==================================================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/tensor, 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 2 items test_sigmoid_.py [WARNING] ME(171811:281473316736816,MainProcess):2026-01-29-17:40:09.819.257 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 64.5663, [24] [bootstrap]: 0.00066334 [type_inference]: 0.246708 [event_method]: 1.892e-05 [auto_monad]: 0.00022196 [graph_reusing]: 6.52001e-06 [inline]: 2.94999e-06 [add_attr]: 0.00956258, [1] [add_attr_with_inline]: 0.00954493, [1] [Cycle 1]: 9.427e-05, [2] [tag_attr]: 1.78e-05 [meta_addattr_fg_expand]: 3.78999e-06 [parallel-infer-symbol]: 3.68e-06 [pre_auto_parallel]: 4.97e-05 [insert-virtual-dataset]: 2.81e-06 [parallel-infer-symbol-second]: 7.39994e-07 [dataset_repeat_opt]: 2.43e-06 [pipeline_split]: 1.79998e-06 [optimize]: 0.029639, [53] [py_interpret_to_execute]: 2.299e-05 [rewriter_before_opt_a]: 8.408e-05 [opt_a]: 0.00319807, [2] [Cycle 1]: 0.00228118, [45] [expand_dump_flag]: 2.89999e-06 [switch_simplify]: 2.823e-05 [loop_unroll]: 1.329e-05 [a_1]: 0.00042037 [with_stream_mark]: 2.216e-05 [recompute_prepare]: 1.077e-05 [updatestate_depend_eliminate]: 6.06e-06 [updatestate_assign_eliminate]: 7.25e-06 [updatestate_loads_eliminate]: 5.37001e-06 [parameter_eliminate]: 1.91998e-06 [a_2]: 0.00012772 [accelerated_algorithm]: 9.49999e-06 [shard]: 3.13998e-06 [meta_shard_fg_expand]: 2.36e-06 [shard_inline]: 8.58001e-06 [merge_send_recv]: 2.189e-05 [auto_parallel]: 9.40001e-06 [parallel]: 4.188e-05 [flash_sp]: 2.042e-05 [merge_comm]: 5.72001e-06 [allreduce_fusion]: 4.94e-06 [matmul_add_comm_reduction]: 1.3e-05 [allreduce_slice_to_reducescatter]: 8.29983e-07 [virtual_shard_identity]: 1.125e-05 [virtual_dataset]: 9.21998e-06 [get_grad_eliminate_]: 8.57e-06 [virtual_output]: 8.60999e-06 [merge_forward]: 5.91e-06 [cell_reuse_recompute_pass]: 1.84e-06 [offload_activation]: 1.351e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.101e-05 [merge_recompute_call_nodes]: 1.76003e-06 [before_grad]: 1.543e-05 [set_forward_comm_id_for_comm_node_pass]: 5.34998e-06 [meta_fg_expand]: 4.37e-06 [flash_sp_send_recv_attached]: 2.54001e-06 [receive_attached]: 1.258e-05 [after_resolve]: 1.399e-05 [a_after_grad]: 1.316e-05 [renormalize]: 0.00090497 [add_forward_monad_depend]: 1.002e-05 [auto_monad_grad]: 2.42001e-06 [auto_monad_eliminator]: 2.481e-05 [cse]: 5.762e-05 [a_3]: 6.799e-05 [Cycle 2]: 0.00090392, [45] [expand_dump_flag]: 1.18001e-06 [switch_simplify]: 9.95002e-06 [loop_unroll]: 8.45999e-06 [a_1]: 0.00022853 [with_stream_mark]: 1.707e-05 [recompute_prepare]: 9.94999e-06 [updatestate_depend_eliminate]: 5.71998e-06 [updatestate_assign_eliminate]: 4.70001e-06 [updatestate_loads_eliminate]: 5.23002e-06 [parameter_eliminate]: 1.42e-06 [a_2]: 0.00011128 [accelerated_algorithm]: 8.80999e-06 [shard]: 1.62001e-06 [meta_shard_fg_expand]: 2.24999e-06 [shard_inline]: 8.84e-06 [merge_send_recv]: 8.55999e-06 [auto_parallel]: 8.37e-06 [parallel]: 6.33998e-06 [flash_sp]: 4.02998e-06 [merge_comm]: 4.95001e-06 [allreduce_fusion]: 4.99998e-06 [matmul_add_comm_reduction]: 9.92001e-06 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 1.004e-05 [virtual_dataset]: 8.32998e-06 [get_grad_eliminate_]: 7.63999e-06 [virtual_output]: 7.75e-06 [merge_forward]: 5.27999e-06 [cell_reuse_recompute_pass]: 1.54998e-06 [offload_activation]: 1.133e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.747e-05 [merge_recompute_call_nodes]: 1.40001e-06 [before_grad]: 1.356e-05 [set_forward_comm_id_for_comm_node_pass]: 5.61e-06 [meta_fg_expand]: 3.34001e-06 [flash_sp_send_recv_attached]: 1.15999e-06 [receive_attached]: 1.14e-06 [after_resolve]: 1.12e-05 [a_after_grad]: 1.181e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.64e-06 [auto_monad_grad]: 9.50007e-07 [auto_monad_eliminator]: 1.33e-05 [cse]: 2.314e-05 [a_3]: 5.222e-05 [py_interpret_to_execute_after_opt_a]: 1.482e-05 [slice_cell_reuse_recomputed_activation]: 2.31e-06 [rewriter_after_opt_a]: 0.00016263 [convert_after_rewriter]: 2.562e-05 [order_py_execute_after_rewriter]: 7.78001e-06 [mutable_eliminate]: 0.00088338 [opt_b]: 0.0120299, [1] [Cycle 1]: 0.0120158, [7] [b_1]: 0.00020092 [b_2]: 1.245e-05 [updatestate_depend_eliminate]: 0.0115048 [updatestate_assign_eliminate]: 1.512e-05 [updatestate_loads_eliminate]: 8.32e-06 [renormalize]: 1.00999e-06 [cse]: 6.333e-05 [optimize_parallel_all_gather_comm]: 3.566e-05 [overlap_param_gather]: 1.99e-06 [cconv]: 4.737e-05 [loop_unroll]: 0.0119653 [opt_after_cconv]: 0.00023215, [1] [Cycle 1]: 0.00021799, [7] [c_1]: 8.284e-05 [parameter_eliminate]: 7.90998e-06 [updatestate_depend_eliminate]: 1.906e-05 [updatestate_assign_eliminate]: 6.23998e-06 [updatestate_loads_eliminate]: 5.07e-06 [cse]: 5.473e-05 [renormalize]: 7.09988e-07 [remove_dup_value]: 2.177e-05 [tuple_transform]: 0.00010993, [1] [Cycle 1]: 0.00010354, [4] [d_1]: 6.952e-05 [none_parameter_eliminate]: 1.67999e-06 [renormalize]: 1.39989e-07 [switch_simplify]: 1.092e-05 [partial_unused_args_eliminate]: 2.06e-06 [add_recomputation]: 0.00010298 [cse_after_recomputation]: 3.174e-05, [1] [Cycle 1]: 2.604e-05, [1] [cse]: 1.887e-05 [environ_conv]: 4.812e-05 [swap_dp_allreduce_reducescatter]: 9.96e-06 [bias_add_comm_swap]: 4.60001e-06 [label_micro_interleaved_index]: 8.05e-06 [label_fine_grained_interleaved_index]: 3.28e-06 [merge_cast_opt]: 1.69e-06 [slice_recompute_activation]: 2.43e-06 [micro_interleaved_order_control]: 2.51e-06 [assign_add_opt]: 1.87001e-06 [ForceFp32Comm]: 9.00007e-07 [remove_cast_before_assign_add]: 1.20999e-06 [full_micro_interleaved_order_control]: 2.29999e-06 [reorder_send_recv_between_fp_bp]: 2.88e-06 [comm_op_add_attrs]: 1.20001e-06 [add_comm_op_reuse_tag]: 1.17e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.17999e-06 [overlap_opt_shard_in_pipeline]: 2.871e-05 [overlap_opt_shard_grad_in_pipeline]: 1.94e-06 [control_data_broadcast_order]: 2.358e-05 [grouped_pairwise_exchange_alltoall]: 1.94e-06 [offloading_packed_experts]: 7.16999e-06 [overlap_recompute_and_grad_model_parallel]: 7.24001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.71002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.59e-06 [overlap_recompute_comm]: 2.35002e-06 [overlap_grad_ring_attention]: 7.83999e-06 [overlap_grad_flash_sp]: 3.424e-05 [begin_end_overlap_inline]: 6.09987e-07 [split_matmul_comm_elemetwise]: 2.63003e-06 [split_layernorm_comm]: 2.50002e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00012003, [1] [Cycle 1]: 0.0001124, [6] [build]: 6.78e-06 [elim_shapecalc]: 2.015e-05 [elim_not_effective]: 2.129e-05 [opt_reshape]: 1.111e-05 [fold_const_symbol]: 1.583e-05 [renormalize]: 4.80009e-07 [detach_backward]: 2.74001e-06 [pipeline_parallel_scheduler]: 2.07999e-06 [auto_monad_reorder]: 3.994e-05 [get_jit_bprop_graph]: 1.67001e-06 [rewriter_after_jit_bprop_graph]: 7.36999e-06 [opt_after_jit_grad]: 0.00082494 [validate]: 8.618e-05 [backend_pass]: 9.89996e-07 [task_emit]: 64.278 [execute]: 1.523e-05 Sums bootstrap : 0.000663s : 0.00% type_inference : 0.246708s : 0.38% event_method : 0.000019s : 0.00% auto_monad : 0.000222s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000023s : 0.00% optimize.rewriter_before_opt_a : 0.000084s : 0.00% optimize.opt_a.expand_dump_flag : 0.000004s : 0.00% optimize.opt_a.switch_simplify : 0.000038s : 0.00% optimize.opt_a.loop_unroll : 0.000022s : 0.00% optimize.opt_a.a_1 : 0.000649s : 0.00% optimize.opt_a.with_stream_mark : 0.000039s : 0.00% optimize.opt_a.recompute_prepare : 0.000021s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000239s : 0.00% optimize.opt_a.accelerated_algorithm : 0.000018s : 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 : 0.000017s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000018s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000011s : 0.00% optimize.opt_a.allreduce_fusion : 0.000010s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000021s : 0.00% optimize.opt_a.virtual_dataset : 0.000018s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000016s : 0.00% optimize.opt_a.virtual_output : 0.000016s : 0.00% optimize.opt_a.merge_forward : 0.000011s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000029s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.00% optimize.opt_a.meta_fg_expand : 0.000008s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000014s : 0.00% optimize.opt_a.after_resolve : 0.000025s : 0.00% optimize.opt_a.a_after_grad : 0.000025s : 0.00% optimize.opt_a.renormalize : 0.000905s : 0.00% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.00% optimize.opt_a.auto_monad_grad : 0.000003s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000038s : 0.00% optimize.opt_a.cse : 0.000081s : 0.00% optimize.opt_a.a_3 : 0.000120s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000015s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000163s : 0.00% optimize.convert_after_rewriter : 0.000026s : 0.00% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000883s : 0.00% optimize.opt_b.b_1 : 0.000201s : 0.00% optimize.opt_b.b_2 : 0.000012s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.011505s : 0.02% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000063s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000047s : 0.00% optimize.loop_unroll : 0.011965s : 0.02% optimize.opt_after_cconv.c_1 : 0.000083s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000055s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.00% optimize.tuple_transform.d_1 : 0.000070s : 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 : 0.000011s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000103s : 0.00% optimize.cse_after_recomputation.cse : 0.000019s : 0.00% optimize.environ_conv : 0.000048s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000005s : 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 : 0.000002s : 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 : 0.000029s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000034s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000003s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000021s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000016s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000040s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000825s : 0.00% validate : 0.000086s : 0.00% backend_pass : 0.000001s : 0.00% task_emit : 64.278046s : 99.57% execute : 0.000015s : 0.00% Time group info: ------[substitution.] 0.000203 55 3.86% : 0.000008s : 2: substitution.depend_value_elim 2.00% : 0.000004s : 5: substitution.elim_not_effective 1.09% : 0.000002s : 5: substitution.fold_const_symbol 4.82% : 0.000010s : 6: substitution.graph_param_transform 55.96% : 0.000113s : 1: substitution.inline 2.79% : 0.000006s : 10: substitution.j_node_and_user_rematch 8.46% : 0.000017s : 10: substitution.remove_not_recompute_node 2.38% : 0.000005s : 2: substitution.replace_old_param 11.16% : 0.000023s : 6: substitution.updatestate_pure_node_eliminater 7.48% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.246639 2 99.74% : 0.245998s : 1: type_inference.infer 0.26% : 0.000641s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000113 1 100.00% : 0.000113s : 1: match.inline ------[predicate.] 0.000258 1419 0.81% : 0.000002s : 13: predicate.accumulaten_eliminater 1.81% : 0.000005s : 6: predicate.ad_related_special_op_eliminate 0.62% : 0.000002s : 12: predicate.addn_check_dump 0.77% : 0.000002s : 13: predicate.addn_zero_filter 0.74% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.85% : 0.000005s : 25: predicate.arithmetic_simplify 0.98% : 0.000003s : 13: predicate.cast_eliminate 0.78% : 0.000002s : 12: predicate.check_bprop_eliminate 0.62% : 0.000002s : 12: predicate.compare_switch_simplify 0.19% : 0.000001s : 6: predicate.const_output_eliminate 0.74% : 0.000002s : 12: predicate.depend_value_elim 0.76% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.81% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.82% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.19% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 6: predicate.elim_not_effective 0.78% : 0.000002s : 6: predicate.elim_shapecalc_of_broadcastargs 1.05% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.27% : 0.000003s : 19: predicate.environ_get_add_eliminate 0.99% : 0.000003s : 19: predicate.environ_get_depend_swap 1.90% : 0.000005s : 31: predicate.environ_get_eliminate 1.13% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.84% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.28% : 0.000003s : 14: predicate.float_depend_g_call 0.62% : 0.000002s : 12: predicate.float_environ_get_switch 0.97% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 6: predicate.fold_const_symbol 0.76% : 0.000002s : 12: predicate.get_grad_eliminate 0.30% : 0.000001s : 6: predicate.graph_param_transform 0.65% : 0.000002s : 12: predicate.incorporate_call 0.60% : 0.000002s : 12: predicate.incorporate_call_switch 5.97% : 0.000015s : 63: predicate.inline 0.79% : 0.000002s : 12: predicate.inline_without_move 0.33% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.84% : 0.000002s : 12: predicate.less_batch_normalization 1.88% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.34% : 0.000006s : 38: predicate.load_eliminater 4.04% : 0.000010s : 6: predicate.loop_unroll_after_grad 1.05% : 0.000003s : 17: predicate.loop_unroll_before_grad 2.17% : 0.000006s : 25: predicate.make_slice_get_slice_eliminator 0.69% : 0.000002s : 12: predicate.merge_addn 0.71% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.79% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.65% : 0.000002s : 13: predicate.minmaximum_grad 1.56% : 0.000004s : 6: predicate.mutable_eliminate 0.48% : 0.000001s : 6: predicate.opt_reshape 0.64% : 0.000002s : 6: predicate.parallel_virtual_node 1.03% : 0.000003s : 14: predicate.partial_defer_inline 1.17% : 0.000003s : 19: predicate.partial_eliminate 0.72% : 0.000002s : 13: predicate.print_const_string_wrapper 0.83% : 0.000002s : 12: predicate.reduce_all_const_elim 1.15% : 0.000003s : 13: predicate.reduce_eliminate 2.17% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.57% : 0.000001s : 12: predicate.remove_not_recompute_node 1.06% : 0.000003s : 25: predicate.replace_applicator 0.52% : 0.000001s : 12: predicate.replace_old_param 0.34% : 0.000001s : 6: predicate.reset_defer_inline 0.70% : 0.000002s : 13: predicate.reshape_eliminate 0.71% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.53% : 0.000001s : 6: predicate.row_tensor_eliminate 1.03% : 0.000003s : 12: predicate.same_eliminate 0.44% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.94% : 0.000002s : 12: predicate.shard_identity_eliminate 0.91% : 0.000002s : 12: predicate.special_op_eliminate 0.81% : 0.000002s : 12: predicate.specialize_transform 0.92% : 0.000002s : 12: predicate.split_environ_get_set_with_tuple_value 0.92% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.51% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.83% : 0.000002s : 14: predicate.switch_defer_inline 1.41% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.23% : 0.000008s : 49: predicate.switch_simplify 0.76% : 0.000002s : 13: predicate.tile_eliminate 0.75% : 0.000002s : 13: predicate.transpose_eliminate 1.90% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.49% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 2.20% : 0.000006s : 25: predicate.tuple_list_get_item_depend_reorder 2.89% : 0.000007s : 37: predicate.tuple_list_get_item_eliminator 1.59% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.82% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.62% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.16% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.49% : 0.000009s : 50: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 6: predicate.value_based_eliminate 0.83% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.71% : 0.000002s : 12: predicate.virtual_output_eliminate 0.39% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.50% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000342 4 8.82% : 0.000030s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.18% : 0.000311s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 64.607981 196 0.00% : 0.000004s : 1: ForceFp32Comm 0.01% : 0.009571s : 1: add_attr 0.01% : 0.009550s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000109s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.00% : 0.000230s : 1: auto_monad 0.00% : 0.000045s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: backend_pass 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.00% : 0.000720s : 1: bootstrap 0.00% : 0.000051s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000030s : 1: convert_after_rewriter 0.00% : 0.000035s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000058s : 1: environ_conv 0.00% : 0.000027s : 1: event_method 0.00% : 0.000030s : 1: execute 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% : 0.000006s : 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% : 0.000005s : 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% : 0.000011s : 1: label_micro_interleaved_index 0.02% : 0.012002s : 1: loop_unroll 0.00% : 0.000007s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.00% : 0.000898s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000053s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000029s : 1: opt.transform.mutable_eliminate 0.00% : 0.001229s : 78: opt.transform.opt_a 0.00% : 0.000080s : 1: opt.transform.opt_after_cconv 0.00% : 0.000043s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000181s : 28: opt.transform.opt_b 0.00% : 0.000078s : 2: opt.transform.opt_trans_graph 0.00% : 0.000063s : 4: opt.transform.symbol_engine_opt 0.00% : 0.003201s : 1: opt_a 0.00% : 0.000237s : 1: opt_after_cconv 0.00% : 0.000843s : 1: opt_after_jit_grad 0.02% : 0.012037s : 1: opt_b 0.05% : 0.029646s : 1: optimize 0.00% : 0.000040s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.00% : 0.000038s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000033s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 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% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000055s : 1: pre_auto_parallel 0.00% : 0.000027s : 1: py_interpret_to_execute 0.00% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000027s : 1: remove_dup_value 0.00% : 0.000558s : 1: renormalize.infer 0.00% : 0.000336s : 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% : 0.000170s : 1: rewriter_after_opt_a 0.00% : 0.000089s : 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% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000123s : 1: symbol_engine_optimizer 99.49% : 64.278089s : 1: task_emit 0.00% : 0.000113s : 1: tuple_transform 0.38% : 0.246738s : 1: type_inference 0.00% : 0.000135s : 1: validate TotalTime = 0.397, [24] [bootstrap]: 0.00058929 [type_inference]: 0.11167 [event_method]: 1.348e-05 [auto_monad]: 0.00016159 [graph_reusing]: 5.61003e-06 [inline]: 3.01001e-06 [add_attr]: 0.06121, [1] [add_attr_with_inline]: 0.0611939, [1] [Cycle 1]: 0.00011235, [2] [tag_attr]: 1.819e-05 [meta_addattr_fg_expand]: 3.91999e-06 [parallel-infer-symbol]: 3.94002e-06 [pre_auto_parallel]: 4.19e-05 [insert-virtual-dataset]: 3.5e-06 [parallel-infer-symbol-second]: 8.70001e-07 [dataset_repeat_opt]: 2.67001e-06 [pipeline_split]: 1.60999e-06 [optimize]: 0.174611, [53] [py_interpret_to_execute]: 2.707e-05 [rewriter_before_opt_a]: 0.0520514 [opt_a]: 0.00418665, [2] [Cycle 1]: 0.00293889, [45] [expand_dump_flag]: 6.41e-06 [switch_simplify]: 4.45e-05 [loop_unroll]: 1.603e-05 [a_1]: 0.00055271 [with_stream_mark]: 3.35e-05 [recompute_prepare]: 1.423e-05 [updatestate_depend_eliminate]: 7.92e-06 [updatestate_assign_eliminate]: 6.28e-06 [updatestate_loads_eliminate]: 6.17999e-06 [parameter_eliminate]: 2.58998e-06 [a_2]: 0.00014285 [accelerated_algorithm]: 1.306e-05 [shard]: 3.86001e-06 [meta_shard_fg_expand]: 5.57999e-06 [shard_inline]: 1.045e-05 [merge_send_recv]: 1.512e-05 [auto_parallel]: 1.433e-05 [parallel]: 3.774e-05 [flash_sp]: 1.383e-05 [merge_comm]: 6.79999e-06 [allreduce_fusion]: 5.82999e-06 [matmul_add_comm_reduction]: 1.559e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.417e-05 [virtual_dataset]: 1.118e-05 [get_grad_eliminate_]: 1.137e-05 [virtual_output]: 1.161e-05 [merge_forward]: 7.03e-06 [cell_reuse_recompute_pass]: 2.41e-06 [offload_activation]: 2.076e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.694e-05 [merge_recompute_call_nodes]: 1.72999e-06 [before_grad]: 2.016e-05 [set_forward_comm_id_for_comm_node_pass]: 7.48999e-06 [meta_fg_expand]: 4.75001e-06 [flash_sp_send_recv_attached]: 3.36999e-06 [receive_attached]: 2.84001e-06 [after_resolve]: 1.677e-05 [a_after_grad]: 1.809e-05 [renormalize]: 0.00118646 [add_forward_monad_depend]: 1.951e-05 [auto_monad_grad]: 3.01999e-06 [auto_monad_eliminator]: 2.913e-05 [cse]: 4.675e-05 [a_3]: 8.017e-05 [Cycle 2]: 0.00122203, [45] [expand_dump_flag]: 2.73e-06 [switch_simplify]: 1.359e-05 [loop_unroll]: 1.026e-05 [a_1]: 0.00024554 [with_stream_mark]: 2.352e-05 [recompute_prepare]: 1.108e-05 [updatestate_depend_eliminate]: 8.26002e-06 [updatestate_assign_eliminate]: 5.99e-06 [updatestate_loads_eliminate]: 4.85001e-06 [parameter_eliminate]: 1.72999e-06 [a_2]: 0.00012701 [accelerated_algorithm]: 1.148e-05 [shard]: 3.2e-06 [meta_shard_fg_expand]: 3.18998e-06 [shard_inline]: 8.66002e-06 [merge_send_recv]: 9.64e-06 [auto_parallel]: 1.195e-05 [parallel]: 8.38999e-06 [flash_sp]: 3.86999e-06 [merge_comm]: 6.43e-06 [allreduce_fusion]: 6.29999e-06 [matmul_add_comm_reduction]: 1.23e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 1.132e-05 [virtual_dataset]: 7.958e-05 [get_grad_eliminate_]: 1.116e-05 [virtual_output]: 1.087e-05 [merge_forward]: 6.98e-06 [cell_reuse_recompute_pass]: 2.77002e-06 [offload_activation]: 1.62e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.58e-05 [merge_recompute_call_nodes]: 1.77001e-06 [before_grad]: 1.989e-05 [set_forward_comm_id_for_comm_node_pass]: 7.01001e-06 [meta_fg_expand]: 4.06001e-06 [flash_sp_send_recv_attached]: 1.59e-06 [receive_attached]: 2.76999e-06 [after_resolve]: 1.637e-05 [a_after_grad]: 1.671e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.97002e-06 [auto_monad_grad]: 1.84998e-06 [auto_monad_eliminator]: 2.002e-05 [cse]: 2.787e-05 [a_3]: 6.198e-05 [py_interpret_to_execute_after_opt_a]: 2.494e-05 [slice_cell_reuse_recomputed_activation]: 2.13998e-06 [rewriter_after_opt_a]: 0.00027239 [convert_after_rewriter]: 1.641e-05 [order_py_execute_after_rewriter]: 8.09002e-06 [mutable_eliminate]: 0.00095388 [opt_b]: 0.00040498, [1] [Cycle 1]: 0.00039133, [7] [b_1]: 0.00024918 [b_2]: 1.54e-05 [updatestate_depend_eliminate]: 1.363e-05 [updatestate_assign_eliminate]: 6.46999e-06 [updatestate_loads_eliminate]: 6.01e-06 [renormalize]: 5.20027e-07 [cse]: 3.786e-05 [optimize_parallel_all_gather_comm]: 3.128e-05 [overlap_param_gather]: 2.68e-06 [cconv]: 4.421e-05 [loop_unroll]: 0.00065209 [opt_after_cconv]: 0.00019914, [1] [Cycle 1]: 0.00018793, [7] [c_1]: 7.384e-05 [parameter_eliminate]: 6.11e-06 [updatestate_depend_eliminate]: 1.169e-05 [updatestate_assign_eliminate]: 5.19e-06 [updatestate_loads_eliminate]: 5.91003e-06 [cse]: 3.033e-05 [renormalize]: 9.10019e-07 [remove_dup_value]: 2.105e-05 [tuple_transform]: 0.00012959, [1] [Cycle 1]: 0.00012184, [4] [d_1]: 7.556e-05 [none_parameter_eliminate]: 1.92999e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 1.372e-05 [partial_unused_args_eliminate]: 2.17999e-06 [add_recomputation]: 9.923e-05 [cse_after_recomputation]: 3.697e-05, [1] [Cycle 1]: 2.935e-05, [1] [cse]: 1.96e-05 [environ_conv]: 1.066e-05 [swap_dp_allreduce_reducescatter]: 1.032e-05 [bias_add_comm_swap]: 4.18999e-06 [label_micro_interleaved_index]: 6.73998e-06 [label_fine_grained_interleaved_index]: 2.98e-06 [merge_cast_opt]: 1.42999e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 3.27002e-06 [assign_add_opt]: 1.66998e-06 [ForceFp32Comm]: 8.80013e-07 [remove_cast_before_assign_add]: 1.12e-06 [full_micro_interleaved_order_control]: 3.41001e-06 [reorder_send_recv_between_fp_bp]: 3.32002e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.90001e-06 [interleave_parallel_branches]: 1.70001e-06 [overlap_opt_shard_in_pipeline]: 1.45999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.80001e-06 [control_data_broadcast_order]: 2.266e-05 [grouped_pairwise_exchange_alltoall]: 1.89999e-06 [offloading_packed_experts]: 6.19999e-06 [overlap_recompute_and_grad_model_parallel]: 8.2e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.57999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.96e-06 [overlap_recompute_comm]: 3.31001e-06 [overlap_grad_ring_attention]: 7.50998e-06 [overlap_grad_flash_sp]: 3.319e-05 [begin_end_overlap_inline]: 6.09987e-07 [split_matmul_comm_elemetwise]: 2.52001e-06 [split_layernorm_comm]: 2.40002e-06 [handle_group_info]: 1.25001e-06 [symbol_engine_optimizer]: 0.114906, [1] [Cycle 1]: 0.114882, [6] [build]: 7.43e-06 [elim_shapecalc]: 2.501e-05 [elim_not_effective]: 2.489e-05 [opt_reshape]: 1.462e-05 [fold_const_symbol]: 1.778e-05 [renormalize]: 2.09984e-07 [detach_backward]: 6.07999e-06 [pipeline_parallel_scheduler]: 2.38002e-06 [auto_monad_reorder]: 6.466e-05 [get_jit_bprop_graph]: 3.33e-06 [rewriter_after_jit_bprop_graph]: 1.483e-05 [opt_after_jit_grad]: 0.0010203 [validate]: 0.0165289 [backend_pass]: 1.92999e-06 [task_emit]: 0.0306303 [execute]: 1.295e-05 Sums bootstrap : 0.000589s : 0.27% type_inference : 0.111670s : 50.93% event_method : 0.000013s : 0.01% auto_monad : 0.000162s : 0.07% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000042s : 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 : 0.000027s : 0.01% optimize.rewriter_before_opt_a : 0.052051s : 23.74% optimize.opt_a.expand_dump_flag : 0.000009s : 0.00% optimize.opt_a.switch_simplify : 0.000058s : 0.03% optimize.opt_a.loop_unroll : 0.000026s : 0.01% optimize.opt_a.a_1 : 0.000798s : 0.36% optimize.opt_a.with_stream_mark : 0.000057s : 0.03% optimize.opt_a.recompute_prepare : 0.000025s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000270s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000025s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000019s : 0.01% optimize.opt_a.merge_send_recv : 0.000025s : 0.01% optimize.opt_a.auto_parallel : 0.000026s : 0.01% optimize.opt_a.parallel : 0.000046s : 0.02% optimize.opt_a.flash_sp : 0.000018s : 0.01% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000012s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000025s : 0.01% optimize.opt_a.virtual_dataset : 0.000091s : 0.04% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.01% optimize.opt_a.virtual_output : 0.000022s : 0.01% optimize.opt_a.merge_forward : 0.000014s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000053s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000040s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.01% 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 : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000033s : 0.02% optimize.opt_a.a_after_grad : 0.000035s : 0.02% optimize.opt_a.renormalize : 0.001187s : 0.54% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000049s : 0.02% optimize.opt_a.cse : 0.000075s : 0.03% optimize.opt_a.a_3 : 0.000142s : 0.06% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000272s : 0.12% optimize.convert_after_rewriter : 0.000016s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000954s : 0.44% optimize.opt_b.b_1 : 0.000249s : 0.11% optimize.opt_b.b_2 : 0.000015s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000038s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000044s : 0.02% optimize.loop_unroll : 0.000652s : 0.30% optimize.opt_after_cconv.c_1 : 0.000074s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000030s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000021s : 0.01% optimize.tuple_transform.d_1 : 0.000076s : 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 : 0.000014s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000099s : 0.05% optimize.cse_after_recomputation.cse : 0.000020s : 0.01% optimize.environ_conv : 0.000011s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 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 : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000033s : 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 : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000018s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000006s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000065s : 0.03% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000015s : 0.01% opt_after_jit_grad : 0.001020s : 0.47% validate : 0.016529s : 7.54% backend_pass : 0.000002s : 0.00% task_emit : 0.030630s : 13.97% execute : 0.000013s : 0.01% Time group info: ------[substitution.] 0.000241 55 4.04% : 0.000010s : 2: substitution.depend_value_elim 1.45% : 0.000003s : 5: substitution.elim_not_effective 1.01% : 0.000002s : 5: substitution.fold_const_symbol 3.53% : 0.000009s : 6: substitution.graph_param_transform 64.30% : 0.000155s : 1: substitution.inline 2.77% : 0.000007s : 10: substitution.j_node_and_user_rematch 3.64% : 0.000009s : 10: substitution.remove_not_recompute_node 2.67% : 0.000006s : 2: substitution.replace_old_param 8.75% : 0.000021s : 6: substitution.updatestate_pure_node_eliminater 7.84% : 0.000019s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.111614 2 99.54% : 0.111104s : 1: type_inference.infer 0.46% : 0.000510s : 1: type_inference.specialize ------[replace.] 0.000022 1 100.00% : 0.000022s : 1: replace.inline ------[match.] 0.000152 1 100.00% : 0.000152s : 1: match.inline ------[predicate.] 0.000343 1419 0.93% : 0.000003s : 13: predicate.accumulaten_eliminater 1.41% : 0.000005s : 6: predicate.ad_related_special_op_eliminate 0.60% : 0.000002s : 12: predicate.addn_check_dump 0.82% : 0.000003s : 13: predicate.addn_zero_filter 0.54% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.62% : 0.000006s : 25: predicate.arithmetic_simplify 0.56% : 0.000002s : 13: predicate.cast_eliminate 0.55% : 0.000002s : 12: predicate.check_bprop_eliminate 0.56% : 0.000002s : 12: predicate.compare_switch_simplify 0.17% : 0.000001s : 6: predicate.const_output_eliminate 0.56% : 0.000002s : 12: predicate.depend_value_elim 0.60% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.73% : 0.000003s : 13: predicate.dict_get_item_eliminator 0.57% : 0.000002s : 13: predicate.dict_set_item_eliminator 0.94% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.23% : 0.000001s : 6: predicate.elim_not_effective 0.69% : 0.000002s : 6: predicate.elim_shapecalc_of_broadcastargs 0.79% : 0.000003s : 19: predicate.environ_add_const_eliminate 0.83% : 0.000003s : 19: predicate.environ_get_add_eliminate 0.86% : 0.000003s : 19: predicate.environ_get_depend_swap 1.47% : 0.000005s : 31: predicate.environ_get_eliminate 0.81% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.64% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.17% : 0.000004s : 14: predicate.float_depend_g_call 0.52% : 0.000002s : 12: predicate.float_environ_get_switch 0.89% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.15% : 0.000001s : 6: predicate.fold_const_symbol 0.73% : 0.000002s : 12: predicate.get_grad_eliminate 0.22% : 0.000001s : 6: predicate.graph_param_transform 0.50% : 0.000002s : 12: predicate.incorporate_call 0.44% : 0.000002s : 12: predicate.incorporate_call_switch 4.18% : 0.000014s : 63: predicate.inline 0.73% : 0.000002s : 12: predicate.inline_without_move 0.26% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.19% : 0.000004s : 12: predicate.less_batch_normalization 1.30% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 1.64% : 0.000006s : 38: predicate.load_eliminater 1.45% : 0.000005s : 6: predicate.loop_unroll_after_grad 0.90% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.43% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.58% : 0.000002s : 12: predicate.merge_addn 0.58% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.53% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.59% : 0.000002s : 13: predicate.minmaximum_grad 1.52% : 0.000005s : 6: predicate.mutable_eliminate 0.29% : 0.000001s : 6: predicate.opt_reshape 0.45% : 0.000002s : 6: predicate.parallel_virtual_node 0.99% : 0.000003s : 14: predicate.partial_defer_inline 0.89% : 0.000003s : 19: predicate.partial_eliminate 0.75% : 0.000003s : 13: predicate.print_const_string_wrapper 0.53% : 0.000002s : 12: predicate.reduce_all_const_elim 0.95% : 0.000003s : 13: predicate.reduce_eliminate 2.04% : 0.000007s : 38: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000002s : 12: predicate.remove_not_recompute_node 0.78% : 0.000003s : 25: predicate.replace_applicator 0.39% : 0.000001s : 12: predicate.replace_old_param 0.34% : 0.000001s : 6: predicate.reset_defer_inline 0.62% : 0.000002s : 13: predicate.reshape_eliminate 0.59% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.46% : 0.000002s : 6: predicate.row_tensor_eliminate 0.83% : 0.000003s : 12: predicate.same_eliminate 0.32% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.75% : 0.000003s : 12: predicate.shard_identity_eliminate 0.75% : 0.000003s : 12: predicate.special_op_eliminate 0.59% : 0.000002s : 12: predicate.specialize_transform 0.93% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 0.80% : 0.000003s : 12: predicate.stack_unstack_eliminate 0.30% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.82% : 0.000003s : 14: predicate.switch_defer_inline 1.52% : 0.000005s : 26: predicate.switch_layer_defer_inline 2.90% : 0.000010s : 49: predicate.switch_simplify 0.58% : 0.000002s : 13: predicate.tile_eliminate 0.63% : 0.000002s : 13: predicate.transpose_eliminate 1.67% : 0.000006s : 25: predicate.tuple_list_convert_item_index_to_positive 1.34% : 0.000005s : 25: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000005s : 25: predicate.tuple_list_get_item_depend_reorder 2.63% : 0.000009s : 37: predicate.tuple_list_get_item_eliminator 1.43% : 0.000005s : 25: predicate.tuple_list_get_set_item_eliminator 2.07% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.18% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 1.98% : 0.000007s : 38: predicate.updatestate_pure_node_eliminater 2.35% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 6: predicate.value_based_eliminate 20.56% : 0.000071s : 12: predicate.virtual_dataset_eliminate 0.69% : 0.000002s : 12: predicate.virtual_output_eliminate 0.27% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.55% : 0.000002s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000414 4 6.90% : 0.000029s : 1: func_graph_cloner_run.FuncGraphClonerGraph 93.10% : 0.000385s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.635965 196 0.00% : 0.000004s : 1: ForceFp32Comm 9.63% : 0.061218s : 1: add_attr 9.62% : 0.061199s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000111s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.03% : 0.000169s : 1: auto_monad 0.01% : 0.000070s : 1: auto_monad_reorder 0.00% : 0.000013s : 1: backend_pass 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.10% : 0.000626s : 1: bootstrap 0.01% : 0.000050s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.01% : 0.000041s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000012s : 1: detach_backward 0.00% : 0.000014s : 1: environ_conv 0.00% : 0.000021s : 1: event_method 0.00% : 0.000022s : 1: execute 0.00% : 0.000008s : 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% : 0.000007s : 1: inline 0.00% : 0.000007s : 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 0.11% : 0.000669s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.15% : 0.000975s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000033s : 1: opt.transform.mutable_eliminate 0.25% : 0.001568s : 78: opt.transform.opt_a 0.01% : 0.000071s : 1: opt.transform.opt_after_cconv 0.01% : 0.000056s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000220s : 28: opt.transform.opt_b 0.01% : 0.000086s : 2: opt.transform.opt_trans_graph 0.01% : 0.000076s : 4: opt.transform.symbol_engine_opt 0.66% : 0.004196s : 1: opt_a 0.03% : 0.000204s : 1: opt_after_cconv 0.16% : 0.001042s : 1: opt_after_jit_grad 0.06% : 0.000411s : 1: opt_b 27.46% : 0.174622s : 1: optimize 0.01% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000047s : 1: pre_auto_parallel 0.00% : 0.000032s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000026s : 1: remove_dup_value 0.10% : 0.000638s : 1: renormalize.infer 0.08% : 0.000535s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000019s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000287s : 1: rewriter_after_opt_a 8.19% : 0.052080s : 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% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 18.07% : 0.114917s : 1: symbol_engine_optimizer 4.82% : 0.030658s : 1: task_emit 0.02% : 0.000133s : 1: tuple_transform 17.56% : 0.111693s : 1: type_inference 2.62% : 0.016632s : 1: validate TotalTime = 1.48642, [24] [bootstrap]: 0.00054372 [type_inference]: 0.356829 [event_method]: 3.951e-05 [auto_monad]: 0.00034298 [graph_reusing]: 1.034e-05 [inline]: 3.18e-06 [add_attr]: 0.0850422, [1] [add_attr_with_inline]: 0.0850275, [1] [Cycle 1]: 0.00012033, [2] [tag_attr]: 5.656e-05 [meta_addattr_fg_expand]: 1.142e-05 [parallel-infer-symbol]: 4.15e-06 [pre_auto_parallel]: 6.96e-05 [insert-virtual-dataset]: 3.14999e-06 [parallel-infer-symbol-second]: 8.30012e-07 [dataset_repeat_opt]: 2.39001e-06 [pipeline_split]: 1.62001e-06 [optimize]: 0.778691, [53] [py_interpret_to_execute]: 5.741e-05 [rewriter_before_opt_a]: 0.00019804 [opt_a]: 0.711686, [3] [Cycle 1]: 0.552245, [45] [expand_dump_flag]: 1.16e-05 [switch_simplify]: 0.00010257 [loop_unroll]: 8.626e-05 [a_1]: 0.00259484 [with_stream_mark]: 5.614e-05 [recompute_prepare]: 5.455e-05 [updatestate_depend_eliminate]: 1.595e-05 [updatestate_assign_eliminate]: 1.24e-05 [updatestate_loads_eliminate]: 1.152e-05 [parameter_eliminate]: 4.60999e-06 [a_2]: 0.00042461 [accelerated_algorithm]: 6.162e-05 [shard]: 2.78003e-06 [meta_shard_fg_expand]: 1.3e-05 [shard_inline]: 2.314e-05 [merge_send_recv]: 2.901e-05 [auto_parallel]: 2.221e-05 [parallel]: 2.591e-05 [flash_sp]: 1.993e-05 [merge_comm]: 1.488e-05 [allreduce_fusion]: 1.406e-05 [matmul_add_comm_reduction]: 5.272e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 3.571e-05 [virtual_dataset]: 2.921e-05 [get_grad_eliminate_]: 2.981e-05 [virtual_output]: 2.942e-05 [merge_forward]: 1.633e-05 [cell_reuse_recompute_pass]: 3.06001e-06 [offload_activation]: 3.233e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.386e-05 [merge_recompute_call_nodes]: 1.74998e-06 [before_grad]: 5.376e-05 [set_forward_comm_id_for_comm_node_pass]: 1.703e-05 [meta_fg_expand]: 0.361376 [flash_sp_send_recv_attached]: 8.27e-06 [receive_attached]: 2.69999e-06 [after_resolve]: 0.00017531 [a_after_grad]: 0.00025155 [renormalize]: 0.183529 [add_forward_monad_depend]: 3.338e-05 [auto_monad_grad]: 2.522e-05 [auto_monad_eliminator]: 0.00018482 [cse]: 0.00041171 [a_3]: 0.00176998 [Cycle 2]: 0.158203, [45] [expand_dump_flag]: 4.36002e-06 [switch_simplify]: 0.00011718 [loop_unroll]: 0.00011463 [a_1]: 0.126041 [with_stream_mark]: 4.011e-05 [recompute_prepare]: 2.362e-05 [updatestate_depend_eliminate]: 4.174e-05 [updatestate_assign_eliminate]: 8.1e-06 [updatestate_loads_eliminate]: 6.01e-06 [parameter_eliminate]: 2.41998e-06 [a_2]: 0.00017022 [accelerated_algorithm]: 1.95e-05 [shard]: 2.92002e-06 [meta_shard_fg_expand]: 7.59002e-06 [shard_inline]: 1.29e-05 [merge_send_recv]: 1.515e-05 [auto_parallel]: 1.462e-05 [parallel]: 1.335e-05 [flash_sp]: 5.86998e-06 [merge_comm]: 6.64999e-06 [allreduce_fusion]: 6.41998e-06 [matmul_add_comm_reduction]: 1.495e-05 [allreduce_slice_to_reducescatter]: 1.11002e-06 [virtual_shard_identity]: 1.5e-05 [virtual_dataset]: 1.253e-05 [get_grad_eliminate_]: 1.126e-05 [virtual_output]: 1.121e-05 [merge_forward]: 6.46999e-06 [cell_reuse_recompute_pass]: 1.68002e-06 [offload_activation]: 1.748e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.436e-05 [merge_recompute_call_nodes]: 1.78002e-06 [before_grad]: 2.188e-05 [set_forward_comm_id_for_comm_node_pass]: 7.41999e-06 [meta_fg_expand]: 0.00014209 [flash_sp_send_recv_attached]: 1.80001e-06 [receive_attached]: 2.97002e-06 [after_resolve]: 2.405e-05 [a_after_grad]: 2.015e-05 [renormalize]: 0.0304532 [add_forward_monad_depend]: 1.147e-05 [auto_monad_grad]: 2.91e-06 [auto_monad_eliminator]: 3.295e-05 [cse]: 0.00023325 [a_3]: 0.00010888 [Cycle 3]: 0.00121707, [45] [expand_dump_flag]: 3.01999e-06 [switch_simplify]: 1.484e-05 [loop_unroll]: 1.226e-05 [a_1]: 0.00032535 [with_stream_mark]: 2.231e-05 [recompute_prepare]: 1.316e-05 [updatestate_depend_eliminate]: 8.67e-06 [updatestate_assign_eliminate]: 6.71999e-06 [updatestate_loads_eliminate]: 6.39001e-06 [parameter_eliminate]: 2.17999e-06 [a_2]: 0.00016171 [accelerated_algorithm]: 1.786e-05 [shard]: 2.34001e-06 [meta_shard_fg_expand]: 3.36999e-06 [shard_inline]: 1.169e-05 [merge_send_recv]: 1.309e-05 [auto_parallel]: 1.357e-05 [parallel]: 1.236e-05 [flash_sp]: 1.72999e-06 [merge_comm]: 7.93001e-06 [allreduce_fusion]: 6.56e-06 [matmul_add_comm_reduction]: 1.416e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 1.415e-05 [virtual_dataset]: 1.336e-05 [get_grad_eliminate_]: 1.162e-05 [virtual_output]: 1.06e-05 [merge_forward]: 6.76999e-06 [cell_reuse_recompute_pass]: 4.74e-06 [offload_activation]: 1.473e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.362e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 2.293e-05 [set_forward_comm_id_for_comm_node_pass]: 8.97e-06 [meta_fg_expand]: 6.20002e-06 [flash_sp_send_recv_attached]: 1.94999e-06 [receive_attached]: 2.91e-06 [after_resolve]: 2.038e-05 [a_after_grad]: 1.916e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.12001e-06 [auto_monad_grad]: 1.81998e-06 [auto_monad_eliminator]: 1.803e-05 [cse]: 3.572e-05 [a_3]: 7.248e-05 [py_interpret_to_execute_after_opt_a]: 2.232e-05 [slice_cell_reuse_recomputed_activation]: 2.06e-06 [rewriter_after_opt_a]: 7.474e-05 [convert_after_rewriter]: 1.096e-05 [order_py_execute_after_rewriter]: 9.20001e-06 [mutable_eliminate]: 0.0637624 [opt_b]: 0.00063811, [1] [Cycle 1]: 0.00062442, [7] [b_1]: 0.00038273 [b_2]: 2e-05 [updatestate_depend_eliminate]: 2.376e-05 [updatestate_assign_eliminate]: 8.90001e-06 [updatestate_loads_eliminate]: 7.78001e-06 [renormalize]: 6.00005e-07 [cse]: 0.0001121 [optimize_parallel_all_gather_comm]: 3.798e-05 [overlap_param_gather]: 2.55002e-06 [cconv]: 4.796e-05 [loop_unroll]: 0.00071782 [opt_after_cconv]: 0.0002674, [1] [Cycle 1]: 0.00025707, [7] [c_1]: 0.00010088 [parameter_eliminate]: 7.25e-06 [updatestate_depend_eliminate]: 1.356e-05 [updatestate_assign_eliminate]: 8.08999e-06 [updatestate_loads_eliminate]: 7.31001e-06 [cse]: 6.098e-05 [renormalize]: 4.59986e-07 [remove_dup_value]: 2.646e-05 [tuple_transform]: 0.00016915, [1] [Cycle 1]: 0.00016157, [4] [d_1]: 0.00011641 [none_parameter_eliminate]: 2.41e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 1.368e-05 [partial_unused_args_eliminate]: 2.16e-06 [add_recomputation]: 0.00013468 [cse_after_recomputation]: 6.322e-05, [1] [Cycle 1]: 5.626e-05, [1] [cse]: 4.618e-05 [environ_conv]: 1.794e-05 [swap_dp_allreduce_reducescatter]: 1.326e-05 [bias_add_comm_swap]: 3.85e-06 [label_micro_interleaved_index]: 6.70998e-06 [label_fine_grained_interleaved_index]: 3.11001e-06 [merge_cast_opt]: 1.54e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.99001e-06 [assign_add_opt]: 1.54e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 3.09001e-06 [reorder_send_recv_between_fp_bp]: 3.36001e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.15001e-06 [interleave_split_concat_branches]: 1.66998e-06 [interleave_parallel_branches]: 1.49998e-06 [overlap_opt_shard_in_pipeline]: 1.40001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.14e-06 [control_data_broadcast_order]: 2.799e-05 [grouped_pairwise_exchange_alltoall]: 2.06e-06 [offloading_packed_experts]: 7.65998e-06 [overlap_recompute_and_grad_model_parallel]: 8.84998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.72001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.69998e-06 [overlap_recompute_comm]: 3.63e-06 [overlap_grad_ring_attention]: 8.00999e-06 [overlap_grad_flash_sp]: 3.911e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.22001e-06 [split_layernorm_comm]: 2.60002e-06 [handle_group_info]: 1.17e-06 [symbol_engine_optimizer]: 0.00025952, [1] [Cycle 1]: 0.0002517, [6] [build]: 4.016e-05 [elim_shapecalc]: 2.271e-05 [elim_not_effective]: 9.602e-05 [opt_reshape]: 1.594e-05 [fold_const_symbol]: 2.414e-05 [renormalize]: 4.50003e-07 [detach_backward]: 2.74001e-06 [pipeline_parallel_scheduler]: 1.84e-06 [auto_monad_reorder]: 4.884e-05 [get_jit_bprop_graph]: 2.29999e-06 [rewriter_after_jit_bprop_graph]: 1.03e-05 [opt_after_jit_grad]: 0.00078872 [validate]: 8.329e-05 [backend_pass]: 1.07998e-06 [task_emit]: 0.263552 [execute]: 1.342e-05 Sums bootstrap : 0.000544s : 0.04% type_inference : 0.356829s : 25.50% event_method : 0.000040s : 0.00% auto_monad : 0.000343s : 0.02% graph_reusing : 0.000010s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000057s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000011s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000070s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000057s : 0.00% optimize.rewriter_before_opt_a : 0.000198s : 0.01% optimize.opt_a.expand_dump_flag : 0.000019s : 0.00% optimize.opt_a.switch_simplify : 0.000235s : 0.02% optimize.opt_a.loop_unroll : 0.000213s : 0.02% optimize.opt_a.a_1 : 0.128961s : 9.22% optimize.opt_a.with_stream_mark : 0.000119s : 0.01% optimize.opt_a.recompute_prepare : 0.000091s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000066s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000027s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000024s : 0.00% optimize.opt_a.parameter_eliminate : 0.000009s : 0.00% optimize.opt_a.a_2 : 0.000757s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000099s : 0.01% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000024s : 0.00% optimize.opt_a.shard_inline : 0.000048s : 0.00% optimize.opt_a.merge_send_recv : 0.000057s : 0.00% optimize.opt_a.auto_parallel : 0.000050s : 0.00% optimize.opt_a.parallel : 0.000052s : 0.00% optimize.opt_a.flash_sp : 0.000028s : 0.00% optimize.opt_a.merge_comm : 0.000029s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000082s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000065s : 0.00% optimize.opt_a.virtual_dataset : 0.000055s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000053s : 0.00% optimize.opt_a.virtual_output : 0.000051s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000009s : 0.00% optimize.opt_a.offload_activation : 0.000065s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000112s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000099s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000033s : 0.00% optimize.opt_a.meta_fg_expand : 0.361524s : 25.83% optimize.opt_a.flash_sp_send_recv_attached : 0.000012s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000220s : 0.02% optimize.opt_a.a_after_grad : 0.000291s : 0.02% optimize.opt_a.renormalize : 0.213982s : 15.29% optimize.opt_a.add_forward_monad_depend : 0.000047s : 0.00% optimize.opt_a.auto_monad_grad : 0.000030s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000236s : 0.02% optimize.opt_a.cse : 0.000681s : 0.05% optimize.opt_a.a_3 : 0.001951s : 0.14% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000075s : 0.01% optimize.convert_after_rewriter : 0.000011s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.063762s : 4.56% optimize.opt_b.b_1 : 0.000383s : 0.03% optimize.opt_b.b_2 : 0.000020s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000112s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000038s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000048s : 0.00% optimize.loop_unroll : 0.000718s : 0.05% optimize.opt_after_cconv.c_1 : 0.000101s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000061s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000026s : 0.00% optimize.tuple_transform.d_1 : 0.000116s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000135s : 0.01% optimize.cse_after_recomputation.cse : 0.000046s : 0.00% optimize.environ_conv : 0.000018s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 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 : 0.000002s : 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 : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000004s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000039s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000003s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000040s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000096s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000049s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.00% opt_after_jit_grad : 0.000789s : 0.06% validate : 0.000083s : 0.01% backend_pass : 0.000001s : 0.00% task_emit : 0.263552s : 18.83% execute : 0.000013s : 0.00% Time group info: ------[substitution.] 0.003450 310 0.53% : 0.000018s : 4: substitution.depend_value_elim 0.10% : 0.000004s : 7: substitution.elim_not_effective 0.30% : 0.000010s : 7: substitution.float_depend_g_call 0.16% : 0.000006s : 2: substitution.float_tuple_getitem_switch 0.08% : 0.000003s : 7: substitution.fold_const_symbol 32.11% : 0.001108s : 4: substitution.getattr_setattr_resolve 0.29% : 0.000010s : 9: substitution.graph_param_transform 0.14% : 0.000005s : 2: substitution.incorporate_call 0.08% : 0.000003s : 2: substitution.incorporate_call_switch 45.17% : 0.001559s : 24: substitution.inline 1.98% : 0.000068s : 5: substitution.inline_without_move 0.56% : 0.000019s : 28: substitution.j_node_and_user_rematch 0.76% : 0.000026s : 3: substitution.less_batch_normalization 0.63% : 0.000022s : 9: substitution.minmaximum_grad 0.36% : 0.000012s : 7: substitution.partial_eliminate 0.60% : 0.000021s : 28: substitution.remove_not_recompute_node 3.82% : 0.000132s : 38: substitution.replace_applicator 0.62% : 0.000022s : 19: substitution.replace_old_param 0.21% : 0.000007s : 1: substitution.set_cell_output_no_recompute 1.40% : 0.000048s : 9: substitution.tuple_list_convert_item_index_to_positive 0.65% : 0.000022s : 9: substitution.tuple_list_get_item_const_eliminator 0.89% : 0.000031s : 9: substitution.tuple_list_get_item_depend_reorder 4.64% : 0.000160s : 31: substitution.tuple_list_get_item_eliminator 0.88% : 0.000030s : 9: substitution.tuple_list_get_set_item_eliminator 1.30% : 0.000045s : 16: substitution.updatestate_pure_node_eliminater 1.72% : 0.000060s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.356694 2 90.29% : 0.322062s : 1: type_inference.infer 9.71% : 0.034632s : 1: type_inference.specialize ------[replace.] 0.000881 49 10.20% : 0.000090s : 3: replace.getattr_setattr_resolve 43.87% : 0.000387s : 24: replace.inline 7.49% : 0.000066s : 1: replace.replace_applicator 36.93% : 0.000325s : 20: replace.tuple_list_get_item_eliminator 1.51% : 0.000013s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002706 49 38.80% : 0.001050s : 3: match.getattr_setattr_resolve 56.69% : 0.001534s : 24: match.inline 0.73% : 0.000020s : 1: match.replace_applicator 3.17% : 0.000086s : 20: match.tuple_list_get_item_eliminator 0.60% : 0.000016s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001422 8683 0.85% : 0.000012s : 85: predicate.accumulaten_eliminater 0.31% : 0.000004s : 9: predicate.ad_related_special_op_eliminate 0.37% : 0.000005s : 37: predicate.addn_check_dump 0.92% : 0.000013s : 85: predicate.addn_zero_filter 0.77% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 2.16% : 0.000031s : 122: predicate.arithmetic_simplify 0.92% : 0.000013s : 85: predicate.cast_eliminate 2.84% : 0.000040s : 260: predicate.check_bprop_eliminate 0.38% : 0.000005s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.44% : 0.000006s : 37: predicate.depend_value_elim 0.94% : 0.000013s : 85: predicate.dict_get_item_const_eliminator 1.07% : 0.000015s : 85: predicate.dict_get_item_eliminator 0.85% : 0.000012s : 85: predicate.dict_set_item_eliminator 0.29% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.10% : 0.000001s : 9: predicate.elim_not_effective 0.18% : 0.000003s : 9: predicate.elim_shapecalc_of_broadcastargs 0.91% : 0.000013s : 94: predicate.environ_add_const_eliminate 0.87% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.89% : 0.000013s : 94: predicate.environ_get_depend_swap 1.37% : 0.000019s : 131: predicate.environ_get_eliminate 0.89% : 0.000013s : 94: predicate.environ_get_set_eliminate 1.29% : 0.000018s : 130: predicate.exchange_switch_depend_value 2.01% : 0.000029s : 130: predicate.float_depend_g_call 0.41% : 0.000006s : 37: predicate.float_environ_get_switch 0.50% : 0.000007s : 46: predicate.float_tuple_getitem_switch 0.05% : 0.000001s : 9: predicate.fold_const_symbol 0.43% : 0.000006s : 37: predicate.get_grad_eliminate 0.66% : 0.000009s : 20: predicate.getattr_setattr_resolve 0.05% : 0.000001s : 9: predicate.graph_param_transform 0.43% : 0.000006s : 37: predicate.incorporate_call 0.34% : 0.000005s : 37: predicate.incorporate_call_switch 4.42% : 0.000063s : 307: predicate.inline 1.66% : 0.000024s : 111: predicate.inline_without_move 0.21% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.61% : 0.000009s : 37: predicate.less_batch_normalization 1.37% : 0.000019s : 123: predicate.list_to_tuple_eliminator_ 1.98% : 0.000028s : 208: predicate.load_eliminater 0.33% : 0.000005s : 9: predicate.loop_unroll_after_grad 2.18% : 0.000031s : 197: predicate.loop_unroll_before_grad 1.17% : 0.000017s : 103: predicate.make_slice_get_slice_eliminator 0.39% : 0.000006s : 37: predicate.merge_addn 2.63% : 0.000037s : 256: predicate.micro_step_allgather_replace 2.75% : 0.000039s : 256: predicate.mini_step_allgather_replace 0.84% : 0.000012s : 85: predicate.minmaximum_grad 0.86% : 0.000012s : 9: predicate.mutable_eliminate 0.14% : 0.000002s : 9: predicate.opt_reshape 0.13% : 0.000002s : 9: predicate.parallel_virtual_node 3.29% : 0.000047s : 130: predicate.partial_defer_inline 1.28% : 0.000018s : 114: predicate.partial_eliminate 1.04% : 0.000015s : 85: predicate.print_const_string_wrapper 0.47% : 0.000007s : 37: predicate.reduce_all_const_elim 1.14% : 0.000016s : 85: predicate.reduce_eliminate 2.12% : 0.000030s : 208: predicate.redundant_stop_gradient_eliminater 0.24% : 0.000003s : 37: predicate.remove_not_recompute_node 2.32% : 0.000033s : 363: predicate.replace_applicator 0.74% : 0.000011s : 111: predicate.replace_old_param 0.11% : 0.000002s : 9: predicate.reset_defer_inline 0.96% : 0.000014s : 85: predicate.reshape_eliminate 2.74% : 0.000039s : 256: predicate.row_tensor_add_zeros_like 0.12% : 0.000002s : 9: predicate.row_tensor_eliminate 2.82% : 0.000040s : 260: predicate.same_eliminate 0.26% : 0.000004s : 39: predicate.set_cell_output_no_recompute 0.52% : 0.000007s : 37: predicate.shard_identity_eliminate 0.23% : 0.000003s : 18: predicate.special_op_eliminate 0.45% : 0.000006s : 37: predicate.specialize_transform 2.77% : 0.000039s : 256: predicate.split_environ_get_set_with_tuple_value 1.48% : 0.000021s : 111: predicate.stack_unstack_eliminate 0.12% : 0.000002s : 9: predicate.switch_call_monad_eliminater 1.45% : 0.000021s : 130: predicate.switch_defer_inline 4.04% : 0.000057s : 390: predicate.switch_layer_defer_inline 4.25% : 0.000061s : 373: predicate.switch_simplify 0.90% : 0.000013s : 85: predicate.tile_eliminate 0.90% : 0.000013s : 85: predicate.transpose_eliminate 1.24% : 0.000018s : 103: predicate.tuple_list_convert_item_index_to_positive 1.27% : 0.000018s : 103: predicate.tuple_list_get_item_const_eliminator 1.42% : 0.000020s : 103: predicate.tuple_list_get_item_depend_reorder 2.65% : 0.000038s : 160: predicate.tuple_list_get_item_eliminator 1.30% : 0.000018s : 103: predicate.tuple_list_get_set_item_eliminator 1.90% : 0.000027s : 140: predicate.tuple_list_set_item_eliminator 1.46% : 0.000021s : 123: predicate.tuple_to_list_eliminator_ 1.98% : 0.000028s : 208: predicate.updatestate_pure_node_eliminater 2.56% : 0.000036s : 246: predicate.updatestate_useless_node_eliminater 0.13% : 0.000002s : 9: predicate.value_based_eliminate 0.47% : 0.000007s : 37: predicate.virtual_dataset_eliminate 0.41% : 0.000006s : 37: predicate.virtual_output_eliminate 0.09% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.14% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006041 53 52.29% : 0.003159s : 23: func_graph_cloner_run.FuncGraphClonerGraph 47.71% : 0.002882s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.699202 247 0.00% : 0.000004s : 1: ForceFp32Comm 3.15% : 0.085052s : 1: add_attr 3.15% : 0.085033s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000142s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000355s : 1: auto_monad 0.00% : 0.000054s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: backend_pass 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.02% : 0.000583s : 1: bootstrap 0.00% : 0.000054s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000033s : 1: control_data_broadcast_order 0.00% : 0.000014s : 1: convert_after_rewriter 0.00% : 0.000067s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.00% : 0.000048s : 1: event_method 0.00% : 0.000023s : 1: execute 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000010s : 1: insert-virtual-dataset 0.00% : 0.000007s : 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 0.03% : 0.000735s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 2.36% : 0.063787s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000054s : 1: opt.transform.mutable_eliminate 4.93% : 0.133071s : 125: opt.transform.opt_a 0.00% : 0.000098s : 1: opt.transform.opt_after_cconv 0.00% : 0.000056s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000349s : 28: opt.transform.opt_b 0.05% : 0.001294s : 2: opt.transform.opt_resolve 0.00% : 0.000127s : 2: opt.transform.opt_trans_graph 0.01% : 0.000154s : 4: opt.transform.symbol_engine_opt 26.37% : 0.711691s : 1: opt_a 0.01% : 0.000272s : 1: opt_after_cconv 0.03% : 0.000804s : 1: opt_after_jit_grad 0.02% : 0.000645s : 1: opt_b 28.85% : 0.778697s : 1: optimize 0.00% : 0.000044s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000044s : 1: overlap_grad_flash_sp 0.00% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000075s : 1: pre_auto_parallel 0.00% : 0.000062s : 1: py_interpret_to_execute 0.00% : 0.000027s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000032s : 1: remove_dup_value 5.97% : 0.161009s : 2: renormalize.infer 1.96% : 0.052934s : 2: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000014s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000079s : 1: rewriter_after_opt_a 0.01% : 0.000203s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000263s : 1: symbol_engine_optimizer 9.77% : 0.263579s : 1: task_emit 0.01% : 0.000173s : 1: tuple_transform 13.22% : 0.356856s : 1: type_inference 0.01% : 0.000144s : 1: validate . [hook] pytest_runtest_teardown:test_sigmoid__bf16[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__bf16[0],max_mem:4.0M [WARNING] ME(171811:281473316736816,MainProcess):2026-01-29-17:41:31.407.283 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. . [hook] pytest_runtest_teardown:test_sigmoid__bf16[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__bf16[1],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 ================== 2 passed, 25 warnings in 278.76s (0:04:38) ==================