==================================================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_003/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 4 items test_swiglu_v2.py [WARNING] ME(164889:281472841023280,MainProcess):2026-01-29-17:37:28.157.615 [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 = 1.00176, [21] [bootstrap]: 0.000675 [type_inference]: 0.979084 [event_method]: 2.504e-05 [auto_monad]: 0.00075129 [graph_reusing]: 7.23e-06 [inline]: 3.05002e-06 [add_attr]: 0.00819831, [1] [add_attr_with_inline]: 0.00818025, [1] [Cycle 1]: 0.00010599, [2] [tag_attr]: 2.552e-05 [meta_addattr_fg_expand]: 6.01e-06 [parallel-infer-symbol]: 4.42e-06 [pre_auto_parallel]: 5.091e-05 [insert-virtual-dataset]: 3.56999e-06 [parallel-infer-symbol-second]: 9.20001e-07 [dataset_repeat_opt]: 2.26e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.0119353, [53] [py_interpret_to_execute]: 3.355e-05 [rewriter_before_opt_a]: 0.00012719 [opt_a]: 0.00825489, [2] [Cycle 1]: 0.00693819, [45] [expand_dump_flag]: 3.55998e-06 [switch_simplify]: 4.381e-05 [loop_unroll]: 2.749e-05 [a_1]: 0.00079519 [with_stream_mark]: 2.419e-05 [recompute_prepare]: 1.511e-05 [updatestate_depend_eliminate]: 7.61999e-06 [updatestate_assign_eliminate]: 1.402e-05 [updatestate_loads_eliminate]: 6.21e-06 [parameter_eliminate]: 2.59001e-06 [a_2]: 0.00024773 [accelerated_algorithm]: 1.459e-05 [shard]: 2.78998e-06 [meta_shard_fg_expand]: 3.95e-06 [shard_inline]: 1.347e-05 [merge_send_recv]: 4.172e-05 [auto_parallel]: 1.56e-05 [parallel]: 4.438e-05 [flash_sp]: 2.173e-05 [merge_comm]: 8.07e-06 [allreduce_fusion]: 6.93e-06 [matmul_add_comm_reduction]: 1.627e-05 [allreduce_slice_to_reducescatter]: 9.40025e-07 [virtual_shard_identity]: 1.936e-05 [virtual_dataset]: 1.331e-05 [get_grad_eliminate_]: 1.372e-05 [virtual_output]: 1.203e-05 [merge_forward]: 7.97e-06 [cell_reuse_recompute_pass]: 2.69999e-06 [offload_activation]: 1.728e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.901e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 2.261e-05 [set_forward_comm_id_for_comm_node_pass]: 7.63999e-06 [meta_fg_expand]: 6.17001e-06 [flash_sp_send_recv_attached]: 2.98e-06 [receive_attached]: 1.197e-05 [after_resolve]: 1.988e-05 [a_after_grad]: 2.031e-05 [renormalize]: 0.00464945 [add_forward_monad_depend]: 1.822e-05 [auto_monad_grad]: 3.08e-06 [auto_monad_eliminator]: 3.474e-05 [cse]: 0.00013596 [a_3]: 0.00010073 [Cycle 2]: 0.00130066, [45] [expand_dump_flag]: 2.86e-06 [switch_simplify]: 1.483e-05 [loop_unroll]: 1.209e-05 [a_1]: 0.00033183 [with_stream_mark]: 2.796e-05 [recompute_prepare]: 1.29e-05 [updatestate_depend_eliminate]: 8.38001e-06 [updatestate_assign_eliminate]: 6.06998e-06 [updatestate_loads_eliminate]: 5.51998e-06 [parameter_eliminate]: 2.41998e-06 [a_2]: 0.00016221 [accelerated_algorithm]: 1.363e-05 [shard]: 3.48999e-06 [meta_shard_fg_expand]: 3.38999e-06 [shard_inline]: 1.179e-05 [merge_send_recv]: 1.378e-05 [auto_parallel]: 1.355e-05 [parallel]: 9.39998e-06 [flash_sp]: 4.75001e-06 [merge_comm]: 7.00998e-06 [allreduce_fusion]: 6.29001e-06 [matmul_add_comm_reduction]: 1.45e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 1.388e-05 [virtual_dataset]: 1.114e-05 [get_grad_eliminate_]: 1.098e-05 [virtual_output]: 1.052e-05 [merge_forward]: 7.51001e-06 [cell_reuse_recompute_pass]: 2.96001e-06 [offload_activation]: 1.673e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.188e-05 [merge_recompute_call_nodes]: 1.52999e-06 [before_grad]: 1.883e-05 [set_forward_comm_id_for_comm_node_pass]: 8.00999e-06 [meta_fg_expand]: 4.99e-06 [flash_sp_send_recv_attached]: 1.98997e-06 [receive_attached]: 2.56e-06 [after_resolve]: 1.606e-05 [a_after_grad]: 1.655e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.93998e-06 [auto_monad_grad]: 2.29001e-06 [auto_monad_eliminator]: 2.188e-05 [cse]: 0.00011237 [a_3]: 7.406e-05 [py_interpret_to_execute_after_opt_a]: 2.76e-05 [slice_cell_reuse_recomputed_activation]: 2.48e-06 [rewriter_after_opt_a]: 0.00034813 [convert_after_rewriter]: 2.029e-05 [order_py_execute_after_rewriter]: 8.36002e-06 [mutable_eliminate]: 0.00084237 [opt_b]: 0.00047109, [1] [Cycle 1]: 0.000461, [7] [b_1]: 0.00029711 [b_2]: 1.39e-05 [updatestate_depend_eliminate]: 1.511e-05 [updatestate_assign_eliminate]: 6.16998e-06 [updatestate_loads_eliminate]: 5.44e-06 [renormalize]: 8.2e-07 [cse]: 7.95e-05 [optimize_parallel_all_gather_comm]: 3.278e-05 [overlap_param_gather]: 2.91e-06 [cconv]: 3.732e-05 [loop_unroll]: 0.0005541 [opt_after_cconv]: 0.00017612, [1] [Cycle 1]: 0.00016755, [7] [c_1]: 5.584e-05 [parameter_eliminate]: 6.19001e-06 [updatestate_depend_eliminate]: 1.009e-05 [updatestate_assign_eliminate]: 5.37001e-06 [updatestate_loads_eliminate]: 4.90001e-06 [cse]: 5.022e-05 [renormalize]: 6.39993e-07 [remove_dup_value]: 6.365e-05 [tuple_transform]: 0.00016338, [1] [Cycle 1]: 0.00015795, [4] [d_1]: 0.00012144 [none_parameter_eliminate]: 2.05002e-06 [renormalize]: 4.2998e-07 [switch_simplify]: 1.296e-05 [partial_unused_args_eliminate]: 2.34999e-06 [add_recomputation]: 9.794e-05 [cse_after_recomputation]: 4.507e-05, [1] [Cycle 1]: 4.014e-05, [1] [cse]: 3.274e-05 [environ_conv]: 2.743e-05 [swap_dp_allreduce_reducescatter]: 1.042e-05 [bias_add_comm_swap]: 3.08e-06 [label_micro_interleaved_index]: 5.29998e-06 [label_fine_grained_interleaved_index]: 3.49001e-06 [merge_cast_opt]: 2.07999e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.39001e-06 [assign_add_opt]: 1.59998e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.10001e-06 [full_micro_interleaved_order_control]: 2.66e-06 [reorder_send_recv_between_fp_bp]: 2.94999e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.09998e-06 [interleave_split_concat_branches]: 1.19e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 2.533e-05 [overlap_opt_shard_grad_in_pipeline]: 1.86998e-06 [control_data_broadcast_order]: 2.467e-05 [grouped_pairwise_exchange_alltoall]: 2.19001e-06 [offloading_packed_experts]: 6.85998e-06 [overlap_recompute_and_grad_model_parallel]: 7.25e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.76e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47999e-06 [overlap_recompute_comm]: 2.26e-06 [overlap_grad_ring_attention]: 6.59999e-06 [overlap_grad_flash_sp]: 4.769e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.43e-06 [split_layernorm_comm]: 2.26998e-06 [handle_group_info]: 1.09998e-06 [symbol_engine_optimizer]: 0.00013612, [1] [Cycle 1]: 0.00012993, [6] [build]: 2.399e-05 [elim_shapecalc]: 1.908e-05 [elim_not_effective]: 2.364e-05 [opt_reshape]: 1.218e-05 [fold_const_symbol]: 1.833e-05 [renormalize]: 3.60014e-07 [detach_backward]: 2.93e-06 [pipeline_parallel_scheduler]: 1.45999e-06 [auto_monad_reorder]: 3.562e-05 [get_jit_bprop_graph]: 2.01e-06 [rewriter_after_jit_bprop_graph]: 6.76e-06 [opt_after_jit_grad]: 0.00065091 [validate]: 9.737e-05 Sums bootstrap : 0.000675s : 0.07% type_inference : 0.979084s : 98.67% event_method : 0.000025s : 0.00% auto_monad : 0.000751s : 0.08% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 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 : 0.000051s : 0.01% insert-virtual-dataset : 0.000004s : 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 : 0.000127s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.01% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001127s : 0.11% optimize.opt_a.with_stream_mark : 0.000052s : 0.01% optimize.opt_a.recompute_prepare : 0.000028s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000020s : 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 : 0.000410s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000028s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.00% optimize.opt_a.merge_send_recv : 0.000056s : 0.01% optimize.opt_a.auto_parallel : 0.000029s : 0.00% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000026s : 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 : 0.000031s : 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_ : 0.000025s : 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 : 0.000034s : 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 : 0.000016s : 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 : 0.000015s : 0.00% optimize.opt_a.after_resolve : 0.000036s : 0.00% optimize.opt_a.a_after_grad : 0.000037s : 0.00% optimize.opt_a.renormalize : 0.004650s : 0.47% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000057s : 0.01% optimize.opt_a.cse : 0.000248s : 0.03% optimize.opt_a.a_3 : 0.000175s : 0.02% 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 : 0.000348s : 0.04% optimize.convert_after_rewriter : 0.000020s : 0.00% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000842s : 0.08% optimize.opt_b.b_1 : 0.000297s : 0.03% 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 : 0.000079s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000554s : 0.06% optimize.opt_after_cconv.c_1 : 0.000056s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 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 : 0.000050s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000064s : 0.01% optimize.tuple_transform.d_1 : 0.000121s : 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 : 0.000010s : 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 : 0.000002s : 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 : 0.000025s : 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 : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000048s : 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 : 0.000024s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000036s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000651s : 0.07% validate : 0.000097s : 0.01% Time group info: ------[substitution.] 0.000441 111 10.76% : 0.000047s : 6: substitution.arithmetic_simplify 0.84% : 0.000004s : 6: substitution.elim_not_effective 3.07% : 0.000014s : 6: substitution.float_tuple_getitem_switch 0.58% : 0.000003s : 6: substitution.fold_const_symbol 2.27% : 0.000010s : 8: substitution.graph_param_transform 42.74% : 0.000188s : 5: substitution.inline 1.84% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.02% : 0.000009s : 4: substitution.minmaximum_grad 2.36% : 0.000010s : 12: substitution.remove_not_recompute_node 1.51% : 0.000007s : 2: substitution.replace_old_param 7.40% : 0.000033s : 8: substitution.tuple_list_convert_item_index_to_positive 3.18% : 0.000014s : 8: substitution.tuple_list_get_item_const_eliminator 5.10% : 0.000022s : 8: substitution.tuple_list_get_item_depend_reorder 11.63% : 0.000051s : 12: substitution.tuple_list_get_item_eliminator 4.71% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.978985 2 99.67% : 0.975792s : 1: type_inference.infer 0.33% : 0.003192s : 1: type_inference.specialize ------[replace.] 0.000045 5 100.00% : 0.000045s : 5: replace.inline ------[match.] 0.000185 5 100.00% : 0.000185s : 5: match.inline ------[predicate.] 0.000405 2113 0.74% : 0.000003s : 21: predicate.accumulaten_eliminater 0.80% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.52% : 0.000002s : 16: predicate.addn_check_dump 0.79% : 0.000003s : 21: predicate.addn_zero_filter 0.63% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.04% : 0.000008s : 37: predicate.arithmetic_simplify 0.79% : 0.000003s : 21: predicate.cast_eliminate 0.63% : 0.000003s : 16: predicate.check_bprop_eliminate 0.62% : 0.000002s : 16: predicate.compare_switch_simplify 0.18% : 0.000001s : 8: predicate.const_output_eliminate 0.61% : 0.000002s : 16: predicate.depend_value_elim 0.75% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.77% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.70% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.03% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.17% : 0.000001s : 8: predicate.elim_not_effective 0.55% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.06% : 0.000004s : 29: predicate.environ_add_const_eliminate 0.94% : 0.000004s : 29: predicate.environ_get_add_eliminate 0.98% : 0.000004s : 29: predicate.environ_get_depend_swap 17.74% : 0.000072s : 45: predicate.environ_get_eliminate 0.92% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.89% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.38% : 0.000006s : 26: predicate.float_depend_g_call 0.54% : 0.000002s : 16: predicate.float_environ_get_switch 0.95% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.79% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.54% : 0.000002s : 16: predicate.incorporate_call 0.50% : 0.000002s : 16: predicate.incorporate_call_switch 4.94% : 0.000020s : 95: predicate.inline 0.78% : 0.000003s : 16: predicate.inline_without_move 0.31% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.77% : 0.000003s : 16: predicate.less_batch_normalization 1.39% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 1.82% : 0.000007s : 58: predicate.load_eliminater 0.88% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.33% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.40% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.59% : 0.000002s : 16: predicate.merge_addn 0.53% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.55% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.72% : 0.000003s : 21: predicate.minmaximum_grad 1.25% : 0.000005s : 8: predicate.mutable_eliminate 0.41% : 0.000002s : 8: predicate.opt_reshape 0.38% : 0.000002s : 8: predicate.parallel_virtual_node 1.35% : 0.000005s : 26: predicate.partial_defer_inline 1.09% : 0.000004s : 29: predicate.partial_eliminate 0.69% : 0.000003s : 21: predicate.print_const_string_wrapper 0.61% : 0.000002s : 16: predicate.reduce_all_const_elim 0.94% : 0.000004s : 21: predicate.reduce_eliminate 1.91% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.48% : 0.000002s : 16: predicate.remove_not_recompute_node 1.02% : 0.000004s : 37: predicate.replace_applicator 0.48% : 0.000002s : 16: predicate.replace_old_param 0.29% : 0.000001s : 8: predicate.reset_defer_inline 0.70% : 0.000003s : 21: predicate.reshape_eliminate 0.61% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.36% : 0.000001s : 8: predicate.row_tensor_eliminate 0.99% : 0.000004s : 16: predicate.same_eliminate 0.36% : 0.000001s : 16: predicate.set_cell_output_no_recompute 0.80% : 0.000003s : 16: predicate.shard_identity_eliminate 0.67% : 0.000003s : 16: predicate.special_op_eliminate 0.63% : 0.000003s : 16: predicate.specialize_transform 0.86% : 0.000003s : 16: predicate.split_environ_get_set_with_tuple_value 0.70% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 8: predicate.switch_call_monad_eliminater 0.92% : 0.000004s : 26: predicate.switch_defer_inline 1.51% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.43% : 0.000014s : 86: predicate.switch_simplify 0.68% : 0.000003s : 21: predicate.tile_eliminate 0.67% : 0.000003s : 21: predicate.transpose_eliminate 1.48% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.50% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.28% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 3.05% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.44% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.06% : 0.000008s : 53: predicate.tuple_list_set_item_eliminator 1.37% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 1.81% : 0.000007s : 58: predicate.updatestate_pure_node_eliminater 2.48% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.35% : 0.000001s : 8: predicate.value_based_eliminate 0.73% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.66% : 0.000003s : 16: predicate.virtual_output_eliminate 0.27% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.39% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004610 32 72.64% : 0.003349s : 25: func_graph_cloner_run.FuncGraphClonerGraph 27.36% : 0.001262s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.028982 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.80% : 0.008205s : 1: add_attr 0.80% : 0.008186s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000103s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.000772s : 1: auto_monad 0.00% : 0.000041s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.07% : 0.000718s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000027s : 1: convert_after_rewriter 0.00% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000032s : 1: environ_conv 0.00% : 0.000032s : 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% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 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 0.05% : 0.000566s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.08% : 0.000858s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000024s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.20% : 0.002040s : 78: opt.transform.opt_a 0.01% : 0.000054s : 1: opt.transform.opt_after_cconv 0.00% : 0.000046s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000277s : 28: opt.transform.opt_b 0.01% : 0.000131s : 2: opt.transform.opt_trans_graph 0.01% : 0.000069s : 4: opt.transform.symbol_engine_opt 0.80% : 0.008259s : 1: opt_a 0.02% : 0.000180s : 1: opt_after_cconv 0.06% : 0.000667s : 1: opt_after_jit_grad 0.05% : 0.000475s : 1: opt_b 1.16% : 0.011941s : 1: optimize 0.00% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000052s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 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% : 0.000006s : 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% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000056s : 1: pre_auto_parallel 0.00% : 0.000038s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000069s : 1: remove_dup_value 0.31% : 0.003175s : 1: renormalize.infer 0.14% : 0.001457s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000358s : 1: rewriter_after_opt_a 0.01% : 0.000135s : 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% : 0.000139s : 1: symbol_engine_optimizer 0.02% : 0.000167s : 1: tuple_transform 95.15% : 0.979113s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_61015_20260129171854.log . [hook] pytest_runtest_teardown:test_swiglu_bfloat16[False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_bfloat16[False-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(164889:281472841023280,MainProcess):2026-01-29-17:38:01.660.511 [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 = 1.85296, [21] [bootstrap]: 0.00076504 [type_inference]: 1.70838 [event_method]: 2.664e-05 [auto_monad]: 9.828e-05 [graph_reusing]: 6.73e-06 [inline]: 3.43e-06 [add_attr]: 0.00696804, [1] [add_attr_with_inline]: 0.00695056, [1] [Cycle 1]: 7.965e-05, [2] [tag_attr]: 2.594e-05 [meta_addattr_fg_expand]: 5.79e-06 [parallel-infer-symbol]: 3.64002e-06 [pre_auto_parallel]: 4.324e-05 [insert-virtual-dataset]: 2.90998e-06 [parallel-infer-symbol-second]: 1.01002e-06 [dataset_repeat_opt]: 2.17999e-06 [pipeline_split]: 1.52999e-06 [optimize]: 0.135708, [53] [py_interpret_to_execute]: 3.872e-05 [rewriter_before_opt_a]: 0.0001258 [opt_a]: 0.132161, [2] [Cycle 1]: 0.130829, [45] [expand_dump_flag]: 3.76001e-06 [switch_simplify]: 4.518e-05 [loop_unroll]: 2.718e-05 [a_1]: 0.00100728 [with_stream_mark]: 2.683e-05 [recompute_prepare]: 2.73e-05 [updatestate_depend_eliminate]: 9.05999e-06 [updatestate_assign_eliminate]: 6.49001e-06 [updatestate_loads_eliminate]: 5.79999e-06 [parameter_eliminate]: 2.84999e-06 [a_2]: 0.00019165 [accelerated_algorithm]: 1.458e-05 [shard]: 2.54001e-06 [meta_shard_fg_expand]: 3.66999e-06 [shard_inline]: 1.226e-05 [merge_send_recv]: 1.262e-05 [auto_parallel]: 1.137e-05 [parallel]: 3.43e-05 [flash_sp]: 1.423e-05 [merge_comm]: 6.86999e-06 [allreduce_fusion]: 6.34001e-06 [matmul_add_comm_reduction]: 1.643e-05 [allreduce_slice_to_reducescatter]: 7.30011e-07 [virtual_shard_identity]: 1.605e-05 [virtual_dataset]: 1.345e-05 [get_grad_eliminate_]: 1.413e-05 [virtual_output]: 1.242e-05 [merge_forward]: 7.35e-06 [cell_reuse_recompute_pass]: 1.57999e-06 [offload_activation]: 1.686e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.562e-05 [merge_recompute_call_nodes]: 1.52999e-06 [before_grad]: 2.199e-05 [set_forward_comm_id_for_comm_node_pass]: 7.06001e-06 [meta_fg_expand]: 5.62001e-06 [flash_sp_send_recv_attached]: 2.64001e-06 [receive_attached]: 2.41e-06 [after_resolve]: 1.768e-05 [a_after_grad]: 2.164e-05 [renormalize]: 0.128566 [add_forward_monad_depend]: 1.882e-05 [auto_monad_grad]: 3.28998e-06 [auto_monad_eliminator]: 3.51e-05 [cse]: 0.00010329 [a_3]: 0.00010871 [Cycle 2]: 0.0013163, [45] [expand_dump_flag]: 2.29001e-06 [switch_simplify]: 1.627e-05 [loop_unroll]: 1.22e-05 [a_1]: 0.00034965 [with_stream_mark]: 9.299e-05 [recompute_prepare]: 1.764e-05 [updatestate_depend_eliminate]: 1.025e-05 [updatestate_assign_eliminate]: 5.87999e-06 [updatestate_loads_eliminate]: 6.10002e-06 [parameter_eliminate]: 3.36001e-06 [a_2]: 0.00017154 [accelerated_algorithm]: 1.23e-05 [shard]: 2.84001e-06 [meta_shard_fg_expand]: 3.88999e-06 [shard_inline]: 1.115e-05 [merge_send_recv]: 1.335e-05 [auto_parallel]: 1.5e-05 [parallel]: 1.042e-05 [flash_sp]: 4.72e-06 [merge_comm]: 7.08e-06 [allreduce_fusion]: 6.23e-06 [matmul_add_comm_reduction]: 1.413e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 1.355e-05 [virtual_dataset]: 1.139e-05 [get_grad_eliminate_]: 1.23e-05 [virtual_output]: 1.031e-05 [merge_forward]: 7.85e-06 [cell_reuse_recompute_pass]: 3.55e-06 [offload_activation]: 1.606e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.087e-05 [merge_recompute_call_nodes]: 1.49e-06 [before_grad]: 1.834e-05 [set_forward_comm_id_for_comm_node_pass]: 6.81001e-06 [meta_fg_expand]: 5.05001e-06 [flash_sp_send_recv_attached]: 1.94e-06 [receive_attached]: 2.22001e-06 [after_resolve]: 1.65e-05 [a_after_grad]: 1.692e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.13002e-06 [auto_monad_grad]: 2.05002e-06 [auto_monad_eliminator]: 1.697e-05 [cse]: 4.336e-05 [a_3]: 6.913e-05 [py_interpret_to_execute_after_opt_a]: 2.583e-05 [slice_cell_reuse_recomputed_activation]: 1.99e-06 [rewriter_after_opt_a]: 0.00028022 [convert_after_rewriter]: 1.353e-05 [order_py_execute_after_rewriter]: 9.32999e-06 [mutable_eliminate]: 0.00079895 [opt_b]: 0.00046425, [1] [Cycle 1]: 0.000456, [7] [b_1]: 0.00031431 [b_2]: 1.35e-05 [updatestate_depend_eliminate]: 1.264e-05 [updatestate_assign_eliminate]: 5.64998e-06 [updatestate_loads_eliminate]: 5.40999e-06 [renormalize]: 8.89995e-07 [cse]: 6.07e-05 [optimize_parallel_all_gather_comm]: 2.625e-05 [overlap_param_gather]: 2.22999e-06 [cconv]: 3.719e-05 [loop_unroll]: 0.00055651 [opt_after_cconv]: 0.00016585, [1] [Cycle 1]: 0.00015809, [7] [c_1]: 5.66e-05 [parameter_eliminate]: 4.70999e-06 [updatestate_depend_eliminate]: 1.064e-05 [updatestate_assign_eliminate]: 5.29e-06 [updatestate_loads_eliminate]: 4.60001e-06 [cse]: 4.05e-05 [renormalize]: 4.69998e-07 [remove_dup_value]: 6.494e-05 [tuple_transform]: 0.0001776, [1] [Cycle 1]: 0.0001724, [4] [d_1]: 0.00013464 [none_parameter_eliminate]: 2.98e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.285e-05 [partial_unused_args_eliminate]: 2.24999e-06 [add_recomputation]: 0.00010139 [cse_after_recomputation]: 4.451e-05, [1] [Cycle 1]: 3.864e-05, [1] [cse]: 3.187e-05 [environ_conv]: 3.87e-05 [swap_dp_allreduce_reducescatter]: 1.17e-05 [bias_add_comm_swap]: 3.8e-06 [label_micro_interleaved_index]: 4.89003e-06 [label_fine_grained_interleaved_index]: 2.96999e-06 [merge_cast_opt]: 1.23002e-06 [slice_recompute_activation]: 2.49001e-06 [micro_interleaved_order_control]: 3.01001e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 8.30012e-07 [full_micro_interleaved_order_control]: 2.61e-06 [reorder_send_recv_between_fp_bp]: 2.84999e-06 [comm_op_add_attrs]: 1.46002e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.20001e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 1.18001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.82999e-06 [control_data_broadcast_order]: 2.511e-05 [grouped_pairwise_exchange_alltoall]: 1.54998e-06 [offloading_packed_experts]: 6.76e-06 [overlap_recompute_and_grad_model_parallel]: 7.23e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.29998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.28002e-06 [overlap_recompute_comm]: 2.93e-06 [overlap_grad_ring_attention]: 7.41001e-06 [overlap_grad_flash_sp]: 3.336e-05 [begin_end_overlap_inline]: 5.60016e-07 [split_matmul_comm_elemetwise]: 2.63e-06 [split_layernorm_comm]: 2.13002e-06 [handle_group_info]: 1.66e-06 [symbol_engine_optimizer]: 0.00012985, [1] [Cycle 1]: 0.0001221, [6] [build]: 1.336e-05 [elim_shapecalc]: 2.017e-05 [elim_not_effective]: 2.454e-05 [opt_reshape]: 1.359e-05 [fold_const_symbol]: 1.842e-05 [renormalize]: 2.3999e-07 [detach_backward]: 2.58e-06 [pipeline_parallel_scheduler]: 1.48002e-06 [auto_monad_reorder]: 3.261e-05 [get_jit_bprop_graph]: 1.92001e-06 [rewriter_after_jit_bprop_graph]: 6.53998e-06 [opt_after_jit_grad]: 0.00061185 [validate]: 7.702e-05 Sums bootstrap : 0.000765s : 0.04% type_inference : 1.708385s : 92.61% event_method : 0.000027s : 0.00% auto_monad : 0.000098s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 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 : 0.000043s : 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 : 0.000039s : 0.00% optimize.rewriter_before_opt_a : 0.000126s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000061s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001357s : 0.07% optimize.opt_a.with_stream_mark : 0.000120s : 0.01% optimize.opt_a.recompute_prepare : 0.000045s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000019s : 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 : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000363s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000027s : 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 : 0.000023s : 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 : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 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 : 0.000030s : 0.00% optimize.opt_a.virtual_dataset : 0.000025s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 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 : 0.000005s : 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 : 0.000011s : 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 : 0.000034s : 0.00% optimize.opt_a.a_after_grad : 0.000039s : 0.00% optimize.opt_a.renormalize : 0.128566s : 6.97% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000052s : 0.00% optimize.opt_a.cse : 0.000147s : 0.01% optimize.opt_a.a_3 : 0.000178s : 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 : 0.000280s : 0.02% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000799s : 0.04% optimize.opt_b.b_1 : 0.000314s : 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 : 0.000061s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000557s : 0.03% 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 : 0.000011s : 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 : 0.000040s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000065s : 0.00% optimize.tuple_transform.d_1 : 0.000135s : 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 : 0.000002s : 0.00% optimize.add_recomputation : 0.000101s : 0.01% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000039s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 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 : 0.000003s : 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 : 0.000001s : 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 : 0.000007s : 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 : 0.000007s : 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 : 0.000013s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000018s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000033s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000612s : 0.03% validate : 0.000077s : 0.00% Time group info: ------[substitution.] 0.000484 111 9.52% : 0.000046s : 6: substitution.arithmetic_simplify 0.65% : 0.000003s : 6: substitution.elim_not_effective 2.59% : 0.000013s : 6: substitution.float_tuple_getitem_switch 0.53% : 0.000003s : 6: substitution.fold_const_symbol 2.03% : 0.000010s : 8: substitution.graph_param_transform 44.47% : 0.000215s : 5: substitution.inline 1.50% : 0.000007s : 12: substitution.j_node_and_user_rematch 2.08% : 0.000010s : 4: substitution.minmaximum_grad 1.93% : 0.000009s : 12: substitution.remove_not_recompute_node 1.28% : 0.000006s : 2: substitution.replace_old_param 8.14% : 0.000039s : 8: substitution.tuple_list_convert_item_index_to_positive 3.69% : 0.000018s : 8: substitution.tuple_list_get_item_const_eliminator 5.44% : 0.000026s : 8: substitution.tuple_list_get_item_depend_reorder 10.93% : 0.000053s : 12: substitution.tuple_list_get_item_eliminator 5.23% : 0.000025s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.708271 2 94.15% : 1.608332s : 1: type_inference.infer 5.85% : 0.099939s : 1: type_inference.specialize ------[replace.] 0.000050 5 100.00% : 0.000050s : 5: replace.inline ------[match.] 0.000212 5 100.00% : 0.000212s : 5: match.inline ------[predicate.] 0.000404 2113 0.84% : 0.000003s : 21: predicate.accumulaten_eliminater 1.10% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.56% : 0.000002s : 16: predicate.addn_check_dump 0.95% : 0.000004s : 21: predicate.addn_zero_filter 0.73% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.32% : 0.000009s : 37: predicate.arithmetic_simplify 0.82% : 0.000003s : 21: predicate.cast_eliminate 0.61% : 0.000002s : 16: predicate.check_bprop_eliminate 0.61% : 0.000002s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.63% : 0.000003s : 16: predicate.depend_value_elim 0.75% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.97% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.74% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.88% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 8: predicate.elim_not_effective 0.50% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 5.83% : 0.000024s : 29: predicate.environ_add_const_eliminate 1.01% : 0.000004s : 29: predicate.environ_get_add_eliminate 0.93% : 0.000004s : 29: predicate.environ_get_depend_swap 1.62% : 0.000007s : 45: predicate.environ_get_eliminate 1.00% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.94% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.38% : 0.000006s : 26: predicate.float_depend_g_call 0.56% : 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 0.66% : 0.000003s : 16: predicate.get_grad_eliminate 0.21% : 0.000001s : 8: predicate.graph_param_transform 0.56% : 0.000002s : 16: predicate.incorporate_call 0.49% : 0.000002s : 16: predicate.incorporate_call_switch 4.91% : 0.000020s : 95: predicate.inline 0.78% : 0.000003s : 16: predicate.inline_without_move 0.30% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.83% : 0.000003s : 16: predicate.less_batch_normalization 1.43% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 1.98% : 0.000008s : 58: predicate.load_eliminater 0.74% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.24% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.52% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.62% : 0.000002s : 16: predicate.merge_addn 0.53% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.64% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.84% : 0.000003s : 21: predicate.minmaximum_grad 1.08% : 0.000004s : 8: predicate.mutable_eliminate 0.37% : 0.000001s : 8: predicate.opt_reshape 0.39% : 0.000002s : 8: predicate.parallel_virtual_node 1.34% : 0.000005s : 26: predicate.partial_defer_inline 1.06% : 0.000004s : 29: predicate.partial_eliminate 0.79% : 0.000003s : 21: predicate.print_const_string_wrapper 0.64% : 0.000003s : 16: predicate.reduce_all_const_elim 1.05% : 0.000004s : 21: predicate.reduce_eliminate 1.96% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.40% : 0.000002s : 16: predicate.remove_not_recompute_node 1.04% : 0.000004s : 37: predicate.replace_applicator 0.40% : 0.000002s : 16: predicate.replace_old_param 0.36% : 0.000001s : 8: predicate.reset_defer_inline 0.85% : 0.000003s : 21: predicate.reshape_eliminate 0.60% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.42% : 0.000002s : 8: predicate.row_tensor_eliminate 0.95% : 0.000004s : 16: predicate.same_eliminate 2.36% : 0.000010s : 16: predicate.set_cell_output_no_recompute 0.77% : 0.000003s : 16: predicate.shard_identity_eliminate 7.07% : 0.000029s : 16: predicate.special_op_eliminate 0.68% : 0.000003s : 16: predicate.specialize_transform 0.99% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.77% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.35% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.03% : 0.000004s : 26: predicate.switch_defer_inline 1.46% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.44% : 0.000014s : 86: predicate.switch_simplify 0.76% : 0.000003s : 21: predicate.tile_eliminate 0.77% : 0.000003s : 21: predicate.transpose_eliminate 1.63% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.58% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.46% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.16% : 0.000013s : 53: predicate.tuple_list_get_item_eliminator 1.46% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.13% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.40% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 1.88% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.59% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.36% : 0.000001s : 8: predicate.value_based_eliminate 0.74% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.65% : 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.] 0.006966 32 63.45% : 0.004420s : 25: func_graph_cloner_run.FuncGraphClonerGraph 36.55% : 0.002546s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.126928 192 0.00% : 0.000005s : 1: ForceFp32Comm 0.33% : 0.006976s : 1: add_attr 0.33% : 0.006955s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000106s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000105s : 1: auto_monad 0.00% : 0.000038s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000812s : 1: bootstrap 0.00% : 0.000041s : 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% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000045s : 1: environ_conv 0.00% : 0.000036s : 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% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 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 0.03% : 0.000566s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000810s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 0.11% : 0.002236s : 78: opt.transform.opt_a 0.00% : 0.000055s : 1: opt.transform.opt_after_cconv 0.00% : 0.000079s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000295s : 28: opt.transform.opt_b 0.01% : 0.000144s : 2: opt.transform.opt_trans_graph 0.00% : 0.000071s : 4: opt.transform.symbol_engine_opt 6.21% : 0.132165s : 1: opt_a 0.01% : 0.000169s : 1: opt_after_cconv 0.03% : 0.000626s : 1: opt_after_jit_grad 0.02% : 0.000468s : 1: opt_b 6.38% : 0.135714s : 1: optimize 0.00% : 0.000030s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000037s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 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% : 0.000007s : 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% : 0.000004s : 1: pipeline_split 0.00% : 0.000048s : 1: pre_auto_parallel 0.00% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000029s : 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 5.91% : 0.125669s : 1: renormalize.infer 0.14% : 0.002881s : 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% : 0.000287s : 1: rewriter_after_opt_a 0.01% : 0.000132s : 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% : 0.000041s : 1: split_layernorm_comm 0.00% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000133s : 1: symbol_engine_optimizer 0.01% : 0.000181s : 1: tuple_transform 80.32% : 1.708425s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_bfloat16[False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_bfloat16[False-bfloat16--1-shape1],max_mem:100.0M [WARNING] ME(164889:281472841023280,MainProcess):2026-01-29-17:38:06.316.240 [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 = 1.14457, [21] [bootstrap]: 0.0009017 [type_inference]: 1.04422 [event_method]: 2.693e-05 [auto_monad]: 9.228e-05 [graph_reusing]: 6.66e-06 [inline]: 3.01001e-06 [add_attr]: 0.00650216, [1] [add_attr_with_inline]: 0.00648352, [1] [Cycle 1]: 8.079e-05, [2] [tag_attr]: 2.786e-05 [meta_addattr_fg_expand]: 5.90002e-06 [parallel-infer-symbol]: 4.42e-06 [pre_auto_parallel]: 4.564e-05 [insert-virtual-dataset]: 2.68003e-06 [parallel-infer-symbol-second]: 1.07998e-06 [dataset_repeat_opt]: 2.41e-06 [pipeline_split]: 1.91e-06 [optimize]: 0.0917739, [53] [py_interpret_to_execute]: 3.699e-05 [rewriter_before_opt_a]: 0.00014368 [opt_a]: 0.087713, [2] [Cycle 1]: 0.0855761, [45] [expand_dump_flag]: 4e-06 [switch_simplify]: 4.562e-05 [loop_unroll]: 2.699e-05 [a_1]: 0.0139506 [with_stream_mark]: 5.195e-05 [recompute_prepare]: 2.738e-05 [updatestate_depend_eliminate]: 1.022e-05 [updatestate_assign_eliminate]: 6.28e-06 [updatestate_loads_eliminate]: 5.76998e-06 [parameter_eliminate]: 3.20002e-06 [a_2]: 0.00023526 [accelerated_algorithm]: 1.462e-05 [shard]: 4.68001e-06 [meta_shard_fg_expand]: 8.66002e-06 [shard_inline]: 1.146e-05 [merge_send_recv]: 1.546e-05 [auto_parallel]: 1.711e-05 [parallel]: 4.595e-05 [flash_sp]: 1.462e-05 [merge_comm]: 8.08001e-06 [allreduce_fusion]: 7.06001e-06 [matmul_add_comm_reduction]: 1.963e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 1.731e-05 [virtual_dataset]: 2.323e-05 [get_grad_eliminate_]: 1.446e-05 [virtual_output]: 1.284e-05 [merge_forward]: 9.92001e-06 [cell_reuse_recompute_pass]: 3.23e-06 [offload_activation]: 0.0622864 [cell_reuse_handle_not_recompute_node_pass]: 0.00010068 [merge_recompute_call_nodes]: 5.01002e-06 [before_grad]: 4.569e-05 [set_forward_comm_id_for_comm_node_pass]: 1.901e-05 [meta_fg_expand]: 1.269e-05 [flash_sp_send_recv_attached]: 9.51e-06 [receive_attached]: 2.69001e-06 [after_resolve]: 2.424e-05 [a_after_grad]: 3.395e-05 [renormalize]: 0.00761128 [add_forward_monad_depend]: 2.267e-05 [auto_monad_grad]: 3.32997e-06 [auto_monad_eliminator]: 4.055e-05 [cse]: 0.00014686 [a_3]: 0.00011355 [Cycle 2]: 0.00211808, [45] [expand_dump_flag]: 3.59002e-06 [switch_simplify]: 1.802e-05 [loop_unroll]: 1.246e-05 [a_1]: 0.00039215 [with_stream_mark]: 3.516e-05 [recompute_prepare]: 1.589e-05 [updatestate_depend_eliminate]: 1.096e-05 [updatestate_assign_eliminate]: 5.99999e-06 [updatestate_loads_eliminate]: 5.81998e-06 [parameter_eliminate]: 2.77002e-06 [a_2]: 0.00017184 [accelerated_algorithm]: 1.482e-05 [shard]: 3.06001e-06 [meta_shard_fg_expand]: 4.60999e-06 [shard_inline]: 1.306e-05 [merge_send_recv]: 1.454e-05 [auto_parallel]: 1.592e-05 [parallel]: 1.13e-05 [flash_sp]: 4.77998e-06 [merge_comm]: 8.23999e-06 [allreduce_fusion]: 7.28999e-06 [matmul_add_comm_reduction]: 1.726e-05 [allreduce_slice_to_reducescatter]: 1.31002e-06 [virtual_shard_identity]: 1.68e-05 [virtual_dataset]: 1.256e-05 [get_grad_eliminate_]: 1.371e-05 [virtual_output]: 1.178e-05 [merge_forward]: 8.12e-06 [cell_reuse_recompute_pass]: 3.80998e-06 [offload_activation]: 1.931e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.794e-05 [merge_recompute_call_nodes]: 2.14e-06 [before_grad]: 2.266e-05 [set_forward_comm_id_for_comm_node_pass]: 8.14002e-06 [meta_fg_expand]: 5.34e-06 [flash_sp_send_recv_attached]: 1.91998e-06 [receive_attached]: 2.29001e-06 [after_resolve]: 1.718e-05 [a_after_grad]: 1.916e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 5.46e-06 [auto_monad_grad]: 2.83e-06 [auto_monad_eliminator]: 2.454e-05 [cse]: 0.00069446 [a_3]: 0.00010826 [py_interpret_to_execute_after_opt_a]: 3.182e-05 [slice_cell_reuse_recomputed_activation]: 2.93e-06 [rewriter_after_opt_a]: 0.00036637 [convert_after_rewriter]: 1.671e-05 [order_py_execute_after_rewriter]: 9.29998e-06 [mutable_eliminate]: 0.0008705 [opt_b]: 0.00051518, [1] [Cycle 1]: 0.00050463, [7] [b_1]: 0.00033846 [b_2]: 1.579e-05 [updatestate_depend_eliminate]: 1.47e-05 [updatestate_assign_eliminate]: 6.03002e-06 [updatestate_loads_eliminate]: 5.94999e-06 [renormalize]: 9.70002e-07 [cse]: 7.322e-05 [optimize_parallel_all_gather_comm]: 3.384e-05 [overlap_param_gather]: 2.18002e-06 [cconv]: 4.359e-05 [loop_unroll]: 0.00060619 [opt_after_cconv]: 0.00018195, [1] [Cycle 1]: 0.00017285, [7] [c_1]: 5.666e-05 [parameter_eliminate]: 5.29998e-06 [updatestate_depend_eliminate]: 1.259e-05 [updatestate_assign_eliminate]: 5.53002e-06 [updatestate_loads_eliminate]: 5.12999e-06 [cse]: 4.863e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 7.373e-05 [tuple_transform]: 0.00017844, [1] [Cycle 1]: 0.00017268, [4] [d_1]: 0.00013433 [none_parameter_eliminate]: 2.69001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.246e-05 [partial_unused_args_eliminate]: 2.72001e-06 [add_recomputation]: 9.319e-05 [cse_after_recomputation]: 4.546e-05, [1] [Cycle 1]: 3.933e-05, [1] [cse]: 3.306e-05 [environ_conv]: 1.321e-05 [swap_dp_allreduce_reducescatter]: 1.044e-05 [bias_add_comm_swap]: 2.79001e-06 [label_micro_interleaved_index]: 5.29998e-06 [label_fine_grained_interleaved_index]: 2.72001e-06 [merge_cast_opt]: 1.36998e-06 [slice_recompute_activation]: 2.12999e-06 [micro_interleaved_order_control]: 2.44001e-06 [assign_add_opt]: 1.24e-06 [ForceFp32Comm]: 8.50006e-07 [remove_cast_before_assign_add]: 1.55999e-06 [full_micro_interleaved_order_control]: 2.49999e-06 [reorder_send_recv_between_fp_bp]: 2.83998e-06 [comm_op_add_attrs]: 1.17999e-06 [add_comm_op_reuse_tag]: 1.14998e-06 [interleave_split_concat_branches]: 1.30001e-06 [interleave_parallel_branches]: 1.20001e-06 [overlap_opt_shard_in_pipeline]: 1.35999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.11998e-06 [control_data_broadcast_order]: 2.43e-05 [grouped_pairwise_exchange_alltoall]: 1.77999e-06 [offloading_packed_experts]: 7.93999e-06 [overlap_recompute_and_grad_model_parallel]: 8.59e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.29e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.63e-06 [overlap_grad_ring_attention]: 6.16998e-06 [overlap_grad_flash_sp]: 3.235e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.41e-06 [split_layernorm_comm]: 1.97001e-06 [handle_group_info]: 1.04e-06 [symbol_engine_optimizer]: 0.00037094, [1] [Cycle 1]: 0.0003641, [6] [build]: 0.00020109 [elim_shapecalc]: 2.356e-05 [elim_not_effective]: 4.539e-05 [opt_reshape]: 1.409e-05 [fold_const_symbol]: 3.627e-05 [renormalize]: 3.50003e-07 [detach_backward]: 3.26001e-06 [pipeline_parallel_scheduler]: 1.50999e-06 [auto_monad_reorder]: 3.294e-05 [get_jit_bprop_graph]: 3.21999e-06 [rewriter_after_jit_bprop_graph]: 6.38998e-06 [opt_after_jit_grad]: 0.00064576 [validate]: 7.973e-05 Sums bootstrap : 0.000902s : 0.08% type_inference : 1.044219s : 91.87% event_method : 0.000027s : 0.00% auto_monad : 0.000092s : 0.01% 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 : 0.000046s : 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 : 0.000037s : 0.00% optimize.rewriter_before_opt_a : 0.000144s : 0.01% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000064s : 0.01% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.014343s : 1.26% optimize.opt_a.with_stream_mark : 0.000087s : 0.01% optimize.opt_a.recompute_prepare : 0.000043s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 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 : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000407s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.00% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000013s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000033s : 0.00% optimize.opt_a.parallel : 0.000057s : 0.01% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000016s : 0.00% optimize.opt_a.allreduce_fusion : 0.000014s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000034s : 0.00% optimize.opt_a.virtual_dataset : 0.000036s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.00% optimize.opt_a.virtual_output : 0.000025s : 0.00% optimize.opt_a.merge_forward : 0.000018s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.062306s : 5.48% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000129s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000007s : 0.00% optimize.opt_a.before_grad : 0.000068s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000018s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 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 : 0.000053s : 0.00% optimize.opt_a.renormalize : 0.007611s : 0.67% optimize.opt_a.add_forward_monad_depend : 0.000028s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000065s : 0.01% optimize.opt_a.cse : 0.000841s : 0.07% optimize.opt_a.a_3 : 0.000222s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000032s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000366s : 0.03% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000870s : 0.08% optimize.opt_b.b_1 : 0.000338s : 0.03% optimize.opt_b.b_2 : 0.000016s : 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 : 0.000073s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000034s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000606s : 0.05% 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 : 0.000013s : 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 : 0.000049s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000074s : 0.01% optimize.tuple_transform.d_1 : 0.000134s : 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 : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000093s : 0.01% optimize.cse_after_recomputation.cse : 0.000033s : 0.00% optimize.environ_conv : 0.000013s : 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 : 0.000001s : 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 : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 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 : 0.000009s : 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 : 0.000003s : 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 : 0.000201s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000045s : 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 : 0.000000s : 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 : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000646s : 0.06% validate : 0.000080s : 0.01% Time group info: ------[substitution.] 0.000566 111 11.05% : 0.000063s : 6: substitution.arithmetic_simplify 3.75% : 0.000021s : 6: substitution.elim_not_effective 2.59% : 0.000015s : 6: substitution.float_tuple_getitem_switch 3.48% : 0.000020s : 6: substitution.fold_const_symbol 2.02% : 0.000011s : 8: substitution.graph_param_transform 38.09% : 0.000215s : 5: substitution.inline 1.81% : 0.000010s : 12: substitution.j_node_and_user_rematch 1.99% : 0.000011s : 4: substitution.minmaximum_grad 3.32% : 0.000019s : 12: substitution.remove_not_recompute_node 1.80% : 0.000010s : 2: substitution.replace_old_param 6.72% : 0.000038s : 8: substitution.tuple_list_convert_item_index_to_positive 2.92% : 0.000017s : 8: substitution.tuple_list_get_item_const_eliminator 4.42% : 0.000025s : 8: substitution.tuple_list_get_item_depend_reorder 12.00% : 0.000068s : 12: substitution.tuple_list_get_item_eliminator 4.02% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.044115 2 99.55% : 1.039462s : 1: type_inference.infer 0.45% : 0.004653s : 1: type_inference.specialize ------[replace.] 0.000054 5 100.00% : 0.000054s : 5: replace.inline ------[match.] 0.000212 5 100.00% : 0.000212s : 5: match.inline ------[predicate.] 0.000410 2113 0.90% : 0.000004s : 21: predicate.accumulaten_eliminater 1.02% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.57% : 0.000002s : 16: predicate.addn_check_dump 1.03% : 0.000004s : 21: predicate.addn_zero_filter 0.75% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.36% : 0.000010s : 37: predicate.arithmetic_simplify 0.84% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000003s : 16: predicate.check_bprop_eliminate 0.58% : 0.000002s : 16: predicate.compare_switch_simplify 0.21% : 0.000001s : 8: predicate.const_output_eliminate 0.63% : 0.000003s : 16: predicate.depend_value_elim 0.95% : 0.000004s : 21: predicate.dict_get_item_const_eliminator 0.88% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.82% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.04% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 8: predicate.elim_not_effective 0.61% : 0.000003s : 8: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.06% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.05% : 0.000004s : 29: predicate.environ_get_depend_swap 1.72% : 0.000007s : 45: predicate.environ_get_eliminate 1.05% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.05% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.07% : 0.000008s : 26: predicate.float_depend_g_call 0.72% : 0.000003s : 16: predicate.float_environ_get_switch 1.08% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.81% : 0.000003s : 16: predicate.get_grad_eliminate 0.32% : 0.000001s : 8: predicate.graph_param_transform 0.56% : 0.000002s : 16: predicate.incorporate_call 0.49% : 0.000002s : 16: predicate.incorporate_call_switch 5.82% : 0.000024s : 95: predicate.inline 1.29% : 0.000005s : 16: predicate.inline_without_move 0.37% : 0.000002s : 16: predicate.j_node_and_user_rematch 0.86% : 0.000004s : 16: predicate.less_batch_normalization 1.71% : 0.000007s : 37: predicate.list_to_tuple_eliminator_ 1.98% : 0.000008s : 58: predicate.load_eliminater 1.26% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.25% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.61% : 0.000007s : 37: predicate.make_slice_get_slice_eliminator 0.72% : 0.000003s : 16: predicate.merge_addn 0.65% : 0.000003s : 16: predicate.micro_step_allgather_replace 0.63% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.74% : 0.000003s : 21: predicate.minmaximum_grad 1.34% : 0.000005s : 8: predicate.mutable_eliminate 0.39% : 0.000002s : 8: predicate.opt_reshape 0.48% : 0.000002s : 8: predicate.parallel_virtual_node 1.71% : 0.000007s : 26: predicate.partial_defer_inline 1.09% : 0.000004s : 29: predicate.partial_eliminate 0.85% : 0.000003s : 21: predicate.print_const_string_wrapper 0.67% : 0.000003s : 16: predicate.reduce_all_const_elim 1.20% : 0.000005s : 21: predicate.reduce_eliminate 3.68% : 0.000015s : 58: predicate.redundant_stop_gradient_eliminater 0.73% : 0.000003s : 16: predicate.remove_not_recompute_node 1.29% : 0.000005s : 37: predicate.replace_applicator 0.50% : 0.000002s : 16: predicate.replace_old_param 0.27% : 0.000001s : 8: predicate.reset_defer_inline 0.95% : 0.000004s : 21: predicate.reshape_eliminate 0.75% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.50% : 0.000002s : 8: predicate.row_tensor_eliminate 1.43% : 0.000006s : 16: predicate.same_eliminate 0.45% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.89% : 0.000004s : 16: predicate.shard_identity_eliminate 0.79% : 0.000003s : 16: predicate.special_op_eliminate 0.68% : 0.000003s : 16: predicate.specialize_transform 1.21% : 0.000005s : 16: predicate.split_environ_get_set_with_tuple_value 1.21% : 0.000005s : 16: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.02% : 0.000004s : 26: predicate.switch_defer_inline 1.57% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.65% : 0.000015s : 86: predicate.switch_simplify 0.91% : 0.000004s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.83% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 2.08% : 0.000009s : 37: predicate.tuple_list_get_item_const_eliminator 1.89% : 0.000008s : 37: predicate.tuple_list_get_item_depend_reorder 3.53% : 0.000014s : 53: predicate.tuple_list_get_item_eliminator 1.87% : 0.000008s : 37: predicate.tuple_list_get_set_item_eliminator 2.36% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.75% : 0.000007s : 37: predicate.tuple_to_list_eliminator_ 1.86% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.54% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 8: predicate.value_based_eliminate 0.74% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.68% : 0.000003s : 16: predicate.virtual_output_eliminate 0.30% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.42% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006651 32 66.40% : 0.004417s : 25: func_graph_cloner_run.FuncGraphClonerGraph 33.60% : 0.002234s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.266391 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.51% : 0.006509s : 1: add_attr 0.51% : 0.006488s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000098s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000098s : 1: auto_monad 0.00% : 0.000037s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.08% : 0.000950s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000017s : 1: environ_conv 0.00% : 0.000035s : 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 0.05% : 0.000619s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.07% : 0.000884s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000035s : 1: opt.transform.mutable_eliminate 1.22% : 0.015421s : 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 0.02% : 0.000314s : 28: opt.transform.opt_b 0.01% : 0.000144s : 2: opt.transform.opt_trans_graph 0.01% : 0.000113s : 4: opt.transform.symbol_engine_opt 6.93% : 0.087718s : 1: opt_a 0.01% : 0.000186s : 1: opt_after_cconv 0.05% : 0.000661s : 1: opt_after_jit_grad 0.04% : 0.000519s : 1: opt_b 7.25% : 0.091781s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 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% : 0.000010s : 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% : 0.000012s : 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% : 0.000050s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000036s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000080s : 1: remove_dup_value 0.40% : 0.005086s : 1: renormalize.infer 0.20% : 0.002502s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000377s : 1: rewriter_after_opt_a 0.01% : 0.000151s : 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 0.03% : 0.000374s : 1: symbol_engine_optimizer 0.01% : 0.000182s : 1: tuple_transform 82.46% : 1.044256s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_bfloat16[True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_bfloat16[True-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(164889:281472841023280,MainProcess):2026-01-29-17:38:10.380.936 [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 = 1.51449, [21] [bootstrap]: 0.00085899 [type_inference]: 1.38959 [event_method]: 2.867e-05 [auto_monad]: 0.00010337 [graph_reusing]: 7.39002e-06 [inline]: 3.23998e-06 [add_attr]: 0.00684963, [1] [add_attr_with_inline]: 0.00683026, [1] [Cycle 1]: 9.171e-05, [2] [tag_attr]: 3.331e-05 [meta_addattr_fg_expand]: 6.68e-06 [parallel-infer-symbol]: 3.97002e-06 [pre_auto_parallel]: 4.964e-05 [insert-virtual-dataset]: 2.79001e-06 [parallel-infer-symbol-second]: 1.17e-06 [dataset_repeat_opt]: 2.51998e-06 [pipeline_split]: 1.77999e-06 [optimize]: 0.115673, [53] [py_interpret_to_execute]: 9.816e-05 [rewriter_before_opt_a]: 0.00011172 [opt_a]: 0.0122146, [2] [Cycle 1]: 0.0104989, [45] [expand_dump_flag]: 4.49998e-06 [switch_simplify]: 4.521e-05 [loop_unroll]: 3.973e-05 [a_1]: 0.00109312 [with_stream_mark]: 3.149e-05 [recompute_prepare]: 1.986e-05 [updatestate_depend_eliminate]: 1.069e-05 [updatestate_assign_eliminate]: 6.43998e-06 [updatestate_loads_eliminate]: 6.36998e-06 [parameter_eliminate]: 2.81e-06 [a_2]: 0.0002026 [accelerated_algorithm]: 1.504e-05 [shard]: 2.84001e-06 [meta_shard_fg_expand]: 5.04e-06 [shard_inline]: 1.184e-05 [merge_send_recv]: 1.508e-05 [auto_parallel]: 1.172e-05 [parallel]: 3.627e-05 [flash_sp]: 1.335e-05 [merge_comm]: 7.52998e-06 [allreduce_fusion]: 6.63998e-06 [matmul_add_comm_reduction]: 1.815e-05 [allreduce_slice_to_reducescatter]: 7.40023e-07 [virtual_shard_identity]: 1.87e-05 [virtual_dataset]: 1.393e-05 [get_grad_eliminate_]: 1.253e-05 [virtual_output]: 1.229e-05 [merge_forward]: 8.31002e-06 [cell_reuse_recompute_pass]: 1.41002e-06 [offload_activation]: 1.977e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.795e-05 [merge_recompute_call_nodes]: 1.49e-06 [before_grad]: 6.162e-05 [set_forward_comm_id_for_comm_node_pass]: 9.19998e-06 [meta_fg_expand]: 6.63e-06 [flash_sp_send_recv_attached]: 3.99002e-06 [receive_attached]: 2.43e-06 [after_resolve]: 1.927e-05 [a_after_grad]: 2.937e-05 [renormalize]: 0.0074955 [add_forward_monad_depend]: 2.075e-05 [auto_monad_grad]: 2.79999e-06 [auto_monad_eliminator]: 3.542e-05 [cse]: 0.00060922 [a_3]: 0.00010964 [Cycle 2]: 0.0016988, [45] [expand_dump_flag]: 4.55999e-06 [switch_simplify]: 1.629e-05 [loop_unroll]: 4.418e-05 [a_1]: 0.00035268 [with_stream_mark]: 3.289e-05 [recompute_prepare]: 1.265e-05 [updatestate_depend_eliminate]: 9.39e-06 [updatestate_assign_eliminate]: 5.79999e-06 [updatestate_loads_eliminate]: 5.51e-06 [parameter_eliminate]: 2.29999e-06 [a_2]: 0.00016455 [accelerated_algorithm]: 1.404e-05 [shard]: 3.36999e-06 [meta_shard_fg_expand]: 5.02e-06 [shard_inline]: 1.074e-05 [merge_send_recv]: 1.43e-05 [auto_parallel]: 1.551e-05 [parallel]: 1.121e-05 [flash_sp]: 4.45e-06 [merge_comm]: 7.36999e-06 [allreduce_fusion]: 6.01e-06 [matmul_add_comm_reduction]: 1.601e-05 [allreduce_slice_to_reducescatter]: 7.10017e-07 [virtual_shard_identity]: 1.301e-05 [virtual_dataset]: 1.091e-05 [get_grad_eliminate_]: 1.168e-05 [virtual_output]: 1.022e-05 [merge_forward]: 7.4e-06 [cell_reuse_recompute_pass]: 3.09001e-06 [offload_activation]: 1.683e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.201e-05 [merge_recompute_call_nodes]: 1.72001e-06 [before_grad]: 1.915e-05 [set_forward_comm_id_for_comm_node_pass]: 7.11001e-06 [meta_fg_expand]: 5.89999e-06 [flash_sp_send_recv_attached]: 1.76e-06 [receive_attached]: 2.94999e-06 [after_resolve]: 1.693e-05 [a_after_grad]: 4.775e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.36999e-06 [auto_monad_grad]: 2.68e-06 [auto_monad_eliminator]: 2.356e-05 [cse]: 0.00035686 [a_3]: 8.865e-05 [py_interpret_to_execute_after_opt_a]: 2.985e-05 [slice_cell_reuse_recomputed_activation]: 2.59001e-06 [rewriter_after_opt_a]: 0.0002985 [convert_after_rewriter]: 1.459e-05 [order_py_execute_after_rewriter]: 9.15999e-06 [mutable_eliminate]: 0.00128417 [opt_b]: 0.00048498, [1] [Cycle 1]: 0.0004735, [7] [b_1]: 0.00031508 [b_2]: 1.4e-05 [updatestate_depend_eliminate]: 1.557e-05 [updatestate_assign_eliminate]: 5.76e-06 [updatestate_loads_eliminate]: 6.21e-06 [renormalize]: 1.35999e-06 [cse]: 7.263e-05 [optimize_parallel_all_gather_comm]: 3.128e-05 [overlap_param_gather]: 2.19001e-06 [cconv]: 4.383e-05 [loop_unroll]: 0.00065652 [opt_after_cconv]: 0.00018348, [1] [Cycle 1]: 0.00017371, [7] [c_1]: 5.987e-05 [parameter_eliminate]: 6.31e-06 [updatestate_depend_eliminate]: 1.27e-05 [updatestate_assign_eliminate]: 5.44e-06 [updatestate_loads_eliminate]: 4.82e-06 [cse]: 4.731e-05 [renormalize]: 8.00006e-07 [remove_dup_value]: 7.618e-05 [tuple_transform]: 0.00016923, [1] [Cycle 1]: 0.00016357, [4] [d_1]: 0.00012534 [none_parameter_eliminate]: 3.13998e-06 [renormalize]: 1.70025e-07 [switch_simplify]: 1.287e-05 [partial_unused_args_eliminate]: 2.51998e-06 [add_recomputation]: 9.714e-05 [cse_after_recomputation]: 4.43e-05, [1] [Cycle 1]: 3.759e-05, [1] [cse]: 3.164e-05 [environ_conv]: 1.531e-05 [swap_dp_allreduce_reducescatter]: 1.012e-05 [bias_add_comm_swap]: 3.6e-06 [label_micro_interleaved_index]: 5.82001e-06 [label_fine_grained_interleaved_index]: 3.3e-06 [merge_cast_opt]: 1.96e-06 [slice_recompute_activation]: 2.36998e-06 [micro_interleaved_order_control]: 3.33998e-06 [assign_add_opt]: 2.21e-06 [ForceFp32Comm]: 9.70002e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.52001e-06 [reorder_send_recv_between_fp_bp]: 2.68998e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.14998e-06 [interleave_split_concat_branches]: 1.30999e-06 [interleave_parallel_branches]: 1.22999e-06 [overlap_opt_shard_in_pipeline]: 1.34e-06 [overlap_opt_shard_grad_in_pipeline]: 1.118e-05 [control_data_broadcast_order]: 6.699e-05 [grouped_pairwise_exchange_alltoall]: 2.43002e-06 [offloading_packed_experts]: 8.86002e-06 [overlap_recompute_and_grad_model_parallel]: 9.84999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.34998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.66e-06 [overlap_recompute_comm]: 2.68e-06 [overlap_grad_ring_attention]: 6.93e-06 [overlap_grad_flash_sp]: 4.668e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 2.91e-06 [split_layernorm_comm]: 2.62001e-06 [handle_group_info]: 1.13001e-06 [symbol_engine_optimizer]: 0.00042892, [1] [Cycle 1]: 0.00041599, [6] [build]: 0.00021951 [elim_shapecalc]: 4.104e-05 [elim_not_effective]: 4.629e-05 [opt_reshape]: 1.501e-05 [fold_const_symbol]: 3.897e-05 [renormalize]: 4.10015e-07 [detach_backward]: 2.86e-06 [pipeline_parallel_scheduler]: 1.91998e-06 [auto_monad_reorder]: 3.841e-05 [get_jit_bprop_graph]: 3.64002e-06 [rewriter_after_jit_bprop_graph]: 9.22999e-06 [opt_after_jit_grad]: 0.0009198 [validate]: 8.615e-05 Sums bootstrap : 0.000859s : 0.06% type_inference : 1.389595s : 98.73% event_method : 0.000029s : 0.00% auto_monad : 0.000103s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000033s : 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 : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000098s : 0.01% optimize.rewriter_before_opt_a : 0.000112s : 0.01% optimize.opt_a.expand_dump_flag : 0.000009s : 0.00% optimize.opt_a.switch_simplify : 0.000062s : 0.00% optimize.opt_a.loop_unroll : 0.000084s : 0.01% optimize.opt_a.a_1 : 0.001446s : 0.10% optimize.opt_a.with_stream_mark : 0.000064s : 0.00% optimize.opt_a.recompute_prepare : 0.000033s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 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 : 0.000367s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000047s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 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 : 0.000034s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000032s : 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 : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000050s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000081s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000016s : 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 : 0.000036s : 0.00% optimize.opt_a.a_after_grad : 0.000077s : 0.01% optimize.opt_a.renormalize : 0.007496s : 0.53% optimize.opt_a.add_forward_monad_depend : 0.000024s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000059s : 0.00% optimize.opt_a.cse : 0.000966s : 0.07% optimize.opt_a.a_3 : 0.000198s : 0.01% 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 : 0.000299s : 0.02% optimize.convert_after_rewriter : 0.000015s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.001284s : 0.09% optimize.opt_b.b_1 : 0.000315s : 0.02% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 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 : 0.000073s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000657s : 0.05% optimize.opt_after_cconv.c_1 : 0.000060s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 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 : 0.000047s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000076s : 0.01% optimize.tuple_transform.d_1 : 0.000125s : 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 : 0.000097s : 0.01% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000015s : 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 : 0.000002s : 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 : 0.000003s : 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 : 0.000011s : 0.00% optimize.control_data_broadcast_order : 0.000067s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000047s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000003s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000220s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000046s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000039s : 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 : 0.000038s : 0.00% get_jit_bprop_graph : 0.000004s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000920s : 0.07% validate : 0.000086s : 0.01% Time group info: ------[substitution.] 0.000586 111 8.23% : 0.000048s : 6: substitution.arithmetic_simplify 1.29% : 0.000008s : 6: substitution.elim_not_effective 2.31% : 0.000014s : 6: substitution.float_tuple_getitem_switch 3.62% : 0.000021s : 6: substitution.fold_const_symbol 1.62% : 0.000010s : 8: substitution.graph_param_transform 43.15% : 0.000253s : 5: substitution.inline 7.21% : 0.000042s : 12: substitution.j_node_and_user_rematch 1.72% : 0.000010s : 4: substitution.minmaximum_grad 1.83% : 0.000011s : 12: substitution.remove_not_recompute_node 1.18% : 0.000007s : 2: substitution.replace_old_param 6.59% : 0.000039s : 8: substitution.tuple_list_convert_item_index_to_positive 2.81% : 0.000016s : 8: substitution.tuple_list_get_item_const_eliminator 4.15% : 0.000024s : 8: substitution.tuple_list_get_item_depend_reorder 10.20% : 0.000060s : 12: substitution.tuple_list_get_item_eliminator 4.07% : 0.000024s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.389478 2 92.45% : 1.284577s : 1: type_inference.infer 7.55% : 0.104901s : 1: type_inference.specialize ------[replace.] 0.000058 5 100.00% : 0.000058s : 5: replace.inline ------[match.] 0.000248 5 100.00% : 0.000248s : 5: match.inline ------[predicate.] 0.000371 2113 0.88% : 0.000003s : 21: predicate.accumulaten_eliminater 0.94% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.60% : 0.000002s : 16: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.97% : 0.000004s : 21: predicate.adjust_all_reduce_mul_add 2.58% : 0.000010s : 37: predicate.arithmetic_simplify 0.89% : 0.000003s : 21: predicate.cast_eliminate 0.80% : 0.000003s : 16: predicate.check_bprop_eliminate 0.65% : 0.000002s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.76% : 0.000003s : 16: predicate.depend_value_elim 0.84% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.99% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.97% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 8: predicate.elim_not_effective 0.58% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.26% : 0.000005s : 29: predicate.environ_get_add_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_depend_swap 1.81% : 0.000007s : 45: predicate.environ_get_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.00% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.60% : 0.000006s : 26: predicate.float_depend_g_call 0.63% : 0.000002s : 16: predicate.float_environ_get_switch 1.10% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 8: predicate.fold_const_symbol 0.71% : 0.000003s : 16: predicate.get_grad_eliminate 0.20% : 0.000001s : 8: predicate.graph_param_transform 0.71% : 0.000003s : 16: predicate.incorporate_call 0.54% : 0.000002s : 16: predicate.incorporate_call_switch 5.49% : 0.000020s : 95: predicate.inline 1.20% : 0.000004s : 16: predicate.inline_without_move 0.47% : 0.000002s : 16: predicate.j_node_and_user_rematch 1.16% : 0.000004s : 16: predicate.less_batch_normalization 1.74% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.27% : 0.000008s : 58: predicate.load_eliminater 1.29% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.49% : 0.000006s : 36: predicate.loop_unroll_before_grad 1.72% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.65% : 0.000002s : 16: predicate.merge_addn 0.65% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.66% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.84% : 0.000003s : 21: predicate.minmaximum_grad 1.41% : 0.000005s : 8: predicate.mutable_eliminate 0.39% : 0.000001s : 8: predicate.opt_reshape 0.46% : 0.000002s : 8: predicate.parallel_virtual_node 1.58% : 0.000006s : 26: predicate.partial_defer_inline 1.13% : 0.000004s : 29: predicate.partial_eliminate 0.94% : 0.000004s : 21: predicate.print_const_string_wrapper 0.67% : 0.000002s : 16: predicate.reduce_all_const_elim 1.15% : 0.000004s : 21: predicate.reduce_eliminate 2.16% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.31% : 0.000005s : 37: predicate.replace_applicator 0.48% : 0.000002s : 16: predicate.replace_old_param 0.22% : 0.000001s : 8: predicate.reset_defer_inline 0.84% : 0.000003s : 21: predicate.reshape_eliminate 0.70% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 8: predicate.row_tensor_eliminate 1.43% : 0.000005s : 16: predicate.same_eliminate 0.41% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.77% : 0.000003s : 16: predicate.shard_identity_eliminate 0.84% : 0.000003s : 16: predicate.special_op_eliminate 0.71% : 0.000003s : 16: predicate.specialize_transform 1.13% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000004s : 16: predicate.stack_unstack_eliminate 0.41% : 0.000002s : 8: predicate.switch_call_monad_eliminater 1.10% : 0.000004s : 26: predicate.switch_defer_inline 1.65% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.85% : 0.000014s : 86: predicate.switch_simplify 0.79% : 0.000003s : 21: predicate.tile_eliminate 0.85% : 0.000003s : 21: predicate.transpose_eliminate 2.04% : 0.000008s : 37: predicate.tuple_list_convert_item_index_to_positive 2.26% : 0.000008s : 37: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.68% : 0.000014s : 53: predicate.tuple_list_get_item_eliminator 1.60% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.76% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.64% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.21% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.97% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.40% : 0.000001s : 8: predicate.value_based_eliminate 0.74% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.70% : 0.000003s : 16: predicate.virtual_output_eliminate 0.29% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.46% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007429 32 68.21% : 0.005068s : 25: func_graph_cloner_run.FuncGraphClonerGraph 31.79% : 0.002362s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.647442 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.42% : 0.006857s : 1: add_attr 0.41% : 0.006835s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000102s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.01% : 0.000109s : 1: auto_monad 0.00% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.06% : 0.000931s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000072s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000047s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.00% : 0.000037s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 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% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.04% : 0.000669s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.08% : 0.001302s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000039s : 1: opt.transform.mutable_eliminate 0.15% : 0.002462s : 78: opt.transform.opt_a 0.00% : 0.000058s : 1: opt.transform.opt_after_cconv 0.00% : 0.000047s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000290s : 28: opt.transform.opt_b 0.01% : 0.000135s : 2: opt.transform.opt_trans_graph 0.01% : 0.000132s : 4: opt.transform.symbol_engine_opt 0.74% : 0.012219s : 1: opt_a 0.01% : 0.000188s : 1: opt_after_cconv 0.06% : 0.000932s : 1: opt_after_jit_grad 0.03% : 0.000490s : 1: opt_b 7.02% : 0.115680s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000051s : 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% : 0.000025s : 1: overlap_opt_shard_grad_in_pipeline 6.00% : 0.098845s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 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% : 0.000054s : 1: pre_auto_parallel 0.01% : 0.000107s : 1: py_interpret_to_execute 0.00% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000081s : 1: remove_dup_value 0.29% : 0.004836s : 1: renormalize.infer 0.16% : 0.002641s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000307s : 1: rewriter_after_opt_a 0.01% : 0.000117s : 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% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000432s : 1: symbol_engine_optimizer 0.01% : 0.000172s : 1: tuple_transform 84.35% : 1.389631s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_bfloat16[True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_bfloat16[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 ================== 4 passed, 25 warnings in 88.75s (0:01:28) ===================