==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_008/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 3 items test_swiglu.py [WARNING] ME(166476:281472866008880,MainProcess):2026-01-29-17:38:59.190.856 [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 = 5.53041, [21] [bootstrap]: 0.00075644 [type_inference]: 5.03311 [event_method]: 2.163e-05 [auto_monad]: 0.00078354 [graph_reusing]: 7.78999e-06 [inline]: 2.64999e-06 [add_attr]: 0.483914, [1] [add_attr_with_inline]: 0.483896, [1] [Cycle 1]: 9.963e-05, [2] [tag_attr]: 2.282e-05 [meta_addattr_fg_expand]: 6.58e-06 [parallel-infer-symbol]: 4.45e-06 [pre_auto_parallel]: 5.28e-05 [insert-virtual-dataset]: 2.91e-06 [parallel-infer-symbol-second]: 9.60019e-07 [dataset_repeat_opt]: 2.21e-06 [pipeline_split]: 2.00002e-06 [optimize]: 0.0108368, [53] [py_interpret_to_execute]: 3.153e-05 [rewriter_before_opt_a]: 9.582e-05 [opt_a]: 0.00738956, [2] [Cycle 1]: 0.00621882, [45] [expand_dump_flag]: 3.59002e-06 [switch_simplify]: 4.306e-05 [loop_unroll]: 2.737e-05 [a_1]: 0.00079064 [with_stream_mark]: 2.078e-05 [recompute_prepare]: 1.375e-05 [updatestate_depend_eliminate]: 7.83999e-06 [updatestate_assign_eliminate]: 6.21e-06 [updatestate_loads_eliminate]: 5.53997e-06 [parameter_eliminate]: 2.06e-06 [a_2]: 0.00020229 [accelerated_algorithm]: 1.49e-05 [shard]: 2.92002e-06 [meta_shard_fg_expand]: 3.6e-06 [shard_inline]: 1.18e-05 [merge_send_recv]: 2.327e-05 [auto_parallel]: 1.205e-05 [parallel]: 5.018e-05 [flash_sp]: 1.921e-05 [merge_comm]: 7.51001e-06 [allreduce_fusion]: 6.62002e-06 [matmul_add_comm_reduction]: 1.563e-05 [allreduce_slice_to_reducescatter]: 9.10019e-07 [virtual_shard_identity]: 1.402e-05 [virtual_dataset]: 1.122e-05 [get_grad_eliminate_]: 1.071e-05 [virtual_output]: 1.088e-05 [merge_forward]: 7.73001e-06 [cell_reuse_recompute_pass]: 1.54e-06 [offload_activation]: 1.504e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.272e-05 [merge_recompute_call_nodes]: 1.67999e-06 [before_grad]: 1.955e-05 [set_forward_comm_id_for_comm_node_pass]: 6.78e-06 [meta_fg_expand]: 5.14e-06 [flash_sp_send_recv_attached]: 2.90998e-06 [receive_attached]: 2.41e-06 [after_resolve]: 1.562e-05 [a_after_grad]: 7.622e-05 [renormalize]: 0.00411899 [add_forward_monad_depend]: 8.89998e-06 [auto_monad_grad]: 3.4e-06 [auto_monad_eliminator]: 2.822e-05 [cse]: 0.0001768 [a_3]: 9.08e-05 [Cycle 2]: 0.00115886, [45] [expand_dump_flag]: 2.30002e-06 [switch_simplify]: 1.391e-05 [loop_unroll]: 1.173e-05 [a_1]: 0.0003218 [with_stream_mark]: 2.279e-05 [recompute_prepare]: 1.205e-05 [updatestate_depend_eliminate]: 8.21002e-06 [updatestate_assign_eliminate]: 5.27999e-06 [updatestate_loads_eliminate]: 4.80999e-06 [parameter_eliminate]: 1.55999e-06 [a_2]: 0.00015804 [accelerated_algorithm]: 1.182e-05 [shard]: 2.41998e-06 [meta_shard_fg_expand]: 3.2e-06 [shard_inline]: 1.076e-05 [merge_send_recv]: 1.129e-05 [auto_parallel]: 1.085e-05 [parallel]: 6.70002e-06 [flash_sp]: 3.71999e-06 [merge_comm]: 6.33e-06 [allreduce_fusion]: 6.08998e-06 [matmul_add_comm_reduction]: 1.178e-05 [allreduce_slice_to_reducescatter]: 7.29982e-07 [virtual_shard_identity]: 1.238e-05 [virtual_dataset]: 1.032e-05 [get_grad_eliminate_]: 1.101e-05 [virtual_output]: 1.029e-05 [merge_forward]: 7.76001e-06 [cell_reuse_recompute_pass]: 2.26998e-06 [offload_activation]: 1.405e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.188e-05 [merge_recompute_call_nodes]: 1.53002e-06 [before_grad]: 1.786e-05 [set_forward_comm_id_for_comm_node_pass]: 7.08998e-06 [meta_fg_expand]: 5.25999e-06 [flash_sp_send_recv_attached]: 1.72999e-06 [receive_attached]: 2.09e-06 [after_resolve]: 1.5e-05 [a_after_grad]: 1.668e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.53e-06 [auto_monad_grad]: 1.60001e-06 [auto_monad_eliminator]: 1.685e-05 [cse]: 5.563e-05 [a_3]: 6.939e-05 [py_interpret_to_execute_after_opt_a]: 1.97e-05 [slice_cell_reuse_recomputed_activation]: 2.43e-06 [rewriter_after_opt_a]: 0.00028775 [convert_after_rewriter]: 1.475e-05 [order_py_execute_after_rewriter]: 8.18001e-06 [mutable_eliminate]: 0.00070318 [opt_b]: 0.00041738, [1] [Cycle 1]: 0.00040981, [7] [b_1]: 0.00028163 [b_2]: 1.282e-05 [updatestate_depend_eliminate]: 1.096e-05 [updatestate_assign_eliminate]: 5.14e-06 [updatestate_loads_eliminate]: 5.69999e-06 [renormalize]: 6.69999e-07 [cse]: 5.505e-05 [optimize_parallel_all_gather_comm]: 2.623e-05 [overlap_param_gather]: 2.21e-06 [cconv]: 3.046e-05 [loop_unroll]: 0.00050062 [opt_after_cconv]: 0.00016108, [1] [Cycle 1]: 0.00015455, [7] [c_1]: 5.546e-05 [parameter_eliminate]: 3.76999e-06 [updatestate_depend_eliminate]: 9.76e-06 [updatestate_assign_eliminate]: 5.21002e-06 [updatestate_loads_eliminate]: 4.99e-06 [cse]: 4.099e-05 [renormalize]: 4.39992e-07 [remove_dup_value]: 7.68e-05 [tuple_transform]: 0.00016166, [1] [Cycle 1]: 0.00015605, [4] [d_1]: 0.00011753 [none_parameter_eliminate]: 2.17999e-06 [renormalize]: 4.50003e-07 [switch_simplify]: 1.378e-05 [partial_unused_args_eliminate]: 3.01999e-06 [add_recomputation]: 8.857e-05 [cse_after_recomputation]: 4.159e-05, [1] [Cycle 1]: 3.633e-05, [1] [cse]: 3.032e-05 [environ_conv]: 2.427e-05 [swap_dp_allreduce_reducescatter]: 1.034e-05 [bias_add_comm_swap]: 2.81e-06 [label_micro_interleaved_index]: 5.66e-06 [label_fine_grained_interleaved_index]: 2.93e-06 [merge_cast_opt]: 1.47001e-06 [slice_recompute_activation]: 2.91e-06 [micro_interleaved_order_control]: 2.48e-06 [assign_add_opt]: 1.48002e-06 [ForceFp32Comm]: 8.59989e-07 [remove_cast_before_assign_add]: 1.44e-06 [full_micro_interleaved_order_control]: 2.37999e-06 [reorder_send_recv_between_fp_bp]: 2.81999e-06 [comm_op_add_attrs]: 1.09998e-06 [add_comm_op_reuse_tag]: 1.00999e-06 [interleave_split_concat_branches]: 1.36998e-06 [interleave_parallel_branches]: 1.75001e-06 [overlap_opt_shard_in_pipeline]: 2.031e-05 [overlap_opt_shard_grad_in_pipeline]: 1.89e-06 [control_data_broadcast_order]: 2.138e-05 [grouped_pairwise_exchange_alltoall]: 1.89e-06 [offloading_packed_experts]: 6.63e-06 [overlap_recompute_and_grad_model_parallel]: 6.66999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.10999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.43002e-06 [overlap_recompute_comm]: 2.69001e-06 [overlap_grad_ring_attention]: 6.23e-06 [overlap_grad_flash_sp]: 3.329e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.79001e-06 [split_layernorm_comm]: 1.89e-06 [handle_group_info]: 1.32e-06 [symbol_engine_optimizer]: 0.00034841, [1] [Cycle 1]: 0.00034323, [6] [build]: 0.00020544 [elim_shapecalc]: 2.202e-05 [elim_not_effective]: 3.341e-05 [opt_reshape]: 1.226e-05 [fold_const_symbol]: 3.235e-05 [renormalize]: 2.59985e-07 [detach_backward]: 3.36001e-06 [pipeline_parallel_scheduler]: 1.52001e-06 [auto_monad_reorder]: 3.791e-05 [get_jit_bprop_graph]: 2.08002e-06 [rewriter_after_jit_bprop_graph]: 4.18001e-06 [opt_after_jit_grad]: 0.00058017 [validate]: 9.404e-05 Sums bootstrap : 0.000756s : 0.01% type_inference : 5.033109s : 99.76% event_method : 0.000022s : 0.00% auto_monad : 0.000784s : 0.02% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 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 : 0.000053s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000032s : 0.00% optimize.rewriter_before_opt_a : 0.000096s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000057s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001112s : 0.02% optimize.opt_a.with_stream_mark : 0.000044s : 0.00% optimize.opt_a.recompute_prepare : 0.000026s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000360s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000027s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000035s : 0.00% optimize.opt_a.auto_parallel : 0.000023s : 0.00% optimize.opt_a.parallel : 0.000057s : 0.00% optimize.opt_a.flash_sp : 0.000023s : 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 : 0.000027s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.00% optimize.opt_a.virtual_dataset : 0.000022s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000022s : 0.00% optimize.opt_a.virtual_output : 0.000021s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000029s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000045s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000037s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000031s : 0.00% optimize.opt_a.a_after_grad : 0.000093s : 0.00% optimize.opt_a.renormalize : 0.004119s : 0.08% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000045s : 0.00% optimize.opt_a.cse : 0.000232s : 0.00% optimize.opt_a.a_3 : 0.000160s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000288s : 0.01% optimize.convert_after_rewriter : 0.000015s : 0.00% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000703s : 0.01% optimize.opt_b.b_1 : 0.000282s : 0.01% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000055s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000030s : 0.00% optimize.loop_unroll : 0.000501s : 0.01% optimize.opt_after_cconv.c_1 : 0.000055s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000041s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000077s : 0.00% optimize.tuple_transform.d_1 : 0.000118s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000089s : 0.00% optimize.cse_after_recomputation.cse : 0.000030s : 0.00% optimize.environ_conv : 0.000024s : 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 : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000020s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 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 : 0.000006s : 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 : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000205s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000032s : 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 : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000580s : 0.01% validate : 0.000094s : 0.00% Time group info: ------[substitution.] 0.000436 111 9.35% : 0.000041s : 6: substitution.arithmetic_simplify 2.84% : 0.000012s : 6: substitution.elim_not_effective 2.47% : 0.000011s : 6: substitution.float_tuple_getitem_switch 3.53% : 0.000015s : 6: substitution.fold_const_symbol 2.25% : 0.000010s : 8: substitution.graph_param_transform 41.26% : 0.000180s : 5: substitution.inline 1.59% : 0.000007s : 12: substitution.j_node_and_user_rematch 2.09% : 0.000009s : 4: substitution.minmaximum_grad 2.29% : 0.000010s : 12: substitution.remove_not_recompute_node 1.11% : 0.000005s : 2: substitution.replace_old_param 6.66% : 0.000029s : 8: substitution.tuple_list_convert_item_index_to_positive 5.27% : 0.000023s : 8: substitution.tuple_list_get_item_const_eliminator 4.77% : 0.000021s : 8: substitution.tuple_list_get_item_depend_reorder 10.12% : 0.000044s : 12: substitution.tuple_list_get_item_eliminator 4.40% : 0.000019s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 5.033017 2 99.94% : 5.029901s : 1: type_inference.infer 0.06% : 0.003116s : 1: type_inference.specialize ------[replace.] 0.000044 5 100.00% : 0.000044s : 5: replace.inline ------[match.] 0.000177 5 100.00% : 0.000177s : 5: match.inline ------[predicate.] 0.000357 2113 0.85% : 0.000003s : 21: predicate.accumulaten_eliminater 0.93% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.60% : 0.000002s : 16: predicate.addn_check_dump 0.90% : 0.000003s : 21: predicate.addn_zero_filter 0.77% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.27% : 0.000008s : 37: predicate.arithmetic_simplify 0.85% : 0.000003s : 21: predicate.cast_eliminate 0.68% : 0.000002s : 16: predicate.check_bprop_eliminate 0.63% : 0.000002s : 16: predicate.compare_switch_simplify 0.21% : 0.000001s : 8: predicate.const_output_eliminate 0.63% : 0.000002s : 16: predicate.depend_value_elim 0.87% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.88% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.86% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.95% : 0.000003s : 16: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 8: predicate.elim_not_effective 0.44% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.04% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_depend_swap 1.87% : 0.000007s : 45: predicate.environ_get_eliminate 1.06% : 0.000004s : 29: predicate.environ_get_set_eliminate 0.98% : 0.000003s : 26: predicate.exchange_switch_depend_value 1.60% : 0.000006s : 26: predicate.float_depend_g_call 0.60% : 0.000002s : 16: predicate.float_environ_get_switch 1.07% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 8: predicate.fold_const_symbol 0.70% : 0.000002s : 16: predicate.get_grad_eliminate 0.22% : 0.000001s : 8: predicate.graph_param_transform 0.63% : 0.000002s : 16: predicate.incorporate_call 0.57% : 0.000002s : 16: predicate.incorporate_call_switch 11.50% : 0.000041s : 95: predicate.inline 0.86% : 0.000003s : 16: predicate.inline_without_move 0.33% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.31% : 0.000005s : 16: predicate.less_batch_normalization 1.63% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.26% : 0.000008s : 58: predicate.load_eliminater 0.86% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.42% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.61% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.68% : 0.000002s : 16: predicate.merge_addn 0.65% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.65% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.82% : 0.000003s : 21: predicate.minmaximum_grad 1.05% : 0.000004s : 8: predicate.mutable_eliminate 0.38% : 0.000001s : 8: predicate.opt_reshape 0.37% : 0.000001s : 8: predicate.parallel_virtual_node 1.33% : 0.000005s : 26: predicate.partial_defer_inline 1.17% : 0.000004s : 29: predicate.partial_eliminate 0.85% : 0.000003s : 21: predicate.print_const_string_wrapper 0.64% : 0.000002s : 16: predicate.reduce_all_const_elim 1.17% : 0.000004s : 21: predicate.reduce_eliminate 2.24% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.36% : 0.000001s : 16: predicate.remove_not_recompute_node 1.12% : 0.000004s : 37: predicate.replace_applicator 0.38% : 0.000001s : 16: predicate.replace_old_param 0.22% : 0.000001s : 8: predicate.reset_defer_inline 0.84% : 0.000003s : 21: predicate.reshape_eliminate 0.74% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.39% : 0.000001s : 8: predicate.row_tensor_eliminate 0.92% : 0.000003s : 16: predicate.same_eliminate 0.43% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.80% : 0.000003s : 16: predicate.shard_identity_eliminate 0.78% : 0.000003s : 16: predicate.special_op_eliminate 0.80% : 0.000003s : 16: predicate.specialize_transform 0.99% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.08% : 0.000004s : 26: predicate.switch_defer_inline 1.77% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.93% : 0.000014s : 86: predicate.switch_simplify 0.83% : 0.000003s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.78% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.61% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.15% : 0.000011s : 53: predicate.tuple_list_get_item_eliminator 1.69% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.38% : 0.000008s : 53: predicate.tuple_list_set_item_eliminator 1.51% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.10% : 0.000007s : 58: predicate.updatestate_pure_node_eliminater 2.98% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.40% : 0.000001s : 8: predicate.value_based_eliminate 0.70% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.72% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.46% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004206 32 74.96% : 0.003153s : 25: func_graph_cloner_run.FuncGraphClonerGraph 25.04% : 0.001053s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 6.031692 192 0.00% : 0.000004s : 1: ForceFp32Comm 8.02% : 0.483920s : 1: add_attr 8.02% : 0.483901s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000093s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000799s : 1: auto_monad 0.00% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.01% : 0.000790s : 1: bootstrap 0.00% : 0.000035s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000028s : 1: environ_conv 0.00% : 0.000029s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 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% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.01% : 0.000510s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000713s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000026s : 1: opt.transform.mutable_eliminate 0.03% : 0.001996s : 78: opt.transform.opt_a 0.00% : 0.000054s : 1: opt.transform.opt_after_cconv 0.00% : 0.000044s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000262s : 28: opt.transform.opt_b 0.00% : 0.000128s : 2: opt.transform.opt_trans_graph 0.00% : 0.000095s : 4: opt.transform.symbol_engine_opt 0.12% : 0.007393s : 1: opt_a 0.00% : 0.000165s : 1: opt_after_cconv 0.01% : 0.000591s : 1: opt_after_jit_grad 0.01% : 0.000421s : 1: opt_b 0.18% : 0.010843s : 1: optimize 0.00% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.00% : 0.000037s : 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% : 0.000024s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000058s : 1: pre_auto_parallel 0.00% : 0.000036s : 1: py_interpret_to_execute 0.00% : 0.000023s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000082s : 1: remove_dup_value 0.05% : 0.002870s : 1: renormalize.infer 0.02% : 0.001237s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000295s : 1: rewriter_after_opt_a 0.00% : 0.000100s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000352s : 1: symbol_engine_optimizer 0.00% : 0.000165s : 1: tuple_transform 83.44% : 5.033134s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_74937_20260129172203.log . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape0] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu_dyn_shape[shape0],max_mem:100.0M [WARNING] ME(166476:281472866008880,MainProcess):2026-01-29-17:40:05.108.112 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.03194, [21] [bootstrap]: 0.00077227 [type_inference]: 1.71367 [event_method]: 2.804e-05 [auto_monad]: 0.00010694 [graph_reusing]: 6.66e-06 [inline]: 3.51999e-06 [add_attr]: 0.187244, [1] [add_attr_with_inline]: 0.187224, [1] [Cycle 1]: 0.00010767, [2] [tag_attr]: 3.128e-05 [meta_addattr_fg_expand]: 5.82001e-06 [parallel-infer-symbol]: 4.09002e-06 [pre_auto_parallel]: 5.384e-05 [insert-virtual-dataset]: 2.74001e-06 [parallel-infer-symbol-second]: 7.7e-07 [dataset_repeat_opt]: 2.09e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.129024, [53] [py_interpret_to_execute]: 3.843e-05 [rewriter_before_opt_a]: 0.00011365 [opt_a]: 0.125135, [2] [Cycle 1]: 0.123655, [45] [expand_dump_flag]: 3.73999e-06 [switch_simplify]: 4.461e-05 [loop_unroll]: 7.718e-05 [a_1]: 0.00125368 [with_stream_mark]: 3.491e-05 [recompute_prepare]: 2.297e-05 [updatestate_depend_eliminate]: 9.97001e-06 [updatestate_assign_eliminate]: 6.48003e-06 [updatestate_loads_eliminate]: 6.68e-06 [parameter_eliminate]: 1.89e-06 [a_2]: 0.00021843 [accelerated_algorithm]: 1.829e-05 [shard]: 2.89001e-06 [meta_shard_fg_expand]: 5.15999e-06 [shard_inline]: 1.27e-05 [merge_send_recv]: 1.462e-05 [auto_parallel]: 1.458e-05 [parallel]: 4.017e-05 [flash_sp]: 1.395e-05 [merge_comm]: 7.79002e-06 [allreduce_fusion]: 6.65002e-06 [matmul_add_comm_reduction]: 1.84e-05 [allreduce_slice_to_reducescatter]: 7.7e-07 [virtual_shard_identity]: 1.908e-05 [virtual_dataset]: 1.462e-05 [get_grad_eliminate_]: 1.434e-05 [virtual_output]: 1.455e-05 [merge_forward]: 1.048e-05 [cell_reuse_recompute_pass]: 2.07999e-06 [offload_activation]: 1.952e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.362e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 2.556e-05 [set_forward_comm_id_for_comm_node_pass]: 8.69998e-06 [meta_fg_expand]: 7.11999e-06 [flash_sp_send_recv_attached]: 3.06001e-06 [receive_attached]: 2.44999e-06 [after_resolve]: 2.117e-05 [a_after_grad]: 2.39e-05 [renormalize]: 0.119479 [add_forward_monad_depend]: 1.446e-05 [auto_monad_grad]: 3.10002e-06 [auto_monad_eliminator]: 4.191e-05 [cse]: 0.00155899 [a_3]: 0.00012516 [Cycle 2]: 0.00146446, [45] [expand_dump_flag]: 3.63999e-06 [switch_simplify]: 2.019e-05 [loop_unroll]: 1.365e-05 [a_1]: 0.00037622 [with_stream_mark]: 3.862e-05 [recompute_prepare]: 1.337e-05 [updatestate_depend_eliminate]: 1.077e-05 [updatestate_assign_eliminate]: 5.59e-06 [updatestate_loads_eliminate]: 5.59998e-06 [parameter_eliminate]: 2.99001e-06 [a_2]: 0.00025846 [accelerated_algorithm]: 1.425e-05 [shard]: 2.93e-06 [meta_shard_fg_expand]: 4.4e-06 [shard_inline]: 1.153e-05 [merge_send_recv]: 1.57e-05 [auto_parallel]: 1.589e-05 [parallel]: 1.065e-05 [flash_sp]: 4.61002e-06 [merge_comm]: 6.74999e-06 [allreduce_fusion]: 6.70998e-06 [matmul_add_comm_reduction]: 1.731e-05 [allreduce_slice_to_reducescatter]: 9.10019e-07 [virtual_shard_identity]: 1.402e-05 [virtual_dataset]: 1.197e-05 [get_grad_eliminate_]: 1.309e-05 [virtual_output]: 1.189e-05 [merge_forward]: 7.23999e-06 [cell_reuse_recompute_pass]: 3.33e-06 [offload_activation]: 1.662e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.407e-05 [merge_recompute_call_nodes]: 1.25001e-06 [before_grad]: 1.966e-05 [set_forward_comm_id_for_comm_node_pass]: 8.12998e-06 [meta_fg_expand]: 6.48e-06 [flash_sp_send_recv_attached]: 1.99e-06 [receive_attached]: 2.79001e-06 [after_resolve]: 1.855e-05 [a_after_grad]: 1.881e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.82998e-06 [auto_monad_grad]: 2.33002e-06 [auto_monad_eliminator]: 2.225e-05 [cse]: 5.73e-05 [a_3]: 7.377e-05 [py_interpret_to_execute_after_opt_a]: 2.748e-05 [slice_cell_reuse_recomputed_activation]: 2.36e-06 [rewriter_after_opt_a]: 0.0003049 [convert_after_rewriter]: 1.55e-05 [order_py_execute_after_rewriter]: 1.053e-05 [mutable_eliminate]: 0.00086285 [opt_b]: 0.00045619, [1] [Cycle 1]: 0.00044683, [7] [b_1]: 0.0003004 [b_2]: 1.574e-05 [updatestate_depend_eliminate]: 1.556e-05 [updatestate_assign_eliminate]: 5.37001e-06 [updatestate_loads_eliminate]: 5.47999e-06 [renormalize]: 5.69999e-07 [cse]: 6.206e-05 [optimize_parallel_all_gather_comm]: 3.26e-05 [overlap_param_gather]: 2.41e-06 [cconv]: 4.03e-05 [loop_unroll]: 0.00057167 [opt_after_cconv]: 0.00020582, [1] [Cycle 1]: 0.00019636, [7] [c_1]: 5.936e-05 [parameter_eliminate]: 5.53997e-06 [updatestate_depend_eliminate]: 1.511e-05 [updatestate_assign_eliminate]: 5.05999e-06 [updatestate_loads_eliminate]: 2.483e-05 [cse]: 4.593e-05 [renormalize]: 5.10016e-07 [remove_dup_value]: 7.027e-05 [tuple_transform]: 0.0001759, [1] [Cycle 1]: 0.00016981, [4] [d_1]: 0.00012842 [none_parameter_eliminate]: 2.32999e-06 [renormalize]: 2.80008e-07 [switch_simplify]: 1.394e-05 [partial_unused_args_eliminate]: 2.14e-06 [add_recomputation]: 0.00010274 [cse_after_recomputation]: 4.82e-05, [1] [Cycle 1]: 4.093e-05, [1] [cse]: 3.418e-05 [environ_conv]: 1.486e-05 [swap_dp_allreduce_reducescatter]: 1.072e-05 [bias_add_comm_swap]: 3.51999e-06 [label_micro_interleaved_index]: 6.24001e-06 [label_fine_grained_interleaved_index]: 2.59999e-06 [merge_cast_opt]: 1.82001e-06 [slice_recompute_activation]: 2.11e-06 [micro_interleaved_order_control]: 2.32999e-06 [assign_add_opt]: 1.22e-06 [ForceFp32Comm]: 9.89996e-07 [remove_cast_before_assign_add]: 1.37999e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 2.73e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 1.08001e-06 [interleave_split_concat_branches]: 1.51998e-06 [interleave_parallel_branches]: 1.33002e-06 [overlap_opt_shard_in_pipeline]: 3.21999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.01e-06 [control_data_broadcast_order]: 2.355e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 8.31002e-06 [overlap_recompute_and_grad_model_parallel]: 8.49002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.62999e-06 [overlap_recompute_comm]: 2.39999e-06 [overlap_grad_ring_attention]: 6.87002e-06 [overlap_grad_flash_sp]: 3.603e-05 [begin_end_overlap_inline]: 5.20027e-07 [split_matmul_comm_elemetwise]: 2.30002e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 0.0003604, [1] [Cycle 1]: 0.00035489, [6] [build]: 0.00019718 [elim_shapecalc]: 2.608e-05 [elim_not_effective]: 3.17e-05 [opt_reshape]: 1.615e-05 [fold_const_symbol]: 3.737e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.63e-06 [pipeline_parallel_scheduler]: 1.50001e-06 [auto_monad_reorder]: 3.043e-05 [get_jit_bprop_graph]: 5.22999e-06 [rewriter_after_jit_bprop_graph]: 6.17999e-06 [opt_after_jit_grad]: 0.00067195 [validate]: 8.624e-05 Sums bootstrap : 0.000772s : 0.04% type_inference : 1.713672s : 92.96% event_method : 0.000028s : 0.00% auto_monad : 0.000107s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000031s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000054s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000114s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000065s : 0.00% optimize.opt_a.loop_unroll : 0.000091s : 0.00% optimize.opt_a.a_1 : 0.001630s : 0.09% optimize.opt_a.with_stream_mark : 0.000074s : 0.00% optimize.opt_a.recompute_prepare : 0.000036s : 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 : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000477s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000033s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000024s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000015s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 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 : 0.000027s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.00% optimize.opt_a.virtual_output : 0.000026s : 0.00% optimize.opt_a.merge_forward : 0.000018s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000058s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000045s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000017s : 0.00% optimize.opt_a.meta_fg_expand : 0.000014s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000040s : 0.00% optimize.opt_a.a_after_grad : 0.000043s : 0.00% optimize.opt_a.renormalize : 0.119479s : 6.48% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000064s : 0.00% optimize.opt_a.cse : 0.001616s : 0.09% optimize.opt_a.a_3 : 0.000199s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000305s : 0.02% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000863s : 0.05% optimize.opt_b.b_1 : 0.000300s : 0.02% optimize.opt_b.b_2 : 0.000016s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000062s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.00% optimize.loop_unroll : 0.000572s : 0.03% optimize.opt_after_cconv.c_1 : 0.000059s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000025s : 0.00% optimize.opt_after_cconv.cse : 0.000046s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000070s : 0.00% optimize.tuple_transform.d_1 : 0.000128s : 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 : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000103s : 0.01% optimize.cse_after_recomputation.cse : 0.000034s : 0.00% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 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 : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 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 : 0.000197s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000032s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000037s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000030s : 0.00% get_jit_bprop_graph : 0.000005s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000672s : 0.04% validate : 0.000086s : 0.00% Time group info: ------[substitution.] 0.000573 111 8.32% : 0.000048s : 6: substitution.arithmetic_simplify 1.34% : 0.000008s : 6: substitution.elim_not_effective 2.13% : 0.000012s : 6: substitution.float_tuple_getitem_switch 3.42% : 0.000020s : 6: substitution.fold_const_symbol 1.59% : 0.000009s : 8: substitution.graph_param_transform 46.21% : 0.000265s : 5: substitution.inline 1.30% : 0.000007s : 12: substitution.j_node_and_user_rematch 2.43% : 0.000014s : 4: substitution.minmaximum_grad 2.01% : 0.000012s : 12: substitution.remove_not_recompute_node 1.09% : 0.000006s : 2: substitution.replace_old_param 7.18% : 0.000041s : 8: substitution.tuple_list_convert_item_index_to_positive 3.37% : 0.000019s : 8: substitution.tuple_list_get_item_const_eliminator 4.60% : 0.000026s : 8: substitution.tuple_list_get_item_depend_reorder 10.88% : 0.000062s : 12: substitution.tuple_list_get_item_eliminator 4.12% : 0.000024s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.713549 2 99.64% : 1.707439s : 1: type_inference.infer 0.36% : 0.006110s : 1: type_inference.specialize ------[replace.] 0.000060 5 100.00% : 0.000060s : 5: replace.inline ------[match.] 0.000261 5 100.00% : 0.000261s : 5: match.inline ------[predicate.] 0.000374 2113 0.90% : 0.000003s : 21: predicate.accumulaten_eliminater 1.54% : 0.000006s : 8: predicate.ad_related_special_op_eliminate 0.63% : 0.000002s : 16: predicate.addn_check_dump 0.87% : 0.000003s : 21: predicate.addn_zero_filter 0.77% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.61% : 0.000010s : 37: predicate.arithmetic_simplify 0.97% : 0.000004s : 21: predicate.cast_eliminate 0.68% : 0.000003s : 16: predicate.check_bprop_eliminate 0.66% : 0.000002s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.68% : 0.000003s : 16: predicate.depend_value_elim 0.80% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.05% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.82% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.18% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 8: predicate.elim_not_effective 0.52% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.04% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.06% : 0.000004s : 29: predicate.environ_get_depend_swap 1.83% : 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 1.79% : 0.000007s : 26: predicate.float_depend_g_call 0.59% : 0.000002s : 16: predicate.float_environ_get_switch 1.32% : 0.000005s : 24: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 8: predicate.fold_const_symbol 0.70% : 0.000003s : 16: predicate.get_grad_eliminate 0.25% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000003s : 16: predicate.incorporate_call 0.54% : 0.000002s : 16: predicate.incorporate_call_switch 5.46% : 0.000020s : 95: predicate.inline 0.79% : 0.000003s : 16: predicate.inline_without_move 0.30% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.38% : 0.000005s : 16: predicate.less_batch_normalization 1.52% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.24% : 0.000008s : 58: predicate.load_eliminater 1.08% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.75% : 0.000007s : 36: predicate.loop_unroll_before_grad 1.85% : 0.000007s : 37: predicate.make_slice_get_slice_eliminator 0.62% : 0.000002s : 16: predicate.merge_addn 0.62% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.69% : 0.000003s : 16: predicate.mini_step_allgather_replace 0.78% : 0.000003s : 21: predicate.minmaximum_grad 1.37% : 0.000005s : 8: predicate.mutable_eliminate 0.39% : 0.000001s : 8: predicate.opt_reshape 0.51% : 0.000002s : 8: predicate.parallel_virtual_node 1.72% : 0.000006s : 26: predicate.partial_defer_inline 1.11% : 0.000004s : 29: predicate.partial_eliminate 0.80% : 0.000003s : 21: predicate.print_const_string_wrapper 0.67% : 0.000003s : 16: predicate.reduce_all_const_elim 1.23% : 0.000005s : 21: predicate.reduce_eliminate 2.08% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.62% : 0.000002s : 16: predicate.remove_not_recompute_node 1.29% : 0.000005s : 37: predicate.replace_applicator 0.43% : 0.000002s : 16: predicate.replace_old_param 0.35% : 0.000001s : 8: predicate.reset_defer_inline 0.87% : 0.000003s : 21: predicate.reshape_eliminate 0.83% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.47% : 0.000002s : 8: predicate.row_tensor_eliminate 1.25% : 0.000005s : 16: predicate.same_eliminate 0.41% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.85% : 0.000003s : 16: predicate.shard_identity_eliminate 0.87% : 0.000003s : 16: predicate.special_op_eliminate 0.71% : 0.000003s : 16: predicate.specialize_transform 1.12% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.93% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.06% : 0.000004s : 26: predicate.switch_defer_inline 1.79% : 0.000007s : 42: predicate.switch_layer_defer_inline 4.09% : 0.000015s : 86: predicate.switch_simplify 1.05% : 0.000004s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.89% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.80% : 0.000014s : 53: predicate.tuple_list_get_item_eliminator 1.56% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.55% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.57% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.08% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.79% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 8: predicate.value_based_eliminate 0.71% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.70% : 0.000003s : 16: predicate.virtual_output_eliminate 0.33% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.51% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.008060 32 63.56% : 0.005123s : 25: func_graph_cloner_run.FuncGraphClonerGraph 36.44% : 0.002937s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.470856 192 0.00% : 0.000004s : 1: ForceFp32Comm 7.58% : 0.187252s : 1: add_attr 7.58% : 0.187229s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000108s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.00% : 0.000114s : 1: auto_monad 0.00% : 0.000035s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000810s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000020s : 1: convert_after_rewriter 0.00% : 0.000051s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000010s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.00% : 0.000036s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000008s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000582s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000875s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000034s : 1: opt.transform.mutable_eliminate 0.11% : 0.002720s : 78: opt.transform.opt_a 0.00% : 0.000058s : 1: opt.transform.opt_after_cconv 0.00% : 0.000054s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000283s : 28: opt.transform.opt_b 0.01% : 0.000139s : 2: opt.transform.opt_trans_graph 0.00% : 0.000105s : 4: opt.transform.symbol_engine_opt 5.06% : 0.125141s : 1: opt_a 0.01% : 0.000210s : 1: opt_after_cconv 0.03% : 0.000685s : 1: opt_after_jit_grad 0.02% : 0.000461s : 1: opt_b 5.22% : 0.129032s : 1: optimize 0.00% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000040s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000059s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000075s : 1: remove_dup_value 0.27% : 0.006598s : 1: renormalize.infer 4.57% : 0.112856s : 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% : 0.000312s : 1: rewriter_after_opt_a 0.00% : 0.000119s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000364s : 1: symbol_engine_optimizer 0.01% : 0.000179s : 1: tuple_transform 69.36% : 1.713704s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape1] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu_dyn_shape[shape1],max_mem:102.0M [WARNING] ME(166476:281472866008880,MainProcess):2026-01-29-17:40:16.772.736 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.23719, [21] [bootstrap]: 0.00079283 [type_inference]: 1.96592 [event_method]: 2.828e-05 [auto_monad]: 9.58e-05 [graph_reusing]: 6.53e-06 [inline]: 6.14001e-06 [add_attr]: 0.235938, [1] [add_attr_with_inline]: 0.23592, [1] [Cycle 1]: 7.696e-05, [2] [tag_attr]: 2.736e-05 [meta_addattr_fg_expand]: 5.52999e-06 [parallel-infer-symbol]: 3.8e-06 [pre_auto_parallel]: 4.935e-05 [insert-virtual-dataset]: 2.94001e-06 [parallel-infer-symbol-second]: 8.59989e-07 [dataset_repeat_opt]: 2.08998e-06 [pipeline_split]: 1.78002e-06 [optimize]: 0.0333151, [53] [py_interpret_to_execute]: 3.964e-05 [rewriter_before_opt_a]: 0.00010013 [opt_a]: 0.0295026, [2] [Cycle 1]: 0.0281092, [45] [expand_dump_flag]: 3.37002e-06 [switch_simplify]: 4.29e-05 [loop_unroll]: 2.698e-05 [a_1]: 0.00125002 [with_stream_mark]: 3.319e-05 [recompute_prepare]: 2.154e-05 [updatestate_depend_eliminate]: 1.178e-05 [updatestate_assign_eliminate]: 6.43e-06 [updatestate_loads_eliminate]: 6.32001e-06 [parameter_eliminate]: 1.69e-06 [a_2]: 0.00023089 [accelerated_algorithm]: 1.798e-05 [shard]: 2.70997e-06 [meta_shard_fg_expand]: 4.86002e-06 [shard_inline]: 1.168e-05 [merge_send_recv]: 1.685e-05 [auto_parallel]: 1.435e-05 [parallel]: 3.364e-05 [flash_sp]: 1.181e-05 [merge_comm]: 8.52e-06 [allreduce_fusion]: 7.04001e-06 [matmul_add_comm_reduction]: 1.838e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 2.394e-05 [virtual_dataset]: 1.605e-05 [get_grad_eliminate_]: 1.556e-05 [virtual_output]: 1.505e-05 [merge_forward]: 9.09998e-06 [cell_reuse_recompute_pass]: 2.37001e-06 [offload_activation]: 2.127e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.464e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 2.905e-05 [set_forward_comm_id_for_comm_node_pass]: 9.12999e-06 [meta_fg_expand]: 6.56999e-06 [flash_sp_send_recv_attached]: 2.73e-06 [receive_attached]: 2.11998e-06 [after_resolve]: 2.044e-05 [a_after_grad]: 2.85e-05 [renormalize]: 0.0246753 [add_forward_monad_depend]: 1.546e-05 [auto_monad_grad]: 2.46e-06 [auto_monad_eliminator]: 3.551e-05 [cse]: 0.00087509 [a_3]: 0.00011773 [Cycle 2]: 0.00137765, [45] [expand_dump_flag]: 3.38e-06 [switch_simplify]: 1.743e-05 [loop_unroll]: 1.278e-05 [a_1]: 0.00042702 [with_stream_mark]: 3.064e-05 [recompute_prepare]: 1.289e-05 [updatestate_depend_eliminate]: 9.62001e-06 [updatestate_assign_eliminate]: 5.81e-06 [updatestate_loads_eliminate]: 5.94999e-06 [parameter_eliminate]: 2.22001e-06 [a_2]: 0.0001676 [accelerated_algorithm]: 1.27e-05 [shard]: 2.37999e-06 [meta_shard_fg_expand]: 4.40999e-06 [shard_inline]: 1.107e-05 [merge_send_recv]: 1.242e-05 [auto_parallel]: 1.54e-05 [parallel]: 9.95002e-06 [flash_sp]: 4.55999e-06 [merge_comm]: 6.34001e-06 [allreduce_fusion]: 6.21998e-06 [matmul_add_comm_reduction]: 1.441e-05 [allreduce_slice_to_reducescatter]: 1.05001e-06 [virtual_shard_identity]: 1.338e-05 [virtual_dataset]: 1.121e-05 [get_grad_eliminate_]: 1.297e-05 [virtual_output]: 1.09e-05 [merge_forward]: 6.96001e-06 [cell_reuse_recompute_pass]: 3.49001e-06 [offload_activation]: 1.647e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.175e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 1.939e-05 [set_forward_comm_id_for_comm_node_pass]: 6.76e-06 [meta_fg_expand]: 6.21e-06 [flash_sp_send_recv_attached]: 2.20002e-06 [receive_attached]: 2.48e-06 [after_resolve]: 1.608e-05 [a_after_grad]: 1.68e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.08e-06 [auto_monad_grad]: 2.21998e-06 [auto_monad_eliminator]: 1.968e-05 [cse]: 8.618e-05 [a_3]: 7.268e-05 [py_interpret_to_execute_after_opt_a]: 2.817e-05 [slice_cell_reuse_recomputed_activation]: 2.51998e-06 [rewriter_after_opt_a]: 0.00028784 [convert_after_rewriter]: 1.401e-05 [order_py_execute_after_rewriter]: 1.026e-05 [mutable_eliminate]: 0.00085433 [opt_b]: 0.00043528, [1] [Cycle 1]: 0.00042617, [7] [b_1]: 0.00029475 [b_2]: 1.486e-05 [updatestate_depend_eliminate]: 1.115e-05 [updatestate_assign_eliminate]: 5.37001e-06 [updatestate_loads_eliminate]: 5.48002e-06 [renormalize]: 8.50006e-07 [cse]: 5.24e-05 [optimize_parallel_all_gather_comm]: 2.656e-05 [overlap_param_gather]: 2.22001e-06 [cconv]: 3.558e-05 [loop_unroll]: 0.00052674 [opt_after_cconv]: 0.00016884, [1] [Cycle 1]: 0.00016052, [7] [c_1]: 5.763e-05 [parameter_eliminate]: 4.23001e-06 [updatestate_depend_eliminate]: 1.146e-05 [updatestate_assign_eliminate]: 5.14e-06 [updatestate_loads_eliminate]: 4.71997e-06 [cse]: 4.119e-05 [renormalize]: 7.29982e-07 [remove_dup_value]: 6.486e-05 [tuple_transform]: 0.0001608, [1] [Cycle 1]: 0.00015573, [4] [d_1]: 0.00011655 [none_parameter_eliminate]: 1.89e-06 [renormalize]: 3.10014e-07 [switch_simplify]: 1.333e-05 [partial_unused_args_eliminate]: 2.07999e-06 [add_recomputation]: 0.00015478 [cse_after_recomputation]: 5.042e-05, [1] [Cycle 1]: 4.334e-05, [1] [cse]: 3.608e-05 [environ_conv]: 1.341e-05 [swap_dp_allreduce_reducescatter]: 1.029e-05 [bias_add_comm_swap]: 3.06999e-06 [label_micro_interleaved_index]: 5.42001e-06 [label_fine_grained_interleaved_index]: 3.07002e-06 [merge_cast_opt]: 1.45999e-06 [slice_recompute_activation]: 1.99999e-06 [micro_interleaved_order_control]: 2.59001e-06 [assign_add_opt]: 1.24998e-06 [ForceFp32Comm]: 9.09989e-07 [remove_cast_before_assign_add]: 1.38002e-06 [full_micro_interleaved_order_control]: 2.46e-06 [reorder_send_recv_between_fp_bp]: 2.63e-06 [comm_op_add_attrs]: 1.24e-06 [add_comm_op_reuse_tag]: 1.00999e-06 [interleave_split_concat_branches]: 1.20999e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 1.25001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.87001e-06 [control_data_broadcast_order]: 2.281e-05 [grouped_pairwise_exchange_alltoall]: 1.59998e-06 [offloading_packed_experts]: 8.05e-06 [overlap_recompute_and_grad_model_parallel]: 8.07e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.21002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37999e-06 [overlap_recompute_comm]: 2.21998e-06 [overlap_grad_ring_attention]: 6.04999e-06 [overlap_grad_flash_sp]: 3.104e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.39001e-06 [split_layernorm_comm]: 1.97001e-06 [handle_group_info]: 1.40999e-06 [symbol_engine_optimizer]: 0.00042963, [1] [Cycle 1]: 0.00042329, [6] [build]: 0.00026725 [elim_shapecalc]: 2.444e-05 [elim_not_effective]: 3.077e-05 [opt_reshape]: 1.707e-05 [fold_const_symbol]: 3.709e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.95998e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 3.232e-05 [get_jit_bprop_graph]: 4.50001e-06 [rewriter_after_jit_bprop_graph]: 5.93998e-06 [opt_after_jit_grad]: 0.00066708 [validate]: 8.808e-05 Sums bootstrap : 0.000793s : 0.04% type_inference : 1.965919s : 98.30% event_method : 0.000028s : 0.00% auto_monad : 0.000096s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000006s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000040s : 0.00% optimize.rewriter_before_opt_a : 0.000100s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001677s : 0.08% optimize.opt_a.with_stream_mark : 0.000064s : 0.00% optimize.opt_a.recompute_prepare : 0.000034s : 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 : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000398s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000031s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000044s : 0.00% optimize.opt_a.flash_sp : 0.000016s : 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 : 0.000033s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.00% optimize.opt_a.virtual_dataset : 0.000027s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000029s : 0.00% optimize.opt_a.virtual_output : 0.000026s : 0.00% optimize.opt_a.merge_forward : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000056s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000048s : 0.00% 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 : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000037s : 0.00% optimize.opt_a.a_after_grad : 0.000045s : 0.00% optimize.opt_a.renormalize : 0.024675s : 1.23% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000055s : 0.00% optimize.opt_a.cse : 0.000961s : 0.05% optimize.opt_a.a_3 : 0.000190s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000288s : 0.01% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000854s : 0.04% optimize.opt_b.b_1 : 0.000295s : 0.01% optimize.opt_b.b_2 : 0.000015s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000052s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000036s : 0.00% optimize.loop_unroll : 0.000527s : 0.03% optimize.opt_after_cconv.c_1 : 0.000058s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000041s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000065s : 0.00% optimize.tuple_transform.d_1 : 0.000117s : 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 : 0.000155s : 0.01% optimize.cse_after_recomputation.cse : 0.000036s : 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 : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000267s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000037s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000032s : 0.00% get_jit_bprop_graph : 0.000005s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000667s : 0.03% validate : 0.000088s : 0.00% Time group info: ------[substitution.] 0.000614 111 13.55% : 0.000083s : 6: substitution.arithmetic_simplify 0.98% : 0.000006s : 6: substitution.elim_not_effective 2.14% : 0.000013s : 6: substitution.float_tuple_getitem_switch 3.16% : 0.000019s : 6: substitution.fold_const_symbol 1.50% : 0.000009s : 8: substitution.graph_param_transform 43.59% : 0.000267s : 5: substitution.inline 1.65% : 0.000010s : 12: substitution.j_node_and_user_rematch 1.85% : 0.000011s : 4: substitution.minmaximum_grad 1.63% : 0.000010s : 12: substitution.remove_not_recompute_node 0.92% : 0.000006s : 2: substitution.replace_old_param 8.70% : 0.000053s : 8: substitution.tuple_list_convert_item_index_to_positive 2.86% : 0.000018s : 8: substitution.tuple_list_get_item_const_eliminator 4.09% : 0.000025s : 8: substitution.tuple_list_get_item_depend_reorder 9.54% : 0.000059s : 12: substitution.tuple_list_get_item_eliminator 3.82% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.965715 2 99.68% : 1.959521s : 1: type_inference.infer 0.32% : 0.006194s : 1: type_inference.specialize ------[replace.] 0.000056 5 100.00% : 0.000056s : 5: replace.inline ------[match.] 0.000263 5 100.00% : 0.000263s : 5: match.inline ------[predicate.] 0.000373 2113 0.91% : 0.000003s : 21: predicate.accumulaten_eliminater 1.18% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.62% : 0.000002s : 16: predicate.addn_check_dump 0.96% : 0.000004s : 21: predicate.addn_zero_filter 0.77% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.73% : 0.000010s : 37: predicate.arithmetic_simplify 0.97% : 0.000004s : 21: predicate.cast_eliminate 0.78% : 0.000003s : 16: predicate.check_bprop_eliminate 0.64% : 0.000002s : 16: predicate.compare_switch_simplify 0.19% : 0.000001s : 8: predicate.const_output_eliminate 0.69% : 0.000003s : 16: predicate.depend_value_elim 0.98% : 0.000004s : 21: predicate.dict_get_item_const_eliminator 1.07% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.90% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.33% : 0.000005s : 16: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 8: predicate.elim_not_effective 0.56% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.22% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.04% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.01% : 0.000004s : 29: predicate.environ_get_depend_swap 1.64% : 0.000006s : 45: predicate.environ_get_eliminate 1.14% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.06% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.61% : 0.000006s : 26: predicate.float_depend_g_call 0.75% : 0.000003s : 16: predicate.float_environ_get_switch 1.19% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 8: predicate.fold_const_symbol 0.77% : 0.000003s : 16: predicate.get_grad_eliminate 0.21% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000003s : 16: predicate.incorporate_call 0.54% : 0.000002s : 16: predicate.incorporate_call_switch 5.39% : 0.000020s : 95: predicate.inline 1.08% : 0.000004s : 16: predicate.inline_without_move 0.32% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.04% : 0.000004s : 16: predicate.less_batch_normalization 1.57% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.23% : 0.000008s : 58: predicate.load_eliminater 1.22% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.42% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.98% : 0.000007s : 37: predicate.make_slice_get_slice_eliminator 0.66% : 0.000002s : 16: predicate.merge_addn 0.75% : 0.000003s : 16: predicate.micro_step_allgather_replace 0.64% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.79% : 0.000003s : 21: predicate.minmaximum_grad 1.47% : 0.000005s : 8: predicate.mutable_eliminate 0.49% : 0.000002s : 8: predicate.opt_reshape 0.53% : 0.000002s : 8: predicate.parallel_virtual_node 1.43% : 0.000005s : 26: predicate.partial_defer_inline 1.14% : 0.000004s : 29: predicate.partial_eliminate 0.98% : 0.000004s : 21: predicate.print_const_string_wrapper 0.71% : 0.000003s : 16: predicate.reduce_all_const_elim 1.24% : 0.000005s : 21: predicate.reduce_eliminate 2.18% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 16: predicate.remove_not_recompute_node 1.12% : 0.000004s : 37: predicate.replace_applicator 0.45% : 0.000002s : 16: predicate.replace_old_param 0.27% : 0.000001s : 8: predicate.reset_defer_inline 0.87% : 0.000003s : 21: predicate.reshape_eliminate 0.70% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.56% : 0.000002s : 8: predicate.row_tensor_eliminate 1.07% : 0.000004s : 16: predicate.same_eliminate 0.41% : 0.000002s : 16: predicate.set_cell_output_no_recompute 1.09% : 0.000004s : 16: predicate.shard_identity_eliminate 0.88% : 0.000003s : 16: predicate.special_op_eliminate 0.69% : 0.000003s : 16: predicate.specialize_transform 1.21% : 0.000005s : 16: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000004s : 16: predicate.stack_unstack_eliminate 0.33% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.22% : 0.000005s : 26: predicate.switch_defer_inline 1.84% : 0.000007s : 42: predicate.switch_layer_defer_inline 3.88% : 0.000014s : 86: predicate.switch_simplify 0.95% : 0.000004s : 21: predicate.tile_eliminate 0.86% : 0.000003s : 21: predicate.transpose_eliminate 1.75% : 0.000007s : 37: predicate.tuple_list_convert_item_index_to_positive 2.10% : 0.000008s : 37: predicate.tuple_list_get_item_const_eliminator 1.54% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.29% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.81% : 0.000007s : 37: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.50% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.21% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 2.93% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.40% : 0.000001s : 8: predicate.value_based_eliminate 0.82% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.83% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.100198 32 97.12% : 0.097308s : 25: func_graph_cloner_run.FuncGraphClonerGraph 2.88% : 0.002889s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.534198 192 0.00% : 0.000004s : 1: ForceFp32Comm 9.31% : 0.235946s : 1: add_attr 9.31% : 0.235924s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000160s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.00% : 0.000102s : 1: auto_monad 0.00% : 0.000037s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.03% : 0.000837s : 1: bootstrap 0.00% : 0.000040s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000026s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000054s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000011s : 1: detach_backward 0.00% : 0.000017s : 1: environ_conv 0.00% : 0.000037s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000008s : 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% : 0.000009s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000536s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000863s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000026s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.10% : 0.002628s : 78: opt.transform.opt_a 0.00% : 0.000056s : 1: opt.transform.opt_after_cconv 0.00% : 0.000073s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000274s : 28: opt.transform.opt_b 0.01% : 0.000127s : 2: opt.transform.opt_trans_graph 0.00% : 0.000104s : 4: opt.transform.symbol_engine_opt 1.16% : 0.029507s : 1: opt_a 0.01% : 0.000173s : 1: opt_after_cconv 0.03% : 0.000678s : 1: opt_after_jit_grad 0.02% : 0.000439s : 1: opt_b 1.31% : 0.033323s : 1: optimize 0.00% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000012s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000054s : 1: pre_auto_parallel 0.00% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000069s : 1: remove_dup_value 0.84% : 0.021407s : 1: renormalize.infer 0.13% : 0.003248s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000295s : 1: rewriter_after_opt_a 0.00% : 0.000105s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000433s : 1: symbol_engine_optimizer 0.01% : 0.000164s : 1: tuple_transform 77.58% : 1.965956s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape2] tests/st/infer/ops/test_internal_ops/test_swiglu.py::test_swiglu_dyn_shape[shape2],max_mem:102.0M =============================== warnings summary =============================== ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 3 passed, 25 warnings in 209.50s (0:03:29) ==================