==================================================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_003/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 1 item test_mint_polar.py TotalTime = 0.792122, [21] [bootstrap]: 0.00096411 [type_inference]: 0.645636 [event_method]: 2.784e-05 [auto_monad]: 0.00013055 [graph_reusing]: 7.18998e-06 [inline]: 3.85e-06 [add_attr]: 0.137809, [1] [add_attr_with_inline]: 0.137793, [1] [Cycle 1]: 0.0001306, [2] [tag_attr]: 3.026e-05 [meta_addattr_fg_expand]: 6.84001e-06 [parallel-infer-symbol]: 4.03001e-06 [pre_auto_parallel]: 6.724e-05 [insert-virtual-dataset]: 3.53999e-06 [parallel-infer-symbol-second]: 1.05999e-06 [dataset_repeat_opt]: 2.41e-06 [pipeline_split]: 1.99999e-06 [optimize]: 0.00645277, [53] [py_interpret_to_execute]: 4.406e-05 [rewriter_before_opt_a]: 0.00011242 [opt_a]: 0.00359844, [2] [Cycle 1]: 0.00284208, [45] [expand_dump_flag]: 3.55e-06 [switch_simplify]: 4.978e-05 [loop_unroll]: 3.275e-05 [a_1]: 0.00080972 [with_stream_mark]: 2.792e-05 [recompute_prepare]: 1.423e-05 [updatestate_depend_eliminate]: 4.92999e-06 [updatestate_assign_eliminate]: 3.61001e-06 [updatestate_loads_eliminate]: 3.09001e-06 [parameter_eliminate]: 2.99001e-06 [a_2]: 8.569e-05 [accelerated_algorithm]: 9.48002e-06 [shard]: 2.50997e-06 [meta_shard_fg_expand]: 2.71999e-06 [shard_inline]: 6.56999e-06 [merge_send_recv]: 1.041e-05 [auto_parallel]: 9.76e-06 [parallel]: 4.522e-05 [flash_sp]: 1.332e-05 [merge_comm]: 4.67998e-06 [allreduce_fusion]: 3.36999e-06 [matmul_add_comm_reduction]: 1.229e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.302e-05 [virtual_dataset]: 8.47e-06 [get_grad_eliminate_]: 1.062e-05 [virtual_output]: 7.36999e-06 [merge_forward]: 4.00998e-06 [cell_reuse_recompute_pass]: 2.38002e-06 [offload_activation]: 1.124e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.923e-05 [merge_recompute_call_nodes]: 1.66002e-06 [before_grad]: 1.261e-05 [set_forward_comm_id_for_comm_node_pass]: 3.97002e-06 [meta_fg_expand]: 3.55998e-06 [flash_sp_send_recv_attached]: 3.25e-06 [receive_attached]: 1.612e-05 [after_resolve]: 1.659e-05 [a_after_grad]: 9.96e-06 [renormalize]: 0.00099445 [add_forward_monad_depend]: 9.20001e-06 [auto_monad_grad]: 3.45e-06 [auto_monad_eliminator]: 2.299e-05 [cse]: 5.073e-05 [a_3]: 6.097e-05 [Cycle 2]: 0.00074083, [45] [expand_dump_flag]: 2.61999e-06 [switch_simplify]: 1.048e-05 [loop_unroll]: 6.63e-06 [a_1]: 0.0001405 [with_stream_mark]: 2.058e-05 [recompute_prepare]: 7.14001e-06 [updatestate_depend_eliminate]: 4.38001e-06 [updatestate_assign_eliminate]: 3.68e-06 [updatestate_loads_eliminate]: 3.9e-06 [parameter_eliminate]: 2.73998e-06 [a_2]: 7.026e-05 [accelerated_algorithm]: 7.06001e-06 [shard]: 2.57001e-06 [meta_shard_fg_expand]: 1.96e-06 [shard_inline]: 5.85002e-06 [merge_send_recv]: 8.45001e-06 [auto_parallel]: 1.028e-05 [parallel]: 8.80001e-06 [flash_sp]: 4.60001e-06 [merge_comm]: 3.57997e-06 [allreduce_fusion]: 3.58e-06 [matmul_add_comm_reduction]: 9.74999e-06 [allreduce_slice_to_reducescatter]: 5.50004e-07 [virtual_shard_identity]: 8.37e-06 [virtual_dataset]: 6.15002e-06 [get_grad_eliminate_]: 7.71999e-06 [virtual_output]: 6.28e-06 [merge_forward]: 4.21001e-06 [cell_reuse_recompute_pass]: 2.40002e-06 [offload_activation]: 1.309e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.806e-05 [merge_recompute_call_nodes]: 1.32999e-06 [before_grad]: 1.108e-05 [set_forward_comm_id_for_comm_node_pass]: 4.54998e-06 [meta_fg_expand]: 2.69001e-06 [flash_sp_send_recv_attached]: 1.50001e-06 [receive_attached]: 2.49001e-06 [after_resolve]: 1.271e-05 [a_after_grad]: 9.52001e-06 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 1.99e-06 [auto_monad_grad]: 1.35999e-06 [auto_monad_eliminator]: 1.155e-05 [cse]: 1.735e-05 [a_3]: 3.526e-05 [py_interpret_to_execute_after_opt_a]: 1.815e-05 [slice_cell_reuse_recomputed_activation]: 2.41e-06 [rewriter_after_opt_a]: 7.386e-05 [convert_after_rewriter]: 1.031e-05 [order_py_execute_after_rewriter]: 5.78002e-06 [mutable_eliminate]: 0.0008878 [opt_b]: 0.00022466, [1] [Cycle 1]: 0.00021551, [7] [b_1]: 0.00012196 [b_2]: 8.40999e-06 [updatestate_depend_eliminate]: 1.02e-05 [updatestate_assign_eliminate]: 3.40998e-06 [updatestate_loads_eliminate]: 3.10002e-06 [renormalize]: 7.7e-07 [cse]: 2.811e-05 [optimize_parallel_all_gather_comm]: 2.161e-05 [overlap_param_gather]: 5.44e-06 [cconv]: 3.996e-05 [loop_unroll]: 0.00054574 [opt_after_cconv]: 0.00011552, [1] [Cycle 1]: 0.00010831, [7] [c_1]: 3.102e-05 [parameter_eliminate]: 6.29001e-06 [updatestate_depend_eliminate]: 8.59e-06 [updatestate_assign_eliminate]: 2.74999e-06 [updatestate_loads_eliminate]: 2.24001e-06 [cse]: 2.098e-05 [renormalize]: 5.60016e-07 [remove_dup_value]: 1.66e-05 [tuple_transform]: 8.522e-05, [1] [Cycle 1]: 7.947e-05, [4] [d_1]: 4.934e-05 [none_parameter_eliminate]: 2.01998e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 6.94999e-06 [partial_unused_args_eliminate]: 2.40002e-06 [add_recomputation]: 9.995e-05 [cse_after_recomputation]: 2.711e-05, [1] [Cycle 1]: 2.066e-05, [1] [cse]: 1.394e-05 [environ_conv]: 2.202e-05 [swap_dp_allreduce_reducescatter]: 5.94e-06 [bias_add_comm_swap]: 3.46999e-06 [label_micro_interleaved_index]: 5.92001e-06 [label_fine_grained_interleaved_index]: 3.29001e-06 [merge_cast_opt]: 1.84e-06 [slice_recompute_activation]: 2.44999e-06 [micro_interleaved_order_control]: 2.98e-06 [assign_add_opt]: 1.67999e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 1.39e-06 [full_micro_interleaved_order_control]: 2.29001e-06 [reorder_send_recv_between_fp_bp]: 3.11001e-06 [comm_op_add_attrs]: 1.40999e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.17999e-06 [overlap_opt_shard_in_pipeline]: 1.216e-05 [overlap_opt_shard_grad_in_pipeline]: 1.90001e-06 [control_data_broadcast_order]: 1.548e-05 [grouped_pairwise_exchange_alltoall]: 1.82001e-06 [offloading_packed_experts]: 3.95998e-06 [overlap_recompute_and_grad_model_parallel]: 5.49998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57001e-06 [overlap_recompute_comm]: 2.34999e-06 [overlap_grad_ring_attention]: 5.70001e-06 [overlap_grad_flash_sp]: 4.873e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.37999e-06 [split_layernorm_comm]: 2.17001e-06 [handle_group_info]: 1.20001e-06 [symbol_engine_optimizer]: 8.689e-05, [1] [Cycle 1]: 8.102e-05, [6] [build]: 4.48999e-06 [elim_shapecalc]: 1.239e-05 [elim_not_effective]: 1.39e-05 [opt_reshape]: 7.85e-06 [fold_const_symbol]: 1.046e-05 [renormalize]: 2.50002e-07 [detach_backward]: 2.42001e-06 [pipeline_parallel_scheduler]: 1.55999e-06 [auto_monad_reorder]: 2.599e-05 [get_jit_bprop_graph]: 1.96998e-06 [rewriter_after_jit_bprop_graph]: 6.07001e-06 [opt_after_jit_grad]: 0.0006844 [validate]: 6.876e-05 Sums bootstrap : 0.000964s : 0.15% type_inference : 0.645636s : 98.86% event_method : 0.000028s : 0.00% auto_monad : 0.000131s : 0.02% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000030s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000067s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000044s : 0.01% optimize.rewriter_before_opt_a : 0.000112s : 0.02% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.01% optimize.opt_a.loop_unroll : 0.000039s : 0.01% optimize.opt_a.a_1 : 0.000950s : 0.15% optimize.opt_a.with_stream_mark : 0.000048s : 0.01% optimize.opt_a.recompute_prepare : 0.000021s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000156s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000017s : 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 : 0.000012s : 0.00% optimize.opt_a.merge_send_recv : 0.000019s : 0.00% optimize.opt_a.auto_parallel : 0.000020s : 0.00% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000018s : 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 : 0.000022s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 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_ : 0.000018s : 0.00% optimize.opt_a.virtual_output : 0.000014s : 0.00% optimize.opt_a.merge_forward : 0.000008s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000024s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000037s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000024s : 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 : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000019s : 0.00% optimize.opt_a.after_resolve : 0.000029s : 0.00% optimize.opt_a.a_after_grad : 0.000019s : 0.00% optimize.opt_a.renormalize : 0.000995s : 0.15% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000035s : 0.01% optimize.opt_a.cse : 0.000068s : 0.01% optimize.opt_a.a_3 : 0.000096s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000018s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000074s : 0.01% optimize.convert_after_rewriter : 0.000010s : 0.00% optimize.order_py_execute_after_rewriter : 0.000006s : 0.00% optimize.mutable_eliminate : 0.000888s : 0.14% optimize.opt_b.b_1 : 0.000122s : 0.02% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000028s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.00% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000040s : 0.01% optimize.loop_unroll : 0.000546s : 0.08% optimize.opt_after_cconv.c_1 : 0.000031s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 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 : 0.000021s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000049s : 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 : 0.000007s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000100s : 0.02% optimize.cse_after_recomputation.cse : 0.000014s : 0.00% optimize.environ_conv : 0.000022s : 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 : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 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 : 0.000012s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000015s : 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000049s : 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 : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000012s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000014s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 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 : 0.000006s : 0.00% opt_after_jit_grad : 0.000684s : 0.10% validate : 0.000069s : 0.01% Time group info: ------[substitution.] 0.000269 29 0.88% : 0.000002s : 2: substitution.elim_not_effective 0.73% : 0.000002s : 2: substitution.fold_const_symbol 2.91% : 0.000008s : 4: substitution.graph_param_transform 81.25% : 0.000218s : 5: substitution.inline 1.85% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.34% : 0.000006s : 4: substitution.remove_not_recompute_node 2.82% : 0.000008s : 4: substitution.replace_old_param 7.21% : 0.000019s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.645499 2 76.91% : 0.496435s : 1: type_inference.infer 23.09% : 0.149063s : 1: type_inference.specialize ------[replace.] 0.000120 9 43.23% : 0.000052s : 5: replace.inline 56.77% : 0.000068s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000231 9 93.01% : 0.000215s : 5: match.inline 6.99% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000236 1341 1.15% : 0.000003s : 14: predicate.accumulaten_eliminater 1.21% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.61% : 0.000001s : 8: predicate.addn_check_dump 0.85% : 0.000002s : 14: predicate.addn_zero_filter 0.74% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.90% : 0.000004s : 22: predicate.arithmetic_simplify 1.02% : 0.000002s : 14: predicate.cast_eliminate 0.60% : 0.000001s : 8: predicate.check_bprop_eliminate 0.52% : 0.000001s : 8: predicate.compare_switch_simplify 0.15% : 0.000000s : 4: predicate.const_output_eliminate 0.59% : 0.000001s : 8: predicate.depend_value_elim 0.89% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.92% : 0.000002s : 14: predicate.dict_get_item_eliminator 1.04% : 0.000002s : 14: predicate.dict_set_item_eliminator 1.00% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 4: predicate.elim_not_effective 0.41% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000003s : 18: predicate.environ_add_const_eliminate 0.96% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.11% : 0.000003s : 18: predicate.environ_get_depend_swap 1.52% : 0.000004s : 26: predicate.environ_get_eliminate 1.08% : 0.000003s : 18: predicate.environ_get_set_eliminate 1.62% : 0.000004s : 23: predicate.exchange_switch_depend_value 2.37% : 0.000006s : 23: predicate.float_depend_g_call 0.49% : 0.000001s : 8: predicate.float_environ_get_switch 1.06% : 0.000003s : 12: predicate.float_tuple_getitem_switch 0.16% : 0.000000s : 4: predicate.fold_const_symbol 0.85% : 0.000002s : 8: predicate.get_grad_eliminate 0.26% : 0.000001s : 4: predicate.graph_param_transform 0.49% : 0.000001s : 8: predicate.incorporate_call 0.41% : 0.000001s : 8: predicate.incorporate_call_switch 6.00% : 0.000014s : 61: predicate.inline 0.74% : 0.000002s : 8: predicate.inline_without_move 0.29% : 0.000001s : 8: predicate.j_node_and_user_rematch 1.07% : 0.000003s : 8: predicate.less_batch_normalization 1.80% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 2.78% : 0.000007s : 40: predicate.load_eliminater 1.00% : 0.000002s : 4: predicate.loop_unroll_after_grad 2.42% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.56% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.64% : 0.000002s : 8: predicate.merge_addn 0.56% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.56% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.93% : 0.000002s : 14: predicate.minmaximum_grad 1.48% : 0.000004s : 4: predicate.mutable_eliminate 0.36% : 0.000001s : 4: predicate.opt_reshape 0.49% : 0.000001s : 4: predicate.parallel_virtual_node 2.01% : 0.000005s : 23: predicate.partial_defer_inline 1.39% : 0.000003s : 22: predicate.partial_eliminate 1.08% : 0.000003s : 14: predicate.print_const_string_wrapper 0.50% : 0.000001s : 8: predicate.reduce_all_const_elim 1.24% : 0.000003s : 14: predicate.reduce_eliminate 2.43% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000001s : 8: predicate.remove_not_recompute_node 1.29% : 0.000003s : 26: predicate.replace_applicator 0.51% : 0.000001s : 8: predicate.replace_old_param 0.41% : 0.000001s : 4: predicate.reset_defer_inline 0.97% : 0.000002s : 14: predicate.reshape_eliminate 0.61% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.36% : 0.000001s : 4: predicate.row_tensor_eliminate 0.64% : 0.000002s : 8: predicate.same_eliminate 0.34% : 0.000001s : 8: predicate.set_cell_output_no_recompute 1.01% : 0.000002s : 8: predicate.shard_identity_eliminate 0.70% : 0.000002s : 8: predicate.special_op_eliminate 0.60% : 0.000001s : 8: predicate.specialize_transform 1.09% : 0.000003s : 8: predicate.split_environ_get_set_with_tuple_value 0.75% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.29% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.55% : 0.000004s : 23: predicate.switch_defer_inline 1.97% : 0.000005s : 31: predicate.switch_layer_defer_inline 5.04% : 0.000012s : 74: predicate.switch_simplify 0.86% : 0.000002s : 14: predicate.tile_eliminate 0.94% : 0.000002s : 14: predicate.transpose_eliminate 1.52% : 0.000004s : 22: predicate.tuple_list_convert_item_index_to_positive 1.48% : 0.000004s : 22: predicate.tuple_list_get_item_const_eliminator 1.44% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 3.18% : 0.000008s : 34: predicate.tuple_list_get_item_eliminator 1.57% : 0.000004s : 22: predicate.tuple_list_get_set_item_eliminator 2.03% : 0.000005s : 30: predicate.tuple_list_set_item_eliminator 1.83% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 2.16% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 3.04% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.34% : 0.000001s : 4: predicate.value_based_eliminate 0.76% : 0.000002s : 8: predicate.virtual_dataset_eliminate 0.64% : 0.000002s : 8: predicate.virtual_output_eliminate 0.22% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.42% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000976 12 48.46% : 0.000473s : 5: func_graph_cloner_run.FuncGraphClonerGraph 51.54% : 0.000503s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.938902 192 0.00% : 0.000004s : 1: ForceFp32Comm 14.68% : 0.137816s : 1: add_attr 14.68% : 0.137798s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000106s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.01% : 0.000137s : 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 0.11% : 0.001010s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000019s : 1: control_data_broadcast_order 0.00% : 0.000014s : 1: convert_after_rewriter 0.00% : 0.000030s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000026s : 1: environ_conv 0.00% : 0.000037s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.06% : 0.000557s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.10% : 0.000903s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000015s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000024s : 1: opt.transform.mutable_eliminate 0.15% : 0.001418s : 78: opt.transform.opt_a 0.00% : 0.000030s : 1: opt.transform.opt_after_cconv 0.00% : 0.000031s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000101s : 28: opt.transform.opt_b 0.01% : 0.000054s : 2: opt.transform.opt_trans_graph 0.00% : 0.000040s : 4: opt.transform.symbol_engine_opt 0.38% : 0.003603s : 1: opt_a 0.01% : 0.000119s : 1: opt_after_cconv 0.07% : 0.000700s : 1: opt_after_jit_grad 0.02% : 0.000229s : 1: opt_b 0.69% : 0.006459s : 1: optimize 0.00% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.01% : 0.000053s : 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% : 0.000016s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000005s : 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% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000073s : 1: pre_auto_parallel 0.01% : 0.000049s : 1: py_interpret_to_execute 0.00% : 0.000022s : 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% : 0.000561s : 1: renormalize.infer 0.04% : 0.000420s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000081s : 1: rewriter_after_opt_a 0.01% : 0.000120s : 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% : 0.000090s : 1: symbol_engine_optimizer 0.01% : 0.000088s : 1: tuple_transform 68.77% : 0.645676s : 1: type_inference TotalTime = 0.327439, [21] [bootstrap]: 0.00054886 [type_inference]: 0.162699 [event_method]: 2.221e-05 [auto_monad]: 7.527e-05 [graph_reusing]: 6.93998e-06 [inline]: 3.26001e-06 [add_attr]: 0.00465251, [1] [add_attr_with_inline]: 0.00463818, [1] [Cycle 1]: 8.29e-05, [2] [tag_attr]: 2.592e-05 [meta_addattr_fg_expand]: 6.21998e-06 [parallel-infer-symbol]: 4.17e-06 [pre_auto_parallel]: 5.084e-05 [insert-virtual-dataset]: 2.74999e-06 [parallel-infer-symbol-second]: 1.04e-06 [dataset_repeat_opt]: 2.21e-06 [pipeline_split]: 1.87999e-06 [optimize]: 0.158375, [53] [py_interpret_to_execute]: 3.742e-05 [rewriter_before_opt_a]: 9.946e-05 [opt_a]: 0.155531, [2] [Cycle 1]: 0.00256144, [45] [expand_dump_flag]: 3.28998e-06 [switch_simplify]: 4.901e-05 [loop_unroll]: 3.278e-05 [a_1]: 0.0007424 [with_stream_mark]: 2.451e-05 [recompute_prepare]: 1.352e-05 [updatestate_depend_eliminate]: 5.83997e-06 [updatestate_assign_eliminate]: 4.50001e-06 [updatestate_loads_eliminate]: 3.67998e-06 [parameter_eliminate]: 2.68e-06 [a_2]: 8.045e-05 [accelerated_algorithm]: 8.33001e-06 [shard]: 2.00002e-06 [meta_shard_fg_expand]: 2.37001e-06 [shard_inline]: 6.68e-06 [merge_send_recv]: 1.007e-05 [auto_parallel]: 1.06e-05 [parallel]: 3.693e-05 [flash_sp]: 1.241e-05 [merge_comm]: 4.1e-06 [allreduce_fusion]: 3.27002e-06 [matmul_add_comm_reduction]: 1.123e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.088e-05 [virtual_dataset]: 6.89001e-06 [get_grad_eliminate_]: 6.17999e-06 [virtual_output]: 6.24999e-06 [merge_forward]: 4.62e-06 [cell_reuse_recompute_pass]: 1.39e-06 [offload_activation]: 1.169e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.735e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 1.076e-05 [set_forward_comm_id_for_comm_node_pass]: 3.28e-06 [meta_fg_expand]: 3.65998e-06 [flash_sp_send_recv_attached]: 3.25002e-06 [receive_attached]: 2.76999e-06 [after_resolve]: 1.152e-05 [a_after_grad]: 1.018e-05 [renormalize]: 0.00097045 [add_forward_monad_depend]: 8.29002e-06 [auto_monad_grad]: 2.91999e-06 [auto_monad_eliminator]: 1.958e-05 [cse]: 3.518e-05 [a_3]: 5.519e-05 [Cycle 2]: 0.152956, [45] [expand_dump_flag]: 2.33998e-06 [switch_simplify]: 9.49e-06 [loop_unroll]: 6.14001e-06 [a_1]: 0.00013497 [with_stream_mark]: 1.855e-05 [recompute_prepare]: 6.66999e-06 [updatestate_depend_eliminate]: 3.88999e-06 [updatestate_assign_eliminate]: 3.61999e-06 [updatestate_loads_eliminate]: 2.86e-06 [parameter_eliminate]: 1.50999e-06 [a_2]: 6.994e-05 [accelerated_algorithm]: 6.44999e-06 [shard]: 1.44e-06 [meta_shard_fg_expand]: 2.15002e-06 [shard_inline]: 5.72001e-06 [merge_send_recv]: 6.86999e-06 [auto_parallel]: 9.07001e-06 [parallel]: 7.23e-06 [flash_sp]: 4.05e-06 [merge_comm]: 3.36999e-06 [allreduce_fusion]: 3.19001e-06 [matmul_add_comm_reduction]: 7.15003e-06 [allreduce_slice_to_reducescatter]: 8.09989e-07 [virtual_shard_identity]: 7.70998e-06 [virtual_dataset]: 5.69e-06 [get_grad_eliminate_]: 5.76e-06 [virtual_output]: 5.92999e-06 [merge_forward]: 3.86999e-06 [cell_reuse_recompute_pass]: 2.01e-06 [offload_activation]: 8.11002e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.522e-05 [merge_recompute_call_nodes]: 1.04e-06 [before_grad]: 9.39e-06 [set_forward_comm_id_for_comm_node_pass]: 3.7e-06 [meta_fg_expand]: 1.81998e-06 [flash_sp_send_recv_attached]: 1.24e-06 [receive_attached]: 1.59e-06 [after_resolve]: 7.128e-05 [a_after_grad]: 1.97e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.126e-05 [auto_monad_grad]: 3.38e-06 [auto_monad_eliminator]: 3.355e-05 [cse]: 4.195e-05 [a_3]: 4.976e-05 [py_interpret_to_execute_after_opt_a]: 2.424e-05 [slice_cell_reuse_recomputed_activation]: 2.56998e-06 [rewriter_after_opt_a]: 4.867e-05 [convert_after_rewriter]: 8.33999e-06 [order_py_execute_after_rewriter]: 5.94e-06 [mutable_eliminate]: 0.00090019 [opt_b]: 0.00024701, [1] [Cycle 1]: 0.00023504, [7] [b_1]: 0.00013342 [b_2]: 1.011e-05 [updatestate_depend_eliminate]: 1.224e-05 [updatestate_assign_eliminate]: 3.6e-06 [updatestate_loads_eliminate]: 2.98e-06 [renormalize]: 9.09989e-07 [cse]: 3.319e-05 [optimize_parallel_all_gather_comm]: 2.717e-05 [overlap_param_gather]: 2.44001e-06 [cconv]: 4.287e-05 [loop_unroll]: 0.00057342 [opt_after_cconv]: 0.00012646, [1] [Cycle 1]: 0.00011671, [7] [c_1]: 3.295e-05 [parameter_eliminate]: 6.39999e-06 [updatestate_depend_eliminate]: 7.50998e-06 [updatestate_assign_eliminate]: 2.61e-06 [updatestate_loads_eliminate]: 2.58003e-06 [cse]: 2.648e-05 [renormalize]: 5.59987e-07 [remove_dup_value]: 1.685e-05 [tuple_transform]: 9.089e-05, [1] [Cycle 1]: 8.509e-05, [4] [d_1]: 5.386e-05 [none_parameter_eliminate]: 2.08002e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 8.27998e-06 [partial_unused_args_eliminate]: 2.58998e-06 [add_recomputation]: 6.361e-05 [cse_after_recomputation]: 2.926e-05, [1] [Cycle 1]: 2.314e-05, [1] [cse]: 1.588e-05 [environ_conv]: 7.78001e-06 [swap_dp_allreduce_reducescatter]: 5.99e-06 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 6.36e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.62999e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.51e-06 [assign_add_opt]: 1.52999e-06 [ForceFp32Comm]: 1.11002e-06 [remove_cast_before_assign_add]: 1.52999e-06 [full_micro_interleaved_order_control]: 2.53998e-06 [reorder_send_recv_between_fp_bp]: 2.94999e-06 [comm_op_add_attrs]: 1.07998e-06 [add_comm_op_reuse_tag]: 1.00999e-06 [interleave_split_concat_branches]: 1.15999e-06 [interleave_parallel_branches]: 1.12e-06 [overlap_opt_shard_in_pipeline]: 1.22999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.96998e-06 [control_data_broadcast_order]: 1.478e-05 [grouped_pairwise_exchange_alltoall]: 2.26998e-06 [offloading_packed_experts]: 4.95999e-06 [overlap_recompute_and_grad_model_parallel]: 6.34999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.33002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.69999e-06 [overlap_grad_ring_attention]: 4.50999e-06 [overlap_grad_flash_sp]: 2.546e-05 [begin_end_overlap_inline]: 5.20027e-07 [split_matmul_comm_elemetwise]: 3.16999e-06 [split_layernorm_comm]: 1.92999e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 9.661e-05, [1] [Cycle 1]: 9.13e-05, [6] [build]: 5.02e-06 [elim_shapecalc]: 1.683e-05 [elim_not_effective]: 1.385e-05 [opt_reshape]: 7.58999e-06 [fold_const_symbol]: 9.92999e-06 [renormalize]: 3.60014e-07 [detach_backward]: 3.01001e-06 [pipeline_parallel_scheduler]: 1.66998e-06 [auto_monad_reorder]: 2.363e-05 [get_jit_bprop_graph]: 2.88e-06 [rewriter_after_jit_bprop_graph]: 7.87e-06 [opt_after_jit_grad]: 0.00071326 [validate]: 5.22e-05 Sums bootstrap : 0.000549s : 0.32% type_inference : 0.162699s : 95.97% event_method : 0.000022s : 0.01% auto_monad : 0.000075s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000051s : 0.03% 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 : 0.02% optimize.rewriter_before_opt_a : 0.000099s : 0.06% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.03% optimize.opt_a.loop_unroll : 0.000039s : 0.02% optimize.opt_a.a_1 : 0.000877s : 0.52% optimize.opt_a.with_stream_mark : 0.000043s : 0.03% optimize.opt_a.recompute_prepare : 0.000020s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000150s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000015s : 0.01% optimize.opt_a.shard : 0.000003s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.01% optimize.opt_a.merge_send_recv : 0.000017s : 0.01% optimize.opt_a.auto_parallel : 0.000020s : 0.01% optimize.opt_a.parallel : 0.000044s : 0.03% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000007s : 0.00% optimize.opt_a.allreduce_fusion : 0.000006s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000018s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000019s : 0.01% optimize.opt_a.virtual_dataset : 0.000013s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000012s : 0.01% optimize.opt_a.virtual_output : 0.000012s : 0.01% optimize.opt_a.merge_forward : 0.000008s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000020s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000033s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000020s : 0.01% 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 : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000083s : 0.05% optimize.opt_a.a_after_grad : 0.000030s : 0.02% optimize.opt_a.renormalize : 0.000971s : 0.57% optimize.opt_a.add_forward_monad_depend : 0.000020s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000053s : 0.03% optimize.opt_a.cse : 0.000077s : 0.05% optimize.opt_a.a_3 : 0.000105s : 0.06% optimize.py_interpret_to_execute_after_opt_a : 0.000024s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000049s : 0.03% optimize.convert_after_rewriter : 0.000008s : 0.00% optimize.order_py_execute_after_rewriter : 0.000006s : 0.00% optimize.mutable_eliminate : 0.000900s : 0.53% optimize.opt_b.b_1 : 0.000133s : 0.08% optimize.opt_b.b_2 : 0.000010s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000033s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.03% optimize.loop_unroll : 0.000573s : 0.34% optimize.opt_after_cconv.c_1 : 0.000033s : 0.02% 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 : 0.000026s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.01% optimize.tuple_transform.d_1 : 0.000054s : 0.03% 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 : 0.000003s : 0.00% optimize.add_recomputation : 0.000064s : 0.04% optimize.cse_after_recomputation.cse : 0.000016s : 0.01% optimize.environ_conv : 0.000008s : 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 : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000015s : 0.01% 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 : 0.000025s : 0.02% 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 : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000014s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.01% 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 : 0.000024s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000713s : 0.42% validate : 0.000052s : 0.03% Time group info: ------[substitution.] 0.000265 29 0.70% : 0.000002s : 2: substitution.elim_not_effective 0.49% : 0.000001s : 2: substitution.fold_const_symbol 2.80% : 0.000007s : 4: substitution.graph_param_transform 81.87% : 0.000217s : 5: substitution.inline 1.47% : 0.000004s : 4: substitution.j_node_and_user_rematch 2.17% : 0.000006s : 4: substitution.remove_not_recompute_node 3.78% : 0.000010s : 4: substitution.replace_old_param 6.72% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.162615 2 99.44% : 0.161701s : 1: type_inference.infer 0.56% : 0.000914s : 1: type_inference.specialize ------[replace.] 0.000079 9 68.35% : 0.000054s : 5: replace.inline 31.65% : 0.000025s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000229 9 93.09% : 0.000214s : 5: match.inline 6.91% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000247 1341 1.03% : 0.000003s : 14: predicate.accumulaten_eliminater 1.31% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.54% : 0.000001s : 8: predicate.addn_check_dump 0.91% : 0.000002s : 14: predicate.addn_zero_filter 0.74% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.56% : 0.000004s : 22: predicate.arithmetic_simplify 0.89% : 0.000002s : 14: predicate.cast_eliminate 0.87% : 0.000002s : 8: predicate.check_bprop_eliminate 0.58% : 0.000001s : 8: predicate.compare_switch_simplify 0.15% : 0.000000s : 4: predicate.const_output_eliminate 0.59% : 0.000001s : 8: predicate.depend_value_elim 0.80% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.89% : 0.000002s : 14: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 14: predicate.dict_set_item_eliminator 0.95% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 4: predicate.elim_not_effective 0.51% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.01% : 0.000002s : 18: predicate.environ_get_add_eliminate 0.94% : 0.000002s : 18: predicate.environ_get_depend_swap 1.52% : 0.000004s : 26: predicate.environ_get_eliminate 0.99% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.25% : 0.000003s : 23: predicate.exchange_switch_depend_value 2.31% : 0.000006s : 23: predicate.float_depend_g_call 0.41% : 0.000001s : 8: predicate.float_environ_get_switch 0.94% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.15% : 0.000000s : 4: predicate.fold_const_symbol 0.53% : 0.000001s : 8: predicate.get_grad_eliminate 0.29% : 0.000001s : 4: predicate.graph_param_transform 0.46% : 0.000001s : 8: predicate.incorporate_call 0.41% : 0.000001s : 8: predicate.incorporate_call_switch 5.48% : 0.000014s : 61: predicate.inline 1.48% : 0.000004s : 8: predicate.inline_without_move 0.26% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.75% : 0.000002s : 8: predicate.less_batch_normalization 1.74% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 2.18% : 0.000005s : 40: predicate.load_eliminater 1.21% : 0.000003s : 4: predicate.loop_unroll_after_grad 2.36% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.83% : 0.000005s : 22: predicate.make_slice_get_slice_eliminator 0.65% : 0.000002s : 8: predicate.merge_addn 0.57% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.66% : 0.000002s : 8: predicate.mini_step_allgather_replace 0.75% : 0.000002s : 14: predicate.minmaximum_grad 2.14% : 0.000005s : 4: predicate.mutable_eliminate 0.45% : 0.000001s : 4: predicate.opt_reshape 0.59% : 0.000001s : 4: predicate.parallel_virtual_node 1.86% : 0.000005s : 23: predicate.partial_defer_inline 1.30% : 0.000003s : 22: predicate.partial_eliminate 0.77% : 0.000002s : 14: predicate.print_const_string_wrapper 0.53% : 0.000001s : 8: predicate.reduce_all_const_elim 0.96% : 0.000002s : 14: predicate.reduce_eliminate 2.30% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000001s : 8: predicate.remove_not_recompute_node 1.22% : 0.000003s : 26: predicate.replace_applicator 1.11% : 0.000003s : 8: predicate.replace_old_param 0.41% : 0.000001s : 4: predicate.reset_defer_inline 0.98% : 0.000002s : 14: predicate.reshape_eliminate 0.91% : 0.000002s : 8: predicate.row_tensor_add_zeros_like 0.49% : 0.000001s : 4: predicate.row_tensor_eliminate 0.85% : 0.000002s : 8: predicate.same_eliminate 0.46% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.88% : 0.000002s : 8: predicate.shard_identity_eliminate 0.58% : 0.000001s : 8: predicate.special_op_eliminate 0.60% : 0.000001s : 8: predicate.specialize_transform 1.56% : 0.000004s : 8: predicate.split_environ_get_set_with_tuple_value 1.98% : 0.000005s : 8: predicate.stack_unstack_eliminate 0.34% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.38% : 0.000003s : 23: predicate.switch_defer_inline 2.06% : 0.000005s : 31: predicate.switch_layer_defer_inline 4.95% : 0.000012s : 74: predicate.switch_simplify 0.85% : 0.000002s : 14: predicate.tile_eliminate 1.01% : 0.000003s : 14: predicate.transpose_eliminate 1.52% : 0.000004s : 22: predicate.tuple_list_convert_item_index_to_positive 1.47% : 0.000004s : 22: predicate.tuple_list_get_item_const_eliminator 1.24% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 2.81% : 0.000007s : 34: predicate.tuple_list_get_item_eliminator 1.42% : 0.000004s : 22: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000006s : 30: predicate.tuple_list_set_item_eliminator 1.54% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 2.19% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.99% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.43% : 0.000001s : 4: predicate.value_based_eliminate 0.72% : 0.000002s : 8: predicate.virtual_dataset_eliminate 0.86% : 0.000002s : 8: predicate.virtual_output_eliminate 0.22% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.38% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000727 12 52.85% : 0.000384s : 5: func_graph_cloner_run.FuncGraphClonerGraph 47.15% : 0.000343s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.492977 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.95% : 0.004659s : 1: add_attr 0.94% : 0.004643s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.01% : 0.000071s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000081s : 1: auto_monad 0.01% : 0.000029s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.12% : 0.000579s : 1: bootstrap 0.01% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000020s : 1: control_data_broadcast_order 0.00% : 0.000012s : 1: convert_after_rewriter 0.01% : 0.000032s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000012s : 1: environ_conv 0.01% : 0.000029s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.12% : 0.000589s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.19% : 0.000920s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000026s : 1: opt.transform.mutable_eliminate 0.28% : 0.001386s : 78: opt.transform.opt_a 0.01% : 0.000031s : 1: opt.transform.opt_after_cconv 0.01% : 0.000036s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000106s : 28: opt.transform.opt_b 0.01% : 0.000059s : 2: opt.transform.opt_trans_graph 0.01% : 0.000043s : 4: opt.transform.symbol_engine_opt 31.55% : 0.155535s : 1: opt_a 0.03% : 0.000130s : 1: opt_after_cconv 0.15% : 0.000735s : 1: opt_after_jit_grad 0.05% : 0.000252s : 1: opt_b 32.13% : 0.158382s : 1: optimize 0.01% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.01% : 0.000030s : 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% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000056s : 1: pre_auto_parallel 0.01% : 0.000042s : 1: py_interpret_to_execute 0.01% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 0.11% : 0.000549s : 1: renormalize.infer 0.08% : 0.000410s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000054s : 1: rewriter_after_opt_a 0.02% : 0.000106s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000007s : 1: slice_recompute_activation 0.00% : 0.000007s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000100s : 1: symbol_engine_optimizer 0.02% : 0.000094s : 1: tuple_transform 33.01% : 0.162723s : 1: type_inference TotalTime = 0.205802, [21] [bootstrap]: 0.00048874 [type_inference]: 0.194256 [event_method]: 2.578e-05 [auto_monad]: 7.749e-05 [graph_reusing]: 7.36999e-06 [inline]: 3.03e-06 [add_attr]: 0.00410198, [1] [add_attr_with_inline]: 0.00408888, [1] [Cycle 1]: 8.143e-05, [2] [tag_attr]: 2.582e-05 [meta_addattr_fg_expand]: 5.79999e-06 [parallel-infer-symbol]: 3.73001e-06 [pre_auto_parallel]: 4.338e-05 [insert-virtual-dataset]: 2.66e-06 [parallel-infer-symbol-second]: 1.08001e-06 [dataset_repeat_opt]: 2.56e-06 [pipeline_split]: 1.71998e-06 [optimize]: 0.00589447, [53] [py_interpret_to_execute]: 3.474e-05 [rewriter_before_opt_a]: 9.232e-05 [opt_a]: 0.00327364, [2] [Cycle 1]: 0.00257502, [45] [expand_dump_flag]: 3.66001e-06 [switch_simplify]: 4.653e-05 [loop_unroll]: 3.223e-05 [a_1]: 0.00071531 [with_stream_mark]: 2.252e-05 [recompute_prepare]: 9.61998e-06 [updatestate_depend_eliminate]: 4.43999e-06 [updatestate_assign_eliminate]: 3.76001e-06 [updatestate_loads_eliminate]: 3.21001e-06 [parameter_eliminate]: 2.11e-06 [a_2]: 7.687e-05 [accelerated_algorithm]: 7.53e-06 [shard]: 2.26e-06 [meta_shard_fg_expand]: 1.72999e-06 [shard_inline]: 5.92001e-06 [merge_send_recv]: 9.71e-06 [auto_parallel]: 8.34002e-06 [parallel]: 2.337e-05 [flash_sp]: 1.168e-05 [merge_comm]: 5.20999e-06 [allreduce_fusion]: 3.70003e-06 [matmul_add_comm_reduction]: 1.076e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 9.97001e-06 [virtual_dataset]: 6.98998e-06 [get_grad_eliminate_]: 5.96e-06 [virtual_output]: 5.97001e-06 [merge_forward]: 4.53999e-06 [cell_reuse_recompute_pass]: 1.18001e-06 [offload_activation]: 1.209e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.436e-05 [merge_recompute_call_nodes]: 1.74998e-06 [before_grad]: 1.214e-05 [set_forward_comm_id_for_comm_node_pass]: 4.38001e-06 [meta_fg_expand]: 3.21999e-06 [flash_sp_send_recv_attached]: 3.37002e-06 [receive_attached]: 2.76e-06 [after_resolve]: 1.211e-05 [a_after_grad]: 9.09e-06 [renormalize]: 0.0009715 [add_forward_monad_depend]: 7.8e-06 [auto_monad_grad]: 2.69999e-06 [auto_monad_eliminator]: 1.767e-05 [cse]: 3.149e-05 [a_3]: 9.763e-05 [Cycle 2]: 0.00068461, [45] [expand_dump_flag]: 1.89e-06 [switch_simplify]: 7.9e-06 [loop_unroll]: 6.48e-06 [a_1]: 0.00012419 [with_stream_mark]: 1.745e-05 [recompute_prepare]: 7.47002e-06 [updatestate_depend_eliminate]: 4.06001e-06 [updatestate_assign_eliminate]: 2.99001e-06 [updatestate_loads_eliminate]: 2.61e-06 [parameter_eliminate]: 1.34e-06 [a_2]: 6.973e-05 [accelerated_algorithm]: 6.44999e-06 [shard]: 1.46002e-06 [meta_shard_fg_expand]: 1.87999e-06 [shard_inline]: 6.69999e-06 [merge_send_recv]: 6.51e-06 [auto_parallel]: 7.28e-06 [parallel]: 6.18998e-06 [flash_sp]: 5.91e-06 [merge_comm]: 3.27002e-06 [allreduce_fusion]: 2.86e-06 [matmul_add_comm_reduction]: 7.32002e-06 [allreduce_slice_to_reducescatter]: 3.39991e-07 [virtual_shard_identity]: 6.76e-06 [virtual_dataset]: 5.66e-06 [get_grad_eliminate_]: 5.64e-06 [virtual_output]: 5.29998e-06 [merge_forward]: 3.9e-06 [cell_reuse_recompute_pass]: 2.36e-06 [offload_activation]: 8.95999e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.547e-05 [merge_recompute_call_nodes]: 1.34998e-06 [before_grad]: 1.009e-05 [set_forward_comm_id_for_comm_node_pass]: 3.66999e-06 [meta_fg_expand]: 1.84e-06 [flash_sp_send_recv_attached]: 1.37999e-06 [receive_attached]: 1.52999e-06 [after_resolve]: 1.074e-05 [a_after_grad]: 9.44998e-06 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.57001e-06 [auto_monad_grad]: 1.82999e-06 [auto_monad_eliminator]: 9.04e-06 [cse]: 1.861e-05 [a_3]: 3.587e-05 [py_interpret_to_execute_after_opt_a]: 1.584e-05 [slice_cell_reuse_recomputed_activation]: 2.69001e-06 [rewriter_after_opt_a]: 4.429e-05 [convert_after_rewriter]: 7.73999e-06 [order_py_execute_after_rewriter]: 5.50001e-06 [mutable_eliminate]: 0.00081188 [opt_b]: 0.00021901, [1] [Cycle 1]: 0.00021027, [7] [b_1]: 0.0001192 [b_2]: 9.00999e-06 [updatestate_depend_eliminate]: 9.45001e-06 [updatestate_assign_eliminate]: 2.91e-06 [updatestate_loads_eliminate]: 3.36999e-06 [renormalize]: 5.69999e-07 [cse]: 2.97e-05 [optimize_parallel_all_gather_comm]: 2.265e-05 [overlap_param_gather]: 2.61e-06 [cconv]: 3.833e-05 [loop_unroll]: 0.00056209 [opt_after_cconv]: 0.00011732, [1] [Cycle 1]: 0.00010982, [7] [c_1]: 3.045e-05 [parameter_eliminate]: 5.48002e-06 [updatestate_depend_eliminate]: 6.78e-06 [updatestate_assign_eliminate]: 3.2e-06 [updatestate_loads_eliminate]: 2.59999e-06 [cse]: 2.436e-05 [renormalize]: 1.19e-06 [remove_dup_value]: 1.58e-05 [tuple_transform]: 8.154e-05, [1] [Cycle 1]: 7.684e-05, [4] [d_1]: 4.925e-05 [none_parameter_eliminate]: 1.72001e-06 [renormalize]: 2.50002e-07 [switch_simplify]: 7.42998e-06 [partial_unused_args_eliminate]: 2.29001e-06 [add_recomputation]: 5.692e-05 [cse_after_recomputation]: 2.489e-05, [1] [Cycle 1]: 1.981e-05, [1] [cse]: 1.349e-05 [environ_conv]: 6.67002e-06 [swap_dp_allreduce_reducescatter]: 6.78998e-06 [bias_add_comm_swap]: 3.8e-06 [label_micro_interleaved_index]: 5.73002e-06 [label_fine_grained_interleaved_index]: 2.79001e-06 [merge_cast_opt]: 1.30001e-06 [slice_recompute_activation]: 2.16998e-06 [micro_interleaved_order_control]: 2.23998e-06 [assign_add_opt]: 1.37999e-06 [ForceFp32Comm]: 1.42999e-06 [remove_cast_before_assign_add]: 1.10999e-06 [full_micro_interleaved_order_control]: 2.37001e-06 [reorder_send_recv_between_fp_bp]: 2.97002e-06 [comm_op_add_attrs]: 1.13001e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.16997e-06 [interleave_parallel_branches]: 1.35001e-06 [overlap_opt_shard_in_pipeline]: 1.23002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.42001e-06 [control_data_broadcast_order]: 1.606e-05 [grouped_pairwise_exchange_alltoall]: 1.71998e-06 [offloading_packed_experts]: 4.77e-06 [overlap_recompute_and_grad_model_parallel]: 5.61e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.50001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.93002e-06 [overlap_recompute_comm]: 2.27999e-06 [overlap_grad_ring_attention]: 4.98001e-06 [overlap_grad_flash_sp]: 2.366e-05 [begin_end_overlap_inline]: 6.30011e-07 [split_matmul_comm_elemetwise]: 2.83998e-06 [split_layernorm_comm]: 2.02999e-06 [handle_group_info]: 1.05001e-06 [symbol_engine_optimizer]: 8.647e-05, [1] [Cycle 1]: 8.122e-05, [6] [build]: 3.85998e-06 [elim_shapecalc]: 1.46e-05 [elim_not_effective]: 1.372e-05 [opt_reshape]: 6.56e-06 [fold_const_symbol]: 1.009e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.78e-06 [pipeline_parallel_scheduler]: 1.57999e-06 [auto_monad_reorder]: 2.002e-05 [get_jit_bprop_graph]: 2.90002e-06 [rewriter_after_jit_bprop_graph]: 7.43e-06 [opt_after_jit_grad]: 0.00061718 [validate]: 5.127e-05 Sums bootstrap : 0.000489s : 0.24% type_inference : 0.194256s : 96.85% event_method : 0.000026s : 0.01% auto_monad : 0.000077s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000043s : 0.02% 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 : 0.000035s : 0.02% optimize.rewriter_before_opt_a : 0.000092s : 0.05% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000054s : 0.03% optimize.opt_a.loop_unroll : 0.000039s : 0.02% optimize.opt_a.a_1 : 0.000840s : 0.42% optimize.opt_a.with_stream_mark : 0.000040s : 0.02% optimize.opt_a.recompute_prepare : 0.000017s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000147s : 0.07% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.01% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000013s : 0.01% optimize.opt_a.merge_send_recv : 0.000016s : 0.01% optimize.opt_a.auto_parallel : 0.000016s : 0.01% optimize.opt_a.parallel : 0.000030s : 0.01% optimize.opt_a.flash_sp : 0.000018s : 0.01% 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 : 0.000018s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000017s : 0.01% optimize.opt_a.virtual_dataset : 0.000013s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000012s : 0.01% optimize.opt_a.virtual_output : 0.000011s : 0.01% optimize.opt_a.merge_forward : 0.000008s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000021s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000030s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000022s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 0.00% optimize.opt_a.meta_fg_expand : 0.000005s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000023s : 0.01% optimize.opt_a.a_after_grad : 0.000019s : 0.01% optimize.opt_a.renormalize : 0.000972s : 0.48% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000027s : 0.01% optimize.opt_a.cse : 0.000050s : 0.02% optimize.opt_a.a_3 : 0.000133s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000016s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000044s : 0.02% optimize.convert_after_rewriter : 0.000008s : 0.00% optimize.order_py_execute_after_rewriter : 0.000006s : 0.00% optimize.mutable_eliminate : 0.000812s : 0.40% optimize.opt_b.b_1 : 0.000119s : 0.06% optimize.opt_b.b_2 : 0.000009s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000030s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000023s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000038s : 0.02% optimize.loop_unroll : 0.000562s : 0.28% optimize.opt_after_cconv.c_1 : 0.000030s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 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 : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000024s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000016s : 0.01% optimize.tuple_transform.d_1 : 0.000049s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 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 : 0.000057s : 0.03% optimize.cse_after_recomputation.cse : 0.000013s : 0.01% optimize.environ_conv : 0.000007s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 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 : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000016s : 0.01% 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 : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000024s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000014s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.01% 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 : 0.000020s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000617s : 0.31% validate : 0.000051s : 0.03% Time group info: ------[substitution.] 0.000246 29 0.98% : 0.000002s : 2: substitution.elim_not_effective 0.55% : 0.000001s : 2: substitution.fold_const_symbol 2.79% : 0.000007s : 4: substitution.graph_param_transform 82.14% : 0.000202s : 5: substitution.inline 2.18% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.36% : 0.000006s : 4: substitution.remove_not_recompute_node 2.17% : 0.000005s : 4: substitution.replace_old_param 6.83% : 0.000017s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.194176 2 99.48% : 0.193163s : 1: type_inference.infer 0.52% : 0.001013s : 1: type_inference.specialize ------[replace.] 0.000074 9 67.65% : 0.000050s : 5: replace.inline 32.35% : 0.000024s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000214 9 93.10% : 0.000199s : 5: match.inline 6.90% : 0.000015s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000264 1341 0.70% : 0.000002s : 14: predicate.accumulaten_eliminater 1.01% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.43% : 0.000001s : 8: predicate.addn_check_dump 0.81% : 0.000002s : 14: predicate.addn_zero_filter 0.63% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.54% : 0.000004s : 22: predicate.arithmetic_simplify 0.98% : 0.000003s : 14: predicate.cast_eliminate 0.47% : 0.000001s : 8: predicate.check_bprop_eliminate 0.38% : 0.000001s : 8: predicate.compare_switch_simplify 0.14% : 0.000000s : 4: predicate.const_output_eliminate 0.55% : 0.000001s : 8: predicate.depend_value_elim 0.76% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.82% : 0.000002s : 14: predicate.dict_get_item_eliminator 0.87% : 0.000002s : 14: predicate.dict_set_item_eliminator 1.02% : 0.000003s : 8: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 4: predicate.elim_not_effective 0.41% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 0.92% : 0.000002s : 18: predicate.environ_add_const_eliminate 0.87% : 0.000002s : 18: predicate.environ_get_add_eliminate 0.89% : 0.000002s : 18: predicate.environ_get_depend_swap 1.48% : 0.000004s : 26: predicate.environ_get_eliminate 0.86% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.30% : 0.000003s : 23: predicate.exchange_switch_depend_value 1.95% : 0.000005s : 23: predicate.float_depend_g_call 0.45% : 0.000001s : 8: predicate.float_environ_get_switch 0.62% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.15% : 0.000000s : 4: predicate.fold_const_symbol 0.47% : 0.000001s : 8: predicate.get_grad_eliminate 0.29% : 0.000001s : 4: predicate.graph_param_transform 0.44% : 0.000001s : 8: predicate.incorporate_call 0.36% : 0.000001s : 8: predicate.incorporate_call_switch 4.98% : 0.000013s : 61: predicate.inline 0.59% : 0.000002s : 8: predicate.inline_without_move 0.25% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.76% : 0.000002s : 8: predicate.less_batch_normalization 1.55% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 1.94% : 0.000005s : 40: predicate.load_eliminater 0.98% : 0.000003s : 4: predicate.loop_unroll_after_grad 1.96% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.63% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.40% : 0.000001s : 8: predicate.merge_addn 0.42% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.43% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.63% : 0.000002s : 14: predicate.minmaximum_grad 1.38% : 0.000004s : 4: predicate.mutable_eliminate 0.22% : 0.000001s : 4: predicate.opt_reshape 0.43% : 0.000001s : 4: predicate.parallel_virtual_node 1.50% : 0.000004s : 23: predicate.partial_defer_inline 1.19% : 0.000003s : 22: predicate.partial_eliminate 0.67% : 0.000002s : 14: predicate.print_const_string_wrapper 0.51% : 0.000001s : 8: predicate.reduce_all_const_elim 1.11% : 0.000003s : 14: predicate.reduce_eliminate 1.96% : 0.000005s : 40: predicate.redundant_stop_gradient_eliminater 0.60% : 0.000002s : 8: predicate.remove_not_recompute_node 1.02% : 0.000003s : 26: predicate.replace_applicator 0.39% : 0.000001s : 8: predicate.replace_old_param 0.32% : 0.000001s : 4: predicate.reset_defer_inline 0.84% : 0.000002s : 14: predicate.reshape_eliminate 0.45% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.42% : 0.000001s : 4: predicate.row_tensor_eliminate 0.81% : 0.000002s : 8: predicate.same_eliminate 0.34% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.56% : 0.000001s : 8: predicate.shard_identity_eliminate 0.53% : 0.000001s : 8: predicate.special_op_eliminate 0.56% : 0.000001s : 8: predicate.specialize_transform 18.81% : 0.000050s : 8: predicate.split_environ_get_set_with_tuple_value 0.65% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.25% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.26% : 0.000003s : 23: predicate.switch_defer_inline 1.91% : 0.000005s : 31: predicate.switch_layer_defer_inline 4.23% : 0.000011s : 74: predicate.switch_simplify 0.71% : 0.000002s : 14: predicate.tile_eliminate 0.68% : 0.000002s : 14: predicate.transpose_eliminate 1.15% : 0.000003s : 22: predicate.tuple_list_convert_item_index_to_positive 1.13% : 0.000003s : 22: predicate.tuple_list_get_item_const_eliminator 1.04% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 2.53% : 0.000007s : 34: predicate.tuple_list_get_item_eliminator 1.12% : 0.000003s : 22: predicate.tuple_list_get_set_item_eliminator 1.60% : 0.000004s : 30: predicate.tuple_list_set_item_eliminator 1.43% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 1.99% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.46% : 0.000006s : 48: predicate.updatestate_useless_node_eliminater 0.31% : 0.000001s : 4: predicate.value_based_eliminate 0.49% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.46% : 0.000001s : 8: predicate.virtual_output_eliminate 0.24% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.37% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000763 12 52.58% : 0.000401s : 5: func_graph_cloner_run.FuncGraphClonerGraph 47.42% : 0.000362s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.218220 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.88% : 0.004108s : 1: add_attr 1.88% : 0.004094s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.03% : 0.000063s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000084s : 1: auto_monad 0.01% : 0.000025s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.24% : 0.000519s : 1: bootstrap 0.02% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000021s : 1: control_data_broadcast_order 0.01% : 0.000011s : 1: convert_after_rewriter 0.01% : 0.000028s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.01% : 0.000032s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 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% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.26% : 0.000575s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.38% : 0.000828s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.01% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000024s : 1: opt.transform.mutable_eliminate 0.60% : 0.001315s : 78: opt.transform.opt_a 0.01% : 0.000029s : 1: opt.transform.opt_after_cconv 0.01% : 0.000031s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000099s : 28: opt.transform.opt_b 0.02% : 0.000054s : 2: opt.transform.opt_trans_graph 0.02% : 0.000040s : 4: opt.transform.symbol_engine_opt 1.50% : 0.003278s : 1: opt_a 0.06% : 0.000121s : 1: opt_after_cconv 0.29% : 0.000634s : 1: opt_after_jit_grad 0.10% : 0.000222s : 1: opt_b 2.70% : 0.005900s : 1: optimize 0.01% : 0.000027s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.01% : 0.000028s : 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% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 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% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000048s : 1: pre_auto_parallel 0.02% : 0.000040s : 1: py_interpret_to_execute 0.01% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000019s : 1: remove_dup_value 0.25% : 0.000545s : 1: renormalize.infer 0.19% : 0.000416s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000049s : 1: rewriter_after_opt_a 0.04% : 0.000097s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000089s : 1: symbol_engine_optimizer 0.04% : 0.000085s : 1: tuple_transform 89.03% : 0.194288s : 1: type_inference ************************************************************************************************** *************************************TEST_OP_GENERALIZE Start************************************* ************************************************************************************************** *****************Start Generalize test PYNATIVE_MODE DiscontiguousInput case***************** [INFO]: TEST_OP_GENERALIZE generate discontiguous input with shape (2, 3), is_contiguous False, origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE generate discontiguous input with shape (2, 3), is_contiguous False, origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE Start to test discontiguous input [INFO]: TEST_OP_GENERALIZE Start to test contiguous input [INFO]: TEST_OP_GENERALIZE Start to compare discontiguous out with contiguous out Compare ['Success'] for 0'th output. *****************End Generalize test PYNATIVE_MODE DiscontiguousInput case***************** *****************Start Generalize test PYNATIVE_MODE ViewTensor case***************** [INFO]: TEST_OP_GENERALIZE generate view input with shape (2, 3), origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE generate view input with shape (2, 3), origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE Start to test no view input [INFO]: TEST_OP_GENERALIZE Start to test view input [INFO]: TEST_OP_GENERALIZE Start to compare view out with no view out Compare ['Success'] for 0'th output. *****************End Generalize test PYNATIVE_MODE ViewTensor case***************** *****************Start Generalize test PYNATIVE_MODE EmptyTensor case***************** [INFO]: TEST_OP_GENERALIZE EmptyTensor random seed 304242644. [INFO]: TEST_OP_GENERALIZE EmptyTensor test random empty shape, loop 0 [INFO]: TEST_OP_GENERALIZE EmptyTensor all_dim_zero is True, set empty tensor to (0, 0), origin shape (2, 3). [INFO]: TEST_OP_GENERALIZE EmptyTensor all_dim_zero is True, set empty tensor to (0, 0), origin shape (2, 3). [INFO]: TEST_OP_GENERALIZE Start to test empty tensor [INFO]: TEST_OP_GENERALIZE Start to compare empty out with expect empty out [INFO]: TEST_OP_GENERALIZE EmptyTensor expect output shape (0,), actual output shape (0, 0) Compare ['Success'] for 0'th output. *****************End Generalize test PYNATIVE_MODE EmptyTensor case***************** *****************Start Generalize test PYNATIVE_MODE ScalarTensor case***************** [INFO]: TEST_OP_GENERALIZE Start to test scalar tensor [INFO]: TEST_OP_GENERALIZE Start to test 1d tensor [INFO]: TEST_OP_GENERALIZE Start to compare scalar tensor out with 1d tensor out Compare ['Success'] for 0'th output. *****************End Generalize test PYNATIVE_MODE ScalarTensor case***************** *****************Start Generalize test PYNATIVE_MODE GradByRequirement case***************** [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, GradByRequirement case is skipped. *****************End Generalize test PYNATIVE_MODE GradByRequirement case***************** *****************Start Generalize test PYNATIVE_MODE Deterministic case***************** [INFO]: TEST_OP_GENERALIZE test deterministic case loop 0 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 1 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 2 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 3 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 4 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. *****************End Generalize test PYNATIVE_MODE Deterministic case***************** *****************Start Generalize test GRAPH_MODE_O0 DiscontiguousInput case***************** [WARNING]: TEST_OP_GENERALIZE GRAPH_MODE_O0 'DiscontiguousInput' is skipped temporarily with 'GRAPH_MODE_O0' and 'GRAPH_MODE_GE', it's will cause accuracy issue after 'Tensor storage refactor'. *****************End Generalize test GRAPH_MODE_O0 DiscontiguousInput case***************** *****************Start Generalize test GRAPH_MODE_O0 ViewTensor case***************** [INFO]: TEST_OP_GENERALIZE generate view input with shape (2, 3), origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE generate view input with shape (2, 3), origin input with shape (2, 3) [INFO]: TEST_OP_GENERALIZE Start to test no view input [INFO]: TEST_OP_GENERALIZE Start to test view input [INFO]: TEST_OP_GENERALIZE Start to compare view out with no view out Compare ['Success'] for 0'th output. *****************End Generalize test GRAPH_MODE_O0 ViewTensor case***************** *****************Start Generalize test GRAPH_MODE_O0 EmptyTensor case***************** [WARNING]: TEST_OP_GENERALIZE GRAPH_MODE_O0 'EmptyTensor' in 'disable_case', EmptyTensor case is skipped. *****************End Generalize test GRAPH_MODE_O0 EmptyTensor case***************** *****************Start Generalize test GRAPH_MODE_O0 ScalarTensor case***************** [INFO]: TEST_OP_GENERALIZE Start to test scalar tensor [INFO]: TEST_OP_GENERALIZE Start to test 1d tensor [INFO]: TEST_OP_GENERALIZE Start to compare scalar tensor out with 1d tensor out Compare ['Success'] for 0'th output. *****************End Generalize test GRAPH_MODE_O0 ScalarTensor case***************** TotalTime = 0.186823, [21] [bootstrap]: 0.00046172 [type_inference]: 0.0094314 [event_method]: 2.312e-05 [auto_monad]: 5.741e-05 [graph_reusing]: 5.60001e-06 [inline]: 2.76e-06 [add_attr]: 0.170342, [1] [add_attr_with_inline]: 0.17033, [1] [Cycle 1]: 8.169e-05, [2] [tag_attr]: 2.541e-05 [meta_addattr_fg_expand]: 5.48997e-06 [parallel-infer-symbol]: 4.16001e-06 [pre_auto_parallel]: 4.351e-05 [insert-virtual-dataset]: 2.78e-06 [parallel-infer-symbol-second]: 7.7e-07 [dataset_repeat_opt]: 2.17999e-06 [pipeline_split]: 1.80001e-06 [optimize]: 0.00565391, [53] [py_interpret_to_execute]: 3.282e-05 [rewriter_before_opt_a]: 9.287e-05 [opt_a]: 0.00310916, [2] [Cycle 1]: 0.00240193, [45] [expand_dump_flag]: 3.98001e-06 [switch_simplify]: 4.663e-05 [loop_unroll]: 3.191e-05 [a_1]: 0.00078035 [with_stream_mark]: 2.306e-05 [recompute_prepare]: 1.092e-05 [updatestate_depend_eliminate]: 4.28999e-06 [updatestate_assign_eliminate]: 3.81001e-06 [updatestate_loads_eliminate]: 3.51001e-06 [parameter_eliminate]: 2.11e-06 [a_2]: 7.722e-05 [accelerated_algorithm]: 7.66999e-06 [shard]: 2.16998e-06 [meta_shard_fg_expand]: 2.24999e-06 [shard_inline]: 7.10998e-06 [merge_send_recv]: 9.62999e-06 [auto_parallel]: 1.036e-05 [parallel]: 2.062e-05 [flash_sp]: 9.87999e-06 [merge_comm]: 3.81001e-06 [allreduce_fusion]: 3.81999e-06 [matmul_add_comm_reduction]: 1.144e-05 [allreduce_slice_to_reducescatter]: 1.13001e-06 [virtual_shard_identity]: 9.94001e-06 [virtual_dataset]: 6.29001e-06 [get_grad_eliminate_]: 6.11e-06 [virtual_output]: 6.14999e-06 [merge_forward]: 3.83001e-06 [cell_reuse_recompute_pass]: 1.45001e-06 [offload_activation]: 1.191e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.564e-05 [merge_recompute_call_nodes]: 1.72001e-06 [before_grad]: 1.034e-05 [set_forward_comm_id_for_comm_node_pass]: 3.86001e-06 [meta_fg_expand]: 2.69999e-06 [flash_sp_send_recv_attached]: 3.23998e-06 [receive_attached]: 2.44999e-06 [after_resolve]: 1.165e-05 [a_after_grad]: 9.27999e-06 [renormalize]: 0.0008227 [add_forward_monad_depend]: 8.75001e-06 [auto_monad_grad]: 2.98e-06 [auto_monad_eliminator]: 1.989e-05 [cse]: 3.354e-05 [a_3]: 5.279e-05 [Cycle 2]: 0.00069302, [45] [expand_dump_flag]: 2.34999e-06 [switch_simplify]: 9.46e-06 [loop_unroll]: 5.96e-06 [a_1]: 0.00013045 [with_stream_mark]: 1.613e-05 [recompute_prepare]: 6.87002e-06 [updatestate_depend_eliminate]: 3.86999e-06 [updatestate_assign_eliminate]: 2.94999e-06 [updatestate_loads_eliminate]: 2.69001e-06 [parameter_eliminate]: 1.76998e-06 [a_2]: 6.808e-05 [accelerated_algorithm]: 6.51999e-06 [shard]: 2.10002e-06 [meta_shard_fg_expand]: 1.60001e-06 [shard_inline]: 5.97001e-06 [merge_send_recv]: 8.51002e-06 [auto_parallel]: 8.48999e-06 [parallel]: 7.97e-06 [flash_sp]: 5.02999e-06 [merge_comm]: 4.54002e-06 [allreduce_fusion]: 4.25999e-06 [matmul_add_comm_reduction]: 7.91001e-06 [allreduce_slice_to_reducescatter]: 6.50005e-07 [virtual_shard_identity]: 7.61999e-06 [virtual_dataset]: 6.09999e-06 [get_grad_eliminate_]: 5.67001e-06 [virtual_output]: 5.94e-06 [merge_forward]: 4.30999e-06 [cell_reuse_recompute_pass]: 2.21e-06 [offload_activation]: 8.07e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.515e-05 [merge_recompute_call_nodes]: 1.21997e-06 [before_grad]: 9.25999e-06 [set_forward_comm_id_for_comm_node_pass]: 4.06001e-06 [meta_fg_expand]: 1.99e-06 [flash_sp_send_recv_attached]: 1.66998e-06 [receive_attached]: 2.64999e-06 [after_resolve]: 1.15e-05 [a_after_grad]: 8.28999e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.06e-06 [auto_monad_grad]: 2.08002e-06 [auto_monad_eliminator]: 7.89997e-06 [cse]: 1.636e-05 [a_3]: 3.476e-05 [py_interpret_to_execute_after_opt_a]: 1.206e-05 [slice_cell_reuse_recomputed_activation]: 2.57001e-06 [rewriter_after_opt_a]: 4.067e-05 [convert_after_rewriter]: 7.73001e-06 [order_py_execute_after_rewriter]: 6.29001e-06 [mutable_eliminate]: 0.00077302 [opt_b]: 0.00021524, [1] [Cycle 1]: 0.00020642, [7] [b_1]: 0.00011973 [b_2]: 8.55001e-06 [updatestate_depend_eliminate]: 6.46e-06 [updatestate_assign_eliminate]: 2.96001e-06 [updatestate_loads_eliminate]: 3.36001e-06 [renormalize]: 1.03001e-06 [cse]: 2.712e-05 [optimize_parallel_all_gather_comm]: 1.825e-05 [overlap_param_gather]: 1.91998e-06 [cconv]: 2.485e-05 [loop_unroll]: 0.00057966 [opt_after_cconv]: 0.00011689, [1] [Cycle 1]: 0.0001091, [7] [c_1]: 3.407e-05 [parameter_eliminate]: 4.42e-06 [updatestate_depend_eliminate]: 6.78e-06 [updatestate_assign_eliminate]: 2.41998e-06 [updatestate_loads_eliminate]: 2.22999e-06 [cse]: 2.107e-05 [renormalize]: 6.00005e-07 [remove_dup_value]: 1.444e-05 [tuple_transform]: 7.856e-05, [1] [Cycle 1]: 7.269e-05, [4] [d_1]: 4.49e-05 [none_parameter_eliminate]: 1.95001e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 6.86999e-06 [partial_unused_args_eliminate]: 2.69001e-06 [add_recomputation]: 5.494e-05 [cse_after_recomputation]: 2.369e-05, [1] [Cycle 1]: 1.88e-05, [1] [cse]: 1.301e-05 [environ_conv]: 5.86e-06 [swap_dp_allreduce_reducescatter]: 5.76998e-06 [bias_add_comm_swap]: 3.58999e-06 [label_micro_interleaved_index]: 5.15999e-06 [label_fine_grained_interleaved_index]: 3.11001e-06 [merge_cast_opt]: 1.26002e-06 [slice_recompute_activation]: 2.58998e-06 [micro_interleaved_order_control]: 2.45997e-06 [assign_add_opt]: 1.37999e-06 [ForceFp32Comm]: 1.12e-06 [remove_cast_before_assign_add]: 1.02998e-06 [full_micro_interleaved_order_control]: 2.57001e-06 [reorder_send_recv_between_fp_bp]: 2.69001e-06 [comm_op_add_attrs]: 1.17999e-06 [add_comm_op_reuse_tag]: 1.00001e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 1.19e-06 [overlap_opt_shard_grad_in_pipeline]: 1.69998e-06 [control_data_broadcast_order]: 1.5e-05 [grouped_pairwise_exchange_alltoall]: 2.16e-06 [offloading_packed_experts]: 4.62e-06 [overlap_recompute_and_grad_model_parallel]: 5.07e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.30999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47999e-06 [overlap_recompute_comm]: 2.71999e-06 [overlap_grad_ring_attention]: 4.74998e-06 [overlap_grad_flash_sp]: 2.348e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.63998e-06 [split_layernorm_comm]: 1.99999e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 8.423e-05, [1] [Cycle 1]: 7.938e-05, [6] [build]: 4.28999e-06 [elim_shapecalc]: 1.25e-05 [elim_not_effective]: 1.342e-05 [opt_reshape]: 7.50998e-06 [fold_const_symbol]: 1.01e-05 [renormalize]: 1.90019e-07 [detach_backward]: 2.37999e-06 [pipeline_parallel_scheduler]: 1.61998e-06 [auto_monad_reorder]: 1.787e-05 [get_jit_bprop_graph]: 1.85001e-06 [rewriter_after_jit_bprop_graph]: 5.71e-06 [opt_after_jit_grad]: 0.00054619 [validate]: 4.461e-05 Sums bootstrap : 0.000462s : 2.99% type_inference : 0.009431s : 61.16% event_method : 0.000023s : 0.15% auto_monad : 0.000057s : 0.37% graph_reusing : 0.000006s : 0.04% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.16% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.04% parallel-infer-symbol : 0.000004s : 0.03% pre_auto_parallel : 0.000044s : 0.28% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000033s : 0.21% optimize.rewriter_before_opt_a : 0.000093s : 0.60% optimize.opt_a.expand_dump_flag : 0.000006s : 0.04% optimize.opt_a.switch_simplify : 0.000056s : 0.36% optimize.opt_a.loop_unroll : 0.000038s : 0.25% optimize.opt_a.a_1 : 0.000911s : 5.91% optimize.opt_a.with_stream_mark : 0.000039s : 0.25% optimize.opt_a.recompute_prepare : 0.000018s : 0.12% optimize.opt_a.updatestate_depend_eliminate : 0.000008s : 0.05% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.04% optimize.opt_a.updatestate_loads_eliminate : 0.000006s : 0.04% optimize.opt_a.parameter_eliminate : 0.000004s : 0.03% optimize.opt_a.a_2 : 0.000145s : 0.94% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.09% optimize.opt_a.shard : 0.000004s : 0.03% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.02% optimize.opt_a.shard_inline : 0.000013s : 0.08% optimize.opt_a.merge_send_recv : 0.000018s : 0.12% optimize.opt_a.auto_parallel : 0.000019s : 0.12% optimize.opt_a.parallel : 0.000029s : 0.19% optimize.opt_a.flash_sp : 0.000015s : 0.10% optimize.opt_a.merge_comm : 0.000008s : 0.05% optimize.opt_a.allreduce_fusion : 0.000008s : 0.05% optimize.opt_a.matmul_add_comm_reduction : 0.000019s : 0.13% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000018s : 0.11% optimize.opt_a.virtual_dataset : 0.000012s : 0.08% optimize.opt_a.get_grad_eliminate_ : 0.000012s : 0.08% optimize.opt_a.virtual_output : 0.000012s : 0.08% optimize.opt_a.merge_forward : 0.000008s : 0.05% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.02% optimize.opt_a.offload_activation : 0.000020s : 0.13% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000031s : 0.20% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.02% optimize.opt_a.before_grad : 0.000020s : 0.13% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 0.05% optimize.opt_a.meta_fg_expand : 0.000005s : 0.03% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.03% optimize.opt_a.receive_attached : 0.000005s : 0.03% optimize.opt_a.after_resolve : 0.000023s : 0.15% optimize.opt_a.a_after_grad : 0.000018s : 0.11% optimize.opt_a.renormalize : 0.000823s : 5.34% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.07% optimize.opt_a.auto_monad_grad : 0.000005s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000028s : 0.18% optimize.opt_a.cse : 0.000050s : 0.32% optimize.opt_a.a_3 : 0.000088s : 0.57% optimize.py_interpret_to_execute_after_opt_a : 0.000012s : 0.08% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.02% optimize.rewriter_after_opt_a : 0.000041s : 0.26% optimize.convert_after_rewriter : 0.000008s : 0.05% optimize.order_py_execute_after_rewriter : 0.000006s : 0.04% optimize.mutable_eliminate : 0.000773s : 5.01% optimize.opt_b.b_1 : 0.000120s : 0.78% optimize.opt_b.b_2 : 0.000009s : 0.06% optimize.opt_b.updatestate_depend_eliminate : 0.000006s : 0.04% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.01% optimize.opt_b.cse : 0.000027s : 0.18% optimize.optimize_parallel_all_gather_comm : 0.000018s : 0.12% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000025s : 0.16% optimize.loop_unroll : 0.000580s : 3.76% optimize.opt_after_cconv.c_1 : 0.000034s : 0.22% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.04% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.01% optimize.opt_after_cconv.cse : 0.000021s : 0.14% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000014s : 0.09% optimize.tuple_transform.d_1 : 0.000045s : 0.29% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000007s : 0.04% optimize.partial_unused_args_eliminate : 0.000003s : 0.02% optimize.add_recomputation : 0.000055s : 0.36% optimize.cse_after_recomputation.cse : 0.000013s : 0.08% optimize.environ_conv : 0.000006s : 0.04% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.04% optimize.bias_add_comm_swap : 0.000004s : 0.02% optimize.label_micro_interleaved_index : 0.000005s : 0.03% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.02% optimize.micro_interleaved_order_control : 0.000002s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000003s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000015s : 0.10% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.03% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.03% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000005s : 0.03% optimize.overlap_grad_flash_sp : 0.000023s : 0.15% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000004s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.08% optimize.symbol_engine_optimizer.elim_not_effective : 0.000013s : 0.09% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.05% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.07% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000018s : 0.12% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000006s : 0.04% opt_after_jit_grad : 0.000546s : 3.54% validate : 0.000045s : 0.29% Time group info: ------[substitution.] 0.000298 29 0.65% : 0.000002s : 2: substitution.elim_not_effective 0.51% : 0.000002s : 2: substitution.fold_const_symbol 2.17% : 0.000006s : 4: substitution.graph_param_transform 85.51% : 0.000255s : 5: substitution.inline 1.19% : 0.000004s : 4: substitution.j_node_and_user_rematch 2.38% : 0.000007s : 4: substitution.remove_not_recompute_node 1.80% : 0.000005s : 4: substitution.replace_old_param 5.78% : 0.000017s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.009360 2 90.35% : 0.008457s : 1: type_inference.infer 9.65% : 0.000903s : 1: type_inference.specialize ------[replace.] 0.000076 9 66.49% : 0.000051s : 5: replace.inline 33.51% : 0.000026s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000268 9 94.30% : 0.000252s : 5: match.inline 5.70% : 0.000015s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000227 1341 1.14% : 0.000003s : 14: predicate.accumulaten_eliminater 0.76% : 0.000002s : 4: predicate.ad_related_special_op_eliminate 0.45% : 0.000001s : 8: predicate.addn_check_dump 0.91% : 0.000002s : 14: predicate.addn_zero_filter 0.79% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.76% : 0.000004s : 22: predicate.arithmetic_simplify 0.95% : 0.000002s : 14: predicate.cast_eliminate 0.68% : 0.000002s : 8: predicate.check_bprop_eliminate 0.49% : 0.000001s : 8: predicate.compare_switch_simplify 0.16% : 0.000000s : 4: predicate.const_output_eliminate 0.68% : 0.000002s : 8: predicate.depend_value_elim 0.90% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.95% : 0.000002s : 14: predicate.dict_get_item_eliminator 1.35% : 0.000003s : 14: predicate.dict_set_item_eliminator 0.82% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.41% : 0.000001s : 4: predicate.elim_not_effective 0.35% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.06% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.05% : 0.000002s : 18: predicate.environ_get_depend_swap 1.74% : 0.000004s : 26: predicate.environ_get_eliminate 0.98% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.46% : 0.000003s : 23: predicate.exchange_switch_depend_value 2.32% : 0.000005s : 23: predicate.float_depend_g_call 0.58% : 0.000001s : 8: predicate.float_environ_get_switch 0.86% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.18% : 0.000000s : 4: predicate.fold_const_symbol 0.62% : 0.000001s : 8: predicate.get_grad_eliminate 0.22% : 0.000000s : 4: predicate.graph_param_transform 0.51% : 0.000001s : 8: predicate.incorporate_call 0.43% : 0.000001s : 8: predicate.incorporate_call_switch 5.79% : 0.000013s : 61: predicate.inline 0.67% : 0.000002s : 8: predicate.inline_without_move 0.29% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.73% : 0.000002s : 8: predicate.less_batch_normalization 1.72% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 2.44% : 0.000006s : 40: predicate.load_eliminater 1.14% : 0.000003s : 4: predicate.loop_unroll_after_grad 2.43% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.64% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.56% : 0.000001s : 8: predicate.merge_addn 0.51% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.63% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.77% : 0.000002s : 14: predicate.minmaximum_grad 1.15% : 0.000003s : 4: predicate.mutable_eliminate 0.32% : 0.000001s : 4: predicate.opt_reshape 0.45% : 0.000001s : 4: predicate.parallel_virtual_node 2.23% : 0.000005s : 23: predicate.partial_defer_inline 1.42% : 0.000003s : 22: predicate.partial_eliminate 1.19% : 0.000003s : 14: predicate.print_const_string_wrapper 0.50% : 0.000001s : 8: predicate.reduce_all_const_elim 1.32% : 0.000003s : 14: predicate.reduce_eliminate 2.34% : 0.000005s : 40: predicate.redundant_stop_gradient_eliminater 0.47% : 0.000001s : 8: predicate.remove_not_recompute_node 1.30% : 0.000003s : 26: predicate.replace_applicator 0.37% : 0.000001s : 8: predicate.replace_old_param 0.33% : 0.000001s : 4: predicate.reset_defer_inline 0.92% : 0.000002s : 14: predicate.reshape_eliminate 0.64% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.34% : 0.000001s : 4: predicate.row_tensor_eliminate 0.84% : 0.000002s : 8: predicate.same_eliminate 0.37% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.82% : 0.000002s : 8: predicate.shard_identity_eliminate 1.00% : 0.000002s : 8: predicate.special_op_eliminate 0.61% : 0.000001s : 8: predicate.specialize_transform 1.17% : 0.000003s : 8: predicate.split_environ_get_set_with_tuple_value 0.69% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.37% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.53% : 0.000003s : 23: predicate.switch_defer_inline 1.99% : 0.000005s : 31: predicate.switch_layer_defer_inline 4.99% : 0.000011s : 74: predicate.switch_simplify 1.10% : 0.000002s : 14: predicate.tile_eliminate 0.90% : 0.000002s : 14: predicate.transpose_eliminate 1.75% : 0.000004s : 22: predicate.tuple_list_convert_item_index_to_positive 1.51% : 0.000003s : 22: predicate.tuple_list_get_item_const_eliminator 1.86% : 0.000004s : 22: predicate.tuple_list_get_item_depend_reorder 3.50% : 0.000008s : 34: predicate.tuple_list_get_item_eliminator 2.20% : 0.000005s : 22: predicate.tuple_list_get_set_item_eliminator 2.21% : 0.000005s : 30: predicate.tuple_list_set_item_eliminator 1.67% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 2.23% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.93% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.32% : 0.000001s : 4: predicate.value_based_eliminate 0.58% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.77% : 0.000002s : 8: predicate.virtual_output_eliminate 0.23% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.53% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000633 12 48.30% : 0.000306s : 5: func_graph_cloner_run.FuncGraphClonerGraph 51.70% : 0.000327s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.365116 192 0.00% : 0.000004s : 1: ForceFp32Comm 46.66% : 0.170349s : 1: add_attr 46.65% : 0.170334s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.02% : 0.000061s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000064s : 1: auto_monad 0.01% : 0.000021s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.13% : 0.000490s : 1: bootstrap 0.01% : 0.000029s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000019s : 1: control_data_broadcast_order 0.00% : 0.000011s : 1: convert_after_rewriter 0.01% : 0.000026s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000009s : 1: environ_conv 0.01% : 0.000029s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 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% : 0.000006s : 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 0.16% : 0.000593s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.22% : 0.000787s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000021s : 1: opt.transform.mutable_eliminate 0.37% : 0.001340s : 78: opt.transform.opt_a 0.01% : 0.000032s : 1: opt.transform.opt_after_cconv 0.01% : 0.000025s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000099s : 28: opt.transform.opt_b 0.01% : 0.000049s : 2: opt.transform.opt_trans_graph 0.01% : 0.000040s : 4: opt.transform.symbol_engine_opt 0.85% : 0.003113s : 1: opt_a 0.03% : 0.000121s : 1: opt_after_cconv 0.15% : 0.000559s : 1: opt_after_jit_grad 0.06% : 0.000219s : 1: opt_b 1.55% : 0.005661s : 1: optimize 0.01% : 0.000022s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.01% : 0.000027s : 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% : 0.000004s : 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% : 0.000009s : 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% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000048s : 1: pre_auto_parallel 0.01% : 0.000037s : 1: py_interpret_to_execute 0.00% : 0.000016s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000018s : 1: remove_dup_value 0.11% : 0.000407s : 1: renormalize.infer 0.11% : 0.000407s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000046s : 1: rewriter_after_opt_a 0.03% : 0.000097s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 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 0.02% : 0.000087s : 1: symbol_engine_optimizer 0.02% : 0.000081s : 1: tuple_transform 2.59% : 0.009453s : 1: type_inference [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:51.804.352 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:51.804.816 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:51.927.939 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:51.928.273 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. TotalTime = 0.196303, [21] [bootstrap]: 0.00051717 [type_inference]: 0.0124948 [event_method]: 2.328e-05 [auto_monad]: 7.179e-05 [graph_reusing]: 6.84001e-06 [inline]: 3.21001e-06 [add_attr]: 0.00390798, [1] [add_attr_with_inline]: 0.00389414, [1] [Cycle 1]: 7.463e-05, [2] [tag_attr]: 2.376e-05 [meta_addattr_fg_expand]: 5.78002e-06 [parallel-infer-symbol]: 4.41002e-06 [pre_auto_parallel]: 3.822e-05 [insert-virtual-dataset]: 2.61e-06 [parallel-infer-symbol-second]: 8.89995e-07 [dataset_repeat_opt]: 2.77002e-06 [pipeline_split]: 2.42001e-06 [optimize]: 0.178343, [53] [py_interpret_to_execute]: 2.912e-05 [rewriter_before_opt_a]: 8.994e-05 [opt_a]: 0.175489, [2] [Cycle 1]: 0.174705, [45] [expand_dump_flag]: 3.78999e-06 [switch_simplify]: 4.422e-05 [loop_unroll]: 3.027e-05 [a_1]: 0.00070957 [with_stream_mark]: 2.052e-05 [recompute_prepare]: 1.226e-05 [updatestate_depend_eliminate]: 4.47e-06 [updatestate_assign_eliminate]: 3.58e-06 [updatestate_loads_eliminate]: 3.09999e-06 [parameter_eliminate]: 1.85001e-06 [a_2]: 7.369e-05 [accelerated_algorithm]: 6.94999e-06 [shard]: 1.86e-06 [meta_shard_fg_expand]: 2.44001e-06 [shard_inline]: 6.39999e-06 [merge_send_recv]: 9.56e-06 [auto_parallel]: 8.72e-06 [parallel]: 2.105e-05 [flash_sp]: 1.029e-05 [merge_comm]: 4.18001e-06 [allreduce_fusion]: 3.45e-06 [matmul_add_comm_reduction]: 1.026e-05 [allreduce_slice_to_reducescatter]: 6.10016e-07 [virtual_shard_identity]: 8.30999e-06 [virtual_dataset]: 5.87001e-06 [get_grad_eliminate_]: 6.24999e-06 [virtual_output]: 5.90002e-06 [merge_forward]: 4.47e-06 [cell_reuse_recompute_pass]: 1.34e-06 [offload_activation]: 1.06e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.496e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 1.051e-05 [set_forward_comm_id_for_comm_node_pass]: 4.37e-06 [meta_fg_expand]: 3.11999e-06 [flash_sp_send_recv_attached]: 2.75002e-06 [receive_attached]: 2.66e-06 [after_resolve]: 1.188e-05 [a_after_grad]: 1.01e-05 [renormalize]: 0.17315 [add_forward_monad_depend]: 1.538e-05 [auto_monad_grad]: 3.41999e-06 [auto_monad_eliminator]: 2.825e-05 [cse]: 3.87e-05 [a_3]: 6.513e-05 [Cycle 2]: 0.00076671, [45] [expand_dump_flag]: 3.46999e-06 [switch_simplify]: 1.03e-05 [loop_unroll]: 6.21e-06 [a_1]: 0.00014214 [with_stream_mark]: 2.574e-05 [recompute_prepare]: 6.23998e-06 [updatestate_depend_eliminate]: 4.12e-06 [updatestate_assign_eliminate]: 3.47997e-06 [updatestate_loads_eliminate]: 3.81001e-06 [parameter_eliminate]: 1.92999e-06 [a_2]: 7.163e-05 [accelerated_algorithm]: 6.31998e-06 [shard]: 2.78998e-06 [meta_shard_fg_expand]: 2.31e-06 [shard_inline]: 5.70001e-06 [merge_send_recv]: 1.059e-05 [auto_parallel]: 1.848e-05 [parallel]: 1.011e-05 [flash_sp]: 5.22999e-06 [merge_comm]: 3.51001e-06 [allreduce_fusion]: 3.11999e-06 [matmul_add_comm_reduction]: 1.064e-05 [allreduce_slice_to_reducescatter]: 7.7e-07 [virtual_shard_identity]: 7.83999e-06 [virtual_dataset]: 6.59001e-06 [get_grad_eliminate_]: 6.64001e-06 [virtual_output]: 5.96e-06 [merge_forward]: 4.70999e-06 [cell_reuse_recompute_pass]: 3.58999e-06 [offload_activation]: 1.233e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.052e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 9.96998e-06 [set_forward_comm_id_for_comm_node_pass]: 4.39002e-06 [meta_fg_expand]: 2.55997e-06 [flash_sp_send_recv_attached]: 1.86003e-06 [receive_attached]: 2.74999e-06 [after_resolve]: 1.346e-05 [a_after_grad]: 9.19e-06 [renormalize]: 1.30007e-07 [add_forward_monad_depend]: 2.41998e-06 [auto_monad_grad]: 1.67001e-06 [auto_monad_eliminator]: 1.021e-05 [cse]: 1.972e-05 [a_3]: 3.379e-05 [py_interpret_to_execute_after_opt_a]: 2.051e-05 [slice_cell_reuse_recomputed_activation]: 2.47001e-06 [rewriter_after_opt_a]: 4.735e-05 [convert_after_rewriter]: 8.47e-06 [order_py_execute_after_rewriter]: 5.69e-06 [mutable_eliminate]: 0.00090295 [opt_b]: 0.00023944, [1] [Cycle 1]: 0.0002281, [7] [b_1]: 0.00012501 [b_2]: 9.39e-06 [updatestate_depend_eliminate]: 1.344e-05 [updatestate_assign_eliminate]: 3.50998e-06 [updatestate_loads_eliminate]: 2.78e-06 [renormalize]: 2.89991e-07 [cse]: 3.085e-05 [optimize_parallel_all_gather_comm]: 2.313e-05 [overlap_param_gather]: 1.86003e-06 [cconv]: 4.346e-05 [loop_unroll]: 0.00061236 [opt_after_cconv]: 0.00012697, [1] [Cycle 1]: 0.00011794, [7] [c_1]: 3.301e-05 [parameter_eliminate]: 6.96999e-06 [updatestate_depend_eliminate]: 8.04002e-06 [updatestate_assign_eliminate]: 2.56998e-06 [updatestate_loads_eliminate]: 2.66999e-06 [cse]: 2.575e-05 [renormalize]: 6.50005e-07 [remove_dup_value]: 1.683e-05 [tuple_transform]: 0.00013577, [1] [Cycle 1]: 0.00012988, [4] [d_1]: 9.803e-05 [none_parameter_eliminate]: 2.56e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 7.22002e-06 [partial_unused_args_eliminate]: 2.37999e-06 [add_recomputation]: 6.511e-05 [cse_after_recomputation]: 2.557e-05, [1] [Cycle 1]: 2.033e-05, [1] [cse]: 1.454e-05 [environ_conv]: 7.01001e-06 [swap_dp_allreduce_reducescatter]: 5.07999e-06 [bias_add_comm_swap]: 3.9e-06 [label_micro_interleaved_index]: 6.28e-06 [label_fine_grained_interleaved_index]: 3.06001e-06 [merge_cast_opt]: 1.52001e-06 [slice_recompute_activation]: 2.36998e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 1.52001e-06 [remove_cast_before_assign_add]: 1.09998e-06 [full_micro_interleaved_order_control]: 2.41998e-06 [reorder_send_recv_between_fp_bp]: 2.80002e-06 [comm_op_add_attrs]: 1.22999e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.22999e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 2.15002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.96998e-06 [control_data_broadcast_order]: 1.45e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 4.61002e-06 [overlap_recompute_and_grad_model_parallel]: 5.07e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.30001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.53e-06 [overlap_grad_ring_attention]: 4.69998e-06 [overlap_grad_flash_sp]: 2.294e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.43e-06 [split_layernorm_comm]: 2.19999e-06 [handle_group_info]: 1.22e-06 [symbol_engine_optimizer]: 8.282e-05, [1] [Cycle 1]: 7.811e-05, [6] [build]: 4.05e-06 [elim_shapecalc]: 1.248e-05 [elim_not_effective]: 1.262e-05 [opt_reshape]: 7.4e-06 [fold_const_symbol]: 9.77001e-06 [renormalize]: 2.10013e-07 [detach_backward]: 2.36e-06 [pipeline_parallel_scheduler]: 1.82999e-06 [auto_monad_reorder]: 1.75e-05 [get_jit_bprop_graph]: 2.68998e-06 [rewriter_after_jit_bprop_graph]: 7.53e-06 [opt_after_jit_grad]: 0.00060906 [validate]: 5.106e-05 Sums bootstrap : 0.000517s : 0.27% type_inference : 0.012495s : 6.53% event_method : 0.000023s : 0.01% auto_monad : 0.000072s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000038s : 0.02% 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 : 0.000029s : 0.02% optimize.rewriter_before_opt_a : 0.000090s : 0.05% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.03% optimize.opt_a.loop_unroll : 0.000036s : 0.02% optimize.opt_a.a_1 : 0.000852s : 0.45% optimize.opt_a.with_stream_mark : 0.000046s : 0.02% optimize.opt_a.recompute_prepare : 0.000018s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000145s : 0.08% optimize.opt_a.accelerated_algorithm : 0.000013s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.01% optimize.opt_a.merge_send_recv : 0.000020s : 0.01% optimize.opt_a.auto_parallel : 0.000027s : 0.01% optimize.opt_a.parallel : 0.000031s : 0.02% optimize.opt_a.flash_sp : 0.000016s : 0.01% 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 : 0.000021s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000016s : 0.01% optimize.opt_a.virtual_dataset : 0.000012s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000013s : 0.01% optimize.opt_a.virtual_output : 0.000012s : 0.01% 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 : 0.000023s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000035s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000020s : 0.01% 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 : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000025s : 0.01% optimize.opt_a.a_after_grad : 0.000019s : 0.01% optimize.opt_a.renormalize : 0.173150s : 90.54% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000038s : 0.02% optimize.opt_a.cse : 0.000058s : 0.03% optimize.opt_a.a_3 : 0.000099s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000047s : 0.02% optimize.convert_after_rewriter : 0.000008s : 0.00% optimize.order_py_execute_after_rewriter : 0.000006s : 0.00% optimize.mutable_eliminate : 0.000903s : 0.47% optimize.opt_b.b_1 : 0.000125s : 0.07% optimize.opt_b.b_2 : 0.000009s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000031s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000023s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.02% optimize.loop_unroll : 0.000612s : 0.32% optimize.opt_after_cconv.c_1 : 0.000033s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 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 : 0.000026s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.01% optimize.tuple_transform.d_1 : 0.000098s : 0.05% 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 : 0.000065s : 0.03% optimize.cse_after_recomputation.cse : 0.000015s : 0.01% optimize.environ_conv : 0.000007s : 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 : 0.000002s : 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 : 0.000002s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000014s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 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 : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000012s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000013s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.01% 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 : 0.000017s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000609s : 0.32% validate : 0.000051s : 0.03% Time group info: ------[substitution.] 0.000242 29 1.03% : 0.000002s : 2: substitution.elim_not_effective 0.54% : 0.000001s : 2: substitution.fold_const_symbol 2.86% : 0.000007s : 4: substitution.graph_param_transform 81.24% : 0.000196s : 5: substitution.inline 1.88% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.46% : 0.000006s : 4: substitution.remove_not_recompute_node 3.13% : 0.000008s : 4: substitution.replace_old_param 6.86% : 0.000017s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.012416 2 92.65% : 0.011503s : 1: type_inference.infer 7.35% : 0.000913s : 1: type_inference.specialize ------[replace.] 0.000076 9 65.59% : 0.000050s : 5: replace.inline 34.41% : 0.000026s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000208 9 92.91% : 0.000193s : 5: match.inline 7.09% : 0.000015s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000233 1341 0.91% : 0.000002s : 14: predicate.accumulaten_eliminater 0.68% : 0.000002s : 4: predicate.ad_related_special_op_eliminate 0.45% : 0.000001s : 8: predicate.addn_check_dump 0.91% : 0.000002s : 14: predicate.addn_zero_filter 0.78% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 2.15% : 0.000005s : 22: predicate.arithmetic_simplify 1.08% : 0.000003s : 14: predicate.cast_eliminate 0.53% : 0.000001s : 8: predicate.check_bprop_eliminate 0.64% : 0.000001s : 8: predicate.compare_switch_simplify 0.15% : 0.000000s : 4: predicate.const_output_eliminate 0.60% : 0.000001s : 8: predicate.depend_value_elim 0.90% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 1.01% : 0.000002s : 14: predicate.dict_get_item_eliminator 0.98% : 0.000002s : 14: predicate.dict_set_item_eliminator 0.96% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 4: predicate.elim_not_effective 0.48% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.31% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.24% : 0.000003s : 18: predicate.environ_get_add_eliminate 1.03% : 0.000002s : 18: predicate.environ_get_depend_swap 1.53% : 0.000004s : 26: predicate.environ_get_eliminate 1.19% : 0.000003s : 18: predicate.environ_get_set_eliminate 1.52% : 0.000004s : 23: predicate.exchange_switch_depend_value 2.31% : 0.000005s : 23: predicate.float_depend_g_call 0.48% : 0.000001s : 8: predicate.float_environ_get_switch 0.91% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.16% : 0.000000s : 4: predicate.fold_const_symbol 0.78% : 0.000002s : 8: predicate.get_grad_eliminate 0.27% : 0.000001s : 4: predicate.graph_param_transform 0.49% : 0.000001s : 8: predicate.incorporate_call 0.38% : 0.000001s : 8: predicate.incorporate_call_switch 6.24% : 0.000015s : 61: predicate.inline 0.58% : 0.000001s : 8: predicate.inline_without_move 0.45% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.78% : 0.000002s : 8: predicate.less_batch_normalization 1.71% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 2.26% : 0.000005s : 40: predicate.load_eliminater 1.10% : 0.000003s : 4: predicate.loop_unroll_after_grad 2.29% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.72% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.58% : 0.000001s : 8: predicate.merge_addn 0.55% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.53% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.85% : 0.000002s : 14: predicate.minmaximum_grad 1.61% : 0.000004s : 4: predicate.mutable_eliminate 0.35% : 0.000001s : 4: predicate.opt_reshape 0.38% : 0.000001s : 4: predicate.parallel_virtual_node 1.86% : 0.000004s : 23: predicate.partial_defer_inline 1.39% : 0.000003s : 22: predicate.partial_eliminate 0.79% : 0.000002s : 14: predicate.print_const_string_wrapper 0.54% : 0.000001s : 8: predicate.reduce_all_const_elim 1.38% : 0.000003s : 14: predicate.reduce_eliminate 2.35% : 0.000005s : 40: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000001s : 8: predicate.remove_not_recompute_node 1.44% : 0.000003s : 26: predicate.replace_applicator 0.57% : 0.000001s : 8: predicate.replace_old_param 0.40% : 0.000001s : 4: predicate.reset_defer_inline 1.38% : 0.000003s : 14: predicate.reshape_eliminate 0.71% : 0.000002s : 8: predicate.row_tensor_add_zeros_like 0.49% : 0.000001s : 4: predicate.row_tensor_eliminate 0.73% : 0.000002s : 8: predicate.same_eliminate 0.38% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.64% : 0.000001s : 8: predicate.shard_identity_eliminate 0.63% : 0.000001s : 8: predicate.special_op_eliminate 0.57% : 0.000001s : 8: predicate.specialize_transform 1.11% : 0.000003s : 8: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.65% : 0.000004s : 23: predicate.switch_defer_inline 2.17% : 0.000005s : 31: predicate.switch_layer_defer_inline 5.24% : 0.000012s : 74: predicate.switch_simplify 1.03% : 0.000002s : 14: predicate.tile_eliminate 0.91% : 0.000002s : 14: predicate.transpose_eliminate 1.45% : 0.000003s : 22: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000004s : 22: predicate.tuple_list_get_item_const_eliminator 1.45% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 3.68% : 0.000009s : 34: predicate.tuple_list_get_item_eliminator 1.34% : 0.000003s : 22: predicate.tuple_list_get_set_item_eliminator 1.98% : 0.000005s : 30: predicate.tuple_list_set_item_eliminator 1.61% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 2.09% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.90% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.42% : 0.000001s : 4: predicate.value_based_eliminate 0.59% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.64% : 0.000001s : 8: predicate.virtual_output_eliminate 0.23% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.59% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000821 12 47.01% : 0.000386s : 5: func_graph_cloner_run.FuncGraphClonerGraph 52.99% : 0.000435s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.553171 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.71% : 0.003916s : 1: add_attr 0.70% : 0.003900s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.01% : 0.000070s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000079s : 1: auto_monad 0.00% : 0.000022s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.10% : 0.000561s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000012s : 1: convert_after_rewriter 0.01% : 0.000028s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.01% : 0.000030s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.11% : 0.000626s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.17% : 0.000920s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000027s : 1: opt.transform.mutable_eliminate 0.23% : 0.001288s : 78: opt.transform.opt_a 0.01% : 0.000031s : 1: opt.transform.opt_after_cconv 0.00% : 0.000027s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000104s : 28: opt.transform.opt_b 0.02% : 0.000103s : 2: opt.transform.opt_trans_graph 0.01% : 0.000038s : 4: opt.transform.symbol_engine_opt 31.72% : 0.175492s : 1: opt_a 0.02% : 0.000131s : 1: opt_after_cconv 0.11% : 0.000620s : 1: opt_after_jit_grad 0.04% : 0.000243s : 1: opt_b 32.24% : 0.178349s : 1: optimize 0.00% : 0.000027s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000009s : 1: order_py_execute_after_rewriter 0.00% : 0.000026s : 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% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000043s : 1: pre_auto_parallel 0.01% : 0.000033s : 1: py_interpret_to_execute 0.00% : 0.000025s : 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 31.18% : 0.172488s : 1: renormalize.infer 0.12% : 0.000642s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000053s : 1: rewriter_after_opt_a 0.02% : 0.000095s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000007s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000008s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000086s : 1: symbol_engine_optimizer 0.03% : 0.000139s : 1: tuple_transform 2.26% : 0.012522s : 1: type_inference TotalTime = 0.350652, [21] [bootstrap]: 0.00049807 [type_inference]: 0.317757 [event_method]: 2.794e-05 [auto_monad]: 7.904e-05 [graph_reusing]: 6.91999e-06 [inline]: 3.51999e-06 [add_attr]: 0.00435969, [1] [add_attr_with_inline]: 0.00434749, [1] [Cycle 1]: 8.295e-05, [2] [tag_attr]: 2.698e-05 [meta_addattr_fg_expand]: 5.39998e-06 [parallel-infer-symbol]: 4.1e-06 [pre_auto_parallel]: 4.726e-05 [insert-virtual-dataset]: 2.75002e-06 [parallel-infer-symbol-second]: 9.39996e-07 [dataset_repeat_opt]: 2.69999e-06 [pipeline_split]: 1.78002e-06 [optimize]: 0.0268721, [53] [py_interpret_to_execute]: 3.583e-05 [rewriter_before_opt_a]: 9.175e-05 [opt_a]: 0.00329174, [2] [Cycle 1]: 0.00257367, [45] [expand_dump_flag]: 3.38e-06 [switch_simplify]: 4.48e-05 [loop_unroll]: 3.008e-05 [a_1]: 0.00076907 [with_stream_mark]: 2.748e-05 [recompute_prepare]: 1.213e-05 [updatestate_depend_eliminate]: 3.89002e-06 [updatestate_assign_eliminate]: 3.36001e-06 [updatestate_loads_eliminate]: 3.02002e-06 [parameter_eliminate]: 1.94e-06 [a_2]: 7.679e-05 [accelerated_algorithm]: 7.05e-06 [shard]: 2.19001e-06 [meta_shard_fg_expand]: 1.92001e-06 [shard_inline]: 6.19999e-06 [merge_send_recv]: 9.92999e-06 [auto_parallel]: 8.58001e-06 [parallel]: 2.245e-05 [flash_sp]: 1.047e-05 [merge_comm]: 4.50001e-06 [allreduce_fusion]: 3.38e-06 [matmul_add_comm_reduction]: 1.146e-05 [allreduce_slice_to_reducescatter]: 9.79984e-07 [virtual_shard_identity]: 9.94999e-06 [virtual_dataset]: 6.08002e-06 [get_grad_eliminate_]: 6.63e-06 [virtual_output]: 6.13998e-06 [merge_forward]: 3.72002e-06 [cell_reuse_recompute_pass]: 1.70001e-06 [offload_activation]: 1.194e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.562e-05 [merge_recompute_call_nodes]: 2.00002e-06 [before_grad]: 1.117e-05 [set_forward_comm_id_for_comm_node_pass]: 3.8e-06 [meta_fg_expand]: 2.37999e-06 [flash_sp_send_recv_attached]: 3.3e-06 [receive_attached]: 2.25002e-06 [after_resolve]: 1.298e-05 [a_after_grad]: 9.73998e-06 [renormalize]: 0.000996 [add_forward_monad_depend]: 9.25999e-06 [auto_monad_grad]: 3.21999e-06 [auto_monad_eliminator]: 2.119e-05 [cse]: 3.426e-05 [a_3]: 5.478e-05 [Cycle 2]: 0.00070215, [45] [expand_dump_flag]: 2.76e-06 [switch_simplify]: 8.48999e-06 [loop_unroll]: 5.73997e-06 [a_1]: 0.00012373 [with_stream_mark]: 2.26e-05 [recompute_prepare]: 6.26998e-06 [updatestate_depend_eliminate]: 4.21001e-06 [updatestate_assign_eliminate]: 3.14999e-06 [updatestate_loads_eliminate]: 2.79999e-06 [parameter_eliminate]: 1.91e-06 [a_2]: 6.564e-05 [accelerated_algorithm]: 5.99999e-06 [shard]: 2.89001e-06 [meta_shard_fg_expand]: 2.49001e-06 [shard_inline]: 5.96998e-06 [merge_send_recv]: 7.56001e-06 [auto_parallel]: 9.40001e-06 [parallel]: 8.97e-06 [flash_sp]: 4.38999e-06 [merge_comm]: 3.7e-06 [allreduce_fusion]: 3.33998e-06 [matmul_add_comm_reduction]: 8.62e-06 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 7.11001e-06 [virtual_dataset]: 5.62001e-06 [get_grad_eliminate_]: 7.33999e-06 [virtual_output]: 5.40999e-06 [merge_forward]: 4.3e-06 [cell_reuse_recompute_pass]: 2.01e-06 [offload_activation]: 1.144e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.601e-05 [merge_recompute_call_nodes]: 1.30999e-06 [before_grad]: 1.056e-05 [set_forward_comm_id_for_comm_node_pass]: 3.93999e-06 [meta_fg_expand]: 2.01e-06 [flash_sp_send_recv_attached]: 1.50999e-06 [receive_attached]: 2.16e-06 [after_resolve]: 1.347e-05 [a_after_grad]: 1.004e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.56e-06 [auto_monad_grad]: 1.71998e-06 [auto_monad_eliminator]: 9.32001e-06 [cse]: 1.695e-05 [a_3]: 3.645e-05 [py_interpret_to_execute_after_opt_a]: 1.675e-05 [slice_cell_reuse_recomputed_activation]: 2.44999e-06 [rewriter_after_opt_a]: 4.159e-05 [convert_after_rewriter]: 7.13e-06 [order_py_execute_after_rewriter]: 5.29e-06 [mutable_eliminate]: 0.00086086 [opt_b]: 0.00022329, [1] [Cycle 1]: 0.0002137, [7] [b_1]: 0.00012066 [b_2]: 8.22e-06 [updatestate_depend_eliminate]: 1.217e-05 [updatestate_assign_eliminate]: 3.08e-06 [updatestate_loads_eliminate]: 2.91999e-06 [renormalize]: 1.15001e-06 [cse]: 2.91e-05 [optimize_parallel_all_gather_comm]: 2.198e-05 [overlap_param_gather]: 2.24001e-06 [cconv]: 4.12e-05 [loop_unroll]: 0.0213625 [opt_after_cconv]: 0.0001611, [1] [Cycle 1]: 0.00015086, [7] [c_1]: 3.672e-05 [parameter_eliminate]: 7.8e-06 [updatestate_depend_eliminate]: 1.461e-05 [updatestate_assign_eliminate]: 4.37e-06 [updatestate_loads_eliminate]: 3.27002e-06 [cse]: 4.45e-05 [renormalize]: 1.20999e-06 [remove_dup_value]: 1.77e-05 [tuple_transform]: 9.344e-05, [1] [Cycle 1]: 8.845e-05, [4] [d_1]: 5.9e-05 [none_parameter_eliminate]: 1.69e-06 [renormalize]: 4.39992e-07 [switch_simplify]: 7.56001e-06 [partial_unused_args_eliminate]: 2.03002e-06 [add_recomputation]: 6.396e-05 [cse_after_recomputation]: 2.947e-05, [1] [Cycle 1]: 2.381e-05, [1] [cse]: 1.506e-05 [environ_conv]: 7.43e-06 [swap_dp_allreduce_reducescatter]: 5.52999e-06 [bias_add_comm_swap]: 3.83001e-06 [label_micro_interleaved_index]: 8.17998e-06 [label_fine_grained_interleaved_index]: 3.25e-06 [merge_cast_opt]: 1.91e-06 [slice_recompute_activation]: 2.53998e-06 [micro_interleaved_order_control]: 3.14999e-06 [assign_add_opt]: 2.07999e-06 [ForceFp32Comm]: 1.31998e-06 [remove_cast_before_assign_add]: 1.09e-06 [full_micro_interleaved_order_control]: 2.32999e-06 [reorder_send_recv_between_fp_bp]: 3.31001e-06 [comm_op_add_attrs]: 1.30001e-06 [add_comm_op_reuse_tag]: 1.08001e-06 [interleave_split_concat_branches]: 1.64e-06 [interleave_parallel_branches]: 1.30999e-06 [overlap_opt_shard_in_pipeline]: 1.90001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.85001e-06 [control_data_broadcast_order]: 1.757e-05 [grouped_pairwise_exchange_alltoall]: 2.56e-06 [offloading_packed_experts]: 4.18999e-06 [overlap_recompute_and_grad_model_parallel]: 5.87999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.56002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.43e-06 [overlap_grad_ring_attention]: 4.54998e-06 [overlap_grad_flash_sp]: 2.445e-05 [begin_end_overlap_inline]: 5.79981e-07 [split_matmul_comm_elemetwise]: 2.79999e-06 [split_layernorm_comm]: 2.07999e-06 [handle_group_info]: 1.14e-06 [symbol_engine_optimizer]: 0.00010223, [1] [Cycle 1]: 9.488e-05, [6] [build]: 3.81001e-06 [elim_shapecalc]: 1.684e-05 [elim_not_effective]: 1.618e-05 [opt_reshape]: 8.72e-06 [fold_const_symbol]: 1.054e-05 [renormalize]: 6.49976e-07 [detach_backward]: 2.29001e-06 [pipeline_parallel_scheduler]: 2.34001e-06 [auto_monad_reorder]: 2.216e-05 [get_jit_bprop_graph]: 2.46e-06 [rewriter_after_jit_bprop_graph]: 8.75999e-06 [opt_after_jit_grad]: 0.00070417 [validate]: 4.497e-05 Sums bootstrap : 0.000498s : 0.14% type_inference : 0.317757s : 92.06% event_method : 0.000028s : 0.01% auto_monad : 0.000079s : 0.02% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 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 : 0.000036s : 0.01% optimize.rewriter_before_opt_a : 0.000092s : 0.03% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.02% optimize.opt_a.loop_unroll : 0.000036s : 0.01% optimize.opt_a.a_1 : 0.000893s : 0.26% optimize.opt_a.with_stream_mark : 0.000050s : 0.01% optimize.opt_a.recompute_prepare : 0.000018s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 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 : 0.000142s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000013s : 0.00% optimize.opt_a.shard : 0.000005s : 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 : 0.000017s : 0.01% optimize.opt_a.auto_parallel : 0.000018s : 0.01% optimize.opt_a.parallel : 0.000031s : 0.01% optimize.opt_a.flash_sp : 0.000015s : 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 : 0.000020s : 0.01% 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 : 0.000012s : 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 : 0.000008s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000023s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000032s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000022s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 0.00% optimize.opt_a.meta_fg_expand : 0.000004s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000026s : 0.01% optimize.opt_a.a_after_grad : 0.000020s : 0.01% optimize.opt_a.renormalize : 0.000996s : 0.29% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000031s : 0.01% optimize.opt_a.cse : 0.000051s : 0.01% optimize.opt_a.a_3 : 0.000091s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000017s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000042s : 0.01% optimize.convert_after_rewriter : 0.000007s : 0.00% optimize.order_py_execute_after_rewriter : 0.000005s : 0.00% optimize.mutable_eliminate : 0.000861s : 0.25% optimize.opt_b.b_1 : 0.000121s : 0.03% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000029s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.021362s : 6.19% optimize.opt_after_cconv.c_1 : 0.000037s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000045s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.01% optimize.tuple_transform.d_1 : 0.000059s : 0.02% 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 : 0.000064s : 0.02% optimize.cse_after_recomputation.cse : 0.000015s : 0.00% optimize.environ_conv : 0.000007s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000018s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000003s : 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 : 0.000002s : 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 : 0.000024s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000016s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000009s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000011s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000022s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000704s : 0.20% validate : 0.000045s : 0.01% Time group info: ------[substitution.] 0.000247 29 0.92% : 0.000002s : 2: substitution.elim_not_effective 0.54% : 0.000001s : 2: substitution.fold_const_symbol 2.70% : 0.000007s : 4: substitution.graph_param_transform 81.39% : 0.000201s : 5: substitution.inline 1.97% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.22% : 0.000005s : 4: substitution.remove_not_recompute_node 3.31% : 0.000008s : 4: substitution.replace_old_param 6.96% : 0.000017s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.317664 2 99.64% : 0.316531s : 1: type_inference.infer 0.36% : 0.001132s : 1: type_inference.specialize ------[replace.] 0.000078 9 65.73% : 0.000051s : 5: replace.inline 34.27% : 0.000027s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000213 9 92.83% : 0.000198s : 5: match.inline 7.17% : 0.000015s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000276 1341 0.72% : 0.000002s : 14: predicate.accumulaten_eliminater 1.06% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.48% : 0.000001s : 8: predicate.addn_check_dump 0.79% : 0.000002s : 14: predicate.addn_zero_filter 0.73% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.28% : 0.000004s : 22: predicate.arithmetic_simplify 0.74% : 0.000002s : 14: predicate.cast_eliminate 0.52% : 0.000001s : 8: predicate.check_bprop_eliminate 0.33% : 0.000001s : 8: predicate.compare_switch_simplify 0.13% : 0.000000s : 4: predicate.const_output_eliminate 0.80% : 0.000002s : 8: predicate.depend_value_elim 0.75% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.80% : 0.000002s : 14: predicate.dict_get_item_eliminator 0.66% : 0.000002s : 14: predicate.dict_set_item_eliminator 0.66% : 0.000002s : 8: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 4: predicate.elim_not_effective 0.38% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 0.96% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.04% : 0.000003s : 18: predicate.environ_get_add_eliminate 1.00% : 0.000003s : 18: predicate.environ_get_depend_swap 1.25% : 0.000003s : 26: predicate.environ_get_eliminate 0.89% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.26% : 0.000003s : 23: predicate.exchange_switch_depend_value 20.13% : 0.000056s : 23: predicate.float_depend_g_call 0.39% : 0.000001s : 8: predicate.float_environ_get_switch 0.51% : 0.000001s : 12: predicate.float_tuple_getitem_switch 0.15% : 0.000000s : 4: predicate.fold_const_symbol 0.68% : 0.000002s : 8: predicate.get_grad_eliminate 0.22% : 0.000001s : 4: predicate.graph_param_transform 0.40% : 0.000001s : 8: predicate.incorporate_call 0.35% : 0.000001s : 8: predicate.incorporate_call_switch 5.23% : 0.000014s : 61: predicate.inline 0.75% : 0.000002s : 8: predicate.inline_without_move 0.22% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.53% : 0.000001s : 8: predicate.less_batch_normalization 1.64% : 0.000005s : 26: predicate.list_to_tuple_eliminator_ 1.93% : 0.000005s : 40: predicate.load_eliminater 2.45% : 0.000007s : 4: predicate.loop_unroll_after_grad 1.81% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.71% : 0.000005s : 22: predicate.make_slice_get_slice_eliminator 0.55% : 0.000002s : 8: predicate.merge_addn 0.46% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.58% : 0.000002s : 8: predicate.mini_step_allgather_replace 0.68% : 0.000002s : 14: predicate.minmaximum_grad 1.25% : 0.000003s : 4: predicate.mutable_eliminate 0.35% : 0.000001s : 4: predicate.opt_reshape 0.29% : 0.000001s : 4: predicate.parallel_virtual_node 1.36% : 0.000004s : 23: predicate.partial_defer_inline 1.14% : 0.000003s : 22: predicate.partial_eliminate 0.66% : 0.000002s : 14: predicate.print_const_string_wrapper 0.38% : 0.000001s : 8: predicate.reduce_all_const_elim 0.90% : 0.000002s : 14: predicate.reduce_eliminate 1.99% : 0.000005s : 40: predicate.redundant_stop_gradient_eliminater 0.45% : 0.000001s : 8: predicate.remove_not_recompute_node 1.20% : 0.000003s : 26: predicate.replace_applicator 0.47% : 0.000001s : 8: predicate.replace_old_param 0.26% : 0.000001s : 4: predicate.reset_defer_inline 0.80% : 0.000002s : 14: predicate.reshape_eliminate 0.39% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.39% : 0.000001s : 4: predicate.row_tensor_eliminate 0.55% : 0.000002s : 8: predicate.same_eliminate 0.30% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.72% : 0.000002s : 8: predicate.shard_identity_eliminate 0.57% : 0.000002s : 8: predicate.special_op_eliminate 0.47% : 0.000001s : 8: predicate.specialize_transform 0.80% : 0.000002s : 8: predicate.split_environ_get_set_with_tuple_value 0.66% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.31% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.23% : 0.000003s : 23: predicate.switch_defer_inline 1.66% : 0.000005s : 31: predicate.switch_layer_defer_inline 4.05% : 0.000011s : 74: predicate.switch_simplify 0.71% : 0.000002s : 14: predicate.tile_eliminate 0.77% : 0.000002s : 14: predicate.transpose_eliminate 1.14% : 0.000003s : 22: predicate.tuple_list_convert_item_index_to_positive 1.09% : 0.000003s : 22: predicate.tuple_list_get_item_const_eliminator 1.02% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 2.86% : 0.000008s : 34: predicate.tuple_list_get_item_eliminator 1.05% : 0.000003s : 22: predicate.tuple_list_get_set_item_eliminator 1.54% : 0.000004s : 30: predicate.tuple_list_set_item_eliminator 1.46% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 1.98% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.33% : 0.000006s : 48: predicate.updatestate_useless_node_eliminater 0.26% : 0.000001s : 4: predicate.value_based_eliminate 0.41% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.41% : 0.000001s : 8: predicate.virtual_output_eliminate 0.18% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.31% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000778 12 45.70% : 0.000356s : 5: func_graph_cloner_run.FuncGraphClonerGraph 54.30% : 0.000422s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.384383 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.14% : 0.004367s : 1: add_attr 1.13% : 0.004352s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.02% : 0.000070s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000085s : 1: auto_monad 0.01% : 0.000028s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.14% : 0.000530s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000021s : 1: control_data_broadcast_order 0.00% : 0.000011s : 1: convert_after_rewriter 0.01% : 0.000033s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000011s : 1: environ_conv 0.01% : 0.000036s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 5.56% : 0.021383s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.23% : 0.000878s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.01% : 0.000038s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000023s : 1: opt.transform.mutable_eliminate 0.34% : 0.001324s : 78: opt.transform.opt_a 0.01% : 0.000034s : 1: opt.transform.opt_after_cconv 0.01% : 0.000032s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000098s : 28: opt.transform.opt_b 0.02% : 0.000064s : 2: opt.transform.opt_trans_graph 0.01% : 0.000047s : 4: opt.transform.symbol_engine_opt 0.86% : 0.003296s : 1: opt_a 0.04% : 0.000166s : 1: opt_after_cconv 0.19% : 0.000724s : 1: opt_after_jit_grad 0.06% : 0.000227s : 1: opt_b 6.99% : 0.026880s : 1: optimize 0.01% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000008s : 1: order_py_execute_after_rewriter 0.01% : 0.000029s : 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% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000052s : 1: pre_auto_parallel 0.01% : 0.000040s : 1: py_interpret_to_execute 0.01% : 0.000020s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000022s : 1: remove_dup_value 0.14% : 0.000540s : 1: renormalize.infer 0.12% : 0.000444s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000047s : 1: rewriter_after_opt_a 0.03% : 0.000097s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000007s : 1: slice_recompute_activation 0.00% : 0.000007s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000105s : 1: symbol_engine_optimizer 0.03% : 0.000096s : 1: tuple_transform 82.68% : 0.317792s : 1: type_inference [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:58.406.149 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:41:58.406.529 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. TotalTime = 2.60015, [21] [bootstrap]: 0.00053817 [type_inference]: 2.40012 [event_method]: 0.00012451 [auto_monad]: 0.00031804 [graph_reusing]: 2.235e-05 [inline]: 7.432e-05 [add_attr]: 0.123653, [1] [add_attr_with_inline]: 0.123637, [1] [Cycle 1]: 0.00019565, [2] [tag_attr]: 0.00011731 [meta_addattr_fg_expand]: 2.235e-05 [parallel-infer-symbol]: 3.91001e-06 [pre_auto_parallel]: 0.00019407 [insert-virtual-dataset]: 2.68e-06 [parallel-infer-symbol-second]: 1.11002e-06 [dataset_repeat_opt]: 2.41998e-06 [pipeline_split]: 1.72001e-06 [optimize]: 0.0739202, [53] [py_interpret_to_execute]: 0.00017645 [rewriter_before_opt_a]: 0.00040513 [opt_a]: 0.0705557, [2] [Cycle 1]: 0.0697993, [45] [expand_dump_flag]: 1.325e-05 [switch_simplify]: 0.00037797 [loop_unroll]: 0.00014052 [a_1]: 0.00504821 [with_stream_mark]: 4.311e-05 [recompute_prepare]: 2.543e-05 [updatestate_depend_eliminate]: 8.94e-06 [updatestate_assign_eliminate]: 5.22999e-06 [updatestate_loads_eliminate]: 4.95999e-06 [parameter_eliminate]: 2.70002e-06 [a_2]: 0.00027962 [accelerated_algorithm]: 1.062e-05 [shard]: 2.29001e-06 [meta_shard_fg_expand]: 8.40001e-06 [shard_inline]: 7.92e-06 [merge_send_recv]: 1.225e-05 [auto_parallel]: 1.273e-05 [parallel]: 2.801e-05 [flash_sp]: 1.321e-05 [merge_comm]: 4.63001e-06 [allreduce_fusion]: 4.03001e-06 [matmul_add_comm_reduction]: 1.21e-05 [allreduce_slice_to_reducescatter]: 1.02998e-06 [virtual_shard_identity]: 1.088e-05 [virtual_dataset]: 7.98001e-06 [get_grad_eliminate_]: 7.13e-06 [virtual_output]: 7.4e-06 [merge_forward]: 4.55999e-06 [cell_reuse_recompute_pass]: 1.86e-06 [offload_activation]: 1.154e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.548e-05 [merge_recompute_call_nodes]: 1.82001e-06 [before_grad]: 1.102e-05 [set_forward_comm_id_for_comm_node_pass]: 4.52003e-06 [meta_fg_expand]: 5.76e-06 [flash_sp_send_recv_attached]: 3.28e-06 [receive_attached]: 2.22001e-06 [after_resolve]: 1.484e-05 [a_after_grad]: 1.036e-05 [renormalize]: 0.0630609 [add_forward_monad_depend]: 1.389e-05 [auto_monad_grad]: 3.43e-06 [auto_monad_eliminator]: 3.246e-05 [cse]: 3.77e-05 [a_3]: 6.837e-05 [Cycle 2]: 0.00073678, [45] [expand_dump_flag]: 2.94001e-06 [switch_simplify]: 9.69e-06 [loop_unroll]: 6.63e-06 [a_1]: 0.00014061 [with_stream_mark]: 2.378e-05 [recompute_prepare]: 7.57002e-06 [updatestate_depend_eliminate]: 4.2e-06 [updatestate_assign_eliminate]: 3.16001e-06 [updatestate_loads_eliminate]: 3.40003e-06 [parameter_eliminate]: 1.99e-06 [a_2]: 6.776e-05 [accelerated_algorithm]: 6.50002e-06 [shard]: 2.89999e-06 [meta_shard_fg_expand]: 2.55002e-06 [shard_inline]: 5.70001e-06 [merge_send_recv]: 8.76002e-06 [auto_parallel]: 1.019e-05 [parallel]: 1.017e-05 [flash_sp]: 4.47e-06 [merge_comm]: 3.98999e-06 [allreduce_fusion]: 3.13e-06 [matmul_add_comm_reduction]: 1.218e-05 [allreduce_slice_to_reducescatter]: 8.30012e-07 [virtual_shard_identity]: 7.75998e-06 [virtual_dataset]: 6.14999e-06 [get_grad_eliminate_]: 6.33e-06 [virtual_output]: 5.54e-06 [merge_forward]: 4.17e-06 [cell_reuse_recompute_pass]: 3.03e-06 [offload_activation]: 1.097e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.268e-05 [merge_recompute_call_nodes]: 1.71002e-06 [before_grad]: 1.126e-05 [set_forward_comm_id_for_comm_node_pass]: 4.34002e-06 [meta_fg_expand]: 2.89001e-06 [flash_sp_send_recv_attached]: 1.79e-06 [receive_attached]: 2.51e-06 [after_resolve]: 1.534e-05 [a_after_grad]: 9.05001e-06 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.65001e-06 [auto_monad_grad]: 1.54e-06 [auto_monad_eliminator]: 8.17e-06 [cse]: 1.881e-05 [a_3]: 3.35e-05 [py_interpret_to_execute_after_opt_a]: 2.045e-05 [slice_cell_reuse_recomputed_activation]: 2.53998e-06 [rewriter_after_opt_a]: 4.861e-05 [convert_after_rewriter]: 7.11999e-06 [order_py_execute_after_rewriter]: 6.63e-06 [mutable_eliminate]: 0.0008765 [opt_b]: 0.00022697, [1] [Cycle 1]: 0.00021681, [7] [b_1]: 0.00012509 [b_2]: 9.25999e-06 [updatestate_depend_eliminate]: 8.89e-06 [updatestate_assign_eliminate]: 2.88e-06 [updatestate_loads_eliminate]: 2.83e-06 [renormalize]: 9.39996e-07 [cse]: 2.837e-05 [optimize_parallel_all_gather_comm]: 2.24e-05 [overlap_param_gather]: 2.29001e-06 [cconv]: 3.961e-05 [loop_unroll]: 0.00057332 [opt_after_cconv]: 0.00011658, [1] [Cycle 1]: 0.00010907, [7] [c_1]: 3.266e-05 [parameter_eliminate]: 6.74999e-06 [updatestate_depend_eliminate]: 6.12001e-06 [updatestate_assign_eliminate]: 2.80997e-06 [updatestate_loads_eliminate]: 3.51999e-06 [cse]: 2.165e-05 [renormalize]: 1.05999e-06 [remove_dup_value]: 1.625e-05 [tuple_transform]: 8.676e-05, [1] [Cycle 1]: 8.168e-05, [4] [d_1]: 5.07e-05 [none_parameter_eliminate]: 2.12999e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 8.32e-06 [partial_unused_args_eliminate]: 2.17999e-06 [add_recomputation]: 6.486e-05 [cse_after_recomputation]: 2.459e-05, [1] [Cycle 1]: 1.942e-05, [1] [cse]: 1.376e-05 [environ_conv]: 6.13002e-06 [swap_dp_allreduce_reducescatter]: 5.77999e-06 [bias_add_comm_swap]: 3.88999e-06 [label_micro_interleaved_index]: 6.99001e-06 [label_fine_grained_interleaved_index]: 3.28998e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 3.25e-06 [assign_add_opt]: 1.71e-06 [ForceFp32Comm]: 1.39e-06 [remove_cast_before_assign_add]: 1.11002e-06 [full_micro_interleaved_order_control]: 2.51998e-06 [reorder_send_recv_between_fp_bp]: 3.09999e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.06002e-06 [interleave_split_concat_branches]: 1.20001e-06 [interleave_parallel_branches]: 1.12e-06 [overlap_opt_shard_in_pipeline]: 1.52001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.72001e-06 [control_data_broadcast_order]: 1.526e-05 [grouped_pairwise_exchange_alltoall]: 1.77001e-06 [offloading_packed_experts]: 3.83001e-06 [overlap_recompute_and_grad_model_parallel]: 5.12999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.63e-06 [overlap_grad_ring_attention]: 4.13001e-06 [overlap_grad_flash_sp]: 2.511e-05 [begin_end_overlap_inline]: 9.50007e-07 [split_matmul_comm_elemetwise]: 2.59999e-06 [split_layernorm_comm]: 2.21998e-06 [handle_group_info]: 1.24e-06 [symbol_engine_optimizer]: 0.00023293, [1] [Cycle 1]: 0.00022575, [6] [build]: 0.00010954 [elim_shapecalc]: 1.793e-05 [elim_not_effective]: 2.838e-05 [opt_reshape]: 8.25e-06 [fold_const_symbol]: 1.73e-05 [renormalize]: 5.50004e-07 [detach_backward]: 2.96999e-06 [pipeline_parallel_scheduler]: 2.12999e-06 [auto_monad_reorder]: 2.228e-05 [get_jit_bprop_graph]: 2.46e-06 [rewriter_after_jit_bprop_graph]: 8.03001e-06 [opt_after_jit_grad]: 0.00074506 [validate]: 6.61e-05 Sums bootstrap : 0.000538s : 0.02% type_inference : 2.400122s : 96.97% event_method : 0.000125s : 0.01% auto_monad : 0.000318s : 0.01% graph_reusing : 0.000022s : 0.00% inline : 0.000074s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000117s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000022s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000194s : 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 : 0.000176s : 0.01% optimize.rewriter_before_opt_a : 0.000405s : 0.02% optimize.opt_a.expand_dump_flag : 0.000016s : 0.00% optimize.opt_a.switch_simplify : 0.000388s : 0.02% optimize.opt_a.loop_unroll : 0.000147s : 0.01% optimize.opt_a.a_1 : 0.005189s : 0.21% optimize.opt_a.with_stream_mark : 0.000067s : 0.00% optimize.opt_a.recompute_prepare : 0.000033s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 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 : 0.000347s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000017s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.00% optimize.opt_a.shard_inline : 0.000014s : 0.00% optimize.opt_a.merge_send_recv : 0.000021s : 0.00% optimize.opt_a.auto_parallel : 0.000023s : 0.00% optimize.opt_a.parallel : 0.000038s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000009s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000019s : 0.00% optimize.opt_a.virtual_dataset : 0.000014s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000013s : 0.00% optimize.opt_a.virtual_output : 0.000013s : 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 : 0.000023s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000038s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 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 : 0.000009s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000030s : 0.00% optimize.opt_a.a_after_grad : 0.000019s : 0.00% optimize.opt_a.renormalize : 0.063061s : 2.55% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000041s : 0.00% optimize.opt_a.cse : 0.000057s : 0.00% optimize.opt_a.a_3 : 0.000102s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000049s : 0.00% optimize.convert_after_rewriter : 0.000007s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000876s : 0.04% optimize.opt_b.b_1 : 0.000125s : 0.01% optimize.opt_b.b_2 : 0.000009s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000028s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.00% optimize.loop_unroll : 0.000573s : 0.02% optimize.opt_after_cconv.c_1 : 0.000033s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000022s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000016s : 0.00% optimize.tuple_transform.d_1 : 0.000051s : 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 : 0.000008s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000065s : 0.00% optimize.cse_after_recomputation.cse : 0.000014s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000015s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000025s : 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 : 0.000110s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000017s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000022s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000745s : 0.03% validate : 0.000066s : 0.00% Time group info: ------[substitution.] 0.001701 305 0.43% : 0.000007s : 4: substitution.depend_value_elim 0.76% : 0.000013s : 2: substitution.elim_not_effective 0.51% : 0.000009s : 2: substitution.fold_const_symbol 0.39% : 0.000007s : 4: substitution.graph_param_transform 65.69% : 0.001118s : 36: substitution.inline 0.30% : 0.000005s : 4: substitution.j_node_and_user_rematch 0.75% : 0.000013s : 8: substitution.minmaximum_grad 0.37% : 0.000006s : 4: substitution.remove_not_recompute_node 0.47% : 0.000008s : 4: substitution.replace_old_param 1.58% : 0.000027s : 10: substitution.switch_simplify 5.79% : 0.000099s : 40: substitution.tuple_list_convert_item_index_to_positive 3.16% : 0.000054s : 44: substitution.tuple_list_get_item_const_eliminator 7.87% : 0.000134s : 44: substitution.tuple_list_get_item_depend_reorder 7.77% : 0.000132s : 55: substitution.tuple_list_get_item_eliminator 4.16% : 0.000071s : 44: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.399655 2 99.52% : 2.388112s : 1: type_inference.infer 0.48% : 0.011543s : 1: type_inference.specialize ------[replace.] 0.000694 65 5.19% : 0.000036s : 4: replace.depend_value_elim 52.58% : 0.000365s : 36: replace.inline 20.31% : 0.000141s : 10: replace.switch_simplify 8.36% : 0.000058s : 4: replace.tuple_list_get_item_depend_reorder 13.56% : 0.000094s : 11: replace.tuple_list_get_item_eliminator ------[match.] 0.001209 65 0.41% : 0.000005s : 4: match.depend_value_elim 90.79% : 0.001098s : 36: match.inline 1.79% : 0.000022s : 10: match.switch_simplify 4.74% : 0.000057s : 4: match.tuple_list_get_item_depend_reorder 2.27% : 0.000027s : 11: match.tuple_list_get_item_eliminator ------[predicate.] 0.000809 4756 1.49% : 0.000012s : 70: predicate.accumulaten_eliminater 0.40% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.29% : 0.000002s : 16: predicate.addn_check_dump 1.29% : 0.000010s : 70: predicate.addn_zero_filter 1.40% : 0.000011s : 70: predicate.adjust_all_reduce_mul_add 2.01% : 0.000016s : 86: predicate.arithmetic_simplify 1.37% : 0.000011s : 70: predicate.cast_eliminate 0.15% : 0.000001s : 8: predicate.check_bprop_eliminate 0.27% : 0.000002s : 16: predicate.compare_switch_simplify 0.05% : 0.000000s : 4: predicate.const_output_eliminate 0.41% : 0.000003s : 18: predicate.depend_value_elim 1.34% : 0.000011s : 70: predicate.dict_get_item_const_eliminator 1.54% : 0.000012s : 70: predicate.dict_get_item_eliminator 1.23% : 0.000010s : 70: predicate.dict_set_item_eliminator 0.38% : 0.000003s : 8: predicate.dumpgradient_eliminate 0.09% : 0.000001s : 4: predicate.elim_not_effective 0.22% : 0.000002s : 4: predicate.elim_shapecalc_of_broadcastargs 1.60% : 0.000013s : 74: predicate.environ_add_const_eliminate 1.33% : 0.000011s : 74: predicate.environ_get_add_eliminate 1.43% : 0.000012s : 74: predicate.environ_get_depend_swap 1.64% : 0.000013s : 90: predicate.environ_get_eliminate 1.29% : 0.000010s : 74: predicate.environ_get_set_eliminate 2.50% : 0.000020s : 121: predicate.exchange_switch_depend_value 3.31% : 0.000027s : 121: predicate.float_depend_g_call 0.32% : 0.000003s : 16: predicate.float_environ_get_switch 0.37% : 0.000003s : 20: predicate.float_tuple_getitem_switch 0.05% : 0.000000s : 4: predicate.fold_const_symbol 0.20% : 0.000002s : 8: predicate.get_grad_eliminate 0.05% : 0.000000s : 4: predicate.graph_param_transform 0.30% : 0.000002s : 16: predicate.incorporate_call 0.27% : 0.000002s : 16: predicate.incorporate_call_switch 6.35% : 0.000051s : 223: predicate.inline 0.19% : 0.000002s : 8: predicate.inline_without_move 0.08% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.27% : 0.000002s : 8: predicate.less_batch_normalization 1.70% : 0.000014s : 93: predicate.list_to_tuple_eliminator_ 2.89% : 0.000023s : 163: predicate.load_eliminater 0.30% : 0.000002s : 4: predicate.loop_unroll_after_grad 3.02% : 0.000024s : 173: predicate.loop_unroll_before_grad 1.93% : 0.000016s : 82: predicate.make_slice_get_slice_eliminator 0.35% : 0.000003s : 16: predicate.merge_addn 0.13% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.14% : 0.000001s : 8: predicate.mini_step_allgather_replace 1.30% : 0.000011s : 70: predicate.minmaximum_grad 0.52% : 0.000004s : 4: predicate.mutable_eliminate 0.10% : 0.000001s : 4: predicate.opt_reshape 0.17% : 0.000001s : 4: predicate.parallel_virtual_node 3.09% : 0.000025s : 121: predicate.partial_defer_inline 1.74% : 0.000014s : 89: predicate.partial_eliminate 1.29% : 0.000010s : 70: predicate.print_const_string_wrapper 0.23% : 0.000002s : 12: predicate.reduce_all_const_elim 1.76% : 0.000014s : 70: predicate.reduce_eliminate 3.03% : 0.000024s : 163: predicate.redundant_stop_gradient_eliminater 0.13% : 0.000001s : 8: predicate.remove_not_recompute_node 1.26% : 0.000010s : 93: predicate.replace_applicator 0.14% : 0.000001s : 8: predicate.replace_old_param 0.11% : 0.000001s : 4: predicate.reset_defer_inline 1.37% : 0.000011s : 70: predicate.reshape_eliminate 0.15% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.15% : 0.000001s : 4: predicate.row_tensor_eliminate 0.22% : 0.000002s : 8: predicate.same_eliminate 0.26% : 0.000002s : 12: predicate.set_cell_output_no_recompute 0.21% : 0.000002s : 8: predicate.shard_identity_eliminate 0.22% : 0.000002s : 8: predicate.special_op_eliminate 0.33% : 0.000003s : 16: predicate.specialize_transform 0.30% : 0.000002s : 8: predicate.split_environ_get_set_with_tuple_value 0.19% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.07% : 0.000001s : 4: predicate.switch_call_monad_eliminater 2.36% : 0.000019s : 121: predicate.switch_defer_inline 2.61% : 0.000021s : 129: predicate.switch_layer_defer_inline 6.40% : 0.000052s : 334: predicate.switch_simplify 1.38% : 0.000011s : 70: predicate.tile_eliminate 1.32% : 0.000011s : 70: predicate.transpose_eliminate 1.68% : 0.000014s : 78: predicate.tuple_list_convert_item_index_to_positive 1.87% : 0.000015s : 82: predicate.tuple_list_get_item_const_eliminator 1.78% : 0.000014s : 82: predicate.tuple_list_get_item_depend_reorder 3.51% : 0.000028s : 109: predicate.tuple_list_get_item_eliminator 1.99% : 0.000016s : 82: predicate.tuple_list_get_set_item_eliminator 2.06% : 0.000017s : 98: predicate.tuple_list_set_item_eliminator 1.71% : 0.000014s : 93: predicate.tuple_to_list_eliminator_ 3.10% : 0.000025s : 163: predicate.updatestate_pure_node_eliminater 3.20% : 0.000026s : 179: predicate.updatestate_useless_node_eliminater 0.12% : 0.000001s : 4: predicate.value_based_eliminate 0.24% : 0.000002s : 8: predicate.virtual_dataset_eliminate 0.20% : 0.000002s : 8: predicate.virtual_output_eliminate 0.06% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.10% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.011644 84 72.72% : 0.008467s : 44: func_graph_cloner_run.FuncGraphClonerGraph 27.28% : 0.003177s : 40: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.867195 209 0.00% : 0.000004s : 1: ForceFp32Comm 4.31% : 0.123661s : 1: add_attr 4.31% : 0.123643s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000071s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.01% : 0.000331s : 1: auto_monad 0.00% : 0.000030s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000571s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000021s : 1: control_data_broadcast_order 0.00% : 0.000011s : 1: convert_after_rewriter 0.00% : 0.000027s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.00% : 0.000139s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000028s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000080s : 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% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.02% : 0.000589s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000024s : 1: micro_interleaved_order_control 0.03% : 0.000898s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000025s : 1: opt.transform.mutable_eliminate 0.22% : 0.006276s : 95: opt.transform.opt_a 0.00% : 0.000031s : 1: opt.transform.opt_after_cconv 0.00% : 0.000037s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000104s : 28: opt.transform.opt_b 0.00% : 0.000057s : 2: opt.transform.opt_trans_graph 0.00% : 0.000066s : 4: opt.transform.symbol_engine_opt 2.46% : 0.070559s : 1: opt_a 0.00% : 0.000120s : 1: opt_after_cconv 0.03% : 0.000768s : 1: opt_after_jit_grad 0.01% : 0.000231s : 1: opt_b 2.58% : 0.073928s : 1: optimize 0.00% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000010s : 1: order_py_execute_after_rewriter 0.00% : 0.000029s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000007s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 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% : 0.000008s : 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% : 0.000204s : 1: pre_auto_parallel 0.01% : 0.000186s : 1: py_interpret_to_execute 0.00% : 0.000025s : 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 2.09% : 0.059890s : 1: renormalize.infer 0.11% : 0.003150s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000055s : 1: rewriter_after_opt_a 0.01% : 0.000413s : 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% : 0.000236s : 1: symbol_engine_optimizer 0.00% : 0.000090s : 1: tuple_transform 83.71% : 2.400239s : 1: type_inference TotalTime = 0.134937, [21] [bootstrap]: 0.00044161 [type_inference]: 0.121367 [event_method]: 2.568e-05 [auto_monad]: 7.963e-05 [graph_reusing]: 7.13e-06 [inline]: 3.76001e-06 [add_attr]: 0.00534114, [1] [add_attr_with_inline]: 0.00532668, [1] [Cycle 1]: 7.537e-05, [2] [tag_attr]: 2.563e-05 [meta_addattr_fg_expand]: 5.63002e-06 [parallel-infer-symbol]: 3.63e-06 [pre_auto_parallel]: 4.82e-05 [insert-virtual-dataset]: 3.28e-06 [parallel-infer-symbol-second]: 9.5999e-07 [dataset_repeat_opt]: 2.44001e-06 [pipeline_split]: 1.90001e-06 [optimize]: 0.00660128, [53] [py_interpret_to_execute]: 4.913e-05 [rewriter_before_opt_a]: 9.814e-05 [opt_a]: 0.00342427, [2] [Cycle 1]: 0.00268564, [45] [expand_dump_flag]: 3.43e-06 [switch_simplify]: 4.698e-05 [loop_unroll]: 3.237e-05 [a_1]: 0.00077249 [with_stream_mark]: 2.62e-05 [recompute_prepare]: 1.128e-05 [updatestate_depend_eliminate]: 4.17998e-06 [updatestate_assign_eliminate]: 3.18e-06 [updatestate_loads_eliminate]: 2.87002e-06 [parameter_eliminate]: 2.64001e-06 [a_2]: 7.834e-05 [accelerated_algorithm]: 7.38e-06 [shard]: 2.64001e-06 [meta_shard_fg_expand]: 2.32999e-06 [shard_inline]: 6.74999e-06 [merge_send_recv]: 1.087e-05 [auto_parallel]: 8.57998e-06 [parallel]: 2.341e-05 [flash_sp]: 1.062e-05 [merge_comm]: 3.53e-06 [allreduce_fusion]: 3.60003e-06 [matmul_add_comm_reduction]: 1.096e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 8.40999e-06 [virtual_dataset]: 6.72002e-06 [get_grad_eliminate_]: 5.66998e-06 [virtual_output]: 6.19001e-06 [merge_forward]: 4.15999e-06 [cell_reuse_recompute_pass]: 1.28002e-06 [offload_activation]: 1.094e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.455e-05 [merge_recompute_call_nodes]: 1.66998e-06 [before_grad]: 1.142e-05 [set_forward_comm_id_for_comm_node_pass]: 4.12998e-06 [meta_fg_expand]: 2.61e-06 [flash_sp_send_recv_attached]: 3.39001e-06 [receive_attached]: 2.27001e-06 [after_resolve]: 1.377e-05 [a_after_grad]: 9.70002e-06 [renormalize]: 0.00107405 [add_forward_monad_depend]: 9.97001e-06 [auto_monad_grad]: 3.51001e-06 [auto_monad_eliminator]: 2.229e-05 [cse]: 5.433e-05 [a_3]: 5.571e-05 [Cycle 2]: 0.00072447, [45] [expand_dump_flag]: 1.76e-06 [switch_simplify]: 9.14e-06 [loop_unroll]: 7.11001e-06 [a_1]: 0.00013041 [with_stream_mark]: 1.928e-05 [recompute_prepare]: 6.32001e-06 [updatestate_depend_eliminate]: 4.04002e-06 [updatestate_assign_eliminate]: 2.96001e-06 [updatestate_loads_eliminate]: 3.23e-06 [parameter_eliminate]: 1.71998e-06 [a_2]: 8.061e-05 [accelerated_algorithm]: 7.01001e-06 [shard]: 2.84999e-06 [meta_shard_fg_expand]: 2.04999e-06 [shard_inline]: 6.11e-06 [merge_send_recv]: 8.40001e-06 [auto_parallel]: 9.09e-06 [parallel]: 9.35001e-06 [flash_sp]: 4.67e-06 [merge_comm]: 3.5e-06 [allreduce_fusion]: 3.55003e-06 [matmul_add_comm_reduction]: 9.81e-06 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 7.26999e-06 [virtual_dataset]: 5.39e-06 [get_grad_eliminate_]: 5.39e-06 [virtual_output]: 5.76998e-06 [merge_forward]: 4.57e-06 [cell_reuse_recompute_pass]: 4e-06 [offload_activation]: 1.347e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.711e-05 [merge_recompute_call_nodes]: 1.99e-06 [before_grad]: 1.055e-05 [set_forward_comm_id_for_comm_node_pass]: 4.51002e-06 [meta_fg_expand]: 2.27999e-06 [flash_sp_send_recv_attached]: 1.48002e-06 [receive_attached]: 2.29001e-06 [after_resolve]: 1.328e-05 [a_after_grad]: 8.82e-06 [renormalize]: 1.59984e-07 [add_forward_monad_depend]: 2.44001e-06 [auto_monad_grad]: 1.71002e-06 [auto_monad_eliminator]: 1.148e-05 [cse]: 1.922e-05 [a_3]: 3.401e-05 [py_interpret_to_execute_after_opt_a]: 2.018e-05 [slice_cell_reuse_recomputed_activation]: 2.12999e-06 [rewriter_after_opt_a]: 4.555e-05 [convert_after_rewriter]: 7.3e-06 [order_py_execute_after_rewriter]: 5.25999e-06 [mutable_eliminate]: 0.00096108 [opt_b]: 0.00030493, [1] [Cycle 1]: 0.00029432, [7] [b_1]: 0.00012846 [b_2]: 3.678e-05 [updatestate_depend_eliminate]: 3.264e-05 [updatestate_assign_eliminate]: 4.96002e-06 [updatestate_loads_eliminate]: 3.16001e-06 [renormalize]: 1.41002e-06 [cse]: 3.767e-05 [optimize_parallel_all_gather_comm]: 2.53e-05 [overlap_param_gather]: 2.32001e-06 [cconv]: 4.123e-05 [loop_unroll]: 0.00063072 [opt_after_cconv]: 0.00012391, [1] [Cycle 1]: 0.00011533, [7] [c_1]: 3.311e-05 [parameter_eliminate]: 6.18998e-06 [updatestate_depend_eliminate]: 8.38001e-06 [updatestate_assign_eliminate]: 3.08e-06 [updatestate_loads_eliminate]: 2.46e-06 [cse]: 2.429e-05 [renormalize]: 9.10019e-07 [remove_dup_value]: 1.76e-05 [tuple_transform]: 0.00011559, [1] [Cycle 1]: 0.00011, [4] [d_1]: 5.111e-05 [none_parameter_eliminate]: 1.62999e-06 [renormalize]: 2.60014e-07 [switch_simplify]: 8.37e-06 [partial_unused_args_eliminate]: 2.26998e-06 [add_recomputation]: 6.09e-05 [cse_after_recomputation]: 2.83e-05, [1] [Cycle 1]: 2.221e-05, [1] [cse]: 1.535e-05 [environ_conv]: 7.55e-06 [swap_dp_allreduce_reducescatter]: 5.73002e-06 [bias_add_comm_swap]: 4.04002e-06 [label_micro_interleaved_index]: 7.36001e-06 [label_fine_grained_interleaved_index]: 2.90998e-06 [merge_cast_opt]: 1.42999e-06 [slice_recompute_activation]: 2.39001e-06 [micro_interleaved_order_control]: 2.43002e-06 [assign_add_opt]: 1.59e-06 [ForceFp32Comm]: 1.14e-06 [remove_cast_before_assign_add]: 1.24998e-06 [full_micro_interleaved_order_control]: 2.72001e-06 [reorder_send_recv_between_fp_bp]: 3.4e-06 [comm_op_add_attrs]: 1.21997e-06 [add_comm_op_reuse_tag]: 1.32e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.52001e-06 [overlap_opt_shard_in_pipeline]: 1.60999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.86e-06 [control_data_broadcast_order]: 1.615e-05 [grouped_pairwise_exchange_alltoall]: 1.88002e-06 [offloading_packed_experts]: 4.25999e-06 [overlap_recompute_and_grad_model_parallel]: 5.30999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.51002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47001e-06 [overlap_recompute_comm]: 2.58998e-06 [overlap_grad_ring_attention]: 4.62e-06 [overlap_grad_flash_sp]: 2.337e-05 [begin_end_overlap_inline]: 6.60017e-07 [split_matmul_comm_elemetwise]: 2.36e-06 [split_layernorm_comm]: 2.15002e-06 [handle_group_info]: 1.25999e-06 [symbol_engine_optimizer]: 0.00024261, [1] [Cycle 1]: 0.00023604, [6] [build]: 0.00014632 [elim_shapecalc]: 1.295e-05 [elim_not_effective]: 1.694e-05 [opt_reshape]: 7.31999e-06 [fold_const_symbol]: 1.581e-05 [renormalize]: 2.50002e-07 [detach_backward]: 2.79001e-06 [pipeline_parallel_scheduler]: 2.24001e-06 [auto_monad_reorder]: 2.043e-05 [get_jit_bprop_graph]: 2.18002e-06 [rewriter_after_jit_bprop_graph]: 7.22002e-06 [opt_after_jit_grad]: 0.0007257 [validate]: 5.017e-05 Sums bootstrap : 0.000442s : 0.34% type_inference : 0.121367s : 94.50% event_method : 0.000026s : 0.02% auto_monad : 0.000080s : 0.06% graph_reusing : 0.000007s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000048s : 0.04% 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 : 0.000049s : 0.04% optimize.rewriter_before_opt_a : 0.000098s : 0.08% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000056s : 0.04% optimize.opt_a.loop_unroll : 0.000039s : 0.03% optimize.opt_a.a_1 : 0.000903s : 0.70% optimize.opt_a.with_stream_mark : 0.000045s : 0.04% optimize.opt_a.recompute_prepare : 0.000018s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000008s : 0.01% 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 : 0.000159s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000013s : 0.01% optimize.opt_a.merge_send_recv : 0.000019s : 0.02% optimize.opt_a.auto_parallel : 0.000018s : 0.01% optimize.opt_a.parallel : 0.000033s : 0.03% optimize.opt_a.flash_sp : 0.000015s : 0.01% optimize.opt_a.merge_comm : 0.000007s : 0.01% optimize.opt_a.allreduce_fusion : 0.000007s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000016s : 0.01% optimize.opt_a.virtual_dataset : 0.000012s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000011s : 0.01% optimize.opt_a.virtual_output : 0.000012s : 0.01% optimize.opt_a.merge_forward : 0.000009s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000024s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000032s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000022s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.01% optimize.opt_a.meta_fg_expand : 0.000005s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000027s : 0.02% optimize.opt_a.a_after_grad : 0.000019s : 0.01% optimize.opt_a.renormalize : 0.001074s : 0.84% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000034s : 0.03% optimize.opt_a.cse : 0.000074s : 0.06% optimize.opt_a.a_3 : 0.000090s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000046s : 0.04% optimize.convert_after_rewriter : 0.000007s : 0.01% optimize.order_py_execute_after_rewriter : 0.000005s : 0.00% optimize.mutable_eliminate : 0.000961s : 0.75% optimize.opt_b.b_1 : 0.000128s : 0.10% optimize.opt_b.b_2 : 0.000037s : 0.03% optimize.opt_b.updatestate_depend_eliminate : 0.000033s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000038s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000025s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.03% optimize.loop_unroll : 0.000631s : 0.49% optimize.opt_after_cconv.c_1 : 0.000033s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.01% 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 : 0.000024s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.01% optimize.tuple_transform.d_1 : 0.000051s : 0.04% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000061s : 0.05% optimize.cse_after_recomputation.cse : 0.000015s : 0.01% optimize.environ_conv : 0.000008s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.01% 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 : 0.000002s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000016s : 0.01% 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 0.02% 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 : 0.000146s : 0.11% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000017s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000016s : 0.01% 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 : 0.000020s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.01% opt_after_jit_grad : 0.000726s : 0.57% validate : 0.000050s : 0.04% Time group info: ------[substitution.] 0.000275 29 1.50% : 0.000004s : 2: substitution.elim_not_effective 2.75% : 0.000008s : 2: substitution.fold_const_symbol 2.74% : 0.000008s : 4: substitution.graph_param_transform 80.00% : 0.000220s : 5: substitution.inline 1.75% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.31% : 0.000006s : 4: substitution.remove_not_recompute_node 2.49% : 0.000007s : 4: substitution.replace_old_param 6.46% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.121284 2 99.21% : 0.120331s : 1: type_inference.infer 0.79% : 0.000953s : 1: type_inference.specialize ------[replace.] 0.000078 9 69.75% : 0.000054s : 5: replace.inline 30.25% : 0.000023s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000232 9 93.19% : 0.000216s : 5: match.inline 6.81% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000233 1341 0.96% : 0.000002s : 14: predicate.accumulaten_eliminater 1.29% : 0.000003s : 4: predicate.ad_related_special_op_eliminate 0.48% : 0.000001s : 8: predicate.addn_check_dump 0.90% : 0.000002s : 14: predicate.addn_zero_filter 0.75% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.70% : 0.000004s : 22: predicate.arithmetic_simplify 0.93% : 0.000002s : 14: predicate.cast_eliminate 0.69% : 0.000002s : 8: predicate.check_bprop_eliminate 0.55% : 0.000001s : 8: predicate.compare_switch_simplify 0.17% : 0.000000s : 4: predicate.const_output_eliminate 0.63% : 0.000001s : 8: predicate.depend_value_elim 0.92% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 1.12% : 0.000003s : 14: predicate.dict_get_item_eliminator 1.05% : 0.000002s : 14: predicate.dict_set_item_eliminator 1.31% : 0.000003s : 8: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 4: predicate.elim_not_effective 0.36% : 0.000001s : 4: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000003s : 18: predicate.environ_add_const_eliminate 0.97% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.65% : 0.000004s : 18: predicate.environ_get_depend_swap 1.51% : 0.000004s : 26: predicate.environ_get_eliminate 1.01% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.45% : 0.000003s : 23: predicate.exchange_switch_depend_value 2.37% : 0.000006s : 23: predicate.float_depend_g_call 0.42% : 0.000001s : 8: predicate.float_environ_get_switch 0.72% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.16% : 0.000000s : 4: predicate.fold_const_symbol 0.65% : 0.000002s : 8: predicate.get_grad_eliminate 0.15% : 0.000000s : 4: predicate.graph_param_transform 0.52% : 0.000001s : 8: predicate.incorporate_call 0.40% : 0.000001s : 8: predicate.incorporate_call_switch 6.35% : 0.000015s : 61: predicate.inline 0.88% : 0.000002s : 8: predicate.inline_without_move 0.28% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.91% : 0.000002s : 8: predicate.less_batch_normalization 1.83% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 2.43% : 0.000006s : 40: predicate.load_eliminater 0.81% : 0.000002s : 4: predicate.loop_unroll_after_grad 2.51% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.64% : 0.000004s : 22: predicate.make_slice_get_slice_eliminator 0.54% : 0.000001s : 8: predicate.merge_addn 0.55% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.50% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.75% : 0.000002s : 14: predicate.minmaximum_grad 1.98% : 0.000005s : 4: predicate.mutable_eliminate 0.33% : 0.000001s : 4: predicate.opt_reshape 0.51% : 0.000001s : 4: predicate.parallel_virtual_node 1.71% : 0.000004s : 23: predicate.partial_defer_inline 1.37% : 0.000003s : 22: predicate.partial_eliminate 0.90% : 0.000002s : 14: predicate.print_const_string_wrapper 0.64% : 0.000001s : 8: predicate.reduce_all_const_elim 1.27% : 0.000003s : 14: predicate.reduce_eliminate 2.50% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.44% : 0.000001s : 8: predicate.remove_not_recompute_node 1.31% : 0.000003s : 26: predicate.replace_applicator 0.62% : 0.000001s : 8: predicate.replace_old_param 0.49% : 0.000001s : 4: predicate.reset_defer_inline 1.08% : 0.000003s : 14: predicate.reshape_eliminate 0.58% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.37% : 0.000001s : 4: predicate.row_tensor_eliminate 1.08% : 0.000003s : 8: predicate.same_eliminate 0.35% : 0.000001s : 8: predicate.set_cell_output_no_recompute 0.67% : 0.000002s : 8: predicate.shard_identity_eliminate 0.59% : 0.000001s : 8: predicate.special_op_eliminate 0.63% : 0.000001s : 8: predicate.specialize_transform 1.00% : 0.000002s : 8: predicate.split_environ_get_set_with_tuple_value 0.66% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 4: predicate.switch_call_monad_eliminater 1.44% : 0.000003s : 23: predicate.switch_defer_inline 1.92% : 0.000004s : 31: predicate.switch_layer_defer_inline 5.00% : 0.000012s : 74: predicate.switch_simplify 1.04% : 0.000002s : 14: predicate.tile_eliminate 0.87% : 0.000002s : 14: predicate.transpose_eliminate 1.71% : 0.000004s : 22: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000004s : 22: predicate.tuple_list_get_item_const_eliminator 1.48% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 3.26% : 0.000008s : 34: predicate.tuple_list_get_item_eliminator 1.54% : 0.000004s : 22: predicate.tuple_list_get_set_item_eliminator 2.03% : 0.000005s : 30: predicate.tuple_list_set_item_eliminator 1.81% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 2.16% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 3.03% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.35% : 0.000001s : 4: predicate.value_based_eliminate 0.71% : 0.000002s : 8: predicate.virtual_dataset_eliminate 0.72% : 0.000002s : 8: predicate.virtual_output_eliminate 0.27% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.42% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000712 12 46.18% : 0.000329s : 5: func_graph_cloner_run.FuncGraphClonerGraph 53.82% : 0.000383s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.149490 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.58% : 0.005349s : 1: add_attr 3.57% : 0.005331s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000065s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.06% : 0.000086s : 1: auto_monad 0.02% : 0.000025s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.32% : 0.000479s : 1: bootstrap 0.03% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000020s : 1: control_data_broadcast_order 0.01% : 0.000011s : 1: convert_after_rewriter 0.02% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000011s : 1: environ_conv 0.02% : 0.000035s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.01% : 0.000010s : 1: label_micro_interleaved_index 0.43% : 0.000645s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.66% : 0.000987s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.01% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000028s : 1: opt.transform.mutable_eliminate 0.90% : 0.001350s : 78: opt.transform.opt_a 0.02% : 0.000032s : 1: opt.transform.opt_after_cconv 0.02% : 0.000030s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000132s : 28: opt.transform.opt_b 0.04% : 0.000057s : 2: opt.transform.opt_trans_graph 0.03% : 0.000049s : 4: opt.transform.symbol_engine_opt 2.29% : 0.003428s : 1: opt_a 0.09% : 0.000128s : 1: opt_after_cconv 0.50% : 0.000744s : 1: opt_after_jit_grad 0.21% : 0.000309s : 1: opt_b 4.42% : 0.006608s : 1: optimize 0.02% : 0.000029s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000009s : 1: order_py_execute_after_rewriter 0.02% : 0.000027s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.01% : 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% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.04% : 0.000053s : 1: pre_auto_parallel 0.04% : 0.000053s : 1: py_interpret_to_execute 0.02% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000022s : 1: remove_dup_value 0.39% : 0.000586s : 1: renormalize.infer 0.32% : 0.000477s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000051s : 1: rewriter_after_opt_a 0.07% : 0.000103s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.16% : 0.000245s : 1: symbol_engine_optimizer 0.08% : 0.000119s : 1: tuple_transform 81.21% : 0.121398s : 1: type_inference [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:42:11.147.709 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. [WARNING] ME(160349:281473873510192,MainProcess):2026-01-29-17:42:11.148.084 [mindspore/common/tensor.py:142] For 'Tensor', if 'dtype' is not None, 'input_data', 'shape' or 'init' must not be None. TotalTime = 0.121778, [21] [bootstrap]: 0.00056425 [type_inference]: 0.107961 [event_method]: 2.321e-05 [auto_monad]: 7.697e-05 [graph_reusing]: 7.65e-06 [inline]: 3.8e-06 [add_attr]: 0.00466068, [1] [add_attr_with_inline]: 0.0046444, [1] [Cycle 1]: 0.00012017, [2] [tag_attr]: 5.75e-05 [meta_addattr_fg_expand]: 6.31e-06 [parallel-infer-symbol]: 5.07e-06 [pre_auto_parallel]: 5.053e-05 [insert-virtual-dataset]: 3.33998e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 2.91e-06 [pipeline_split]: 2.11e-06 [optimize]: 0.00727083, [53] [py_interpret_to_execute]: 3.933e-05 [rewriter_before_opt_a]: 0.00013253 [opt_a]: 0.00392359, [2] [Cycle 1]: 0.00309652, [45] [expand_dump_flag]: 3.53e-06 [switch_simplify]: 5.044e-05 [loop_unroll]: 3.343e-05 [a_1]: 0.00105292 [with_stream_mark]: 3.391e-05 [recompute_prepare]: 1.683e-05 [updatestate_depend_eliminate]: 4.70001e-06 [updatestate_assign_eliminate]: 3.53e-06 [updatestate_loads_eliminate]: 3.22997e-06 [parameter_eliminate]: 2.69999e-06 [a_2]: 7.78e-05 [accelerated_algorithm]: 7.73001e-06 [shard]: 2.73003e-06 [meta_shard_fg_expand]: 3.06001e-06 [shard_inline]: 6.56e-06 [merge_send_recv]: 1.084e-05 [auto_parallel]: 1.182e-05 [parallel]: 2.402e-05 [flash_sp]: 1.411e-05 [merge_comm]: 4.58999e-06 [allreduce_fusion]: 3.75e-06 [matmul_add_comm_reduction]: 1.272e-05 [allreduce_slice_to_reducescatter]: 9.5999e-07 [virtual_shard_identity]: 1.231e-05 [virtual_dataset]: 6.25002e-06 [get_grad_eliminate_]: 6.08998e-06 [virtual_output]: 6.44001e-06 [merge_forward]: 4.62e-06 [cell_reuse_recompute_pass]: 2.52001e-06 [offload_activation]: 1.143e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.882e-05 [merge_recompute_call_nodes]: 2.17001e-06 [before_grad]: 1.202e-05 [set_forward_comm_id_for_comm_node_pass]: 5.14e-06 [meta_fg_expand]: 3.03e-06 [flash_sp_send_recv_attached]: 2.99001e-06 [receive_attached]: 2.56e-06 [after_resolve]: 1.509e-05 [a_after_grad]: 1.061e-05 [renormalize]: 0.0011208 [add_forward_monad_depend]: 9.27999e-06 [auto_monad_grad]: 3.23998e-06 [auto_monad_eliminator]: 2.426e-05 [cse]: 3.534e-05 [a_3]: 5.64e-05 [Cycle 2]: 0.00080917, [45] [expand_dump_flag]: 2.40002e-06 [switch_simplify]: 8.50001e-06 [loop_unroll]: 7.23e-06 [a_1]: 0.00016316 [with_stream_mark]: 2.263e-05 [recompute_prepare]: 1.003e-05 [updatestate_depend_eliminate]: 4.04002e-06 [updatestate_assign_eliminate]: 3.31001e-06 [updatestate_loads_eliminate]: 3.49001e-06 [parameter_eliminate]: 2.14e-06 [a_2]: 6.932e-05 [accelerated_algorithm]: 6.59001e-06 [shard]: 3.06999e-06 [meta_shard_fg_expand]: 2.64999e-06 [shard_inline]: 6.48e-06 [merge_send_recv]: 9.74e-06 [auto_parallel]: 9.96e-06 [parallel]: 9.09e-06 [flash_sp]: 4.48001e-06 [merge_comm]: 4.05e-06 [allreduce_fusion]: 3.38e-06 [matmul_add_comm_reduction]: 1.182e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 9.62999e-06 [virtual_dataset]: 6.24001e-06 [get_grad_eliminate_]: 6.61e-06 [virtual_output]: 6.06e-06 [merge_forward]: 4.81002e-06 [cell_reuse_recompute_pass]: 2.64001e-06 [offload_activation]: 1.11e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.081e-05 [merge_recompute_call_nodes]: 1.89999e-06 [before_grad]: 1.058e-05 [set_forward_comm_id_for_comm_node_pass]: 5.31998e-06 [meta_fg_expand]: 2.48002e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 2.49001e-06 [after_resolve]: 1.445e-05 [a_after_grad]: 9.19e-06 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.66999e-06 [auto_monad_grad]: 2.56e-06 [auto_monad_eliminator]: 1.232e-05 [cse]: 2.331e-05 [a_3]: 3.471e-05 [py_interpret_to_execute_after_opt_a]: 1.881e-05 [slice_cell_reuse_recomputed_activation]: 2.96999e-06 [rewriter_after_opt_a]: 4.67e-05 [convert_after_rewriter]: 7.16001e-06 [order_py_execute_after_rewriter]: 6.38e-06 [mutable_eliminate]: 0.00094424 [opt_b]: 0.0002648, [1] [Cycle 1]: 0.00025133, [7] [b_1]: 0.00012233 [b_2]: 2.813e-05 [updatestate_depend_eliminate]: 1.312e-05 [updatestate_assign_eliminate]: 3.38999e-06 [updatestate_loads_eliminate]: 3.71999e-06 [renormalize]: 1.96e-06 [cse]: 3.62e-05 [optimize_parallel_all_gather_comm]: 5.312e-05 [overlap_param_gather]: 2.93998e-06 [cconv]: 4.301e-05 [loop_unroll]: 0.00077245 [opt_after_cconv]: 0.00014229, [1] [Cycle 1]: 0.00013313, [7] [c_1]: 3.338e-05 [parameter_eliminate]: 7.48999e-06 [updatestate_depend_eliminate]: 1.066e-05 [updatestate_assign_eliminate]: 2.73e-06 [updatestate_loads_eliminate]: 2.98e-06 [cse]: 3.611e-05 [renormalize]: 1.07e-06 [remove_dup_value]: 1.663e-05 [tuple_transform]: 0.00012724, [1] [Cycle 1]: 0.00012203, [4] [d_1]: 8.666e-05 [none_parameter_eliminate]: 2.09999e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 7.89002e-06 [partial_unused_args_eliminate]: 2.58e-06 [add_recomputation]: 6.533e-05 [cse_after_recomputation]: 2.863e-05, [1] [Cycle 1]: 2.33e-05, [1] [cse]: 1.722e-05 [environ_conv]: 6.51999e-06 [swap_dp_allreduce_reducescatter]: 6.53e-06 [bias_add_comm_swap]: 3.76001e-06 [label_micro_interleaved_index]: 7.78999e-06 [label_fine_grained_interleaved_index]: 3.11001e-06 [merge_cast_opt]: 1.60001e-06 [slice_recompute_activation]: 2.44999e-06 [micro_interleaved_order_control]: 2.90002e-06 [assign_add_opt]: 1.59998e-06 [ForceFp32Comm]: 1.21002e-06 [remove_cast_before_assign_add]: 1.20999e-06 [full_micro_interleaved_order_control]: 2.37001e-06 [reorder_send_recv_between_fp_bp]: 3.08e-06 [comm_op_add_attrs]: 1.34e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.06002e-06 [overlap_opt_shard_in_pipeline]: 1.27e-06 [overlap_opt_shard_grad_in_pipeline]: 2.01e-06 [control_data_broadcast_order]: 1.627e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 5.29998e-06 [overlap_recompute_and_grad_model_parallel]: 4.90999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.32999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49998e-06 [overlap_recompute_comm]: 3.13e-06 [overlap_grad_ring_attention]: 4.59998e-06 [overlap_grad_flash_sp]: 2.411e-05 [begin_end_overlap_inline]: 5.60016e-07 [split_matmul_comm_elemetwise]: 2.84999e-06 [split_layernorm_comm]: 2.24001e-06 [handle_group_info]: 1.98002e-06 [symbol_engine_optimizer]: 0.00020686, [1] [Cycle 1]: 0.00020124, [6] [build]: 0.00010144 [elim_shapecalc]: 1.56e-05 [elim_not_effective]: 1.635e-05 [opt_reshape]: 6.72002e-06 [fold_const_symbol]: 1.78e-05 [renormalize]: 4.59986e-07 [detach_backward]: 3.25e-06 [pipeline_parallel_scheduler]: 2.53e-06 [auto_monad_reorder]: 2.085e-05 [get_jit_bprop_graph]: 2.31998e-06 [rewriter_after_jit_bprop_graph]: 7.48e-06 [opt_after_jit_grad]: 0.0008404 [validate]: 5.654e-05 Sums bootstrap : 0.000564s : 0.49% type_inference : 0.107961s : 93.17% event_method : 0.000023s : 0.02% auto_monad : 0.000077s : 0.07% graph_reusing : 0.000008s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000057s : 0.05% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.01% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000051s : 0.04% 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 : 0.000039s : 0.03% optimize.rewriter_before_opt_a : 0.000133s : 0.11% optimize.opt_a.expand_dump_flag : 0.000006s : 0.01% optimize.opt_a.switch_simplify : 0.000059s : 0.05% optimize.opt_a.loop_unroll : 0.000041s : 0.04% optimize.opt_a.a_1 : 0.001216s : 1.05% optimize.opt_a.with_stream_mark : 0.000057s : 0.05% optimize.opt_a.recompute_prepare : 0.000027s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000147s : 0.13% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.01% optimize.opt_a.shard : 0.000006s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000013s : 0.01% optimize.opt_a.merge_send_recv : 0.000021s : 0.02% optimize.opt_a.auto_parallel : 0.000022s : 0.02% optimize.opt_a.parallel : 0.000033s : 0.03% optimize.opt_a.flash_sp : 0.000019s : 0.02% optimize.opt_a.merge_comm : 0.000009s : 0.01% optimize.opt_a.allreduce_fusion : 0.000007s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000025s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000022s : 0.02% optimize.opt_a.virtual_dataset : 0.000012s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000013s : 0.01% optimize.opt_a.virtual_output : 0.000013s : 0.01% optimize.opt_a.merge_forward : 0.000009s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000023s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000023s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000010s : 0.01% optimize.opt_a.meta_fg_expand : 0.000006s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000030s : 0.03% optimize.opt_a.a_after_grad : 0.000020s : 0.02% optimize.opt_a.renormalize : 0.001121s : 0.97% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000037s : 0.03% optimize.opt_a.cse : 0.000059s : 0.05% optimize.opt_a.a_3 : 0.000091s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000019s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000047s : 0.04% optimize.convert_after_rewriter : 0.000007s : 0.01% optimize.order_py_execute_after_rewriter : 0.000006s : 0.01% optimize.mutable_eliminate : 0.000944s : 0.81% optimize.opt_b.b_1 : 0.000122s : 0.11% optimize.opt_b.b_2 : 0.000028s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000002s : 0.00% optimize.opt_b.cse : 0.000036s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000053s : 0.05% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000043s : 0.04% optimize.loop_unroll : 0.000772s : 0.67% optimize.opt_after_cconv.c_1 : 0.000033s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.01% 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 : 0.000036s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.01% optimize.tuple_transform.d_1 : 0.000087s : 0.07% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000065s : 0.06% optimize.cse_after_recomputation.cse : 0.000017s : 0.01% optimize.environ_conv : 0.000007s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.01% 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 : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000016s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000024s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000101s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000016s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000018s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000003s : 0.00% auto_monad_reorder : 0.000021s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.01% opt_after_jit_grad : 0.000840s : 0.73% validate : 0.000057s : 0.05% Time group info: ------[substitution.] 0.000289 29 1.35% : 0.000004s : 2: substitution.elim_not_effective 2.81% : 0.000008s : 2: substitution.fold_const_symbol 2.67% : 0.000008s : 4: substitution.graph_param_transform 78.57% : 0.000227s : 5: substitution.inline 1.92% : 0.000006s : 4: substitution.j_node_and_user_rematch 2.50% : 0.000007s : 4: substitution.remove_not_recompute_node 2.43% : 0.000007s : 4: substitution.replace_old_param 7.76% : 0.000022s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.107878 2 99.12% : 0.106934s : 1: type_inference.infer 0.88% : 0.000944s : 1: type_inference.specialize ------[replace.] 0.000108 9 51.85% : 0.000056s : 5: replace.inline 48.15% : 0.000052s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000243 9 92.02% : 0.000224s : 5: match.inline 7.98% : 0.000019s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000431 1341 0.48% : 0.000002s : 14: predicate.accumulaten_eliminater 0.88% : 0.000004s : 4: predicate.ad_related_special_op_eliminate 0.26% : 0.000001s : 8: predicate.addn_check_dump 0.54% : 0.000002s : 14: predicate.addn_zero_filter 0.40% : 0.000002s : 14: predicate.adjust_all_reduce_mul_add 1.06% : 0.000005s : 22: predicate.arithmetic_simplify 0.59% : 0.000003s : 14: predicate.cast_eliminate 0.33% : 0.000001s : 8: predicate.check_bprop_eliminate 0.38% : 0.000002s : 8: predicate.compare_switch_simplify 0.09% : 0.000000s : 4: predicate.const_output_eliminate 0.28% : 0.000001s : 8: predicate.depend_value_elim 0.49% : 0.000002s : 14: predicate.dict_get_item_const_eliminator 0.74% : 0.000003s : 14: predicate.dict_get_item_eliminator 0.45% : 0.000002s : 14: predicate.dict_set_item_eliminator 0.61% : 0.000003s : 8: predicate.dumpgradient_eliminate 0.15% : 0.000001s : 4: predicate.elim_not_effective 0.39% : 0.000002s : 4: predicate.elim_shapecalc_of_broadcastargs 0.70% : 0.000003s : 18: predicate.environ_add_const_eliminate 0.54% : 0.000002s : 18: predicate.environ_get_add_eliminate 0.59% : 0.000003s : 18: predicate.environ_get_depend_swap 0.82% : 0.000004s : 26: predicate.environ_get_eliminate 0.53% : 0.000002s : 18: predicate.environ_get_set_eliminate 0.79% : 0.000003s : 23: predicate.exchange_switch_depend_value 1.31% : 0.000006s : 23: predicate.float_depend_g_call 0.22% : 0.000001s : 8: predicate.float_environ_get_switch 0.44% : 0.000002s : 12: predicate.float_tuple_getitem_switch 0.09% : 0.000000s : 4: predicate.fold_const_symbol 0.35% : 0.000002s : 8: predicate.get_grad_eliminate 0.11% : 0.000000s : 4: predicate.graph_param_transform 0.26% : 0.000001s : 8: predicate.incorporate_call 0.21% : 0.000001s : 8: predicate.incorporate_call_switch 3.45% : 0.000015s : 61: predicate.inline 0.41% : 0.000002s : 8: predicate.inline_without_move 0.22% : 0.000001s : 8: predicate.j_node_and_user_rematch 0.45% : 0.000002s : 8: predicate.less_batch_normalization 0.91% : 0.000004s : 26: predicate.list_to_tuple_eliminator_ 1.29% : 0.000006s : 40: predicate.load_eliminater 0.89% : 0.000004s : 4: predicate.loop_unroll_after_grad 1.40% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.07% : 0.000005s : 22: predicate.make_slice_get_slice_eliminator 0.30% : 0.000001s : 8: predicate.merge_addn 0.26% : 0.000001s : 8: predicate.micro_step_allgather_replace 0.26% : 0.000001s : 8: predicate.mini_step_allgather_replace 0.40% : 0.000002s : 14: predicate.minmaximum_grad 1.05% : 0.000005s : 4: predicate.mutable_eliminate 0.23% : 0.000001s : 4: predicate.opt_reshape 0.19% : 0.000001s : 4: predicate.parallel_virtual_node 1.35% : 0.000006s : 23: predicate.partial_defer_inline 0.93% : 0.000004s : 22: predicate.partial_eliminate 0.57% : 0.000002s : 14: predicate.print_const_string_wrapper 0.28% : 0.000001s : 8: predicate.reduce_all_const_elim 0.79% : 0.000003s : 14: predicate.reduce_eliminate 1.42% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.35% : 0.000002s : 8: predicate.remove_not_recompute_node 0.77% : 0.000003s : 26: predicate.replace_applicator 0.43% : 0.000002s : 8: predicate.replace_old_param 0.17% : 0.000001s : 4: predicate.reset_defer_inline 0.73% : 0.000003s : 14: predicate.reshape_eliminate 0.29% : 0.000001s : 8: predicate.row_tensor_add_zeros_like 0.19% : 0.000001s : 4: predicate.row_tensor_eliminate 0.43% : 0.000002s : 8: predicate.same_eliminate 0.45% : 0.000002s : 8: predicate.set_cell_output_no_recompute 0.53% : 0.000002s : 8: predicate.shard_identity_eliminate 0.38% : 0.000002s : 8: predicate.special_op_eliminate 0.30% : 0.000001s : 8: predicate.specialize_transform 0.57% : 0.000002s : 8: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000002s : 8: predicate.stack_unstack_eliminate 0.18% : 0.000001s : 4: predicate.switch_call_monad_eliminater 0.77% : 0.000003s : 23: predicate.switch_defer_inline 1.07% : 0.000005s : 31: predicate.switch_layer_defer_inline 2.82% : 0.000012s : 74: predicate.switch_simplify 0.43% : 0.000002s : 14: predicate.tile_eliminate 0.63% : 0.000003s : 14: predicate.transpose_eliminate 0.98% : 0.000004s : 22: predicate.tuple_list_convert_item_index_to_positive 0.72% : 0.000003s : 22: predicate.tuple_list_get_item_const_eliminator 0.72% : 0.000003s : 22: predicate.tuple_list_get_item_depend_reorder 2.37% : 0.000010s : 34: predicate.tuple_list_get_item_eliminator 0.73% : 0.000003s : 22: predicate.tuple_list_get_set_item_eliminator 1.09% : 0.000005s : 30: predicate.tuple_list_set_item_eliminator 0.86% : 0.000004s : 26: predicate.tuple_to_list_eliminator_ 44.54% : 0.000192s : 40: predicate.updatestate_pure_node_eliminater 1.70% : 0.000007s : 48: predicate.updatestate_useless_node_eliminater 0.22% : 0.000001s : 4: predicate.value_based_eliminate 0.29% : 0.000001s : 8: predicate.virtual_dataset_eliminate 0.32% : 0.000001s : 8: predicate.virtual_output_eliminate 0.15% : 0.000001s : 4: predicate.virtual_view_grad_eliminate 0.21% : 0.000001s : 4: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000745 12 50.04% : 0.000373s : 5: func_graph_cloner_run.FuncGraphClonerGraph 49.96% : 0.000372s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.136729 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.42% : 0.004669s : 1: add_attr 3.40% : 0.004651s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.05% : 0.000070s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.06% : 0.000083s : 1: auto_monad 0.02% : 0.000026s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.01% : 0.000007s : 1: bias_add_comm_swap 0.44% : 0.000602s : 1: bootstrap 0.04% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000020s : 1: control_data_broadcast_order 0.01% : 0.000013s : 1: convert_after_rewriter 0.02% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.01% : 0.000007s : 1: detach_backward 0.01% : 0.000010s : 1: environ_conv 0.02% : 0.000031s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.01% : 0.000007s : 1: inline 0.01% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.01% : 0.000011s : 1: label_micro_interleaved_index 0.58% : 0.000796s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.71% : 0.000972s : 1: mutable_eliminate 0.01% : 0.000008s : 1: offloading_packed_experts 0.02% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000029s : 1: opt.transform.mutable_eliminate 1.23% : 0.001681s : 78: opt.transform.opt_a 0.02% : 0.000032s : 1: opt.transform.opt_after_cconv 0.03% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000120s : 28: opt.transform.opt_b 0.07% : 0.000092s : 2: opt.transform.opt_trans_graph 0.04% : 0.000052s : 4: opt.transform.symbol_engine_opt 2.87% : 0.003928s : 1: opt_a 0.11% : 0.000146s : 1: opt_after_cconv 0.63% : 0.000862s : 1: opt_after_jit_grad 0.20% : 0.000270s : 1: opt_b 5.32% : 0.007278s : 1: optimize 0.05% : 0.000062s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.02% : 0.000028s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.04% : 0.000056s : 1: pre_auto_parallel 0.03% : 0.000044s : 1: py_interpret_to_execute 0.02% : 0.000024s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000021s : 1: remove_dup_value 0.47% : 0.000646s : 1: renormalize.infer 0.34% : 0.000460s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000055s : 1: rewriter_after_opt_a 0.10% : 0.000143s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.15% : 0.000210s : 1: symbol_engine_optimizer 0.10% : 0.000131s : 1: tuple_transform 78.98% : 0.107991s : 1: type_inference *****************Start Generalize test GRAPH_MODE_O0 GradByRequirement case***************** [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, GradByRequirement case is skipped. *****************End Generalize test GRAPH_MODE_O0 GradByRequirement case***************** *****************Start Generalize test GRAPH_MODE_O0 Deterministic case***************** [INFO]: TEST_OP_GENERALIZE test deterministic case loop 0 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 1 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 2 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 3 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. [INFO]: TEST_OP_GENERALIZE test deterministic case loop 4 [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic first time. [INFO]: TEST_OP_GENERALIZE Start to test func forward with deterministic second time. [INFO]: TEST_OP_GENERALIZE Start to compare forward second time out with first time out Compare ['Success'] for 0'th output. [WARNING]: TEST_OP_GENERALIZE case_config['disable_grad'] is True, Deterministic case with backward is skipped. *****************End Generalize test GRAPH_MODE_O0 Deterministic case***************** [WARNING]: TEST_OP_GENERALIZE GRAPH_MODE_GE is skipped. ************************************************************************************************** **************************************TEST_OP_GENERALIZE End************************************** ************************************************************************************************** ************************************************************************************************* **************************************TEST_OP_DYNAMIC Start************************************** ************************************************************************************************* [WARNING]: TEST_DYNAMIC GRAPH_MODE_GE is skipped, Ge backend don't support dynamic situations any longer. *********************Begin DynamicTest for with PYNATIVE_MODE ********************* Start DynamicTest running on PYNATIVE_MODE with static shape with first inputs... [WARNING]: TEST_DYNAMIC DynamicTest Grad Test is skipped. End Start DynamicTest running on PYNATIVE_MODE with static shape with second inputs... End Start DynamicTest testing with [PYNATIVE_MODE] [Resize]... Compare ['Success'] for 0'th output of Resize. End Start DynamicTest testing with [PYNATIVE_MODE] [DYNAMIC_SHAPE] [None]... Compare ['Success'] for 0'th output of Forward. End Start DynamicTest testing with [PYNATIVE_MODE] [DYNAMIC_RANK] [None]... Compare ['Success'] for 0'th output of Forward. End *********************End DynamicTest for with PYNATIVE_MODE ********************* *********************Begin DynamicTest for with GRAPH_MODE_O0 ********************* Start DynamicTest running on GRAPH_MODE_O0 with static shape with first inputs... [WARNING]: TEST_DYNAMIC DynamicTest Grad Test is skipped. End Start DynamicTest running on GRAPH_MODE_O0 with static shape with second inputs... End Start DynamicTest testing with [GRAPH_MODE_O0] [Resize]... Compare ['Success'] for 0'th output of Resize. End Start DynamicTest testing with [GRAPH_MODE_O0] [DYNAMIC_SHAPE] [None]... Compare ['Success'] for 0'th output of Forward. End Start DynamicTest testing with [GRAPH_MODE_O0] [DYNAMIC_RANK] [None]... Compare ['Success'] for 0'th output of Forward. End *********************End DynamicTest for with GRAPH_MODE_O0 ********************* ************************************************************************************************* ***************************************TEST_OP_DYNAMIC End*************************************** ************************************************************************************************* . [hook] pytest_runtest_teardown:test_polar_dynamic_shape tests/st/ops/test_mint_polar.py::test_polar_dynamic_shape,max_mem:4.0M =============================== 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 330.00s (0:05:30) ==================