0.00054347 [b_2]: 2.42e-05 [updatestate_depend_eliminate]: 1.941e-05 [updatestate_assign_eliminate]: 1.186e-05 [updatestate_loads_eliminate]: 1.413e-05 [renormalize]: 9.5999e-07 [cse]: 8.891e-05 [optimize_parallel_all_gather_comm]: 4.089e-05 [overlap_param_gather]: 2.44001e-06 [cconv]: 4.384e-05 [loop_unroll]: 0.00053276 [opt_after_cconv]: 0.00030507, [1] [Cycle 1]: 0.00029654, [7] [c_1]: 0.00013822 [parameter_eliminate]: 4.58999e-06 [updatestate_depend_eliminate]: 1.913e-05 [updatestate_assign_eliminate]: 1.103e-05 [updatestate_loads_eliminate]: 1.314e-05 [cse]: 7.149e-05 [renormalize]: 5.39992e-07 [remove_dup_value]: 0.00010274 [tuple_transform]: 0.00025495, [1] [Cycle 1]: 0.00024922, [4] [d_1]: 0.00020075 [none_parameter_eliminate]: 2.98e-06 [renormalize]: 3.19997e-07 [switch_simplify]: 2.311e-05 [partial_unused_args_eliminate]: 2.11998e-06 [add_recomputation]: 0.00015579 [cse_after_recomputation]: 6.906e-05, [1] [Cycle 1]: 6.26e-05, [1] [cse]: 5.572e-05 [environ_conv]: 2.699e-05 [swap_dp_allreduce_reducescatter]: 2.048e-05 [bias_add_comm_swap]: 3.03e-06 [label_micro_interleaved_index]: 5.23002e-06 [label_fine_grained_interleaved_index]: 3.01001e-06 [merge_cast_opt]: 1.66e-06 [slice_recompute_activation]: 2.44001e-06 [micro_interleaved_order_control]: 2.73998e-06 [assign_add_opt]: 1.22999e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 9.20001e-07 [full_micro_interleaved_order_control]: 2.27001e-06 [reorder_send_recv_between_fp_bp]: 3.16001e-06 [comm_op_add_attrs]: 1.30001e-06 [add_comm_op_reuse_tag]: 9.09989e-07 [interleave_split_concat_branches]: 1.29998e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 1.15999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.22999e-06 [control_data_broadcast_order]: 3.794e-05 [grouped_pairwise_exchange_alltoall]: 1.57999e-06 [offloading_packed_experts]: 1.103e-05 [overlap_recompute_and_grad_model_parallel]: 1.007e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.29e-06 [overlap_recompute_allgather_and_fa_grad]: 1.36002e-06 [overlap_recompute_comm]: 2.49999e-06 [overlap_grad_ring_attention]: 9.14e-06 [overlap_grad_flash_sp]: 4.807e-05 [begin_end_overlap_inline]: 4.89992e-07 [split_matmul_comm_elemetwise]: 2.84999e-06 [split_layernorm_comm]: 2.09e-06 [handle_group_info]: 1.17e-06 [symbol_engine_optimizer]: 0.00051743, [1] [Cycle 1]: 0.00051119, [6] [build]: 0.0002888 [elim_shapecalc]: 3.496e-05 [elim_not_effective]: 5.041e-05 [opt_reshape]: 3.418e-05 [fold_const_symbol]: 5.871e-05 [renormalize]: 3.49974e-07 [detach_backward]: 3.12997e-06 [pipeline_parallel_scheduler]: 1.89e-06 [auto_monad_reorder]: 6.215e-05 [get_jit_bprop_graph]: 2.06e-06 [rewriter_after_jit_bprop_graph]: 7.46001e-06 [opt_after_jit_grad]: 0.00068797 [validate]: 0.0001076 Sums bootstrap : 0.000821s : 0.25% type_inference : 0.291387s : 87.89% event_method : 0.000228s : 0.07% auto_monad : 0.000847s : 0.26% graph_reusing : 0.000051s : 0.02% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000243s : 0.07% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000061s : 0.02% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000284s : 0.09% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000351s : 0.11% optimize.rewriter_before_opt_a : 0.000928s : 0.28% optimize.opt_a.expand_dump_flag : 0.000055s : 0.02% optimize.opt_a.switch_simplify : 0.001042s : 0.31% optimize.opt_a.loop_unroll : 0.000349s : 0.11% optimize.opt_a.a_1 : 0.011068s : 3.34% optimize.opt_a.with_stream_mark : 0.000101s : 0.03% optimize.opt_a.recompute_prepare : 0.000069s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000034s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001124s : 0.34% optimize.opt_a.accelerated_algorithm : 0.000106s : 0.03% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000033s : 0.01% optimize.opt_a.shard_inline : 0.000045s : 0.01% optimize.opt_a.merge_send_recv : 0.000044s : 0.01% optimize.opt_a.auto_parallel : 0.000041s : 0.01% optimize.opt_a.parallel : 0.000046s : 0.01% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000029s : 0.01% optimize.opt_a.allreduce_fusion : 0.000026s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000046s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000056s : 0.02% optimize.opt_a.virtual_dataset : 0.000042s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.01% optimize.opt_a.virtual_output : 0.000042s : 0.01% optimize.opt_a.merge_forward : 0.000028s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000050s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000113s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000077s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000032s : 0.01% optimize.opt_a.meta_fg_expand : 0.000027s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000062s : 0.02% optimize.opt_a.a_after_grad : 0.000069s : 0.02% optimize.opt_a.renormalize : 0.013031s : 3.93% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000188s : 0.06% optimize.opt_a.cse : 0.002244s : 0.68% optimize.opt_a.a_3 : 0.000325s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000882s : 0.27% optimize.convert_after_rewriter : 0.000026s : 0.01% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000852s : 0.26% optimize.opt_b.b_1 : 0.000543s : 0.16% optimize.opt_b.b_2 : 0.000024s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000089s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000041s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.01% optimize.loop_unroll : 0.000533s : 0.16% optimize.opt_after_cconv.c_1 : 0.000138s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000071s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000103s : 0.03% optimize.tuple_transform.d_1 : 0.000201s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000023s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000156s : 0.05% optimize.cse_after_recomputation.cse : 0.000056s : 0.02% optimize.environ_conv : 0.000027s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 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 : 0.000002s : 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 : 0.000001s : 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 : 0.000038s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 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 : 0.000048s : 0.01% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000289s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000050s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000059s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000062s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000688s : 0.21% validate : 0.000108s : 0.03% Time group info: ------[substitution.] 0.004000 569 0.43% : 0.000017s : 8: substitution.depend_value_elim 0.35% : 0.000014s : 14: substitution.elim_not_effective 0.44% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.69% : 0.000028s : 14: substitution.fold_const_symbol 0.38% : 0.000015s : 17: substitution.graph_param_transform 71.11% : 0.002844s : 71: substitution.inline 0.33% : 0.000013s : 29: substitution.j_node_and_user_rematch 0.87% : 0.000035s : 6: substitution.less_batch_normalization 1.70% : 0.000068s : 2: substitution.list_to_tuple_eliminator_ 0.17% : 0.000007s : 6: substitution.load_eliminater 0.81% : 0.000032s : 21: substitution.minmaximum_grad 0.21% : 0.000008s : 2: substitution.opt_reshape 0.55% : 0.000022s : 29: substitution.remove_not_recompute_node 0.22% : 0.000009s : 4: substitution.replace_old_param 1.91% : 0.000076s : 18: substitution.reshape_eliminate 1.58% : 0.000063s : 24: substitution.switch_simplify 3.96% : 0.000159s : 51: substitution.tuple_list_convert_item_index_to_positive 2.13% : 0.000085s : 51: substitution.tuple_list_get_item_const_eliminator 2.75% : 0.000110s : 51: substitution.tuple_list_get_item_depend_reorder 5.57% : 0.000223s : 73: substitution.tuple_list_get_item_eliminator 2.66% : 0.000106s : 51: substitution.tuple_list_get_set_item_eliminator 0.64% : 0.000026s : 6: substitution.updatestate_pure_node_eliminater 0.54% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.290902 2 92.29% : 0.268470s : 1: type_inference.infer 7.71% : 0.022432s : 1: type_inference.specialize ------[replace.] 0.001427 115 3.37% : 0.000048s : 5: replace.depend_value_elim 57.86% : 0.000826s : 71: replace.inline 3.45% : 0.000049s : 2: replace.list_to_tuple_eliminator_ 27.14% : 0.000387s : 24: replace.switch_simplify 8.18% : 0.000117s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002947 115 0.08% : 0.000002s : 5: match.depend_value_elim 94.71% : 0.002791s : 71: match.inline 2.20% : 0.000065s : 2: match.list_to_tuple_eliminator_ 1.73% : 0.000051s : 24: match.switch_simplify 1.28% : 0.000038s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001693 9701 1.19% : 0.000020s : 123: predicate.accumulaten_eliminater 0.32% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.48% : 0.000008s : 58: predicate.addn_check_dump 1.15% : 0.000019s : 123: predicate.addn_zero_filter 1.15% : 0.000020s : 123: predicate.adjust_all_reduce_mul_add 2.41% : 0.000041s : 181: predicate.arithmetic_simplify 1.12% : 0.000019s : 123: predicate.cast_eliminate 0.29% : 0.000005s : 34: predicate.check_bprop_eliminate 0.46% : 0.000008s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.59% : 0.000010s : 61: predicate.depend_value_elim 1.14% : 0.000019s : 123: predicate.dict_get_item_const_eliminator 1.19% : 0.000020s : 123: predicate.dict_get_item_eliminator 1.04% : 0.000018s : 123: predicate.dict_set_item_eliminator 0.36% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.20% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000020s : 140: predicate.environ_add_const_eliminate 1.16% : 0.000020s : 140: predicate.environ_get_add_eliminate 1.19% : 0.000020s : 140: predicate.environ_get_depend_swap 1.71% : 0.000029s : 198: predicate.environ_get_eliminate 1.18% : 0.000020s : 140: predicate.environ_get_set_eliminate 1.88% : 0.000032s : 209: predicate.exchange_switch_depend_value 2.90% : 0.000049s : 209: predicate.float_depend_g_call 0.48% : 0.000008s : 58: predicate.float_environ_get_switch 0.66% : 0.000011s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.36% : 0.000006s : 35: predicate.get_grad_eliminate 0.09% : 0.000002s : 17: predicate.graph_param_transform 0.49% : 0.000008s : 58: predicate.incorporate_call 0.45% : 0.000008s : 58: predicate.incorporate_call_switch 6.14% : 0.000104s : 459: predicate.inline 0.40% : 0.000007s : 35: predicate.inline_without_move 0.15% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.50% : 0.000009s : 36: predicate.less_batch_normalization 1.89% : 0.000032s : 172: predicate.list_to_tuple_eliminator_ 2.49% : 0.000042s : 295: predicate.load_eliminater 0.32% : 0.000005s : 17: predicate.loop_unroll_after_grad 3.32% : 0.000056s : 314: predicate.loop_unroll_before_grad 1.50% : 0.000025s : 157: predicate.make_slice_get_slice_eliminator 0.50% : 0.000008s : 58: predicate.merge_addn 0.28% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.29% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.12% : 0.000019s : 123: predicate.minmaximum_grad 0.40% : 0.000007s : 17: predicate.mutable_eliminate 0.17% : 0.000003s : 17: predicate.opt_reshape 0.17% : 0.000003s : 17: predicate.parallel_virtual_node 3.19% : 0.000054s : 209: predicate.partial_defer_inline 1.47% : 0.000025s : 155: predicate.partial_eliminate 1.08% : 0.000018s : 123: predicate.print_const_string_wrapper 0.45% : 0.000008s : 53: predicate.reduce_all_const_elim 1.59% : 0.000027s : 123: predicate.reduce_eliminate 2.45% : 0.000041s : 295: predicate.redundant_stop_gradient_eliminater 0.19% : 0.000003s : 35: predicate.remove_not_recompute_node 1.07% : 0.000018s : 172: predicate.replace_applicator 0.19% : 0.000003s : 35: predicate.replace_old_param 0.13% : 0.000002s : 17: predicate.reset_defer_inline 1.32% : 0.000022s : 123: predicate.reshape_eliminate 0.30% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.17% : 0.000003s : 17: predicate.row_tensor_eliminate 0.43% : 0.000007s : 34: predicate.same_eliminate 0.22% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.40% : 0.000007s : 35: predicate.shard_identity_eliminate 0.34% : 0.000006s : 34: predicate.special_op_eliminate 0.55% : 0.000009s : 58: predicate.specialize_transform 0.44% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.38% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.15% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.19% : 0.000037s : 209: predicate.switch_defer_inline 2.36% : 0.000040s : 243: predicate.switch_layer_defer_inline 7.71% : 0.000131s : 646: predicate.switch_simplify 1.27% : 0.000022s : 123: predicate.tile_eliminate 1.16% : 0.000020s : 123: predicate.transpose_eliminate 1.70% : 0.000029s : 157: predicate.tuple_list_convert_item_index_to_positive 3.42% : 0.000058s : 157: predicate.tuple_list_get_item_const_eliminator 1.60% : 0.000027s : 157: predicate.tuple_list_get_item_depend_reorder 3.26% : 0.000055s : 228: predicate.tuple_list_get_item_eliminator 1.64% : 0.000028s : 157: predicate.tuple_list_get_set_item_eliminator 2.19% : 0.000037s : 215: predicate.tuple_list_set_item_eliminator 1.56% : 0.000026s : 170: predicate.tuple_to_list_eliminator_ 2.43% : 0.000041s : 295: predicate.updatestate_pure_node_eliminater 3.14% : 0.000053s : 353: predicate.updatestate_useless_node_eliminater 0.17% : 0.000003s : 17: predicate.value_based_eliminate 0.32% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.31% : 0.000005s : 35: predicate.virtual_output_eliminate 0.15% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.19% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.017137 133 55.58% : 0.009525s : 53: func_graph_cloner_run.FuncGraphClonerGraph 44.42% : 0.007613s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.410961 209 0.00% : 0.000003s : 1: ForceFp32Comm 1.44% : 0.005904s : 1: add_attr 1.43% : 0.005879s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000161s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.21% : 0.000865s : 1: auto_monad 0.02% : 0.000068s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000856s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000042s : 1: control_data_broadcast_order 0.01% : 0.000031s : 1: convert_after_rewriter 0.02% : 0.000072s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000030s : 1: environ_conv 0.06% : 0.000241s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000060s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.13% : 0.000542s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.21% : 0.000863s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.01% : 0.000036s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000043s : 1: opt.transform.mutable_eliminate 3.52% : 0.014467s : 95: opt.transform.opt_a 0.03% : 0.000137s : 1: opt.transform.opt_after_cconv 0.02% : 0.000075s : 1: opt.transform.opt_after_jit_grad 0.13% : 0.000532s : 28: opt.transform.opt_b 0.05% : 0.000221s : 2: opt.transform.opt_trans_graph 0.04% : 0.000173s : 4: opt.transform.symbol_engine_opt 7.69% : 0.031589s : 1: opt_a 0.08% : 0.000309s : 1: opt_after_cconv 0.17% : 0.000698s : 1: opt_after_jit_grad 0.18% : 0.000759s : 1: opt_b 9.24% : 0.037991s : 1: optimize 0.01% : 0.000045s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.01% : 0.000052s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.07% : 0.000297s : 1: pre_auto_parallel 0.09% : 0.000365s : 1: py_interpret_to_execute 0.01% : 0.000038s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000109s : 1: remove_dup_value 1.52% : 0.006259s : 1: renormalize.infer 1.64% : 0.006753s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.22% : 0.000894s : 1: rewriter_after_opt_a 0.23% : 0.000954s : 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 0.01% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.13% : 0.000522s : 1: symbol_engine_optimizer 0.06% : 0.000260s : 1: tuple_transform 70.91% : 0.291424s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape1-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape1-1],max_mem:274.0M [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:38:07.464.2 [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 = 0.324748, [21] [bootstrap]: 0.00077763 [type_inference]: 0.27947 [event_method]: 0.00021792 [auto_monad]: 0.00077376 [graph_reusing]: 5.268e-05 [inline]: 3.46001e-06 [add_attr]: 0.00510242, [1] [add_attr_with_inline]: 0.00508346, [1] [Cycle 1]: 0.00030871, [2] [tag_attr]: 0.00019793 [meta_addattr_fg_expand]: 5.621e-05 [parallel-infer-symbol]: 4.26001e-06 [pre_auto_parallel]: 0.00025383 [insert-virtual-dataset]: 2.59999e-06 [parallel-infer-symbol-second]: 1.50999e-06 [dataset_repeat_opt]: 2.27999e-06 [pipeline_split]: 1.66e-06 [optimize]: 0.0369889, [53] [py_interpret_to_execute]: 0.00026275 [rewriter_before_opt_a]: 0.00080255 [opt_a]: 0.030515, [2] [Cycle 1]: 0.028168, [45] [expand_dump_flag]: 3.329e-05 [switch_simplify]: 0.00088883 [loop_unroll]: 0.00034462 [a_1]: 0.00947815 [with_stream_mark]: 5.855e-05 [recompute_prepare]: 4.061e-05 [updatestate_depend_eliminate]: 2.048e-05 [updatestate_assign_eliminate]: 1.881e-05 [updatestate_loads_eliminate]: 1.842e-05 [parameter_eliminate]: 2.78e-06 [a_2]: 0.00079021 [accelerated_algorithm]: 6.318e-05 [shard]: 2.19001e-06 [meta_shard_fg_expand]: 2.172e-05 [shard_inline]: 2.297e-05 [merge_send_recv]: 3.363e-05 [auto_parallel]: 2.263e-05 [parallel]: 3.798e-05 [flash_sp]: 1.657e-05 [merge_comm]: 1.449e-05 [allreduce_fusion]: 1.261e-05 [matmul_add_comm_reduction]: 2.295e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.944e-05 [virtual_dataset]: 2.353e-05 [get_grad_eliminate_]: 2.14e-05 [virtual_output]: 2.145e-05 [merge_forward]: 1.305e-05 [cell_reuse_recompute_pass]: 1.67001e-06 [offload_activation]: 2.304e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.676e-05 [merge_recompute_call_nodes]: 1.69998e-06 [before_grad]: 3.982e-05 [set_forward_comm_id_for_comm_node_pass]: 1.488e-05 [meta_fg_expand]: 1.9e-05 [flash_sp_send_recv_attached]: 6.52001e-06 [receive_attached]: 3.35e-06 [after_resolve]: 3.122e-05 [a_after_grad]: 3.897e-05 [renormalize]: 0.0138435 [add_forward_monad_depend]: 1.486e-05 [auto_monad_grad]: 3.61001e-06 [auto_monad_eliminator]: 0.00010838 [cse]: 0.00123692 [a_3]: 0.00020615 [Cycle 2]: 0.00232755, [45] [expand_dump_flag]: 4.01001e-06 [switch_simplify]: 2.81e-05 [loop_unroll]: 2.264e-05 [a_1]: 0.00069012 [with_stream_mark]: 4.46e-05 [recompute_prepare]: 2.711e-05 [updatestate_depend_eliminate]: 1.617e-05 [updatestate_assign_eliminate]: 1.32e-05 [updatestate_loads_eliminate]: 1.545e-05 [parameter_eliminate]: 3.13e-06 [a_2]: 0.00032439 [accelerated_algorithm]: 3.813e-05 [shard]: 2.96001e-06 [meta_shard_fg_expand]: 8.62998e-06 [shard_inline]: 2.2e-05 [merge_send_recv]: 2.25e-05 [auto_parallel]: 2.129e-05 [parallel]: 1.251e-05 [flash_sp]: 4.45e-06 [merge_comm]: 1.347e-05 [allreduce_fusion]: 1.452e-05 [matmul_add_comm_reduction]: 2.367e-05 [allreduce_slice_to_reducescatter]: 1.17e-06 [virtual_shard_identity]: 3.171e-05 [virtual_dataset]: 2.246e-05 [get_grad_eliminate_]: 2.122e-05 [virtual_output]: 2.139e-05 [merge_forward]: 1.496e-05 [cell_reuse_recompute_pass]: 3.68e-06 [offload_activation]: 2.504e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.997e-05 [merge_recompute_call_nodes]: 1.95001e-06 [before_grad]: 3.889e-05 [set_forward_comm_id_for_comm_node_pass]: 1.615e-05 [meta_fg_expand]: 1.159e-05 [flash_sp_send_recv_attached]: 2.09e-06 [receive_attached]: 2.56e-06 [after_resolve]: 3.169e-05 [a_after_grad]: 3.562e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 5.76998e-06 [auto_monad_grad]: 3.44001e-06 [auto_monad_eliminator]: 7.301e-05 [cse]: 9.583e-05 [a_3]: 0.00014907 [py_interpret_to_execute_after_opt_a]: 3.907e-05 [slice_cell_reuse_recomputed_activation]: 2.58e-06 [rewriter_after_opt_a]: 0.00092887 [convert_after_rewriter]: 3.157e-05 [order_py_execute_after_rewriter]: 1.509e-05 [mutable_eliminate]: 0.0008966 [opt_b]: 0.00080042, [1] [Cycle 1]: 0.00078951, [7] [b_1]: 0.00055622 [b_2]: 2.676e-05 [updatestate_depend_eliminate]: 2.198e-05 [updatestate_assign_eliminate]: 1.257e-05 [updatestate_loads_eliminate]: 1.505e-05 [renormalize]: 5.8001e-07 [cse]: 0.00010018 [optimize_parallel_all_gather_comm]: 4.652e-05 [overlap_param_gather]: 3.55e-06 [cconv]: 4.985e-05 [loop_unroll]: 0.00059945 [opt_after_cconv]: 0.00031405, [1] [Cycle 1]: 0.00030237, [7] [c_1]: 0.00013062 [parameter_eliminate]: 5.57001e-06 [updatestate_depend_eliminate]: 2.142e-05 [updatestate_assign_eliminate]: 1.153e-05 [updatestate_loads_eliminate]: 1.288e-05 [cse]: 7.737e-05 [renormalize]: 1.71e-06 [remove_dup_value]: 0.00010873 [tuple_transform]: 0.00026887, [1] [Cycle 1]: 0.00026221, [4] [d_1]: 0.00020996 [none_parameter_eliminate]: 2.79001e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 2.315e-05 [partial_unused_args_eliminate]: 2.54999e-06 [add_recomputation]: 0.00016065 [cse_after_recomputation]: 7.746e-05, [1] [Cycle 1]: 7.043e-05, [1] [cse]: 6.147e-05 [environ_conv]: 2.705e-05 [swap_dp_allreduce_reducescatter]: 2.023e-05 [bias_add_comm_swap]: 3.41999e-06 [label_micro_interleaved_index]: 5.96998e-06 [label_fine_grained_interleaved_index]: 2.71e-06 [merge_cast_opt]: 1.82001e-06 [slice_recompute_activation]: 2.19001e-06 [micro_interleaved_order_control]: 2.49999e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 1.11002e-06 [remove_cast_before_assign_add]: 1.14e-06 [full_micro_interleaved_order_control]: 2.29999e-06 [reorder_send_recv_between_fp_bp]: 3.58e-06 [comm_op_add_attrs]: 1.00001e-06 [add_comm_op_reuse_tag]: 1.27999e-06 [interleave_split_concat_branches]: 1.37e-06 [interleave_parallel_branches]: 1.25999e-06 [overlap_opt_shard_in_pipeline]: 2.98e-06 [overlap_opt_shard_grad_in_pipeline]: 2.39001e-06 [control_data_broadcast_order]: 4.021e-05 [grouped_pairwise_exchange_alltoall]: 1.74e-06 [offloading_packed_experts]: 1.113e-05 [overlap_recompute_and_grad_model_parallel]: 1.079e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.45999e-06 [overlap_recompute_comm]: 2.63998e-06 [overlap_grad_ring_attention]: 8.96002e-06 [overlap_grad_flash_sp]: 5.213e-05 [begin_end_overlap_inline]: 1.06997e-06 [split_matmul_comm_elemetwise]: 2.17999e-06 [split_layernorm_comm]: 1.96e-06 [handle_group_info]: 1.19998e-06 [symbol_engine_optimizer]: 0.00052777, [1] [Cycle 1]: 0.00052237, [6] [build]: 0.00029786 [elim_shapecalc]: 3.509e-05 [elim_not_effective]: 5.552e-05 [opt_reshape]: 3.37e-05 [fold_const_symbol]: 5.53e-05 [renormalize]: 2.3999e-07 [detach_backward]: 2.84999e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 6.241e-05 [get_jit_bprop_graph]: 1.98997e-06 [rewriter_after_jit_bprop_graph]: 7.38e-06 [opt_after_jit_grad]: 0.0006765 [validate]: 0.00011222 Sums bootstrap : 0.000778s : 0.24% type_inference : 0.279470s : 87.78% event_method : 0.000218s : 0.07% auto_monad : 0.000774s : 0.24% graph_reusing : 0.000053s : 0.02% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000198s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000056s : 0.02% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000254s : 0.08% insert-virtual-dataset : 0.000003s : 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 : 0.000263s : 0.08% optimize.rewriter_before_opt_a : 0.000803s : 0.25% optimize.opt_a.expand_dump_flag : 0.000037s : 0.01% optimize.opt_a.switch_simplify : 0.000917s : 0.29% optimize.opt_a.loop_unroll : 0.000367s : 0.12% optimize.opt_a.a_1 : 0.010168s : 3.19% optimize.opt_a.with_stream_mark : 0.000103s : 0.03% optimize.opt_a.recompute_prepare : 0.000068s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000032s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000034s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001115s : 0.35% optimize.opt_a.accelerated_algorithm : 0.000101s : 0.03% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000030s : 0.01% optimize.opt_a.shard_inline : 0.000045s : 0.01% optimize.opt_a.merge_send_recv : 0.000056s : 0.02% optimize.opt_a.auto_parallel : 0.000044s : 0.01% optimize.opt_a.parallel : 0.000050s : 0.02% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000028s : 0.01% optimize.opt_a.allreduce_fusion : 0.000027s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000047s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000061s : 0.02% optimize.opt_a.virtual_dataset : 0.000046s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000043s : 0.01% optimize.opt_a.virtual_output : 0.000043s : 0.01% optimize.opt_a.merge_forward : 0.000028s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000097s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000079s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.01% optimize.opt_a.meta_fg_expand : 0.000031s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000063s : 0.02% optimize.opt_a.a_after_grad : 0.000075s : 0.02% optimize.opt_a.renormalize : 0.013844s : 4.35% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.01% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000181s : 0.06% optimize.opt_a.cse : 0.001333s : 0.42% optimize.opt_a.a_3 : 0.000355s : 0.11% optimize.py_interpret_to_execute_after_opt_a : 0.000039s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000929s : 0.29% optimize.convert_after_rewriter : 0.000032s : 0.01% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000897s : 0.28% optimize.opt_b.b_1 : 0.000556s : 0.17% optimize.opt_b.b_2 : 0.000027s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000100s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000047s : 0.01% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000050s : 0.02% optimize.loop_unroll : 0.000599s : 0.19% optimize.opt_after_cconv.c_1 : 0.000131s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000021s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000077s : 0.02% optimize.opt_after_cconv.renormalize : 0.000002s : 0.00% optimize.remove_dup_value : 0.000109s : 0.03% optimize.tuple_transform.d_1 : 0.000210s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000023s : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000161s : 0.05% optimize.cse_after_recomputation.cse : 0.000061s : 0.02% optimize.environ_conv : 0.000027s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 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 : 0.000004s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000040s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000052s : 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 : 0.000298s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000056s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000055s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000062s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000676s : 0.21% validate : 0.000112s : 0.04% Time group info: ------[substitution.] 0.003588 569 0.46% : 0.000016s : 8: substitution.depend_value_elim 0.50% : 0.000018s : 14: substitution.elim_not_effective 0.56% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.68% : 0.000025s : 14: substitution.fold_const_symbol 0.43% : 0.000015s : 17: substitution.graph_param_transform 68.89% : 0.002472s : 71: substitution.inline 0.39% : 0.000014s : 29: substitution.j_node_and_user_rematch 0.91% : 0.000033s : 6: substitution.less_batch_normalization 1.73% : 0.000062s : 2: substitution.list_to_tuple_eliminator_ 0.17% : 0.000006s : 6: substitution.load_eliminater 0.97% : 0.000035s : 21: substitution.minmaximum_grad 0.22% : 0.000008s : 2: substitution.opt_reshape 0.59% : 0.000021s : 29: substitution.remove_not_recompute_node 0.25% : 0.000009s : 4: substitution.replace_old_param 1.92% : 0.000069s : 18: substitution.reshape_eliminate 1.51% : 0.000054s : 24: substitution.switch_simplify 4.29% : 0.000154s : 51: substitution.tuple_list_convert_item_index_to_positive 2.36% : 0.000085s : 51: substitution.tuple_list_get_item_const_eliminator 2.99% : 0.000107s : 51: substitution.tuple_list_get_item_depend_reorder 5.86% : 0.000210s : 73: substitution.tuple_list_get_item_eliminator 2.91% : 0.000104s : 51: substitution.tuple_list_get_set_item_eliminator 0.77% : 0.000028s : 6: substitution.updatestate_pure_node_eliminater 0.64% : 0.000023s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.279021 2 92.65% : 0.258516s : 1: type_inference.infer 7.35% : 0.020505s : 1: type_inference.specialize ------[replace.] 0.001197 115 3.59% : 0.000043s : 5: replace.depend_value_elim 55.15% : 0.000660s : 71: replace.inline 3.85% : 0.000046s : 2: replace.list_to_tuple_eliminator_ 27.19% : 0.000325s : 24: replace.switch_simplify 10.21% : 0.000122s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002563 115 0.09% : 0.000002s : 5: match.depend_value_elim 94.69% : 0.002427s : 71: match.inline 2.30% : 0.000059s : 2: match.list_to_tuple_eliminator_ 1.63% : 0.000042s : 24: match.switch_simplify 1.29% : 0.000033s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001661 9701 1.22% : 0.000020s : 123: predicate.accumulaten_eliminater 0.31% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.50% : 0.000008s : 58: predicate.addn_check_dump 1.20% : 0.000020s : 123: predicate.addn_zero_filter 1.07% : 0.000018s : 123: predicate.adjust_all_reduce_mul_add 2.24% : 0.000037s : 181: predicate.arithmetic_simplify 1.11% : 0.000018s : 123: predicate.cast_eliminate 0.33% : 0.000005s : 34: predicate.check_bprop_eliminate 0.49% : 0.000008s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.60% : 0.000010s : 61: predicate.depend_value_elim 1.42% : 0.000024s : 123: predicate.dict_get_item_const_eliminator 1.27% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.12% : 0.000019s : 123: predicate.dict_set_item_eliminator 0.43% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.09% : 0.000002s : 17: predicate.elim_not_effective 0.20% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000020s : 140: predicate.environ_add_const_eliminate 1.23% : 0.000020s : 140: predicate.environ_get_add_eliminate 1.19% : 0.000020s : 140: predicate.environ_get_depend_swap 1.80% : 0.000030s : 198: predicate.environ_get_eliminate 1.18% : 0.000020s : 140: predicate.environ_get_set_eliminate 1.93% : 0.000032s : 209: predicate.exchange_switch_depend_value 2.76% : 0.000046s : 209: predicate.float_depend_g_call 0.50% : 0.000008s : 58: predicate.float_environ_get_switch 0.69% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.36% : 0.000006s : 35: predicate.get_grad_eliminate 0.11% : 0.000002s : 17: predicate.graph_param_transform 0.50% : 0.000008s : 58: predicate.incorporate_call 0.46% : 0.000008s : 58: predicate.incorporate_call_switch 6.02% : 0.000100s : 459: predicate.inline 0.44% : 0.000007s : 35: predicate.inline_without_move 0.15% : 0.000002s : 35: predicate.j_node_and_user_rematch 0.49% : 0.000008s : 36: predicate.less_batch_normalization 1.74% : 0.000029s : 172: predicate.list_to_tuple_eliminator_ 2.65% : 0.000044s : 295: predicate.load_eliminater 0.37% : 0.000006s : 17: predicate.loop_unroll_after_grad 3.52% : 0.000059s : 314: predicate.loop_unroll_before_grad 1.62% : 0.000027s : 157: predicate.make_slice_get_slice_eliminator 0.53% : 0.000009s : 58: predicate.merge_addn 0.32% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.31% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.10% : 0.000018s : 123: predicate.minmaximum_grad 0.41% : 0.000007s : 17: predicate.mutable_eliminate 0.18% : 0.000003s : 17: predicate.opt_reshape 0.18% : 0.000003s : 17: predicate.parallel_virtual_node 3.30% : 0.000055s : 209: predicate.partial_defer_inline 1.48% : 0.000025s : 155: predicate.partial_eliminate 1.11% : 0.000018s : 123: predicate.print_const_string_wrapper 0.48% : 0.000008s : 53: predicate.reduce_all_const_elim 1.50% : 0.000025s : 123: predicate.reduce_eliminate 2.64% : 0.000044s : 295: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 35: predicate.remove_not_recompute_node 1.09% : 0.000018s : 172: predicate.replace_applicator 0.19% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.23% : 0.000020s : 123: predicate.reshape_eliminate 0.31% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.18% : 0.000003s : 17: predicate.row_tensor_eliminate 0.48% : 0.000008s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.40% : 0.000007s : 35: predicate.shard_identity_eliminate 0.36% : 0.000006s : 34: predicate.special_op_eliminate 0.61% : 0.000010s : 58: predicate.specialize_transform 0.45% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.46% : 0.000008s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.21% : 0.000037s : 209: predicate.switch_defer_inline 2.39% : 0.000040s : 243: predicate.switch_layer_defer_inline 7.34% : 0.000122s : 646: predicate.switch_simplify 1.17% : 0.000019s : 123: predicate.tile_eliminate 1.17% : 0.000019s : 123: predicate.transpose_eliminate 1.78% : 0.000030s : 157: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000029s : 157: predicate.tuple_list_get_item_const_eliminator 1.58% : 0.000026s : 157: predicate.tuple_list_get_item_depend_reorder 3.08% : 0.000051s : 228: predicate.tuple_list_get_item_eliminator 1.63% : 0.000027s : 157: predicate.tuple_list_get_set_item_eliminator 2.34% : 0.000039s : 215: predicate.tuple_list_set_item_eliminator 1.61% : 0.000027s : 170: predicate.tuple_to_list_eliminator_ 2.61% : 0.000043s : 295: predicate.updatestate_pure_node_eliminater 3.44% : 0.000057s : 353: predicate.updatestate_useless_node_eliminater 0.16% : 0.000003s : 17: predicate.value_based_eliminate 0.35% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.33% : 0.000006s : 35: predicate.virtual_output_eliminate 0.14% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.016714 133 56.31% : 0.009411s : 53: func_graph_cloner_run.FuncGraphClonerGraph 43.69% : 0.007303s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.395137 209 0.00% : 0.000004s : 1: ForceFp32Comm 1.29% : 0.005109s : 1: add_attr 1.29% : 0.005089s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.04% : 0.000166s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.20% : 0.000789s : 1: auto_monad 0.02% : 0.000067s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000816s : 1: bootstrap 0.01% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000043s : 1: control_data_broadcast_order 0.01% : 0.000037s : 1: convert_after_rewriter 0.02% : 0.000082s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000031s : 1: environ_conv 0.06% : 0.000230s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.02% : 0.000060s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.15% : 0.000610s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.23% : 0.000909s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.01% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000049s : 1: opt.transform.mutable_eliminate 3.41% : 0.013477s : 95: opt.transform.opt_a 0.03% : 0.000129s : 1: opt.transform.opt_after_cconv 0.02% : 0.000076s : 1: opt.transform.opt_after_jit_grad 0.14% : 0.000547s : 28: opt.transform.opt_b 0.06% : 0.000230s : 2: opt.transform.opt_trans_graph 0.04% : 0.000173s : 4: opt.transform.symbol_engine_opt 7.72% : 0.030520s : 1: opt_a 0.08% : 0.000319s : 1: opt_after_cconv 0.17% : 0.000687s : 1: opt_after_jit_grad 0.20% : 0.000805s : 1: opt_b 9.36% : 0.036996s : 1: optimize 0.01% : 0.000052s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.01% : 0.000056s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.07% : 0.000263s : 1: pre_auto_parallel 0.07% : 0.000271s : 1: py_interpret_to_execute 0.01% : 0.000044s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000115s : 1: remove_dup_value 1.63% : 0.006424s : 1: renormalize.infer 1.87% : 0.007397s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.24% : 0.000944s : 1: rewriter_after_opt_a 0.21% : 0.000814s : 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% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.13% : 0.000532s : 1: symbol_engine_optimizer 0.07% : 0.000273s : 1: tuple_transform 70.74% : 0.279508s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape1-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape1-16],max_mem:272.0M [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:38:15.281.753 [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 = 0.641033, [21] [bootstrap]: 0.00094046 [type_inference]: 0.56929 [event_method]: 0.00021128 [auto_monad]: 0.00073126 [graph_reusing]: 4.92e-05 [inline]: 3.28e-06 [add_attr]: 0.00523645, [1] [add_attr_with_inline]: 0.00521906, [1] [Cycle 1]: 0.00029971, [2] [tag_attr]: 0.00019148 [meta_addattr_fg_expand]: 5.956e-05 [parallel-infer-symbol]: 3.66999e-06 [pre_auto_parallel]: 0.00024241 [insert-virtual-dataset]: 2.59001e-06 [parallel-infer-symbol-second]: 1.10999e-06 [dataset_repeat_opt]: 2.12001e-06 [pipeline_split]: 2.21e-06 [optimize]: 0.0632236, [53] [py_interpret_to_execute]: 0.00028402 [rewriter_before_opt_a]: 0.00078713 [opt_a]: 0.0570347, [2] [Cycle 1]: 0.0548441, [45] [expand_dump_flag]: 1.703e-05 [switch_simplify]: 0.00081121 [loop_unroll]: 0.00032003 [a_1]: 0.00916932 [with_stream_mark]: 5.662e-05 [recompute_prepare]: 4.038e-05 [updatestate_depend_eliminate]: 2.149e-05 [updatestate_assign_eliminate]: 1.612e-05 [updatestate_loads_eliminate]: 1.899e-05 [parameter_eliminate]: 3.02002e-06 [a_2]: 0.00082203 [accelerated_algorithm]: 6.277e-05 [shard]: 2.22001e-06 [meta_shard_fg_expand]: 1.792e-05 [shard_inline]: 2.412e-05 [merge_send_recv]: 2.152e-05 [auto_parallel]: 2.162e-05 [parallel]: 3.385e-05 [flash_sp]: 1.6e-05 [merge_comm]: 1.381e-05 [allreduce_fusion]: 1.259e-05 [matmul_add_comm_reduction]: 2.227e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 2.758e-05 [virtual_dataset]: 2.289e-05 [get_grad_eliminate_]: 2.224e-05 [virtual_output]: 2.182e-05 [merge_forward]: 1.348e-05 [cell_reuse_recompute_pass]: 2.14999e-06 [offload_activation]: 2.384e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.538e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 3.939e-05 [set_forward_comm_id_for_comm_node_pass]: 1.372e-05 [meta_fg_expand]: 1.743e-05 [flash_sp_send_recv_attached]: 6.06e-06 [receive_attached]: 2.46998e-06 [after_resolve]: 2.92e-05 [a_after_grad]: 3.635e-05 [renormalize]: 0.040444 [add_forward_monad_depend]: 1.41e-05 [auto_monad_grad]: 3.42002e-06 [auto_monad_eliminator]: 8.912e-05 [cse]: 0.00184147 [a_3]: 0.00017669 [Cycle 2]: 0.00217456, [45] [expand_dump_flag]: 3.18e-06 [switch_simplify]: 2.657e-05 [loop_unroll]: 2.134e-05 [a_1]: 0.00066038 [with_stream_mark]: 3.807e-05 [recompute_prepare]: 2.593e-05 [updatestate_depend_eliminate]: 1.633e-05 [updatestate_assign_eliminate]: 1.162e-05 [updatestate_loads_eliminate]: 1.466e-05 [parameter_eliminate]: 2.49001e-06 [a_2]: 0.00031677 [accelerated_algorithm]: 3.482e-05 [shard]: 2.80002e-06 [meta_shard_fg_expand]: 8.58001e-06 [shard_inline]: 2.166e-05 [merge_send_recv]: 2.148e-05 [auto_parallel]: 2.12e-05 [parallel]: 1.161e-05 [flash_sp]: 4.53001e-06 [merge_comm]: 1.316e-05 [allreduce_fusion]: 1.226e-05 [matmul_add_comm_reduction]: 2.419e-05 [allreduce_slice_to_reducescatter]: 1.45999e-06 [virtual_shard_identity]: 2.372e-05 [virtual_dataset]: 2.091e-05 [get_grad_eliminate_]: 2.121e-05 [virtual_output]: 1.989e-05 [merge_forward]: 1.37e-05 [cell_reuse_recompute_pass]: 3.56999e-06 [offload_activation]: 2.503e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.365e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 3.641e-05 [set_forward_comm_id_for_comm_node_pass]: 1.395e-05 [meta_fg_expand]: 9.44e-06 [flash_sp_send_recv_attached]: 2.00002e-06 [receive_attached]: 2.79999e-06 [after_resolve]: 2.811e-05 [a_after_grad]: 3.364e-05 [renormalize]: 6.00121e-08 [add_forward_monad_depend]: 3.25e-06 [auto_monad_grad]: 2.83998e-06 [auto_monad_eliminator]: 6.696e-05 [cse]: 8.271e-05 [a_3]: 0.00014093 [py_interpret_to_execute_after_opt_a]: 3.33e-05 [slice_cell_reuse_recomputed_activation]: 2.25002e-06 [rewriter_after_opt_a]: 0.00088287 [convert_after_rewriter]: 2.67e-05 [order_py_execute_after_rewriter]: 1.478e-05 [mutable_eliminate]: 0.00080573 [opt_b]: 0.00076934, [1] [Cycle 1]: 0.00075973, [7] [b_1]: 0.00055196 [b_2]: 2.493e-05 [updatestate_depend_eliminate]: 1.864e-05 [updatestate_assign_eliminate]: 1.215e-05 [updatestate_loads_eliminate]: 1.45e-05 [renormalize]: 1.07e-06 [cse]: 8.726e-05 [optimize_parallel_all_gather_comm]: 3.876e-05 [overlap_param_gather]: 2.39001e-06 [cconv]: 4.147e-05 [loop_unroll]: 0.00054848 [opt_after_cconv]: 0.00029937, [1] [Cycle 1]: 0.00029074, [7] [c_1]: 0.00012722 [parameter_eliminate]: 4.65999e-06 [updatestate_depend_eliminate]: 1.951e-05 [updatestate_assign_eliminate]: 1.131e-05 [updatestate_loads_eliminate]: 1.342e-05 [cse]: 7.561e-05 [renormalize]: 4.19997e-07 [remove_dup_value]: 9.837e-05 [tuple_transform]: 0.00025532, [1] [Cycle 1]: 0.00024916, [4] [d_1]: 0.00019736 [none_parameter_eliminate]: 2.64999e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 2.435e-05 [partial_unused_args_eliminate]: 1.96e-06 [add_recomputation]: 0.00016795 [cse_after_recomputation]: 7.816e-05, [1] [Cycle 1]: 7.043e-05, [1] [cse]: 6.144e-05 [environ_conv]: 2.512e-05 [swap_dp_allreduce_reducescatter]: 2.002e-05 [bias_add_comm_swap]: 2.68e-06 [label_micro_interleaved_index]: 6.12001e-06 [label_fine_grained_interleaved_index]: 2.61e-06 [merge_cast_opt]: 1.47999e-06 [slice_recompute_activation]: 2.18998e-06 [micro_interleaved_order_control]: 2.48e-06 [assign_add_opt]: 1.75001e-06 [ForceFp32Comm]: 8.80013e-07 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.49999e-06 [reorder_send_recv_between_fp_bp]: 3.36001e-06 [comm_op_add_attrs]: 1.09998e-06 [add_comm_op_reuse_tag]: 9.40025e-07 [interleave_split_concat_branches]: 1.29e-06 [interleave_parallel_branches]: 1.37e-06 [overlap_opt_shard_in_pipeline]: 1.17e-06 [overlap_opt_shard_grad_in_pipeline]: 1.68002e-06 [control_data_broadcast_order]: 3.98e-05 [grouped_pairwise_exchange_alltoall]: 1.92001e-06 [offloading_packed_experts]: 1.19e-05 [overlap_recompute_and_grad_model_parallel]: 1.053e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.22999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.21e-06 [overlap_grad_ring_attention]: 8.80001e-06 [overlap_grad_flash_sp]: 5.202e-05 [begin_end_overlap_inline]: 8.2e-07 [split_matmul_comm_elemetwise]: 2.26998e-06 [split_layernorm_comm]: 1.60999e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.0005316, [1] [Cycle 1]: 0.0005257, [6] [build]: 0.00029363 [elim_shapecalc]: 3.675e-05 [elim_not_effective]: 5.26e-05 [opt_reshape]: 3.348e-05 [fold_const_symbol]: 5.554e-05 [renormalize]: 3.19997e-07 [detach_backward]: 2.53e-06 [pipeline_parallel_scheduler]: 1.45999e-06 [auto_monad_reorder]: 6.637e-05 [get_jit_bprop_graph]: 2.29001e-06 [rewriter_after_jit_bprop_graph]: 8.02e-06 [opt_after_jit_grad]: 0.00065513 [validate]: 0.00012762 Sums bootstrap : 0.000940s : 0.15% type_inference : 0.569290s : 89.71% event_method : 0.000211s : 0.03% auto_monad : 0.000731s : 0.12% graph_reusing : 0.000049s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000191s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000060s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000242s : 0.04% 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 : 0.000284s : 0.04% optimize.rewriter_before_opt_a : 0.000787s : 0.12% optimize.opt_a.expand_dump_flag : 0.000020s : 0.00% optimize.opt_a.switch_simplify : 0.000838s : 0.13% optimize.opt_a.loop_unroll : 0.000341s : 0.05% optimize.opt_a.a_1 : 0.009830s : 1.55% optimize.opt_a.with_stream_mark : 0.000095s : 0.01% optimize.opt_a.recompute_prepare : 0.000066s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000034s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001139s : 0.18% optimize.opt_a.accelerated_algorithm : 0.000098s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000026s : 0.00% optimize.opt_a.shard_inline : 0.000046s : 0.01% optimize.opt_a.merge_send_recv : 0.000043s : 0.01% optimize.opt_a.auto_parallel : 0.000043s : 0.01% optimize.opt_a.parallel : 0.000045s : 0.01% optimize.opt_a.flash_sp : 0.000021s : 0.00% optimize.opt_a.merge_comm : 0.000027s : 0.00% optimize.opt_a.allreduce_fusion : 0.000025s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000046s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000051s : 0.01% optimize.opt_a.virtual_dataset : 0.000044s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000043s : 0.01% optimize.opt_a.virtual_output : 0.000042s : 0.01% optimize.opt_a.merge_forward : 0.000027s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000089s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000076s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.00% optimize.opt_a.meta_fg_expand : 0.000027s : 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 : 0.000057s : 0.01% optimize.opt_a.a_after_grad : 0.000070s : 0.01% optimize.opt_a.renormalize : 0.040444s : 6.37% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000156s : 0.02% optimize.opt_a.cse : 0.001924s : 0.30% optimize.opt_a.a_3 : 0.000318s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000883s : 0.14% optimize.convert_after_rewriter : 0.000027s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000806s : 0.13% optimize.opt_b.b_1 : 0.000552s : 0.09% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000087s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000039s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000548s : 0.09% optimize.opt_after_cconv.c_1 : 0.000127s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000076s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000098s : 0.02% optimize.tuple_transform.d_1 : 0.000197s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000168s : 0.03% optimize.cse_after_recomputation.cse : 0.000061s : 0.01% optimize.environ_conv : 0.000025s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 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 : 0.000040s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 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 : 0.000052s : 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 : 0.000294s : 0.05% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000037s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000053s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000033s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000056s : 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 : 0.000066s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000655s : 0.10% validate : 0.000128s : 0.02% Time group info: ------[substitution.] 0.003425 569 0.53% : 0.000018s : 8: substitution.depend_value_elim 0.43% : 0.000015s : 14: substitution.elim_not_effective 0.56% : 0.000019s : 12: substitution.float_tuple_getitem_switch 0.71% : 0.000024s : 14: substitution.fold_const_symbol 0.43% : 0.000015s : 17: substitution.graph_param_transform 69.18% : 0.002370s : 71: substitution.inline 0.39% : 0.000013s : 29: substitution.j_node_and_user_rematch 0.97% : 0.000033s : 6: substitution.less_batch_normalization 1.72% : 0.000059s : 2: substitution.list_to_tuple_eliminator_ 0.17% : 0.000006s : 6: substitution.load_eliminater 0.93% : 0.000032s : 21: substitution.minmaximum_grad 0.24% : 0.000008s : 2: substitution.opt_reshape 0.61% : 0.000021s : 29: substitution.remove_not_recompute_node 0.23% : 0.000008s : 4: substitution.replace_old_param 1.82% : 0.000062s : 18: substitution.reshape_eliminate 1.38% : 0.000047s : 24: substitution.switch_simplify 4.32% : 0.000148s : 51: substitution.tuple_list_convert_item_index_to_positive 2.34% : 0.000080s : 51: substitution.tuple_list_get_item_const_eliminator 3.00% : 0.000103s : 51: substitution.tuple_list_get_item_depend_reorder 5.82% : 0.000199s : 73: substitution.tuple_list_get_item_eliminator 2.96% : 0.000102s : 51: substitution.tuple_list_get_set_item_eliminator 0.68% : 0.000023s : 6: substitution.updatestate_pure_node_eliminater 0.56% : 0.000019s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.568921 2 91.04% : 0.517950s : 1: type_inference.infer 8.96% : 0.050970s : 1: type_inference.specialize ------[replace.] 0.001113 115 4.00% : 0.000044s : 5: replace.depend_value_elim 56.25% : 0.000626s : 71: replace.inline 3.89% : 0.000043s : 2: replace.list_to_tuple_eliminator_ 26.76% : 0.000298s : 24: replace.switch_simplify 9.10% : 0.000101s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002453 115 0.09% : 0.000002s : 5: match.depend_value_elim 94.84% : 0.002326s : 71: match.inline 2.30% : 0.000056s : 2: match.list_to_tuple_eliminator_ 1.44% : 0.000035s : 24: match.switch_simplify 1.33% : 0.000033s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001618 9701 1.22% : 0.000020s : 123: predicate.accumulaten_eliminater 0.37% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.49% : 0.000008s : 58: predicate.addn_check_dump 1.14% : 0.000018s : 123: predicate.addn_zero_filter 1.10% : 0.000018s : 123: predicate.adjust_all_reduce_mul_add 2.33% : 0.000038s : 181: predicate.arithmetic_simplify 1.22% : 0.000020s : 123: predicate.cast_eliminate 0.31% : 0.000005s : 34: predicate.check_bprop_eliminate 0.50% : 0.000008s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.61% : 0.000010s : 61: predicate.depend_value_elim 1.22% : 0.000020s : 123: predicate.dict_get_item_const_eliminator 1.32% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.13% : 0.000018s : 123: predicate.dict_set_item_eliminator 0.41% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.09% : 0.000001s : 17: predicate.elim_not_effective 0.23% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.29% : 0.000021s : 140: predicate.environ_add_const_eliminate 1.35% : 0.000022s : 140: predicate.environ_get_add_eliminate 1.24% : 0.000020s : 140: predicate.environ_get_depend_swap 1.80% : 0.000029s : 198: predicate.environ_get_eliminate 1.28% : 0.000021s : 140: predicate.environ_get_set_eliminate 1.92% : 0.000031s : 209: predicate.exchange_switch_depend_value 2.86% : 0.000046s : 209: predicate.float_depend_g_call 0.50% : 0.000008s : 58: predicate.float_environ_get_switch 0.70% : 0.000011s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.36% : 0.000006s : 35: predicate.get_grad_eliminate 0.10% : 0.000002s : 17: predicate.graph_param_transform 0.53% : 0.000009s : 58: predicate.incorporate_call 0.49% : 0.000008s : 58: predicate.incorporate_call_switch 5.96% : 0.000096s : 459: predicate.inline 0.46% : 0.000007s : 35: predicate.inline_without_move 0.15% : 0.000002s : 35: predicate.j_node_and_user_rematch 0.51% : 0.000008s : 36: predicate.less_batch_normalization 1.76% : 0.000028s : 172: predicate.list_to_tuple_eliminator_ 2.66% : 0.000043s : 295: predicate.load_eliminater 0.42% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.43% : 0.000055s : 314: predicate.loop_unroll_before_grad 1.56% : 0.000025s : 157: predicate.make_slice_get_slice_eliminator 0.51% : 0.000008s : 58: predicate.merge_addn 0.30% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.31% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.16% : 0.000019s : 123: predicate.minmaximum_grad 0.43% : 0.000007s : 17: predicate.mutable_eliminate 0.22% : 0.000003s : 17: predicate.opt_reshape 0.20% : 0.000003s : 17: predicate.parallel_virtual_node 3.17% : 0.000051s : 209: predicate.partial_defer_inline 1.53% : 0.000025s : 155: predicate.partial_eliminate 1.13% : 0.000018s : 123: predicate.print_const_string_wrapper 0.50% : 0.000008s : 53: predicate.reduce_all_const_elim 1.52% : 0.000025s : 123: predicate.reduce_eliminate 2.62% : 0.000042s : 295: predicate.redundant_stop_gradient_eliminater 0.19% : 0.000003s : 35: predicate.remove_not_recompute_node 1.10% : 0.000018s : 172: predicate.replace_applicator 0.19% : 0.000003s : 35: predicate.replace_old_param 0.10% : 0.000002s : 17: predicate.reset_defer_inline 1.27% : 0.000021s : 123: predicate.reshape_eliminate 0.31% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.19% : 0.000003s : 17: predicate.row_tensor_eliminate 0.48% : 0.000008s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.40% : 0.000006s : 35: predicate.shard_identity_eliminate 0.35% : 0.000006s : 34: predicate.special_op_eliminate 0.63% : 0.000010s : 58: predicate.specialize_transform 0.44% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.13% : 0.000034s : 209: predicate.switch_defer_inline 2.34% : 0.000038s : 243: predicate.switch_layer_defer_inline 6.90% : 0.000112s : 646: predicate.switch_simplify 1.19% : 0.000019s : 123: predicate.tile_eliminate 1.17% : 0.000019s : 123: predicate.transpose_eliminate 1.71% : 0.000028s : 157: predicate.tuple_list_convert_item_index_to_positive 1.89% : 0.000030s : 157: predicate.tuple_list_get_item_const_eliminator 1.59% : 0.000026s : 157: predicate.tuple_list_get_item_depend_reorder 3.19% : 0.000052s : 228: predicate.tuple_list_get_item_eliminator 1.73% : 0.000028s : 157: predicate.tuple_list_get_set_item_eliminator 2.30% : 0.000037s : 215: predicate.tuple_list_set_item_eliminator 1.62% : 0.000026s : 170: predicate.tuple_to_list_eliminator_ 2.64% : 0.000043s : 295: predicate.updatestate_pure_node_eliminater 3.20% : 0.000052s : 353: predicate.updatestate_useless_node_eliminater 0.16% : 0.000003s : 17: predicate.value_based_eliminate 0.35% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.35% : 0.000006s : 35: predicate.virtual_output_eliminate 0.16% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.19% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.015447 133 58.82% : 0.009086s : 53: func_graph_cloner_run.FuncGraphClonerGraph 41.18% : 0.006361s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.763878 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.69% : 0.005243s : 1: add_attr 0.68% : 0.005225s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.02% : 0.000175s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.10% : 0.000745s : 1: auto_monad 0.01% : 0.000072s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.13% : 0.000980s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000043s : 1: control_data_broadcast_order 0.00% : 0.000032s : 1: convert_after_rewriter 0.01% : 0.000082s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.03% : 0.000224s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000056s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.07% : 0.000558s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.11% : 0.000816s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.01% : 0.000039s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000043s : 1: opt.transform.mutable_eliminate 1.70% : 0.013001s : 95: opt.transform.opt_a 0.02% : 0.000125s : 1: opt.transform.opt_after_cconv 0.01% : 0.000077s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000543s : 28: opt.transform.opt_b 0.03% : 0.000218s : 2: opt.transform.opt_trans_graph 0.02% : 0.000172s : 4: opt.transform.symbol_engine_opt 7.47% : 0.057039s : 1: opt_a 0.04% : 0.000303s : 1: opt_after_cconv 0.09% : 0.000667s : 1: opt_after_jit_grad 0.10% : 0.000773s : 1: opt_b 8.28% : 0.063231s : 1: optimize 0.01% : 0.000044s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.01% : 0.000056s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 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% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.03% : 0.000251s : 1: pre_auto_parallel 0.04% : 0.000294s : 1: py_interpret_to_execute 0.01% : 0.000039s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000105s : 1: remove_dup_value 4.50% : 0.034366s : 1: renormalize.infer 0.79% : 0.006057s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.12% : 0.000895s : 1: rewriter_after_opt_a 0.10% : 0.000797s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000536s : 1: symbol_engine_optimizer 0.03% : 0.000260s : 1: tuple_transform 74.53% : 0.569326s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape2-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape2-1],max_mem:352.0M [WARNING] ME(166698:281473598218032,MainProcess):2026-01-29-17:38:36.871.268 [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 = 0.381037, [21] [bootstrap]: 0.0010661 [type_inference]: 0.330111 [event_method]: 0.00025856 [auto_monad]: 0.00105444 [graph_reusing]: 6.869e-05 [inline]: 3.23998e-06 [add_attr]: 0.00638679, [1] [add_attr_with_inline]: 0.00636679, [1] [Cycle 1]: 0.00034573, [2] [tag_attr]: 0.00022347 [meta_addattr_fg_expand]: 6.832e-05 [parallel-infer-symbol]: 4.1e-06 [pre_auto_parallel]: 0.00028009 [insert-virtual-dataset]: 3.29001e-06 [parallel-infer-symbol-second]: 1.36998e-06 [dataset_repeat_opt]: 2.44001e-06 [pipeline_split]: 1.54e-06 [optimize]: 0.0403941, [53] [py_interpret_to_execute]: 0.00027849 [rewriter_before_opt_a]: 0.00096877 [opt_a]: 0.0334676, [2] [Cycle 1]: 0.0310368, [45] [expand_dump_flag]: 3.406e-05 [switch_simplify]: 0.00095829 [loop_unroll]: 0.00036204 [a_1]: 0.0107127 [with_stream_mark]: 6.446e-05 [recompute_prepare]: 4.278e-05 [updatestate_depend_eliminate]: 2.194e-05 [updatestate_assign_eliminate]: 4.084e-05 [updatestate_loads_eliminate]: 1.977e-05 [parameter_eliminate]: 2.98e-06 [a_2]: 0.00086039 [accelerated_algorithm]: 6.392e-05 [shard]: 2.69001e-06 [meta_shard_fg_expand]: 2.905e-05 [shard_inline]: 2.384e-05 [merge_send_recv]: 2.063e-05 [auto_parallel]: 2.136e-05 [parallel]: 4.061e-05 [flash_sp]: 1.719e-05 [merge_comm]: 1.476e-05 [allreduce_fusion]: 1.281e-05 [matmul_add_comm_reduction]: 2.266e-05 [allreduce_slice_to_reducescatter]: 1.24e-06 [virtual_shard_identity]: 2.723e-05 [virtual_dataset]: 2.321e-05 [get_grad_eliminate_]: 2.163e-05 [virtual_output]: 2.129e-05 [merge_forward]: 1.384e-05 [cell_reuse_recompute_pass]: 2.49999e-06 [offload_activation]: 2.359e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.849e-05 [merge_recompute_call_nodes]: 2.07999e-06 [before_grad]: 4.12e-05 [set_forward_comm_id_for_comm_node_pass]: 1.495e-05 [meta_fg_expand]: 1.898e-05 [flash_sp_send_recv_attached]: 5.69e-06 [receive_attached]: 2.75002e-06 [after_resolve]: 3.127e-05 [a_after_grad]: 3.672e-05 [renormalize]: 0.0136811 [add_forward_monad_depend]: 1.388e-05 [auto_monad_grad]: 3.41001e-06 [auto_monad_eliminator]: 9.397e-05 [cse]: 0.00287192 [a_3]: 0.00018828 [Cycle 2]: 0.00240992, [45] [expand_dump_flag]: 3.88999e-06 [switch_simplify]: 2.738e-05 [loop_unroll]: 2.202e-05 [a_1]: 0.00068041 [with_stream_mark]: 4.36e-05 [recompute_prepare]: 2.578e-05 [updatestate_depend_eliminate]: 1.687e-05 [updatestate_assign_eliminate]: 1.187e-05 [updatestate_loads_eliminate]: 1.374e-05 [parameter_eliminate]: 2.52001e-06 [a_2]: 0.00042806 [accelerated_algorithm]: 3.572e-05 [shard]: 2.50002e-06 [meta_shard_fg_expand]: 1.092e-05 [shard_inline]: 2.178e-05 [merge_send_recv]: 2.321e-05 [auto_parallel]: 2.091e-05 [parallel]: 1.262e-05 [flash_sp]: 5.20001e-06 [merge_comm]: 1.364e-05 [allreduce_fusion]: 1.216e-05 [matmul_add_comm_reduction]: 2.549e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 2.631e-05 [virtual_dataset]: 2.062e-05 [get_grad_eliminate_]: 2.174e-05 [virtual_output]: 2.083e-05 [merge_forward]: 1.472e-05 [cell_reuse_recompute_pass]: 3.34001e-06 [offload_activation]: 2.627e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.598e-05 [merge_recompute_call_nodes]: 1.64e-06 [before_grad]: 3.744e-05 [set_forward_comm_id_for_comm_node_pass]: 1.557e-05 [meta_fg_expand]: 1.094e-05 [flash_sp_send_recv_attached]: 2.54001e-06 [receive_attached]: 2.51e-06 [after_resolve]: 2.991e-05 [a_after_grad]: 3.367e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 5.53002e-06 [auto_monad_grad]: 3.28e-06 [auto_monad_eliminator]: 8.265e-05 [cse]: 0.00010045 [a_3]: 0.00014899 [py_interpret_to_execute_after_opt_a]: 4.098e-05 [slice_cell_reuse_recomputed_activation]: 2.63e-06 [rewriter_after_opt_a]: 0.00096224 [convert_after_rewriter]: 3.346e-05 [order_py_execute_after_rewriter]: 1.59e-05 [mutable_eliminate]: 0.00088379 [opt_b]: 0.00090781, [1] [Cycle 1]: 0.00089777, [7] [b_1]: 0.00056721 [b_2]: 2.751e-05 [updatestate_depend_eliminate]: 9.441e-05 [updatestate_assign_eliminate]: 1.345e-05 [updatestate_loads_eliminate]: 1.536e-05 [renormalize]: 1.07e-06 [cse]: 0.00012261 [optimize_parallel_all_gather_comm]: 4.993e-05 [overlap_param_gather]: 3.94002e-06 [cconv]: 4.601e-05 [loop_unroll]: 0.00067506 [opt_after_cconv]: 0.00032558, [1] [Cycle 1]: 0.00031542, [7] [c_1]: 0.00013093 [parameter_eliminate]: 6.52001e-06 [updatestate_depend_eliminate]: 2.166e-05 [updatestate_assign_eliminate]: 1.147e-05 [updatestate_loads_eliminate]: 1.465e-05 [cse]: 8.96e-05 [renormalize]: 6.49976e-07 [remove_dup_value]: 0.00011699 [tuple_transform]: 0.00026728, [1] [Cycle 1]: 0.00025974, [4] [d_1]: 0.00020876 [none_parameter_eliminate]: 2.78998e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 2.396e-05 [partial_unused_args_eliminate]: 1.94e-06 [add_recomputation]: 0.00015953 [cse_after_recomputation]: 7.787e-05, [1] [Cycle 1]: 7.139e-05, [1] [cse]: 6.419e-05 [environ_conv]: 3.005e-05 [swap_dp_allreduce_reducescatter]: 1.89e-05 [bias_add_comm_swap]: 3.97998e-06 [label_micro_interleaved_index]: 6.21e-06 [label_fine_grained_interleaved_index]: 3.37002e-06 [merge_cast_opt]: 1.32e-06 [slice_recompute_activation]: 2.22001e-06 [micro_interleaved_order_control]: 2.56998e-06 [assign_add_opt]: 1.49e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 2.46e-06 [reorder_send_recv_between_fp_bp]: 2.61999e-06 [comm_op_add_attrs]: 1.07e-06 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.23002e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 2.89001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.26998e-06 [control_data_broadcast_order]: 3.997e-05 [grouped_pairwise_exchange_alltoall]: 1.62001e-06 [offloading_packed_experts]: 1.196e-05 [overlap_recompute_and_grad_model_parallel]: 9.89001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.33002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37e-06 [overlap_recompute_comm]: 2.34999e-06 [overlap_grad_ring_attention]: 9.10001e-06 [overlap_grad_flash_sp]: 5.326e-05 [begin_end_overlap_inline]: 7.80012e-07 [split_matmul_comm_elemetwise]: 2.42001e-06 [split_layernorm_comm]: 1.87999e-06 [handle_group_info]: 1.04e-06 [symbol_engine_optimizer]: 0.00055596, [1] [Cycle 1]: 0.00055006, [6] [build]: 0.00031065 [elim_shapecalc]: 3.951e-05 [elim_not_effective]: 5.625e-05 [opt_reshape]: 3.451e-05 [fold_const_symbol]: 5.969e-05 [renormalize]: 4.2998e-07 [detach_backward]: 3.58e-06 [pipeline_parallel_scheduler]: 1.47001e-06 [auto_monad_reorder]: 6.937e-05 [get_jit_bprop_graph]: 2.36e-06 [rewriter_after_jit_bprop_graph]: 6.87002e-06 [opt_after_jit_grad]: 0.00081846 [validate]: 0.00013178 Sums bootstrap : 0.001066s : 0.29% type_inference : 0.330111s : 88.44% event_method : 0.000259s : 0.07% auto_monad : 0.001054s : 0.28% graph_reusing : 0.000069s : 0.02% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000223s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000068s : 0.02% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000280s : 0.08% 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 : 0.000278s : 0.07% optimize.rewriter_before_opt_a : 0.000969s : 0.26% optimize.opt_a.expand_dump_flag : 0.000038s : 0.01% optimize.opt_a.switch_simplify : 0.000986s : 0.26% optimize.opt_a.loop_unroll : 0.000384s : 0.10% optimize.opt_a.a_1 : 0.011393s : 3.05% optimize.opt_a.with_stream_mark : 0.000108s : 0.03% optimize.opt_a.recompute_prepare : 0.000069s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000039s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000053s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000034s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001288s : 0.35% optimize.opt_a.accelerated_algorithm : 0.000100s : 0.03% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000040s : 0.01% optimize.opt_a.shard_inline : 0.000046s : 0.01% optimize.opt_a.merge_send_recv : 0.000044s : 0.01% optimize.opt_a.auto_parallel : 0.000042s : 0.01% optimize.opt_a.parallel : 0.000053s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.01% optimize.opt_a.merge_comm : 0.000028s : 0.01% optimize.opt_a.allreduce_fusion : 0.000025s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000048s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000054s : 0.01% optimize.opt_a.virtual_dataset : 0.000044s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000043s : 0.01% optimize.opt_a.virtual_output : 0.000042s : 0.01% optimize.opt_a.merge_forward : 0.000029s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000050s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000094s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000079s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.01% optimize.opt_a.meta_fg_expand : 0.000030s : 0.01% 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 : 0.000061s : 0.02% optimize.opt_a.a_after_grad : 0.000070s : 0.02% optimize.opt_a.renormalize : 0.013681s : 3.67% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.01% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000177s : 0.05% optimize.opt_a.cse : 0.002972s : 0.80% optimize.opt_a.a_3 : 0.000337s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000041s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000962s : 0.26% optimize.convert_after_rewriter : 0.000033s : 0.01% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.000884s : 0.24% optimize.opt_b.b_1 : 0.000567s : 0.15% optimize.opt_b.b_2 : 0.000028s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000094s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000123s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000050s : 0.01% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000046s : 0.01% optimize.loop_unroll : 0.000675s : 0.18% optimize.opt_after_cconv.c_1 : 0.000131s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000022s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.cse : 0.000090s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000117s : 0.03% optimize.tuple_transform.d_1 : 0.000209s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000160s : 0.04% optimize.cse_after_recomputation.cse : 0.000064s : 0.02% optimize.environ_conv : 0.000030s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 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 : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000040s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 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 : 0.000053s : 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 : 0.000311s : 0.08% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000056s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000035s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000060s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000069s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000818s : 0.22% validate : 0.000132s : 0.04% Time group info: ------[substitution.] 0.004306 569 0.43% : 0.000018s : 8: substitution.depend_value_elim 0.41% : 0.000018s : 14: substitution.elim_not_effective 0.47% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.65% : 0.000028s : 14: substitution.fold_const_symbol 0.38% : 0.000016s : 17: substitution.graph_param_transform 71.51% : 0.003079s : 71: substitution.inline 0.31% : 0.000013s : 29: substitution.j_node_and_user_rematch 0.76% : 0.000033s : 6: substitution.less_batch_normalization 1.57% : 0.000067s : 2: substitution.list_to_tuple_eliminator_ 0.15% : 0.000006s : 6: substitution.load_eliminater 0.93% : 0.000040s : 21: substitution.minmaximum_grad 0.20% : 0.000008s : 2: substitution.opt_reshape 0.49% : 0.000021s : 29: substitution.remove_not_recompute_node 0.18% : 0.000008s : 4: substitution.replace_old_param 1.67% : 0.000072s : 18: substitution.reshape_eliminate 1.38% : 0.000059s : 24: substitution.switch_simplify 3.85% : 0.000166s : 51: substitution.tuple_list_convert_item_index_to_positive 2.55% : 0.000110s : 51: substitution.tuple_list_get_item_const_eliminator 2.93% : 0.000126s : 51: substitution.tuple_list_get_item_depend_reorder 5.22% : 0.000225s : 73: substitution.tuple_list_get_item_eliminator 2.74% : 0.000118s : 51: substitution.tuple_list_get_set_item_eliminator 0.67% : 0.000029s : 6: substitution.updatestate_pure_node_eliminater 0.54% : 0.000023s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.329437 2 92.04% : 0.303203s : 1: type_inference.infer 7.96% : 0.026234s : 1: type_inference.specialize ------[replace.] 0.001316 115 4.06% : 0.000053s : 5: replace.depend_value_elim 54.98% : 0.000723s : 71: replace.inline 3.78% : 0.000050s : 2: replace.list_to_tuple_eliminator_ 28.46% : 0.000374s : 24: replace.switch_simplify 8.72% : 0.000115s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003176 115 0.07% : 0.000002s : 5: match.depend_value_elim 95.44% : 0.003031s : 71: match.inline 2.02% : 0.000064s : 2: match.list_to_tuple_eliminator_ 1.37% : 0.000043s : 24: match.switch_simplify 1.10% : 0.000035s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001720 9701 1.04% : 0.000018s : 123: predicate.accumulaten_eliminater 0.36% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.53% : 0.000009s : 58: predicate.addn_check_dump 1.12% : 0.000019s : 123: predicate.addn_zero_filter 1.01% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.23% : 0.000038s : 181: predicate.arithmetic_simplify 1.17% : 0.000020s : 123: predicate.cast_eliminate 0.29% : 0.000005s : 34: predicate.check_bprop_eliminate 0.51% : 0.000009s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 1.56% : 0.000027s : 61: predicate.depend_value_elim 1.19% : 0.000021s : 123: predicate.dict_get_item_const_eliminator 1.21% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.06% : 0.000018s : 123: predicate.dict_set_item_eliminator 0.43% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.22% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.25% : 0.000022s : 140: predicate.environ_add_const_eliminate 1.26% : 0.000022s : 140: predicate.environ_get_add_eliminate 1.24% : 0.000021s : 140: predicate.environ_get_depend_swap 1.82% : 0.000031s : 198: predicate.environ_get_eliminate 1.19% : 0.000020s : 140: predicate.environ_get_set_eliminate 1.82% : 0.000031s : 209: predicate.exchange_switch_depend_value 2.66% : 0.000046s : 209: predicate.float_depend_g_call 0.50% : 0.000009s : 58: predicate.float_environ_get_switch 0.73% : 0.000013s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.32% : 0.000006s : 35: predicate.get_grad_eliminate 0.09% : 0.000002s : 17: predicate.graph_param_transform 0.51% : 0.000009s : 58: predicate.incorporate_call 0.46% : 0.000008s : 58: predicate.incorporate_call_switch 5.85% : 0.000101s : 459: predicate.inline 0.42% : 0.000007s : 35: predicate.inline_without_move 0.16% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.46% : 0.000008s : 36: predicate.less_batch_normalization 1.80% : 0.000031s : 172: predicate.list_to_tuple_eliminator_ 2.51% : 0.000043s : 295: predicate.load_eliminater 0.43% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.82% : 0.000066s : 314: predicate.loop_unroll_before_grad 1.54% : 0.000027s : 157: predicate.make_slice_get_slice_eliminator 0.54% : 0.000009s : 58: predicate.merge_addn 0.28% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.28% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.21% : 0.000021s : 123: predicate.minmaximum_grad 0.49% : 0.000009s : 17: predicate.mutable_eliminate 0.23% : 0.000004s : 17: predicate.opt_reshape 0.19% : 0.000003s : 17: predicate.parallel_virtual_node 3.65% : 0.000063s : 209: predicate.partial_defer_inline 1.43% : 0.000025s : 155: predicate.partial_eliminate 1.09% : 0.000019s : 123: predicate.print_const_string_wrapper 0.46% : 0.000008s : 53: predicate.reduce_all_const_elim 1.59% : 0.000027s : 123: predicate.reduce_eliminate 2.50% : 0.000043s : 295: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 35: predicate.remove_not_recompute_node 1.08% : 0.000019s : 172: predicate.replace_applicator 0.18% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.24% : 0.000021s : 123: predicate.reshape_eliminate 0.33% : 0.000006s : 34: predicate.row_tensor_add_zeros_like 0.19% : 0.000003s : 17: predicate.row_tensor_eliminate 0.62% : 0.000011s : 34: predicate.same_eliminate 0.20% : 0.000003s : 40: predicate.set_cell_output_no_recompute 0.41% : 0.000007s : 35: predicate.shard_identity_eliminate 0.32% : 0.000005s : 34: predicate.special_op_eliminate 0.59% : 0.000010s : 58: predicate.specialize_transform 0.39% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.34% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.06% : 0.000035s : 209: predicate.switch_defer_inline 2.36% : 0.000041s : 243: predicate.switch_layer_defer_inline 7.57% : 0.000130s : 646: predicate.switch_simplify 1.12% : 0.000019s : 123: predicate.tile_eliminate 1.20% : 0.000021s : 123: predicate.transpose_eliminate 1.72% : 0.000030s : 157: predicate.tuple_list_convert_item_index_to_positive 1.79% : 0.000031s : 157: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000028s : 157: predicate.tuple_list_get_item_depend_reorder 3.04% : 0.000052s : 228: predicate.tuple_list_get_item_eliminator 1.71% : 0.000029s : 157: predicate.tuple_list_get_set_item_eliminator 2.22% : 0.000038s : 215: predicate.tuple_list_set_item_eliminator 1.58% : 0.000027s : 170: predicate.tuple_to_list_eliminator_ 2.43% : 0.000042s : 295: predicate.updatestate_pure_node_eliminater 3.08% : 0.000053s : 353: predicate.updatestate_useless_node_eliminater 0.16% : 0.000003s : 17: predicate.value_based_eliminate 0.33% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.33% : 0.000006s : 35: predicate.virtual_output_eliminate 0.15% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.18% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.020647 133 54.61% : 0.011276s : 53: func_graph_cloner_run.FuncGraphClonerGraph 45.39% : 0.009371s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.457302 209 0.00% : 0.000003s : 1: ForceFp32Comm 1.40% : 0.006393s : 1: add_attr 1.39% : 0.006372s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.04% : 0.000165s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.24% : 0.001080s : 1: auto_monad 0.02% : 0.000075s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.25% : 0.001127s : 1: bootstrap 0.01% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000044s : 1: control_data_broadcast_order 0.01% : 0.000040s : 1: convert_after_rewriter 0.02% : 0.000081s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000034s : 1: environ_conv 0.06% : 0.000271s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.02% : 0.000077s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.15% : 0.000686s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.20% : 0.000897s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.01% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000053s : 1: opt.transform.mutable_eliminate 3.26% : 0.014920s : 95: opt.transform.opt_a 0.03% : 0.000129s : 1: opt.transform.opt_after_cconv 0.02% : 0.000083s : 1: opt.transform.opt_after_jit_grad 0.12% : 0.000554s : 28: opt.transform.opt_b 0.05% : 0.000229s : 2: opt.transform.opt_trans_graph 0.04% : 0.000183s : 4: opt.transform.symbol_engine_opt 7.32% : 0.033473s : 1: opt_a 0.07% : 0.000330s : 1: opt_after_cconv 0.18% : 0.000831s : 1: opt_after_jit_grad 0.20% : 0.000913s : 1: opt_b 8.83% : 0.040402s : 1: optimize 0.01% : 0.000055s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.01% : 0.000057s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.06% : 0.000291s : 1: pre_auto_parallel 0.06% : 0.000289s : 1: py_interpret_to_execute 0.01% : 0.000045s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000123s : 1: remove_dup_value 1.46% : 0.006677s : 1: renormalize.infer 1.53% : 0.006984s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.21% : 0.000979s : 1: rewriter_after_opt_a 0.22% : 0.000989s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.12% : 0.000561s : 1: symbol_engine_optimizer 0.06% : 0.000272s : 1: tuple_transform 72.19% : 0.330148s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_bf16_0[True-mstype0-k_n_shape2-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_bf16_0[True-mstype0-k_n_shape2-16],max_mem:352.0M =============================== 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 ================== 6 passed, 25 warnings in 140.47s (0:02:20) ==================