==================================================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_002/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 3 items test_matmul_split.py [WARNING] ME(160728:281472910737200,MainProcess):2026-01-29-17:37:22.961.238 [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 = 2.52959, [21] [bootstrap]: 0.00078315 [type_inference]: 2.26278 [event_method]: 0.00020475 [auto_monad]: 0.0008734 [graph_reusing]: 4.79e-05 [inline]: 3.21001e-06 [add_attr]: 0.12578, [1] [add_attr_with_inline]: 0.125744, [1] [Cycle 1]: 0.00038725, [2] [tag_attr]: 0.00019809 [meta_addattr_fg_expand]: 4.96e-05 [parallel-infer-symbol]: 4.32e-06 [pre_auto_parallel]: 0.00026691 [insert-virtual-dataset]: 3.53e-06 [parallel-infer-symbol-second]: 1.84998e-06 [dataset_repeat_opt]: 2.69001e-06 [pipeline_split]: 2.22999e-06 [optimize]: 0.137657, [53] [py_interpret_to_execute]: 0.00021421 [rewriter_before_opt_a]: 0.00082352 [opt_a]: 0.130789, [2] [Cycle 1]: 0.128666, [45] [expand_dump_flag]: 1.673e-05 [switch_simplify]: 0.00080926 [loop_unroll]: 0.00025431 [a_1]: 0.0805825 [with_stream_mark]: 6.74e-05 [recompute_prepare]: 4.518e-05 [updatestate_depend_eliminate]: 2.24e-05 [updatestate_assign_eliminate]: 5.404e-05 [updatestate_loads_eliminate]: 2.086e-05 [parameter_eliminate]: 3.26999e-06 [a_2]: 0.00090606 [accelerated_algorithm]: 7.496e-05 [shard]: 2.43e-06 [meta_shard_fg_expand]: 2.538e-05 [shard_inline]: 2.592e-05 [merge_send_recv]: 2.027e-05 [auto_parallel]: 2.158e-05 [parallel]: 9.978e-05 [flash_sp]: 1.508e-05 [merge_comm]: 1.723e-05 [allreduce_fusion]: 1.349e-05 [matmul_add_comm_reduction]: 2.275e-05 [allreduce_slice_to_reducescatter]: 1.28002e-06 [virtual_shard_identity]: 3.08e-05 [virtual_dataset]: 2.383e-05 [get_grad_eliminate_]: 2.355e-05 [virtual_output]: 2.297e-05 [merge_forward]: 1.28e-05 [cell_reuse_recompute_pass]: 2.85002e-06 [offload_activation]: 2.541e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.188e-05 [merge_recompute_call_nodes]: 1.86998e-06 [before_grad]: 4.346e-05 [set_forward_comm_id_for_comm_node_pass]: 1.688e-05 [meta_fg_expand]: 2.092e-05 [flash_sp_send_recv_attached]: 6.84999e-06 [receive_attached]: 1.615e-05 [after_resolve]: 3.646e-05 [a_after_grad]: 3.835e-05 [renormalize]: 0.0434215 [add_forward_monad_depend]: 2.343e-05 [auto_monad_grad]: 3.46999e-06 [auto_monad_eliminator]: 8.93e-05 [cse]: 0.00092327 [a_3]: 0.00016898 [Cycle 2]: 0.00210314, [45] [expand_dump_flag]: 3.50998e-06 [switch_simplify]: 2.334e-05 [loop_unroll]: 1.951e-05 [a_1]: 0.00062183 [with_stream_mark]: 3.384e-05 [recompute_prepare]: 2.101e-05 [updatestate_depend_eliminate]: 1.517e-05 [updatestate_assign_eliminate]: 1.107e-05 [updatestate_loads_eliminate]: 1.418e-05 [parameter_eliminate]: 2.69999e-06 [a_2]: 0.00029791 [accelerated_algorithm]: 2.858e-05 [shard]: 2.86999e-06 [meta_shard_fg_expand]: 7.35e-06 [shard_inline]: 1.973e-05 [merge_send_recv]: 1.989e-05 [auto_parallel]: 1.877e-05 [parallel]: 1.064e-05 [flash_sp]: 5.29e-06 [merge_comm]: 1.219e-05 [allreduce_fusion]: 1.213e-05 [matmul_add_comm_reduction]: 2.072e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 2.154e-05 [virtual_dataset]: 1.811e-05 [get_grad_eliminate_]: 1.859e-05 [virtual_output]: 1.832e-05 [merge_forward]: 1.194e-05 [cell_reuse_recompute_pass]: 2.94001e-06 [offload_activation]: 2.233e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.016e-05 [merge_recompute_call_nodes]: 2.49001e-06 [before_grad]: 3.396e-05 [set_forward_comm_id_for_comm_node_pass]: 1.251e-05 [meta_fg_expand]: 8.58001e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 2.60002e-06 [after_resolve]: 2.64e-05 [a_after_grad]: 3.139e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.03e-06 [auto_monad_grad]: 2.12001e-06 [auto_monad_eliminator]: 6.193e-05 [cse]: 0.0001802 [a_3]: 0.00013518 [py_interpret_to_execute_after_opt_a]: 5.671e-05 [slice_cell_reuse_recomputed_activation]: 2.70002e-06 [rewriter_after_opt_a]: 0.00097086 [convert_after_rewriter]: 4.848e-05 [order_py_execute_after_rewriter]: 1.457e-05 [mutable_eliminate]: 0.00107544 [opt_b]: 0.00074323, [1] [Cycle 1]: 0.00073406, [7] [b_1]: 0.00051681 [b_2]: 2.11e-05 [updatestate_depend_eliminate]: 1.859e-05 [updatestate_assign_eliminate]: 1.104e-05 [updatestate_loads_eliminate]: 1.439e-05 [renormalize]: 7.40023e-07 [cse]: 0.0001096 [optimize_parallel_all_gather_comm]: 4.361e-05 [overlap_param_gather]: 3.001e-05 [cconv]: 4.375e-05 [loop_unroll]: 0.00053975 [opt_after_cconv]: 0.0003083, [1] [Cycle 1]: 0.0003005, [7] [c_1]: 0.00013127 [parameter_eliminate]: 4.10998e-06 [updatestate_depend_eliminate]: 1.939e-05 [updatestate_assign_eliminate]: 1.402e-05 [updatestate_loads_eliminate]: 1.405e-05 [cse]: 7.886e-05 [renormalize]: 4.90021e-07 [remove_dup_value]: 9.654e-05 [tuple_transform]: 0.00024173, [1] [Cycle 1]: 0.00023656, [4] [d_1]: 0.00019227 [none_parameter_eliminate]: 2.21e-06 [renormalize]: 3.09985e-07 [switch_simplify]: 2.176e-05 [partial_unused_args_eliminate]: 2.18002e-06 [add_recomputation]: 0.00015854 [cse_after_recomputation]: 6.77e-05, [1] [Cycle 1]: 6.276e-05, [1] [cse]: 5.608e-05 [environ_conv]: 3.474e-05 [swap_dp_allreduce_reducescatter]: 1.747e-05 [bias_add_comm_swap]: 2.76999e-06 [label_micro_interleaved_index]: 5.63997e-06 [label_fine_grained_interleaved_index]: 2.93e-06 [merge_cast_opt]: 1.74e-06 [slice_recompute_activation]: 2.54001e-06 [micro_interleaved_order_control]: 2.57001e-06 [assign_add_opt]: 1.24998e-06 [ForceFp32Comm]: 1.27999e-06 [remove_cast_before_assign_add]: 1.12e-06 [full_micro_interleaved_order_control]: 2.65997e-06 [reorder_send_recv_between_fp_bp]: 2.65997e-06 [comm_op_add_attrs]: 1.36002e-06 [add_comm_op_reuse_tag]: 1.10999e-06 [interleave_split_concat_branches]: 1.14e-06 [interleave_parallel_branches]: 1.20999e-06 [overlap_opt_shard_in_pipeline]: 4.766e-05 [overlap_opt_shard_grad_in_pipeline]: 2.66e-06 [control_data_broadcast_order]: 3.775e-05 [grouped_pairwise_exchange_alltoall]: 1.72999e-06 [offloading_packed_experts]: 9.79e-06 [overlap_recompute_and_grad_model_parallel]: 1.042e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.45999e-06 [overlap_recompute_comm]: 2.71e-06 [overlap_grad_ring_attention]: 9.54e-06 [overlap_grad_flash_sp]: 8.889e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.56e-06 [split_layernorm_comm]: 1.87999e-06 [handle_group_info]: 1.22e-06 [symbol_engine_optimizer]: 0.00075952, [1] [Cycle 1]: 0.00075341, [6] [build]: 0.00050297 [elim_shapecalc]: 3.065e-05 [elim_not_effective]: 6.965e-05 [opt_reshape]: 2.999e-05 [fold_const_symbol]: 5.66e-05 [renormalize]: 3.80009e-07 [detach_backward]: 3.06999e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 6.688e-05 [get_jit_bprop_graph]: 1.77001e-06 [rewriter_after_jit_bprop_graph]: 5.94e-06 [opt_after_jit_grad]: 0.00069755 [validate]: 0.00014959 Sums bootstrap : 0.000783s : 0.03% type_inference : 2.262779s : 94.18% event_method : 0.000205s : 0.01% auto_monad : 0.000873s : 0.04% graph_reusing : 0.000048s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000198s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000050s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000267s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000214s : 0.01% optimize.rewriter_before_opt_a : 0.000824s : 0.03% optimize.opt_a.expand_dump_flag : 0.000020s : 0.00% optimize.opt_a.switch_simplify : 0.000833s : 0.03% optimize.opt_a.loop_unroll : 0.000274s : 0.01% optimize.opt_a.a_1 : 0.081204s : 3.38% optimize.opt_a.with_stream_mark : 0.000101s : 0.00% optimize.opt_a.recompute_prepare : 0.000066s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000065s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000035s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001204s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000104s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000033s : 0.00% optimize.opt_a.shard_inline : 0.000046s : 0.00% optimize.opt_a.merge_send_recv : 0.000040s : 0.00% optimize.opt_a.auto_parallel : 0.000040s : 0.00% optimize.opt_a.parallel : 0.000110s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000029s : 0.00% optimize.opt_a.allreduce_fusion : 0.000026s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000043s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.00% optimize.opt_a.virtual_dataset : 0.000042s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.00% optimize.opt_a.virtual_output : 0.000041s : 0.00% optimize.opt_a.merge_forward : 0.000025s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000092s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000077s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000029s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000019s : 0.00% optimize.opt_a.after_resolve : 0.000063s : 0.00% optimize.opt_a.a_after_grad : 0.000070s : 0.00% optimize.opt_a.renormalize : 0.043422s : 1.81% optimize.opt_a.add_forward_monad_depend : 0.000026s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000151s : 0.01% optimize.opt_a.cse : 0.001103s : 0.05% optimize.opt_a.a_3 : 0.000304s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000057s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000971s : 0.04% optimize.convert_after_rewriter : 0.000048s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.001075s : 0.04% optimize.opt_b.b_1 : 0.000517s : 0.02% optimize.opt_b.b_2 : 0.000021s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000110s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000044s : 0.00% optimize.overlap_param_gather : 0.000030s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000540s : 0.02% optimize.opt_after_cconv.c_1 : 0.000131s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000079s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000097s : 0.00% optimize.tuple_transform.d_1 : 0.000192s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000159s : 0.01% optimize.cse_after_recomputation.cse : 0.000056s : 0.00% optimize.environ_conv : 0.000035s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000017s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000048s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000038s : 0.00% 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 : 0.000089s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000503s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000031s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000070s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000030s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000057s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000067s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000698s : 0.03% validate : 0.000150s : 0.01% Time group info: ------[substitution.] 0.003474 569 0.52% : 0.000018s : 8: substitution.depend_value_elim 1.00% : 0.000035s : 14: substitution.elim_not_effective 0.61% : 0.000021s : 12: substitution.float_tuple_getitem_switch 0.77% : 0.000027s : 14: substitution.fold_const_symbol 0.46% : 0.000016s : 17: substitution.graph_param_transform 65.23% : 0.002266s : 71: substitution.inline 0.42% : 0.000014s : 29: substitution.j_node_and_user_rematch 1.17% : 0.000041s : 6: substitution.less_batch_normalization 1.93% : 0.000067s : 2: substitution.list_to_tuple_eliminator_ 0.18% : 0.000006s : 6: substitution.load_eliminater 2.18% : 0.000076s : 21: substitution.minmaximum_grad 0.18% : 0.000006s : 2: substitution.opt_reshape 0.59% : 0.000020s : 29: substitution.remove_not_recompute_node 0.26% : 0.000009s : 4: substitution.replace_old_param 1.59% : 0.000055s : 18: substitution.reshape_eliminate 3.25% : 0.000113s : 24: substitution.switch_simplify 4.27% : 0.000148s : 51: substitution.tuple_list_convert_item_index_to_positive 2.17% : 0.000075s : 51: substitution.tuple_list_get_item_const_eliminator 2.98% : 0.000103s : 51: substitution.tuple_list_get_item_depend_reorder 6.14% : 0.000213s : 73: substitution.tuple_list_get_item_eliminator 2.91% : 0.000101s : 51: substitution.tuple_list_get_set_item_eliminator 0.58% : 0.000020s : 6: substitution.updatestate_pure_node_eliminater 0.62% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.262407 2 99.28% : 2.246141s : 1: type_inference.infer 0.72% : 0.016266s : 1: type_inference.specialize ------[replace.] 0.001334 115 4.04% : 0.000054s : 5: replace.depend_value_elim 62.30% : 0.000831s : 71: replace.inline 3.42% : 0.000046s : 2: replace.list_to_tuple_eliminator_ 22.53% : 0.000300s : 24: replace.switch_simplify 7.71% : 0.000103s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002428 115 0.09% : 0.000002s : 5: match.depend_value_elim 91.61% : 0.002224s : 71: match.inline 2.63% : 0.000064s : 2: match.list_to_tuple_eliminator_ 4.15% : 0.000101s : 24: match.switch_simplify 1.51% : 0.000037s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001574 9701 1.11% : 0.000018s : 123: predicate.accumulaten_eliminater 0.35% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.56% : 0.000009s : 58: predicate.addn_check_dump 1.18% : 0.000019s : 123: predicate.addn_zero_filter 1.06% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.16% : 0.000034s : 181: predicate.arithmetic_simplify 1.55% : 0.000024s : 123: predicate.cast_eliminate 0.30% : 0.000005s : 34: predicate.check_bprop_eliminate 0.55% : 0.000009s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.71% : 0.000011s : 61: predicate.depend_value_elim 1.19% : 0.000019s : 123: predicate.dict_get_item_const_eliminator 1.30% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.11% : 0.000017s : 123: predicate.dict_set_item_eliminator 0.41% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.09% : 0.000001s : 17: predicate.elim_not_effective 0.19% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.23% : 0.000019s : 140: predicate.environ_add_const_eliminate 1.25% : 0.000020s : 140: predicate.environ_get_add_eliminate 1.18% : 0.000019s : 140: predicate.environ_get_depend_swap 1.81% : 0.000029s : 198: predicate.environ_get_eliminate 1.22% : 0.000019s : 140: predicate.environ_get_set_eliminate 1.93% : 0.000030s : 209: predicate.exchange_switch_depend_value 2.92% : 0.000046s : 209: predicate.float_depend_g_call 0.62% : 0.000010s : 58: predicate.float_environ_get_switch 0.74% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.09% : 0.000001s : 17: predicate.fold_const_symbol 0.35% : 0.000006s : 35: predicate.get_grad_eliminate 0.11% : 0.000002s : 17: predicate.graph_param_transform 0.56% : 0.000009s : 58: predicate.incorporate_call 0.50% : 0.000008s : 58: predicate.incorporate_call_switch 6.01% : 0.000095s : 459: predicate.inline 0.45% : 0.000007s : 35: predicate.inline_without_move 0.16% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.50% : 0.000008s : 36: predicate.less_batch_normalization 1.62% : 0.000025s : 172: predicate.list_to_tuple_eliminator_ 2.55% : 0.000040s : 295: predicate.load_eliminater 0.29% : 0.000005s : 17: predicate.loop_unroll_after_grad 3.09% : 0.000049s : 314: predicate.loop_unroll_before_grad 1.52% : 0.000024s : 157: predicate.make_slice_get_slice_eliminator 0.56% : 0.000009s : 58: predicate.merge_addn 0.30% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.29% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.18% : 0.000019s : 123: predicate.minmaximum_grad 1.31% : 0.000021s : 17: predicate.mutable_eliminate 0.17% : 0.000003s : 17: predicate.opt_reshape 0.19% : 0.000003s : 17: predicate.parallel_virtual_node 3.58% : 0.000056s : 209: predicate.partial_defer_inline 1.51% : 0.000024s : 155: predicate.partial_eliminate 1.10% : 0.000017s : 123: predicate.print_const_string_wrapper 0.54% : 0.000008s : 53: predicate.reduce_all_const_elim 1.73% : 0.000027s : 123: predicate.reduce_eliminate 2.59% : 0.000041s : 295: predicate.redundant_stop_gradient_eliminater 0.20% : 0.000003s : 35: predicate.remove_not_recompute_node 1.12% : 0.000018s : 172: predicate.replace_applicator 0.22% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.25% : 0.000020s : 123: predicate.reshape_eliminate 0.32% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.18% : 0.000003s : 17: predicate.row_tensor_eliminate 0.46% : 0.000007s : 34: predicate.same_eliminate 0.22% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.37% : 0.000006s : 35: predicate.shard_identity_eliminate 0.34% : 0.000005s : 34: predicate.special_op_eliminate 0.67% : 0.000011s : 58: predicate.specialize_transform 0.39% : 0.000006s : 34: predicate.split_environ_get_set_with_tuple_value 0.43% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.13% : 0.000033s : 209: predicate.switch_defer_inline 2.33% : 0.000037s : 243: predicate.switch_layer_defer_inline 6.62% : 0.000104s : 646: predicate.switch_simplify 1.10% : 0.000017s : 123: predicate.tile_eliminate 1.07% : 0.000017s : 123: predicate.transpose_eliminate 1.80% : 0.000028s : 157: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000028s : 157: predicate.tuple_list_get_item_const_eliminator 1.58% : 0.000025s : 157: predicate.tuple_list_get_item_depend_reorder 3.24% : 0.000051s : 228: predicate.tuple_list_get_item_eliminator 1.55% : 0.000024s : 157: predicate.tuple_list_get_set_item_eliminator 2.23% : 0.000035s : 215: predicate.tuple_list_set_item_eliminator 1.59% : 0.000025s : 170: predicate.tuple_to_list_eliminator_ 2.51% : 0.000040s : 295: predicate.updatestate_pure_node_eliminater 3.13% : 0.000049s : 353: predicate.updatestate_useless_node_eliminater 0.18% : 0.000003s : 17: predicate.value_based_eliminate 0.35% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.37% : 0.000006s : 35: predicate.virtual_output_eliminate 0.16% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.18% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.012911 135 62.51% : 0.008070s : 55: func_graph_cloner_run.FuncGraphClonerGraph 37.49% : 0.004841s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.921677 209 0.00% : 0.000004s : 1: ForceFp32Comm 4.31% : 0.125788s : 1: add_attr 4.30% : 0.125749s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000164s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000896s : 1: auto_monad 0.00% : 0.000072s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.03% : 0.000827s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000042s : 1: control_data_broadcast_order 0.00% : 0.000057s : 1: convert_after_rewriter 0.00% : 0.000071s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000039s : 1: environ_conv 0.01% : 0.000217s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000054s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000549s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.001089s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000084s : 1: opt.transform.mutable_eliminate 2.89% : 0.084350s : 95: opt.transform.opt_a 0.00% : 0.000130s : 1: opt.transform.opt_after_cconv 0.00% : 0.000071s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000506s : 28: opt.transform.opt_b 0.01% : 0.000211s : 2: opt.transform.opt_trans_graph 0.01% : 0.000181s : 4: opt.transform.symbol_engine_opt 4.48% : 0.130794s : 1: opt_a 0.01% : 0.000312s : 1: opt_after_cconv 0.02% : 0.000710s : 1: opt_after_jit_grad 0.03% : 0.000747s : 1: opt_b 4.71% : 0.137664s : 1: optimize 0.00% : 0.000048s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000093s : 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% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000052s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000035s : 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% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000281s : 1: pre_auto_parallel 0.01% : 0.000226s : 1: py_interpret_to_execute 0.00% : 0.000063s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000102s : 1: remove_dup_value 0.22% : 0.006387s : 1: renormalize.infer 1.27% : 0.037013s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000983s : 1: rewriter_after_opt_a 0.03% : 0.000842s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000021s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000763s : 1: symbol_engine_optimizer 0.01% : 0.000245s : 1: tuple_transform 77.45% : 2.262823s : 1: type_inference . [hook] pytest_runtest_teardown:test_dynamic_shape[input_shape0] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_dynamic_shape[input_shape0],max_mem:140.0M [WARNING] ME(160728:281472910737200,MainProcess):2026-01-29-17:38:15.606.286 [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 = 1.19574, [21] [bootstrap]: 0.00102609 [type_inference]: 1.07907 [event_method]: 0.00021832 [auto_monad]: 0.0007523 [graph_reusing]: 4.104e-05 [inline]: 3.48999e-06 [add_attr]: 0.00610335, [1] [add_attr_with_inline]: 0.00608321, [1] [Cycle 1]: 0.00040931, [2] [tag_attr]: 0.00029144 [meta_addattr_fg_expand]: 4.778e-05 [parallel-infer-symbol]: 4.27998e-06 [pre_auto_parallel]: 0.00025062 [insert-virtual-dataset]: 2.88e-06 [parallel-infer-symbol-second]: 1.14998e-06 [dataset_repeat_opt]: 2.71e-06 [pipeline_split]: 1.95001e-06 [optimize]: 0.106983, [53] [py_interpret_to_execute]: 0.00025314 [rewriter_before_opt_a]: 0.00078923 [opt_a]: 0.100159, [2] [Cycle 1]: 0.0868468, [45] [expand_dump_flag]: 3.044e-05 [switch_simplify]: 0.00081746 [loop_unroll]: 0.00030844 [a_1]: 0.0510591 [with_stream_mark]: 7.234e-05 [recompute_prepare]: 4.459e-05 [updatestate_depend_eliminate]: 2.006e-05 [updatestate_assign_eliminate]: 1.732e-05 [updatestate_loads_eliminate]: 1.944e-05 [parameter_eliminate]: 3.78999e-06 [a_2]: 0.00079663 [accelerated_algorithm]: 7.327e-05 [shard]: 2.66999e-06 [meta_shard_fg_expand]: 2.476e-05 [shard_inline]: 2.296e-05 [merge_send_recv]: 2.174e-05 [auto_parallel]: 2.195e-05 [parallel]: 4.177e-05 [flash_sp]: 1.658e-05 [merge_comm]: 1.356e-05 [allreduce_fusion]: 1.256e-05 [matmul_add_comm_reduction]: 2.337e-05 [allreduce_slice_to_reducescatter]: 8.09989e-07 [virtual_shard_identity]: 2.883e-05 [virtual_dataset]: 2.213e-05 [get_grad_eliminate_]: 2.012e-05 [virtual_output]: 2.029e-05 [merge_forward]: 1.222e-05 [cell_reuse_recompute_pass]: 2.61e-06 [offload_activation]: 2.46e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.956e-05 [merge_recompute_call_nodes]: 1.65001e-06 [before_grad]: 3.893e-05 [set_forward_comm_id_for_comm_node_pass]: 1.426e-05 [meta_fg_expand]: 1.473e-05 [flash_sp_send_recv_attached]: 6.83e-06 [receive_attached]: 2.76e-06 [after_resolve]: 3.231e-05 [a_after_grad]: 3.581e-05 [renormalize]: 0.0308687 [add_forward_monad_depend]: 2.273e-05 [auto_monad_grad]: 3.36001e-06 [auto_monad_eliminator]: 9.861e-05 [cse]: 0.00135068 [a_3]: 0.00021207 [Cycle 2]: 0.0132886, [45] [expand_dump_flag]: 4.4e-06 [switch_simplify]: 2.663e-05 [loop_unroll]: 2.192e-05 [a_1]: 0.00069001 [with_stream_mark]: 4.608e-05 [recompute_prepare]: 2.642e-05 [updatestate_depend_eliminate]: 1.664e-05 [updatestate_assign_eliminate]: 1.279e-05 [updatestate_loads_eliminate]: 0.0107377 [parameter_eliminate]: 9.79e-06 [a_2]: 0.00040811 [accelerated_algorithm]: 3.452e-05 [shard]: 4.33999e-06 [meta_shard_fg_expand]: 1.142e-05 [shard_inline]: 2.236e-05 [merge_send_recv]: 3.364e-05 [auto_parallel]: 2.545e-05 [parallel]: 1.29e-05 [flash_sp]: 6.29999e-06 [merge_comm]: 1.356e-05 [allreduce_fusion]: 1.219e-05 [matmul_add_comm_reduction]: 2.605e-05 [allreduce_slice_to_reducescatter]: 1.17e-06 [virtual_shard_identity]: 2.423e-05 [virtual_dataset]: 2.055e-05 [get_grad_eliminate_]: 2.012e-05 [virtual_output]: 2.047e-05 [merge_forward]: 1.273e-05 [cell_reuse_recompute_pass]: 3.23e-06 [offload_activation]: 2.597e-05 [cell_reuse_handle_not_recompute_node_pass]: 7.87e-05 [merge_recompute_call_nodes]: 2.62001e-06 [before_grad]: 4.181e-05 [set_forward_comm_id_for_comm_node_pass]: 1.598e-05 [meta_fg_expand]: 1.061e-05 [flash_sp_send_recv_attached]: 2.18998e-06 [receive_attached]: 3.01999e-06 [after_resolve]: 3.281e-05 [a_after_grad]: 3.357e-05 [renormalize]: 5.00004e-08 [add_forward_monad_depend]: 6.38e-06 [auto_monad_grad]: 3.4e-06 [auto_monad_eliminator]: 8.256e-05 [cse]: 0.00011139 [a_3]: 0.00014877 [py_interpret_to_execute_after_opt_a]: 3.782e-05 [slice_cell_reuse_recomputed_activation]: 2.64999e-06 [rewriter_after_opt_a]: 0.00094309 [convert_after_rewriter]: 3.721e-05 [order_py_execute_after_rewriter]: 1.482e-05 [mutable_eliminate]: 0.0008917 [opt_b]: 0.00094909, [1] [Cycle 1]: 0.00093858, [7] [b_1]: 0.00069368 [b_2]: 2.511e-05 [updatestate_depend_eliminate]: 2.346e-05 [updatestate_assign_eliminate]: 1.186e-05 [updatestate_loads_eliminate]: 1.472e-05 [renormalize]: 1.30999e-06 [cse]: 0.00010991 [optimize_parallel_all_gather_comm]: 4.806e-05 [overlap_param_gather]: 3.80998e-06 [cconv]: 4.435e-05 [loop_unroll]: 0.00071447 [opt_after_cconv]: 0.00031794, [1] [Cycle 1]: 0.00030536, [7] [c_1]: 0.00013042 [parameter_eliminate]: 6.84999e-06 [updatestate_depend_eliminate]: 2.067e-05 [updatestate_assign_eliminate]: 1.085e-05 [updatestate_loads_eliminate]: 1.333e-05 [cse]: 8.487e-05 [renormalize]: 8.00006e-07 [remove_dup_value]: 0.0001033 [tuple_transform]: 0.00026507, [1] [Cycle 1]: 0.00025938, [4] [d_1]: 0.00020902 [none_parameter_eliminate]: 2.63e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 2.307e-05 [partial_unused_args_eliminate]: 2.20002e-06 [add_recomputation]: 0.00016616 [cse_after_recomputation]: 8.209e-05, [1] [Cycle 1]: 7.275e-05, [1] [cse]: 6.242e-05 [environ_conv]: 2.623e-05 [swap_dp_allreduce_reducescatter]: 2.186e-05 [bias_add_comm_swap]: 3.56001e-06 [label_micro_interleaved_index]: 7.04001e-06 [label_fine_grained_interleaved_index]: 2.86999e-06 [merge_cast_opt]: 1.45001e-06 [slice_recompute_activation]: 2.32001e-06 [micro_interleaved_order_control]: 2.83e-06 [assign_add_opt]: 1.60999e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.26998e-06 [reorder_send_recv_between_fp_bp]: 2.99999e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.77001e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 3.61999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.36e-06 [control_data_broadcast_order]: 3.978e-05 [grouped_pairwise_exchange_alltoall]: 2.11e-06 [offloading_packed_experts]: 1.067e-05 [overlap_recompute_and_grad_model_parallel]: 1.086e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.19998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.72001e-06 [overlap_recompute_comm]: 2.53e-06 [overlap_grad_ring_attention]: 9.40001e-06 [overlap_grad_flash_sp]: 5.492e-05 [begin_end_overlap_inline]: 6.39993e-07 [split_matmul_comm_elemetwise]: 2.40002e-06 [split_layernorm_comm]: 1.91e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00056091, [1] [Cycle 1]: 0.00055368, [6] [build]: 0.0003128 [elim_shapecalc]: 3.856e-05 [elim_not_effective]: 5.661e-05 [opt_reshape]: 3.438e-05 [fold_const_symbol]: 5.906e-05 [renormalize]: 3.69997e-07 [detach_backward]: 3.03e-06 [pipeline_parallel_scheduler]: 1.42999e-06 [auto_monad_reorder]: 6.601e-05 [get_jit_bprop_graph]: 2.26998e-06 [rewriter_after_jit_bprop_graph]: 4.90001e-06 [opt_after_jit_grad]: 0.00079485 [validate]: 0.000112 Sums bootstrap : 0.001026s : 0.09% type_inference : 1.079074s : 90.82% event_method : 0.000218s : 0.02% auto_monad : 0.000752s : 0.06% graph_reusing : 0.000041s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000291s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000048s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000251s : 0.02% 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 : 0.000253s : 0.02% optimize.rewriter_before_opt_a : 0.000789s : 0.07% optimize.opt_a.expand_dump_flag : 0.000035s : 0.00% optimize.opt_a.switch_simplify : 0.000844s : 0.07% optimize.opt_a.loop_unroll : 0.000330s : 0.03% optimize.opt_a.a_1 : 0.051749s : 4.36% optimize.opt_a.with_stream_mark : 0.000118s : 0.01% optimize.opt_a.recompute_prepare : 0.000071s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.010757s : 0.91% optimize.opt_a.parameter_eliminate : 0.000014s : 0.00% optimize.opt_a.a_2 : 0.001205s : 0.10% optimize.opt_a.accelerated_algorithm : 0.000108s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000036s : 0.00% optimize.opt_a.shard_inline : 0.000045s : 0.00% optimize.opt_a.merge_send_recv : 0.000055s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000055s : 0.00% optimize.opt_a.flash_sp : 0.000023s : 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 : 0.000049s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000053s : 0.00% optimize.opt_a.virtual_dataset : 0.000043s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000040s : 0.00% optimize.opt_a.virtual_output : 0.000041s : 0.00% optimize.opt_a.merge_forward : 0.000025s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000051s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000128s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000081s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000030s : 0.00% optimize.opt_a.meta_fg_expand : 0.000025s : 0.00% 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 : 0.000065s : 0.01% optimize.opt_a.a_after_grad : 0.000069s : 0.01% optimize.opt_a.renormalize : 0.030869s : 2.60% optimize.opt_a.add_forward_monad_depend : 0.000029s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000181s : 0.02% optimize.opt_a.cse : 0.001462s : 0.12% optimize.opt_a.a_3 : 0.000361s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000943s : 0.08% optimize.convert_after_rewriter : 0.000037s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000892s : 0.08% optimize.opt_b.b_1 : 0.000694s : 0.06% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% 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 : 0.000110s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000048s : 0.00% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000714s : 0.06% optimize.opt_after_cconv.c_1 : 0.000130s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000021s : 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 : 0.000085s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000103s : 0.01% optimize.tuple_transform.d_1 : 0.000209s : 0.02% 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 : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000166s : 0.01% optimize.cse_after_recomputation.cse : 0.000062s : 0.01% optimize.environ_conv : 0.000026s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000022s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000004s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000040s : 0.00% 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000055s : 0.00% 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 : 0.000313s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000039s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000057s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000059s : 0.00% 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 : 0.000005s : 0.00% opt_after_jit_grad : 0.000795s : 0.07% validate : 0.000112s : 0.01% Time group info: ------[substitution.] 0.004337 569 0.40% : 0.000017s : 8: substitution.depend_value_elim 0.40% : 0.000017s : 14: substitution.elim_not_effective 0.45% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.66% : 0.000029s : 14: substitution.fold_const_symbol 0.35% : 0.000015s : 17: substitution.graph_param_transform 71.08% : 0.003082s : 71: substitution.inline 0.34% : 0.000015s : 29: substitution.j_node_and_user_rematch 0.94% : 0.000041s : 6: substitution.less_batch_normalization 1.50% : 0.000065s : 2: substitution.list_to_tuple_eliminator_ 0.15% : 0.000007s : 6: substitution.load_eliminater 0.90% : 0.000039s : 21: substitution.minmaximum_grad 0.22% : 0.000010s : 2: substitution.opt_reshape 0.51% : 0.000022s : 29: substitution.remove_not_recompute_node 0.24% : 0.000010s : 4: substitution.replace_old_param 1.86% : 0.000080s : 18: substitution.reshape_eliminate 1.11% : 0.000048s : 24: substitution.switch_simplify 3.95% : 0.000171s : 51: substitution.tuple_list_convert_item_index_to_positive 2.20% : 0.000096s : 51: substitution.tuple_list_get_item_const_eliminator 2.84% : 0.000123s : 51: substitution.tuple_list_get_item_depend_reorder 5.97% : 0.000259s : 73: substitution.tuple_list_get_item_eliminator 2.76% : 0.000120s : 51: substitution.tuple_list_get_set_item_eliminator 0.61% : 0.000026s : 6: substitution.updatestate_pure_node_eliminater 0.57% : 0.000025s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.078666 2 93.82% : 1.011974s : 1: type_inference.infer 6.18% : 0.066692s : 1: type_inference.specialize ------[replace.] 0.001407 115 3.85% : 0.000054s : 5: replace.depend_value_elim 62.73% : 0.000883s : 71: replace.inline 3.33% : 0.000047s : 2: replace.list_to_tuple_eliminator_ 22.24% : 0.000313s : 24: replace.switch_simplify 7.85% : 0.000110s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003180 115 0.07% : 0.000002s : 5: match.depend_value_elim 95.29% : 0.003030s : 71: match.inline 1.95% : 0.000062s : 2: match.list_to_tuple_eliminator_ 1.19% : 0.000038s : 24: match.switch_simplify 1.50% : 0.000048s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.041915 9701 0.04% : 0.000019s : 123: predicate.accumulaten_eliminater 0.01% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.02% : 0.000008s : 58: predicate.addn_check_dump 0.04% : 0.000019s : 123: predicate.addn_zero_filter 0.04% : 0.000019s : 123: predicate.adjust_all_reduce_mul_add 0.09% : 0.000038s : 181: predicate.arithmetic_simplify 0.05% : 0.000020s : 123: predicate.cast_eliminate 0.01% : 0.000005s : 34: predicate.check_bprop_eliminate 0.02% : 0.000008s : 58: predicate.compare_switch_simplify 0.00% : 0.000001s : 17: predicate.const_output_eliminate 0.02% : 0.000010s : 61: predicate.depend_value_elim 0.05% : 0.000020s : 123: predicate.dict_get_item_const_eliminator 0.05% : 0.000022s : 123: predicate.dict_get_item_eliminator 0.05% : 0.000021s : 123: predicate.dict_set_item_eliminator 0.02% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.00% : 0.000002s : 17: predicate.elim_not_effective 0.01% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 0.06% : 0.000025s : 140: predicate.environ_add_const_eliminate 0.05% : 0.000023s : 140: predicate.environ_get_add_eliminate 0.05% : 0.000022s : 140: predicate.environ_get_depend_swap 0.07% : 0.000030s : 198: predicate.environ_get_eliminate 0.05% : 0.000021s : 140: predicate.environ_get_set_eliminate 0.08% : 0.000035s : 209: predicate.exchange_switch_depend_value 0.12% : 0.000049s : 209: predicate.float_depend_g_call 0.02% : 0.000008s : 58: predicate.float_environ_get_switch 0.03% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.00% : 0.000001s : 17: predicate.fold_const_symbol 0.01% : 0.000006s : 35: predicate.get_grad_eliminate 0.00% : 0.000002s : 17: predicate.graph_param_transform 0.02% : 0.000008s : 58: predicate.incorporate_call 0.02% : 0.000007s : 58: predicate.incorporate_call_switch 96.17% : 0.040310s : 459: predicate.inline 0.02% : 0.000007s : 35: predicate.inline_without_move 0.01% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.02% : 0.000008s : 36: predicate.less_batch_normalization 0.07% : 0.000029s : 172: predicate.list_to_tuple_eliminator_ 0.10% : 0.000042s : 295: predicate.load_eliminater 0.02% : 0.000007s : 17: predicate.loop_unroll_after_grad 0.12% : 0.000050s : 314: predicate.loop_unroll_before_grad 0.06% : 0.000025s : 157: predicate.make_slice_get_slice_eliminator 0.02% : 0.000009s : 58: predicate.merge_addn 0.01% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.01% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.04% : 0.000019s : 123: predicate.minmaximum_grad 0.02% : 0.000007s : 17: predicate.mutable_eliminate 0.01% : 0.000003s : 17: predicate.opt_reshape 0.01% : 0.000003s : 17: predicate.parallel_virtual_node 0.15% : 0.000061s : 209: predicate.partial_defer_inline 0.06% : 0.000024s : 155: predicate.partial_eliminate 0.05% : 0.000022s : 123: predicate.print_const_string_wrapper 0.02% : 0.000008s : 53: predicate.reduce_all_const_elim 0.07% : 0.000028s : 123: predicate.reduce_eliminate 0.11% : 0.000044s : 295: predicate.redundant_stop_gradient_eliminater 0.01% : 0.000003s : 35: predicate.remove_not_recompute_node 0.04% : 0.000018s : 172: predicate.replace_applicator 0.01% : 0.000003s : 35: predicate.replace_old_param 0.00% : 0.000002s : 17: predicate.reset_defer_inline 0.05% : 0.000022s : 123: predicate.reshape_eliminate 0.01% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.01% : 0.000003s : 17: predicate.row_tensor_eliminate 0.02% : 0.000008s : 34: predicate.same_eliminate 0.01% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.01% : 0.000006s : 35: predicate.shard_identity_eliminate 0.01% : 0.000006s : 34: predicate.special_op_eliminate 0.03% : 0.000011s : 58: predicate.specialize_transform 0.02% : 0.000008s : 34: predicate.split_environ_get_set_with_tuple_value 0.01% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.01% : 0.000003s : 17: predicate.switch_call_monad_eliminater 0.08% : 0.000034s : 209: predicate.switch_defer_inline 0.10% : 0.000040s : 243: predicate.switch_layer_defer_inline 0.27% : 0.000112s : 646: predicate.switch_simplify 0.05% : 0.000021s : 123: predicate.tile_eliminate 0.04% : 0.000018s : 123: predicate.transpose_eliminate 0.07% : 0.000030s : 157: predicate.tuple_list_convert_item_index_to_positive 0.07% : 0.000029s : 157: predicate.tuple_list_get_item_const_eliminator 0.07% : 0.000029s : 157: predicate.tuple_list_get_item_depend_reorder 0.13% : 0.000056s : 228: predicate.tuple_list_get_item_eliminator 0.07% : 0.000029s : 157: predicate.tuple_list_get_set_item_eliminator 0.09% : 0.000037s : 215: predicate.tuple_list_set_item_eliminator 0.06% : 0.000026s : 170: predicate.tuple_to_list_eliminator_ 0.18% : 0.000076s : 295: predicate.updatestate_pure_node_eliminater 0.14% : 0.000058s : 353: predicate.updatestate_useless_node_eliminater 0.01% : 0.000003s : 17: predicate.value_based_eliminate 0.01% : 0.000005s : 35: predicate.virtual_dataset_eliminate 0.01% : 0.000006s : 35: predicate.virtual_output_eliminate 0.01% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.01% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.066467 135 85.93% : 0.057116s : 55: func_graph_cloner_run.FuncGraphClonerGraph 14.07% : 0.009351s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.395831 209 0.00% : 0.000003s : 1: ForceFp32Comm 0.44% : 0.006112s : 1: add_attr 0.44% : 0.006088s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000197s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.06% : 0.000769s : 1: auto_monad 0.01% : 0.000074s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.08% : 0.001089s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000045s : 1: control_data_broadcast_order 0.00% : 0.000045s : 1: convert_after_rewriter 0.01% : 0.000086s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000030s : 1: environ_conv 0.02% : 0.000231s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000049s : 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% : 0.000007s : 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 0.05% : 0.000731s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.07% : 0.000908s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000046s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 3.94% : 0.055032s : 95: opt.transform.opt_a 0.01% : 0.000129s : 1: opt.transform.opt_after_cconv 0.01% : 0.000083s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000668s : 28: opt.transform.opt_b 0.02% : 0.000229s : 2: opt.transform.opt_trans_graph 0.01% : 0.000182s : 4: opt.transform.symbol_engine_opt 7.18% : 0.100164s : 1: opt_a 0.02% : 0.000322s : 1: opt_after_cconv 0.06% : 0.000812s : 1: opt_after_jit_grad 0.07% : 0.000953s : 1: opt_b 7.67% : 0.106992s : 1: optimize 0.00% : 0.000053s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 1: order_py_execute_after_rewriter 0.00% : 0.000059s : 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% : 0.000007s : 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% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000026s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000259s : 1: pre_auto_parallel 0.02% : 0.000263s : 1: py_interpret_to_execute 0.00% : 0.000045s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000108s : 1: remove_dup_value 0.53% : 0.007401s : 1: renormalize.infer 1.68% : 0.023442s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000962s : 1: rewriter_after_opt_a 0.06% : 0.000812s : 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% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000565s : 1: symbol_engine_optimizer 0.02% : 0.000269s : 1: tuple_transform 77.31% : 1.079105s : 1: type_inference . [hook] pytest_runtest_teardown:test_dynamic_shape[input_shape1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_dynamic_shape[input_shape1],max_mem:196.0M [WARNING] ME(160728:281472910737200,MainProcess):2026-01-29-17:38:56.945.816 [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 = 1.09977, [21] [bootstrap]: 0.00083675 [type_inference]: 0.927585 [event_method]: 0.00020273 [auto_monad]: 0.00073503 [graph_reusing]: 4.268e-05 [inline]: 2.86e-06 [add_attr]: 0.06942, [1] [add_attr_with_inline]: 0.0693988, [1] [Cycle 1]: 0.00032278, [2] [tag_attr]: 0.00021331 [meta_addattr_fg_expand]: 4.544e-05 [parallel-infer-symbol]: 4.80999e-06 [pre_auto_parallel]: 0.00025024 [insert-virtual-dataset]: 2.79001e-06 [parallel-infer-symbol-second]: 1.27999e-06 [dataset_repeat_opt]: 2.81999e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.0994391, [53] [py_interpret_to_execute]: 0.00024894 [rewriter_before_opt_a]: 0.00077877 [opt_a]: 0.0930191, [2] [Cycle 1]: 0.0908109, [45] [expand_dump_flag]: 3.209e-05 [switch_simplify]: 0.00077753 [loop_unroll]: 0.00030637 [a_1]: 0.00979502 [with_stream_mark]: 6.396e-05 [recompute_prepare]: 4.043e-05 [updatestate_depend_eliminate]: 2.055e-05 [updatestate_assign_eliminate]: 1.634e-05 [updatestate_loads_eliminate]: 1.902e-05 [parameter_eliminate]: 2.56e-06 [a_2]: 0.00079382 [accelerated_algorithm]: 6.22e-05 [shard]: 2.92002e-06 [meta_shard_fg_expand]: 2.291e-05 [shard_inline]: 2.234e-05 [merge_send_recv]: 1.919e-05 [auto_parallel]: 2.083e-05 [parallel]: 3.911e-05 [flash_sp]: 1.536e-05 [merge_comm]: 1.391e-05 [allreduce_fusion]: 1.232e-05 [matmul_add_comm_reduction]: 2.304e-05 [allreduce_slice_to_reducescatter]: 1.07998e-06 [virtual_shard_identity]: 2.691e-05 [virtual_dataset]: 2.254e-05 [get_grad_eliminate_]: 2.049e-05 [virtual_output]: 2.132e-05 [merge_forward]: 1.246e-05 [cell_reuse_recompute_pass]: 2.18002e-06 [offload_activation]: 2.375e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.486e-05 [merge_recompute_call_nodes]: 1.53002e-06 [before_grad]: 3.783e-05 [set_forward_comm_id_for_comm_node_pass]: 1.418e-05 [meta_fg_expand]: 1.481e-05 [flash_sp_send_recv_attached]: 5.90002e-06 [receive_attached]: 2.49001e-06 [after_resolve]: 2.867e-05 [a_after_grad]: 3.577e-05 [renormalize]: 0.0472111 [add_forward_monad_depend]: 2.286e-05 [auto_monad_grad]: 3.98999e-06 [auto_monad_eliminator]: 0.00010128 [cse]: 0.0303768 [a_3]: 0.00018272 [Cycle 2]: 0.00218961, [45] [expand_dump_flag]: 4.46002e-06 [switch_simplify]: 2.572e-05 [loop_unroll]: 2.152e-05 [a_1]: 0.0006536 [with_stream_mark]: 4.276e-05 [recompute_prepare]: 2.335e-05 [updatestate_depend_eliminate]: 1.754e-05 [updatestate_assign_eliminate]: 1.189e-05 [updatestate_loads_eliminate]: 1.435e-05 [parameter_eliminate]: 3.12002e-06 [a_2]: 0.00030603 [accelerated_algorithm]: 3.313e-05 [shard]: 2.89999e-06 [meta_shard_fg_expand]: 8.90999e-06 [shard_inline]: 2.251e-05 [merge_send_recv]: 2.102e-05 [auto_parallel]: 2.058e-05 [parallel]: 1.144e-05 [flash_sp]: 4.62e-06 [merge_comm]: 1.308e-05 [allreduce_fusion]: 1.234e-05 [matmul_add_comm_reduction]: 2.343e-05 [allreduce_slice_to_reducescatter]: 9.30013e-07 [virtual_shard_identity]: 2.413e-05 [virtual_dataset]: 1.931e-05 [get_grad_eliminate_]: 2.168e-05 [virtual_output]: 1.933e-05 [merge_forward]: 1.325e-05 [cell_reuse_recompute_pass]: 3.38999e-06 [offload_activation]: 2.648e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.667e-05 [merge_recompute_call_nodes]: 1.86998e-06 [before_grad]: 3.87e-05 [set_forward_comm_id_for_comm_node_pass]: 1.393e-05 [meta_fg_expand]: 8.95999e-06 [flash_sp_send_recv_attached]: 1.94999e-06 [receive_attached]: 3.04001e-06 [after_resolve]: 3.128e-05 [a_after_grad]: 3.484e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 4.67e-06 [auto_monad_grad]: 2.74001e-06 [auto_monad_eliminator]: 7.258e-05 [cse]: 9.248e-05 [a_3]: 0.00014081 [py_interpret_to_execute_after_opt_a]: 3.735e-05 [slice_cell_reuse_recomputed_activation]: 2.52001e-06 [rewriter_after_opt_a]: 0.00099397 [convert_after_rewriter]: 3.365e-05 [order_py_execute_after_rewriter]: 1.464e-05 [mutable_eliminate]: 0.00084309 [opt_b]: 0.0007695, [1] [Cycle 1]: 0.00075966, [7] [b_1]: 0.00054203 [b_2]: 2.255e-05 [updatestate_depend_eliminate]: 1.963e-05 [updatestate_assign_eliminate]: 1.142e-05 [updatestate_loads_eliminate]: 1.459e-05 [renormalize]: 1.02e-06 [cse]: 0.00010315 [optimize_parallel_all_gather_comm]: 4.832e-05 [overlap_param_gather]: 6.27001e-06 [cconv]: 4.483e-05 [loop_unroll]: 0.00060031 [opt_after_cconv]: 0.00029551, [1] [Cycle 1]: 0.00028711, [7] [c_1]: 0.00012589 [parameter_eliminate]: 5.54e-06 [updatestate_depend_eliminate]: 1.816e-05 [updatestate_assign_eliminate]: 1.101e-05 [updatestate_loads_eliminate]: 1.273e-05 [cse]: 7.415e-05 [renormalize]: 7.2e-07 [remove_dup_value]: 0.00010489 [tuple_transform]: 0.00025459, [1] [Cycle 1]: 0.0002492, [4] [d_1]: 0.00020428 [none_parameter_eliminate]: 2.64999e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 2.196e-05 [partial_unused_args_eliminate]: 2.14999e-06 [add_recomputation]: 0.00015466 [cse_after_recomputation]: 7.101e-05, [1] [Cycle 1]: 6.444e-05, [1] [cse]: 5.633e-05 [environ_conv]: 2.543e-05 [swap_dp_allreduce_reducescatter]: 1.969e-05 [bias_add_comm_swap]: 3.33e-06 [label_micro_interleaved_index]: 6.47001e-06 [label_fine_grained_interleaved_index]: 2.88e-06 [merge_cast_opt]: 1.76e-06 [slice_recompute_activation]: 2.24999e-06 [micro_interleaved_order_control]: 2.79001e-06 [assign_add_opt]: 1.19e-06 [ForceFp32Comm]: 1.31002e-06 [remove_cast_before_assign_add]: 1.47001e-06 [full_micro_interleaved_order_control]: 2.56998e-06 [reorder_send_recv_between_fp_bp]: 2.84999e-06 [comm_op_add_attrs]: 1.35999e-06 [add_comm_op_reuse_tag]: 1.04003e-06 [interleave_split_concat_branches]: 1.25001e-06 [interleave_parallel_branches]: 1.02998e-06 [overlap_opt_shard_in_pipeline]: 4.48999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.39001e-06 [control_data_broadcast_order]: 3.718e-05 [grouped_pairwise_exchange_alltoall]: 1.76e-06 [offloading_packed_experts]: 1.08e-05 [overlap_recompute_and_grad_model_parallel]: 9.85002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.26002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.71e-06 [overlap_recompute_comm]: 2.40002e-06 [overlap_grad_ring_attention]: 1.004e-05 [overlap_grad_flash_sp]: 5.415e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.24999e-06 [split_layernorm_comm]: 2.00002e-06 [handle_group_info]: 1.00001e-06 [symbol_engine_optimizer]: 0.0005465, [1] [Cycle 1]: 0.0005397, [6] [build]: 0.00031095 [elim_shapecalc]: 3.289e-05 [elim_not_effective]: 5.333e-05 [opt_reshape]: 3.398e-05 [fold_const_symbol]: 5.762e-05 [renormalize]: 2.89991e-07 [detach_backward]: 3.48e-06 [pipeline_parallel_scheduler]: 1.50999e-06 [auto_monad_reorder]: 6.376e-05 [get_jit_bprop_graph]: 2.06e-06 [rewriter_after_jit_bprop_graph]: 6.16e-06 [opt_after_jit_grad]: 0.00075596 [validate]: 0.00011891 Sums bootstrap : 0.000837s : 0.08% type_inference : 0.927585s : 90.14% event_method : 0.000203s : 0.02% auto_monad : 0.000735s : 0.07% graph_reusing : 0.000043s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000213s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000045s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000250s : 0.02% 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 : 0.000249s : 0.02% optimize.rewriter_before_opt_a : 0.000779s : 0.08% optimize.opt_a.expand_dump_flag : 0.000037s : 0.00% optimize.opt_a.switch_simplify : 0.000803s : 0.08% optimize.opt_a.loop_unroll : 0.000328s : 0.03% optimize.opt_a.a_1 : 0.010449s : 1.02% optimize.opt_a.with_stream_mark : 0.000107s : 0.01% optimize.opt_a.recompute_prepare : 0.000064s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000033s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001100s : 0.11% optimize.opt_a.accelerated_algorithm : 0.000095s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000032s : 0.00% optimize.opt_a.shard_inline : 0.000045s : 0.00% optimize.opt_a.merge_send_recv : 0.000040s : 0.00% optimize.opt_a.auto_parallel : 0.000041s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 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 : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000051s : 0.00% optimize.opt_a.virtual_dataset : 0.000042s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000042s : 0.00% optimize.opt_a.virtual_output : 0.000041s : 0.00% optimize.opt_a.merge_forward : 0.000026s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000050s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000092s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000077s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.00% optimize.opt_a.meta_fg_expand : 0.000024s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.01% optimize.opt_a.a_after_grad : 0.000071s : 0.01% optimize.opt_a.renormalize : 0.047211s : 4.59% optimize.opt_a.add_forward_monad_depend : 0.000028s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000174s : 0.02% optimize.opt_a.cse : 0.030469s : 2.96% optimize.opt_a.a_3 : 0.000324s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000994s : 0.10% optimize.convert_after_rewriter : 0.000034s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000843s : 0.08% optimize.opt_b.b_1 : 0.000542s : 0.05% optimize.opt_b.b_2 : 0.000023s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000103s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000048s : 0.00% optimize.overlap_param_gather : 0.000006s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000600s : 0.06% optimize.opt_after_cconv.c_1 : 0.000126s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000074s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000105s : 0.01% optimize.tuple_transform.d_1 : 0.000204s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000022s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000155s : 0.02% optimize.cse_after_recomputation.cse : 0.000056s : 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 : 0.000002s : 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 : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000004s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000037s : 0.00% 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000054s : 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 : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000033s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000053s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000058s : 0.01% 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 : 0.000064s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000756s : 0.07% validate : 0.000119s : 0.01% Time group info: ------[substitution.] 0.003946 569 0.43% : 0.000017s : 8: substitution.depend_value_elim 0.40% : 0.000016s : 14: substitution.elim_not_effective 0.43% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.71% : 0.000028s : 14: substitution.fold_const_symbol 0.40% : 0.000016s : 17: substitution.graph_param_transform 71.96% : 0.002840s : 71: substitution.inline 0.35% : 0.000014s : 29: substitution.j_node_and_user_rematch 0.85% : 0.000034s : 6: substitution.less_batch_normalization 1.53% : 0.000061s : 2: substitution.list_to_tuple_eliminator_ 0.16% : 0.000006s : 6: substitution.load_eliminater 0.89% : 0.000035s : 21: substitution.minmaximum_grad 0.24% : 0.000010s : 2: substitution.opt_reshape 0.54% : 0.000021s : 29: substitution.remove_not_recompute_node 0.20% : 0.000008s : 4: substitution.replace_old_param 1.64% : 0.000065s : 18: substitution.reshape_eliminate 1.16% : 0.000046s : 24: substitution.switch_simplify 3.89% : 0.000154s : 51: substitution.tuple_list_convert_item_index_to_positive 2.31% : 0.000091s : 51: substitution.tuple_list_get_item_const_eliminator 2.82% : 0.000111s : 51: substitution.tuple_list_get_item_depend_reorder 5.19% : 0.000205s : 73: substitution.tuple_list_get_item_eliminator 2.71% : 0.000107s : 51: substitution.tuple_list_get_set_item_eliminator 0.61% : 0.000024s : 6: substitution.updatestate_pure_node_eliminater 0.55% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.927179 2 96.74% : 0.896928s : 1: type_inference.infer 3.26% : 0.030251s : 1: type_inference.specialize ------[replace.] 0.001106 115 4.08% : 0.000045s : 5: replace.depend_value_elim 56.76% : 0.000628s : 71: replace.inline 3.53% : 0.000039s : 2: replace.list_to_tuple_eliminator_ 26.82% : 0.000297s : 24: replace.switch_simplify 8.81% : 0.000097s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002926 115 0.08% : 0.000002s : 5: match.depend_value_elim 95.65% : 0.002799s : 71: match.inline 1.97% : 0.000058s : 2: match.list_to_tuple_eliminator_ 1.22% : 0.000036s : 24: match.switch_simplify 1.08% : 0.000032s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001571 9701 1.27% : 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 1.20% : 0.000019s : 123: predicate.addn_zero_filter 1.11% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.37% : 0.000037s : 181: predicate.arithmetic_simplify 1.21% : 0.000019s : 123: predicate.cast_eliminate 0.32% : 0.000005s : 34: predicate.check_bprop_eliminate 0.51% : 0.000008s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.69% : 0.000011s : 61: predicate.depend_value_elim 1.25% : 0.000020s : 123: predicate.dict_get_item_const_eliminator 1.31% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.14% : 0.000018s : 123: predicate.dict_set_item_eliminator 0.39% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.09% : 0.000001s : 17: predicate.elim_not_effective 0.23% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000020s : 140: predicate.environ_add_const_eliminate 1.29% : 0.000020s : 140: predicate.environ_get_add_eliminate 1.25% : 0.000020s : 140: predicate.environ_get_depend_swap 1.93% : 0.000030s : 198: predicate.environ_get_eliminate 1.23% : 0.000019s : 140: predicate.environ_get_set_eliminate 1.91% : 0.000030s : 209: predicate.exchange_switch_depend_value 2.76% : 0.000043s : 209: predicate.float_depend_g_call 0.51% : 0.000008s : 58: predicate.float_environ_get_switch 0.71% : 0.000011s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.37% : 0.000006s : 35: predicate.get_grad_eliminate 0.09% : 0.000001s : 17: predicate.graph_param_transform 0.54% : 0.000008s : 58: predicate.incorporate_call 0.47% : 0.000007s : 58: predicate.incorporate_call_switch 5.66% : 0.000089s : 459: predicate.inline 0.45% : 0.000007s : 35: predicate.inline_without_move 0.15% : 0.000002s : 35: predicate.j_node_and_user_rematch 0.53% : 0.000008s : 36: predicate.less_batch_normalization 1.69% : 0.000027s : 172: predicate.list_to_tuple_eliminator_ 2.62% : 0.000041s : 295: predicate.load_eliminater 0.41% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.24% : 0.000051s : 314: predicate.loop_unroll_before_grad 1.52% : 0.000024s : 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 0.29% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.16% : 0.000018s : 123: predicate.minmaximum_grad 0.49% : 0.000008s : 17: predicate.mutable_eliminate 0.18% : 0.000003s : 17: predicate.opt_reshape 0.17% : 0.000003s : 17: predicate.parallel_virtual_node 3.29% : 0.000052s : 209: predicate.partial_defer_inline 1.54% : 0.000024s : 155: predicate.partial_eliminate 1.20% : 0.000019s : 123: predicate.print_const_string_wrapper 0.47% : 0.000007s : 53: predicate.reduce_all_const_elim 1.68% : 0.000026s : 123: predicate.reduce_eliminate 2.82% : 0.000044s : 295: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 35: predicate.remove_not_recompute_node 1.08% : 0.000017s : 172: predicate.replace_applicator 0.21% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.27% : 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 0.51% : 0.000008s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.39% : 0.000006s : 35: predicate.shard_identity_eliminate 0.34% : 0.000005s : 34: predicate.special_op_eliminate 0.60% : 0.000009s : 58: predicate.specialize_transform 0.43% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.12% : 0.000033s : 209: predicate.switch_defer_inline 2.41% : 0.000038s : 243: predicate.switch_layer_defer_inline 6.59% : 0.000104s : 646: predicate.switch_simplify 1.14% : 0.000018s : 123: predicate.tile_eliminate 1.13% : 0.000018s : 123: predicate.transpose_eliminate 1.74% : 0.000027s : 157: predicate.tuple_list_convert_item_index_to_positive 1.80% : 0.000028s : 157: predicate.tuple_list_get_item_const_eliminator 1.78% : 0.000028s : 157: predicate.tuple_list_get_item_depend_reorder 3.08% : 0.000048s : 228: predicate.tuple_list_get_item_eliminator 1.71% : 0.000027s : 157: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000039s : 215: predicate.tuple_list_set_item_eliminator 1.69% : 0.000027s : 170: predicate.tuple_to_list_eliminator_ 2.61% : 0.000041s : 295: predicate.updatestate_pure_node_eliminater 3.27% : 0.000051s : 353: predicate.updatestate_useless_node_eliminater 0.17% : 0.000003s : 17: predicate.value_based_eliminate 0.34% : 0.000005s : 35: predicate.virtual_dataset_eliminate 0.35% : 0.000006s : 35: predicate.virtual_output_eliminate 0.15% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.19% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.017626 135 55.56% : 0.009793s : 55: func_graph_cloner_run.FuncGraphClonerGraph 44.44% : 0.007833s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.330260 209 0.00% : 0.000004s : 1: ForceFp32Comm 5.22% : 0.069428s : 1: add_attr 5.22% : 0.069404s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000161s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.06% : 0.000754s : 1: auto_monad 0.01% : 0.000070s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.07% : 0.000918s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000041s : 1: control_data_broadcast_order 0.00% : 0.000041s : 1: convert_after_rewriter 0.01% : 0.000075s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.02% : 0.000215s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000050s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.05% : 0.000613s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.06% : 0.000855s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000038s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000046s : 1: opt.transform.mutable_eliminate 1.02% : 0.013527s : 95: opt.transform.opt_a 0.01% : 0.000124s : 1: opt.transform.opt_after_cconv 0.01% : 0.000074s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000527s : 28: opt.transform.opt_b 0.02% : 0.000223s : 2: opt.transform.opt_trans_graph 0.01% : 0.000173s : 4: opt.transform.symbol_engine_opt 6.99% : 0.093024s : 1: opt_a 0.02% : 0.000299s : 1: opt_after_cconv 0.06% : 0.000772s : 1: opt_after_jit_grad 0.06% : 0.000773s : 1: opt_b 7.48% : 0.099446s : 1: optimize 0.00% : 0.000053s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000058s : 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% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 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% : 0.000013s : 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% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000257s : 1: pre_auto_parallel 0.02% : 0.000258s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000111s : 1: remove_dup_value 2.95% : 0.039177s : 1: renormalize.infer 0.60% : 0.008011s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.08% : 0.001012s : 1: rewriter_after_opt_a 0.06% : 0.000791s : 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 0.04% : 0.000550s : 1: symbol_engine_optimizer 0.02% : 0.000259s : 1: tuple_transform 69.73% : 0.927629s : 1: type_inference . [hook] pytest_runtest_teardown:test_dynamic_shape[input_shape2] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_dynamic_shape[input_shape2],max_mem:208.0M =============================== 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 ================== 3 passed, 25 warnings in 180.33s (0:03:00) ==================