==================================================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/compiler/stream_event, configfile: ../../../../../../../sault/virtual_test/virtualenv_005/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 1 item test_with_stream.py TotalTime = 0.810456, [21] [bootstrap]: 0.00066818 [type_inference]: 0.723565 [event_method]: 3.012e-05 [auto_monad]: 0.00014243 [graph_reusing]: 7.47002e-06 [inline]: 2.32001e-06 [add_attr]: 0.0762559, [1] [add_attr_with_inline]: 0.0762392, [1] [Cycle 1]: 0.00012452, [2] [tag_attr]: 3.373e-05 [meta_addattr_fg_expand]: 7.13e-06 [parallel-infer-symbol]: 3.81999e-06 [pre_auto_parallel]: 6.644e-05 [insert-virtual-dataset]: 3.06999e-06 [parallel-infer-symbol-second]: 6.19999e-07 [dataset_repeat_opt]: 2.34001e-06 [pipeline_split]: 1.84998e-06 [optimize]: 0.00885836, [53] [py_interpret_to_execute]: 3.684e-05 [rewriter_before_opt_a]: 0.00012623 [opt_a]: 0.00627072, [3] [Cycle 1]: 0.00408121, [45] [expand_dump_flag]: 4.22e-06 [switch_simplify]: 0.00012063 [loop_unroll]: 3.226e-05 [a_1]: 0.00090589 [with_stream_mark]: 0.00011909 [recompute_prepare]: 2.759e-05 [updatestate_depend_eliminate]: 1.025e-05 [updatestate_assign_eliminate]: 8.27998e-06 [updatestate_loads_eliminate]: 7.47998e-06 [parameter_eliminate]: 4.48001e-06 [a_2]: 0.00042164 [accelerated_algorithm]: 3.547e-05 [shard]: 2.54999e-06 [meta_shard_fg_expand]: 3.83001e-06 [shard_inline]: 1.042e-05 [merge_send_recv]: 1.287e-05 [auto_parallel]: 1.353e-05 [parallel]: 6.037e-05 [flash_sp]: 1.39e-05 [merge_comm]: 7.53999e-06 [allreduce_fusion]: 7.19001e-06 [matmul_add_comm_reduction]: 1.626e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 1.648e-05 [virtual_dataset]: 9.88002e-06 [get_grad_eliminate_]: 1.036e-05 [virtual_output]: 9.75002e-06 [merge_forward]: 6.98998e-06 [cell_reuse_recompute_pass]: 1.27999e-06 [offload_activation]: 1.525e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.354e-05 [merge_recompute_call_nodes]: 1.89e-06 [before_grad]: 1.763e-05 [set_forward_comm_id_for_comm_node_pass]: 7.05e-06 [meta_fg_expand]: 5.62999e-06 [flash_sp_send_recv_attached]: 5.77999e-06 [receive_attached]: 2.73e-06 [after_resolve]: 1.66e-05 [a_after_grad]: 1.526e-05 [renormalize]: 0.00159244 [add_forward_monad_depend]: 1.035e-05 [auto_monad_grad]: 2.99999e-06 [auto_monad_eliminator]: 2.865e-05 [cse]: 6.642e-05 [a_3]: 7.013e-05 [Cycle 2]: 0.0015522, [45] [expand_dump_flag]: 3.11001e-06 [switch_simplify]: 1.099e-05 [loop_unroll]: 7.43e-06 [a_1]: 0.00020755 [with_stream_mark]: 1.688e-05 [recompute_prepare]: 8.73001e-06 [updatestate_depend_eliminate]: 5.84e-06 [updatestate_assign_eliminate]: 4.60999e-06 [updatestate_loads_eliminate]: 4.92999e-06 [parameter_eliminate]: 2.02001e-06 [a_2]: 0.00021641 [accelerated_algorithm]: 1.015e-05 [shard]: 2.22001e-06 [meta_shard_fg_expand]: 2.29001e-06 [shard_inline]: 5.55001e-06 [merge_send_recv]: 8.77e-06 [auto_parallel]: 1.023e-05 [parallel]: 8.84e-06 [flash_sp]: 4.08999e-06 [merge_comm]: 3.43999e-06 [allreduce_fusion]: 3.21999e-06 [matmul_add_comm_reduction]: 1.031e-05 [allreduce_slice_to_reducescatter]: 5.59987e-07 [virtual_shard_identity]: 6.09999e-06 [virtual_dataset]: 5.22e-06 [get_grad_eliminate_]: 5.61003e-06 [virtual_output]: 5.67001e-06 [merge_forward]: 3.71999e-06 [cell_reuse_recompute_pass]: 2.09999e-06 [offload_activation]: 9.19e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.103e-05 [merge_recompute_call_nodes]: 1.58002e-06 [before_grad]: 9.99001e-06 [set_forward_comm_id_for_comm_node_pass]: 3.95e-06 [meta_fg_expand]: 2.48e-06 [flash_sp_send_recv_attached]: 1.83002e-06 [receive_attached]: 2.04e-06 [after_resolve]: 1.084e-05 [a_after_grad]: 7.78999e-06 [renormalize]: 0.00053592 [add_forward_monad_depend]: 5.44e-06 [auto_monad_grad]: 2.14e-06 [auto_monad_eliminator]: 1.265e-05 [cse]: 2.354e-05 [a_3]: 4.028e-05 [Cycle 3]: 0.00061633, [45] [expand_dump_flag]: 1.96e-06 [switch_simplify]: 6.38998e-06 [loop_unroll]: 4.94e-06 [a_1]: 0.00012216 [with_stream_mark]: 9.96e-06 [recompute_prepare]: 5.57001e-06 [updatestate_depend_eliminate]: 3.31001e-06 [updatestate_assign_eliminate]: 2.44999e-06 [updatestate_loads_eliminate]: 2.11e-06 [parameter_eliminate]: 9.70002e-07 [a_2]: 7.659e-05 [accelerated_algorithm]: 9.69999e-06 [shard]: 1.01002e-06 [meta_shard_fg_expand]: 1.37e-06 [shard_inline]: 5.24998e-06 [merge_send_recv]: 5.34e-06 [auto_parallel]: 6.92002e-06 [parallel]: 4.85001e-06 [flash_sp]: 1.04998e-06 [merge_comm]: 3.48e-06 [allreduce_fusion]: 3.14001e-06 [matmul_add_comm_reduction]: 7.08998e-06 [allreduce_slice_to_reducescatter]: 3.19997e-07 [virtual_shard_identity]: 5.79999e-06 [virtual_dataset]: 5.41002e-06 [get_grad_eliminate_]: 5.19e-06 [virtual_output]: 5.06997e-06 [merge_forward]: 3.55003e-06 [cell_reuse_recompute_pass]: 1.34e-06 [offload_activation]: 7.18998e-06 [cell_reuse_handle_not_recompute_node_pass]: 9.44998e-06 [merge_recompute_call_nodes]: 7.09988e-07 [before_grad]: 8.41002e-06 [set_forward_comm_id_for_comm_node_pass]: 3.3e-06 [meta_fg_expand]: 2.40002e-06 [flash_sp_send_recv_attached]: 1.06002e-06 [receive_attached]: 1.17999e-06 [after_resolve]: 8.77e-06 [a_after_grad]: 7.36999e-06 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.33002e-06 [auto_monad_grad]: 1.20999e-06 [auto_monad_eliminator]: 7.16001e-06 [cse]: 1.48e-05 [a_3]: 3.096e-05 [py_interpret_to_execute_after_opt_a]: 1.303e-05 [slice_cell_reuse_recomputed_activation]: 2.30002e-06 [rewriter_after_opt_a]: 7.206e-05 [convert_after_rewriter]: 9.65002e-06 [order_py_execute_after_rewriter]: 5.69e-06 [mutable_eliminate]: 0.00077806 [opt_b]: 0.00020747, [1] [Cycle 1]: 0.00019808, [7] [b_1]: 0.00011445 [b_2]: 8.40001e-06 [updatestate_depend_eliminate]: 8.27998e-06 [updatestate_assign_eliminate]: 2.44999e-06 [updatestate_loads_eliminate]: 2.61e-06 [renormalize]: 7.2e-07 [cse]: 2.41e-05 [optimize_parallel_all_gather_comm]: 1.942e-05 [overlap_param_gather]: 4.67998e-06 [cconv]: 3.178e-05 [loop_unroll]: 0.00047824 [opt_after_cconv]: 0.00010504, [1] [Cycle 1]: 9.839e-05, [7] [c_1]: 2.559e-05 [parameter_eliminate]: 4.38999e-06 [updatestate_depend_eliminate]: 6.89999e-06 [updatestate_assign_eliminate]: 2.64001e-06 [updatestate_loads_eliminate]: 2.33998e-06 [cse]: 2.158e-05 [renormalize]: 6.69999e-07 [remove_dup_value]: 1.847e-05 [tuple_transform]: 7.436e-05, [1] [Cycle 1]: 6.933e-05, [4] [d_1]: 3.981e-05 [none_parameter_eliminate]: 2.64999e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 6.66e-06 [partial_unused_args_eliminate]: 2.29001e-06 [add_recomputation]: 6.189e-05 [cse_after_recomputation]: 2.26e-05, [1] [Cycle 1]: 1.777e-05, [1] [cse]: 1.216e-05 [environ_conv]: 2.079e-05 [swap_dp_allreduce_reducescatter]: 5.56998e-06 [bias_add_comm_swap]: 3.01999e-06 [label_micro_interleaved_index]: 5.43002e-06 [label_fine_grained_interleaved_index]: 2.79001e-06 [merge_cast_opt]: 1.25999e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.81999e-06 [assign_add_opt]: 1.34e-06 [ForceFp32Comm]: 1.00001e-06 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.68e-06 [reorder_send_recv_between_fp_bp]: 3.25e-06 [comm_op_add_attrs]: 1.04e-06 [add_comm_op_reuse_tag]: 1.07998e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.44e-06 [overlap_opt_shard_in_pipeline]: 3.331e-05 [overlap_opt_shard_grad_in_pipeline]: 2.39001e-06 [control_data_broadcast_order]: 1.332e-05 [grouped_pairwise_exchange_alltoall]: 1.78002e-06 [offloading_packed_experts]: 3.73001e-06 [overlap_recompute_and_grad_model_parallel]: 6.41e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.58e-06 [overlap_grad_ring_attention]: 1.627e-05 [overlap_grad_flash_sp]: 3.847e-05 [begin_end_overlap_inline]: 6.30011e-07 [split_matmul_comm_elemetwise]: 2.42001e-06 [split_layernorm_comm]: 2.13002e-06 [handle_group_info]: 1.09e-06 [symbol_engine_optimizer]: 7.565e-05, [1] [Cycle 1]: 7.07e-05, [6] [build]: 3.08e-06 [elim_shapecalc]: 9.68002e-06 [elim_not_effective]: 1.306e-05 [opt_reshape]: 6.63003e-06 [fold_const_symbol]: 8.95999e-06 [renormalize]: 1.80007e-07 [detach_backward]: 2.56998e-06 [pipeline_parallel_scheduler]: 1.50999e-06 [auto_monad_reorder]: 2.604e-05 [get_jit_bprop_graph]: 2.21e-06 [rewriter_after_jit_bprop_graph]: 4.52e-06 [opt_after_jit_grad]: 0.00055772 [validate]: 7.279e-05 Sums bootstrap : 0.000668s : 0.09% type_inference : 0.723565s : 98.73% event_method : 0.000030s : 0.00% auto_monad : 0.000142s : 0.02% graph_reusing : 0.000007s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000034s : 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 : 0.000066s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000037s : 0.01% optimize.rewriter_before_opt_a : 0.000126s : 0.02% optimize.opt_a.expand_dump_flag : 0.000009s : 0.00% optimize.opt_a.switch_simplify : 0.000138s : 0.02% optimize.opt_a.loop_unroll : 0.000045s : 0.01% optimize.opt_a.a_1 : 0.001236s : 0.17% optimize.opt_a.with_stream_mark : 0.000146s : 0.02% optimize.opt_a.recompute_prepare : 0.000042s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.000715s : 0.10% optimize.opt_a.accelerated_algorithm : 0.000055s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000021s : 0.00% optimize.opt_a.merge_send_recv : 0.000027s : 0.00% optimize.opt_a.auto_parallel : 0.000031s : 0.00% optimize.opt_a.parallel : 0.000074s : 0.01% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000014s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000034s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000028s : 0.00% optimize.opt_a.virtual_dataset : 0.000021s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.00% optimize.opt_a.virtual_output : 0.000020s : 0.00% optimize.opt_a.merge_forward : 0.000014s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000032s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000044s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000036s : 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 : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000036s : 0.00% optimize.opt_a.a_after_grad : 0.000030s : 0.00% optimize.opt_a.renormalize : 0.002128s : 0.29% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000048s : 0.01% optimize.opt_a.cse : 0.000105s : 0.01% optimize.opt_a.a_3 : 0.000141s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000013s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000072s : 0.01% optimize.convert_after_rewriter : 0.000010s : 0.00% optimize.order_py_execute_after_rewriter : 0.000006s : 0.00% optimize.mutable_eliminate : 0.000778s : 0.11% optimize.opt_b.b_1 : 0.000114s : 0.02% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000024s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000019s : 0.00% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000032s : 0.00% optimize.loop_unroll : 0.000478s : 0.07% optimize.opt_after_cconv.c_1 : 0.000026s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000022s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.00% optimize.tuple_transform.d_1 : 0.000040s : 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 : 0.000007s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000062s : 0.01% optimize.cse_after_recomputation.cse : 0.000012s : 0.00% optimize.environ_conv : 0.000021s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 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 : 0.000003s : 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 : 0.000033s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 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 : 0.000016s : 0.00% optimize.overlap_grad_flash_sp : 0.000038s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000010s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000013s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000009s : 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 : 0.000026s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000558s : 0.08% validate : 0.000073s : 0.01% Time group info: ------[substitution.] 0.000461 69 33.96% : 0.000156s : 8: substitution.arithmetic_simplify 3.10% : 0.000014s : 6: substitution.depend_value_elim 0.48% : 0.000002s : 2: substitution.elim_not_effective 0.32% : 0.000001s : 2: substitution.fold_const_symbol 1.30% : 0.000006s : 3: substitution.graph_param_transform 44.15% : 0.000203s : 11: substitution.inline 1.49% : 0.000007s : 10: substitution.j_node_and_user_rematch 5.19% : 0.000024s : 3: substitution.less_batch_normalization 0.77% : 0.000004s : 4: substitution.redundant_stop_gradient_eliminater 2.14% : 0.000010s : 10: substitution.remove_not_recompute_node 0.56% : 0.000003s : 2: substitution.replace_applicator 1.53% : 0.000007s : 3: substitution.replace_old_param 1.05% : 0.000005s : 2: substitution.set_cell_output_no_recompute 2.01% : 0.000009s : 2: substitution.specialize_transform 1.94% : 0.000009s : 1: substitution.switch_simplify ------[type_inference.] 0.723476 2 99.79% : 0.721922s : 1: type_inference.infer 0.21% : 0.001554s : 1: type_inference.specialize ------[replace.] 0.000146 10 23.59% : 0.000035s : 2: replace.depend_value_elim 40.90% : 0.000060s : 7: replace.inline 35.52% : 0.000052s : 1: replace.switch_simplify ------[match.] 0.000206 10 1.67% : 0.000003s : 2: match.depend_value_elim 94.47% : 0.000194s : 7: match.inline 3.86% : 0.000008s : 1: match.switch_simplify ------[predicate.] 0.000355 2207 1.19% : 0.000004s : 26: predicate.accumulaten_eliminater 0.43% : 0.000002s : 3: predicate.ad_related_special_op_eliminate 1.16% : 0.000004s : 31: predicate.addn_check_dump 1.02% : 0.000004s : 26: predicate.addn_zero_filter 0.92% : 0.000003s : 26: predicate.adjust_all_reduce_mul_add 3.27% : 0.000012s : 51: predicate.arithmetic_simplify 1.03% : 0.000004s : 26: predicate.cast_eliminate 0.52% : 0.000002s : 11: predicate.check_bprop_eliminate 1.17% : 0.000004s : 31: predicate.compare_switch_simplify 0.07% : 0.000000s : 3: predicate.const_output_eliminate 1.09% : 0.000004s : 26: predicate.depend_value_elim 1.05% : 0.000004s : 26: predicate.dict_get_item_const_eliminator 1.38% : 0.000005s : 26: predicate.dict_get_item_eliminator 1.14% : 0.000004s : 26: predicate.dict_set_item_eliminator 0.46% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.17% : 0.000001s : 3: predicate.elim_not_effective 0.24% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.17% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.02% : 0.000004s : 29: predicate.environ_get_depend_swap 2.23% : 0.000008s : 54: predicate.environ_get_eliminate 1.07% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.19% : 0.000004s : 31: predicate.exchange_switch_depend_value 1.91% : 0.000007s : 31: predicate.float_depend_g_call 1.09% : 0.000004s : 31: predicate.float_environ_get_switch 1.25% : 0.000004s : 34: predicate.float_tuple_getitem_switch 0.07% : 0.000000s : 3: predicate.fold_const_symbol 0.66% : 0.000002s : 13: predicate.get_grad_eliminate 0.09% : 0.000000s : 3: predicate.graph_param_transform 1.06% : 0.000004s : 25: predicate.incorporate_call 0.88% : 0.000003s : 25: predicate.incorporate_call_switch 6.08% : 0.000022s : 105: predicate.inline 0.72% : 0.000003s : 13: predicate.inline_without_move 0.30% : 0.000001s : 13: predicate.j_node_and_user_rematch 1.06% : 0.000004s : 13: predicate.less_batch_normalization 1.55% : 0.000005s : 32: predicate.list_to_tuple_eliminator_ 2.23% : 0.000008s : 58: predicate.load_eliminater 0.51% : 0.000002s : 3: predicate.loop_unroll_after_grad 1.70% : 0.000006s : 42: predicate.loop_unroll_before_grad 1.54% : 0.000005s : 32: predicate.make_slice_get_slice_eliminator 1.16% : 0.000004s : 31: predicate.merge_addn 0.47% : 0.000002s : 11: predicate.micro_step_allgather_replace 0.55% : 0.000002s : 11: predicate.mini_step_allgather_replace 0.99% : 0.000004s : 26: predicate.minmaximum_grad 0.59% : 0.000002s : 3: predicate.mutable_eliminate 0.27% : 0.000001s : 3: predicate.opt_reshape 0.30% : 0.000001s : 3: predicate.parallel_virtual_node 1.54% : 0.000005s : 31: predicate.partial_defer_inline 1.22% : 0.000004s : 29: predicate.partial_eliminate 1.11% : 0.000004s : 26: predicate.print_const_string_wrapper 0.97% : 0.000003s : 23: predicate.reduce_all_const_elim 1.37% : 0.000005s : 26: predicate.reduce_eliminate 2.34% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.50% : 0.000002s : 13: predicate.remove_not_recompute_node 1.24% : 0.000004s : 37: predicate.replace_applicator 0.52% : 0.000002s : 13: predicate.replace_old_param 0.22% : 0.000001s : 3: predicate.reset_defer_inline 1.04% : 0.000004s : 26: predicate.reshape_eliminate 0.56% : 0.000002s : 11: predicate.row_tensor_add_zeros_like 0.27% : 0.000001s : 3: predicate.row_tensor_eliminate 0.78% : 0.000003s : 11: predicate.same_eliminate 0.55% : 0.000002s : 21: predicate.set_cell_output_no_recompute 1.54% : 0.000005s : 13: predicate.shard_identity_eliminate 0.33% : 0.000001s : 6: predicate.special_op_eliminate 1.55% : 0.000005s : 31: predicate.specialize_transform 0.88% : 0.000003s : 11: predicate.split_environ_get_set_with_tuple_value 0.85% : 0.000003s : 13: predicate.stack_unstack_eliminate 0.17% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.28% : 0.000005s : 31: predicate.switch_defer_inline 1.81% : 0.000006s : 42: predicate.switch_layer_defer_inline 4.77% : 0.000017s : 109: predicate.switch_simplify 0.98% : 0.000003s : 26: predicate.tile_eliminate 1.14% : 0.000004s : 26: predicate.transpose_eliminate 1.35% : 0.000005s : 32: predicate.tuple_list_convert_item_index_to_positive 1.38% : 0.000005s : 32: predicate.tuple_list_get_item_const_eliminator 1.28% : 0.000005s : 32: predicate.tuple_list_get_item_depend_reorder 2.86% : 0.000010s : 57: predicate.tuple_list_get_item_eliminator 1.28% : 0.000005s : 32: predicate.tuple_list_get_set_item_eliminator 2.44% : 0.000009s : 57: predicate.tuple_list_set_item_eliminator 1.28% : 0.000005s : 32: predicate.tuple_to_list_eliminator_ 2.19% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 3.30% : 0.000012s : 83: predicate.updatestate_useless_node_eliminater 0.20% : 0.000001s : 3: predicate.value_based_eliminate 0.58% : 0.000002s : 13: predicate.virtual_dataset_eliminate 0.80% : 0.000003s : 13: predicate.virtual_output_eliminate 0.11% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.23% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001081 14 38.26% : 0.000413s : 4: func_graph_cloner_run.FuncGraphClonerGraph 61.74% : 0.000667s : 10: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.900212 267 0.00% : 0.000006s : 1: ForceFp32Comm 8.47% : 0.076263s : 1: add_attr 8.47% : 0.076245s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000067s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000149s : 1: auto_monad 0.00% : 0.000030s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.08% : 0.000705s : 1: bootstrap 0.00% : 0.000036s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000013s : 1: convert_after_rewriter 0.00% : 0.000026s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000025s : 1: environ_conv 0.00% : 0.000038s : 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% : 0.000005s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.05% : 0.000490s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.09% : 0.000789s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000014s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000017s : 1: opt.transform.mutable_eliminate 0.27% : 0.002453s : 151: opt.transform.opt_a 0.00% : 0.000024s : 1: opt.transform.opt_after_cconv 0.00% : 0.000023s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000094s : 28: opt.transform.opt_b 0.00% : 0.000044s : 2: opt.transform.opt_trans_graph 0.00% : 0.000035s : 4: opt.transform.symbol_engine_opt 0.70% : 0.006275s : 1: opt_a 0.01% : 0.000109s : 1: opt_after_cconv 0.06% : 0.000568s : 1: opt_after_jit_grad 0.02% : 0.000211s : 1: opt_b 0.98% : 0.008864s : 1: optimize 0.00% : 0.000023s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.00% : 0.000042s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000020s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000039s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000071s : 1: pre_auto_parallel 0.00% : 0.000041s : 1: py_interpret_to_execute 0.00% : 0.000017s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000023s : 1: remove_dup_value 0.14% : 0.001225s : 2: renormalize.infer 0.10% : 0.000884s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000077s : 1: rewriter_after_opt_a 0.01% : 0.000131s : 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% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000078s : 1: symbol_engine_optimizer 0.01% : 0.000077s : 1: tuple_transform 80.38% : 0.723592s : 1: type_inference TotalTime = 1.62389, [21] [bootstrap]: 0.00348494 [type_inference]: 1.40547 [event_method]: 1.777e-05 [auto_monad]: 0.00014518 [graph_reusing]: 6.34999e-06 [inline]: 2.88e-06 [add_attr]: 0.203328, [1] [add_attr_with_inline]: 0.203299, [1] [Cycle 1]: 0.00012427, [2] [tag_attr]: 2.362e-05 [meta_addattr_fg_expand]: 5.76e-06 [parallel-infer-symbol]: 3.95e-06 [pre_auto_parallel]: 0.00013428 [insert-virtual-dataset]: 3.15998e-06 [parallel-infer-symbol-second]: 1.00999e-06 [dataset_repeat_opt]: 2.56e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.010457, [53] [py_interpret_to_execute]: 3.16e-05 [rewriter_before_opt_a]: 0.00080381 [opt_a]: 0.00430461, [2] [Cycle 1]: 0.00367154, [45] [expand_dump_flag]: 3.21001e-06 [switch_simplify]: 0.00012907 [loop_unroll]: 2.334e-05 [a_1]: 0.00059996 [with_stream_mark]: 1.74e-05 [recompute_prepare]: 8.04997e-06 [updatestate_depend_eliminate]: 4.17e-06 [updatestate_assign_eliminate]: 3.34001e-06 [updatestate_loads_eliminate]: 3.66001e-06 [parameter_eliminate]: 2.14999e-06 [a_2]: 8.726e-05 [accelerated_algorithm]: 1.871e-05 [shard]: 2.20002e-06 [meta_shard_fg_expand]: 1.97001e-06 [shard_inline]: 6.24001e-06 [merge_send_recv]: 8.62998e-06 [auto_parallel]: 6.58e-06 [parallel]: 0.00032238 [flash_sp]: 8.23999e-06 [merge_comm]: 5.40999e-06 [allreduce_fusion]: 3.37002e-06 [matmul_add_comm_reduction]: 1.223e-05 [allreduce_slice_to_reducescatter]: 6.29982e-07 [virtual_shard_identity]: 3.858e-05 [virtual_dataset]: 6.40002e-06 [get_grad_eliminate_]: 6.09001e-06 [virtual_output]: 6.16e-06 [merge_forward]: 4.25999e-06 [cell_reuse_recompute_pass]: 1.27e-06 [offload_activation]: 1.144e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.288e-05 [merge_recompute_call_nodes]: 1.69e-06 [before_grad]: 1.151e-05 [set_forward_comm_id_for_comm_node_pass]: 3.66001e-06 [meta_fg_expand]: 2.83003e-06 [flash_sp_send_recv_attached]: 4.60001e-06 [receive_attached]: 2.46e-06 [after_resolve]: 1.094e-05 [a_after_grad]: 8.85001e-06 [renormalize]: 0.00187265 [add_forward_monad_depend]: 6.74001e-06 [auto_monad_grad]: 3.13e-06 [auto_monad_eliminator]: 1.827e-05 [cse]: 3.301e-05 [a_3]: 6.861e-05 [Cycle 2]: 0.00061996, [45] [expand_dump_flag]: 2.07001e-06 [switch_simplify]: 7.31001e-06 [loop_unroll]: 5.12e-06 [a_1]: 0.00012719 [with_stream_mark]: 1.06e-05 [recompute_prepare]: 5.57999e-06 [updatestate_depend_eliminate]: 2.97002e-06 [updatestate_assign_eliminate]: 2.58e-06 [updatestate_loads_eliminate]: 2.54001e-06 [parameter_eliminate]: 1.42e-06 [a_2]: 7.245e-05 [accelerated_algorithm]: 8.62e-06 [shard]: 1.12e-06 [meta_shard_fg_expand]: 1.79e-06 [shard_inline]: 5.65001e-06 [merge_send_recv]: 6.29999e-06 [auto_parallel]: 5.94e-06 [parallel]: 5.47999e-06 [flash_sp]: 3.38999e-06 [merge_comm]: 3.59002e-06 [allreduce_fusion]: 3.04999e-06 [matmul_add_comm_reduction]: 7.01001e-06 [allreduce_slice_to_reducescatter]: 3.19997e-07 [virtual_shard_identity]: 5.82999e-06 [virtual_dataset]: 4.97999e-06 [get_grad_eliminate_]: 4.76002e-06 [virtual_output]: 4.62e-06 [merge_forward]: 3.04001e-06 [cell_reuse_recompute_pass]: 1.62999e-06 [offload_activation]: 7.88001e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.129e-05 [merge_recompute_call_nodes]: 8.10018e-07 [before_grad]: 8.01001e-06 [set_forward_comm_id_for_comm_node_pass]: 3.43e-06 [meta_fg_expand]: 1.91e-06 [flash_sp_send_recv_attached]: 1.57999e-06 [receive_attached]: 1.49e-06 [after_resolve]: 8.97e-06 [a_after_grad]: 7.17002e-06 [renormalize]: 5.9983e-08 [add_forward_monad_depend]: 1.37e-06 [auto_monad_grad]: 8.70001e-07 [auto_monad_eliminator]: 6.93998e-06 [cse]: 1.443e-05 [a_3]: 3.095e-05 [py_interpret_to_execute_after_opt_a]: 1.09e-05 [slice_cell_reuse_recomputed_activation]: 2.11998e-06 [rewriter_after_opt_a]: 0.001035 [convert_after_rewriter]: 0.00105018 [order_py_execute_after_rewriter]: 8.71002e-06 [mutable_eliminate]: 0.00071087 [opt_b]: 0.00031719, [1] [Cycle 1]: 0.00030936, [7] [b_1]: 0.00011946 [b_2]: 8.18999e-06 [updatestate_depend_eliminate]: 6.38e-06 [updatestate_assign_eliminate]: 2.63e-06 [updatestate_loads_eliminate]: 2.44999e-06 [renormalize]: 6.89994e-07 [cse]: 2.468e-05 [optimize_parallel_all_gather_comm]: 5.961e-05 [overlap_param_gather]: 0.0003724 [cconv]: 3.514e-05 [loop_unroll]: 0.00045486 [opt_after_cconv]: 0.00010227, [1] [Cycle 1]: 9.539e-05, [7] [c_1]: 2.614e-05 [parameter_eliminate]: 4.85999e-06 [updatestate_depend_eliminate]: 5.99999e-06 [updatestate_assign_eliminate]: 2.44001e-06 [updatestate_loads_eliminate]: 2.64001e-06 [cse]: 1.897e-05 [renormalize]: 3.69997e-07 [remove_dup_value]: 1.631e-05 [tuple_transform]: 7.094e-05, [1] [Cycle 1]: 6.618e-05, [4] [d_1]: 3.943e-05 [none_parameter_eliminate]: 1.53002e-06 [renormalize]: 1.60013e-07 [switch_simplify]: 6.14001e-06 [partial_unused_args_eliminate]: 1.94e-06 [add_recomputation]: 7.359e-05 [cse_after_recomputation]: 2.335e-05, [1] [Cycle 1]: 1.84e-05, [1] [cse]: 1.288e-05 [environ_conv]: 5.02e-06 [swap_dp_allreduce_reducescatter]: 5.79999e-06 [bias_add_comm_swap]: 3.16001e-06 [label_micro_interleaved_index]: 4.74998e-06 [label_fine_grained_interleaved_index]: 2.61999e-06 [merge_cast_opt]: 1.30999e-06 [slice_recompute_activation]: 2.19001e-06 [micro_interleaved_order_control]: 2.46e-06 [assign_add_opt]: 1.34998e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.13001e-06 [full_micro_interleaved_order_control]: 2.64001e-06 [reorder_send_recv_between_fp_bp]: 3.04999e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.02998e-06 [interleave_split_concat_branches]: 1.19998e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 1.219e-05 [overlap_opt_shard_grad_in_pipeline]: 2.36e-06 [control_data_broadcast_order]: 1.293e-05 [grouped_pairwise_exchange_alltoall]: 2.19999e-06 [offloading_packed_experts]: 4.1e-06 [overlap_recompute_and_grad_model_parallel]: 4.95999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.50001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47999e-06 [overlap_recompute_comm]: 2.36998e-06 [overlap_grad_ring_attention]: 4.72e-06 [overlap_grad_flash_sp]: 0.00052436 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.44999e-06 [split_layernorm_comm]: 1.96e-06 [handle_group_info]: 1.15999e-06 [symbol_engine_optimizer]: 7.769e-05, [1] [Cycle 1]: 7.26e-05, [6] [build]: 3.13e-06 [elim_shapecalc]: 9.40001e-06 [elim_not_effective]: 1.31e-05 [opt_reshape]: 6.83e-06 [fold_const_symbol]: 1.001e-05 [renormalize]: 1.80007e-07 [detach_backward]: 2.64001e-06 [pipeline_parallel_scheduler]: 2.43e-06 [auto_monad_reorder]: 1.82e-05 [get_jit_bprop_graph]: 2.24001e-06 [rewriter_after_jit_bprop_graph]: 4.66997e-06 [opt_after_jit_grad]: 0.00047649 [validate]: 4.076e-05 Sums bootstrap : 0.003485s : 0.25% type_inference : 1.405475s : 99.03% event_method : 0.000018s : 0.00% auto_monad : 0.000145s : 0.01% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000134s : 0.01% 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 : 0.000032s : 0.00% optimize.rewriter_before_opt_a : 0.000804s : 0.06% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000136s : 0.01% optimize.opt_a.loop_unroll : 0.000028s : 0.00% optimize.opt_a.a_1 : 0.000727s : 0.05% optimize.opt_a.with_stream_mark : 0.000028s : 0.00% optimize.opt_a.recompute_prepare : 0.000014s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000160s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000027s : 0.00% optimize.opt_a.shard : 0.000003s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.00% optimize.opt_a.merge_send_recv : 0.000015s : 0.00% optimize.opt_a.auto_parallel : 0.000013s : 0.00% optimize.opt_a.parallel : 0.000328s : 0.02% optimize.opt_a.flash_sp : 0.000012s : 0.00% optimize.opt_a.merge_comm : 0.000009s : 0.00% optimize.opt_a.allreduce_fusion : 0.000006s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000019s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000044s : 0.00% optimize.opt_a.virtual_dataset : 0.000011s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000011s : 0.00% optimize.opt_a.virtual_output : 0.000011s : 0.00% optimize.opt_a.merge_forward : 0.000007s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000019s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000024s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000020s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000007s : 0.00% optimize.opt_a.meta_fg_expand : 0.000005s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000020s : 0.00% optimize.opt_a.a_after_grad : 0.000016s : 0.00% optimize.opt_a.renormalize : 0.001873s : 0.13% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000025s : 0.00% optimize.opt_a.cse : 0.000047s : 0.00% optimize.opt_a.a_3 : 0.000100s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000011s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001035s : 0.07% optimize.convert_after_rewriter : 0.001050s : 0.07% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000711s : 0.05% optimize.opt_b.b_1 : 0.000119s : 0.01% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000025s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000060s : 0.00% optimize.overlap_param_gather : 0.000372s : 0.03% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000455s : 0.03% optimize.opt_after_cconv.c_1 : 0.000026s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000019s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000016s : 0.00% optimize.tuple_transform.d_1 : 0.000039s : 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 : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000074s : 0.01% optimize.cse_after_recomputation.cse : 0.000013s : 0.00% optimize.environ_conv : 0.000005s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 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 : 0.000012s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000524s : 0.04% 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 : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000009s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000013s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 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 : 0.000018s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000476s : 0.03% validate : 0.000041s : 0.00% Time group info: ------[substitution.] 0.000276 29 29.45% : 0.000081s : 4: substitution.arithmetic_simplify 0.74% : 0.000002s : 2: substitution.elim_not_effective 0.68% : 0.000002s : 2: substitution.fold_const_symbol 2.19% : 0.000006s : 3: substitution.graph_param_transform 54.95% : 0.000152s : 5: substitution.inline 1.31% : 0.000004s : 4: substitution.j_node_and_user_rematch 4.15% : 0.000011s : 2: substitution.less_batch_normalization 2.15% : 0.000006s : 4: substitution.remove_not_recompute_node 1.40% : 0.000004s : 2: substitution.replace_old_param 3.00% : 0.000008s : 1: substitution.switch_simplify ------[type_inference.] 1.405127 2 99.88% : 1.403466s : 1: type_inference.infer 0.12% : 0.001660s : 1: type_inference.specialize ------[replace.] 0.000090 6 43.69% : 0.000039s : 5: replace.inline 56.31% : 0.000051s : 1: replace.switch_simplify ------[match.] 0.000156 6 95.34% : 0.000149s : 5: match.inline 4.66% : 0.000007s : 1: match.switch_simplify ------[predicate.] 0.000210 937 0.70% : 0.000001s : 10: predicate.accumulaten_eliminater 0.64% : 0.000001s : 3: predicate.ad_related_special_op_eliminate 0.41% : 0.000001s : 6: predicate.addn_check_dump 0.67% : 0.000001s : 10: predicate.addn_zero_filter 0.61% : 0.000001s : 10: predicate.adjust_all_reduce_mul_add 2.18% : 0.000005s : 16: predicate.arithmetic_simplify 0.91% : 0.000002s : 10: predicate.cast_eliminate 0.43% : 0.000001s : 6: predicate.check_bprop_eliminate 0.40% : 0.000001s : 6: predicate.compare_switch_simplify 0.14% : 0.000000s : 3: predicate.const_output_eliminate 0.41% : 0.000001s : 6: predicate.depend_value_elim 0.68% : 0.000001s : 10: predicate.dict_get_item_const_eliminator 0.76% : 0.000002s : 10: predicate.dict_get_item_eliminator 0.71% : 0.000001s : 10: predicate.dict_set_item_eliminator 0.83% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.18% : 0.000000s : 3: predicate.elim_not_effective 0.31% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 0.87% : 0.000002s : 13: predicate.environ_add_const_eliminate 0.74% : 0.000002s : 13: predicate.environ_get_add_eliminate 0.84% : 0.000002s : 13: predicate.environ_get_depend_swap 1.59% : 0.000003s : 19: predicate.environ_get_eliminate 0.81% : 0.000002s : 13: predicate.environ_get_set_eliminate 0.94% : 0.000002s : 15: predicate.exchange_switch_depend_value 1.67% : 0.000004s : 15: predicate.float_depend_g_call 0.37% : 0.000001s : 6: predicate.float_environ_get_switch 0.53% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.12% : 0.000000s : 3: predicate.fold_const_symbol 0.48% : 0.000001s : 6: predicate.get_grad_eliminate 0.15% : 0.000000s : 3: predicate.graph_param_transform 0.47% : 0.000001s : 6: predicate.incorporate_call 0.37% : 0.000001s : 6: predicate.incorporate_call_switch 4.63% : 0.000010s : 43: predicate.inline 0.53% : 0.000001s : 6: predicate.inline_without_move 0.26% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.65% : 0.000001s : 6: predicate.less_batch_normalization 1.11% : 0.000002s : 16: predicate.list_to_tuple_eliminator_ 1.61% : 0.000003s : 26: predicate.load_eliminater 0.76% : 0.000002s : 3: predicate.loop_unroll_after_grad 1.71% : 0.000004s : 25: predicate.loop_unroll_before_grad 1.65% : 0.000003s : 16: predicate.make_slice_get_slice_eliminator 0.42% : 0.000001s : 6: predicate.merge_addn 0.50% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.47% : 0.000001s : 6: predicate.mini_step_allgather_replace 0.62% : 0.000001s : 10: predicate.minmaximum_grad 1.20% : 0.000003s : 3: predicate.mutable_eliminate 0.29% : 0.000001s : 3: predicate.opt_reshape 0.52% : 0.000001s : 3: predicate.parallel_virtual_node 1.30% : 0.000003s : 15: predicate.partial_defer_inline 0.93% : 0.000002s : 13: predicate.partial_eliminate 0.82% : 0.000002s : 10: predicate.print_const_string_wrapper 0.50% : 0.000001s : 6: predicate.reduce_all_const_elim 1.00% : 0.000002s : 10: predicate.reduce_eliminate 1.70% : 0.000004s : 26: predicate.redundant_stop_gradient_eliminater 0.65% : 0.000001s : 6: predicate.remove_not_recompute_node 0.90% : 0.000002s : 16: predicate.replace_applicator 0.41% : 0.000001s : 6: predicate.replace_old_param 0.33% : 0.000001s : 3: predicate.reset_defer_inline 0.73% : 0.000002s : 10: predicate.reshape_eliminate 10.86% : 0.000023s : 6: predicate.row_tensor_add_zeros_like 0.31% : 0.000001s : 3: predicate.row_tensor_eliminate 0.68% : 0.000001s : 6: predicate.same_eliminate 0.30% : 0.000001s : 6: predicate.set_cell_output_no_recompute 14.01% : 0.000029s : 6: predicate.shard_identity_eliminate 0.89% : 0.000002s : 6: predicate.special_op_eliminate 0.57% : 0.000001s : 6: predicate.specialize_transform 0.69% : 0.000001s : 6: predicate.split_environ_get_set_with_tuple_value 0.62% : 0.000001s : 6: predicate.stack_unstack_eliminate 0.25% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.04% : 0.000002s : 15: predicate.switch_defer_inline 1.42% : 0.000003s : 21: predicate.switch_layer_defer_inline 3.97% : 0.000008s : 51: predicate.switch_simplify 0.65% : 0.000001s : 10: predicate.tile_eliminate 0.91% : 0.000002s : 10: predicate.transpose_eliminate 1.42% : 0.000003s : 16: predicate.tuple_list_convert_item_index_to_positive 1.11% : 0.000002s : 16: predicate.tuple_list_get_item_const_eliminator 1.01% : 0.000002s : 16: predicate.tuple_list_get_item_depend_reorder 2.43% : 0.000005s : 22: predicate.tuple_list_get_item_eliminator 1.06% : 0.000002s : 16: predicate.tuple_list_get_set_item_eliminator 1.69% : 0.000004s : 22: predicate.tuple_list_set_item_eliminator 1.52% : 0.000003s : 16: predicate.tuple_to_list_eliminator_ 1.51% : 0.000003s : 26: predicate.updatestate_pure_node_eliminater 2.05% : 0.000004s : 32: predicate.updatestate_useless_node_eliminater 0.43% : 0.000001s : 3: predicate.value_based_eliminate 0.49% : 0.000001s : 6: predicate.virtual_dataset_eliminate 0.46% : 0.000001s : 6: predicate.virtual_output_eliminate 0.21% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.30% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001114 11 44.40% : 0.000495s : 4: func_graph_cloner_run.FuncGraphClonerGraph 55.60% : 0.000620s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.840897 192 0.00% : 0.000004s : 1: ForceFp32Comm 11.05% : 0.203334s : 1: add_attr 11.04% : 0.203303s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000077s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000151s : 1: auto_monad 0.00% : 0.000022s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.19% : 0.003520s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000016s : 1: control_data_broadcast_order 0.06% : 0.001058s : 1: convert_after_rewriter 0.00% : 0.000027s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000008s : 1: environ_conv 0.00% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 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 0.03% : 0.000464s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000723s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000012s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000017s : 1: opt.transform.mutable_eliminate 0.07% : 0.001277s : 78: opt.transform.opt_a 0.00% : 0.000025s : 1: opt.transform.opt_after_cconv 0.00% : 0.000022s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000093s : 28: opt.transform.opt_b 0.00% : 0.000043s : 2: opt.transform.opt_trans_graph 0.00% : 0.000036s : 4: opt.transform.symbol_engine_opt 0.23% : 0.004309s : 1: opt_a 0.01% : 0.000106s : 1: opt_after_cconv 0.03% : 0.000486s : 1: opt_after_jit_grad 0.02% : 0.000322s : 1: opt_b 0.57% : 0.010464s : 1: optimize 0.00% : 0.000063s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.03% : 0.000529s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000015s : 1: overlap_opt_shard_in_pipeline 0.02% : 0.000378s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000139s : 1: pre_auto_parallel 0.00% : 0.000036s : 1: py_interpret_to_execute 0.00% : 0.000014s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000020s : 1: remove_dup_value 0.06% : 0.001128s : 1: renormalize.infer 0.04% : 0.000735s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.001042s : 1: rewriter_after_opt_a 0.04% : 0.000810s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000080s : 1: symbol_engine_optimizer 0.00% : 0.000074s : 1: tuple_transform 76.35% : 1.405602s : 1: type_inference TotalTime = 0.552005, [30] [bootstrap]: 0.00030079 [type_inference]: 0.389918 [event_method]: 0.00010295 [auto_monad]: 0.00020925 [graph_reusing]: 9.61e-06 [pre_auto_parallel]: 3.27002e-06 [py_interpret_to_execute]: 5.072e-05 [rewriter_before_opt_a]: 0.00013932 [expand_dump_flag]: 3.75998e-06 [jit_opt_a]: 0.158103, [2] [Cycle 1]: 0.152283, [27] [switch_simplify]: 0.00018595 [loop_unroll]: 5.42e-05 [a_1]: 0.00118154 [with_stream_mark]: 3.931e-05 [recompute_prepare]: 2.503e-05 [updatestate_depend_eliminate]: 9.73998e-06 [updatestate_assign_eliminate]: 7.45e-06 [updatestate_loads_eliminate]: 6.77002e-06 [parameter_eliminate]: 3.56999e-06 [specialize_transform]: 1.493e-05 [updatestate_useless_node_eliminater]: 1.407e-05 [accelerated_algorithm]: 2.748e-05 [meta_shard_fg_expand]: 4.55999e-06 [get_grad_eliminate_]: 1.347e-05 [merge_forward]: 9.88002e-06 [cell_reuse_recompute_pass]: 1.02e-06 [cell_reuse_handle_not_recompute_node_pass]: 2.955e-05 [j_node_and_user_rematch]: 3.908e-05 [meta_fg_expand]: 0.126409 [replace_old_param]: 8.437e-05 [inline_without_move]: 6.835e-05 [renormalize]: 0.0236447 [add_forward_monad_depend]: 1.697e-05 [auto_monad_grad]: 3.28998e-06 [auto_monad_eliminator]: 1.832e-05 [cse]: 3.382e-05 [replace_applicator]: 2.514e-05 [Cycle 2]: 0.00056675, [27] [switch_simplify]: 6.27001e-06 [loop_unroll]: 5.14e-06 [a_1]: 6.686e-05 [with_stream_mark]: 1.798e-05 [recompute_prepare]: 4.75999e-06 [updatestate_depend_eliminate]: 3.81999e-06 [updatestate_assign_eliminate]: 2.91e-06 [updatestate_loads_eliminate]: 2.56e-06 [parameter_eliminate]: 1.92001e-06 [specialize_transform]: 4.68999e-06 [updatestate_useless_node_eliminater]: 4.22e-06 [accelerated_algorithm]: 4.72e-06 [meta_shard_fg_expand]: 2.41998e-06 [get_grad_eliminate_]: 4.12998e-06 [merge_forward]: 4.59002e-06 [cell_reuse_recompute_pass]: 3.08e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.823e-05 [j_node_and_user_rematch]: 7.56001e-06 [meta_fg_expand]: 0.00021734 [replace_old_param]: 8.40999e-06 [inline_without_move]: 4.63999e-06 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 2.76e-06 [auto_monad_grad]: 1.80001e-06 [auto_monad_eliminator]: 7.7e-06 [cse]: 1.533e-05 [replace_applicator]: 4.84e-06 [py_interpret_to_execute_after_opt_a]: 1.628e-05 [rewriter_after_opt_a]: 4.016e-05 [convert_after_rewriter]: 6.53e-06 [order_py_execute_after_rewriter]: 4.97999e-06 [mutable_eliminate]: 0.00075018 [jit_opt_b]: 5.185e-05, [1] [Cycle 1]: 4.273e-05, [2] [frontend_op_eliminate]: 1.312e-05 [inline_after_opt_a]: 1.492e-05 [cconv]: 3.526e-05 [loop_unroll]: 0.00049686 [jit_opt_after_cconv]: 0.00019779, [1] [Cycle 1]: 0.00014699, [11] [c_1]: 1.698e-05 [parameter_eliminate]: 5.54e-06 [updatestate_depend_eliminate]: 7.75998e-06 [updatestate_assign_eliminate]: 1.99999e-06 [updatestate_loads_eliminate]: 2.10002e-06 [cse]: 2.68e-05 [call_graph_tuple_transform]: 1.901e-05 [tuple_list_get_item_eliminator]: 3.88999e-06 [none_parameter_eliminate]: 1.57999e-06 [renormalize]: 6.30011e-07 [switch_simplify]: 4.12e-06 [remove_dup_value]: 1.798e-05 [partial_unused_args_eliminate]: 2.99999e-06 [environ_conv]: 6.56e-06 [add_recomputation]: 4.696e-05 [cse_after_recomputation]: 2.447e-05, [1] [Cycle 1]: 1.787e-05, [1] [cse]: 9.22999e-06 [auto_monad_reorder]: 1.74e-05 [get_jit_bprop_graph]: 2.34001e-06 [rewriter_after_jit_bprop_graph]: 0.00031103 [opt_after_jit_grad]: 0.00058846 [symbol_engine_optimizer]: 7.928e-05, [1] [Cycle 1]: 7.129e-05, [6] [build]: 4.43999e-06 [elim_shapecalc]: 6.52001e-06 [elim_not_effective]: 1.51e-05 [opt_reshape]: 5.04e-06 [fold_const_symbol]: 7.75998e-06 [renormalize]: 8.70001e-07 [validate]: 4.277e-05 Sums bootstrap : 0.000301s : 0.06% type_inference : 0.389918s : 71.45% event_method : 0.000103s : 0.02% auto_monad : 0.000209s : 0.04% graph_reusing : 0.000010s : 0.00% pre_auto_parallel : 0.000003s : 0.00% py_interpret_to_execute : 0.000051s : 0.01% rewriter_before_opt_a : 0.000139s : 0.03% expand_dump_flag : 0.000004s : 0.00% jit_opt_a.switch_simplify : 0.000192s : 0.04% jit_opt_a.loop_unroll : 0.000059s : 0.01% jit_opt_a.a_1 : 0.001248s : 0.23% jit_opt_a.with_stream_mark : 0.000057s : 0.01% jit_opt_a.recompute_prepare : 0.000030s : 0.01% jit_opt_a.updatestate_depend_eliminate : 0.000014s : 0.00% jit_opt_a.updatestate_assign_eliminate : 0.000010s : 0.00% jit_opt_a.updatestate_loads_eliminate : 0.000009s : 0.00% jit_opt_a.parameter_eliminate : 0.000005s : 0.00% jit_opt_a.specialize_transform : 0.000020s : 0.00% jit_opt_a.updatestate_useless_node_eliminater : 0.000018s : 0.00% jit_opt_a.accelerated_algorithm : 0.000032s : 0.01% jit_opt_a.meta_shard_fg_expand : 0.000007s : 0.00% jit_opt_a.get_grad_eliminate_ : 0.000018s : 0.00% jit_opt_a.merge_forward : 0.000014s : 0.00% jit_opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% jit_opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.01% jit_opt_a.j_node_and_user_rematch : 0.000047s : 0.01% jit_opt_a.meta_fg_expand : 0.126626s : 23.20% jit_opt_a.replace_old_param : 0.000093s : 0.02% jit_opt_a.inline_without_move : 0.000073s : 0.01% jit_opt_a.renormalize : 0.023645s : 4.33% jit_opt_a.add_forward_monad_depend : 0.000020s : 0.00% jit_opt_a.auto_monad_grad : 0.000005s : 0.00% jit_opt_a.auto_monad_eliminator : 0.000026s : 0.00% jit_opt_a.cse : 0.000049s : 0.01% jit_opt_a.replace_applicator : 0.000030s : 0.01% py_interpret_to_execute_after_opt_a : 0.000016s : 0.00% rewriter_after_opt_a : 0.000040s : 0.01% convert_after_rewriter : 0.000007s : 0.00% order_py_execute_after_rewriter : 0.000005s : 0.00% mutable_eliminate : 0.000750s : 0.14% jit_opt_b.frontend_op_eliminate : 0.000013s : 0.00% jit_opt_b.inline_after_opt_a : 0.000015s : 0.00% cconv : 0.000035s : 0.01% loop_unroll : 0.000497s : 0.09% jit_opt_after_cconv.c_1 : 0.000017s : 0.00% jit_opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% jit_opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% jit_opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% jit_opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% jit_opt_after_cconv.cse : 0.000027s : 0.00% jit_opt_after_cconv.call_graph_tuple_transform : 0.000019s : 0.00% jit_opt_after_cconv.tuple_list_get_item_eliminator : 0.000004s : 0.00% jit_opt_after_cconv.none_parameter_eliminate : 0.000002s : 0.00% jit_opt_after_cconv.renormalize : 0.000001s : 0.00% jit_opt_after_cconv.switch_simplify : 0.000004s : 0.00% remove_dup_value : 0.000018s : 0.00% partial_unused_args_eliminate : 0.000003s : 0.00% environ_conv : 0.000007s : 0.00% add_recomputation : 0.000047s : 0.01% cse_after_recomputation.cse : 0.000009s : 0.00% auto_monad_reorder : 0.000017s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000311s : 0.06% opt_after_jit_grad : 0.000588s : 0.11% symbol_engine_optimizer.build : 0.000004s : 0.00% symbol_engine_optimizer.elim_shapecalc : 0.000007s : 0.00% symbol_engine_optimizer.elim_not_effective : 0.000015s : 0.00% symbol_engine_optimizer.opt_reshape : 0.000005s : 0.00% symbol_engine_optimizer.fold_const_symbol : 0.000008s : 0.00% symbol_engine_optimizer.renormalize : 0.000001s : 0.00% validate : 0.000043s : 0.01% Time group info: ------[substitution.] 0.000465 59 10.89% : 0.000051s : 1: substitution.arithmetic_simplify 0.63% : 0.000003s : 1: substitution.elim_not_effective 0.25% : 0.000001s : 1: substitution.fold_const_symbol 1.17% : 0.000005s : 1: substitution.graph_param_transform 55.27% : 0.000257s : 10: substitution.inline 5.71% : 0.000027s : 2: substitution.inline_without_move 4.39% : 0.000020s : 9: substitution.j_node_and_user_rematch 2.25% : 0.000010s : 1: substitution.less_batch_normalization 0.87% : 0.000004s : 2: substitution.minmaximum_grad 4.02% : 0.000019s : 3: substitution.partial_eliminate 1.66% : 0.000008s : 9: substitution.remove_not_recompute_node 1.45% : 0.000007s : 2: substitution.replace_applicator 1.58% : 0.000007s : 7: substitution.replace_old_param 0.97% : 0.000005s : 1: substitution.set_cell_output_no_recompute 2.08% : 0.000010s : 1: substitution.switch_simplify 1.63% : 0.000008s : 2: substitution.tuple_list_convert_item_index_to_positive 1.13% : 0.000005s : 2: substitution.tuple_list_get_item_depend_reorder 4.03% : 0.000019s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.389792 2 99.35% : 0.387256s : 1: type_inference.infer 0.65% : 0.002537s : 1: type_inference.specialize ------[replace.] 0.000159 13 52.08% : 0.000083s : 10: replace.inline 37.18% : 0.000059s : 1: replace.switch_simplify 10.74% : 0.000017s : 2: replace.tuple_list_get_item_eliminator ------[match.] 0.000273 13 91.98% : 0.000251s : 10: match.inline 3.31% : 0.000009s : 1: match.switch_simplify 4.71% : 0.000013s : 2: match.tuple_list_get_item_eliminator ------[predicate.] 0.000228 1295 1.37% : 0.000003s : 21: predicate.accumulaten_eliminater 0.83% : 0.000002s : 1: predicate.ad_related_special_op_eliminate 1.32% : 0.000003s : 21: predicate.addn_check_dump 1.40% : 0.000003s : 21: predicate.addn_zero_filter 2.03% : 0.000005s : 21: predicate.arithmetic_simplify 1.59% : 0.000004s : 21: predicate.cast_eliminate 0.17% : 0.000000s : 1: predicate.check_bprop_eliminate 1.16% : 0.000003s : 21: predicate.compare_switch_simplify 1.17% : 0.000003s : 21: predicate.depend_value_elim 1.20% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.67% : 0.000004s : 21: predicate.dict_get_item_eliminator 1.30% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.81% : 0.000002s : 1: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 1: predicate.elim_not_effective 0.21% : 0.000000s : 1: predicate.elim_shapecalc_of_broadcastargs 1.26% : 0.000003s : 21: predicate.environ_add_const_eliminate 1.15% : 0.000003s : 21: predicate.environ_get_add_eliminate 1.17% : 0.000003s : 21: predicate.environ_get_depend_swap 1.30% : 0.000003s : 21: predicate.environ_get_eliminate 1.17% : 0.000003s : 21: predicate.environ_get_set_eliminate 0.04% : 0.000000s : 1: predicate.fold_const_symbol 0.94% : 0.000002s : 12: predicate.get_grad_eliminate 0.18% : 0.000000s : 1: predicate.graph_param_transform 5.05% : 0.000011s : 35: predicate.inline 3.07% : 0.000007s : 36: predicate.inline_without_move 0.40% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.34% : 0.000003s : 12: predicate.less_batch_normalization 1.43% : 0.000003s : 23: predicate.list_to_tuple_eliminator_ 1.61% : 0.000004s : 24: predicate.load_eliminater 1.08% : 0.000002s : 1: predicate.loop_unroll_after_grad 3.81% : 0.000009s : 59: predicate.loop_unroll_before_grad 1.58% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 1.17% : 0.000003s : 21: predicate.merge_addn 1.19% : 0.000003s : 21: predicate.minmaximum_grad 1.38% : 0.000003s : 1: predicate.mutable_eliminate 0.28% : 0.000001s : 1: predicate.opt_reshape 1.93% : 0.000004s : 24: predicate.partial_eliminate 1.30% : 0.000003s : 21: predicate.print_const_string_wrapper 1.75% : 0.000004s : 21: predicate.reduce_eliminate 1.51% : 0.000003s : 23: predicate.redundant_stop_gradient_eliminater 0.75% : 0.000002s : 12: predicate.remove_not_recompute_node 1.66% : 0.000004s : 25: predicate.replace_applicator 2.02% : 0.000005s : 36: predicate.replace_old_param 0.28% : 0.000001s : 1: predicate.reset_defer_inline 1.34% : 0.000003s : 21: predicate.reshape_eliminate 1.80% : 0.000004s : 21: predicate.row_tensor_add_zeros_like 0.38% : 0.000001s : 1: predicate.row_tensor_eliminate 1.30% : 0.000003s : 21: predicate.same_eliminate 0.59% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.36% : 0.000001s : 2: predicate.special_op_eliminate 1.27% : 0.000003s : 12: predicate.specialize_transform 1.45% : 0.000003s : 21: predicate.split_environ_get_set_with_tuple_value 1.25% : 0.000003s : 21: predicate.stack_unstack_eliminate 0.21% : 0.000000s : 1: predicate.switch_call_monad_eliminater 2.67% : 0.000006s : 33: predicate.switch_defer_inline 2.23% : 0.000005s : 33: predicate.switch_layer_defer_inline 7.68% : 0.000017s : 95: predicate.switch_simplify 1.30% : 0.000003s : 21: predicate.tile_eliminate 1.53% : 0.000003s : 21: predicate.transpose_eliminate 1.92% : 0.000004s : 21: predicate.tuple_list_convert_item_index_to_positive 1.47% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 3.33% : 0.000008s : 25: predicate.tuple_list_get_item_eliminator 1.69% : 0.000004s : 21: predicate.tuple_list_set_item_eliminator 1.58% : 0.000004s : 23: predicate.tuple_to_list_eliminator_ 1.41% : 0.000003s : 24: predicate.updatestate_pure_node_eliminater 2.86% : 0.000007s : 36: predicate.updatestate_useless_node_eliminater 1.70% : 0.000004s : 21: predicate.value_based_eliminate 0.07% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.31% : 0.000001s : 1: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.002594 31 74.29% : 0.001927s : 18: func_graph_cloner_run.FuncGraphClonerGraph 25.71% : 0.000667s : 13: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.577337 72 0.01% : 0.000050s : 1: add_recomputation 0.04% : 0.000217s : 1: auto_monad 0.00% : 0.000020s : 1: auto_monad_reorder 0.06% : 0.000328s : 1: bootstrap 0.01% : 0.000038s : 1: cconv 0.00% : 0.000009s : 1: convert_after_rewriter 0.00% : 0.000027s : 1: cse_after_recomputation 0.00% : 0.000009s : 1: environ_conv 0.02% : 0.000111s : 1: event_method 0.00% : 0.000007s : 1: expand_dump_flag 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 27.39% : 0.158107s : 1: jit_opt_a 0.03% : 0.000201s : 1: jit_opt_after_cconv 0.01% : 0.000055s : 1: jit_opt_b 0.09% : 0.000507s : 1: loop_unroll 0.13% : 0.000762s : 1: mutable_eliminate 0.32% : 0.001861s : 26: opt.transform.jit_opt_a 0.01% : 0.000040s : 4: opt.transform.jit_opt_after_cconv 0.00% : 0.000019s : 4: opt.transform.jit_opt_b 0.00% : 0.000014s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000017s : 1: opt.transform.mutable_eliminate 0.00% : 0.000021s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000031s : 4: opt.transform.symbol_engine_opt 0.10% : 0.000601s : 1: opt_after_jit_grad 0.00% : 0.000007s : 1: order_py_execute_after_rewriter 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pre_auto_parallel 0.01% : 0.000054s : 1: py_interpret_to_execute 0.00% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000021s : 1: remove_dup_value 4.00% : 0.023080s : 1: renormalize.infer 0.10% : 0.000549s : 1: renormalize.specialize 0.05% : 0.000316s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000044s : 1: rewriter_after_opt_a 0.02% : 0.000143s : 1: rewriter_before_opt_a 0.01% : 0.000082s : 1: symbol_engine_optimizer 67.54% : 0.389943s : 1: type_inference . [hook] pytest_runtest_teardown:test_stream_with_control_flow tests/st/compiler/stream_event/test_with_stream.py::test_stream_with_control_flow,max_mem:8.0M =============================== 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 ================== 1 passed, 25 warnings in 124.30s (0:02:04) ==================