==================================================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/ops, configfile: ../../../../../../sault/virtual_test/virtualenv_006/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 2 items test_ops_adaptive_max_pool1d.py . [hook] pytest_runtest_teardown:test_adaptive_max_pool1d[pynative] tests/st/ops/test_ops_adaptive_max_pool1d.py::test_adaptive_max_pool1d[pynative],max_mem:18.0M TotalTime = 2.57426, [21] [bootstrap]: 0.00063714 [type_inference]: 2.32988 [event_method]: 0.00074819 [auto_monad]: 0.00018518 [graph_reusing]: 8.98002e-06 [inline]: 2.61e-06 [add_attr]: 0.00855772, [1] [add_attr_with_inline]: 0.00854079, [1] [Cycle 1]: 0.00012756, [2] [tag_attr]: 3.718e-05 [meta_addattr_fg_expand]: 7.9e-06 [parallel-infer-symbol]: 4.1e-06 [pre_auto_parallel]: 6.299e-05 [insert-virtual-dataset]: 2.96001e-06 [parallel-infer-symbol-second]: 8.29983e-07 [dataset_repeat_opt]: 2.11e-06 [pipeline_split]: 1.93002e-06 [optimize]: 0.233222, [53] [py_interpret_to_execute]: 6.16e-06 [rewriter_before_opt_a]: 0.00027311 [opt_a]: 0.230066, [2] [Cycle 1]: 0.00501837, [45] [expand_dump_flag]: 4.1e-06 [switch_simplify]: 0.0001016 [loop_unroll]: 3.97e-05 [a_1]: 0.000853 [with_stream_mark]: 2.268e-05 [recompute_prepare]: 1.142e-05 [updatestate_depend_eliminate]: 5.30999e-06 [updatestate_assign_eliminate]: 4.13001e-06 [updatestate_loads_eliminate]: 4.00998e-06 [parameter_eliminate]: 2.21e-06 [a_2]: 0.00011502 [accelerated_algorithm]: 9.15999e-06 [shard]: 3.11001e-06 [meta_shard_fg_expand]: 2.73998e-06 [shard_inline]: 7.89002e-06 [merge_send_recv]: 2.856e-05 [auto_parallel]: 8.32998e-06 [parallel]: 4.151e-05 [flash_sp]: 1.802e-05 [merge_comm]: 4.99998e-06 [allreduce_fusion]: 4.17003e-06 [matmul_add_comm_reduction]: 1.152e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 1.229e-05 [virtual_dataset]: 8.04997e-06 [get_grad_eliminate_]: 7.86001e-06 [virtual_output]: 7.16001e-06 [merge_forward]: 4.84e-06 [cell_reuse_recompute_pass]: 1.47001e-06 [offload_activation]: 1.233e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.556e-05 [merge_recompute_call_nodes]: 1.86e-06 [before_grad]: 1.331e-05 [set_forward_comm_id_for_comm_node_pass]: 4.33001e-06 [meta_fg_expand]: 4.01001e-06 [flash_sp_send_recv_attached]: 2.61e-06 [receive_attached]: 1.101e-05 [after_resolve]: 1.259e-05 [a_after_grad]: 1.203e-05 [renormalize]: 0.00312502 [add_forward_monad_depend]: 1.628e-05 [auto_monad_grad]: 2.61e-06 [auto_monad_eliminator]: 2.643e-05 [cse]: 4.737e-05 [a_3]: 7.53e-05 [Cycle 2]: 0.225027, [45] [expand_dump_flag]: 2.88998e-06 [switch_simplify]: 1.133e-05 [loop_unroll]: 7.8e-06 [a_1]: 0.00020671 [with_stream_mark]: 2.185e-05 [recompute_prepare]: 9.75002e-06 [updatestate_depend_eliminate]: 5.53997e-06 [updatestate_assign_eliminate]: 3.76999e-06 [updatestate_loads_eliminate]: 3.53e-06 [parameter_eliminate]: 2.37999e-06 [a_2]: 9.782e-05 [accelerated_algorithm]: 7.71999e-06 [shard]: 2.77002e-06 [meta_shard_fg_expand]: 2.46e-06 [shard_inline]: 7.98999e-06 [merge_send_recv]: 1.11e-05 [auto_parallel]: 1.112e-05 [parallel]: 9.47999e-06 [flash_sp]: 4.45e-06 [merge_comm]: 4.85999e-06 [allreduce_fusion]: 4.17e-06 [matmul_add_comm_reduction]: 1.112e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 8.50001e-06 [virtual_dataset]: 7.13e-06 [get_grad_eliminate_]: 6.90998e-06 [virtual_output]: 7.15e-06 [merge_forward]: 5.09e-06 [cell_reuse_recompute_pass]: 3.13998e-06 [offload_activation]: 1.22e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.344e-05 [merge_recompute_call_nodes]: 1.36002e-06 [before_grad]: 1.187e-05 [set_forward_comm_id_for_comm_node_pass]: 4.3e-06 [meta_fg_expand]: 3.13998e-06 [flash_sp_send_recv_attached]: 1.65001e-06 [receive_attached]: 2.37999e-06 [after_resolve]: 1.193e-05 [a_after_grad]: 1.087e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.47001e-06 [auto_monad_grad]: 1.78997e-06 [auto_monad_eliminator]: 1.04e-05 [cse]: 2.274e-05 [a_3]: 0.224186 [py_interpret_to_execute_after_opt_a]: 1.385e-05 [slice_cell_reuse_recomputed_activation]: 4.95001e-06 [rewriter_after_opt_a]: 4.519e-05 [convert_after_rewriter]: 1.39e-06 [order_py_execute_after_rewriter]: 1.27999e-06 [mutable_eliminate]: 0.0008172 [opt_b]: 0.00046712, [1] [Cycle 1]: 0.00045653, [7] [b_1]: 0.00031526 [b_2]: 1.348e-05 [updatestate_depend_eliminate]: 1.565e-05 [updatestate_assign_eliminate]: 4.96002e-06 [updatestate_loads_eliminate]: 4.72e-06 [renormalize]: 7.2e-07 [cse]: 5.529e-05 [optimize_parallel_all_gather_comm]: 2.773e-05 [overlap_param_gather]: 6.61999e-06 [cconv]: 4.108e-05 [loop_unroll]: 0.00054265 [opt_after_cconv]: 0.00012949, [1] [Cycle 1]: 0.00012233, [7] [c_1]: 3.712e-05 [parameter_eliminate]: 6.33998e-06 [updatestate_depend_eliminate]: 7.53999e-06 [updatestate_assign_eliminate]: 3.33e-06 [updatestate_loads_eliminate]: 3.04999e-06 [cse]: 2.98e-05 [renormalize]: 3.39991e-07 [remove_dup_value]: 1.97e-05 [tuple_transform]: 0.00011429, [1] [Cycle 1]: 0.000109, [4] [d_1]: 7.819e-05 [none_parameter_eliminate]: 2.02999e-06 [renormalize]: 1.39989e-07 [switch_simplify]: 8.95999e-06 [partial_unused_args_eliminate]: 2.43e-06 [add_recomputation]: 7.044e-05 [cse_after_recomputation]: 2.832e-05, [1] [Cycle 1]: 2.239e-05, [1] [cse]: 1.704e-05 [environ_conv]: 2.6e-05 [swap_dp_allreduce_reducescatter]: 7.92998e-06 [bias_add_comm_swap]: 2.83e-06 [label_micro_interleaved_index]: 5.10999e-06 [label_fine_grained_interleaved_index]: 2.94999e-06 [merge_cast_opt]: 1.84998e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 2.76e-06 [assign_add_opt]: 1.27e-06 [ForceFp32Comm]: 9.5999e-07 [remove_cast_before_assign_add]: 8.10018e-07 [full_micro_interleaved_order_control]: 2.13002e-06 [reorder_send_recv_between_fp_bp]: 2.79999e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.05001e-06 [interleave_split_concat_branches]: 1.40001e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 2.499e-05 [overlap_opt_shard_grad_in_pipeline]: 2.49001e-06 [control_data_broadcast_order]: 1.703e-05 [grouped_pairwise_exchange_alltoall]: 1.77001e-06 [offloading_packed_experts]: 5.25001e-06 [overlap_recompute_and_grad_model_parallel]: 6.09001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.21997e-06 [overlap_recompute_allgather_and_fa_grad]: 1.32e-06 [overlap_recompute_comm]: 2.64001e-06 [overlap_grad_ring_attention]: 5.19e-06 [overlap_grad_flash_sp]: 2.719e-05 [begin_end_overlap_inline]: 9.70002e-07 [split_matmul_comm_elemetwise]: 3.09999e-06 [split_layernorm_comm]: 2.12001e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00011621, [1] [Cycle 1]: 0.00011088, [6] [build]: 2.575e-05 [elim_shapecalc]: 1.415e-05 [elim_not_effective]: 1.702e-05 [opt_reshape]: 8.78001e-06 [fold_const_symbol]: 1.201e-05 [renormalize]: 1.8999e-07 [detach_backward]: 2.60002e-06 [pipeline_parallel_scheduler]: 1.80001e-06 [auto_monad_reorder]: 2.89e-05 [get_jit_bprop_graph]: 2.07001e-06 [rewriter_after_jit_bprop_graph]: 5.62001e-06 [opt_after_jit_grad]: 0.00059011 [validate]: 8.478e-05 Sums bootstrap : 0.000637s : 0.02% type_inference : 2.329881s : 90.85% event_method : 0.000748s : 0.03% auto_monad : 0.000185s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000037s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000063s : 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 : 0.000006s : 0.00% optimize.rewriter_before_opt_a : 0.000273s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000113s : 0.00% optimize.opt_a.loop_unroll : 0.000048s : 0.00% optimize.opt_a.a_1 : 0.001060s : 0.04% optimize.opt_a.with_stream_mark : 0.000045s : 0.00% optimize.opt_a.recompute_prepare : 0.000021s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000213s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000017s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000016s : 0.00% optimize.opt_a.merge_send_recv : 0.000040s : 0.00% optimize.opt_a.auto_parallel : 0.000019s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000010s : 0.00% optimize.opt_a.allreduce_fusion : 0.000008s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000021s : 0.00% optimize.opt_a.virtual_dataset : 0.000015s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000015s : 0.00% optimize.opt_a.virtual_output : 0.000014s : 0.00% optimize.opt_a.merge_forward : 0.000010s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000029s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000025s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.00% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000013s : 0.00% optimize.opt_a.after_resolve : 0.000025s : 0.00% optimize.opt_a.a_after_grad : 0.000023s : 0.00% optimize.opt_a.renormalize : 0.003125s : 0.12% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000037s : 0.00% optimize.opt_a.cse : 0.000070s : 0.00% optimize.opt_a.a_3 : 0.224262s : 8.74% optimize.py_interpret_to_execute_after_opt_a : 0.000014s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000005s : 0.00% optimize.rewriter_after_opt_a : 0.000045s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000817s : 0.03% optimize.opt_b.b_1 : 0.000315s : 0.01% optimize.opt_b.b_2 : 0.000013s : 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 : 0.000055s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.00% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000543s : 0.02% optimize.opt_after_cconv.c_1 : 0.000037s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000030s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000020s : 0.00% optimize.tuple_transform.d_1 : 0.000078s : 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 : 0.000009s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000070s : 0.00% optimize.cse_after_recomputation.cse : 0.000017s : 0.00% optimize.environ_conv : 0.000026s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000025s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000017s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000027s : 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 : 0.000026s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000014s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000017s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000009s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000012s : 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 : 0.000029s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000590s : 0.02% validate : 0.000085s : 0.00% Time group info: ------[substitution.] 0.000378 63 0.87% : 0.000003s : 3: substitution.elim_not_effective 2.90% : 0.000011s : 3: substitution.float_tuple_getitem_switch 0.44% : 0.000002s : 3: substitution.fold_const_symbol 2.10% : 0.000008s : 5: substitution.graph_param_transform 55.46% : 0.000210s : 8: substitution.inline 1.42% : 0.000005s : 6: substitution.j_node_and_user_rematch 2.48% : 0.000009s : 2: substitution.minmaximum_grad 1.61% : 0.000006s : 6: substitution.remove_not_recompute_node 1.33% : 0.000005s : 2: substitution.replace_old_param 2.06% : 0.000008s : 1: substitution.switch_simplify 5.92% : 0.000022s : 4: substitution.tuple_list_convert_item_index_to_positive 2.39% : 0.000009s : 4: substitution.tuple_list_get_item_const_eliminator 3.96% : 0.000015s : 4: substitution.tuple_list_get_item_depend_reorder 13.07% : 0.000049s : 8: substitution.tuple_list_get_item_eliminator 3.98% : 0.000015s : 4: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.110198 2 99.85% : 2.106946s : 1: type_inference.infer 0.15% : 0.003252s : 1: type_inference.specialize ------[replace.] 0.000108 11 59.09% : 0.000064s : 8: replace.inline 24.72% : 0.000027s : 1: replace.switch_simplify 16.19% : 0.000017s : 2: replace.tuple_list_get_item_eliminator ------[match.] 0.000218 11 94.43% : 0.000206s : 8: match.inline 3.15% : 0.000007s : 1: match.switch_simplify 2.42% : 0.000005s : 2: match.tuple_list_get_item_eliminator ------[predicate.] 0.000278 1664 0.96% : 0.000003s : 18: predicate.accumulaten_eliminater 0.83% : 0.000002s : 5: predicate.ad_related_special_op_eliminate 0.63% : 0.000002s : 10: predicate.addn_check_dump 0.96% : 0.000003s : 18: predicate.addn_zero_filter 0.80% : 0.000002s : 18: predicate.adjust_all_reduce_mul_add 2.03% : 0.000006s : 28: predicate.arithmetic_simplify 0.94% : 0.000003s : 18: predicate.cast_eliminate 0.52% : 0.000001s : 10: predicate.check_bprop_eliminate 0.47% : 0.000001s : 10: predicate.compare_switch_simplify 0.19% : 0.000001s : 5: predicate.const_output_eliminate 0.49% : 0.000001s : 10: predicate.depend_value_elim 0.91% : 0.000003s : 18: predicate.dict_get_item_const_eliminator 1.00% : 0.000003s : 18: predicate.dict_get_item_eliminator 0.87% : 0.000002s : 18: predicate.dict_set_item_eliminator 0.97% : 0.000003s : 10: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 5: predicate.elim_not_effective 0.59% : 0.000002s : 5: predicate.elim_shapecalc_of_broadcastargs 1.27% : 0.000004s : 23: predicate.environ_add_const_eliminate 1.05% : 0.000003s : 23: predicate.environ_get_add_eliminate 1.03% : 0.000003s : 23: predicate.environ_get_depend_swap 1.61% : 0.000004s : 33: predicate.environ_get_eliminate 1.06% : 0.000003s : 23: predicate.environ_get_set_eliminate 1.35% : 0.000004s : 28: predicate.exchange_switch_depend_value 2.23% : 0.000006s : 28: predicate.float_depend_g_call 0.50% : 0.000001s : 10: predicate.float_environ_get_switch 0.82% : 0.000002s : 15: predicate.float_tuple_getitem_switch 0.16% : 0.000000s : 5: predicate.fold_const_symbol 0.60% : 0.000002s : 10: predicate.get_grad_eliminate 0.19% : 0.000001s : 5: predicate.graph_param_transform 0.51% : 0.000001s : 10: predicate.incorporate_call 0.40% : 0.000001s : 10: predicate.incorporate_call_switch 5.64% : 0.000016s : 76: predicate.inline 0.78% : 0.000002s : 10: predicate.inline_without_move 0.29% : 0.000001s : 10: predicate.j_node_and_user_rematch 1.00% : 0.000003s : 10: predicate.less_batch_normalization 1.61% : 0.000004s : 30: predicate.list_to_tuple_eliminator_ 2.26% : 0.000006s : 48: predicate.load_eliminater 0.96% : 0.000003s : 5: predicate.loop_unroll_after_grad 2.44% : 0.000007s : 48: predicate.loop_unroll_before_grad 1.63% : 0.000005s : 28: predicate.make_slice_get_slice_eliminator 0.49% : 0.000001s : 10: predicate.merge_addn 0.62% : 0.000002s : 10: predicate.micro_step_allgather_replace 1.99% : 0.000006s : 10: predicate.mini_step_allgather_replace 0.82% : 0.000002s : 18: predicate.minmaximum_grad 1.19% : 0.000003s : 5: predicate.mutable_eliminate 0.33% : 0.000001s : 5: predicate.opt_reshape 0.41% : 0.000001s : 5: predicate.parallel_virtual_node 1.73% : 0.000005s : 28: predicate.partial_defer_inline 1.32% : 0.000004s : 25: predicate.partial_eliminate 0.91% : 0.000003s : 18: predicate.print_const_string_wrapper 0.62% : 0.000002s : 10: predicate.reduce_all_const_elim 1.16% : 0.000003s : 18: predicate.reduce_eliminate 2.40% : 0.000007s : 48: predicate.redundant_stop_gradient_eliminater 0.35% : 0.000001s : 10: predicate.remove_not_recompute_node 1.36% : 0.000004s : 30: predicate.replace_applicator 0.56% : 0.000002s : 10: predicate.replace_old_param 0.36% : 0.000001s : 5: predicate.reset_defer_inline 0.89% : 0.000002s : 18: predicate.reshape_eliminate 0.87% : 0.000002s : 10: predicate.row_tensor_add_zeros_like 0.51% : 0.000001s : 5: predicate.row_tensor_eliminate 0.68% : 0.000002s : 10: predicate.same_eliminate 0.45% : 0.000001s : 10: predicate.set_cell_output_no_recompute 1.18% : 0.000003s : 10: predicate.shard_identity_eliminate 0.69% : 0.000002s : 10: predicate.special_op_eliminate 0.70% : 0.000002s : 10: predicate.specialize_transform 1.43% : 0.000004s : 10: predicate.split_environ_get_set_with_tuple_value 0.70% : 0.000002s : 10: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 5: predicate.switch_call_monad_eliminater 1.58% : 0.000004s : 28: predicate.switch_defer_inline 1.97% : 0.000005s : 38: predicate.switch_layer_defer_inline 5.35% : 0.000015s : 93: predicate.switch_simplify 0.98% : 0.000003s : 18: predicate.tile_eliminate 0.98% : 0.000003s : 18: predicate.transpose_eliminate 1.62% : 0.000004s : 28: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000005s : 28: predicate.tuple_list_get_item_const_eliminator 1.50% : 0.000004s : 28: predicate.tuple_list_get_item_depend_reorder 3.54% : 0.000010s : 40: predicate.tuple_list_get_item_eliminator 1.48% : 0.000004s : 28: predicate.tuple_list_get_set_item_eliminator 2.39% : 0.000007s : 38: predicate.tuple_list_set_item_eliminator 1.53% : 0.000004s : 30: predicate.tuple_to_list_eliminator_ 2.25% : 0.000006s : 48: predicate.updatestate_pure_node_eliminater 2.98% : 0.000008s : 58: predicate.updatestate_useless_node_eliminater 0.36% : 0.000001s : 5: predicate.value_based_eliminate 0.69% : 0.000002s : 10: predicate.virtual_dataset_eliminate 0.63% : 0.000002s : 10: predicate.virtual_output_eliminate 0.24% : 0.000001s : 5: predicate.virtual_view_grad_eliminate 0.39% : 0.000001s : 5: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003206 27 72.52% : 0.002325s : 17: func_graph_cloner_run.FuncGraphClonerGraph 27.48% : 0.000881s : 10: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.045286 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.28% : 0.008564s : 1: add_attr 0.28% : 0.008545s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000075s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000199s : 1: auto_monad 0.00% : 0.000033s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000673s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000020s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000030s : 1: environ_conv 0.03% : 0.000768s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 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% : 0.000004s : 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% : 0.000554s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000831s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000026s : 1: opt.transform.mutable_eliminate 7.41% : 0.225790s : 78: opt.transform.opt_a 0.00% : 0.000036s : 1: opt.transform.opt_after_cconv 0.00% : 0.000035s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000292s : 28: opt.transform.opt_b 0.00% : 0.000085s : 2: opt.transform.opt_trans_graph 0.00% : 0.000048s : 4: opt.transform.symbol_engine_opt 7.55% : 0.230071s : 1: opt_a 0.00% : 0.000133s : 1: opt_after_cconv 0.02% : 0.000604s : 1: opt_after_jit_grad 0.02% : 0.000471s : 1: opt_b 7.66% : 0.233229s : 1: optimize 0.00% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000031s : 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% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000029s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000010s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000067s : 1: pre_auto_parallel 0.00% : 0.000010s : 1: py_interpret_to_execute 0.00% : 0.000020s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000003s : 1: remove_cast_before_assign_add 0.00% : 0.000023s : 1: remove_dup_value 0.07% : 0.002106s : 1: renormalize.infer 0.03% : 0.001006s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000051s : 1: rewriter_after_opt_a 0.01% : 0.000281s : 1: rewriter_before_opt_a 0.00% : 0.000008s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000120s : 1: symbol_engine_optimizer 0.00% : 0.000117s : 1: tuple_transform 76.51% : 2.329924s : 1: type_inference TotalTime = 3.33081, [21] [bootstrap]: 0.00053717 [type_inference]: 2.07397 [event_method]: 0.0001506 [auto_monad]: 0.00020105 [graph_reusing]: 1.221e-05 [inline]: 3.06001e-06 [add_attr]: 0.0042879, [1] [add_attr_with_inline]: 0.0042777, [1] [Cycle 1]: 0.00011366, [2] [tag_attr]: 5.747e-05 [meta_addattr_fg_expand]: 1.219e-05 [parallel-infer-symbol]: 3.80998e-06 [pre_auto_parallel]: 7.219e-05 [insert-virtual-dataset]: 2.76e-06 [parallel-infer-symbol-second]: 8.50006e-07 [dataset_repeat_opt]: 2.31e-06 [pipeline_split]: 1.93997e-06 [optimize]: 1.2507, [53] [py_interpret_to_execute]: 5.99e-06 [rewriter_before_opt_a]: 0.00040906 [opt_a]: 1.24724, [3] [Cycle 1]: 1.23914, [45] [expand_dump_flag]: 5.25001e-06 [switch_simplify]: 0.00018687 [loop_unroll]: 0.324473 [a_1]: 0.00197417 [with_stream_mark]: 4.416e-05 [recompute_prepare]: 3.125e-05 [updatestate_depend_eliminate]: 1.15e-05 [updatestate_assign_eliminate]: 8.21002e-06 [updatestate_loads_eliminate]: 7.96001e-06 [parameter_eliminate]: 5.07e-06 [a_2]: 0.00025642 [accelerated_algorithm]: 2.374e-05 [shard]: 2.27001e-06 [meta_shard_fg_expand]: 7.58999e-06 [shard_inline]: 1.665e-05 [merge_send_recv]: 2.378e-05 [auto_parallel]: 1.876e-05 [parallel]: 4.167e-05 [flash_sp]: 1.734e-05 [merge_comm]: 1.131e-05 [allreduce_fusion]: 9.22001e-06 [matmul_add_comm_reduction]: 4e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 2.279e-05 [virtual_dataset]: 1.67e-05 [get_grad_eliminate_]: 1.532e-05 [virtual_output]: 1.665e-05 [merge_forward]: 1.227e-05 [cell_reuse_recompute_pass]: 2.50002e-06 [offload_activation]: 2.408e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.674e-05 [merge_recompute_call_nodes]: 2.19999e-06 [before_grad]: 3.044e-05 [set_forward_comm_id_for_comm_node_pass]: 1.226e-05 [meta_fg_expand]: 0.0235184 [flash_sp_send_recv_attached]: 6.37001e-06 [receive_attached]: 2.76e-06 [after_resolve]: 0.00010152 [a_after_grad]: 0.000137 [renormalize]: 0.885268 [add_forward_monad_depend]: 3.216e-05 [auto_monad_grad]: 1.703e-05 [auto_monad_eliminator]: 0.00012518 [cse]: 0.00057255 [a_3]: 0.00144863 [Cycle 2]: 0.00669059, [45] [expand_dump_flag]: 5.77001e-06 [switch_simplify]: 9.604e-05 [loop_unroll]: 8.245e-05 [a_1]: 0.00216832 [with_stream_mark]: 4.459e-05 [recompute_prepare]: 2.279e-05 [updatestate_depend_eliminate]: 9.89999e-06 [updatestate_assign_eliminate]: 7.56001e-06 [updatestate_loads_eliminate]: 6.75998e-06 [parameter_eliminate]: 3.3e-06 [a_2]: 0.00020231 [accelerated_algorithm]: 1.653e-05 [shard]: 3.38e-06 [meta_shard_fg_expand]: 5.24998e-06 [shard_inline]: 1.405e-05 [merge_send_recv]: 1.54e-05 [auto_parallel]: 1.472e-05 [parallel]: 9.98998e-06 [flash_sp]: 5.89999e-06 [merge_comm]: 7.98999e-06 [allreduce_fusion]: 7.52002e-06 [matmul_add_comm_reduction]: 1.667e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 1.664e-05 [virtual_dataset]: 1.33e-05 [get_grad_eliminate_]: 1.247e-05 [virtual_output]: 1.249e-05 [merge_forward]: 8.28001e-06 [cell_reuse_recompute_pass]: 1.81003e-06 [offload_activation]: 1.849e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.957e-05 [merge_recompute_call_nodes]: 1.80001e-06 [before_grad]: 2.281e-05 [set_forward_comm_id_for_comm_node_pass]: 8.67998e-06 [meta_fg_expand]: 0.00021534 [flash_sp_send_recv_attached]: 3.30998e-06 [receive_attached]: 2.46e-06 [after_resolve]: 2.924e-05 [a_after_grad]: 2.375e-05 [renormalize]: 0.0028017 [add_forward_monad_depend]: 1.073e-05 [auto_monad_grad]: 2.83e-06 [auto_monad_eliminator]: 3.694e-05 [cse]: 0.00019126 [a_3]: 0.00011495 [Cycle 3]: 0.00138405, [45] [expand_dump_flag]: 2.92002e-06 [switch_simplify]: 1.765e-05 [loop_unroll]: 1.291e-05 [a_1]: 0.00039634 [with_stream_mark]: 2.402e-05 [recompute_prepare]: 1.506e-05 [updatestate_depend_eliminate]: 9.09e-06 [updatestate_assign_eliminate]: 6.79001e-06 [updatestate_loads_eliminate]: 6.24999e-06 [parameter_eliminate]: 2.04e-06 [a_2]: 0.00018903 [accelerated_algorithm]: 1.498e-05 [shard]: 2.44001e-06 [meta_shard_fg_expand]: 3.23998e-06 [shard_inline]: 1.356e-05 [merge_send_recv]: 1.328e-05 [auto_parallel]: 1.462e-05 [parallel]: 9.50001e-06 [flash_sp]: 2.24001e-06 [merge_comm]: 7.68999e-06 [allreduce_fusion]: 7.63999e-06 [matmul_add_comm_reduction]: 1.675e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 1.586e-05 [virtual_dataset]: 1.306e-05 [get_grad_eliminate_]: 1.301e-05 [virtual_output]: 1.321e-05 [merge_forward]: 9.09e-06 [cell_reuse_recompute_pass]: 3.21999e-06 [offload_activation]: 1.601e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.771e-05 [merge_recompute_call_nodes]: 2.19999e-06 [before_grad]: 2.243e-05 [set_forward_comm_id_for_comm_node_pass]: 7.85e-06 [meta_fg_expand]: 5.94e-06 [flash_sp_send_recv_attached]: 1.74e-06 [receive_attached]: 3.12002e-06 [after_resolve]: 1.809e-05 [a_after_grad]: 2.308e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.67001e-06 [auto_monad_grad]: 2.39999e-06 [auto_monad_eliminator]: 1.95e-05 [cse]: 6.355e-05 [a_3]: 8.692e-05 [py_interpret_to_execute_after_opt_a]: 8.82e-06 [slice_cell_reuse_recomputed_activation]: 2.45002e-06 [rewriter_after_opt_a]: 4.672e-05 [convert_after_rewriter]: 1.19e-06 [order_py_execute_after_rewriter]: 1.32e-06 [mutable_eliminate]: 0.00076938 [opt_b]: 0.00052448, [1] [Cycle 1]: 0.00051541, [7] [b_1]: 0.00037742 [b_2]: 1.633e-05 [updatestate_depend_eliminate]: 1.32e-05 [updatestate_assign_eliminate]: 6.35002e-06 [updatestate_loads_eliminate]: 6.04001e-06 [renormalize]: 1.27e-06 [cse]: 5.369e-05 [optimize_parallel_all_gather_comm]: 3.089e-05 [overlap_param_gather]: 2.17999e-06 [cconv]: 3.769e-05 [loop_unroll]: 0.00049757 [opt_after_cconv]: 0.00020117, [1] [Cycle 1]: 0.00019356, [7] [c_1]: 7.421e-05 [parameter_eliminate]: 6.41e-06 [updatestate_depend_eliminate]: 1.097e-05 [updatestate_assign_eliminate]: 7.43e-06 [updatestate_loads_eliminate]: 6.93e-06 [cse]: 5.223e-05 [renormalize]: 4.7998e-07 [remove_dup_value]: 7.909e-05 [tuple_transform]: 0.00016431, [1] [Cycle 1]: 0.00015801, [4] [d_1]: 0.00012025 [none_parameter_eliminate]: 2.18002e-06 [renormalize]: 2.89991e-07 [switch_simplify]: 1.538e-05 [partial_unused_args_eliminate]: 2.26e-06 [add_recomputation]: 9.788e-05 [cse_after_recomputation]: 4.777e-05, [1] [Cycle 1]: 4.162e-05, [1] [cse]: 3.561e-05 [environ_conv]: 1.38e-05 [swap_dp_allreduce_reducescatter]: 1.165e-05 [bias_add_comm_swap]: 3.74002e-06 [label_micro_interleaved_index]: 5.27001e-06 [label_fine_grained_interleaved_index]: 2.92002e-06 [merge_cast_opt]: 1.72001e-06 [slice_recompute_activation]: 2.43e-06 [micro_interleaved_order_control]: 2.81e-06 [assign_add_opt]: 1.67001e-06 [ForceFp32Comm]: 8.50006e-07 [remove_cast_before_assign_add]: 1.21997e-06 [full_micro_interleaved_order_control]: 2.56998e-06 [reorder_send_recv_between_fp_bp]: 2.73e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.21997e-06 [interleave_parallel_branches]: 1.05999e-06 [overlap_opt_shard_in_pipeline]: 1.42999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.94e-06 [control_data_broadcast_order]: 2.509e-05 [grouped_pairwise_exchange_alltoall]: 2.03002e-06 [offloading_packed_experts]: 7.57998e-06 [overlap_recompute_and_grad_model_parallel]: 7.43999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.14e-06 [overlap_recompute_allgather_and_fa_grad]: 1.24998e-06 [overlap_recompute_comm]: 2.93e-06 [overlap_grad_ring_attention]: 6.94001e-06 [overlap_grad_flash_sp]: 3.606e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.34999e-06 [split_layernorm_comm]: 2.11e-06 [handle_group_info]: 1.08001e-06 [symbol_engine_optimizer]: 0.00013557, [1] [Cycle 1]: 0.00013025, [6] [build]: 1.358e-05 [elim_shapecalc]: 1.983e-05 [elim_not_effective]: 2.733e-05 [opt_reshape]: 1.793e-05 [fold_const_symbol]: 2.159e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.44999e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 2.916e-05 [get_jit_bprop_graph]: 2.36e-06 [rewriter_after_jit_bprop_graph]: 5.71998e-06 [opt_after_jit_grad]: 0.00055693 [validate]: 7.636e-05 Sums bootstrap : 0.000537s : 0.02% type_inference : 2.073974s : 62.38% event_method : 0.000151s : 0.00% auto_monad : 0.000201s : 0.01% graph_reusing : 0.000012s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000057s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000012s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000072s : 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 : 0.000006s : 0.00% optimize.rewriter_before_opt_a : 0.000409s : 0.01% optimize.opt_a.expand_dump_flag : 0.000014s : 0.00% optimize.opt_a.switch_simplify : 0.000301s : 0.01% optimize.opt_a.loop_unroll : 0.324569s : 9.76% optimize.opt_a.a_1 : 0.004539s : 0.14% optimize.opt_a.with_stream_mark : 0.000113s : 0.00% optimize.opt_a.recompute_prepare : 0.000069s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000030s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000648s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000055s : 0.00% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000016s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.00% optimize.opt_a.merge_send_recv : 0.000052s : 0.00% optimize.opt_a.auto_parallel : 0.000048s : 0.00% optimize.opt_a.parallel : 0.000061s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000027s : 0.00% optimize.opt_a.allreduce_fusion : 0.000024s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000073s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000055s : 0.00% optimize.opt_a.virtual_dataset : 0.000043s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000041s : 0.00% optimize.opt_a.virtual_output : 0.000042s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000059s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000094s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000006s : 0.00% optimize.opt_a.before_grad : 0.000076s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.023740s : 0.71% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.00% optimize.opt_a.after_resolve : 0.000149s : 0.00% optimize.opt_a.a_after_grad : 0.000184s : 0.01% optimize.opt_a.renormalize : 0.888069s : 26.71% optimize.opt_a.add_forward_monad_depend : 0.000046s : 0.00% optimize.opt_a.auto_monad_grad : 0.000022s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000182s : 0.01% optimize.opt_a.cse : 0.000827s : 0.02% optimize.opt_a.a_3 : 0.001651s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000009s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000047s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000769s : 0.02% optimize.opt_b.b_1 : 0.000377s : 0.01% optimize.opt_b.b_2 : 0.000016s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000054s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.00% optimize.loop_unroll : 0.000498s : 0.01% optimize.opt_after_cconv.c_1 : 0.000074s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000052s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000079s : 0.00% optimize.tuple_transform.d_1 : 0.000120s : 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 : 0.000015s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000098s : 0.00% optimize.cse_after_recomputation.cse : 0.000036s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000025s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 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 : 0.000014s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000029s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000557s : 0.02% validate : 0.000076s : 0.00% Time group info: ------[substitution.] 0.002170 285 0.20% : 0.000004s : 8: substitution.elim_not_effective 0.56% : 0.000012s : 12: substitution.float_depend_g_call 0.76% : 0.000017s : 6: substitution.float_tuple_getitem_switch 0.16% : 0.000004s : 8: substitution.fold_const_symbol 29.48% : 0.000640s : 5: substitution.getattr_setattr_resolve 0.51% : 0.000011s : 11: substitution.graph_param_transform 0.16% : 0.000003s : 2: substitution.incorporate_call 0.12% : 0.000003s : 2: substitution.incorporate_call_switch 44.65% : 0.000969s : 24: substitution.inline 1.37% : 0.000030s : 3: substitution.inline_without_move 0.75% : 0.000016s : 25: substitution.j_node_and_user_rematch 0.94% : 0.000020s : 11: substitution.minmaximum_grad 0.09% : 0.000002s : 1: substitution.opt_reshape 0.61% : 0.000013s : 12: substitution.partial_eliminate 0.98% : 0.000021s : 25: substitution.remove_not_recompute_node 4.77% : 0.000104s : 31: substitution.replace_applicator 0.68% : 0.000015s : 13: substitution.replace_old_param 1.10% : 0.000024s : 3: substitution.reshape_eliminate 0.22% : 0.000005s : 1: substitution.set_cell_output_no_recompute 0.63% : 0.000014s : 4: substitution.switch_simplify 2.39% : 0.000052s : 13: substitution.tuple_list_convert_item_index_to_positive 1.00% : 0.000022s : 13: substitution.tuple_list_get_item_const_eliminator 1.50% : 0.000032s : 13: substitution.tuple_list_get_item_depend_reorder 4.90% : 0.000106s : 26: substitution.tuple_list_get_item_eliminator 1.49% : 0.000032s : 13: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.073794 2 99.74% : 2.068437s : 1: type_inference.infer 0.26% : 0.005356s : 1: type_inference.specialize ------[replace.] 0.000665 44 11.41% : 0.000076s : 4: replace.getattr_setattr_resolve 52.05% : 0.000346s : 24: replace.inline 14.62% : 0.000097s : 4: replace.replace_applicator 9.26% : 0.000062s : 4: replace.switch_simplify 12.66% : 0.000084s : 8: replace.tuple_list_get_item_eliminator ------[match.] 0.001625 44 36.45% : 0.000592s : 4: match.getattr_setattr_resolve 58.67% : 0.000953s : 24: match.inline 2.20% : 0.000036s : 4: match.replace_applicator 0.65% : 0.000011s : 4: match.switch_simplify 2.02% : 0.000033s : 8: match.tuple_list_get_item_eliminator ------[predicate.] 0.001192 7485 0.83% : 0.000010s : 72: predicate.accumulaten_eliminater 0.31% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.39% : 0.000005s : 35: predicate.addn_check_dump 0.87% : 0.000010s : 72: predicate.addn_zero_filter 0.75% : 0.000009s : 72: predicate.adjust_all_reduce_mul_add 1.54% : 0.000018s : 107: predicate.arithmetic_simplify 4.63% : 0.000055s : 72: predicate.cast_eliminate 2.37% : 0.000028s : 220: predicate.check_bprop_eliminate 0.39% : 0.000005s : 35: predicate.compare_switch_simplify 0.08% : 0.000001s : 11: predicate.const_output_eliminate 0.42% : 0.000005s : 35: predicate.depend_value_elim 0.84% : 0.000010s : 72: predicate.dict_get_item_const_eliminator 0.90% : 0.000011s : 72: predicate.dict_get_item_eliminator 0.81% : 0.000010s : 72: predicate.dict_set_item_eliminator 0.33% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.08% : 0.000001s : 11: predicate.elim_not_effective 0.15% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 0.91% : 0.000011s : 83: predicate.environ_add_const_eliminate 0.85% : 0.000010s : 83: predicate.environ_get_add_eliminate 0.89% : 0.000011s : 83: predicate.environ_get_depend_swap 1.32% : 0.000016s : 118: predicate.environ_get_eliminate 0.87% : 0.000010s : 83: predicate.environ_get_set_eliminate 1.20% : 0.000014s : 104: predicate.exchange_switch_depend_value 1.87% : 0.000022s : 104: predicate.float_depend_g_call 0.43% : 0.000005s : 35: predicate.float_environ_get_switch 0.57% : 0.000007s : 46: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 11: predicate.fold_const_symbol 0.46% : 0.000005s : 35: predicate.get_grad_eliminate 0.65% : 0.000008s : 31: predicate.getattr_setattr_resolve 0.11% : 0.000001s : 11: predicate.graph_param_transform 0.43% : 0.000005s : 35: predicate.incorporate_call 0.36% : 0.000004s : 35: predicate.incorporate_call_switch 4.36% : 0.000052s : 268: predicate.inline 1.37% : 0.000016s : 84: predicate.inline_without_move 0.21% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.66% : 0.000008s : 35: predicate.less_batch_normalization 1.17% : 0.000014s : 102: predicate.list_to_tuple_eliminator_ 1.95% : 0.000023s : 174: predicate.load_eliminater 0.29% : 0.000003s : 11: predicate.loop_unroll_after_grad 3.03% : 0.000036s : 186: predicate.loop_unroll_before_grad 1.09% : 0.000013s : 94: predicate.make_slice_get_slice_eliminator 0.41% : 0.000005s : 35: predicate.merge_addn 2.21% : 0.000026s : 204: predicate.micro_step_allgather_replace 2.23% : 0.000027s : 204: predicate.mini_step_allgather_replace 0.79% : 0.000009s : 72: predicate.minmaximum_grad 0.44% : 0.000005s : 11: predicate.mutable_eliminate 0.15% : 0.000002s : 11: predicate.opt_reshape 0.15% : 0.000002s : 11: predicate.parallel_virtual_node 2.00% : 0.000024s : 104: predicate.partial_defer_inline 1.14% : 0.000014s : 91: predicate.partial_eliminate 0.80% : 0.000010s : 72: predicate.print_const_string_wrapper 0.43% : 0.000005s : 35: predicate.reduce_all_const_elim 1.03% : 0.000012s : 72: predicate.reduce_eliminate 1.97% : 0.000024s : 174: predicate.redundant_stop_gradient_eliminater 0.30% : 0.000004s : 35: predicate.remove_not_recompute_node 2.29% : 0.000027s : 292: predicate.replace_applicator 0.59% : 0.000007s : 84: predicate.replace_old_param 4.07% : 0.000049s : 11: predicate.reset_defer_inline 0.91% : 0.000011s : 72: predicate.reshape_eliminate 2.36% : 0.000028s : 204: predicate.row_tensor_add_zeros_like 0.17% : 0.000002s : 11: predicate.row_tensor_eliminate 2.84% : 0.000034s : 220: predicate.same_eliminate 0.35% : 0.000004s : 35: predicate.set_cell_output_no_recompute 0.60% : 0.000007s : 35: predicate.shard_identity_eliminate 0.30% : 0.000004s : 22: predicate.special_op_eliminate 0.45% : 0.000005s : 35: predicate.specialize_transform 2.32% : 0.000028s : 204: predicate.split_environ_get_set_with_tuple_value 1.19% : 0.000014s : 84: predicate.stack_unstack_eliminate 0.17% : 0.000002s : 11: predicate.switch_call_monad_eliminater 1.36% : 0.000016s : 104: predicate.switch_defer_inline 3.66% : 0.000044s : 324: predicate.switch_layer_defer_inline 4.44% : 0.000053s : 344: predicate.switch_simplify 0.88% : 0.000010s : 72: predicate.tile_eliminate 0.83% : 0.000010s : 72: predicate.transpose_eliminate 1.19% : 0.000014s : 94: predicate.tuple_list_convert_item_index_to_positive 1.21% : 0.000014s : 94: predicate.tuple_list_get_item_const_eliminator 1.12% : 0.000013s : 94: predicate.tuple_list_get_item_depend_reorder 2.26% : 0.000027s : 137: predicate.tuple_list_get_item_eliminator 1.18% : 0.000014s : 94: predicate.tuple_list_get_set_item_eliminator 1.68% : 0.000020s : 129: predicate.tuple_list_set_item_eliminator 1.20% : 0.000014s : 102: predicate.tuple_to_list_eliminator_ 1.83% : 0.000022s : 174: predicate.updatestate_pure_node_eliminater 2.35% : 0.000028s : 209: predicate.updatestate_useless_node_eliminater 0.15% : 0.000002s : 11: predicate.value_based_eliminate 0.45% : 0.000005s : 35: predicate.virtual_dataset_eliminate 0.46% : 0.000005s : 35: predicate.virtual_output_eliminate 0.14% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.16% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007269 80 72.27% : 0.005253s : 43: func_graph_cloner_run.FuncGraphClonerGraph 27.73% : 0.002016s : 37: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 5.807548 243 0.00% : 0.000004s : 1: ForceFp32Comm 0.07% : 0.004294s : 1: add_attr 0.07% : 0.004282s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000102s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000212s : 1: auto_monad 0.00% : 0.000033s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.01% : 0.000568s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000051s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000017s : 1: environ_conv 0.00% : 0.000164s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.01% : 0.000507s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000784s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000030s : 1: opt.transform.mutable_eliminate 5.72% : 0.332348s : 125: opt.transform.opt_a 0.00% : 0.000073s : 1: opt.transform.opt_after_cconv 0.00% : 0.000049s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000360s : 28: opt.transform.opt_b 0.01% : 0.000788s : 2: opt.transform.opt_resolve 0.00% : 0.000133s : 2: opt.transform.opt_trans_graph 0.00% : 0.000083s : 4: opt.transform.symbol_engine_opt 21.48% : 1.247242s : 1: opt_a 0.00% : 0.000205s : 1: opt_after_cconv 0.01% : 0.000568s : 1: opt_after_jit_grad 0.01% : 0.000528s : 1: opt_b 21.54% : 1.250702s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000077s : 1: pre_auto_parallel 0.00% : 0.000009s : 1: py_interpret_to_execute 0.00% : 0.000012s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000084s : 1: remove_dup_value 15.19% : 0.882283s : 2: renormalize.infer 0.10% : 0.005754s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000052s : 1: rewriter_after_opt_a 0.01% : 0.000416s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000139s : 1: symbol_engine_optimizer 0.00% : 0.000167s : 1: tuple_transform 35.71% : 2.074003s : 1: type_inference TotalTime = 2.13112, [21] [bootstrap]: 0.00046957 [type_inference]: 2.1165 [event_method]: 3.085e-05 [auto_monad]: 0.00010609 [graph_reusing]: 8.33999e-06 [inline]: 3.28e-06 [add_attr]: 0.00462414, [1] [add_attr_with_inline]: 0.00460997, [1] [Cycle 1]: 8.021e-05, [2] [tag_attr]: 3.016e-05 [meta_addattr_fg_expand]: 6.66e-06 [parallel-infer-symbol]: 3.54002e-06 [pre_auto_parallel]: 4.788e-05 [insert-virtual-dataset]: 2.81e-06 [parallel-infer-symbol-second]: 9.20001e-07 [dataset_repeat_opt]: 2.43e-06 [pipeline_split]: 1.67999e-06 [optimize]: 0.00847284, [53] [py_interpret_to_execute]: 7.36001e-06 [rewriter_before_opt_a]: 0.00027634 [opt_a]: 0.00564292, [2] [Cycle 1]: 0.00491041, [45] [expand_dump_flag]: 3.41999e-06 [switch_simplify]: 9.56e-05 [loop_unroll]: 3.379e-05 [a_1]: 0.00069426 [with_stream_mark]: 2.061e-05 [recompute_prepare]: 9.37999e-06 [updatestate_depend_eliminate]: 3.95e-06 [updatestate_assign_eliminate]: 3.36999e-06 [updatestate_loads_eliminate]: 3.03998e-06 [parameter_eliminate]: 2.31e-06 [a_2]: 8.6e-05 [accelerated_algorithm]: 7.94002e-06 [shard]: 2.59999e-06 [meta_shard_fg_expand]: 1.90001e-06 [shard_inline]: 6.19001e-06 [merge_send_recv]: 8.90001e-06 [auto_parallel]: 7.03e-06 [parallel]: 2.117e-05 [flash_sp]: 9.60001e-06 [merge_comm]: 3.83001e-06 [allreduce_fusion]: 3.53999e-06 [matmul_add_comm_reduction]: 1.035e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 9.10001e-06 [virtual_dataset]: 7.4e-06 [get_grad_eliminate_]: 7.08998e-06 [virtual_output]: 6.54001e-06 [merge_forward]: 4.52e-06 [cell_reuse_recompute_pass]: 1.72001e-06 [offload_activation]: 1.15e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.372e-05 [merge_recompute_call_nodes]: 1.71002e-06 [before_grad]: 1.157e-05 [set_forward_comm_id_for_comm_node_pass]: 3.53999e-06 [meta_fg_expand]: 3.21999e-06 [flash_sp_send_recv_attached]: 2.61999e-06 [receive_attached]: 2.66e-06 [after_resolve]: 1.055e-05 [a_after_grad]: 1.107e-05 [renormalize]: 0.00335591 [add_forward_monad_depend]: 1.07e-05 [auto_monad_grad]: 2.79001e-06 [auto_monad_eliminator]: 2.353e-05 [cse]: 3.739e-05 [a_3]: 6.223e-05 [Cycle 2]: 0.00071614, [45] [expand_dump_flag]: 2.66e-06 [switch_simplify]: 1.044e-05 [loop_unroll]: 6.21e-06 [a_1]: 0.00013409 [with_stream_mark]: 2.027e-05 [recompute_prepare]: 7.01999e-06 [updatestate_depend_eliminate]: 4.22e-06 [updatestate_assign_eliminate]: 2.78998e-06 [updatestate_loads_eliminate]: 3.78001e-06 [parameter_eliminate]: 2.36e-06 [a_2]: 7.163e-05 [accelerated_algorithm]: 6.65998e-06 [shard]: 2.51e-06 [meta_shard_fg_expand]: 2.74001e-06 [shard_inline]: 6.46e-06 [merge_send_recv]: 8.43001e-06 [auto_parallel]: 1.079e-05 [parallel]: 1.071e-05 [flash_sp]: 4.45e-06 [merge_comm]: 3.75e-06 [allreduce_fusion]: 3.26001e-06 [matmul_add_comm_reduction]: 8.94998e-06 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 7.63999e-06 [virtual_dataset]: 6.14999e-06 [get_grad_eliminate_]: 6.59999e-06 [virtual_output]: 5.54e-06 [merge_forward]: 4.47e-06 [cell_reuse_recompute_pass]: 3.21999e-06 [offload_activation]: 1.058e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.754e-05 [merge_recompute_call_nodes]: 1.32999e-06 [before_grad]: 1.082e-05 [set_forward_comm_id_for_comm_node_pass]: 4.99e-06 [meta_fg_expand]: 2.88e-06 [flash_sp_send_recv_attached]: 1.87001e-06 [receive_attached]: 2.71999e-06 [after_resolve]: 1.332e-05 [a_after_grad]: 9.15001e-06 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 2.07001e-06 [auto_monad_grad]: 1.85001e-06 [auto_monad_eliminator]: 8.3e-06 [cse]: 1.725e-05 [a_3]: 3.485e-05 [py_interpret_to_execute_after_opt_a]: 7.46999e-06 [slice_cell_reuse_recomputed_activation]: 2.48e-06 [rewriter_after_opt_a]: 2.272e-05 [convert_after_rewriter]: 1.19e-06 [order_py_execute_after_rewriter]: 2.11e-06 [mutable_eliminate]: 0.00076155 [opt_b]: 0.00029166, [1] [Cycle 1]: 0.00028235, [7] [b_1]: 0.00019489 [b_2]: 8.17998e-06 [updatestate_depend_eliminate]: 7.85e-06 [updatestate_assign_eliminate]: 2.79001e-06 [updatestate_loads_eliminate]: 2.39999e-06 [renormalize]: 6.29982e-07 [cse]: 2.511e-05 [optimize_parallel_all_gather_comm]: 2.118e-05 [overlap_param_gather]: 2.43e-06 [cconv]: 3.522e-05 [loop_unroll]: 0.00049672 [opt_after_cconv]: 0.00011424, [1] [Cycle 1]: 0.0001075, [7] [c_1]: 3.121e-05 [parameter_eliminate]: 5.24e-06 [updatestate_depend_eliminate]: 6.44001e-06 [updatestate_assign_eliminate]: 2.22999e-06 [updatestate_loads_eliminate]: 1.99999e-06 [cse]: 2.12e-05 [renormalize]: 7.80012e-07 [remove_dup_value]: 1.78e-05 [tuple_transform]: 0.00023091, [1] [Cycle 1]: 0.00022589, [4] [d_1]: 0.00019412 [none_parameter_eliminate]: 2.41e-06 [renormalize]: 3.00002e-07 [switch_simplify]: 8.45001e-06 [partial_unused_args_eliminate]: 2.16e-06 [add_recomputation]: 5.847e-05 [cse_after_recomputation]: 2.73e-05, [1] [Cycle 1]: 2.244e-05, [1] [cse]: 1.646e-05 [environ_conv]: 1.234e-05 [swap_dp_allreduce_reducescatter]: 5.22999e-06 [bias_add_comm_swap]: 3.75e-06 [label_micro_interleaved_index]: 5.66e-06 [label_fine_grained_interleaved_index]: 3.2e-06 [merge_cast_opt]: 1.46998e-06 [slice_recompute_activation]: 2.21e-06 [micro_interleaved_order_control]: 2.69001e-06 [assign_add_opt]: 1.35001e-06 [ForceFp32Comm]: 1.17999e-06 [remove_cast_before_assign_add]: 1.12e-06 [full_micro_interleaved_order_control]: 2.65997e-06 [reorder_send_recv_between_fp_bp]: 2.89001e-06 [comm_op_add_attrs]: 1.19e-06 [add_comm_op_reuse_tag]: 1.05001e-06 [interleave_split_concat_branches]: 1.14e-06 [interleave_parallel_branches]: 1.44e-06 [overlap_opt_shard_in_pipeline]: 1.35999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.91e-06 [control_data_broadcast_order]: 1.655e-05 [grouped_pairwise_exchange_alltoall]: 1.57999e-06 [offloading_packed_experts]: 4.37998e-06 [overlap_recompute_and_grad_model_parallel]: 5.40999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.29998e-06 [overlap_recompute_comm]: 2.37999e-06 [overlap_grad_ring_attention]: 4.73001e-06 [overlap_grad_flash_sp]: 2.259e-05 [begin_end_overlap_inline]: 5.20027e-07 [split_matmul_comm_elemetwise]: 2.71999e-06 [split_layernorm_comm]: 2.27999e-06 [handle_group_info]: 1.08001e-06 [symbol_engine_optimizer]: 8.734e-05, [1] [Cycle 1]: 8.134e-05, [6] [build]: 1.209e-05 [elim_shapecalc]: 1.093e-05 [elim_not_effective]: 1.331e-05 [opt_reshape]: 6.78e-06 [fold_const_symbol]: 9.76e-06 [renormalize]: 1.8999e-07 [detach_backward]: 2.51e-06 [pipeline_parallel_scheduler]: 1.57999e-06 [auto_monad_reorder]: 1.908e-05 [get_jit_bprop_graph]: 2.11e-06 [rewriter_after_jit_bprop_graph]: 6.74999e-06 [opt_after_jit_grad]: 0.00055882 [validate]: 7.039e-05 Sums bootstrap : 0.000470s : 0.02% type_inference : 2.116497s : 99.58% event_method : 0.000031s : 0.00% auto_monad : 0.000106s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000030s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000048s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000007s : 0.00% optimize.rewriter_before_opt_a : 0.000276s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000106s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.000828s : 0.04% optimize.opt_a.with_stream_mark : 0.000041s : 0.00% optimize.opt_a.recompute_prepare : 0.000016s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000158s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000015s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000013s : 0.00% optimize.opt_a.merge_send_recv : 0.000017s : 0.00% optimize.opt_a.auto_parallel : 0.000018s : 0.00% optimize.opt_a.parallel : 0.000032s : 0.00% optimize.opt_a.flash_sp : 0.000014s : 0.00% optimize.opt_a.merge_comm : 0.000008s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000019s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000017s : 0.00% optimize.opt_a.virtual_dataset : 0.000014s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000014s : 0.00% optimize.opt_a.virtual_output : 0.000012s : 0.00% optimize.opt_a.merge_forward : 0.000009s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000022s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000031s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000022s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.00% optimize.opt_a.meta_fg_expand : 0.000006s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000024s : 0.00% optimize.opt_a.a_after_grad : 0.000020s : 0.00% optimize.opt_a.renormalize : 0.003356s : 0.16% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000032s : 0.00% optimize.opt_a.cse : 0.000055s : 0.00% optimize.opt_a.a_3 : 0.000097s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000007s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000023s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000002s : 0.00% optimize.mutable_eliminate : 0.000762s : 0.04% optimize.opt_b.b_1 : 0.000195s : 0.01% 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 : 0.000003s : 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 : 0.000021s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000497s : 0.02% optimize.opt_after_cconv.c_1 : 0.000031s : 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 : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000021s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.00% optimize.tuple_transform.d_1 : 0.000194s : 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 : 0.000008s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000058s : 0.00% optimize.cse_after_recomputation.cse : 0.000016s : 0.00% optimize.environ_conv : 0.000012s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000005s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 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 : 0.000017s : 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 : 0.000001s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 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 : 0.000012s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000011s : 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 : 0.000019s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000559s : 0.03% validate : 0.000070s : 0.00% Time group info: ------[substitution.] 0.000248 27 1.15% : 0.000003s : 2: substitution.elim_not_effective 0.56% : 0.000001s : 2: substitution.fold_const_symbol 2.75% : 0.000007s : 4: substitution.graph_param_transform 78.45% : 0.000194s : 6: substitution.inline 1.92% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.36% : 0.000006s : 4: substitution.remove_not_recompute_node 2.79% : 0.000007s : 2: substitution.replace_old_param 4.01% : 0.000010s : 1: substitution.switch_simplify 6.00% : 0.000015s : 2: substitution.tuple_list_get_item_eliminator ------[type_inference.] 2.116379 2 91.49% : 1.936273s : 1: type_inference.infer 8.51% : 0.180106s : 1: type_inference.specialize ------[replace.] 0.000100 9 54.14% : 0.000054s : 6: replace.inline 26.82% : 0.000027s : 1: replace.switch_simplify 19.05% : 0.000019s : 2: replace.tuple_list_get_item_eliminator ------[match.] 0.000213 9 89.46% : 0.000191s : 6: match.inline 4.17% : 0.000009s : 1: match.switch_simplify 6.37% : 0.000014s : 2: match.tuple_list_get_item_eliminator ------[predicate.] 0.000216 1318 0.94% : 0.000002s : 14: predicate.accumulaten_eliminater 0.76% : 0.000002s : 4: predicate.ad_related_special_op_eliminate 0.62% : 0.000001s : 8: predicate.addn_check_dump 0.97% : 0.000002s : 14: predicate.addn_zero_filter 0.88% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 2.14% : 0.000005s : 22: predicate.arithmetic_simplify 1.08% : 0.000002s : 14: predicate.cast_eliminate 0.59% : 0.000001s : 8: predicate.check_bprop_eliminate 0.56% : 0.000001s : 8: predicate.compare_switch_simplify 0.45% : 0.000001s : 4: predicate.const_output_eliminate 0.53% : 0.000001s : 8: predicate.depend_value_elim 0.88% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 1.02% : 0.000002s : 14: predicate.dict_get_item_eliminator 0.94% : 0.000002s : 14: predicate.dict_set_item_eliminator 1.10% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.19% : 0.000000s : 4: predicate.elim_not_effective 0.35% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.23% : 0.000003s : 18: predicate.environ_add_const_eliminate 0.99% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.02% : 0.000002s : 18: predicate.environ_get_depend_swap 1.57% : 0.000003s : 26: predicate.environ_get_eliminate 1.03% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.37% : 0.000003s : 22: predicate.exchange_switch_depend_value 2.34% : 0.000005s : 22: predicate.float_depend_g_call 0.53% : 0.000001s : 8: predicate.float_environ_get_switch 0.85% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.17% : 0.000000s : 4: predicate.fold_const_symbol 0.71% : 0.000002s : 8: predicate.get_grad_eliminate 0.30% : 0.000001s : 4: predicate.graph_param_transform 0.52% : 0.000001s : 8: predicate.incorporate_call 0.43% : 0.000001s : 8: predicate.incorporate_call_switch 5.89% : 0.000013s : 60: predicate.inline 0.94% : 0.000002s : 8: predicate.inline_without_move 0.30% : 0.000001s : 8: predicate.j_node_and_user_rematch 1.04% : 0.000002s : 8: predicate.less_batch_normalization 1.75% : 0.000004s : 24: predicate.list_to_tuple_eliminator_ 2.18% : 0.000005s : 38: predicate.load_eliminater 1.02% : 0.000002s : 4: predicate.loop_unroll_after_grad 2.44% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.72% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.59% : 0.000001s : 8: predicate.merge_addn 0.52% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.57% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 14: predicate.minmaximum_grad 1.57% : 0.000003s : 4: predicate.mutable_eliminate 0.29% : 0.000001s : 4: predicate.opt_reshape 0.40% : 0.000001s : 4: predicate.parallel_virtual_node 1.93% : 0.000004s : 22: predicate.partial_defer_inline 1.32% : 0.000003s : 20: predicate.partial_eliminate 1.19% : 0.000003s : 14: predicate.print_const_string_wrapper 0.66% : 0.000001s : 8: predicate.reduce_all_const_elim 1.42% : 0.000003s : 14: predicate.reduce_eliminate 2.38% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.50% : 0.000001s : 8: predicate.remove_not_recompute_node 1.38% : 0.000003s : 24: predicate.replace_applicator 0.73% : 0.000002s : 8: predicate.replace_old_param 0.26% : 0.000001s : 4: predicate.reset_defer_inline 0.88% : 0.000002s : 14: predicate.reshape_eliminate 0.53% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.46% : 0.000001s : 4: predicate.row_tensor_eliminate 0.84% : 0.000002s : 8: predicate.same_eliminate 0.41% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.69% : 0.000001s : 8: predicate.shard_identity_eliminate 0.62% : 0.000001s : 8: predicate.special_op_eliminate 0.58% : 0.000001s : 8: predicate.specialize_transform 0.94% : 0.000002s : 8: predicate.split_environ_get_set_with_tuple_value 0.94% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.44% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.51% : 0.000003s : 22: predicate.switch_defer_inline 1.95% : 0.000004s : 30: predicate.switch_layer_defer_inline 5.47% : 0.000012s : 75: predicate.switch_simplify 0.95% : 0.000002s : 14: predicate.tile_eliminate 1.00% : 0.000002s : 14: predicate.transpose_eliminate 1.44% : 0.000003s : 22: predicate.tuple_list_convert_item_index_to_positive 1.58% : 0.000003s : 22: predicate.tuple_list_get_item_const_eliminator 1.32% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 3.30% : 0.000007s : 32: predicate.tuple_list_get_item_eliminator 1.59% : 0.000003s : 22: predicate.tuple_list_get_set_item_eliminator 2.70% : 0.000006s : 30: predicate.tuple_list_set_item_eliminator 1.69% : 0.000004s : 24: predicate.tuple_to_list_eliminator_ 2.17% : 0.000005s : 38: predicate.updatestate_pure_node_eliminater 2.80% : 0.000006s : 46: predicate.updatestate_useless_node_eliminater 0.31% : 0.000001s : 4: predicate.value_based_eliminate 0.68% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.81% : 0.000002s : 8: predicate.virtual_output_eliminate 0.28% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.34% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003021 24 66.22% : 0.002000s : 16: func_graph_cloner_run.FuncGraphClonerGraph 33.78% : 0.001020s : 8: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.149152 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.22% : 0.004631s : 1: add_attr 0.21% : 0.004614s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000063s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000112s : 1: auto_monad 0.00% : 0.000023s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000500s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000020s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000030s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.00% : 0.000040s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000508s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.04% : 0.000776s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000016s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000020s : 1: opt.transform.mutable_eliminate 0.06% : 0.001327s : 78: opt.transform.opt_a 0.00% : 0.000030s : 1: opt.transform.opt_after_cconv 0.00% : 0.000028s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000106s : 28: opt.transform.opt_b 0.01% : 0.000200s : 2: opt.transform.opt_trans_graph 0.00% : 0.000037s : 4: opt.transform.symbol_engine_opt 0.26% : 0.005647s : 1: opt_a 0.01% : 0.000122s : 1: opt_after_cconv 0.03% : 0.000572s : 1: opt_after_jit_grad 0.01% : 0.000296s : 1: opt_b 0.39% : 0.008479s : 1: optimize 0.00% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000005s : 1: order_py_execute_after_rewriter 0.00% : 0.000026s : 1: overlap_grad_flash_sp 0.00% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 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% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 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% : 0.000052s : 1: pre_auto_parallel 0.00% : 0.000011s : 1: py_interpret_to_execute 0.00% : 0.000010s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 0.10% : 0.002188s : 1: renormalize.infer 0.05% : 0.001154s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000026s : 1: rewriter_after_opt_a 0.01% : 0.000283s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000008s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000090s : 1: symbol_engine_optimizer 0.01% : 0.000234s : 1: tuple_transform 98.48% : 2.116527s : 1: type_inference . [hook] pytest_runtest_teardown:test_adaptive_max_pool1d[KBK] tests/st/ops/test_ops_adaptive_max_pool1d.py::test_adaptive_max_pool1d[KBK],max_mem:20.0M =============================== 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 ================== 2 passed, 25 warnings in 159.26s (0:02:39) ==================