==================================================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_006/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 12 items test_swiglu.py [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:37:21.499.794 [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 = 0.909496, [21] [bootstrap]: 0.00068319 [type_inference]: 0.841874 [event_method]: 2.873e-05 [auto_monad]: 0.00110716 [graph_reusing]: 1.116e-05 [inline]: 3.61999e-06 [add_attr]: 0.0205755, [1] [add_attr_with_inline]: 0.0205568, [1] [Cycle 1]: 0.00011625, [2] [tag_attr]: 2.924e-05 [meta_addattr_fg_expand]: 6.29999e-06 [parallel-infer-symbol]: 3.88999e-06 [pre_auto_parallel]: 4.862e-05 [insert-virtual-dataset]: 2.86e-06 [parallel-infer-symbol-second]: 1.27999e-06 [dataset_repeat_opt]: 2.41998e-06 [pipeline_split]: 1.92001e-06 [optimize]: 0.0441066, [53] [py_interpret_to_execute]: 3.639e-05 [rewriter_before_opt_a]: 0.00010752 [opt_a]: 0.0404065, [2] [Cycle 1]: 0.0390694, [45] [expand_dump_flag]: 4.02002e-06 [switch_simplify]: 4.384e-05 [loop_unroll]: 2.769e-05 [a_1]: 0.00085471 [with_stream_mark]: 3.072e-05 [recompute_prepare]: 1.639e-05 [updatestate_depend_eliminate]: 8.54e-06 [updatestate_assign_eliminate]: 6.19001e-06 [updatestate_loads_eliminate]: 5.66998e-06 [parameter_eliminate]: 2.64999e-06 [a_2]: 0.00018244 [accelerated_algorithm]: 1.369e-05 [shard]: 3.18998e-06 [meta_shard_fg_expand]: 3.55e-06 [shard_inline]: 1.186e-05 [merge_send_recv]: 1.339e-05 [auto_parallel]: 1.339e-05 [parallel]: 5.346e-05 [flash_sp]: 2.099e-05 [merge_comm]: 7.71001e-06 [allreduce_fusion]: 6.38998e-06 [matmul_add_comm_reduction]: 1.546e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 1.664e-05 [virtual_dataset]: 1.111e-05 [get_grad_eliminate_]: 1.185e-05 [virtual_output]: 1.065e-05 [merge_forward]: 7.87998e-06 [cell_reuse_recompute_pass]: 2.27001e-06 [offload_activation]: 1.616e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.616e-05 [merge_recompute_call_nodes]: 1.43002e-06 [before_grad]: 2.089e-05 [set_forward_comm_id_for_comm_node_pass]: 6.96001e-06 [meta_fg_expand]: 4.95001e-06 [flash_sp_send_recv_attached]: 2.78e-06 [receive_attached]: 2.60002e-06 [after_resolve]: 1.634e-05 [a_after_grad]: 1.806e-05 [renormalize]: 0.0368957 [add_forward_monad_depend]: 1.277e-05 [auto_monad_grad]: 3.38999e-06 [auto_monad_eliminator]: 3.447e-05 [cse]: 0.00018696 [a_3]: 9.616e-05 [Cycle 2]: 0.00132191, [45] [expand_dump_flag]: 3.03998e-06 [switch_simplify]: 1.426e-05 [loop_unroll]: 1.154e-05 [a_1]: 0.00032995 [with_stream_mark]: 2.76e-05 [recompute_prepare]: 1.339e-05 [updatestate_depend_eliminate]: 8.34002e-06 [updatestate_assign_eliminate]: 5.89e-06 [updatestate_loads_eliminate]: 5.44e-06 [parameter_eliminate]: 1.97001e-06 [a_2]: 0.00016207 [accelerated_algorithm]: 1.187e-05 [shard]: 3.39001e-06 [meta_shard_fg_expand]: 3.11999e-06 [shard_inline]: 1.174e-05 [merge_send_recv]: 1.428e-05 [auto_parallel]: 1.317e-05 [parallel]: 1.02e-05 [flash_sp]: 4.37998e-06 [merge_comm]: 6.76e-06 [allreduce_fusion]: 6.07001e-06 [matmul_add_comm_reduction]: 1.522e-05 [allreduce_slice_to_reducescatter]: 1.11002e-06 [virtual_shard_identity]: 1.382e-05 [virtual_dataset]: 1.178e-05 [get_grad_eliminate_]: 1.139e-05 [virtual_output]: 1.09e-05 [merge_forward]: 6.68e-06 [cell_reuse_recompute_pass]: 2.81999e-06 [offload_activation]: 1.619e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.482e-05 [merge_recompute_call_nodes]: 1.49e-06 [before_grad]: 2.002e-05 [set_forward_comm_id_for_comm_node_pass]: 6.73e-06 [meta_fg_expand]: 5.32001e-06 [flash_sp_send_recv_attached]: 1.97001e-06 [receive_attached]: 2.63998e-06 [after_resolve]: 1.662e-05 [a_after_grad]: 1.69e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.49001e-06 [auto_monad_grad]: 2.26e-06 [auto_monad_eliminator]: 2.289e-05 [cse]: 0.00012311 [a_3]: 7.553e-05 [py_interpret_to_execute_after_opt_a]: 2.993e-05 [slice_cell_reuse_recomputed_activation]: 2.78e-06 [rewriter_after_opt_a]: 0.00036023 [convert_after_rewriter]: 1.753e-05 [order_py_execute_after_rewriter]: 9.24e-06 [mutable_eliminate]: 0.00083634 [opt_b]: 0.00046786, [1] [Cycle 1]: 0.00045835, [7] [b_1]: 0.00029478 [b_2]: 1.468e-05 [updatestate_depend_eliminate]: 1.44e-05 [updatestate_assign_eliminate]: 6.25002e-06 [updatestate_loads_eliminate]: 5.69999e-06 [renormalize]: 8.50006e-07 [cse]: 7.744e-05 [optimize_parallel_all_gather_comm]: 3.457e-05 [overlap_param_gather]: 2.08998e-06 [cconv]: 3.863e-05 [loop_unroll]: 0.00057896 [opt_after_cconv]: 0.00018673, [1] [Cycle 1]: 0.00017807, [7] [c_1]: 5.704e-05 [parameter_eliminate]: 6.29001e-06 [updatestate_depend_eliminate]: 1.141e-05 [updatestate_assign_eliminate]: 5.91998e-06 [updatestate_loads_eliminate]: 4.79998e-06 [cse]: 5.382e-05 [renormalize]: 3.30008e-07 [remove_dup_value]: 6.546e-05 [tuple_transform]: 0.00016629, [1] [Cycle 1]: 0.000161, [4] [d_1]: 0.00012471 [none_parameter_eliminate]: 2.22001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.266e-05 [partial_unused_args_eliminate]: 2.16e-06 [add_recomputation]: 9.826e-05 [cse_after_recomputation]: 4.464e-05, [1] [Cycle 1]: 3.952e-05, [1] [cse]: 3.301e-05 [environ_conv]: 2.669e-05 [swap_dp_allreduce_reducescatter]: 1.094e-05 [bias_add_comm_swap]: 2.93e-06 [label_micro_interleaved_index]: 8.27e-06 [label_fine_grained_interleaved_index]: 2.91e-06 [merge_cast_opt]: 1.32999e-06 [slice_recompute_activation]: 2.47001e-06 [micro_interleaved_order_control]: 3.04999e-06 [assign_add_opt]: 1.84e-06 [ForceFp32Comm]: 1.34e-06 [remove_cast_before_assign_add]: 1.54e-06 [full_micro_interleaved_order_control]: 2.58e-06 [reorder_send_recv_between_fp_bp]: 2.73e-06 [comm_op_add_attrs]: 1.42e-06 [add_comm_op_reuse_tag]: 1.17e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.12e-06 [overlap_opt_shard_in_pipeline]: 2.39e-05 [overlap_opt_shard_grad_in_pipeline]: 1.91e-06 [control_data_broadcast_order]: 2.729e-05 [grouped_pairwise_exchange_alltoall]: 1.96e-06 [offloading_packed_experts]: 6.14999e-06 [overlap_recompute_and_grad_model_parallel]: 7.18e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.54e-06 [overlap_recompute_comm]: 2.42001e-06 [overlap_grad_ring_attention]: 7.1e-06 [overlap_grad_flash_sp]: 4.831e-05 [begin_end_overlap_inline]: 8.89995e-07 [split_matmul_comm_elemetwise]: 2.54001e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.55001e-06 [symbol_engine_optimizer]: 0.00012562, [1] [Cycle 1]: 0.00011968, [6] [build]: 1.277e-05 [elim_shapecalc]: 1.866e-05 [elim_not_effective]: 2.353e-05 [opt_reshape]: 1.234e-05 [fold_const_symbol]: 1.891e-05 [renormalize]: 3.00002e-07 [detach_backward]: 2.88e-06 [pipeline_parallel_scheduler]: 1.79e-06 [auto_monad_reorder]: 3.584e-05 [get_jit_bprop_graph]: 1.94e-06 [rewriter_after_jit_bprop_graph]: 6.68e-06 [opt_after_jit_grad]: 0.00065735 [validate]: 9.313e-05 Sums bootstrap : 0.000683s : 0.08% type_inference : 0.841874s : 94.84% event_method : 0.000029s : 0.00% auto_monad : 0.001107s : 0.12% graph_reusing : 0.000011s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.01% 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 : 0.000036s : 0.00% optimize.rewriter_before_opt_a : 0.000108s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000058s : 0.01% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001185s : 0.13% optimize.opt_a.with_stream_mark : 0.000058s : 0.01% optimize.opt_a.recompute_prepare : 0.000030s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000345s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000024s : 0.00% optimize.opt_a.merge_send_recv : 0.000028s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000064s : 0.01% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000031s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.00% optimize.opt_a.virtual_output : 0.000022s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000032s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000051s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000033s : 0.00% optimize.opt_a.a_after_grad : 0.000035s : 0.00% optimize.opt_a.renormalize : 0.036896s : 4.16% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000057s : 0.01% optimize.opt_a.cse : 0.000310s : 0.03% optimize.opt_a.a_3 : 0.000172s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000360s : 0.04% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000836s : 0.09% optimize.opt_b.b_1 : 0.000295s : 0.03% optimize.opt_b.b_2 : 0.000015s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000077s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000039s : 0.00% optimize.loop_unroll : 0.000579s : 0.07% optimize.opt_after_cconv.c_1 : 0.000057s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000054s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000065s : 0.01% optimize.tuple_transform.d_1 : 0.000125s : 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 : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000098s : 0.01% optimize.cse_after_recomputation.cse : 0.000033s : 0.00% optimize.environ_conv : 0.000027s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 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 : 0.000002s : 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 : 0.000024s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000048s : 0.01% 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000013s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000019s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000024s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 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 : 0.000036s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000657s : 0.07% validate : 0.000093s : 0.01% Time group info: ------[substitution.] 0.000463 111 9.81% : 0.000045s : 6: substitution.arithmetic_simplify 0.84% : 0.000004s : 6: substitution.elim_not_effective 2.89% : 0.000013s : 6: substitution.float_tuple_getitem_switch 0.66% : 0.000003s : 6: substitution.fold_const_symbol 2.39% : 0.000011s : 8: substitution.graph_param_transform 43.04% : 0.000199s : 5: substitution.inline 1.92% : 0.000009s : 12: substitution.j_node_and_user_rematch 2.07% : 0.000010s : 4: substitution.minmaximum_grad 2.24% : 0.000010s : 12: substitution.remove_not_recompute_node 1.38% : 0.000006s : 2: substitution.replace_old_param 7.04% : 0.000033s : 8: substitution.tuple_list_convert_item_index_to_positive 5.29% : 0.000025s : 8: substitution.tuple_list_get_item_const_eliminator 4.67% : 0.000022s : 8: substitution.tuple_list_get_item_depend_reorder 11.32% : 0.000052s : 12: substitution.tuple_list_get_item_eliminator 4.45% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.841752 2 99.57% : 0.838108s : 1: type_inference.infer 0.43% : 0.003644s : 1: type_inference.specialize ------[replace.] 0.000044 5 100.00% : 0.000044s : 5: replace.inline ------[match.] 0.000196 5 100.00% : 0.000196s : 5: match.inline ------[predicate.] 0.000346 2113 0.88% : 0.000003s : 21: predicate.accumulaten_eliminater 1.17% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.64% : 0.000002s : 16: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.75% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.42% : 0.000008s : 37: predicate.arithmetic_simplify 0.86% : 0.000003s : 21: predicate.cast_eliminate 0.70% : 0.000002s : 16: predicate.check_bprop_eliminate 0.65% : 0.000002s : 16: predicate.compare_switch_simplify 0.21% : 0.000001s : 8: predicate.const_output_eliminate 0.67% : 0.000002s : 16: predicate.depend_value_elim 0.85% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.89% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.88% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.33% : 0.000005s : 16: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 8: predicate.elim_not_effective 0.57% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.34% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.06% : 0.000004s : 29: predicate.environ_get_depend_swap 1.76% : 0.000006s : 45: predicate.environ_get_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.08% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.69% : 0.000006s : 26: predicate.float_depend_g_call 0.65% : 0.000002s : 16: predicate.float_environ_get_switch 1.13% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.82% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.69% : 0.000002s : 16: predicate.incorporate_call 0.59% : 0.000002s : 16: predicate.incorporate_call_switch 5.74% : 0.000020s : 95: predicate.inline 0.96% : 0.000003s : 16: predicate.inline_without_move 0.33% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.86% : 0.000003s : 16: predicate.less_batch_normalization 1.66% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.28% : 0.000008s : 58: predicate.load_eliminater 1.28% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.58% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.68% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.72% : 0.000002s : 16: predicate.merge_addn 0.63% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.77% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.84% : 0.000003s : 21: predicate.minmaximum_grad 1.48% : 0.000005s : 8: predicate.mutable_eliminate 0.49% : 0.000002s : 8: predicate.opt_reshape 0.53% : 0.000002s : 8: predicate.parallel_virtual_node 1.46% : 0.000005s : 26: predicate.partial_defer_inline 1.20% : 0.000004s : 29: predicate.partial_eliminate 0.92% : 0.000003s : 21: predicate.print_const_string_wrapper 0.66% : 0.000002s : 16: predicate.reduce_all_const_elim 1.10% : 0.000004s : 21: predicate.reduce_eliminate 2.21% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.51% : 0.000002s : 16: predicate.remove_not_recompute_node 1.27% : 0.000004s : 37: predicate.replace_applicator 0.38% : 0.000001s : 16: predicate.replace_old_param 0.35% : 0.000001s : 8: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.71% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.52% : 0.000002s : 8: predicate.row_tensor_eliminate 1.16% : 0.000004s : 16: predicate.same_eliminate 0.59% : 0.000002s : 16: predicate.set_cell_output_no_recompute 1.09% : 0.000004s : 16: predicate.shard_identity_eliminate 0.88% : 0.000003s : 16: predicate.special_op_eliminate 0.77% : 0.000003s : 16: predicate.specialize_transform 1.28% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.99% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.41% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.10% : 0.000004s : 26: predicate.switch_defer_inline 1.74% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.99% : 0.000014s : 86: predicate.switch_simplify 0.82% : 0.000003s : 21: predicate.tile_eliminate 0.91% : 0.000003s : 21: predicate.transpose_eliminate 1.86% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 3.24% : 0.000011s : 53: predicate.tuple_list_get_item_eliminator 1.63% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.51% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.54% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.17% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.98% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 8: predicate.value_based_eliminate 0.73% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.78% : 0.000003s : 16: predicate.virtual_output_eliminate 0.36% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.085332 32 60.67% : 0.051769s : 25: func_graph_cloner_run.FuncGraphClonerGraph 39.33% : 0.033563s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.013497 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.03% : 0.020582s : 1: add_attr 2.03% : 0.020562s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000104s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.11% : 0.001147s : 1: auto_monad 0.00% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.07% : 0.000724s : 1: bootstrap 0.00% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000023s : 1: convert_after_rewriter 0.00% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.00% : 0.000037s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000017s : 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% : 0.000011s : 1: label_micro_interleaved_index 0.06% : 0.000590s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.08% : 0.000850s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000034s : 1: opt.transform.mutable_eliminate 0.20% : 0.002014s : 78: opt.transform.opt_a 0.01% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000049s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000275s : 28: opt.transform.opt_b 0.01% : 0.000135s : 2: opt.transform.opt_trans_graph 0.01% : 0.000069s : 4: opt.transform.symbol_engine_opt 3.99% : 0.040411s : 1: opt_a 0.02% : 0.000191s : 1: opt_after_cconv 0.07% : 0.000671s : 1: opt_after_jit_grad 0.05% : 0.000473s : 1: opt_b 4.35% : 0.044112s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 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% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000029s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000053s : 1: pre_auto_parallel 0.00% : 0.000041s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000070s : 1: remove_dup_value 0.31% : 0.003093s : 1: renormalize.infer 3.33% : 0.033785s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000372s : 1: rewriter_after_opt_a 0.01% : 0.000113s : 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% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000128s : 1: symbol_engine_optimizer 0.02% : 0.000169s : 1: tuple_transform 83.07% : 0.841910s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_56408_20260129171803.log . [hook] pytest_runtest_teardown:test_swiglu[False-float32--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-float32--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:00.656.085 [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 = 1.45437, [21] [bootstrap]: 0.00083237 [type_inference]: 1.32712 [event_method]: 2.541e-05 [auto_monad]: 0.00011539 [graph_reusing]: 7.7e-06 [inline]: 3.65998e-06 [add_attr]: 0.101158, [1] [add_attr_with_inline]: 0.10114, [1] [Cycle 1]: 8.017e-05, [2] [tag_attr]: 2.446e-05 [meta_addattr_fg_expand]: 5.64e-06 [parallel-infer-symbol]: 3.98001e-06 [pre_auto_parallel]: 4.657e-05 [insert-virtual-dataset]: 2.46e-06 [parallel-infer-symbol-second]: 7.79983e-07 [dataset_repeat_opt]: 1.93002e-06 [pipeline_split]: 2.11e-06 [optimize]: 0.0238376, [53] [py_interpret_to_execute]: 3.114e-05 [rewriter_before_opt_a]: 8.94e-05 [opt_a]: 0.0100711, [2] [Cycle 1]: 0.00885471, [45] [expand_dump_flag]: 4.03001e-06 [switch_simplify]: 4.057e-05 [loop_unroll]: 2.653e-05 [a_1]: 0.00092366 [with_stream_mark]: 2.237e-05 [recompute_prepare]: 1.711e-05 [updatestate_depend_eliminate]: 7.89002e-06 [updatestate_assign_eliminate]: 5.91998e-06 [updatestate_loads_eliminate]: 6.59999e-06 [parameter_eliminate]: 1.92999e-06 [a_2]: 0.00018456 [accelerated_algorithm]: 1.299e-05 [shard]: 2.17001e-06 [meta_shard_fg_expand]: 3.5e-06 [shard_inline]: 1.11e-05 [merge_send_recv]: 1.268e-05 [auto_parallel]: 1.062e-05 [parallel]: 3.133e-05 [flash_sp]: 1.064e-05 [merge_comm]: 6.87002e-06 [allreduce_fusion]: 7.73001e-06 [matmul_add_comm_reduction]: 1.442e-05 [allreduce_slice_to_reducescatter]: 5.89993e-07 [virtual_shard_identity]: 1.326e-05 [virtual_dataset]: 1.325e-05 [get_grad_eliminate_]: 1.18e-05 [virtual_output]: 1.268e-05 [merge_forward]: 7.16999e-06 [cell_reuse_recompute_pass]: 1.30001e-06 [offload_activation]: 1.6e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.445e-05 [merge_recompute_call_nodes]: 1.42999e-06 [before_grad]: 2.066e-05 [set_forward_comm_id_for_comm_node_pass]: 8.13999e-06 [meta_fg_expand]: 5.03002e-06 [flash_sp_send_recv_attached]: 2.34999e-06 [receive_attached]: 2.46e-06 [after_resolve]: 1.639e-05 [a_after_grad]: 2.113e-05 [renormalize]: 0.00674779 [add_forward_monad_depend]: 1.184e-05 [auto_monad_grad]: 2.88e-06 [auto_monad_eliminator]: 3.316e-05 [cse]: 0.00011843 [a_3]: 0.00010357 [Cycle 2]: 0.00120064, [45] [expand_dump_flag]: 3.03e-06 [switch_simplify]: 1.547e-05 [loop_unroll]: 1.204e-05 [a_1]: 0.00033938 [with_stream_mark]: 2.366e-05 [recompute_prepare]: 1.187e-05 [updatestate_depend_eliminate]: 7.92998e-06 [updatestate_assign_eliminate]: 5.57999e-06 [updatestate_loads_eliminate]: 5.18002e-06 [parameter_eliminate]: 2.14e-06 [a_2]: 0.00016052 [accelerated_algorithm]: 1.161e-05 [shard]: 2.71e-06 [meta_shard_fg_expand]: 3.28e-06 [shard_inline]: 1.067e-05 [merge_send_recv]: 1.247e-05 [auto_parallel]: 1.343e-05 [parallel]: 9.96998e-06 [flash_sp]: 4.74e-06 [merge_comm]: 6.29999e-06 [allreduce_fusion]: 5.96e-06 [matmul_add_comm_reduction]: 1.375e-05 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 1.291e-05 [virtual_dataset]: 1.061e-05 [get_grad_eliminate_]: 1.122e-05 [virtual_output]: 1.042e-05 [merge_forward]: 7.88999e-06 [cell_reuse_recompute_pass]: 2.71999e-06 [offload_activation]: 1.511e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.363e-05 [merge_recompute_call_nodes]: 1.72999e-06 [before_grad]: 1.883e-05 [set_forward_comm_id_for_comm_node_pass]: 6.81001e-06 [meta_fg_expand]: 4.80001e-06 [flash_sp_send_recv_attached]: 1.89e-06 [receive_attached]: 2.50997e-06 [after_resolve]: 1.644e-05 [a_after_grad]: 1.692e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.04e-06 [auto_monad_grad]: 1.35999e-06 [auto_monad_eliminator]: 1.427e-05 [cse]: 3.971e-05 [a_3]: 6.758e-05 [py_interpret_to_execute_after_opt_a]: 2.475e-05 [slice_cell_reuse_recomputed_activation]: 2.79999e-06 [rewriter_after_opt_a]: 0.0002654 [convert_after_rewriter]: 1.244e-05 [order_py_execute_after_rewriter]: 8.64998e-06 [mutable_eliminate]: 0.00080843 [opt_b]: 0.00040435, [1] [Cycle 1]: 0.00039495, [7] [b_1]: 0.00027821 [b_2]: 1.246e-05 [updatestate_depend_eliminate]: 9.78998e-06 [updatestate_assign_eliminate]: 4.90001e-06 [updatestate_loads_eliminate]: 4.76002e-06 [renormalize]: 6.30011e-07 [cse]: 4.596e-05 [optimize_parallel_all_gather_comm]: 2.572e-05 [overlap_param_gather]: 2.27001e-06 [cconv]: 3.464e-05 [loop_unroll]: 0.00053386 [opt_after_cconv]: 0.00016029, [1] [Cycle 1]: 0.00015374, [7] [c_1]: 5.593e-05 [parameter_eliminate]: 4.03999e-06 [updatestate_depend_eliminate]: 8.81002e-06 [updatestate_assign_eliminate]: 6.12001e-06 [updatestate_loads_eliminate]: 4.76002e-06 [cse]: 3.802e-05 [renormalize]: 8.80013e-07 [remove_dup_value]: 5.859e-05 [tuple_transform]: 0.00015305, [1] [Cycle 1]: 0.00014838, [4] [d_1]: 0.00011305 [none_parameter_eliminate]: 2.12999e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 1.263e-05 [partial_unused_args_eliminate]: 1.89e-06 [add_recomputation]: 9.409e-05 [cse_after_recomputation]: 4.181e-05, [1] [Cycle 1]: 3.564e-05, [1] [cse]: 3.013e-05 [environ_conv]: 1.51e-05 [swap_dp_allreduce_reducescatter]: 9.03002e-06 [bias_add_comm_swap]: 2.81e-06 [label_micro_interleaved_index]: 5.16002e-06 [label_fine_grained_interleaved_index]: 2.84999e-06 [merge_cast_opt]: 1.25999e-06 [slice_recompute_activation]: 2.01998e-06 [micro_interleaved_order_control]: 2.49999e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 8.50006e-07 [remove_cast_before_assign_add]: 1.02998e-06 [full_micro_interleaved_order_control]: 2.16e-06 [reorder_send_recv_between_fp_bp]: 3.08e-06 [comm_op_add_attrs]: 9.67001e-06 [add_comm_op_reuse_tag]: 1.42999e-06 [interleave_split_concat_branches]: 8.25999e-06 [interleave_parallel_branches]: 1.27e-06 [overlap_opt_shard_in_pipeline]: 9.49e-06 [overlap_opt_shard_grad_in_pipeline]: 3.40998e-06 [control_data_broadcast_order]: 5.311e-05 [grouped_pairwise_exchange_alltoall]: 1.71e-06 [offloading_packed_experts]: 8.27998e-06 [overlap_recompute_and_grad_model_parallel]: 6.84999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.81e-06 [overlap_grad_ring_attention]: 7.69002e-06 [overlap_grad_flash_sp]: 4.403e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 1.97999e-06 [handle_group_info]: 1.22999e-06 [symbol_engine_optimizer]: 0.00019473, [1] [Cycle 1]: 0.00017951, [6] [build]: 2.17e-05 [elim_shapecalc]: 3.952e-05 [elim_not_effective]: 3.354e-05 [opt_reshape]: 1.463e-05 [fold_const_symbol]: 1.937e-05 [renormalize]: 6.30011e-07 [detach_backward]: 2.36e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 3.79e-05 [get_jit_bprop_graph]: 2.32999e-06 [rewriter_after_jit_bprop_graph]: 1.004e-05 [opt_after_jit_grad]: 0.00086983 [validate]: 8.712e-05 Sums bootstrap : 0.000832s : 0.06% type_inference : 1.327117s : 98.91% event_method : 0.000025s : 0.00% auto_monad : 0.000115s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 0.00% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000031s : 0.00% optimize.rewriter_before_opt_a : 0.000089s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000056s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001263s : 0.09% optimize.opt_a.with_stream_mark : 0.000046s : 0.00% optimize.opt_a.recompute_prepare : 0.000029s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000345s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000025s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000025s : 0.00% optimize.opt_a.auto_parallel : 0.000024s : 0.00% optimize.opt_a.parallel : 0.000041s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000013s : 0.00% optimize.opt_a.allreduce_fusion : 0.000014s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000031s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000039s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000033s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.006748s : 0.50% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000047s : 0.00% optimize.opt_a.cse : 0.000158s : 0.01% optimize.opt_a.a_3 : 0.000171s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000265s : 0.02% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000808s : 0.06% optimize.opt_b.b_1 : 0.000278s : 0.02% optimize.opt_b.b_2 : 0.000012s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000046s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000534s : 0.04% optimize.opt_after_cconv.c_1 : 0.000056s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000038s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000059s : 0.00% optimize.tuple_transform.d_1 : 0.000113s : 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 : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000094s : 0.01% optimize.cse_after_recomputation.cse : 0.000030s : 0.00% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000010s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000008s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000009s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000053s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000044s : 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 : 0.000022s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000034s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000038s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.00% opt_after_jit_grad : 0.000870s : 0.06% validate : 0.000087s : 0.01% Time group info: ------[substitution.] 0.000421 111 9.78% : 0.000041s : 6: substitution.arithmetic_simplify 0.90% : 0.000004s : 6: substitution.elim_not_effective 2.57% : 0.000011s : 6: substitution.float_tuple_getitem_switch 0.72% : 0.000003s : 6: substitution.fold_const_symbol 2.31% : 0.000010s : 8: substitution.graph_param_transform 45.66% : 0.000192s : 5: substitution.inline 1.70% : 0.000007s : 12: substitution.j_node_and_user_rematch 1.96% : 0.000008s : 4: substitution.minmaximum_grad 2.20% : 0.000009s : 12: substitution.remove_not_recompute_node 1.33% : 0.000006s : 2: substitution.replace_old_param 7.55% : 0.000032s : 8: substitution.tuple_list_convert_item_index_to_positive 3.25% : 0.000014s : 8: substitution.tuple_list_get_item_const_eliminator 4.59% : 0.000019s : 8: substitution.tuple_list_get_item_depend_reorder 10.86% : 0.000046s : 12: substitution.tuple_list_get_item_eliminator 4.62% : 0.000019s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.327008 2 99.69% : 1.322855s : 1: type_inference.infer 0.31% : 0.004153s : 1: type_inference.specialize ------[replace.] 0.000045 5 100.00% : 0.000045s : 5: replace.inline ------[match.] 0.000189 5 100.00% : 0.000189s : 5: match.inline ------[predicate.] 0.000340 2113 0.92% : 0.000003s : 21: predicate.accumulaten_eliminater 1.32% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.66% : 0.000002s : 16: predicate.addn_check_dump 1.02% : 0.000003s : 21: predicate.addn_zero_filter 0.84% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.35% : 0.000008s : 37: predicate.arithmetic_simplify 0.89% : 0.000003s : 21: predicate.cast_eliminate 0.72% : 0.000002s : 16: predicate.check_bprop_eliminate 0.67% : 0.000002s : 16: predicate.compare_switch_simplify 0.21% : 0.000001s : 8: predicate.const_output_eliminate 0.65% : 0.000002s : 16: predicate.depend_value_elim 0.95% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.02% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.92% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.12% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.37% : 0.000001s : 8: predicate.elim_not_effective 0.60% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.20% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.15% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.21% : 0.000004s : 29: predicate.environ_get_depend_swap 1.85% : 0.000006s : 45: predicate.environ_get_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.02% : 0.000003s : 26: predicate.exchange_switch_depend_value 1.67% : 0.000006s : 26: predicate.float_depend_g_call 0.70% : 0.000002s : 16: predicate.float_environ_get_switch 1.15% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 8: predicate.fold_const_symbol 0.73% : 0.000002s : 16: predicate.get_grad_eliminate 0.30% : 0.000001s : 8: predicate.graph_param_transform 0.69% : 0.000002s : 16: predicate.incorporate_call 0.59% : 0.000002s : 16: predicate.incorporate_call_switch 5.57% : 0.000019s : 95: predicate.inline 0.82% : 0.000003s : 16: predicate.inline_without_move 0.34% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.87% : 0.000003s : 16: predicate.less_batch_normalization 1.65% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.29% : 0.000008s : 58: predicate.load_eliminater 1.02% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.54% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.74% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.68% : 0.000002s : 16: predicate.merge_addn 0.65% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.69% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.93% : 0.000003s : 21: predicate.minmaximum_grad 1.14% : 0.000004s : 8: predicate.mutable_eliminate 0.59% : 0.000002s : 8: predicate.opt_reshape 0.48% : 0.000002s : 8: predicate.parallel_virtual_node 1.49% : 0.000005s : 26: predicate.partial_defer_inline 1.21% : 0.000004s : 29: predicate.partial_eliminate 0.94% : 0.000003s : 21: predicate.print_const_string_wrapper 0.69% : 0.000002s : 16: predicate.reduce_all_const_elim 1.35% : 0.000005s : 21: predicate.reduce_eliminate 2.25% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.22% : 0.000004s : 37: predicate.replace_applicator 0.40% : 0.000001s : 16: predicate.replace_old_param 0.30% : 0.000001s : 8: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.69% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.42% : 0.000001s : 8: predicate.row_tensor_eliminate 1.12% : 0.000004s : 16: predicate.same_eliminate 0.44% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.82% : 0.000003s : 16: predicate.shard_identity_eliminate 0.81% : 0.000003s : 16: predicate.special_op_eliminate 0.79% : 0.000003s : 16: predicate.specialize_transform 1.04% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.35% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.17% : 0.000004s : 26: predicate.switch_defer_inline 1.80% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.06% : 0.000014s : 86: predicate.switch_simplify 0.88% : 0.000003s : 21: predicate.tile_eliminate 0.91% : 0.000003s : 21: predicate.transpose_eliminate 1.82% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.72% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.63% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.78% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.51% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.57% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.17% : 0.000007s : 58: predicate.updatestate_pure_node_eliminater 2.97% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 8: predicate.value_based_eliminate 0.77% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.85% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.49% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005944 32 70.65% : 0.004199s : 25: func_graph_cloner_run.FuncGraphClonerGraph 29.35% : 0.001745s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.588599 192 0.00% : 0.000004s : 1: ForceFp32Comm 6.37% : 0.101165s : 1: add_attr 6.37% : 0.101144s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000098s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000123s : 1: auto_monad 0.00% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.06% : 0.000874s : 1: bootstrap 0.00% : 0.000038s : 1: cconv 0.00% : 0.000062s : 1: comm_op_add_attrs 0.00% : 0.000057s : 1: control_data_broadcast_order 0.00% : 0.000016s : 1: convert_after_rewriter 0.00% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.00% : 0.000033s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000012s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.03% : 0.000544s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.05% : 0.000820s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 0.13% : 0.002096s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000053s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000259s : 28: opt.transform.opt_b 0.01% : 0.000123s : 2: opt.transform.opt_trans_graph 0.01% : 0.000097s : 4: opt.transform.symbol_engine_opt 0.63% : 0.010075s : 1: opt_a 0.01% : 0.000164s : 1: opt_after_cconv 0.06% : 0.000887s : 1: opt_after_jit_grad 0.03% : 0.000408s : 1: opt_b 1.50% : 0.023845s : 1: optimize 0.00% : 0.000030s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000013s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000051s : 1: pre_auto_parallel 0.00% : 0.000035s : 1: py_interpret_to_execute 0.00% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000063s : 1: remove_dup_value 0.28% : 0.004417s : 1: renormalize.infer 0.15% : 0.002315s : 1: renormalize.specialize 0.65% : 0.010276s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000272s : 1: rewriter_after_opt_a 0.01% : 0.000094s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000198s : 1: symbol_engine_optimizer 0.01% : 0.000156s : 1: tuple_transform 83.54% : 1.327145s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[False-float32--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-float32--1-shape1],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:04.474.571 [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 = 1.69269, [21] [bootstrap]: 0.00081266 [type_inference]: 1.55387 [event_method]: 2.669e-05 [auto_monad]: 9.478e-05 [graph_reusing]: 6.46e-06 [inline]: 3.75e-06 [add_attr]: 0.00575904, [1] [add_attr_with_inline]: 0.00573974, [1] [Cycle 1]: 7.967e-05, [2] [tag_attr]: 2.669e-05 [meta_addattr_fg_expand]: 6.12001e-06 [parallel-infer-symbol]: 4.29997e-06 [pre_auto_parallel]: 4.781e-05 [insert-virtual-dataset]: 2.85998e-06 [parallel-infer-symbol-second]: 8.09989e-07 [dataset_repeat_opt]: 1.89999e-06 [pipeline_split]: 1.89999e-06 [optimize]: 0.13111, [53] [py_interpret_to_execute]: 3.838e-05 [rewriter_before_opt_a]: 9.097e-05 [opt_a]: 0.127529, [2] [Cycle 1]: 0.126258, [45] [expand_dump_flag]: 3.41001e-06 [switch_simplify]: 4.418e-05 [loop_unroll]: 2.741e-05 [a_1]: 0.00100289 [with_stream_mark]: 2.639e-05 [recompute_prepare]: 6.959e-05 [updatestate_depend_eliminate]: 8.87e-06 [updatestate_assign_eliminate]: 6.12999e-06 [updatestate_loads_eliminate]: 5.72999e-06 [parameter_eliminate]: 2.59999e-06 [a_2]: 0.00019016 [accelerated_algorithm]: 1.289e-05 [shard]: 2.69999e-06 [meta_shard_fg_expand]: 3.66001e-06 [shard_inline]: 1.124e-05 [merge_send_recv]: 1.326e-05 [auto_parallel]: 1.241e-05 [parallel]: 2.954e-05 [flash_sp]: 1.042e-05 [merge_comm]: 6.76999e-06 [allreduce_fusion]: 6.46e-06 [matmul_add_comm_reduction]: 1.687e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 1.396e-05 [virtual_dataset]: 1.196e-05 [get_grad_eliminate_]: 1.195e-05 [virtual_output]: 1.193e-05 [merge_forward]: 8.46002e-06 [cell_reuse_recompute_pass]: 1.31998e-06 [offload_activation]: 1.679e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.449e-05 [merge_recompute_call_nodes]: 1.46002e-06 [before_grad]: 1.991e-05 [set_forward_comm_id_for_comm_node_pass]: 7.01999e-06 [meta_fg_expand]: 5.14e-06 [flash_sp_send_recv_attached]: 2.59001e-06 [receive_attached]: 2.51e-06 [after_resolve]: 1.734e-05 [a_after_grad]: 1.993e-05 [renormalize]: 0.123332 [add_forward_monad_depend]: 1.404e-05 [auto_monad_grad]: 2.89999e-06 [auto_monad_eliminator]: 3.742e-05 [cse]: 0.00072665 [a_3]: 0.0001136 [Cycle 2]: 0.00125312, [45] [expand_dump_flag]: 3.51001e-06 [switch_simplify]: 1.595e-05 [loop_unroll]: 1.201e-05 [a_1]: 0.00035115 [with_stream_mark]: 3.379e-05 [recompute_prepare]: 1.396e-05 [updatestate_depend_eliminate]: 8.64998e-06 [updatestate_assign_eliminate]: 6.11998e-06 [updatestate_loads_eliminate]: 5.52999e-06 [parameter_eliminate]: 2.69001e-06 [a_2]: 0.00015962 [accelerated_algorithm]: 1.214e-05 [shard]: 2.99001e-06 [meta_shard_fg_expand]: 3.56001e-06 [shard_inline]: 1.058e-05 [merge_send_recv]: 1.317e-05 [auto_parallel]: 1.456e-05 [parallel]: 1.038e-05 [flash_sp]: 4.05998e-06 [merge_comm]: 6.83e-06 [allreduce_fusion]: 5.96e-06 [matmul_add_comm_reduction]: 1.628e-05 [allreduce_slice_to_reducescatter]: 8.00006e-07 [virtual_shard_identity]: 1.331e-05 [virtual_dataset]: 1.197e-05 [get_grad_eliminate_]: 1.19e-05 [virtual_output]: 1.07e-05 [merge_forward]: 7.03998e-06 [cell_reuse_recompute_pass]: 3.62002e-06 [offload_activation]: 1.521e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.117e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 1.841e-05 [set_forward_comm_id_for_comm_node_pass]: 6.67002e-06 [meta_fg_expand]: 5.58997e-06 [flash_sp_send_recv_attached]: 1.83002e-06 [receive_attached]: 2.63e-06 [after_resolve]: 1.693e-05 [a_after_grad]: 1.765e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.25e-06 [auto_monad_grad]: 2.44999e-06 [auto_monad_eliminator]: 2.059e-05 [cse]: 4.887e-05 [a_3]: 7.106e-05 [py_interpret_to_execute_after_opt_a]: 2.752e-05 [slice_cell_reuse_recomputed_activation]: 2.88e-06 [rewriter_after_opt_a]: 0.00030158 [convert_after_rewriter]: 1.369e-05 [order_py_execute_after_rewriter]: 9.51003e-06 [mutable_eliminate]: 0.00086918 [opt_b]: 0.00047948, [1] [Cycle 1]: 0.00046941, [7] [b_1]: 0.00030456 [b_2]: 1.366e-05 [updatestate_depend_eliminate]: 2.801e-05 [updatestate_assign_eliminate]: 6.04999e-06 [updatestate_loads_eliminate]: 5.32001e-06 [renormalize]: 1.34e-06 [cse]: 6.589e-05 [optimize_parallel_all_gather_comm]: 3.028e-05 [overlap_param_gather]: 2.02001e-06 [cconv]: 4.125e-05 [loop_unroll]: 0.00058243 [opt_after_cconv]: 0.0001667, [1] [Cycle 1]: 0.00015758, [7] [c_1]: 5.74e-05 [parameter_eliminate]: 5.72999e-06 [updatestate_depend_eliminate]: 1.071e-05 [updatestate_assign_eliminate]: 4.99998e-06 [updatestate_loads_eliminate]: 4.85999e-06 [cse]: 3.925e-05 [renormalize]: 4.19997e-07 [remove_dup_value]: 6.916e-05 [tuple_transform]: 0.00015896, [1] [Cycle 1]: 0.00015323, [4] [d_1]: 0.00011462 [none_parameter_eliminate]: 2.61999e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 1.294e-05 [partial_unused_args_eliminate]: 2.51998e-06 [add_recomputation]: 9.789e-05 [cse_after_recomputation]: 4.297e-05, [1] [Cycle 1]: 3.697e-05, [1] [cse]: 3.077e-05 [environ_conv]: 1.598e-05 [swap_dp_allreduce_reducescatter]: 9.69e-06 [bias_add_comm_swap]: 3.51001e-06 [label_micro_interleaved_index]: 6.18998e-06 [label_fine_grained_interleaved_index]: 2.78e-06 [merge_cast_opt]: 1.32999e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.92002e-06 [assign_add_opt]: 1.21997e-06 [ForceFp32Comm]: 8.49977e-07 [remove_cast_before_assign_add]: 1.24998e-06 [full_micro_interleaved_order_control]: 2.68998e-06 [reorder_send_recv_between_fp_bp]: 2.98998e-06 [comm_op_add_attrs]: 1.25999e-06 [add_comm_op_reuse_tag]: 1.13001e-06 [interleave_split_concat_branches]: 1.99e-06 [interleave_parallel_branches]: 1.22e-06 [overlap_opt_shard_in_pipeline]: 1.52001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.97999e-06 [control_data_broadcast_order]: 2.154e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 7.17002e-06 [overlap_recompute_and_grad_model_parallel]: 8e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.49998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.35999e-06 [overlap_recompute_comm]: 2.04e-06 [overlap_grad_ring_attention]: 5.94e-06 [overlap_grad_flash_sp]: 3.07e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.37001e-06 [split_layernorm_comm]: 1.82999e-06 [handle_group_info]: 1.19e-06 [symbol_engine_optimizer]: 0.00012846, [1] [Cycle 1]: 0.00012376, [6] [build]: 1.502e-05 [elim_shapecalc]: 1.799e-05 [elim_not_effective]: 2.425e-05 [opt_reshape]: 1.222e-05 [fold_const_symbol]: 1.885e-05 [renormalize]: 4.40021e-07 [detach_backward]: 3.73001e-06 [pipeline_parallel_scheduler]: 1.39e-06 [auto_monad_reorder]: 2.85e-05 [get_jit_bprop_graph]: 2.13998e-06 [rewriter_after_jit_bprop_graph]: 6.06e-06 [opt_after_jit_grad]: 0.0006152 [validate]: 7.409e-05 Sums bootstrap : 0.000813s : 0.05% type_inference : 1.553870s : 92.18% event_method : 0.000027s : 0.00% auto_monad : 0.000095s : 0.01% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000048s : 0.00% 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 : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000091s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001354s : 0.08% optimize.opt_a.with_stream_mark : 0.000060s : 0.00% optimize.opt_a.recompute_prepare : 0.000084s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000350s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000025s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000026s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000040s : 0.00% optimize.opt_a.flash_sp : 0.000014s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000032s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000046s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000038s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000034s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.123332s : 7.32% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000058s : 0.00% optimize.opt_a.cse : 0.000776s : 0.05% optimize.opt_a.a_3 : 0.000185s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000302s : 0.02% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000869s : 0.05% optimize.opt_b.b_1 : 0.000305s : 0.02% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000028s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000066s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000582s : 0.03% optimize.opt_after_cconv.c_1 : 0.000057s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000039s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000069s : 0.00% optimize.tuple_transform.d_1 : 0.000115s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000098s : 0.01% optimize.cse_after_recomputation.cse : 0.000031s : 0.00% optimize.environ_conv : 0.000016s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% 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 : 0.000003s : 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 : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 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 : 0.000015s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000024s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.00% 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 : 0.000029s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000615s : 0.04% validate : 0.000074s : 0.00% Time group info: ------[substitution.] 0.000457 111 9.67% : 0.000044s : 6: substitution.arithmetic_simplify 0.93% : 0.000004s : 6: substitution.elim_not_effective 2.71% : 0.000012s : 6: substitution.float_tuple_getitem_switch 0.53% : 0.000002s : 6: substitution.fold_const_symbol 2.01% : 0.000009s : 8: substitution.graph_param_transform 44.71% : 0.000204s : 5: substitution.inline 1.65% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.26% : 0.000010s : 4: substitution.minmaximum_grad 2.16% : 0.000010s : 12: substitution.remove_not_recompute_node 1.48% : 0.000007s : 2: substitution.replace_old_param 7.82% : 0.000036s : 8: substitution.tuple_list_convert_item_index_to_positive 3.26% : 0.000015s : 8: substitution.tuple_list_get_item_const_eliminator 4.60% : 0.000021s : 8: substitution.tuple_list_get_item_depend_reorder 11.42% : 0.000052s : 12: substitution.tuple_list_get_item_eliminator 4.79% : 0.000022s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.553459 2 99.73% : 1.549318s : 1: type_inference.infer 0.27% : 0.004141s : 1: type_inference.specialize ------[replace.] 0.000047 5 100.00% : 0.000047s : 5: replace.inline ------[match.] 0.000200 5 100.00% : 0.000200s : 5: match.inline ------[predicate.] 0.000354 2113 0.89% : 0.000003s : 21: predicate.accumulaten_eliminater 1.03% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.64% : 0.000002s : 16: predicate.addn_check_dump 1.03% : 0.000004s : 21: predicate.addn_zero_filter 0.91% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.47% : 0.000009s : 37: predicate.arithmetic_simplify 0.91% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000002s : 16: predicate.check_bprop_eliminate 0.64% : 0.000002s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.62% : 0.000002s : 16: predicate.depend_value_elim 0.82% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.90% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.84% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.92% : 0.000003s : 16: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 8: predicate.elim_not_effective 0.45% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.17% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.18% : 0.000004s : 29: predicate.environ_get_depend_swap 1.87% : 0.000007s : 45: predicate.environ_get_eliminate 1.23% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.00% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.78% : 0.000006s : 26: predicate.float_depend_g_call 0.66% : 0.000002s : 16: predicate.float_environ_get_switch 1.12% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.75% : 0.000003s : 16: predicate.get_grad_eliminate 0.25% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000002s : 16: predicate.incorporate_call 0.58% : 0.000002s : 16: predicate.incorporate_call_switch 5.53% : 0.000020s : 95: predicate.inline 0.87% : 0.000003s : 16: predicate.inline_without_move 0.32% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.88% : 0.000003s : 16: predicate.less_batch_normalization 1.72% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.28% : 0.000008s : 58: predicate.load_eliminater 1.09% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.52% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.69% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.69% : 0.000002s : 16: predicate.merge_addn 0.75% : 0.000003s : 16: predicate.micro_step_allgather_replace 0.66% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.87% : 0.000003s : 21: predicate.minmaximum_grad 1.53% : 0.000005s : 8: predicate.mutable_eliminate 0.42% : 0.000001s : 8: predicate.opt_reshape 0.52% : 0.000002s : 8: predicate.parallel_virtual_node 1.73% : 0.000006s : 26: predicate.partial_defer_inline 1.19% : 0.000004s : 29: predicate.partial_eliminate 0.87% : 0.000003s : 21: predicate.print_const_string_wrapper 0.68% : 0.000002s : 16: predicate.reduce_all_const_elim 1.33% : 0.000005s : 21: predicate.reduce_eliminate 2.31% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.37% : 0.000001s : 16: predicate.remove_not_recompute_node 1.23% : 0.000004s : 37: predicate.replace_applicator 0.62% : 0.000002s : 16: predicate.replace_old_param 0.29% : 0.000001s : 8: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.81% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.42% : 0.000001s : 8: predicate.row_tensor_eliminate 1.28% : 0.000005s : 16: predicate.same_eliminate 0.48% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.85% : 0.000003s : 16: predicate.shard_identity_eliminate 0.83% : 0.000003s : 16: predicate.special_op_eliminate 0.77% : 0.000003s : 16: predicate.specialize_transform 1.14% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.34% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.13% : 0.000004s : 26: predicate.switch_defer_inline 1.77% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.09% : 0.000014s : 86: predicate.switch_simplify 0.86% : 0.000003s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.84% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.92% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.61% : 0.000013s : 53: predicate.tuple_list_get_item_eliminator 1.71% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.56% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.59% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.14% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 3.05% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.47% : 0.000002s : 8: predicate.value_based_eliminate 0.74% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.87% : 0.000003s : 16: predicate.virtual_output_eliminate 0.33% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.47% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.098624 32 97.68% : 0.096337s : 25: func_graph_cloner_run.FuncGraphClonerGraph 2.32% : 0.002287s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.955573 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.29% : 0.005766s : 1: add_attr 0.29% : 0.005744s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000103s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000100s : 1: auto_monad 0.00% : 0.000034s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000858s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000046s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.00% : 0.000036s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 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% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000594s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.05% : 0.000886s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000024s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.12% : 0.002259s : 78: opt.transform.opt_a 0.00% : 0.000056s : 1: opt.transform.opt_after_cconv 0.00% : 0.000048s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000283s : 28: opt.transform.opt_b 0.01% : 0.000124s : 2: opt.transform.opt_trans_graph 0.00% : 0.000069s : 4: opt.transform.symbol_engine_opt 6.52% : 0.127534s : 1: opt_a 0.01% : 0.000170s : 1: opt_after_cconv 0.03% : 0.000628s : 1: opt_after_jit_grad 0.02% : 0.000484s : 1: opt_b 6.70% : 0.131118s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000004s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000053s : 1: pre_auto_parallel 0.00% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000074s : 1: remove_dup_value 6.18% : 0.120809s : 1: renormalize.infer 0.13% : 0.002504s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000313s : 1: rewriter_after_opt_a 0.00% : 0.000096s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000131s : 1: symbol_engine_optimizer 0.01% : 0.000162s : 1: tuple_transform 79.46% : 1.553910s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[False-float16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-float16--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:08.777.900 [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 = 1.96383, [21] [bootstrap]: 0.00148194 [type_inference]: 1.63685 [event_method]: 2.67e-05 [auto_monad]: 0.00010468 [graph_reusing]: 7.36999e-06 [inline]: 3.52002e-06 [add_attr]: 0.155353, [1] [add_attr_with_inline]: 0.155332, [1] [Cycle 1]: 8.313e-05, [2] [tag_attr]: 2.55e-05 [meta_addattr_fg_expand]: 6.66999e-06 [parallel-infer-symbol]: 4.43999e-06 [pre_auto_parallel]: 4.864e-05 [insert-virtual-dataset]: 2.57001e-06 [parallel-infer-symbol-second]: 7.50006e-07 [dataset_repeat_opt]: 2.07999e-06 [pipeline_split]: 2.04e-06 [optimize]: 0.168673, [53] [py_interpret_to_execute]: 4.05e-05 [rewriter_before_opt_a]: 9.343e-05 [opt_a]: 0.0113932, [2] [Cycle 1]: 0.00969454, [45] [expand_dump_flag]: 3.36001e-06 [switch_simplify]: 4.35e-05 [loop_unroll]: 2.718e-05 [a_1]: 0.00105964 [with_stream_mark]: 2.793e-05 [recompute_prepare]: 1.985e-05 [updatestate_depend_eliminate]: 7.72002e-06 [updatestate_assign_eliminate]: 7.15003e-06 [updatestate_loads_eliminate]: 6.12001e-06 [parameter_eliminate]: 2.35002e-06 [a_2]: 0.00018986 [accelerated_algorithm]: 1.397e-05 [shard]: 3.18998e-06 [meta_shard_fg_expand]: 3.63e-06 [shard_inline]: 1.199e-05 [merge_send_recv]: 1.261e-05 [auto_parallel]: 1.319e-05 [parallel]: 3.033e-05 [flash_sp]: 1.209e-05 [merge_comm]: 7.11001e-06 [allreduce_fusion]: 6.17999e-06 [matmul_add_comm_reduction]: 1.731e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 1.422e-05 [virtual_dataset]: 1.214e-05 [get_grad_eliminate_]: 1.317e-05 [virtual_output]: 1.239e-05 [merge_forward]: 8.10999e-06 [cell_reuse_recompute_pass]: 1.34e-06 [offload_activation]: 1.709e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.521e-05 [merge_recompute_call_nodes]: 1.70001e-06 [before_grad]: 2.187e-05 [set_forward_comm_id_for_comm_node_pass]: 7.08e-06 [meta_fg_expand]: 5.51e-06 [flash_sp_send_recv_attached]: 2.74999e-06 [receive_attached]: 2.58e-06 [after_resolve]: 1.739e-05 [a_after_grad]: 2.235e-05 [renormalize]: 0.00690104 [add_forward_monad_depend]: 1.395e-05 [auto_monad_grad]: 3.48e-06 [auto_monad_eliminator]: 3.955e-05 [cse]: 0.00056893 [a_3]: 0.00011418 [Cycle 2]: 0.00168236, [45] [expand_dump_flag]: 3.03e-06 [switch_simplify]: 1.526e-05 [loop_unroll]: 1.282e-05 [a_1]: 0.00036635 [with_stream_mark]: 3.346e-05 [recompute_prepare]: 1.317e-05 [updatestate_depend_eliminate]: 9.12001e-06 [updatestate_assign_eliminate]: 6.31e-06 [updatestate_loads_eliminate]: 6.11e-06 [parameter_eliminate]: 2.35002e-06 [a_2]: 0.00019297 [accelerated_algorithm]: 1.237e-05 [shard]: 3.61001e-06 [meta_shard_fg_expand]: 5.44e-06 [shard_inline]: 1.141e-05 [merge_send_recv]: 1.426e-05 [auto_parallel]: 1.514e-05 [parallel]: 1.044e-05 [flash_sp]: 5.30999e-06 [merge_comm]: 6.26e-06 [allreduce_fusion]: 6.09999e-06 [matmul_add_comm_reduction]: 1.633e-05 [allreduce_slice_to_reducescatter]: 1.34e-06 [virtual_shard_identity]: 1.27e-05 [virtual_dataset]: 1.135e-05 [get_grad_eliminate_]: 1.214e-05 [virtual_output]: 1.096e-05 [merge_forward]: 8.25e-06 [cell_reuse_recompute_pass]: 3.63e-06 [offload_activation]: 1.659e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.263e-05 [merge_recompute_call_nodes]: 1.80001e-06 [before_grad]: 1.915e-05 [set_forward_comm_id_for_comm_node_pass]: 6.68e-06 [meta_fg_expand]: 5.66998e-06 [flash_sp_send_recv_attached]: 2.41e-06 [receive_attached]: 3.54002e-06 [after_resolve]: 1.769e-05 [a_after_grad]: 1.806e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.26999e-06 [auto_monad_grad]: 2.06e-06 [auto_monad_eliminator]: 2.242e-05 [cse]: 0.00038863 [a_3]: 8.123e-05 [py_interpret_to_execute_after_opt_a]: 2.704e-05 [slice_cell_reuse_recomputed_activation]: 3.71001e-06 [rewriter_after_opt_a]: 0.00031969 [convert_after_rewriter]: 1.521e-05 [order_py_execute_after_rewriter]: 8.77e-06 [mutable_eliminate]: 0.00092126 [opt_b]: 0.00046911, [1] [Cycle 1]: 0.00045859, [7] [b_1]: 0.00031046 [b_2]: 1.386e-05 [updatestate_depend_eliminate]: 1.301e-05 [updatestate_assign_eliminate]: 6.20997e-06 [updatestate_loads_eliminate]: 5.27001e-06 [renormalize]: 1.31998e-06 [cse]: 6.558e-05 [optimize_parallel_all_gather_comm]: 3.294e-05 [overlap_param_gather]: 2.14999e-06 [cconv]: 4.353e-05 [loop_unroll]: 0.153972 [opt_after_cconv]: 0.00023448, [1] [Cycle 1]: 0.00022116, [7] [c_1]: 6.69e-05 [parameter_eliminate]: 7.31001e-06 [updatestate_depend_eliminate]: 1.991e-05 [updatestate_assign_eliminate]: 5.97999e-06 [updatestate_loads_eliminate]: 5.56e-06 [cse]: 7.653e-05 [renormalize]: 1.00999e-06 [remove_dup_value]: 8.154e-05 [tuple_transform]: 0.00018387, [1] [Cycle 1]: 0.00017753, [4] [d_1]: 0.00013846 [none_parameter_eliminate]: 2.16e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 1.281e-05 [partial_unused_args_eliminate]: 2.61e-06 [add_recomputation]: 0.00010828 [cse_after_recomputation]: 4.659e-05, [1] [Cycle 1]: 3.984e-05, [1] [cse]: 3.332e-05 [environ_conv]: 1.876e-05 [swap_dp_allreduce_reducescatter]: 1.032e-05 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 8.55001e-06 [label_fine_grained_interleaved_index]: 3.43999e-06 [merge_cast_opt]: 1.43002e-06 [slice_recompute_activation]: 2.22999e-06 [micro_interleaved_order_control]: 2.51e-06 [assign_add_opt]: 1.74998e-06 [ForceFp32Comm]: 1.05999e-06 [remove_cast_before_assign_add]: 1.14998e-06 [full_micro_interleaved_order_control]: 2.34001e-06 [reorder_send_recv_between_fp_bp]: 3.12002e-06 [comm_op_add_attrs]: 1.19e-06 [add_comm_op_reuse_tag]: 1.11002e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 1.86e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06e-06 [control_data_broadcast_order]: 2.462e-05 [grouped_pairwise_exchange_alltoall]: 1.76e-06 [offloading_packed_experts]: 7.66001e-06 [overlap_recompute_and_grad_model_parallel]: 7.75998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37999e-06 [overlap_recompute_comm]: 2.29001e-06 [overlap_grad_ring_attention]: 6.54999e-06 [overlap_grad_flash_sp]: 3.262e-05 [begin_end_overlap_inline]: 6.99976e-07 [split_matmul_comm_elemetwise]: 2.86e-06 [split_layernorm_comm]: 1.96e-06 [handle_group_info]: 1.92001e-06 [symbol_engine_optimizer]: 0.00018203, [1] [Cycle 1]: 0.00017735, [6] [build]: 1.493e-05 [elim_shapecalc]: 7.269e-05 [elim_not_effective]: 2.487e-05 [opt_reshape]: 1.326e-05 [fold_const_symbol]: 1.96e-05 [renormalize]: 1.80007e-07 [detach_backward]: 3.76999e-06 [pipeline_parallel_scheduler]: 1.79e-06 [auto_monad_reorder]: 2.75e-05 [get_jit_bprop_graph]: 2.38002e-06 [rewriter_after_jit_bprop_graph]: 7.71999e-06 [opt_after_jit_grad]: 0.00075311 [validate]: 8.114e-05 Sums bootstrap : 0.001482s : 0.08% type_inference : 1.636852s : 90.58% event_method : 0.000027s : 0.00% auto_monad : 0.000105s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.00% 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 : 0.000041s : 0.00% optimize.rewriter_before_opt_a : 0.000093s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001426s : 0.08% optimize.opt_a.with_stream_mark : 0.000061s : 0.00% optimize.opt_a.recompute_prepare : 0.000033s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000383s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000027s : 0.00% optimize.opt_a.auto_parallel : 0.000028s : 0.00% optimize.opt_a.parallel : 0.000041s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000013s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000034s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000025s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000040s : 0.00% optimize.opt_a.renormalize : 0.006901s : 0.38% 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 : 0.000062s : 0.00% optimize.opt_a.cse : 0.000958s : 0.05% optimize.opt_a.a_3 : 0.000195s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000320s : 0.02% optimize.convert_after_rewriter : 0.000015s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000921s : 0.05% optimize.opt_b.b_1 : 0.000310s : 0.02% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000066s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.153972s : 8.52% optimize.opt_after_cconv.c_1 : 0.000067s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000077s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000082s : 0.00% optimize.tuple_transform.d_1 : 0.000138s : 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 : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000108s : 0.01% optimize.cse_after_recomputation.cse : 0.000033s : 0.00% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 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 : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000025s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000033s : 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000015s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000073s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000028s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000753s : 0.04% validate : 0.000081s : 0.00% Time group info: ------[substitution.] 0.000492 111 9.98% : 0.000049s : 6: substitution.arithmetic_simplify 0.86% : 0.000004s : 6: substitution.elim_not_effective 2.42% : 0.000012s : 6: substitution.float_tuple_getitem_switch 0.51% : 0.000003s : 6: substitution.fold_const_symbol 2.00% : 0.000010s : 8: substitution.graph_param_transform 43.28% : 0.000213s : 5: substitution.inline 1.61% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.43% : 0.000012s : 4: substitution.minmaximum_grad 2.23% : 0.000011s : 12: substitution.remove_not_recompute_node 1.37% : 0.000007s : 2: substitution.replace_old_param 7.71% : 0.000038s : 8: substitution.tuple_list_convert_item_index_to_positive 3.29% : 0.000016s : 8: substitution.tuple_list_get_item_const_eliminator 5.04% : 0.000025s : 8: substitution.tuple_list_get_item_depend_reorder 12.28% : 0.000060s : 12: substitution.tuple_list_get_item_eliminator 4.99% : 0.000025s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.636717 2 99.73% : 1.632287s : 1: type_inference.infer 0.27% : 0.004431s : 1: type_inference.specialize ------[replace.] 0.000051 5 100.00% : 0.000051s : 5: replace.inline ------[match.] 0.000209 5 100.00% : 0.000209s : 5: match.inline ------[predicate.] 0.000366 2113 0.85% : 0.000003s : 21: predicate.accumulaten_eliminater 1.04% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.64% : 0.000002s : 16: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.80% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.24% : 0.000008s : 37: predicate.arithmetic_simplify 0.89% : 0.000003s : 21: predicate.cast_eliminate 0.72% : 0.000003s : 16: predicate.check_bprop_eliminate 0.69% : 0.000003s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.66% : 0.000002s : 16: predicate.depend_value_elim 0.94% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.01% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.82% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.03% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 8: predicate.elim_not_effective 0.45% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.16% : 0.000004s : 29: predicate.environ_get_depend_swap 1.81% : 0.000007s : 45: predicate.environ_get_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.07% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.70% : 0.000006s : 26: predicate.float_depend_g_call 0.63% : 0.000002s : 16: predicate.float_environ_get_switch 1.06% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.91% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000002s : 16: predicate.incorporate_call 0.61% : 0.000002s : 16: predicate.incorporate_call_switch 5.60% : 0.000020s : 95: predicate.inline 0.92% : 0.000003s : 16: predicate.inline_without_move 0.31% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.85% : 0.000003s : 16: predicate.less_batch_normalization 1.77% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.20% : 0.000008s : 58: predicate.load_eliminater 2.40% : 0.000009s : 8: predicate.loop_unroll_after_grad 1.51% : 0.000006s : 36: predicate.loop_unroll_before_grad 2.07% : 0.000008s : 37: predicate.make_slice_get_slice_eliminator 0.68% : 0.000002s : 16: predicate.merge_addn 0.64% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.71% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.82% : 0.000003s : 21: predicate.minmaximum_grad 1.23% : 0.000004s : 8: predicate.mutable_eliminate 0.54% : 0.000002s : 8: predicate.opt_reshape 0.47% : 0.000002s : 8: predicate.parallel_virtual_node 1.46% : 0.000005s : 26: predicate.partial_defer_inline 1.15% : 0.000004s : 29: predicate.partial_eliminate 0.86% : 0.000003s : 21: predicate.print_const_string_wrapper 0.70% : 0.000003s : 16: predicate.reduce_all_const_elim 1.29% : 0.000005s : 21: predicate.reduce_eliminate 2.27% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.20% : 0.000004s : 37: predicate.replace_applicator 0.49% : 0.000002s : 16: predicate.replace_old_param 0.35% : 0.000001s : 8: predicate.reset_defer_inline 0.89% : 0.000003s : 21: predicate.reshape_eliminate 0.72% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 8: predicate.row_tensor_eliminate 1.08% : 0.000004s : 16: predicate.same_eliminate 0.40% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.83% : 0.000003s : 16: predicate.shard_identity_eliminate 0.87% : 0.000003s : 16: predicate.special_op_eliminate 0.73% : 0.000003s : 16: predicate.specialize_transform 1.27% : 0.000005s : 16: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.39% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.13% : 0.000004s : 26: predicate.switch_defer_inline 1.85% : 0.000007s : 42: predicate.switch_layer_defer_inline 3.80% : 0.000014s : 86: predicate.switch_simplify 0.82% : 0.000003s : 21: predicate.tile_eliminate 0.94% : 0.000003s : 21: predicate.transpose_eliminate 1.78% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.79% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.60% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.39% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.78% : 0.000007s : 37: predicate.tuple_list_get_set_item_eliminator 2.73% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.59% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.25% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 3.01% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.43% : 0.000002s : 8: predicate.value_based_eliminate 0.70% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.71% : 0.000003s : 16: predicate.virtual_output_eliminate 0.31% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.42% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006609 32 65.11% : 0.004303s : 25: func_graph_cloner_run.FuncGraphClonerGraph 34.89% : 0.002306s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.297583 192 0.00% : 0.000004s : 1: ForceFp32Comm 6.76% : 0.155361s : 1: add_attr 6.76% : 0.155337s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000114s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000126s : 1: auto_monad 0.00% : 0.000032s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.07% : 0.001646s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.00% : 0.000035s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 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% : 0.000012s : 1: label_micro_interleaved_index 6.70% : 0.154004s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000936s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000054s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.10% : 0.002326s : 78: opt.transform.opt_a 0.00% : 0.000065s : 1: opt.transform.opt_after_cconv 0.00% : 0.000051s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000288s : 28: opt.transform.opt_b 0.01% : 0.000149s : 2: opt.transform.opt_trans_graph 0.01% : 0.000126s : 4: opt.transform.symbol_engine_opt 0.50% : 0.011397s : 1: opt_a 0.01% : 0.000240s : 1: opt_after_cconv 0.03% : 0.000767s : 1: opt_after_jit_grad 0.02% : 0.000473s : 1: opt_b 7.34% : 0.168679s : 1: optimize 0.00% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000036s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000053s : 1: pre_auto_parallel 0.00% : 0.000045s : 1: py_interpret_to_execute 0.00% : 0.000055s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000087s : 1: remove_dup_value 0.18% : 0.004230s : 1: renormalize.infer 0.12% : 0.002652s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000328s : 1: rewriter_after_opt_a 0.00% : 0.000098s : 1: rewriter_before_opt_a 0.00% : 0.000009s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000185s : 1: symbol_engine_optimizer 0.01% : 0.000187s : 1: tuple_transform 71.24% : 1.636901s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[False-float16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-float16--1-shape1],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:13.748.539 [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 = 2.23522, [21] [bootstrap]: 0.00069455 [type_inference]: 2.02451 [event_method]: 2.491e-05 [auto_monad]: 9e-05 [graph_reusing]: 6.48998e-06 [inline]: 3.55e-06 [add_attr]: 0.00646091, [1] [add_attr_with_inline]: 0.00644353, [1] [Cycle 1]: 7.922e-05, [2] [tag_attr]: 2.639e-05 [meta_addattr_fg_expand]: 5.87001e-06 [parallel-infer-symbol]: 3.83001e-06 [pre_auto_parallel]: 5.251e-05 [insert-virtual-dataset]: 2.96001e-06 [parallel-infer-symbol-second]: 7.79983e-07 [dataset_repeat_opt]: 1.99e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.202473, [53] [py_interpret_to_execute]: 3.834e-05 [rewriter_before_opt_a]: 9.319e-05 [opt_a]: 0.199042, [2] [Cycle 1]: 0.197319, [45] [expand_dump_flag]: 3.38999e-06 [switch_simplify]: 4.243e-05 [loop_unroll]: 2.631e-05 [a_1]: 0.0010305 [with_stream_mark]: 2.652e-05 [recompute_prepare]: 1.751e-05 [updatestate_depend_eliminate]: 8.95001e-06 [updatestate_assign_eliminate]: 6.16998e-06 [updatestate_loads_eliminate]: 5.59998e-06 [parameter_eliminate]: 2.64999e-06 [a_2]: 0.00019068 [accelerated_algorithm]: 1.38e-05 [shard]: 2.43998e-06 [meta_shard_fg_expand]: 3.51001e-06 [shard_inline]: 1.116e-05 [merge_send_recv]: 1.487e-05 [auto_parallel]: 1.223e-05 [parallel]: 2.995e-05 [flash_sp]: 1.273e-05 [merge_comm]: 7.3e-06 [allreduce_fusion]: 7.11999e-06 [matmul_add_comm_reduction]: 1.719e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 1.788e-05 [virtual_dataset]: 1.389e-05 [get_grad_eliminate_]: 1.264e-05 [virtual_output]: 1.228e-05 [merge_forward]: 7.16001e-06 [cell_reuse_recompute_pass]: 1.92999e-06 [offload_activation]: 1.866e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.353e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 2.26e-05 [set_forward_comm_id_for_comm_node_pass]: 6.92002e-06 [meta_fg_expand]: 5.53002e-06 [flash_sp_send_recv_attached]: 3.36999e-06 [receive_attached]: 2.44001e-06 [after_resolve]: 1.657e-05 [a_after_grad]: 2.098e-05 [renormalize]: 0.194866 [add_forward_monad_depend]: 1.439e-05 [auto_monad_grad]: 3.57997e-06 [auto_monad_eliminator]: 3.636e-05 [cse]: 0.0002542 [a_3]: 0.00010716 [Cycle 2]: 0.00170641, [45] [expand_dump_flag]: 2.75002e-06 [switch_simplify]: 1.529e-05 [loop_unroll]: 1.205e-05 [a_1]: 0.00040548 [with_stream_mark]: 0.0004121 [recompute_prepare]: 2.355e-05 [updatestate_depend_eliminate]: 1.348e-05 [updatestate_assign_eliminate]: 6.11e-06 [updatestate_loads_eliminate]: 5.64e-06 [parameter_eliminate]: 3.53e-06 [a_2]: 0.00017568 [accelerated_algorithm]: 1.205e-05 [shard]: 3.08e-06 [meta_shard_fg_expand]: 4.4e-06 [shard_inline]: 1.071e-05 [merge_send_recv]: 1.258e-05 [auto_parallel]: 1.53e-05 [parallel]: 1.092e-05 [flash_sp]: 5.26998e-06 [merge_comm]: 6.39001e-06 [allreduce_fusion]: 5.86e-06 [matmul_add_comm_reduction]: 1.517e-05 [allreduce_slice_to_reducescatter]: 1.08001e-06 [virtual_shard_identity]: 1.268e-05 [virtual_dataset]: 1.084e-05 [get_grad_eliminate_]: 1.159e-05 [virtual_output]: 1.049e-05 [merge_forward]: 6.63e-06 [cell_reuse_recompute_pass]: 3.51999e-06 [offload_activation]: 1.687e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.072e-05 [merge_recompute_call_nodes]: 1.99999e-06 [before_grad]: 1.883e-05 [set_forward_comm_id_for_comm_node_pass]: 6.76e-06 [meta_fg_expand]: 5.03002e-06 [flash_sp_send_recv_attached]: 1.81e-06 [receive_attached]: 2.98e-06 [after_resolve]: 1.552e-05 [a_after_grad]: 1.698e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 2.96999e-06 [auto_monad_grad]: 1.86998e-06 [auto_monad_eliminator]: 1.669e-05 [cse]: 4.459e-05 [a_3]: 6.858e-05 [py_interpret_to_execute_after_opt_a]: 2.212e-05 [slice_cell_reuse_recomputed_activation]: 2.35002e-06 [rewriter_after_opt_a]: 0.00026369 [convert_after_rewriter]: 1.23e-05 [order_py_execute_after_rewriter]: 9.25999e-06 [mutable_eliminate]: 0.00077704 [opt_b]: 0.00045473, [1] [Cycle 1]: 0.00044528, [7] [b_1]: 0.00029955 [b_2]: 1.376e-05 [updatestate_depend_eliminate]: 1.454e-05 [updatestate_assign_eliminate]: 5.85002e-06 [updatestate_loads_eliminate]: 5.27001e-06 [renormalize]: 8.30012e-07 [cse]: 6.21e-05 [optimize_parallel_all_gather_comm]: 3.05e-05 [overlap_param_gather]: 2.14e-06 [cconv]: 4.034e-05 [loop_unroll]: 0.00057593 [opt_after_cconv]: 0.0001696, [1] [Cycle 1]: 0.00016006, [7] [c_1]: 5.607e-05 [parameter_eliminate]: 4.93001e-06 [updatestate_depend_eliminate]: 1.239e-05 [updatestate_assign_eliminate]: 5.15999e-06 [updatestate_loads_eliminate]: 4.67e-06 [cse]: 4.15e-05 [renormalize]: 7.59988e-07 [remove_dup_value]: 6.252e-05 [tuple_transform]: 0.00020212, [1] [Cycle 1]: 0.00019701, [4] [d_1]: 0.00015703 [none_parameter_eliminate]: 2.58e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.344e-05 [partial_unused_args_eliminate]: 2.78e-06 [add_recomputation]: 9.562e-05 [cse_after_recomputation]: 4.306e-05, [1] [Cycle 1]: 3.692e-05, [1] [cse]: 3.067e-05 [environ_conv]: 1.54e-05 [swap_dp_allreduce_reducescatter]: 9.30001e-06 [bias_add_comm_swap]: 4.68999e-06 [label_micro_interleaved_index]: 5.81003e-06 [label_fine_grained_interleaved_index]: 2.91999e-06 [merge_cast_opt]: 1.69e-06 [slice_recompute_activation]: 2.52001e-06 [micro_interleaved_order_control]: 2.85998e-06 [assign_add_opt]: 1.50999e-06 [ForceFp32Comm]: 9.79984e-07 [remove_cast_before_assign_add]: 1.69e-06 [full_micro_interleaved_order_control]: 2.75002e-06 [reorder_send_recv_between_fp_bp]: 3.18e-06 [comm_op_add_attrs]: 1.51002e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.24e-06 [interleave_parallel_branches]: 1.22999e-06 [overlap_opt_shard_in_pipeline]: 1.29e-06 [overlap_opt_shard_grad_in_pipeline]: 1.79e-06 [control_data_broadcast_order]: 2.195e-05 [grouped_pairwise_exchange_alltoall]: 1.91e-06 [offloading_packed_experts]: 6.98998e-06 [overlap_recompute_and_grad_model_parallel]: 8.17e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.28002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39998e-06 [overlap_recompute_comm]: 2.28002e-06 [overlap_grad_ring_attention]: 6.20002e-06 [overlap_grad_flash_sp]: 3.122e-05 [begin_end_overlap_inline]: 7.30011e-07 [split_matmul_comm_elemetwise]: 2.69999e-06 [split_layernorm_comm]: 2.17001e-06 [handle_group_info]: 1.30999e-06 [symbol_engine_optimizer]: 0.00012018, [1] [Cycle 1]: 0.00011575, [6] [build]: 1.541e-05 [elim_shapecalc]: 1.577e-05 [elim_not_effective]: 2.226e-05 [opt_reshape]: 1.245e-05 [fold_const_symbol]: 1.945e-05 [renormalize]: 2.3999e-07 [detach_backward]: 4.32998e-06 [pipeline_parallel_scheduler]: 1.74e-06 [auto_monad_reorder]: 2.695e-05 [get_jit_bprop_graph]: 2.02999e-06 [rewriter_after_jit_bprop_graph]: 6.26e-06 [opt_after_jit_grad]: 0.00057173 [validate]: 7.047e-05 Sums bootstrap : 0.000695s : 0.03% type_inference : 2.024506s : 90.89% event_method : 0.000025s : 0.00% auto_monad : 0.000090s : 0.00% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000053s : 0.00% 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 : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000093s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000058s : 0.00% optimize.opt_a.loop_unroll : 0.000038s : 0.00% optimize.opt_a.a_1 : 0.001436s : 0.06% optimize.opt_a.with_stream_mark : 0.000439s : 0.02% optimize.opt_a.recompute_prepare : 0.000041s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000366s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000027s : 0.00% optimize.opt_a.auto_parallel : 0.000028s : 0.00% optimize.opt_a.parallel : 0.000041s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000032s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.00% optimize.opt_a.virtual_dataset : 0.000025s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000014s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000044s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000032s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.194866s : 8.75% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000053s : 0.00% optimize.opt_a.cse : 0.000299s : 0.01% optimize.opt_a.a_3 : 0.000176s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000264s : 0.01% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000777s : 0.03% optimize.opt_b.b_1 : 0.000300s : 0.01% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000062s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.00% optimize.loop_unroll : 0.000576s : 0.03% optimize.opt_after_cconv.c_1 : 0.000056s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000042s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000063s : 0.00% optimize.tuple_transform.d_1 : 0.000157s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000096s : 0.00% optimize.cse_after_recomputation.cse : 0.000031s : 0.00% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000005s : 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000002s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 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 : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 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 : 0.000015s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000022s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000027s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000572s : 0.03% validate : 0.000070s : 0.00% Time group info: ------[substitution.] 0.000519 111 9.52% : 0.000049s : 6: substitution.arithmetic_simplify 0.93% : 0.000005s : 6: substitution.elim_not_effective 2.28% : 0.000012s : 6: substitution.float_tuple_getitem_switch 0.55% : 0.000003s : 6: substitution.fold_const_symbol 9.89% : 0.000051s : 8: substitution.graph_param_transform 41.80% : 0.000217s : 5: substitution.inline 1.61% : 0.000008s : 12: substitution.j_node_and_user_rematch 1.76% : 0.000009s : 4: substitution.minmaximum_grad 1.80% : 0.000009s : 12: substitution.remove_not_recompute_node 1.00% : 0.000005s : 2: substitution.replace_old_param 7.51% : 0.000039s : 8: substitution.tuple_list_convert_item_index_to_positive 2.91% : 0.000015s : 8: substitution.tuple_list_get_item_const_eliminator 4.11% : 0.000021s : 8: substitution.tuple_list_get_item_depend_reorder 10.31% : 0.000054s : 12: substitution.tuple_list_get_item_eliminator 4.01% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.024399 2 99.80% : 2.020398s : 1: type_inference.infer 0.20% : 0.004001s : 1: type_inference.specialize ------[replace.] 0.000049 5 100.00% : 0.000049s : 5: replace.inline ------[match.] 0.000214 5 100.00% : 0.000214s : 5: match.inline ------[predicate.] 0.000397 2113 0.88% : 0.000003s : 21: predicate.accumulaten_eliminater 0.88% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.62% : 0.000002s : 16: predicate.addn_check_dump 0.83% : 0.000003s : 21: predicate.addn_zero_filter 0.71% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.17% : 0.000009s : 37: predicate.arithmetic_simplify 1.05% : 0.000004s : 21: predicate.cast_eliminate 0.64% : 0.000003s : 16: predicate.check_bprop_eliminate 0.58% : 0.000002s : 16: predicate.compare_switch_simplify 0.18% : 0.000001s : 8: predicate.const_output_eliminate 0.65% : 0.000003s : 16: predicate.depend_value_elim 0.80% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.89% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.78% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.98% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 8: predicate.elim_not_effective 0.38% : 0.000001s : 8: predicate.elim_shapecalc_of_broadcastargs 1.11% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.03% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.03% : 0.000004s : 29: predicate.environ_get_depend_swap 1.71% : 0.000007s : 45: predicate.environ_get_eliminate 1.14% : 0.000005s : 29: predicate.environ_get_set_eliminate 0.90% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.52% : 0.000006s : 26: predicate.float_depend_g_call 0.59% : 0.000002s : 16: predicate.float_environ_get_switch 0.99% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 8: predicate.fold_const_symbol 0.68% : 0.000003s : 16: predicate.get_grad_eliminate 0.19% : 0.000001s : 8: predicate.graph_param_transform 0.58% : 0.000002s : 16: predicate.incorporate_call 0.52% : 0.000002s : 16: predicate.incorporate_call_switch 4.81% : 0.000019s : 95: predicate.inline 0.78% : 0.000003s : 16: predicate.inline_without_move 0.29% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.83% : 0.000003s : 16: predicate.less_batch_normalization 1.54% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 1.98% : 0.000008s : 58: predicate.load_eliminater 1.06% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.28% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.49% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.61% : 0.000002s : 16: predicate.merge_addn 0.57% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.58% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.75% : 0.000003s : 21: predicate.minmaximum_grad 1.34% : 0.000005s : 8: predicate.mutable_eliminate 0.35% : 0.000001s : 8: predicate.opt_reshape 0.40% : 0.000002s : 8: predicate.parallel_virtual_node 1.20% : 0.000005s : 26: predicate.partial_defer_inline 1.02% : 0.000004s : 29: predicate.partial_eliminate 0.77% : 0.000003s : 21: predicate.print_const_string_wrapper 0.62% : 0.000002s : 16: predicate.reduce_all_const_elim 1.11% : 0.000004s : 21: predicate.reduce_eliminate 2.00% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.36% : 0.000001s : 16: predicate.remove_not_recompute_node 1.08% : 0.000004s : 37: predicate.replace_applicator 0.48% : 0.000002s : 16: predicate.replace_old_param 0.28% : 0.000001s : 8: predicate.reset_defer_inline 0.77% : 0.000003s : 21: predicate.reshape_eliminate 0.65% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.53% : 0.000002s : 8: predicate.row_tensor_eliminate 0.88% : 0.000003s : 16: predicate.same_eliminate 0.41% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.79% : 0.000003s : 16: predicate.shard_identity_eliminate 0.72% : 0.000003s : 16: predicate.special_op_eliminate 0.70% : 0.000003s : 16: predicate.specialize_transform 0.92% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.84% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.29% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.03% : 0.000004s : 26: predicate.switch_defer_inline 1.57% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.50% : 0.000014s : 86: predicate.switch_simplify 0.82% : 0.000003s : 21: predicate.tile_eliminate 0.81% : 0.000003s : 21: predicate.transpose_eliminate 1.67% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.62% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.52% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 14.49% : 0.000058s : 53: predicate.tuple_list_get_item_eliminator 1.62% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.41% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.39% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 1.93% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.63% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.38% : 0.000002s : 8: predicate.value_based_eliminate 0.78% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.71% : 0.000003s : 16: predicate.virtual_output_eliminate 0.29% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.41% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.210907 32 98.91% : 0.208617s : 25: func_graph_cloner_run.FuncGraphClonerGraph 1.09% : 0.002290s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.641788 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.24% : 0.006468s : 1: add_attr 0.24% : 0.006448s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000100s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000095s : 1: auto_monad 0.00% : 0.000032s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000009s : 1: bias_add_comm_swap 0.03% : 0.000750s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000016s : 1: convert_after_rewriter 0.00% : 0.000046s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.00% : 0.000033s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000587s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000791s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.09% : 0.002306s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000046s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000278s : 28: opt.transform.opt_b 0.01% : 0.000167s : 2: opt.transform.opt_trans_graph 0.00% : 0.000066s : 4: opt.transform.symbol_engine_opt 7.53% : 0.199046s : 1: opt_a 0.01% : 0.000173s : 1: opt_after_cconv 0.02% : 0.000585s : 1: opt_after_jit_grad 0.02% : 0.000458s : 1: opt_b 7.66% : 0.202480s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000057s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000067s : 1: remove_dup_value 7.28% : 0.192337s : 1: renormalize.infer 0.10% : 0.002512s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000270s : 1: rewriter_after_opt_a 0.00% : 0.000098s : 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% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000123s : 1: symbol_engine_optimizer 0.01% : 0.000205s : 1: tuple_transform 76.64% : 2.024539s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:19.671.074 [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 = 2.36393, [21] [bootstrap]: 0.00079779 [type_inference]: 2.22145 [event_method]: 2.726e-05 [auto_monad]: 0.00010463 [graph_reusing]: 6.46e-06 [inline]: 4.25999e-06 [add_attr]: 0.00661258, [1] [add_attr_with_inline]: 0.00659175, [1] [Cycle 1]: 0.00013551, [2] [tag_attr]: 8.262e-05 [meta_addattr_fg_expand]: 6.89001e-06 [parallel-infer-symbol]: 3.95e-06 [pre_auto_parallel]: 4.72e-05 [insert-virtual-dataset]: 2.51e-06 [parallel-infer-symbol-second]: 8.89995e-07 [dataset_repeat_opt]: 2.12001e-06 [pipeline_split]: 1.67999e-06 [optimize]: 0.134001, [53] [py_interpret_to_execute]: 3.645e-05 [rewriter_before_opt_a]: 0.00010924 [opt_a]: 0.130578, [2] [Cycle 1]: 0.129347, [45] [expand_dump_flag]: 4.67998e-06 [switch_simplify]: 4.47e-05 [loop_unroll]: 2.806e-05 [a_1]: 0.00113482 [with_stream_mark]: 2.957e-05 [recompute_prepare]: 1.797e-05 [updatestate_depend_eliminate]: 1.12e-05 [updatestate_assign_eliminate]: 6.96999e-06 [updatestate_loads_eliminate]: 5.67001e-06 [parameter_eliminate]: 2.17999e-06 [a_2]: 0.00019093 [accelerated_algorithm]: 1.374e-05 [shard]: 2.53e-06 [meta_shard_fg_expand]: 4.12e-06 [shard_inline]: 1.097e-05 [merge_send_recv]: 1.28e-05 [auto_parallel]: 1.062e-05 [parallel]: 3.343e-05 [flash_sp]: 1.045e-05 [merge_comm]: 7.16999e-06 [allreduce_fusion]: 6.68e-06 [matmul_add_comm_reduction]: 1.636e-05 [allreduce_slice_to_reducescatter]: 5.69999e-07 [virtual_shard_identity]: 1.483e-05 [virtual_dataset]: 1.291e-05 [get_grad_eliminate_]: 1.286e-05 [virtual_output]: 1.309e-05 [merge_forward]: 7.87e-06 [cell_reuse_recompute_pass]: 1.64998e-06 [offload_activation]: 1.664e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.587e-05 [merge_recompute_call_nodes]: 1.48002e-06 [before_grad]: 2.129e-05 [set_forward_comm_id_for_comm_node_pass]: 7.23e-06 [meta_fg_expand]: 5.10999e-06 [flash_sp_send_recv_attached]: 2.89001e-06 [receive_attached]: 2.29001e-06 [after_resolve]: 1.659e-05 [a_after_grad]: 2.002e-05 [renormalize]: 0.126883 [add_forward_monad_depend]: 1.372e-05 [auto_monad_grad]: 4.11001e-06 [auto_monad_eliminator]: 3.711e-05 [cse]: 0.0001995 [a_3]: 0.00010801 [Cycle 2]: 0.00121581, [45] [expand_dump_flag]: 2.70002e-06 [switch_simplify]: 1.519e-05 [loop_unroll]: 1.176e-05 [a_1]: 0.00034832 [with_stream_mark]: 2.628e-05 [recompute_prepare]: 1.213e-05 [updatestate_depend_eliminate]: 9.00999e-06 [updatestate_assign_eliminate]: 5.67001e-06 [updatestate_loads_eliminate]: 5.47999e-06 [parameter_eliminate]: 2.61999e-06 [a_2]: 0.00016362 [accelerated_algorithm]: 1.189e-05 [shard]: 2.49001e-06 [meta_shard_fg_expand]: 3.93999e-06 [shard_inline]: 1.132e-05 [merge_send_recv]: 1.328e-05 [auto_parallel]: 1.556e-05 [parallel]: 1.051e-05 [flash_sp]: 4.48001e-06 [merge_comm]: 6.69999e-06 [allreduce_fusion]: 6.13998e-06 [matmul_add_comm_reduction]: 1.514e-05 [allreduce_slice_to_reducescatter]: 1.14998e-06 [virtual_shard_identity]: 1.334e-05 [virtual_dataset]: 1.086e-05 [get_grad_eliminate_]: 1.138e-05 [virtual_output]: 1.083e-05 [merge_forward]: 7.25998e-06 [cell_reuse_recompute_pass]: 3.38e-06 [offload_activation]: 1.646e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.052e-05 [merge_recompute_call_nodes]: 1.99e-06 [before_grad]: 1.822e-05 [set_forward_comm_id_for_comm_node_pass]: 6.81999e-06 [meta_fg_expand]: 5.04003e-06 [flash_sp_send_recv_attached]: 1.81e-06 [receive_attached]: 2.96999e-06 [after_resolve]: 1.573e-05 [a_after_grad]: 1.789e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.37999e-06 [auto_monad_grad]: 2.01998e-06 [auto_monad_eliminator]: 1.723e-05 [cse]: 4.111e-05 [a_3]: 6.864e-05 [py_interpret_to_execute_after_opt_a]: 2.642e-05 [slice_cell_reuse_recomputed_activation]: 2.77002e-06 [rewriter_after_opt_a]: 0.00028643 [convert_after_rewriter]: 1.405e-05 [order_py_execute_after_rewriter]: 9.99001e-06 [mutable_eliminate]: 0.000823 [opt_b]: 0.00043259, [1] [Cycle 1]: 0.00042413, [7] [b_1]: 0.00028783 [b_2]: 1.381e-05 [updatestate_depend_eliminate]: 1.363e-05 [updatestate_assign_eliminate]: 5.38002e-06 [updatestate_loads_eliminate]: 5.24e-06 [renormalize]: 6.19999e-07 [cse]: 5.623e-05 [optimize_parallel_all_gather_comm]: 3.047e-05 [overlap_param_gather]: 2.34001e-06 [cconv]: 3.952e-05 [loop_unroll]: 0.00052036 [opt_after_cconv]: 0.00016403, [1] [Cycle 1]: 0.00015581, [7] [c_1]: 5.602e-05 [parameter_eliminate]: 5.39998e-06 [updatestate_depend_eliminate]: 1.031e-05 [updatestate_assign_eliminate]: 4.77998e-06 [updatestate_loads_eliminate]: 4.57e-06 [cse]: 3.824e-05 [renormalize]: 5.60016e-07 [remove_dup_value]: 7.073e-05 [tuple_transform]: 0.00015623, [1] [Cycle 1]: 0.00015113, [4] [d_1]: 0.00011401 [none_parameter_eliminate]: 1.94e-06 [renormalize]: 1.40019e-07 [switch_simplify]: 1.267e-05 [partial_unused_args_eliminate]: 3.04001e-06 [add_recomputation]: 0.00010293 [cse_after_recomputation]: 4.215e-05, [1] [Cycle 1]: 3.625e-05, [1] [cse]: 3.054e-05 [environ_conv]: 1.895e-05 [swap_dp_allreduce_reducescatter]: 9.67999e-06 [bias_add_comm_swap]: 3.22002e-06 [label_micro_interleaved_index]: 5.17999e-06 [label_fine_grained_interleaved_index]: 2.96001e-06 [merge_cast_opt]: 1.87999e-06 [slice_recompute_activation]: 2.58e-06 [micro_interleaved_order_control]: 3.16999e-06 [assign_add_opt]: 1.64e-06 [ForceFp32Comm]: 8.59989e-07 [remove_cast_before_assign_add]: 1.04e-06 [full_micro_interleaved_order_control]: 2.57001e-06 [reorder_send_recv_between_fp_bp]: 3.06999e-06 [comm_op_add_attrs]: 1.11002e-06 [add_comm_op_reuse_tag]: 1.05999e-06 [interleave_split_concat_branches]: 1.40999e-06 [interleave_parallel_branches]: 1.14998e-06 [overlap_opt_shard_in_pipeline]: 1.29e-06 [overlap_opt_shard_grad_in_pipeline]: 1.92001e-06 [control_data_broadcast_order]: 2.219e-05 [grouped_pairwise_exchange_alltoall]: 2.07001e-06 [offloading_packed_experts]: 6.69999e-06 [overlap_recompute_and_grad_model_parallel]: 8.16002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.64999e-06 [overlap_grad_ring_attention]: 5.76e-06 [overlap_grad_flash_sp]: 3.468e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 3.01999e-06 [split_layernorm_comm]: 2.14e-06 [handle_group_info]: 1.40999e-06 [symbol_engine_optimizer]: 0.00012557, [1] [Cycle 1]: 0.00012002, [6] [build]: 1.436e-05 [elim_shapecalc]: 1.603e-05 [elim_not_effective]: 2.279e-05 [opt_reshape]: 1.408e-05 [fold_const_symbol]: 1.964e-05 [renormalize]: 1.69995e-07 [detach_backward]: 3.68e-06 [pipeline_parallel_scheduler]: 1.61998e-06 [auto_monad_reorder]: 2.841e-05 [get_jit_bprop_graph]: 1.97999e-06 [rewriter_after_jit_bprop_graph]: 6.94999e-06 [opt_after_jit_grad]: 0.00054988 [validate]: 7.535e-05 Sums bootstrap : 0.000798s : 0.03% type_inference : 2.221445s : 94.28% event_method : 0.000027s : 0.00% auto_monad : 0.000105s : 0.00% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000083s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 0.00% 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 : 0.000036s : 0.00% optimize.rewriter_before_opt_a : 0.000109s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001483s : 0.06% optimize.opt_a.with_stream_mark : 0.000056s : 0.00% optimize.opt_a.recompute_prepare : 0.000030s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000355s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000026s : 0.00% optimize.opt_a.auto_parallel : 0.000026s : 0.00% optimize.opt_a.parallel : 0.000044s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000032s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000028s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000024s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000033s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000046s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000040s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000032s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.126883s : 5.39% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000054s : 0.00% optimize.opt_a.cse : 0.000241s : 0.01% optimize.opt_a.a_3 : 0.000177s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000286s : 0.01% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000823s : 0.03% optimize.opt_b.b_1 : 0.000288s : 0.01% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000056s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.00% optimize.loop_unroll : 0.000520s : 0.02% optimize.opt_after_cconv.c_1 : 0.000056s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000038s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000071s : 0.00% optimize.tuple_transform.d_1 : 0.000114s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000103s : 0.00% optimize.cse_after_recomputation.cse : 0.000031s : 0.00% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000035s : 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 : 0.000014s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000028s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000550s : 0.02% validate : 0.000075s : 0.00% Time group info: ------[substitution.] 0.000531 111 8.50% : 0.000045s : 6: substitution.arithmetic_simplify 0.84% : 0.000004s : 6: substitution.elim_not_effective 2.34% : 0.000012s : 6: substitution.float_tuple_getitem_switch 0.50% : 0.000003s : 6: substitution.fold_const_symbol 1.90% : 0.000010s : 8: substitution.graph_param_transform 51.56% : 0.000274s : 5: substitution.inline 1.28% : 0.000007s : 12: substitution.j_node_and_user_rematch 2.33% : 0.000012s : 4: substitution.minmaximum_grad 2.03% : 0.000011s : 12: substitution.remove_not_recompute_node 1.14% : 0.000006s : 2: substitution.replace_old_param 6.79% : 0.000036s : 8: substitution.tuple_list_convert_item_index_to_positive 2.76% : 0.000015s : 8: substitution.tuple_list_get_item_const_eliminator 4.19% : 0.000022s : 8: substitution.tuple_list_get_item_depend_reorder 9.48% : 0.000050s : 12: substitution.tuple_list_get_item_eliminator 4.36% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.221309 2 93.47% : 2.076363s : 1: type_inference.infer 6.53% : 0.144946s : 1: type_inference.specialize ------[replace.] 0.000058 5 100.00% : 0.000058s : 5: replace.inline ------[match.] 0.000269 5 100.00% : 0.000269s : 5: match.inline ------[predicate.] 0.000357 2113 0.94% : 0.000003s : 21: predicate.accumulaten_eliminater 1.15% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.78% : 0.000003s : 16: predicate.addn_check_dump 1.06% : 0.000004s : 21: predicate.addn_zero_filter 0.86% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.42% : 0.000009s : 37: predicate.arithmetic_simplify 0.98% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000002s : 16: predicate.check_bprop_eliminate 0.64% : 0.000002s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.64% : 0.000002s : 16: predicate.depend_value_elim 0.89% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.96% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.85% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.10% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 8: predicate.elim_not_effective 0.39% : 0.000001s : 8: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.16% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_depend_swap 1.97% : 0.000007s : 45: predicate.environ_get_eliminate 1.30% : 0.000005s : 29: predicate.environ_get_set_eliminate 1.19% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.93% : 0.000007s : 26: predicate.float_depend_g_call 0.64% : 0.000002s : 16: predicate.float_environ_get_switch 1.07% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.72% : 0.000003s : 16: predicate.get_grad_eliminate 0.20% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000002s : 16: predicate.incorporate_call 0.59% : 0.000002s : 16: predicate.incorporate_call_switch 5.50% : 0.000020s : 95: predicate.inline 0.78% : 0.000003s : 16: predicate.inline_without_move 0.32% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.88% : 0.000003s : 16: predicate.less_batch_normalization 1.60% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.32% : 0.000008s : 58: predicate.load_eliminater 1.38% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.52% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.62% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.69% : 0.000002s : 16: predicate.merge_addn 0.67% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.63% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.87% : 0.000003s : 21: predicate.minmaximum_grad 1.33% : 0.000005s : 8: predicate.mutable_eliminate 0.57% : 0.000002s : 8: predicate.opt_reshape 0.52% : 0.000002s : 8: predicate.parallel_virtual_node 1.80% : 0.000006s : 26: predicate.partial_defer_inline 1.20% : 0.000004s : 29: predicate.partial_eliminate 0.98% : 0.000003s : 21: predicate.print_const_string_wrapper 0.66% : 0.000002s : 16: predicate.reduce_all_const_elim 1.28% : 0.000005s : 21: predicate.reduce_eliminate 2.16% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.17% : 0.000004s : 37: predicate.replace_applicator 0.45% : 0.000002s : 16: predicate.replace_old_param 0.29% : 0.000001s : 8: predicate.reset_defer_inline 1.01% : 0.000004s : 21: predicate.reshape_eliminate 0.69% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.51% : 0.000002s : 8: predicate.row_tensor_eliminate 0.94% : 0.000003s : 16: predicate.same_eliminate 0.41% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.73% : 0.000003s : 16: predicate.shard_identity_eliminate 0.82% : 0.000003s : 16: predicate.special_op_eliminate 0.78% : 0.000003s : 16: predicate.specialize_transform 0.97% : 0.000003s : 16: predicate.split_environ_get_set_with_tuple_value 0.97% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.33% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.14% : 0.000004s : 26: predicate.switch_defer_inline 1.73% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.10% : 0.000015s : 86: predicate.switch_simplify 1.05% : 0.000004s : 21: predicate.tile_eliminate 0.87% : 0.000003s : 21: predicate.transpose_eliminate 2.01% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.59% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.33% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.75% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.80% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.59% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.26% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.96% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 8: predicate.value_based_eliminate 0.77% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.83% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.44% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007397 32 62.25% : 0.004604s : 25: func_graph_cloner_run.FuncGraphClonerGraph 37.75% : 0.002792s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.634157 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.25% : 0.006620s : 1: add_attr 0.25% : 0.006597s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000108s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000111s : 1: auto_monad 0.00% : 0.000033s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000847s : 1: bootstrap 0.00% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.00% : 0.000036s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000531s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000835s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000026s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.09% : 0.002332s : 78: opt.transform.opt_a 0.00% : 0.000054s : 1: opt.transform.opt_after_cconv 0.00% : 0.000045s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000268s : 28: opt.transform.opt_b 0.00% : 0.000124s : 2: opt.transform.opt_trans_graph 0.00% : 0.000069s : 4: opt.transform.symbol_engine_opt 4.96% : 0.130582s : 1: opt_a 0.01% : 0.000167s : 1: opt_after_cconv 0.02% : 0.000561s : 1: opt_after_jit_grad 0.02% : 0.000436s : 1: opt_b 5.09% : 0.134007s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000038s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000052s : 1: pre_auto_parallel 0.00% : 0.000041s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000076s : 1: remove_dup_value 4.70% : 0.123842s : 1: renormalize.infer 0.11% : 0.003018s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000296s : 1: rewriter_after_opt_a 0.00% : 0.000114s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000128s : 1: symbol_engine_optimizer 0.01% : 0.000159s : 1: tuple_transform 84.33% : 2.221479s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[False-bfloat16--1-shape1],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:26.315.5 [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 = 2.55329, [21] [bootstrap]: 0.00083754 [type_inference]: 2.30915 [event_method]: 2.609e-05 [auto_monad]: 9.532e-05 [graph_reusing]: 6.70998e-06 [inline]: 3.04999e-06 [add_attr]: 0.00614276, [1] [add_attr_with_inline]: 0.00612477, [1] [Cycle 1]: 8.176e-05, [2] [tag_attr]: 2.81e-05 [meta_addattr_fg_expand]: 6.09999e-06 [parallel-infer-symbol]: 4.17e-06 [pre_auto_parallel]: 4.969e-05 [insert-virtual-dataset]: 2.91e-06 [parallel-infer-symbol-second]: 8.60018e-07 [dataset_repeat_opt]: 2.41e-06 [pipeline_split]: 1.77001e-06 [optimize]: 0.235943, [53] [py_interpret_to_execute]: 4.47e-05 [rewriter_before_opt_a]: 9.721e-05 [opt_a]: 0.23176, [2] [Cycle 1]: 0.230011, [45] [expand_dump_flag]: 3.98001e-06 [switch_simplify]: 4.204e-05 [loop_unroll]: 2.695e-05 [a_1]: 0.00107164 [with_stream_mark]: 3.036e-05 [recompute_prepare]: 2.136e-05 [updatestate_depend_eliminate]: 1.015e-05 [updatestate_assign_eliminate]: 5.87999e-06 [updatestate_loads_eliminate]: 5.76998e-06 [parameter_eliminate]: 2.74001e-06 [a_2]: 0.00019764 [accelerated_algorithm]: 1.443e-05 [shard]: 2.17001e-06 [meta_shard_fg_expand]: 4.02002e-06 [shard_inline]: 1.168e-05 [merge_send_recv]: 1.411e-05 [auto_parallel]: 1.131e-05 [parallel]: 2.795e-05 [flash_sp]: 1.28e-05 [merge_comm]: 7.66001e-06 [allreduce_fusion]: 6.18998e-06 [matmul_add_comm_reduction]: 1.62e-05 [allreduce_slice_to_reducescatter]: 8.30012e-07 [virtual_shard_identity]: 1.613e-05 [virtual_dataset]: 1.224e-05 [get_grad_eliminate_]: 1.213e-05 [virtual_output]: 1.238e-05 [merge_forward]: 6.94999e-06 [cell_reuse_recompute_pass]: 2.01003e-06 [offload_activation]: 1.903e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.729e-05 [merge_recompute_call_nodes]: 1.97001e-06 [before_grad]: 2.171e-05 [set_forward_comm_id_for_comm_node_pass]: 6.86001e-06 [meta_fg_expand]: 4.97e-06 [flash_sp_send_recv_attached]: 3.88001e-06 [receive_attached]: 2.06e-06 [after_resolve]: 1.697e-05 [a_after_grad]: 2.608e-05 [renormalize]: 0.22723 [add_forward_monad_depend]: 1.412e-05 [auto_monad_grad]: 3.53e-06 [auto_monad_eliminator]: 3.865e-05 [cse]: 0.00050913 [a_3]: 0.00011423 [Cycle 2]: 0.00173146, [45] [expand_dump_flag]: 3.63999e-06 [switch_simplify]: 1.739e-05 [loop_unroll]: 1.217e-05 [a_1]: 0.0003925 [with_stream_mark]: 3.831e-05 [recompute_prepare]: 1.778e-05 [updatestate_depend_eliminate]: 1.055e-05 [updatestate_assign_eliminate]: 6.94999e-06 [updatestate_loads_eliminate]: 6.21e-06 [parameter_eliminate]: 2.72001e-06 [a_2]: 0.00017163 [accelerated_algorithm]: 1.437e-05 [shard]: 4.21001e-06 [meta_shard_fg_expand]: 4.02e-06 [shard_inline]: 1.143e-05 [merge_send_recv]: 1.368e-05 [auto_parallel]: 1.606e-05 [parallel]: 1.234e-05 [flash_sp]: 4.62998e-06 [merge_comm]: 7.36001e-06 [allreduce_fusion]: 5.99999e-06 [matmul_add_comm_reduction]: 1.691e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 1.728e-05 [virtual_dataset]: 1.189e-05 [get_grad_eliminate_]: 1.236e-05 [virtual_output]: 1.103e-05 [merge_forward]: 8.33999e-06 [cell_reuse_recompute_pass]: 4.3e-06 [offload_activation]: 1.722e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.75e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 1.991e-05 [set_forward_comm_id_for_comm_node_pass]: 8.72998e-06 [meta_fg_expand]: 5.87999e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 3.11001e-06 [after_resolve]: 1.833e-05 [a_after_grad]: 1.787e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.18001e-06 [auto_monad_grad]: 3.36999e-06 [auto_monad_eliminator]: 2.687e-05 [cse]: 0.00032802 [a_3]: 9.062e-05 [py_interpret_to_execute_after_opt_a]: 3.242e-05 [slice_cell_reuse_recomputed_activation]: 2.48e-06 [rewriter_after_opt_a]: 0.00039624 [convert_after_rewriter]: 1.904e-05 [order_py_execute_after_rewriter]: 9.80002e-06 [mutable_eliminate]: 0.00089609 [opt_b]: 0.00049467, [1] [Cycle 1]: 0.00048345, [7] [b_1]: 0.00031973 [b_2]: 1.689e-05 [updatestate_depend_eliminate]: 1.533e-05 [updatestate_assign_eliminate]: 5.97001e-06 [updatestate_loads_eliminate]: 5.60001e-06 [renormalize]: 1.09e-06 [cse]: 6.945e-05 [optimize_parallel_all_gather_comm]: 3.75e-05 [overlap_param_gather]: 2.50002e-06 [cconv]: 4.733e-05 [loop_unroll]: 0.0006666 [opt_after_cconv]: 0.0001877, [1] [Cycle 1]: 0.0001773, [7] [c_1]: 6.045e-05 [parameter_eliminate]: 6.78e-06 [updatestate_depend_eliminate]: 1.348e-05 [updatestate_assign_eliminate]: 5.42001e-06 [updatestate_loads_eliminate]: 5.07e-06 [cse]: 4.962e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 7.257e-05 [tuple_transform]: 0.00016633, [1] [Cycle 1]: 0.00016089, [4] [d_1]: 0.0001235 [none_parameter_eliminate]: 2.16e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 1.269e-05 [partial_unused_args_eliminate]: 2.48e-06 [add_recomputation]: 0.00010388 [cse_after_recomputation]: 4.429e-05, [1] [Cycle 1]: 3.808e-05, [1] [cse]: 3.165e-05 [environ_conv]: 1.702e-05 [swap_dp_allreduce_reducescatter]: 9.76998e-06 [bias_add_comm_swap]: 3.63e-06 [label_micro_interleaved_index]: 6.48e-06 [label_fine_grained_interleaved_index]: 2.82002e-06 [merge_cast_opt]: 2.17001e-06 [slice_recompute_activation]: 2.60002e-06 [micro_interleaved_order_control]: 2.57001e-06 [assign_add_opt]: 1.39e-06 [ForceFp32Comm]: 1.06002e-06 [remove_cast_before_assign_add]: 1.45001e-06 [full_micro_interleaved_order_control]: 3.09999e-06 [reorder_send_recv_between_fp_bp]: 2.86e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 1.20999e-06 [interleave_split_concat_branches]: 1.19e-06 [interleave_parallel_branches]: 1.24e-06 [overlap_opt_shard_in_pipeline]: 1.66e-06 [overlap_opt_shard_grad_in_pipeline]: 2.32999e-06 [control_data_broadcast_order]: 2.318e-05 [grouped_pairwise_exchange_alltoall]: 1.79e-06 [offloading_packed_experts]: 6.73e-06 [overlap_recompute_and_grad_model_parallel]: 8.00999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.50999e-06 [overlap_recompute_comm]: 2.24001e-06 [overlap_grad_ring_attention]: 6.09001e-06 [overlap_grad_flash_sp]: 3.427e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.44001e-06 [split_layernorm_comm]: 1.81e-06 [handle_group_info]: 1.21002e-06 [symbol_engine_optimizer]: 0.00040205, [1] [Cycle 1]: 0.00039589, [6] [build]: 0.00022354 [elim_shapecalc]: 2.715e-05 [elim_not_effective]: 4.426e-05 [opt_reshape]: 1.409e-05 [fold_const_symbol]: 3.728e-05 [renormalize]: 2.00002e-07 [detach_backward]: 3.12002e-06 [pipeline_parallel_scheduler]: 1.67999e-06 [auto_monad_reorder]: 3.332e-05 [get_jit_bprop_graph]: 4.03001e-06 [rewriter_after_jit_bprop_graph]: 5.84999e-06 [opt_after_jit_grad]: 0.00066394 [validate]: 7.653e-05 Sums bootstrap : 0.000838s : 0.03% type_inference : 2.309149s : 90.71% event_method : 0.000026s : 0.00% auto_monad : 0.000095s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000028s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.00% 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 : 0.000045s : 0.00% optimize.rewriter_before_opt_a : 0.000097s : 0.00% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001464s : 0.06% optimize.opt_a.with_stream_mark : 0.000069s : 0.00% optimize.opt_a.recompute_prepare : 0.000039s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000369s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000028s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000040s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000015s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000033s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000055s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000042s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000016s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000044s : 0.00% optimize.opt_a.renormalize : 0.227230s : 8.93% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000066s : 0.00% optimize.opt_a.cse : 0.000837s : 0.03% optimize.opt_a.a_3 : 0.000205s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000032s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000396s : 0.02% optimize.convert_after_rewriter : 0.000019s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000896s : 0.04% optimize.opt_b.b_1 : 0.000320s : 0.01% optimize.opt_b.b_2 : 0.000017s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000069s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000037s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000047s : 0.00% optimize.loop_unroll : 0.000667s : 0.03% optimize.opt_after_cconv.c_1 : 0.000060s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000050s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000073s : 0.00% optimize.tuple_transform.d_1 : 0.000124s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000104s : 0.00% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% 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 : 0.000002s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000034s : 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 : 0.000224s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000027s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000044s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000037s : 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 : 0.000033s : 0.00% get_jit_bprop_graph : 0.000004s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000664s : 0.03% validate : 0.000077s : 0.00% Time group info: ------[substitution.] 0.000575 111 12.30% : 0.000071s : 6: substitution.arithmetic_simplify 3.91% : 0.000022s : 6: substitution.elim_not_effective 2.41% : 0.000014s : 6: substitution.float_tuple_getitem_switch 3.48% : 0.000020s : 6: substitution.fold_const_symbol 1.81% : 0.000010s : 8: substitution.graph_param_transform 41.02% : 0.000236s : 5: substitution.inline 1.51% : 0.000009s : 12: substitution.j_node_and_user_rematch 2.29% : 0.000013s : 4: substitution.minmaximum_grad 1.86% : 0.000011s : 12: substitution.remove_not_recompute_node 1.10% : 0.000006s : 2: substitution.replace_old_param 6.59% : 0.000038s : 8: substitution.tuple_list_convert_item_index_to_positive 2.91% : 0.000017s : 8: substitution.tuple_list_get_item_const_eliminator 4.09% : 0.000024s : 8: substitution.tuple_list_get_item_depend_reorder 10.49% : 0.000060s : 12: substitution.tuple_list_get_item_eliminator 4.22% : 0.000024s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.309037 2 95.48% : 2.204556s : 1: type_inference.infer 4.52% : 0.104480s : 1: type_inference.specialize ------[replace.] 0.000052 5 100.00% : 0.000052s : 5: replace.inline ------[match.] 0.000232 5 100.00% : 0.000232s : 5: match.inline ------[predicate.] 0.000372 2113 0.88% : 0.000003s : 21: predicate.accumulaten_eliminater 0.86% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.60% : 0.000002s : 16: predicate.addn_check_dump 1.05% : 0.000004s : 21: predicate.addn_zero_filter 0.79% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.35% : 0.000009s : 37: predicate.arithmetic_simplify 0.86% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000003s : 16: predicate.check_bprop_eliminate 0.67% : 0.000002s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.59% : 0.000002s : 16: predicate.depend_value_elim 0.88% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.99% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.92% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.88% : 0.000003s : 16: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 8: predicate.elim_not_effective 0.64% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.26% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_depend_swap 1.71% : 0.000006s : 45: predicate.environ_get_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.97% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.59% : 0.000006s : 26: predicate.float_depend_g_call 0.61% : 0.000002s : 16: predicate.float_environ_get_switch 1.17% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 8: predicate.fold_const_symbol 0.84% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.61% : 0.000002s : 16: predicate.incorporate_call 0.54% : 0.000002s : 16: predicate.incorporate_call_switch 5.34% : 0.000020s : 95: predicate.inline 1.12% : 0.000004s : 16: predicate.inline_without_move 0.30% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.99% : 0.000004s : 16: predicate.less_batch_normalization 1.60% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.30% : 0.000009s : 58: predicate.load_eliminater 1.45% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.46% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.74% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.66% : 0.000002s : 16: predicate.merge_addn 0.62% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.65% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.80% : 0.000003s : 21: predicate.minmaximum_grad 1.90% : 0.000007s : 8: predicate.mutable_eliminate 0.41% : 0.000002s : 8: predicate.opt_reshape 0.47% : 0.000002s : 8: predicate.parallel_virtual_node 1.44% : 0.000005s : 26: predicate.partial_defer_inline 1.12% : 0.000004s : 29: predicate.partial_eliminate 0.87% : 0.000003s : 21: predicate.print_const_string_wrapper 0.75% : 0.000003s : 16: predicate.reduce_all_const_elim 1.09% : 0.000004s : 21: predicate.reduce_eliminate 2.32% : 0.000009s : 58: predicate.redundant_stop_gradient_eliminater 0.46% : 0.000002s : 16: predicate.remove_not_recompute_node 1.40% : 0.000005s : 37: predicate.replace_applicator 0.42% : 0.000002s : 16: predicate.replace_old_param 0.33% : 0.000001s : 8: predicate.reset_defer_inline 0.87% : 0.000003s : 21: predicate.reshape_eliminate 0.72% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.59% : 0.000002s : 8: predicate.row_tensor_eliminate 1.61% : 0.000006s : 16: predicate.same_eliminate 0.37% : 0.000001s : 16: predicate.set_cell_output_no_recompute 1.05% : 0.000004s : 16: predicate.shard_identity_eliminate 0.75% : 0.000003s : 16: predicate.special_op_eliminate 0.78% : 0.000003s : 16: predicate.specialize_transform 1.41% : 0.000005s : 16: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.41% : 0.000002s : 8: predicate.switch_call_monad_eliminater 1.10% : 0.000004s : 26: predicate.switch_defer_inline 1.70% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.10% : 0.000015s : 86: predicate.switch_simplify 0.92% : 0.000003s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.75% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 2.05% : 0.000008s : 37: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.45% : 0.000013s : 53: predicate.tuple_list_get_item_eliminator 2.05% : 0.000008s : 37: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.61% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.06% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.80% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.50% : 0.000002s : 8: predicate.value_based_eliminate 0.72% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.82% : 0.000003s : 16: predicate.virtual_output_eliminate 0.33% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006965 32 63.29% : 0.004408s : 25: func_graph_cloner_run.FuncGraphClonerGraph 36.71% : 0.002557s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.025474 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.20% : 0.006150s : 1: add_attr 0.20% : 0.006129s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000109s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000101s : 1: auto_monad 0.00% : 0.000038s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000900s : 1: bootstrap 0.00% : 0.000052s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000024s : 1: convert_after_rewriter 0.00% : 0.000047s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000020s : 1: environ_conv 0.00% : 0.000035s : 1: event_method 0.00% : 0.000008s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 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 0.02% : 0.000682s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000914s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000041s : 1: opt.transform.mutable_eliminate 0.08% : 0.002375s : 78: opt.transform.opt_a 0.00% : 0.000059s : 1: opt.transform.opt_after_cconv 0.00% : 0.000044s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000297s : 28: opt.transform.opt_b 0.00% : 0.000133s : 2: opt.transform.opt_trans_graph 0.00% : 0.000117s : 4: opt.transform.symbol_engine_opt 7.66% : 0.231764s : 1: opt_a 0.01% : 0.000192s : 1: opt_after_cconv 0.02% : 0.000679s : 1: opt_after_jit_grad 0.02% : 0.000500s : 1: opt_b 7.80% : 0.235950s : 1: optimize 0.00% : 0.000042s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000011s : 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 0.00% : 0.000054s : 1: pre_auto_parallel 0.00% : 0.000049s : 1: py_interpret_to_execute 0.00% : 0.000039s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000078s : 1: remove_dup_value 7.41% : 0.224329s : 1: renormalize.infer 0.10% : 0.002875s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000414s : 1: rewriter_after_opt_a 0.00% : 0.000102s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000406s : 1: symbol_engine_optimizer 0.01% : 0.000169s : 1: tuple_transform 76.32% : 2.309185s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-float32--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-float32--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:32.486.062 [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 = 2.73303, [21] [bootstrap]: 0.00090504 [type_inference]: 2.50104 [event_method]: 2.451e-05 [auto_monad]: 9.571e-05 [graph_reusing]: 6.16e-06 [inline]: 4.08001e-06 [add_attr]: 0.213921, [1] [add_attr_with_inline]: 0.213898, [1] [Cycle 1]: 8.66e-05, [2] [tag_attr]: 2.963e-05 [meta_addattr_fg_expand]: 6.63e-06 [parallel-infer-symbol]: 3.88999e-06 [pre_auto_parallel]: 4.981e-05 [insert-virtual-dataset]: 3.23e-06 [parallel-infer-symbol-second]: 9.5999e-07 [dataset_repeat_opt]: 2.24001e-06 [pipeline_split]: 1.62001e-06 [optimize]: 0.0161037, [53] [py_interpret_to_execute]: 4.344e-05 [rewriter_before_opt_a]: 0.00010594 [opt_a]: 0.0122089, [2] [Cycle 1]: 0.0108487, [45] [expand_dump_flag]: 4.11001e-06 [switch_simplify]: 4.317e-05 [loop_unroll]: 2.693e-05 [a_1]: 0.00112291 [with_stream_mark]: 3.413e-05 [recompute_prepare]: 2.012e-05 [updatestate_depend_eliminate]: 9.24e-06 [updatestate_assign_eliminate]: 6.36e-06 [updatestate_loads_eliminate]: 5.86e-06 [parameter_eliminate]: 2.41998e-06 [a_2]: 0.0002017 [accelerated_algorithm]: 2.19e-05 [shard]: 3.08998e-06 [meta_shard_fg_expand]: 4.97e-06 [shard_inline]: 1.214e-05 [merge_send_recv]: 1.433e-05 [auto_parallel]: 1.381e-05 [parallel]: 3.268e-05 [flash_sp]: 1.37e-05 [merge_comm]: 8.06001e-06 [allreduce_fusion]: 6.59001e-06 [matmul_add_comm_reduction]: 1.897e-05 [allreduce_slice_to_reducescatter]: 1.66e-06 [virtual_shard_identity]: 1.939e-05 [virtual_dataset]: 1.387e-05 [get_grad_eliminate_]: 1.463e-05 [virtual_output]: 1.414e-05 [merge_forward]: 9.39e-06 [cell_reuse_recompute_pass]: 2.60002e-06 [offload_activation]: 1.96e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.211e-05 [merge_recompute_call_nodes]: 1.71e-06 [before_grad]: 2.467e-05 [set_forward_comm_id_for_comm_node_pass]: 8.60999e-06 [meta_fg_expand]: 6.16998e-06 [flash_sp_send_recv_attached]: 3.69002e-06 [receive_attached]: 2.41998e-06 [after_resolve]: 1.985e-05 [a_after_grad]: 2.191e-05 [renormalize]: 0.00766094 [add_forward_monad_depend]: 1.371e-05 [auto_monad_grad]: 2.58998e-06 [auto_monad_eliminator]: 3.794e-05 [cse]: 0.0007737 [a_3]: 0.00011167 [Cycle 2]: 0.00134268, [45] [expand_dump_flag]: 3.89002e-06 [switch_simplify]: 1.594e-05 [loop_unroll]: 1.322e-05 [a_1]: 0.00036063 [with_stream_mark]: 3.414e-05 [recompute_prepare]: 1.587e-05 [updatestate_depend_eliminate]: 9.31e-06 [updatestate_assign_eliminate]: 6.33e-06 [updatestate_loads_eliminate]: 5.72001e-06 [parameter_eliminate]: 2.74999e-06 [a_2]: 0.00017568 [accelerated_algorithm]: 1.39e-05 [shard]: 2.88e-06 [meta_shard_fg_expand]: 5.30001e-06 [shard_inline]: 1.118e-05 [merge_send_recv]: 1.381e-05 [auto_parallel]: 1.45e-05 [parallel]: 1.046e-05 [flash_sp]: 5.35001e-06 [merge_comm]: 6.71e-06 [allreduce_fusion]: 6.45002e-06 [matmul_add_comm_reduction]: 1.651e-05 [allreduce_slice_to_reducescatter]: 8.99978e-07 [virtual_shard_identity]: 1.492e-05 [virtual_dataset]: 1.158e-05 [get_grad_eliminate_]: 1.265e-05 [virtual_output]: 1.191e-05 [merge_forward]: 7.58001e-06 [cell_reuse_recompute_pass]: 2.61999e-06 [offload_activation]: 1.794e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.395e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 2.072e-05 [set_forward_comm_id_for_comm_node_pass]: 6.64001e-06 [meta_fg_expand]: 6.64999e-06 [flash_sp_send_recv_attached]: 1.89e-06 [receive_attached]: 2.91e-06 [after_resolve]: 1.698e-05 [a_after_grad]: 1.69e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.33998e-06 [auto_monad_grad]: 2.48e-06 [auto_monad_eliminator]: 2.424e-05 [cse]: 6.318e-05 [a_3]: 7.495e-05 [py_interpret_to_execute_after_opt_a]: 2.625e-05 [slice_cell_reuse_recomputed_activation]: 2.07999e-06 [rewriter_after_opt_a]: 0.00030099 [convert_after_rewriter]: 1.312e-05 [order_py_execute_after_rewriter]: 9.41e-06 [mutable_eliminate]: 0.00107536 [opt_b]: 0.00046316, [1] [Cycle 1]: 0.00045255, [7] [b_1]: 0.00030438 [b_2]: 1.306e-05 [updatestate_depend_eliminate]: 1.471e-05 [updatestate_assign_eliminate]: 5.94999e-06 [updatestate_loads_eliminate]: 5.36998e-06 [renormalize]: 8.2e-07 [cse]: 6.543e-05 [optimize_parallel_all_gather_comm]: 2.972e-05 [overlap_param_gather]: 2.57001e-06 [cconv]: 4.125e-05 [loop_unroll]: 0.00052914 [opt_after_cconv]: 0.00016429, [1] [Cycle 1]: 0.00015697, [7] [c_1]: 5.707e-05 [parameter_eliminate]: 5.40001e-06 [updatestate_depend_eliminate]: 1.011e-05 [updatestate_assign_eliminate]: 4.80999e-06 [updatestate_loads_eliminate]: 4.67e-06 [cse]: 4.043e-05 [renormalize]: 4.39992e-07 [remove_dup_value]: 6.628e-05 [tuple_transform]: 0.00015753, [1] [Cycle 1]: 0.00015286, [4] [d_1]: 0.00011558 [none_parameter_eliminate]: 2.17999e-06 [renormalize]: 1.39989e-07 [switch_simplify]: 1.276e-05 [partial_unused_args_eliminate]: 2.06998e-06 [add_recomputation]: 9.446e-05 [cse_after_recomputation]: 4.111e-05, [1] [Cycle 1]: 3.564e-05, [1] [cse]: 2.937e-05 [environ_conv]: 1.565e-05 [swap_dp_allreduce_reducescatter]: 9.42999e-06 [bias_add_comm_swap]: 3.04001e-06 [label_micro_interleaved_index]: 5.39e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.91e-06 [slice_recompute_activation]: 2.73003e-06 [micro_interleaved_order_control]: 2.19999e-06 [assign_add_opt]: 1.40001e-06 [ForceFp32Comm]: 8.50006e-07 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.42001e-06 [reorder_send_recv_between_fp_bp]: 2.81e-06 [comm_op_add_attrs]: 1.11002e-06 [add_comm_op_reuse_tag]: 1.08001e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 1.27999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.98002e-06 [control_data_broadcast_order]: 2.153e-05 [grouped_pairwise_exchange_alltoall]: 2.11e-06 [offloading_packed_experts]: 6.09999e-06 [overlap_recompute_and_grad_model_parallel]: 7.3e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.97999e-06 [overlap_recompute_comm]: 2.63e-06 [overlap_grad_ring_attention]: 6.14001e-06 [overlap_grad_flash_sp]: 3.164e-05 [begin_end_overlap_inline]: 4.89992e-07 [split_matmul_comm_elemetwise]: 2.79999e-06 [split_layernorm_comm]: 1.87999e-06 [handle_group_info]: 1.12e-06 [symbol_engine_optimizer]: 0.00030948, [1] [Cycle 1]: 0.00030469, [6] [build]: 0.00017707 [elim_shapecalc]: 1.799e-05 [elim_not_effective]: 2.554e-05 [opt_reshape]: 1.314e-05 [fold_const_symbol]: 3.491e-05 [renormalize]: 2.10013e-07 [detach_backward]: 2.41e-06 [pipeline_parallel_scheduler]: 1.59998e-06 [auto_monad_reorder]: 2.8e-05 [get_jit_bprop_graph]: 3.11999e-06 [rewriter_after_jit_bprop_graph]: 5.13002e-06 [opt_after_jit_grad]: 0.00052987 [validate]: 6.895e-05 Sums bootstrap : 0.000905s : 0.04% type_inference : 2.501044s : 99.33% event_method : 0.000025s : 0.00% auto_monad : 0.000096s : 0.00% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000030s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.00% 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 : 0.000043s : 0.00% optimize.rewriter_before_opt_a : 0.000106s : 0.00% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001484s : 0.06% optimize.opt_a.with_stream_mark : 0.000068s : 0.00% optimize.opt_a.recompute_prepare : 0.000036s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000377s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000036s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000028s : 0.00% optimize.opt_a.auto_parallel : 0.000028s : 0.00% optimize.opt_a.parallel : 0.000043s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000015s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000034s : 0.00% optimize.opt_a.virtual_dataset : 0.000025s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.00% optimize.opt_a.virtual_output : 0.000026s : 0.00% optimize.opt_a.merge_forward : 0.000017s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000056s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000045s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.00% optimize.opt_a.meta_fg_expand : 0.000013s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000037s : 0.00% optimize.opt_a.a_after_grad : 0.000039s : 0.00% optimize.opt_a.renormalize : 0.007661s : 0.30% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000062s : 0.00% optimize.opt_a.cse : 0.000837s : 0.03% optimize.opt_a.a_3 : 0.000187s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000301s : 0.01% optimize.convert_after_rewriter : 0.000013s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.001075s : 0.04% optimize.opt_b.b_1 : 0.000304s : 0.01% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000065s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000529s : 0.02% optimize.opt_after_cconv.c_1 : 0.000057s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000040s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000066s : 0.00% optimize.tuple_transform.d_1 : 0.000116s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000094s : 0.00% optimize.cse_after_recomputation.cse : 0.000029s : 0.00% optimize.environ_conv : 0.000016s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 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 : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000032s : 0.00% 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 : 0.000177s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000035s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000028s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000530s : 0.02% validate : 0.000069s : 0.00% Time group info: ------[substitution.] 0.000535 111 9.12% : 0.000049s : 6: substitution.arithmetic_simplify 0.94% : 0.000005s : 6: substitution.elim_not_effective 2.57% : 0.000014s : 6: substitution.float_tuple_getitem_switch 3.47% : 0.000019s : 6: substitution.fold_const_symbol 1.75% : 0.000009s : 8: substitution.graph_param_transform 44.89% : 0.000240s : 5: substitution.inline 1.51% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.85% : 0.000015s : 4: substitution.minmaximum_grad 2.18% : 0.000012s : 12: substitution.remove_not_recompute_node 1.25% : 0.000007s : 2: substitution.replace_old_param 6.83% : 0.000037s : 8: substitution.tuple_list_convert_item_index_to_positive 3.76% : 0.000020s : 8: substitution.tuple_list_get_item_const_eliminator 4.22% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 10.66% : 0.000057s : 12: substitution.tuple_list_get_item_eliminator 3.98% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.500940 2 99.82% : 2.496394s : 1: type_inference.infer 0.18% : 0.004546s : 1: type_inference.specialize ------[replace.] 0.000057 5 100.00% : 0.000057s : 5: replace.inline ------[match.] 0.000236 5 100.00% : 0.000236s : 5: match.inline ------[predicate.] 0.000369 2113 1.10% : 0.000004s : 21: predicate.accumulaten_eliminater 0.92% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.64% : 0.000002s : 16: predicate.addn_check_dump 0.99% : 0.000004s : 21: predicate.addn_zero_filter 0.85% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.56% : 0.000009s : 37: predicate.arithmetic_simplify 0.89% : 0.000003s : 21: predicate.cast_eliminate 0.69% : 0.000003s : 16: predicate.check_bprop_eliminate 0.67% : 0.000002s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.65% : 0.000002s : 16: predicate.depend_value_elim 0.98% : 0.000004s : 21: predicate.dict_get_item_const_eliminator 0.91% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.84% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.94% : 0.000003s : 16: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 8: predicate.elim_not_effective 0.48% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.32% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.11% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_depend_swap 1.91% : 0.000007s : 45: predicate.environ_get_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.99% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.66% : 0.000006s : 26: predicate.float_depend_g_call 0.73% : 0.000003s : 16: predicate.float_environ_get_switch 1.20% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.80% : 0.000003s : 16: predicate.get_grad_eliminate 0.21% : 0.000001s : 8: predicate.graph_param_transform 0.67% : 0.000002s : 16: predicate.incorporate_call 0.55% : 0.000002s : 16: predicate.incorporate_call_switch 5.35% : 0.000020s : 95: predicate.inline 1.05% : 0.000004s : 16: predicate.inline_without_move 0.34% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.05% : 0.000004s : 16: predicate.less_batch_normalization 1.69% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.20% : 0.000008s : 58: predicate.load_eliminater 1.16% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.39% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.70% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.80% : 0.000003s : 16: predicate.merge_addn 0.62% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.65% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.82% : 0.000003s : 21: predicate.minmaximum_grad 1.93% : 0.000007s : 8: predicate.mutable_eliminate 0.41% : 0.000002s : 8: predicate.opt_reshape 0.44% : 0.000002s : 8: predicate.parallel_virtual_node 1.50% : 0.000006s : 26: predicate.partial_defer_inline 1.13% : 0.000004s : 29: predicate.partial_eliminate 0.86% : 0.000003s : 21: predicate.print_const_string_wrapper 0.64% : 0.000002s : 16: predicate.reduce_all_const_elim 1.16% : 0.000004s : 21: predicate.reduce_eliminate 2.22% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.47% : 0.000002s : 16: predicate.remove_not_recompute_node 1.12% : 0.000004s : 37: predicate.replace_applicator 0.43% : 0.000002s : 16: predicate.replace_old_param 0.27% : 0.000001s : 8: predicate.reset_defer_inline 1.09% : 0.000004s : 21: predicate.reshape_eliminate 0.67% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.47% : 0.000002s : 8: predicate.row_tensor_eliminate 1.47% : 0.000005s : 16: predicate.same_eliminate 0.41% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.90% : 0.000003s : 16: predicate.shard_identity_eliminate 0.79% : 0.000003s : 16: predicate.special_op_eliminate 0.85% : 0.000003s : 16: predicate.specialize_transform 1.17% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.87% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.33% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.08% : 0.000004s : 26: predicate.switch_defer_inline 1.65% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.91% : 0.000014s : 86: predicate.switch_simplify 1.06% : 0.000004s : 21: predicate.tile_eliminate 0.91% : 0.000003s : 21: predicate.transpose_eliminate 1.91% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.97% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.62% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.59% : 0.000013s : 53: predicate.tuple_list_get_item_eliminator 1.83% : 0.000007s : 37: predicate.tuple_list_get_set_item_eliminator 2.54% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.58% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.13% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.83% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 8: predicate.value_based_eliminate 0.76% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.95% : 0.000003s : 16: predicate.virtual_output_eliminate 0.31% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007012 32 63.95% : 0.004484s : 25: func_graph_cloner_run.FuncGraphClonerGraph 36.05% : 0.002528s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.973563 192 0.00% : 0.000004s : 1: ForceFp32Comm 7.19% : 0.213928s : 1: add_attr 7.19% : 0.213903s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000099s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000101s : 1: auto_monad 0.00% : 0.000032s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000974s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000017s : 1: convert_after_rewriter 0.00% : 0.000044s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.00% : 0.000034s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000540s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.001092s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.08% : 0.002404s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000043s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000281s : 28: opt.transform.opt_b 0.00% : 0.000126s : 2: opt.transform.opt_trans_graph 0.00% : 0.000087s : 4: opt.transform.symbol_engine_opt 0.41% : 0.012213s : 1: opt_a 0.01% : 0.000168s : 1: opt_after_cconv 0.02% : 0.000543s : 1: opt_after_jit_grad 0.02% : 0.000468s : 1: opt_b 0.54% : 0.016109s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000055s : 1: pre_auto_parallel 0.00% : 0.000048s : 1: py_interpret_to_execute 0.00% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000071s : 1: remove_dup_value 0.16% : 0.004700s : 1: renormalize.infer 0.10% : 0.002940s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000312s : 1: rewriter_after_opt_a 0.00% : 0.000112s : 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% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000312s : 1: symbol_engine_optimizer 0.01% : 0.000161s : 1: tuple_transform 84.11% : 2.501078s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-float32--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-float32--1-shape1],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:42.941.950 [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 = 3.191, [21] [bootstrap]: 0.00078215 [type_inference]: 2.90783 [event_method]: 2.541e-05 [auto_monad]: 9.572e-05 [graph_reusing]: 6.67002e-06 [inline]: 3.83999e-06 [add_attr]: 0.00626116, [1] [add_attr_with_inline]: 0.00624289, [1] [Cycle 1]: 7.752e-05, [2] [tag_attr]: 2.625e-05 [meta_addattr_fg_expand]: 5.91998e-06 [parallel-infer-symbol]: 3.68e-06 [pre_auto_parallel]: 4.375e-05 [insert-virtual-dataset]: 2.54001e-06 [parallel-infer-symbol-second]: 8.99978e-07 [dataset_repeat_opt]: 2.23998e-06 [pipeline_split]: 1.88002e-06 [optimize]: 0.274957, [53] [py_interpret_to_execute]: 3.447e-05 [rewriter_before_opt_a]: 9.434e-05 [opt_a]: 0.271263, [2] [Cycle 1]: 0.269786, [45] [expand_dump_flag]: 7.125e-05 [switch_simplify]: 4.374e-05 [loop_unroll]: 2.67e-05 [a_1]: 0.00107169 [with_stream_mark]: 2.504e-05 [recompute_prepare]: 1.785e-05 [updatestate_depend_eliminate]: 8.99003e-06 [updatestate_assign_eliminate]: 6.02999e-06 [updatestate_loads_eliminate]: 6.02001e-06 [parameter_eliminate]: 2.61e-06 [a_2]: 0.00019688 [accelerated_algorithm]: 1.342e-05 [shard]: 2.72001e-06 [meta_shard_fg_expand]: 3.49001e-06 [shard_inline]: 1.093e-05 [merge_send_recv]: 1.359e-05 [auto_parallel]: 1.073e-05 [parallel]: 2.794e-05 [flash_sp]: 1.048e-05 [merge_comm]: 6.91001e-06 [allreduce_fusion]: 6.53e-06 [matmul_add_comm_reduction]: 1.591e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.676e-05 [virtual_dataset]: 1.239e-05 [get_grad_eliminate_]: 1.22e-05 [virtual_output]: 1.307e-05 [merge_forward]: 6.58998e-06 [cell_reuse_recompute_pass]: 1.19003e-06 [offload_activation]: 1.795e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.544e-05 [merge_recompute_call_nodes]: 1.86e-06 [before_grad]: 2.178e-05 [set_forward_comm_id_for_comm_node_pass]: 7.16999e-06 [meta_fg_expand]: 5.62001e-06 [flash_sp_send_recv_attached]: 3.06001e-06 [receive_attached]: 2.88e-06 [after_resolve]: 1.688e-05 [a_after_grad]: 2.134e-05 [renormalize]: 0.267059 [add_forward_monad_depend]: 1.243e-05 [auto_monad_grad]: 2.72001e-06 [auto_monad_eliminator]: 3.431e-05 [cse]: 0.00044787 [a_3]: 0.00010773 [Cycle 2]: 0.00146144, [45] [expand_dump_flag]: 3.41999e-06 [switch_simplify]: 1.498e-05 [loop_unroll]: 1.194e-05 [a_1]: 0.00034699 [with_stream_mark]: 2.996e-05 [recompute_prepare]: 1.226e-05 [updatestate_depend_eliminate]: 8.68001e-06 [updatestate_assign_eliminate]: 6.01998e-06 [updatestate_loads_eliminate]: 5.57001e-06 [parameter_eliminate]: 2.00002e-06 [a_2]: 0.00016244 [accelerated_algorithm]: 1.212e-05 [shard]: 2.63e-06 [meta_shard_fg_expand]: 3.45e-06 [shard_inline]: 1.065e-05 [merge_send_recv]: 1.287e-05 [auto_parallel]: 1.318e-05 [parallel]: 8.89e-06 [flash_sp]: 4.32998e-06 [merge_comm]: 6.64001e-06 [allreduce_fusion]: 6.04001e-06 [matmul_add_comm_reduction]: 1.383e-05 [allreduce_slice_to_reducescatter]: 1.81998e-06 [virtual_shard_identity]: 1.184e-05 [virtual_dataset]: 1.032e-05 [get_grad_eliminate_]: 1.177e-05 [virtual_output]: 1.133e-05 [merge_forward]: 7.22002e-06 [cell_reuse_recompute_pass]: 2.82002e-06 [offload_activation]: 1.572e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.129e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 1.887e-05 [set_forward_comm_id_for_comm_node_pass]: 6.76999e-06 [meta_fg_expand]: 4.77e-06 [flash_sp_send_recv_attached]: 2.06998e-06 [receive_attached]: 2.94001e-06 [after_resolve]: 1.679e-05 [a_after_grad]: 1.714e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.53998e-06 [auto_monad_grad]: 2.66999e-06 [auto_monad_eliminator]: 1.698e-05 [cse]: 0.00027623 [a_3]: 7.691e-05 [py_interpret_to_execute_after_opt_a]: 2.8e-05 [slice_cell_reuse_recomputed_activation]: 2.07999e-06 [rewriter_after_opt_a]: 0.00028803 [convert_after_rewriter]: 1.299e-05 [order_py_execute_after_rewriter]: 9.26002e-06 [mutable_eliminate]: 0.00084798 [opt_b]: 0.00044834, [1] [Cycle 1]: 0.00043985, [7] [b_1]: 0.00030184 [b_2]: 1.348e-05 [updatestate_depend_eliminate]: 1.229e-05 [updatestate_assign_eliminate]: 5.95002e-06 [updatestate_loads_eliminate]: 5.09e-06 [renormalize]: 6.69999e-07 [cse]: 5.563e-05 [optimize_parallel_all_gather_comm]: 2.835e-05 [overlap_param_gather]: 2.06998e-06 [cconv]: 3.901e-05 [loop_unroll]: 0.0005435 [opt_after_cconv]: 0.00017564, [1] [Cycle 1]: 0.00016764, [7] [c_1]: 5.774e-05 [parameter_eliminate]: 4.99998e-06 [updatestate_depend_eliminate]: 1.148e-05 [updatestate_assign_eliminate]: 5.10001e-06 [updatestate_loads_eliminate]: 4.53001e-06 [cse]: 4.656e-05 [renormalize]: 8.2e-07 [remove_dup_value]: 6.464e-05 [tuple_transform]: 0.00016948, [1] [Cycle 1]: 0.00016384, [4] [d_1]: 0.00012231 [none_parameter_eliminate]: 2.31e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 1.445e-05 [partial_unused_args_eliminate]: 2.69001e-06 [add_recomputation]: 9.534e-05 [cse_after_recomputation]: 4.711e-05, [1] [Cycle 1]: 4.04e-05, [1] [cse]: 3.158e-05 [environ_conv]: 1.699e-05 [swap_dp_allreduce_reducescatter]: 1.096e-05 [bias_add_comm_swap]: 2.98e-06 [label_micro_interleaved_index]: 5.35001e-06 [label_fine_grained_interleaved_index]: 2.73e-06 [merge_cast_opt]: 1.68002e-06 [slice_recompute_activation]: 2.53e-06 [micro_interleaved_order_control]: 2.84001e-06 [assign_add_opt]: 1.45999e-06 [ForceFp32Comm]: 1.02e-06 [remove_cast_before_assign_add]: 1.14e-06 [full_micro_interleaved_order_control]: 2.34001e-06 [reorder_send_recv_between_fp_bp]: 2.95002e-06 [comm_op_add_attrs]: 1.14e-06 [add_comm_op_reuse_tag]: 1.45001e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 1.44998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06e-06 [control_data_broadcast_order]: 2.552e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 6.86001e-06 [overlap_recompute_and_grad_model_parallel]: 8.77999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.32999e-06 [overlap_grad_ring_attention]: 6.54001e-06 [overlap_grad_flash_sp]: 3.173e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.56e-06 [split_layernorm_comm]: 1.79998e-06 [handle_group_info]: 1.17e-06 [symbol_engine_optimizer]: 0.00032613, [1] [Cycle 1]: 0.00031989, [6] [build]: 0.00017886 [elim_shapecalc]: 2.093e-05 [elim_not_effective]: 2.687e-05 [opt_reshape]: 1.282e-05 [fold_const_symbol]: 3.668e-05 [renormalize]: 2.60014e-07 [detach_backward]: 3.24001e-06 [pipeline_parallel_scheduler]: 1.62001e-06 [auto_monad_reorder]: 3.074e-05 [get_jit_bprop_graph]: 3.56999e-06 [rewriter_after_jit_bprop_graph]: 6.12999e-06 [opt_after_jit_grad]: 0.00063005 [validate]: 7.364e-05 Sums bootstrap : 0.000782s : 0.02% type_inference : 2.907829s : 91.34% event_method : 0.000025s : 0.00% auto_monad : 0.000096s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000044s : 0.00% 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 : 0.000034s : 0.00% optimize.rewriter_before_opt_a : 0.000094s : 0.00% optimize.opt_a.expand_dump_flag : 0.000075s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001419s : 0.04% optimize.opt_a.with_stream_mark : 0.000055s : 0.00% optimize.opt_a.recompute_prepare : 0.000030s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000359s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000026s : 0.00% optimize.opt_a.auto_parallel : 0.000024s : 0.00% optimize.opt_a.parallel : 0.000037s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000030s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000029s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000024s : 0.00% optimize.opt_a.merge_forward : 0.000014s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000047s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000034s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.267059s : 8.39% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000051s : 0.00% optimize.opt_a.cse : 0.000724s : 0.02% optimize.opt_a.a_3 : 0.000185s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000288s : 0.01% optimize.convert_after_rewriter : 0.000013s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000848s : 0.03% optimize.opt_b.b_1 : 0.000302s : 0.01% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000056s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000039s : 0.00% optimize.loop_unroll : 0.000544s : 0.02% optimize.opt_after_cconv.c_1 : 0.000058s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000047s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000065s : 0.00% optimize.tuple_transform.d_1 : 0.000122s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000095s : 0.00% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 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 : 0.000002s : 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 : 0.000026s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 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 : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000032s : 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 : 0.000179s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000037s : 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 : 0.000031s : 0.00% get_jit_bprop_graph : 0.000004s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000630s : 0.02% validate : 0.000074s : 0.00% Time group info: ------[substitution.] 0.000497 111 9.24% : 0.000046s : 6: substitution.arithmetic_simplify 1.04% : 0.000005s : 6: substitution.elim_not_effective 2.41% : 0.000012s : 6: substitution.float_tuple_getitem_switch 3.83% : 0.000019s : 6: substitution.fold_const_symbol 1.96% : 0.000010s : 8: substitution.graph_param_transform 44.34% : 0.000220s : 5: substitution.inline 1.70% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.00% : 0.000010s : 4: substitution.minmaximum_grad 1.91% : 0.000009s : 12: substitution.remove_not_recompute_node 1.14% : 0.000006s : 2: substitution.replace_old_param 6.98% : 0.000035s : 8: substitution.tuple_list_convert_item_index_to_positive 3.22% : 0.000016s : 8: substitution.tuple_list_get_item_const_eliminator 4.73% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 11.05% : 0.000055s : 12: substitution.tuple_list_get_item_eliminator 4.45% : 0.000022s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.907721 2 99.85% : 2.903375s : 1: type_inference.infer 0.15% : 0.004346s : 1: type_inference.specialize ------[replace.] 0.000051 5 100.00% : 0.000051s : 5: replace.inline ------[match.] 0.000216 5 100.00% : 0.000216s : 5: match.inline ------[predicate.] 0.000359 2113 0.87% : 0.000003s : 21: predicate.accumulaten_eliminater 1.17% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.64% : 0.000002s : 16: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.83% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.42% : 0.000009s : 37: predicate.arithmetic_simplify 0.93% : 0.000003s : 21: predicate.cast_eliminate 0.70% : 0.000003s : 16: predicate.check_bprop_eliminate 0.64% : 0.000002s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.66% : 0.000002s : 16: predicate.depend_value_elim 0.90% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.93% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.87% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.47% : 0.000005s : 16: predicate.dumpgradient_eliminate 0.40% : 0.000001s : 8: predicate.elim_not_effective 0.83% : 0.000003s : 8: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.05% : 0.000004s : 29: predicate.environ_get_depend_swap 1.76% : 0.000006s : 45: predicate.environ_get_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.02% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.66% : 0.000006s : 26: predicate.float_depend_g_call 0.72% : 0.000003s : 16: predicate.float_environ_get_switch 1.09% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 8: predicate.fold_const_symbol 0.74% : 0.000003s : 16: predicate.get_grad_eliminate 0.28% : 0.000001s : 8: predicate.graph_param_transform 0.66% : 0.000002s : 16: predicate.incorporate_call 0.59% : 0.000002s : 16: predicate.incorporate_call_switch 5.53% : 0.000020s : 95: predicate.inline 0.93% : 0.000003s : 16: predicate.inline_without_move 0.31% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.96% : 0.000003s : 16: predicate.less_batch_normalization 1.76% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.23% : 0.000008s : 58: predicate.load_eliminater 1.22% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.55% : 0.000006s : 36: predicate.loop_unroll_before_grad 1.73% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.70% : 0.000003s : 16: predicate.merge_addn 0.64% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.64% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.81% : 0.000003s : 21: predicate.minmaximum_grad 1.48% : 0.000005s : 8: predicate.mutable_eliminate 0.39% : 0.000001s : 8: predicate.opt_reshape 0.48% : 0.000002s : 8: predicate.parallel_virtual_node 1.64% : 0.000006s : 26: predicate.partial_defer_inline 1.16% : 0.000004s : 29: predicate.partial_eliminate 1.00% : 0.000004s : 21: predicate.print_const_string_wrapper 0.76% : 0.000003s : 16: predicate.reduce_all_const_elim 1.20% : 0.000004s : 21: predicate.reduce_eliminate 2.32% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.53% : 0.000002s : 16: predicate.remove_not_recompute_node 1.25% : 0.000004s : 37: predicate.replace_applicator 0.53% : 0.000002s : 16: predicate.replace_old_param 0.27% : 0.000001s : 8: predicate.reset_defer_inline 0.87% : 0.000003s : 21: predicate.reshape_eliminate 0.70% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.43% : 0.000002s : 8: predicate.row_tensor_eliminate 1.07% : 0.000004s : 16: predicate.same_eliminate 0.47% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.77% : 0.000003s : 16: predicate.shard_identity_eliminate 0.83% : 0.000003s : 16: predicate.special_op_eliminate 0.83% : 0.000003s : 16: predicate.specialize_transform 1.10% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.09% : 0.000004s : 26: predicate.switch_defer_inline 1.71% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.03% : 0.000014s : 86: predicate.switch_simplify 0.98% : 0.000004s : 21: predicate.tile_eliminate 0.91% : 0.000003s : 21: predicate.transpose_eliminate 1.82% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 2.00% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.24% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.75% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.68% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.54% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.18% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.94% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 8: predicate.value_based_eliminate 0.70% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.80% : 0.000003s : 16: predicate.virtual_output_eliminate 0.35% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.44% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006620 32 67.36% : 0.004459s : 25: func_graph_cloner_run.FuncGraphClonerGraph 32.64% : 0.002160s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.742015 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.17% : 0.006268s : 1: add_attr 0.17% : 0.006248s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000102s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000102s : 1: auto_monad 0.00% : 0.000035s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000841s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000029s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000010s : 1: detach_backward 0.00% : 0.000020s : 1: environ_conv 0.00% : 0.000033s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 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 0.01% : 0.000556s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000863s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000033s : 1: opt.transform.mutable_eliminate 0.06% : 0.002280s : 78: opt.transform.opt_a 0.00% : 0.000056s : 1: opt.transform.opt_after_cconv 0.00% : 0.000053s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000280s : 28: opt.transform.opt_b 0.00% : 0.000133s : 2: opt.transform.opt_trans_graph 0.00% : 0.000092s : 4: opt.transform.symbol_engine_opt 7.25% : 0.271267s : 1: opt_a 0.00% : 0.000180s : 1: opt_after_cconv 0.02% : 0.000646s : 1: opt_after_jit_grad 0.01% : 0.000452s : 1: opt_b 7.35% : 0.274965s : 1: optimize 0.00% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000049s : 1: pre_auto_parallel 0.00% : 0.000039s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000070s : 1: remove_dup_value 7.07% : 0.264621s : 1: renormalize.infer 0.06% : 0.002419s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000296s : 1: rewriter_after_opt_a 0.00% : 0.000099s : 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% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000330s : 1: symbol_engine_optimizer 0.00% : 0.000173s : 1: tuple_transform 77.71% : 2.907869s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-float16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-float16--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:38:56.965.792 [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 = 3.39153, [21] [bootstrap]: 0.00080521 [type_inference]: 3.1441 [event_method]: 2.402e-05 [auto_monad]: 9.373e-05 [graph_reusing]: 6.55002e-06 [inline]: 7.05e-06 [add_attr]: 0.00689144, [1] [add_attr_with_inline]: 0.00687281, [1] [Cycle 1]: 8.479e-05, [2] [tag_attr]: 3.14e-05 [meta_addattr_fg_expand]: 6.01e-06 [parallel-infer-symbol]: 4.10998e-06 [pre_auto_parallel]: 5.316e-05 [insert-virtual-dataset]: 3.07002e-06 [parallel-infer-symbol-second]: 7.7e-07 [dataset_repeat_opt]: 2.01e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.238461, [53] [py_interpret_to_execute]: 3.959e-05 [rewriter_before_opt_a]: 0.0001117 [opt_a]: 0.234357, [2] [Cycle 1]: 0.233017, [45] [expand_dump_flag]: 4.36002e-06 [switch_simplify]: 4.619e-05 [loop_unroll]: 2.813e-05 [a_1]: 0.00118908 [with_stream_mark]: 3.11e-05 [recompute_prepare]: 2.122e-05 [updatestate_depend_eliminate]: 9.31e-06 [updatestate_assign_eliminate]: 5.97999e-06 [updatestate_loads_eliminate]: 5.79e-06 [parameter_eliminate]: 2.74001e-06 [a_2]: 0.00023681 [accelerated_algorithm]: 1.577e-05 [shard]: 2.89999e-06 [meta_shard_fg_expand]: 5.37999e-06 [shard_inline]: 1.205e-05 [merge_send_recv]: 1.535e-05 [auto_parallel]: 1.295e-05 [parallel]: 2.903e-05 [flash_sp]: 1.223e-05 [merge_comm]: 6.90002e-06 [allreduce_fusion]: 6.63e-06 [matmul_add_comm_reduction]: 1.673e-05 [allreduce_slice_to_reducescatter]: 1.17e-06 [virtual_shard_identity]: 1.917e-05 [virtual_dataset]: 1.319e-05 [get_grad_eliminate_]: 1.254e-05 [virtual_output]: 1.228e-05 [merge_forward]: 6.99001e-06 [cell_reuse_recompute_pass]: 2.20002e-06 [offload_activation]: 1.763e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.901e-05 [merge_recompute_call_nodes]: 1.87001e-06 [before_grad]: 2.352e-05 [set_forward_comm_id_for_comm_node_pass]: 8.42e-06 [meta_fg_expand]: 5.35001e-06 [flash_sp_send_recv_attached]: 3.14999e-06 [receive_attached]: 2.17001e-06 [after_resolve]: 1.859e-05 [a_after_grad]: 2.122e-05 [renormalize]: 0.230476 [add_forward_monad_depend]: 1.45e-05 [auto_monad_grad]: 3.3e-06 [auto_monad_eliminator]: 3.32e-05 [cse]: 0.00012963 [a_3]: 0.00010585 [Cycle 2]: 0.001323, [45] [expand_dump_flag]: 2.19999e-06 [switch_simplify]: 1.546e-05 [loop_unroll]: 1.183e-05 [a_1]: 0.00035625 [with_stream_mark]: 2.521e-05 [recompute_prepare]: 1.26e-05 [updatestate_depend_eliminate]: 9.06998e-06 [updatestate_assign_eliminate]: 6.05002e-06 [updatestate_loads_eliminate]: 5.27001e-06 [parameter_eliminate]: 2.22999e-06 [a_2]: 0.00024637 [accelerated_algorithm]: 1.2e-05 [shard]: 3.17002e-06 [meta_shard_fg_expand]: 4.24997e-06 [shard_inline]: 1.15e-05 [merge_send_recv]: 1.296e-05 [auto_parallel]: 1.362e-05 [parallel]: 1.018e-05 [flash_sp]: 4.48999e-06 [merge_comm]: 6.89999e-06 [allreduce_fusion]: 5.92999e-06 [matmul_add_comm_reduction]: 1.456e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 1.22e-05 [virtual_dataset]: 1.092e-05 [get_grad_eliminate_]: 1.17e-05 [virtual_output]: 1.089e-05 [merge_forward]: 6.81999e-06 [cell_reuse_recompute_pass]: 2.99999e-06 [offload_activation]: 1.56e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.306e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 1.918e-05 [set_forward_comm_id_for_comm_node_pass]: 6.68e-06 [meta_fg_expand]: 5.10001e-06 [flash_sp_send_recv_attached]: 1.84998e-06 [receive_attached]: 2.67001e-06 [after_resolve]: 1.63e-05 [a_after_grad]: 1.709e-05 [renormalize]: 5.9983e-08 [add_forward_monad_depend]: 2.53e-06 [auto_monad_grad]: 1.65001e-06 [auto_monad_eliminator]: 1.784e-05 [cse]: 4.297e-05 [a_3]: 7.34e-05 [py_interpret_to_execute_after_opt_a]: 2.627e-05 [slice_cell_reuse_recomputed_activation]: 2.12999e-06 [rewriter_after_opt_a]: 0.00029255 [convert_after_rewriter]: 1.381e-05 [order_py_execute_after_rewriter]: 9.21998e-06 [mutable_eliminate]: 0.00101942 [opt_b]: 0.00044334, [1] [Cycle 1]: 0.0004345, [7] [b_1]: 0.00029366 [b_2]: 1.351e-05 [updatestate_depend_eliminate]: 1.219e-05 [updatestate_assign_eliminate]: 6.11998e-06 [updatestate_loads_eliminate]: 5.17999e-06 [renormalize]: 9.49978e-07 [cse]: 6.105e-05 [optimize_parallel_all_gather_comm]: 2.925e-05 [overlap_param_gather]: 2.21e-06 [cconv]: 3.701e-05 [loop_unroll]: 0.0006567 [opt_after_cconv]: 0.000214, [1] [Cycle 1]: 0.00020564, [7] [c_1]: 5.915e-05 [parameter_eliminate]: 5.61e-06 [updatestate_depend_eliminate]: 1.245e-05 [updatestate_assign_eliminate]: 5.24e-06 [updatestate_loads_eliminate]: 4.52998e-06 [cse]: 4.532e-05 [renormalize]: 6.89994e-07 [remove_dup_value]: 6.806e-05 [tuple_transform]: 0.00015877, [1] [Cycle 1]: 0.00015295, [4] [d_1]: 0.00011601 [none_parameter_eliminate]: 2.36e-06 [renormalize]: 3.30008e-07 [switch_simplify]: 1.224e-05 [partial_unused_args_eliminate]: 2.20002e-06 [add_recomputation]: 0.00010736 [cse_after_recomputation]: 4.463e-05, [1] [Cycle 1]: 3.879e-05, [1] [cse]: 3.272e-05 [environ_conv]: 4.074e-05 [swap_dp_allreduce_reducescatter]: 1.091e-05 [bias_add_comm_swap]: 3.78001e-06 [label_micro_interleaved_index]: 5.94e-06 [label_fine_grained_interleaved_index]: 2.88003e-06 [merge_cast_opt]: 1.67001e-06 [slice_recompute_activation]: 2.38002e-06 [micro_interleaved_order_control]: 2.18998e-06 [assign_add_opt]: 1.65001e-06 [ForceFp32Comm]: 8.89995e-07 [remove_cast_before_assign_add]: 1.07998e-06 [full_micro_interleaved_order_control]: 2.68e-06 [reorder_send_recv_between_fp_bp]: 2.89999e-06 [comm_op_add_attrs]: 1.08001e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 1.13001e-06 [interleave_parallel_branches]: 1.19e-06 [overlap_opt_shard_in_pipeline]: 1.89e-06 [overlap_opt_shard_grad_in_pipeline]: 2.05002e-06 [control_data_broadcast_order]: 2.202e-05 [grouped_pairwise_exchange_alltoall]: 1.67001e-06 [offloading_packed_experts]: 6.70002e-06 [overlap_recompute_and_grad_model_parallel]: 7.75e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.55999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.46002e-06 [overlap_recompute_comm]: 2.38998e-06 [overlap_grad_ring_attention]: 5.92999e-06 [overlap_grad_flash_sp]: 3.159e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.36998e-06 [split_layernorm_comm]: 1.73002e-06 [handle_group_info]: 1.37e-06 [symbol_engine_optimizer]: 0.00037403, [1] [Cycle 1]: 0.00036854, [6] [build]: 0.00022731 [elim_shapecalc]: 2.107e-05 [elim_not_effective]: 2.694e-05 [opt_reshape]: 1.437e-05 [fold_const_symbol]: 3.612e-05 [renormalize]: 9.00007e-07 [detach_backward]: 3.26001e-06 [pipeline_parallel_scheduler]: 1.68002e-06 [auto_monad_reorder]: 3.072e-05 [get_jit_bprop_graph]: 3.07002e-06 [rewriter_after_jit_bprop_graph]: 5.85002e-06 [opt_after_jit_grad]: 0.00072381 [validate]: 8.606e-05 Sums bootstrap : 0.000805s : 0.02% type_inference : 3.144096s : 92.93% event_method : 0.000024s : 0.00% auto_monad : 0.000094s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000007s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000031s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000053s : 0.00% 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 : 0.000040s : 0.00% optimize.rewriter_before_opt_a : 0.000112s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000062s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001545s : 0.05% optimize.opt_a.with_stream_mark : 0.000056s : 0.00% optimize.opt_a.recompute_prepare : 0.000034s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000483s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000028s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000024s : 0.00% optimize.opt_a.merge_send_recv : 0.000028s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000039s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000031s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000014s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000033s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000052s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000043s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.230476s : 6.81% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000051s : 0.00% optimize.opt_a.cse : 0.000173s : 0.01% optimize.opt_a.a_3 : 0.000179s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000293s : 0.01% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.001019s : 0.03% optimize.opt_b.b_1 : 0.000294s : 0.01% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000061s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000657s : 0.02% optimize.opt_after_cconv.c_1 : 0.000059s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000045s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000068s : 0.00% optimize.tuple_transform.d_1 : 0.000116s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000107s : 0.00% optimize.cse_after_recomputation.cse : 0.000033s : 0.00% optimize.environ_conv : 0.000041s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% 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 : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000032s : 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 : 0.000227s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000036s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000031s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000724s : 0.02% validate : 0.000086s : 0.00% Time group info: ------[substitution.] 0.000654 111 20.07% : 0.000131s : 6: substitution.arithmetic_simplify 0.83% : 0.000005s : 6: substitution.elim_not_effective 1.91% : 0.000013s : 6: substitution.float_tuple_getitem_switch 2.94% : 0.000019s : 6: substitution.fold_const_symbol 1.52% : 0.000010s : 8: substitution.graph_param_transform 41.77% : 0.000273s : 5: substitution.inline 1.32% : 0.000009s : 12: substitution.j_node_and_user_rematch 1.58% : 0.000010s : 4: substitution.minmaximum_grad 1.56% : 0.000010s : 12: substitution.remove_not_recompute_node 1.00% : 0.000007s : 2: substitution.replace_old_param 5.49% : 0.000036s : 8: substitution.tuple_list_convert_item_index_to_positive 3.37% : 0.000022s : 8: substitution.tuple_list_get_item_const_eliminator 3.52% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 8.50% : 0.000056s : 12: substitution.tuple_list_get_item_eliminator 4.60% : 0.000030s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 3.143988 2 99.85% : 3.139117s : 1: type_inference.infer 0.15% : 0.004871s : 1: type_inference.specialize ------[replace.] 0.000058 5 100.00% : 0.000058s : 5: replace.inline ------[match.] 0.000270 5 100.00% : 0.000270s : 5: match.inline ------[predicate.] 0.000362 2113 0.94% : 0.000003s : 21: predicate.accumulaten_eliminater 1.07% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.61% : 0.000002s : 16: predicate.addn_check_dump 1.01% : 0.000004s : 21: predicate.addn_zero_filter 0.85% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.37% : 0.000009s : 37: predicate.arithmetic_simplify 0.94% : 0.000003s : 21: predicate.cast_eliminate 0.71% : 0.000003s : 16: predicate.check_bprop_eliminate 0.72% : 0.000003s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.79% : 0.000003s : 16: predicate.depend_value_elim 0.86% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.96% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.85% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.14% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 8: predicate.elim_not_effective 0.42% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.13% : 0.000004s : 29: predicate.environ_get_depend_swap 1.90% : 0.000007s : 45: predicate.environ_get_eliminate 1.23% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.09% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.61% : 0.000006s : 26: predicate.float_depend_g_call 0.73% : 0.000003s : 16: predicate.float_environ_get_switch 1.12% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 8: predicate.fold_const_symbol 0.75% : 0.000003s : 16: predicate.get_grad_eliminate 0.23% : 0.000001s : 8: predicate.graph_param_transform 0.72% : 0.000003s : 16: predicate.incorporate_call 0.57% : 0.000002s : 16: predicate.incorporate_call_switch 5.45% : 0.000020s : 95: predicate.inline 0.89% : 0.000003s : 16: predicate.inline_without_move 0.34% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.92% : 0.000003s : 16: predicate.less_batch_normalization 1.95% : 0.000007s : 37: predicate.list_to_tuple_eliminator_ 2.34% : 0.000008s : 58: predicate.load_eliminater 1.13% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.51% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.75% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.69% : 0.000002s : 16: predicate.merge_addn 0.73% : 0.000003s : 16: predicate.micro_step_allgather_replace 0.75% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.85% : 0.000003s : 21: predicate.minmaximum_grad 1.68% : 0.000006s : 8: predicate.mutable_eliminate 0.42% : 0.000002s : 8: predicate.opt_reshape 0.40% : 0.000001s : 8: predicate.parallel_virtual_node 1.64% : 0.000006s : 26: predicate.partial_defer_inline 1.19% : 0.000004s : 29: predicate.partial_eliminate 0.89% : 0.000003s : 21: predicate.print_const_string_wrapper 0.66% : 0.000002s : 16: predicate.reduce_all_const_elim 1.28% : 0.000005s : 21: predicate.reduce_eliminate 2.23% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.56% : 0.000002s : 16: predicate.remove_not_recompute_node 1.13% : 0.000004s : 37: predicate.replace_applicator 0.50% : 0.000002s : 16: predicate.replace_old_param 0.26% : 0.000001s : 8: predicate.reset_defer_inline 0.98% : 0.000004s : 21: predicate.reshape_eliminate 0.74% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.47% : 0.000002s : 8: predicate.row_tensor_eliminate 1.02% : 0.000004s : 16: predicate.same_eliminate 0.45% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.83% : 0.000003s : 16: predicate.shard_identity_eliminate 0.85% : 0.000003s : 16: predicate.special_op_eliminate 0.74% : 0.000003s : 16: predicate.specialize_transform 1.10% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.38% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.10% : 0.000004s : 26: predicate.switch_defer_inline 1.72% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.11% : 0.000015s : 86: predicate.switch_simplify 0.91% : 0.000003s : 21: predicate.tile_eliminate 0.88% : 0.000003s : 21: predicate.transpose_eliminate 1.90% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.76% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.60% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.38% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.75% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.40% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.86% : 0.000007s : 37: predicate.tuple_to_list_eliminator_ 2.22% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.99% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.43% : 0.000002s : 8: predicate.value_based_eliminate 0.78% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.74% : 0.000003s : 16: predicate.virtual_output_eliminate 0.35% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006587 32 65.61% : 0.004322s : 25: func_graph_cloner_run.FuncGraphClonerGraph 34.39% : 0.002265s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.870340 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.18% : 0.006898s : 1: add_attr 0.18% : 0.006878s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000112s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.00% : 0.000099s : 1: auto_monad 0.00% : 0.000035s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.02% : 0.000870s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000045s : 1: environ_conv 0.00% : 0.000032s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000010s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000670s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.001036s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000036s : 1: opt.transform.mutable_eliminate 0.07% : 0.002549s : 78: opt.transform.opt_a 0.00% : 0.000057s : 1: opt.transform.opt_after_cconv 0.00% : 0.000049s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000272s : 28: opt.transform.opt_b 0.00% : 0.000126s : 2: opt.transform.opt_trans_graph 0.00% : 0.000094s : 4: opt.transform.symbol_engine_opt 6.06% : 0.234361s : 1: opt_a 0.01% : 0.000218s : 1: opt_after_cconv 0.02% : 0.000740s : 1: opt_after_jit_grad 0.01% : 0.000447s : 1: opt_b 6.16% : 0.238468s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 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% : 0.000004s : 1: pipeline_split 0.00% : 0.000058s : 1: pre_auto_parallel 0.00% : 0.000044s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000072s : 1: remove_dup_value 5.89% : 0.227931s : 1: renormalize.infer 0.07% : 0.002527s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000302s : 1: rewriter_after_opt_a 0.00% : 0.000116s : 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% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000377s : 1: symbol_engine_optimizer 0.00% : 0.000162s : 1: tuple_transform 81.24% : 3.144126s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-float16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-float16--1-shape1],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:39:07.320.781 [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 = 3.42704, [21] [bootstrap]: 0.00080213 [type_inference]: 3.1379 [event_method]: 2.527e-05 [auto_monad]: 9.407e-05 [graph_reusing]: 7.06999e-06 [inline]: 3.11001e-06 [add_attr]: 0.27296, [1] [add_attr_with_inline]: 0.272944, [1] [Cycle 1]: 8.079e-05, [2] [tag_attr]: 2.88e-05 [meta_addattr_fg_expand]: 6.24001e-06 [parallel-infer-symbol]: 3.73999e-06 [pre_auto_parallel]: 7.083e-05 [insert-virtual-dataset]: 2.93e-06 [parallel-infer-symbol-second]: 1.30001e-06 [dataset_repeat_opt]: 2.33998e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.0142143, [53] [py_interpret_to_execute]: 4.407e-05 [rewriter_before_opt_a]: 0.00010883 [opt_a]: 0.0105307, [2] [Cycle 1]: 0.00928532, [45] [expand_dump_flag]: 3.16999e-06 [switch_simplify]: 4.128e-05 [loop_unroll]: 2.629e-05 [a_1]: 0.00108555 [with_stream_mark]: 2.688e-05 [recompute_prepare]: 1.669e-05 [updatestate_depend_eliminate]: 8.55999e-06 [updatestate_assign_eliminate]: 6.17999e-06 [updatestate_loads_eliminate]: 5.91e-06 [parameter_eliminate]: 2.09e-06 [a_2]: 0.00018953 [accelerated_algorithm]: 1.485e-05 [shard]: 2.41e-06 [meta_shard_fg_expand]: 3.68999e-06 [shard_inline]: 1.15e-05 [merge_send_recv]: 1.382e-05 [auto_parallel]: 9.44998e-06 [parallel]: 2.675e-05 [flash_sp]: 1.057e-05 [merge_comm]: 6.50002e-06 [allreduce_fusion]: 6.02999e-06 [matmul_add_comm_reduction]: 1.488e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 1.498e-05 [virtual_dataset]: 1.218e-05 [get_grad_eliminate_]: 1.237e-05 [virtual_output]: 1.242e-05 [merge_forward]: 6.74999e-06 [cell_reuse_recompute_pass]: 1.37999e-06 [offload_activation]: 1.822e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.358e-05 [merge_recompute_call_nodes]: 1.63002e-06 [before_grad]: 2.169e-05 [set_forward_comm_id_for_comm_node_pass]: 6.79999e-06 [meta_fg_expand]: 5.15999e-06 [flash_sp_send_recv_attached]: 2.99999e-06 [receive_attached]: 2.23002e-06 [after_resolve]: 1.46e-05 [a_after_grad]: 2.107e-05 [renormalize]: 0.00658795 [add_forward_monad_depend]: 1.065e-05 [auto_monad_grad]: 3.08998e-06 [auto_monad_eliminator]: 3.257e-05 [cse]: 0.00052156 [a_3]: 0.00010878 [Cycle 2]: 0.00122918, [45] [expand_dump_flag]: 3.08e-06 [switch_simplify]: 1.553e-05 [loop_unroll]: 1.192e-05 [a_1]: 0.00035233 [with_stream_mark]: 2.603e-05 [recompute_prepare]: 1.155e-05 [updatestate_depend_eliminate]: 8.18999e-06 [updatestate_assign_eliminate]: 5.65001e-06 [updatestate_loads_eliminate]: 5.40999e-06 [parameter_eliminate]: 2.39001e-06 [a_2]: 0.00015811 [accelerated_algorithm]: 1.159e-05 [shard]: 2.34999e-06 [meta_shard_fg_expand]: 3.93999e-06 [shard_inline]: 1.038e-05 [merge_send_recv]: 1.249e-05 [auto_parallel]: 1.312e-05 [parallel]: 1.012e-05 [flash_sp]: 4.57e-06 [merge_comm]: 6.48e-06 [allreduce_fusion]: 5.89e-06 [matmul_add_comm_reduction]: 1.411e-05 [allreduce_slice_to_reducescatter]: 7.40023e-07 [virtual_shard_identity]: 1.172e-05 [virtual_dataset]: 1.082e-05 [get_grad_eliminate_]: 1.172e-05 [virtual_output]: 1.025e-05 [merge_forward]: 6.64001e-06 [cell_reuse_recompute_pass]: 3.09999e-06 [offload_activation]: 1.622e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.05e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 1.901e-05 [set_forward_comm_id_for_comm_node_pass]: 6.36e-06 [meta_fg_expand]: 5.39e-06 [flash_sp_send_recv_attached]: 1.95001e-06 [receive_attached]: 2.44001e-06 [after_resolve]: 1.558e-05 [a_after_grad]: 1.661e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.82999e-06 [auto_monad_grad]: 1.86e-06 [auto_monad_eliminator]: 1.59e-05 [cse]: 7.148e-05 [a_3]: 7.081e-05 [py_interpret_to_execute_after_opt_a]: 2.42e-05 [slice_cell_reuse_recomputed_activation]: 2.41e-06 [rewriter_after_opt_a]: 0.00028303 [convert_after_rewriter]: 1.284e-05 [order_py_execute_after_rewriter]: 8.80001e-06 [mutable_eliminate]: 0.00085486 [opt_b]: 0.00044174, [1] [Cycle 1]: 0.000433, [7] [b_1]: 0.00029682 [b_2]: 1.339e-05 [updatestate_depend_eliminate]: 1.15e-05 [updatestate_assign_eliminate]: 6.04001e-06 [updatestate_loads_eliminate]: 5.46e-06 [renormalize]: 6.10016e-07 [cse]: 5.806e-05 [optimize_parallel_all_gather_comm]: 5.53e-05 [overlap_param_gather]: 2.71e-06 [cconv]: 3.719e-05 [loop_unroll]: 0.00054629 [opt_after_cconv]: 0.00016585, [1] [Cycle 1]: 0.00015773, [7] [c_1]: 5.634e-05 [parameter_eliminate]: 3.63e-06 [updatestate_depend_eliminate]: 1.094e-05 [updatestate_assign_eliminate]: 5.20999e-06 [updatestate_loads_eliminate]: 4.72e-06 [cse]: 4.157e-05 [renormalize]: 5.00004e-07 [remove_dup_value]: 6.687e-05 [tuple_transform]: 0.0001575, [1] [Cycle 1]: 0.00015198, [4] [d_1]: 0.00011443 [none_parameter_eliminate]: 2.04999e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 1.275e-05 [partial_unused_args_eliminate]: 2.04e-06 [add_recomputation]: 0.0001004 [cse_after_recomputation]: 4.586e-05, [1] [Cycle 1]: 3.976e-05, [1] [cse]: 3.376e-05 [environ_conv]: 1.7e-05 [swap_dp_allreduce_reducescatter]: 1.027e-05 [bias_add_comm_swap]: 3.06001e-06 [label_micro_interleaved_index]: 4.42e-06 [label_fine_grained_interleaved_index]: 2.76999e-06 [merge_cast_opt]: 1.55999e-06 [slice_recompute_activation]: 2.39001e-06 [micro_interleaved_order_control]: 2.39999e-06 [assign_add_opt]: 1.39e-06 [ForceFp32Comm]: 1.24998e-06 [remove_cast_before_assign_add]: 1.39998e-06 [full_micro_interleaved_order_control]: 2.65002e-06 [reorder_send_recv_between_fp_bp]: 2.64001e-06 [comm_op_add_attrs]: 1.35001e-06 [add_comm_op_reuse_tag]: 1.34003e-06 [interleave_split_concat_branches]: 1.18001e-06 [interleave_parallel_branches]: 1.25001e-06 [overlap_opt_shard_in_pipeline]: 1.76e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06e-06 [control_data_broadcast_order]: 2.023e-05 [grouped_pairwise_exchange_alltoall]: 1.74e-06 [offloading_packed_experts]: 7.01001e-06 [overlap_recompute_and_grad_model_parallel]: 7.66999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.43002e-06 [overlap_recompute_comm]: 2.69999e-06 [overlap_grad_ring_attention]: 5.76998e-06 [overlap_grad_flash_sp]: 3.167e-05 [begin_end_overlap_inline]: 5.40022e-07 [split_matmul_comm_elemetwise]: 2.31e-06 [split_layernorm_comm]: 1.89e-06 [handle_group_info]: 1.29e-06 [symbol_engine_optimizer]: 0.00030691, [1] [Cycle 1]: 0.00030184, [6] [build]: 0.00016973 [elim_shapecalc]: 1.721e-05 [elim_not_effective]: 2.595e-05 [opt_reshape]: 1.412e-05 [fold_const_symbol]: 3.662e-05 [renormalize]: 3.80009e-07 [detach_backward]: 3.09001e-06 [pipeline_parallel_scheduler]: 1.55999e-06 [auto_monad_reorder]: 2.778e-05 [get_jit_bprop_graph]: 2.89001e-06 [rewriter_after_jit_bprop_graph]: 5.92999e-06 [opt_after_jit_grad]: 0.00060262 [validate]: 7.646e-05 Sums bootstrap : 0.000802s : 0.03% type_inference : 3.137903s : 99.52% event_method : 0.000025s : 0.00% auto_monad : 0.000094s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000071s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000044s : 0.00% optimize.rewriter_before_opt_a : 0.000109s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000057s : 0.00% optimize.opt_a.loop_unroll : 0.000038s : 0.00% optimize.opt_a.a_1 : 0.001438s : 0.05% optimize.opt_a.with_stream_mark : 0.000053s : 0.00% optimize.opt_a.recompute_prepare : 0.000028s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000348s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.00% optimize.opt_a.merge_send_recv : 0.000026s : 0.00% optimize.opt_a.auto_parallel : 0.000023s : 0.00% optimize.opt_a.parallel : 0.000037s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000013s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000029s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000013s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000044s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000030s : 0.00% optimize.opt_a.a_after_grad : 0.000038s : 0.00% optimize.opt_a.renormalize : 0.006588s : 0.21% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000048s : 0.00% optimize.opt_a.cse : 0.000593s : 0.02% optimize.opt_a.a_3 : 0.000180s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000024s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000283s : 0.01% optimize.convert_after_rewriter : 0.000013s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000855s : 0.03% optimize.opt_b.b_1 : 0.000297s : 0.01% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000058s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000055s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000546s : 0.02% optimize.opt_after_cconv.c_1 : 0.000056s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000042s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000067s : 0.00% optimize.tuple_transform.d_1 : 0.000114s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000100s : 0.00% optimize.cse_after_recomputation.cse : 0.000034s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000004s : 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 : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000020s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000032s : 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 : 0.000170s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000037s : 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 : 0.000028s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000603s : 0.02% validate : 0.000076s : 0.00% Time group info: ------[substitution.] 0.000517 111 8.95% : 0.000046s : 6: substitution.arithmetic_simplify 1.05% : 0.000005s : 6: substitution.elim_not_effective 2.28% : 0.000012s : 6: substitution.float_tuple_getitem_switch 3.67% : 0.000019s : 6: substitution.fold_const_symbol 1.85% : 0.000010s : 8: substitution.graph_param_transform 45.07% : 0.000233s : 5: substitution.inline 1.54% : 0.000008s : 12: substitution.j_node_and_user_rematch 1.83% : 0.000009s : 4: substitution.minmaximum_grad 1.87% : 0.000010s : 12: substitution.remove_not_recompute_node 1.07% : 0.000006s : 2: substitution.replace_old_param 7.69% : 0.000040s : 8: substitution.tuple_list_convert_item_index_to_positive 3.28% : 0.000017s : 8: substitution.tuple_list_get_item_const_eliminator 5.09% : 0.000026s : 8: substitution.tuple_list_get_item_depend_reorder 10.69% : 0.000055s : 12: substitution.tuple_list_get_item_eliminator 4.06% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 3.137793 2 99.86% : 3.133357s : 1: type_inference.infer 0.14% : 0.004437s : 1: type_inference.specialize ------[replace.] 0.000049 5 100.00% : 0.000049s : 5: replace.inline ------[match.] 0.000229 5 100.00% : 0.000229s : 5: match.inline ------[predicate.] 0.000354 2113 1.13% : 0.000004s : 21: predicate.accumulaten_eliminater 1.04% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.62% : 0.000002s : 16: predicate.addn_check_dump 0.94% : 0.000003s : 21: predicate.addn_zero_filter 0.81% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.41% : 0.000009s : 37: predicate.arithmetic_simplify 0.97% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000002s : 16: predicate.check_bprop_eliminate 0.62% : 0.000002s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.65% : 0.000002s : 16: predicate.depend_value_elim 0.91% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.93% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.85% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.88% : 0.000003s : 16: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 8: predicate.elim_not_effective 0.47% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.15% : 0.000004s : 29: predicate.environ_get_depend_swap 1.80% : 0.000006s : 45: predicate.environ_get_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.02% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.60% : 0.000006s : 26: predicate.float_depend_g_call 0.74% : 0.000003s : 16: predicate.float_environ_get_switch 1.10% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 8: predicate.fold_const_symbol 0.80% : 0.000003s : 16: predicate.get_grad_eliminate 0.21% : 0.000001s : 8: predicate.graph_param_transform 0.67% : 0.000002s : 16: predicate.incorporate_call 0.57% : 0.000002s : 16: predicate.incorporate_call_switch 5.44% : 0.000019s : 95: predicate.inline 0.84% : 0.000003s : 16: predicate.inline_without_move 0.33% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.02% : 0.000004s : 16: predicate.less_batch_normalization 1.68% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.31% : 0.000008s : 58: predicate.load_eliminater 0.99% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.47% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.67% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.78% : 0.000003s : 16: predicate.merge_addn 0.64% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.64% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.89% : 0.000003s : 21: predicate.minmaximum_grad 1.28% : 0.000005s : 8: predicate.mutable_eliminate 0.52% : 0.000002s : 8: predicate.opt_reshape 0.51% : 0.000002s : 8: predicate.parallel_virtual_node 1.71% : 0.000006s : 26: predicate.partial_defer_inline 1.23% : 0.000004s : 29: predicate.partial_eliminate 0.91% : 0.000003s : 21: predicate.print_const_string_wrapper 0.71% : 0.000003s : 16: predicate.reduce_all_const_elim 1.21% : 0.000004s : 21: predicate.reduce_eliminate 2.28% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.37% : 0.000001s : 16: predicate.remove_not_recompute_node 1.32% : 0.000005s : 37: predicate.replace_applicator 0.38% : 0.000001s : 16: predicate.replace_old_param 0.34% : 0.000001s : 8: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.90% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.57% : 0.000002s : 8: predicate.row_tensor_eliminate 1.20% : 0.000004s : 16: predicate.same_eliminate 0.47% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.87% : 0.000003s : 16: predicate.shard_identity_eliminate 0.88% : 0.000003s : 16: predicate.special_op_eliminate 0.76% : 0.000003s : 16: predicate.specialize_transform 1.18% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.13% : 0.000004s : 26: predicate.switch_defer_inline 1.73% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.00% : 0.000014s : 86: predicate.switch_simplify 0.98% : 0.000003s : 21: predicate.tile_eliminate 0.96% : 0.000003s : 21: predicate.transpose_eliminate 1.87% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.97% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.57% : 0.000013s : 53: predicate.tuple_list_get_item_eliminator 1.74% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.82% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.61% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.18% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.91% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 8: predicate.value_based_eliminate 0.76% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.74% : 0.000003s : 16: predicate.virtual_output_eliminate 0.33% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.65% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.202603 32 99.01% : 0.200599s : 25: func_graph_cloner_run.FuncGraphClonerGraph 0.99% : 0.002004s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.723514 192 0.00% : 0.000004s : 1: ForceFp32Comm 7.33% : 0.272968s : 1: add_attr 7.33% : 0.272948s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000105s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000100s : 1: auto_monad 0.00% : 0.000032s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000865s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000024s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000010s : 1: detach_backward 0.00% : 0.000020s : 1: environ_conv 0.00% : 0.000032s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 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% : 0.000007s : 1: label_micro_interleaved_index 0.01% : 0.000556s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000869s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000032s : 1: opt.transform.mutable_eliminate 0.06% : 0.002275s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000044s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000275s : 28: opt.transform.opt_b 0.00% : 0.000125s : 2: opt.transform.opt_trans_graph 0.00% : 0.000089s : 4: opt.transform.symbol_engine_opt 0.28% : 0.010534s : 1: opt_a 0.00% : 0.000169s : 1: opt_after_cconv 0.02% : 0.000615s : 1: opt_after_jit_grad 0.01% : 0.000446s : 1: opt_b 0.38% : 0.014222s : 1: optimize 0.00% : 0.000061s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 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% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000077s : 1: pre_auto_parallel 0.00% : 0.000048s : 1: py_interpret_to_execute 0.00% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000071s : 1: remove_dup_value 0.12% : 0.004322s : 1: renormalize.infer 0.06% : 0.002251s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000290s : 1: rewriter_after_opt_a 0.00% : 0.000114s : 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% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000310s : 1: symbol_engine_optimizer 0.00% : 0.000160s : 1: tuple_transform 84.27% : 3.137943s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(158798:281473171148592,MainProcess):2026-01-29-17:39:17.797.728 [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 = 2.32218, [21] [bootstrap]: 0.00083641 [type_inference]: 2.08321 [event_method]: 2.675e-05 [auto_monad]: 9.523e-05 [graph_reusing]: 6.48e-06 [inline]: 3.11001e-06 [add_attr]: 0.00669484, [1] [add_attr_with_inline]: 0.00667675, [1] [Cycle 1]: 8.623e-05, [2] [tag_attr]: 3.103e-05 [meta_addattr_fg_expand]: 6.96999e-06 [parallel-infer-symbol]: 4.45999e-06 [pre_auto_parallel]: 4.891e-05 [insert-virtual-dataset]: 2.94001e-06 [parallel-infer-symbol-second]: 7.80012e-07 [dataset_repeat_opt]: 2.07999e-06 [pipeline_split]: 2.21998e-06 [optimize]: 0.230334, [53] [py_interpret_to_execute]: 4.263e-05 [rewriter_before_opt_a]: 0.00010178 [opt_a]: 0.226686, [2] [Cycle 1]: 0.0329204, [45] [expand_dump_flag]: 3.16999e-06 [switch_simplify]: 0.00011263 [loop_unroll]: 2.91e-05 [a_1]: 0.00124761 [with_stream_mark]: 2.787e-05 [recompute_prepare]: 1.796e-05 [updatestate_depend_eliminate]: 8.89e-06 [updatestate_assign_eliminate]: 7.15e-06 [updatestate_loads_eliminate]: 5.74999e-06 [parameter_eliminate]: 2.46e-06 [a_2]: 0.00018934 [accelerated_algorithm]: 5.577e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 4.99998e-06 [shard_inline]: 1.233e-05 [merge_send_recv]: 1.23e-05 [auto_parallel]: 1.187e-05 [parallel]: 3.538e-05 [flash_sp]: 1.266e-05 [merge_comm]: 7.36001e-06 [allreduce_fusion]: 6.96999e-06 [matmul_add_comm_reduction]: 1.712e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 1.591e-05 [virtual_dataset]: 1.216e-05 [get_grad_eliminate_]: 1.186e-05 [virtual_output]: 1.229e-05 [merge_forward]: 7.85e-06 [cell_reuse_recompute_pass]: 1.29e-06 [offload_activation]: 1.666e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.471e-05 [merge_recompute_call_nodes]: 1.87001e-06 [before_grad]: 2.06e-05 [set_forward_comm_id_for_comm_node_pass]: 7.11001e-06 [meta_fg_expand]: 5.19003e-06 [flash_sp_send_recv_attached]: 2.86999e-06 [receive_attached]: 2.42001e-06 [after_resolve]: 2.331e-05 [a_after_grad]: 2.366e-05 [renormalize]: 0.0294864 [add_forward_monad_depend]: 1.213e-05 [auto_monad_grad]: 2.88e-06 [auto_monad_eliminator]: 3.414e-05 [cse]: 0.00084058 [a_3]: 0.00010857 [Cycle 2]: 0.193747, [45] [expand_dump_flag]: 3.55e-06 [switch_simplify]: 1.496e-05 [loop_unroll]: 1.2e-05 [a_1]: 0.00043329 [with_stream_mark]: 3.151e-05 [recompute_prepare]: 1.36e-05 [updatestate_depend_eliminate]: 9.27999e-06 [updatestate_assign_eliminate]: 5.89e-06 [updatestate_loads_eliminate]: 5.73002e-06 [parameter_eliminate]: 2.22001e-06 [a_2]: 0.00016606 [accelerated_algorithm]: 1.26e-05 [shard]: 2.93998e-06 [meta_shard_fg_expand]: 3.81001e-06 [shard_inline]: 1.076e-05 [merge_send_recv]: 1.24e-05 [auto_parallel]: 1.426e-05 [parallel]: 1.05e-05 [flash_sp]: 4.23999e-06 [merge_comm]: 6.61999e-06 [allreduce_fusion]: 5.97001e-06 [matmul_add_comm_reduction]: 1.509e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 1.335e-05 [virtual_dataset]: 1.086e-05 [get_grad_eliminate_]: 1.2e-05 [virtual_output]: 1.094e-05 [merge_forward]: 7.38999e-06 [cell_reuse_recompute_pass]: 3.01001e-06 [offload_activation]: 1.614e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.144e-05 [merge_recompute_call_nodes]: 2.19999e-06 [before_grad]: 1.945e-05 [set_forward_comm_id_for_comm_node_pass]: 7.3e-06 [meta_fg_expand]: 6.08998e-06 [flash_sp_send_recv_attached]: 1.92999e-06 [receive_attached]: 3.01001e-06 [after_resolve]: 1.731e-05 [a_after_grad]: 1.754e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.08e-06 [auto_monad_grad]: 2.26e-06 [auto_monad_eliminator]: 2.212e-05 [cse]: 5.124e-05 [a_3]: 0.192414 [py_interpret_to_execute_after_opt_a]: 3.471e-05 [slice_cell_reuse_recomputed_activation]: 3.51999e-06 [rewriter_after_opt_a]: 0.00033019 [convert_after_rewriter]: 1.43e-05 [order_py_execute_after_rewriter]: 8.92999e-06 [mutable_eliminate]: 0.00080664 [opt_b]: 0.00045511, [1] [Cycle 1]: 0.00044567, [7] [b_1]: 0.00029946 [b_2]: 1.327e-05 [updatestate_depend_eliminate]: 1.18e-05 [updatestate_assign_eliminate]: 5.71e-06 [updatestate_loads_eliminate]: 5.69999e-06 [renormalize]: 1.10999e-06 [cse]: 6.957e-05 [optimize_parallel_all_gather_comm]: 2.93e-05 [overlap_param_gather]: 2.21e-06 [cconv]: 4.086e-05 [loop_unroll]: 0.00051306 [opt_after_cconv]: 0.00016126, [1] [Cycle 1]: 0.00015366, [7] [c_1]: 5.709e-05 [parameter_eliminate]: 4.42998e-06 [updatestate_depend_eliminate]: 9.77001e-06 [updatestate_assign_eliminate]: 5.22999e-06 [updatestate_loads_eliminate]: 4.83001e-06 [cse]: 3.665e-05 [renormalize]: 4.89992e-07 [remove_dup_value]: 6.469e-05 [tuple_transform]: 0.0001535, [1] [Cycle 1]: 0.00014873, [4] [d_1]: 0.00011253 [none_parameter_eliminate]: 1.92001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.241e-05 [partial_unused_args_eliminate]: 1.98002e-06 [add_recomputation]: 9.185e-05 [cse_after_recomputation]: 4.233e-05, [1] [Cycle 1]: 3.69e-05, [1] [cse]: 3.057e-05 [environ_conv]: 1.437e-05 [swap_dp_allreduce_reducescatter]: 9.61e-06 [bias_add_comm_swap]: 2.78e-06 [label_micro_interleaved_index]: 4.75999e-06 [label_fine_grained_interleaved_index]: 2.76e-06 [merge_cast_opt]: 1.59e-06 [slice_recompute_activation]: 2.37001e-06 [micro_interleaved_order_control]: 2.88e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.14e-06 [full_micro_interleaved_order_control]: 2.24001e-06 [reorder_send_recv_between_fp_bp]: 2.76e-06 [comm_op_add_attrs]: 1.05999e-06 [add_comm_op_reuse_tag]: 8.39995e-07 [interleave_split_concat_branches]: 1.24e-06 [interleave_parallel_branches]: 1.17999e-06 [overlap_opt_shard_in_pipeline]: 1.14e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06998e-06 [control_data_broadcast_order]: 2.175e-05 [grouped_pairwise_exchange_alltoall]: 1.60001e-06 [offloading_packed_experts]: 6.93e-06 [overlap_recompute_and_grad_model_parallel]: 7.68001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40999e-06 [overlap_recompute_comm]: 2.12001e-06 [overlap_grad_ring_attention]: 3.976e-05 [overlap_grad_flash_sp]: 3.08e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.24999e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 1.09998e-06 [symbol_engine_optimizer]: 0.00030798, [1] [Cycle 1]: 0.00030312, [6] [build]: 0.00017083 [elim_shapecalc]: 1.88e-05 [elim_not_effective]: 2.576e-05 [opt_reshape]: 1.314e-05 [fold_const_symbol]: 3.577e-05 [renormalize]: 2.40019e-07 [detach_backward]: 2.81e-06 [pipeline_parallel_scheduler]: 1.60001e-06 [auto_monad_reorder]: 3.025e-05 [get_jit_bprop_graph]: 3.71999e-06 [rewriter_after_jit_bprop_graph]: 5.47001e-06 [opt_after_jit_grad]: 0.0005668 [validate]: 7.225e-05 Sums bootstrap : 0.000836s : 0.04% type_inference : 2.083211s : 90.02% event_method : 0.000027s : 0.00% auto_monad : 0.000095s : 0.00% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000031s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.00% 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 : 0.000043s : 0.00% optimize.rewriter_before_opt_a : 0.000102s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000128s : 0.01% optimize.opt_a.loop_unroll : 0.000041s : 0.00% optimize.opt_a.a_1 : 0.001681s : 0.07% optimize.opt_a.with_stream_mark : 0.000059s : 0.00% optimize.opt_a.recompute_prepare : 0.000032s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000355s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000068s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000025s : 0.00% optimize.opt_a.auto_parallel : 0.000026s : 0.00% optimize.opt_a.parallel : 0.000046s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000032s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000029s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000033s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000046s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000040s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000041s : 0.00% optimize.opt_a.a_after_grad : 0.000041s : 0.00% optimize.opt_a.renormalize : 0.029486s : 1.27% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000056s : 0.00% optimize.opt_a.cse : 0.000892s : 0.04% optimize.opt_a.a_3 : 0.192523s : 8.32% optimize.py_interpret_to_execute_after_opt_a : 0.000035s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000330s : 0.01% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000807s : 0.03% optimize.opt_b.b_1 : 0.000299s : 0.01% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000070s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000513s : 0.02% optimize.opt_after_cconv.c_1 : 0.000057s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000037s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000065s : 0.00% optimize.tuple_transform.d_1 : 0.000113s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000092s : 0.00% optimize.cse_after_recomputation.cse : 0.000031s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 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 : 0.000022s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000040s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 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 : 0.000171s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000019s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000036s : 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 : 0.000030s : 0.00% get_jit_bprop_graph : 0.000004s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000567s : 0.02% validate : 0.000072s : 0.00% Time group info: ------[substitution.] 0.000590 111 8.30% : 0.000049s : 6: substitution.arithmetic_simplify 0.97% : 0.000006s : 6: substitution.elim_not_effective 2.18% : 0.000013s : 6: substitution.float_tuple_getitem_switch 3.33% : 0.000020s : 6: substitution.fold_const_symbol 1.54% : 0.000009s : 8: substitution.graph_param_transform 49.68% : 0.000293s : 5: substitution.inline 1.23% : 0.000007s : 12: substitution.j_node_and_user_rematch 1.91% : 0.000011s : 4: substitution.minmaximum_grad 1.80% : 0.000011s : 12: substitution.remove_not_recompute_node 1.16% : 0.000007s : 2: substitution.replace_old_param 6.38% : 0.000038s : 8: substitution.tuple_list_convert_item_index_to_positive 3.54% : 0.000021s : 8: substitution.tuple_list_get_item_const_eliminator 3.99% : 0.000024s : 8: substitution.tuple_list_get_item_depend_reorder 10.27% : 0.000061s : 12: substitution.tuple_list_get_item_eliminator 3.71% : 0.000022s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.083099 2 99.78% : 2.078515s : 1: type_inference.infer 0.22% : 0.004584s : 1: type_inference.specialize ------[replace.] 0.000058 5 100.00% : 0.000058s : 5: replace.inline ------[match.] 0.000289 5 100.00% : 0.000289s : 5: match.inline ------[predicate.] 0.000375 2113 0.90% : 0.000003s : 21: predicate.accumulaten_eliminater 0.90% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.61% : 0.000002s : 16: predicate.addn_check_dump 0.98% : 0.000004s : 21: predicate.addn_zero_filter 0.79% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.42% : 0.000009s : 37: predicate.arithmetic_simplify 0.89% : 0.000003s : 21: predicate.cast_eliminate 2.14% : 0.000008s : 16: predicate.check_bprop_eliminate 0.58% : 0.000002s : 16: predicate.compare_switch_simplify 0.18% : 0.000001s : 8: predicate.const_output_eliminate 0.62% : 0.000002s : 16: predicate.depend_value_elim 0.86% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.12% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.88% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.97% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 8: predicate.elim_not_effective 0.41% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.17% : 0.000004s : 29: predicate.environ_get_depend_swap 1.77% : 0.000007s : 45: predicate.environ_get_eliminate 1.14% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.97% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.00% : 0.000007s : 26: predicate.float_depend_g_call 0.63% : 0.000002s : 16: predicate.float_environ_get_switch 1.06% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 8: predicate.fold_const_symbol 0.72% : 0.000003s : 16: predicate.get_grad_eliminate 0.28% : 0.000001s : 8: predicate.graph_param_transform 0.62% : 0.000002s : 16: predicate.incorporate_call 0.53% : 0.000002s : 16: predicate.incorporate_call_switch 5.46% : 0.000020s : 95: predicate.inline 0.98% : 0.000004s : 16: predicate.inline_without_move 0.30% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.87% : 0.000003s : 16: predicate.less_batch_normalization 1.63% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.26% : 0.000008s : 58: predicate.load_eliminater 1.01% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.47% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.68% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.61% : 0.000002s : 16: predicate.merge_addn 0.65% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.75% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.83% : 0.000003s : 21: predicate.minmaximum_grad 1.05% : 0.000004s : 8: predicate.mutable_eliminate 0.41% : 0.000002s : 8: predicate.opt_reshape 0.50% : 0.000002s : 8: predicate.parallel_virtual_node 1.71% : 0.000006s : 26: predicate.partial_defer_inline 1.26% : 0.000005s : 29: predicate.partial_eliminate 0.85% : 0.000003s : 21: predicate.print_const_string_wrapper 0.67% : 0.000003s : 16: predicate.reduce_all_const_elim 1.24% : 0.000005s : 21: predicate.reduce_eliminate 2.22% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.34% : 0.000005s : 37: predicate.replace_applicator 0.53% : 0.000002s : 16: predicate.replace_old_param 0.33% : 0.000001s : 8: predicate.reset_defer_inline 0.86% : 0.000003s : 21: predicate.reshape_eliminate 0.73% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.41% : 0.000002s : 8: predicate.row_tensor_eliminate 1.06% : 0.000004s : 16: predicate.same_eliminate 0.39% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.95% : 0.000004s : 16: predicate.shard_identity_eliminate 0.75% : 0.000003s : 16: predicate.special_op_eliminate 0.78% : 0.000003s : 16: predicate.specialize_transform 1.34% : 0.000005s : 16: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000004s : 16: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.11% : 0.000004s : 26: predicate.switch_defer_inline 2.42% : 0.000009s : 42: predicate.switch_layer_defer_inline 4.04% : 0.000015s : 86: predicate.switch_simplify 1.01% : 0.000004s : 21: predicate.tile_eliminate 0.90% : 0.000003s : 21: predicate.transpose_eliminate 1.88% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.79% : 0.000007s : 37: predicate.tuple_list_get_item_depend_reorder 3.15% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.79% : 0.000007s : 37: predicate.tuple_list_get_set_item_eliminator 2.52% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.60% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.09% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.92% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 8: predicate.value_based_eliminate 0.67% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.82% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.029290 32 15.99% : 0.004684s : 25: func_graph_cloner_run.FuncGraphClonerGraph 84.01% : 0.024606s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.784103 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.24% : 0.006702s : 1: add_attr 0.24% : 0.006681s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000096s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000101s : 1: auto_monad 0.00% : 0.000035s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000903s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000010s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.00% : 0.000036s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000523s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000817s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000026s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000029s : 1: opt.transform.mutable_eliminate 7.00% : 0.194976s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000044s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000277s : 28: opt.transform.opt_b 0.00% : 0.000122s : 2: opt.transform.opt_trans_graph 0.00% : 0.000089s : 4: opt.transform.symbol_engine_opt 8.14% : 0.226690s : 1: opt_a 0.01% : 0.000165s : 1: opt_after_cconv 0.02% : 0.000580s : 1: opt_after_jit_grad 0.02% : 0.000459s : 1: opt_b 8.27% : 0.230341s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000034s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000045s : 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% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000054s : 1: pre_auto_parallel 0.00% : 0.000047s : 1: py_interpret_to_execute 0.00% : 0.000040s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000069s : 1: remove_dup_value 0.16% : 0.004591s : 1: renormalize.infer 0.89% : 0.024878s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000337s : 1: rewriter_after_opt_a 0.00% : 0.000107s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000311s : 1: symbol_engine_optimizer 0.01% : 0.000157s : 1: tuple_transform 74.83% : 2.083241s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu[True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu[True-bfloat16--1-shape1],max_mem:100.0M =============================== 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 ================= 12 passed, 25 warnings in 161.52s (0:02:41) ==================