==================================================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_001/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(168463:281473373822768,MainProcess):2026-01-29-17:39:39.270.900 [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 = 0.166071, [21] [bootstrap]: 0.00062023 [type_inference]: 0.148817 [event_method]: 1.502e-05 [auto_monad]: 0.00018469 [graph_reusing]: 5.82001e-06 [inline]: 2.76999e-06 [add_attr]: 0.00909689, [1] [add_attr_with_inline]: 0.00908193, [1] [Cycle 1]: 9.667e-05, [2] [tag_attr]: 1.72e-05 [meta_addattr_fg_expand]: 3.78001e-06 [parallel-infer-symbol]: 4.12998e-06 [pre_auto_parallel]: 4.457e-05 [insert-virtual-dataset]: 2.55002e-06 [parallel-infer-symbol-second]: 1.24e-06 [dataset_repeat_opt]: 2.22999e-06 [pipeline_split]: 2.26e-06 [optimize]: 0.00633475, [53] [py_interpret_to_execute]: 2.171e-05 [rewriter_before_opt_a]: 0.0001501 [opt_a]: 0.00328073, [2] [Cycle 1]: 0.00225063, [45] [expand_dump_flag]: 3.51001e-06 [switch_simplify]: 2.947e-05 [loop_unroll]: 1.501e-05 [a_1]: 0.00041118 [with_stream_mark]: 2.094e-05 [recompute_prepare]: 1.127e-05 [updatestate_depend_eliminate]: 6.93e-06 [updatestate_assign_eliminate]: 9.15001e-06 [updatestate_loads_eliminate]: 5.44998e-06 [parameter_eliminate]: 1.92999e-06 [a_2]: 0.00014038 [accelerated_algorithm]: 1.049e-05 [shard]: 2.51998e-06 [meta_shard_fg_expand]: 3.41001e-06 [shard_inline]: 1.021e-05 [merge_send_recv]: 2.296e-05 [auto_parallel]: 9.74999e-06 [parallel]: 4.863e-05 [flash_sp]: 2.058e-05 [merge_comm]: 6.30002e-06 [allreduce_fusion]: 5.83002e-06 [matmul_add_comm_reduction]: 1.265e-05 [allreduce_slice_to_reducescatter]: 7.50006e-07 [virtual_shard_identity]: 1.265e-05 [virtual_dataset]: 9.66003e-06 [get_grad_eliminate_]: 9.24e-06 [virtual_output]: 9.07999e-06 [merge_forward]: 5.98002e-06 [cell_reuse_recompute_pass]: 2.17001e-06 [offload_activation]: 1.461e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.994e-05 [merge_recompute_call_nodes]: 1.81998e-06 [before_grad]: 1.755e-05 [set_forward_comm_id_for_comm_node_pass]: 6.21e-06 [meta_fg_expand]: 4.38001e-06 [flash_sp_send_recv_attached]: 3.10002e-06 [receive_attached]: 2.77002e-06 [after_resolve]: 1.425e-05 [a_after_grad]: 1.47e-05 [renormalize]: 0.00079881 [add_forward_monad_depend]: 5.89e-06 [auto_monad_grad]: 2.74001e-06 [auto_monad_eliminator]: 2.419e-05 [cse]: 6.413e-05 [a_3]: 7.52e-05 [Cycle 2]: 0.00101803, [45] [expand_dump_flag]: 1.43002e-06 [switch_simplify]: 1.223e-05 [loop_unroll]: 1.022e-05 [a_1]: 0.00022185 [with_stream_mark]: 1.891e-05 [recompute_prepare]: 1.023e-05 [updatestate_depend_eliminate]: 5.77999e-06 [updatestate_assign_eliminate]: 6.02001e-06 [updatestate_loads_eliminate]: 4.87998e-06 [parameter_eliminate]: 1.69e-06 [a_2]: 0.00012577 [accelerated_algorithm]: 9.64999e-06 [shard]: 1.99999e-06 [meta_shard_fg_expand]: 2.42001e-06 [shard_inline]: 9.61e-06 [merge_send_recv]: 8.33001e-06 [auto_parallel]: 9.32001e-06 [parallel]: 7.93999e-06 [flash_sp]: 4.79998e-06 [merge_comm]: 5.82999e-06 [allreduce_fusion]: 5.89999e-06 [matmul_add_comm_reduction]: 1.108e-05 [allreduce_slice_to_reducescatter]: 1.10999e-06 [virtual_shard_identity]: 1.153e-05 [virtual_dataset]: 8.93002e-06 [get_grad_eliminate_]: 8.71002e-06 [virtual_output]: 8.54e-06 [merge_forward]: 6.10002e-06 [cell_reuse_recompute_pass]: 2.86e-06 [offload_activation]: 1.269e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.048e-05 [merge_recompute_call_nodes]: 1.07998e-06 [before_grad]: 1.717e-05 [set_forward_comm_id_for_comm_node_pass]: 5.91e-06 [meta_fg_expand]: 4.15999e-06 [flash_sp_send_recv_attached]: 1.32999e-06 [receive_attached]: 2.26e-06 [after_resolve]: 1.353e-05 [a_after_grad]: 1.35e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 1.59998e-06 [auto_monad_grad]: 2.02999e-06 [auto_monad_eliminator]: 1.622e-05 [cse]: 3.508e-05 [a_3]: 5.802e-05 [py_interpret_to_execute_after_opt_a]: 1.885e-05 [slice_cell_reuse_recomputed_activation]: 2.31e-06 [rewriter_after_opt_a]: 0.00018833 [convert_after_rewriter]: 1.418e-05 [order_py_execute_after_rewriter]: 6.89999e-06 [mutable_eliminate]: 0.00080523 [opt_b]: 0.00033384, [1] [Cycle 1]: 0.00032515, [7] [b_1]: 0.00021386 [b_2]: 1.249e-05 [updatestate_depend_eliminate]: 1.254e-05 [updatestate_assign_eliminate]: 5.59e-06 [updatestate_loads_eliminate]: 4.67e-06 [renormalize]: 7.50006e-07 [cse]: 3.64e-05 [optimize_parallel_all_gather_comm]: 2.529e-05 [overlap_param_gather]: 1.79e-06 [cconv]: 3.71e-05 [loop_unroll]: 0.0005183 [opt_after_cconv]: 0.00015209, [1] [Cycle 1]: 0.00014546, [7] [c_1]: 5.784e-05 [parameter_eliminate]: 5.17e-06 [updatestate_depend_eliminate]: 9.02999e-06 [updatestate_assign_eliminate]: 4.91002e-06 [updatestate_loads_eliminate]: 4.18999e-06 [cse]: 2.644e-05 [renormalize]: 7.09988e-07 [remove_dup_value]: 1.81e-05 [tuple_transform]: 0.00010102, [1] [Cycle 1]: 9.565e-05, [4] [d_1]: 6.316e-05 [none_parameter_eliminate]: 2.43998e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 1.04e-05 [partial_unused_args_eliminate]: 1.90001e-06 [add_recomputation]: 8.525e-05 [cse_after_recomputation]: 2.803e-05, [1] [Cycle 1]: 2.254e-05, [1] [cse]: 1.686e-05 [environ_conv]: 2.159e-05 [swap_dp_allreduce_reducescatter]: 8.50001e-06 [bias_add_comm_swap]: 3.13998e-06 [label_micro_interleaved_index]: 5.42001e-06 [label_fine_grained_interleaved_index]: 2.88e-06 [merge_cast_opt]: 1.47001e-06 [slice_recompute_activation]: 2.10002e-06 [micro_interleaved_order_control]: 2.68e-06 [assign_add_opt]: 1.19998e-06 [ForceFp32Comm]: 8.59989e-07 [remove_cast_before_assign_add]: 1.22e-06 [full_micro_interleaved_order_control]: 2.71e-06 [reorder_send_recv_between_fp_bp]: 2.94999e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.01002e-06 [interleave_split_concat_branches]: 1.55999e-06 [interleave_parallel_branches]: 1.17999e-06 [overlap_opt_shard_in_pipeline]: 2.481e-05 [overlap_opt_shard_grad_in_pipeline]: 1.97999e-06 [control_data_broadcast_order]: 2.101e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 6.01998e-06 [overlap_recompute_and_grad_model_parallel]: 6.63e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.83e-06 [overlap_grad_ring_attention]: 6.29999e-06 [overlap_grad_flash_sp]: 3.346e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.23998e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.22e-06 [symbol_engine_optimizer]: 0.00010898, [1] [Cycle 1]: 0.00010351, [6] [build]: 5.32999e-06 [elim_shapecalc]: 1.619e-05 [elim_not_effective]: 2.114e-05 [opt_reshape]: 9.76998e-06 [fold_const_symbol]: 1.731e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.78e-06 [pipeline_parallel_scheduler]: 1.64e-06 [auto_monad_reorder]: 3.768e-05 [get_jit_bprop_graph]: 1.84e-06 [rewriter_after_jit_bprop_graph]: 5.24998e-06 [opt_after_jit_grad]: 0.00060343 [validate]: 8.013e-05 Sums bootstrap : 0.000620s : 0.40% type_inference : 0.148817s : 95.54% event_method : 0.000015s : 0.01% auto_monad : 0.000185s : 0.12% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 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 : 0.000045s : 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 : 0.000022s : 0.01% optimize.rewriter_before_opt_a : 0.000150s : 0.10% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000042s : 0.03% optimize.opt_a.loop_unroll : 0.000025s : 0.02% optimize.opt_a.a_1 : 0.000633s : 0.41% optimize.opt_a.with_stream_mark : 0.000040s : 0.03% optimize.opt_a.recompute_prepare : 0.000021s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000015s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000266s : 0.17% optimize.opt_a.accelerated_algorithm : 0.000020s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000020s : 0.01% optimize.opt_a.merge_send_recv : 0.000031s : 0.02% optimize.opt_a.auto_parallel : 0.000019s : 0.01% optimize.opt_a.parallel : 0.000057s : 0.04% optimize.opt_a.flash_sp : 0.000025s : 0.02% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000012s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000024s : 0.02% optimize.opt_a.virtual_dataset : 0.000019s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000018s : 0.01% optimize.opt_a.virtual_output : 0.000018s : 0.01% optimize.opt_a.merge_forward : 0.000012s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000027s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000050s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000035s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.01% optimize.opt_a.meta_fg_expand : 0.000009s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000028s : 0.02% optimize.opt_a.a_after_grad : 0.000028s : 0.02% optimize.opt_a.renormalize : 0.000799s : 0.51% optimize.opt_a.add_forward_monad_depend : 0.000007s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000040s : 0.03% optimize.opt_a.cse : 0.000099s : 0.06% optimize.opt_a.a_3 : 0.000133s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000019s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000188s : 0.12% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000805s : 0.52% optimize.opt_b.b_1 : 0.000214s : 0.14% optimize.opt_b.b_2 : 0.000012s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000036s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000025s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.02% optimize.loop_unroll : 0.000518s : 0.33% optimize.opt_after_cconv.c_1 : 0.000058s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000026s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.01% optimize.tuple_transform.d_1 : 0.000063s : 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 : 0.000010s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000085s : 0.05% optimize.cse_after_recomputation.cse : 0.000017s : 0.01% optimize.environ_conv : 0.000022s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000025s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 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 : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000033s : 0.02% 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 : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000021s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000017s : 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 : 0.000038s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000603s : 0.39% validate : 0.000080s : 0.05% Time group info: ------[substitution.] 0.000189 55 5.20% : 0.000010s : 2: substitution.depend_value_elim 1.66% : 0.000003s : 5: substitution.elim_not_effective 1.34% : 0.000003s : 5: substitution.fold_const_symbol 4.33% : 0.000008s : 6: substitution.graph_param_transform 55.06% : 0.000104s : 1: substitution.inline 4.23% : 0.000008s : 10: substitution.j_node_and_user_rematch 9.54% : 0.000018s : 10: substitution.remove_not_recompute_node 2.41% : 0.000005s : 2: substitution.replace_old_param 8.30% : 0.000016s : 6: substitution.updatestate_pure_node_eliminater 7.93% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.148757 2 99.70% : 0.148317s : 1: type_inference.infer 0.30% : 0.000440s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000103 1 100.00% : 0.000103s : 1: match.inline ------[predicate.] 0.000275 1419 0.81% : 0.000002s : 13: predicate.accumulaten_eliminater 1.12% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.71% : 0.000002s : 12: predicate.addn_check_dump 0.85% : 0.000002s : 13: predicate.addn_zero_filter 0.77% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.84% : 0.000005s : 25: predicate.arithmetic_simplify 0.79% : 0.000002s : 13: predicate.cast_eliminate 0.82% : 0.000002s : 12: predicate.check_bprop_eliminate 0.75% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000001s : 6: predicate.const_output_eliminate 0.79% : 0.000002s : 12: predicate.depend_value_elim 0.79% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.87% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.79% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.22% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.33% : 0.000001s : 6: predicate.elim_not_effective 0.64% : 0.000002s : 6: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.17% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.08% : 0.000003s : 19: predicate.environ_get_depend_swap 1.98% : 0.000005s : 31: predicate.environ_get_eliminate 1.19% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.87% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.47% : 0.000004s : 14: predicate.float_depend_g_call 0.70% : 0.000002s : 12: predicate.float_environ_get_switch 1.07% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 6: predicate.fold_const_symbol 0.80% : 0.000002s : 12: predicate.get_grad_eliminate 0.31% : 0.000001s : 6: predicate.graph_param_transform 0.79% : 0.000002s : 12: predicate.incorporate_call 0.68% : 0.000002s : 12: predicate.incorporate_call_switch 5.88% : 0.000016s : 63: predicate.inline 1.01% : 0.000003s : 12: predicate.inline_without_move 0.42% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.92% : 0.000003s : 12: predicate.less_batch_normalization 1.89% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.31% : 0.000006s : 38: predicate.load_eliminater 1.11% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.33% : 0.000004s : 17: predicate.loop_unroll_before_grad 1.72% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.75% : 0.000002s : 12: predicate.merge_addn 0.85% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.74% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 13: predicate.minmaximum_grad 1.57% : 0.000004s : 6: predicate.mutable_eliminate 0.44% : 0.000001s : 6: predicate.opt_reshape 0.44% : 0.000001s : 6: predicate.parallel_virtual_node 1.12% : 0.000003s : 14: predicate.partial_defer_inline 1.32% : 0.000004s : 19: predicate.partial_eliminate 0.81% : 0.000002s : 13: predicate.print_const_string_wrapper 0.79% : 0.000002s : 12: predicate.reduce_all_const_elim 1.04% : 0.000003s : 13: predicate.reduce_eliminate 2.30% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.61% : 0.000002s : 12: predicate.remove_not_recompute_node 1.13% : 0.000003s : 25: predicate.replace_applicator 0.77% : 0.000002s : 12: predicate.replace_old_param 0.41% : 0.000001s : 6: predicate.reset_defer_inline 0.83% : 0.000002s : 13: predicate.reshape_eliminate 0.81% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.54% : 0.000001s : 6: predicate.row_tensor_eliminate 1.06% : 0.000003s : 12: predicate.same_eliminate 0.47% : 0.000001s : 12: predicate.set_cell_output_no_recompute 1.01% : 0.000003s : 12: predicate.shard_identity_eliminate 0.92% : 0.000003s : 12: predicate.special_op_eliminate 1.04% : 0.000003s : 12: predicate.specialize_transform 1.30% : 0.000004s : 12: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000003s : 12: predicate.stack_unstack_eliminate 0.51% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.87% : 0.000002s : 14: predicate.switch_defer_inline 1.64% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.96% : 0.000011s : 49: predicate.switch_simplify 0.78% : 0.000002s : 13: predicate.tile_eliminate 0.80% : 0.000002s : 13: predicate.transpose_eliminate 1.59% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000005s : 25: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000005s : 25: predicate.tuple_list_get_item_depend_reorder 2.91% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.58% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.57% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.39% : 0.000007s : 38: predicate.updatestate_pure_node_eliminater 3.47% : 0.000010s : 50: predicate.updatestate_useless_node_eliminater 0.42% : 0.000001s : 6: predicate.value_based_eliminate 0.79% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.82% : 0.000002s : 12: predicate.virtual_output_eliminate 0.44% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.59% : 0.000002s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000248 4 9.62% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 90.38% : 0.000225s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.183861 192 0.00% : 0.000004s : 1: ForceFp32Comm 4.95% : 0.009103s : 1: add_attr 4.94% : 0.009087s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.05% : 0.000090s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.11% : 0.000194s : 1: auto_monad 0.02% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.37% : 0.000672s : 1: bootstrap 0.02% : 0.000041s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.01% : 0.000025s : 1: control_data_broadcast_order 0.01% : 0.000018s : 1: convert_after_rewriter 0.02% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000026s : 1: environ_conv 0.01% : 0.000022s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000010s : 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% : 0.000006s : 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 0.29% : 0.000529s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.45% : 0.000819s : 1: mutable_eliminate 0.01% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000026s : 1: opt.transform.mutable_eliminate 0.70% : 0.001278s : 78: opt.transform.opt_a 0.03% : 0.000056s : 1: opt.transform.opt_after_cconv 0.02% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.11% : 0.000195s : 28: opt.transform.opt_b 0.04% : 0.000071s : 2: opt.transform.opt_trans_graph 0.03% : 0.000060s : 4: opt.transform.symbol_engine_opt 1.79% : 0.003285s : 1: opt_a 0.08% : 0.000156s : 1: opt_after_cconv 0.34% : 0.000618s : 1: opt_after_jit_grad 0.18% : 0.000338s : 1: opt_b 3.45% : 0.006341s : 1: optimize 0.02% : 0.000030s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.02% : 0.000038s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.02% : 0.000029s : 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 0.01% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 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 0.03% : 0.000050s : 1: pre_auto_parallel 0.01% : 0.000026s : 1: py_interpret_to_execute 0.01% : 0.000022s : 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 0.26% : 0.000487s : 1: renormalize.infer 0.16% : 0.000302s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.11% : 0.000197s : 1: rewriter_after_opt_a 0.08% : 0.000156s : 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 0.01% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.06% : 0.000112s : 1: symbol_engine_optimizer 0.06% : 0.000104s : 1: tuple_transform 80.95% : 0.148841s : 1: type_inference TotalTime = 0.158134, [21] [bootstrap]: 0.00085121 [type_inference]: 0.00507555 [event_method]: 1.921e-05 [auto_monad]: 0.00022632 [graph_reusing]: 6.34999e-06 [inline]: 3.38e-06 [add_attr]: 0.144356, [1] [add_attr_with_inline]: 0.144341, [1] [Cycle 1]: 7.149e-05, [2] [tag_attr]: 1.951e-05 [meta_addattr_fg_expand]: 3.4e-06 [parallel-infer-symbol]: 4.05e-06 [pre_auto_parallel]: 4.314e-05 [insert-virtual-dataset]: 2.46e-06 [parallel-infer-symbol-second]: 1.03001e-06 [dataset_repeat_opt]: 2.44999e-06 [pipeline_split]: 1.96e-06 [optimize]: 0.00659469, [53] [py_interpret_to_execute]: 2.667e-05 [rewriter_before_opt_a]: 6.607e-05 [opt_a]: 0.00353188, [2] [Cycle 1]: 0.00245014, [45] [expand_dump_flag]: 3.11999e-06 [switch_simplify]: 2.736e-05 [loop_unroll]: 1.505e-05 [a_1]: 0.00046114 [with_stream_mark]: 2.483e-05 [recompute_prepare]: 1.359e-05 [updatestate_depend_eliminate]: 7.28999e-06 [updatestate_assign_eliminate]: 5.91998e-06 [updatestate_loads_eliminate]: 6.16e-06 [parameter_eliminate]: 2.00002e-06 [a_2]: 0.00014163 [accelerated_algorithm]: 1.134e-05 [shard]: 2.58998e-06 [meta_shard_fg_expand]: 2.51e-06 [shard_inline]: 9.81e-06 [merge_send_recv]: 1.209e-05 [auto_parallel]: 1.065e-05 [parallel]: 3.482e-05 [flash_sp]: 1.186e-05 [merge_comm]: 6.79001e-06 [allreduce_fusion]: 5.79e-06 [matmul_add_comm_reduction]: 1.358e-05 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 1.506e-05 [virtual_dataset]: 1.007e-05 [get_grad_eliminate_]: 9.04e-06 [virtual_output]: 9.18002e-06 [merge_forward]: 6.55002e-06 [cell_reuse_recompute_pass]: 1.52001e-06 [offload_activation]: 1.604e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.429e-05 [merge_recompute_call_nodes]: 1.81998e-06 [before_grad]: 2.002e-05 [set_forward_comm_id_for_comm_node_pass]: 6.59999e-06 [meta_fg_expand]: 4.30999e-06 [flash_sp_send_recv_attached]: 4.1e-06 [receive_attached]: 2.69999e-06 [after_resolve]: 1.467e-05 [a_after_grad]: 1.478e-05 [renormalize]: 0.00097395 [add_forward_monad_depend]: 8.50001e-06 [auto_monad_grad]: 2.71e-06 [auto_monad_eliminator]: 2.873e-05 [cse]: 4.129e-05 [a_3]: 8.211e-05 [Cycle 2]: 0.00106717, [45] [expand_dump_flag]: 2.37001e-06 [switch_simplify]: 1.35e-05 [loop_unroll]: 9.97001e-06 [a_1]: 0.00023668 [with_stream_mark]: 2.406e-05 [recompute_prepare]: 1.138e-05 [updatestate_depend_eliminate]: 8.03999e-06 [updatestate_assign_eliminate]: 6.00002e-06 [updatestate_loads_eliminate]: 6.01e-06 [parameter_eliminate]: 1.69e-06 [a_2]: 0.00013228 [accelerated_algorithm]: 1.023e-05 [shard]: 2.45002e-06 [meta_shard_fg_expand]: 3.43999e-06 [shard_inline]: 9.65002e-06 [merge_send_recv]: 1.198e-05 [auto_parallel]: 1.277e-05 [parallel]: 8.72998e-06 [flash_sp]: 4.23999e-06 [merge_comm]: 6.47001e-06 [allreduce_fusion]: 5.59e-06 [matmul_add_comm_reduction]: 1.22e-05 [allreduce_slice_to_reducescatter]: 8.00006e-07 [virtual_shard_identity]: 1.199e-05 [virtual_dataset]: 9.82999e-06 [get_grad_eliminate_]: 9.36002e-06 [virtual_output]: 9.34998e-06 [merge_forward]: 6.34999e-06 [cell_reuse_recompute_pass]: 3.37002e-06 [offload_activation]: 1.491e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.325e-05 [merge_recompute_call_nodes]: 1.57001e-06 [before_grad]: 1.85e-05 [set_forward_comm_id_for_comm_node_pass]: 6.31998e-06 [meta_fg_expand]: 3.98001e-06 [flash_sp_send_recv_attached]: 1.54e-06 [receive_attached]: 2.42001e-06 [after_resolve]: 1.463e-05 [a_after_grad]: 1.455e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.22999e-06 [auto_monad_grad]: 1.87001e-06 [auto_monad_eliminator]: 1.796e-05 [cse]: 2.915e-05 [a_3]: 6.038e-05 [py_interpret_to_execute_after_opt_a]: 2.049e-05 [slice_cell_reuse_recomputed_activation]: 2.04e-06 [rewriter_after_opt_a]: 0.00019676 [convert_after_rewriter]: 1.321e-05 [order_py_execute_after_rewriter]: 7.10998e-06 [mutable_eliminate]: 0.00086455 [opt_b]: 0.00034163, [1] [Cycle 1]: 0.00033241, [7] [b_1]: 0.00021916 [b_2]: 1.16e-05 [updatestate_depend_eliminate]: 1.08e-05 [updatestate_assign_eliminate]: 5.52001e-06 [updatestate_loads_eliminate]: 5.29e-06 [renormalize]: 1.25999e-06 [cse]: 3.345e-05 [optimize_parallel_all_gather_comm]: 2.416e-05 [overlap_param_gather]: 1.96e-06 [cconv]: 3.763e-05 [loop_unroll]: 0.00054518 [opt_after_cconv]: 0.00015954, [1] [Cycle 1]: 0.00015213, [7] [c_1]: 6.102e-05 [parameter_eliminate]: 5.42001e-06 [updatestate_depend_eliminate]: 8.74e-06 [updatestate_assign_eliminate]: 5.17999e-06 [updatestate_loads_eliminate]: 4.59002e-06 [cse]: 2.593e-05 [renormalize]: 8.60018e-07 [remove_dup_value]: 1.791e-05 [tuple_transform]: 0.00010541, [1] [Cycle 1]: 0.0001001, [4] [d_1]: 6.562e-05 [none_parameter_eliminate]: 1.50999e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 1.031e-05 [partial_unused_args_eliminate]: 1.98002e-06 [add_recomputation]: 8.385e-05 [cse_after_recomputation]: 2.847e-05, [1] [Cycle 1]: 2.302e-05, [1] [cse]: 1.618e-05 [environ_conv]: 8.09002e-06 [swap_dp_allreduce_reducescatter]: 8.95999e-06 [bias_add_comm_swap]: 3.41001e-06 [label_micro_interleaved_index]: 4.87e-06 [label_fine_grained_interleaved_index]: 2.80002e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 2.09e-06 [micro_interleaved_order_control]: 2.53e-06 [assign_add_opt]: 1.40001e-06 [ForceFp32Comm]: 1.21997e-06 [remove_cast_before_assign_add]: 1.16002e-06 [full_micro_interleaved_order_control]: 2.54001e-06 [reorder_send_recv_between_fp_bp]: 3.01001e-06 [comm_op_add_attrs]: 1.07998e-06 [add_comm_op_reuse_tag]: 9.99979e-07 [interleave_split_concat_branches]: 1.30999e-06 [interleave_parallel_branches]: 1.55999e-06 [overlap_opt_shard_in_pipeline]: 1.17999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.86e-06 [control_data_broadcast_order]: 2.043e-05 [grouped_pairwise_exchange_alltoall]: 1.54e-06 [offloading_packed_experts]: 6.36e-06 [overlap_recompute_and_grad_model_parallel]: 6.71e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.50999e-06 [overlap_recompute_comm]: 2.67001e-06 [overlap_grad_ring_attention]: 5.91998e-06 [overlap_grad_flash_sp]: 2.964e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.15002e-06 [split_layernorm_comm]: 2.14999e-06 [handle_group_info]: 1.25001e-06 [symbol_engine_optimizer]: 0.00011017, [1] [Cycle 1]: 0.00010461, [6] [build]: 5.59e-06 [elim_shapecalc]: 1.556e-05 [elim_not_effective]: 1.996e-05 [opt_reshape]: 1.141e-05 [fold_const_symbol]: 1.678e-05 [renormalize]: 3.00002e-07 [detach_backward]: 2.91e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 3.061e-05 [get_jit_bprop_graph]: 1.94999e-06 [rewriter_after_jit_bprop_graph]: 5.32001e-06 [opt_after_jit_grad]: 0.000629 [validate]: 6.58e-05 Sums bootstrap : 0.000851s : 6.79% type_inference : 0.005076s : 40.49% event_method : 0.000019s : 0.15% auto_monad : 0.000226s : 1.81% graph_reusing : 0.000006s : 0.05% inline : 0.000003s : 0.03% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.16% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000003s : 0.03% parallel-infer-symbol : 0.000004s : 0.03% pre_auto_parallel : 0.000043s : 0.34% insert-virtual-dataset : 0.000002s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.02% pipeline_split : 0.000002s : 0.02% optimize.py_interpret_to_execute : 0.000027s : 0.21% optimize.rewriter_before_opt_a : 0.000066s : 0.53% optimize.opt_a.expand_dump_flag : 0.000005s : 0.04% optimize.opt_a.switch_simplify : 0.000041s : 0.33% optimize.opt_a.loop_unroll : 0.000025s : 0.20% optimize.opt_a.a_1 : 0.000698s : 5.57% optimize.opt_a.with_stream_mark : 0.000049s : 0.39% optimize.opt_a.recompute_prepare : 0.000025s : 0.20% optimize.opt_a.updatestate_depend_eliminate : 0.000015s : 0.12% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.10% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.10% optimize.opt_a.parameter_eliminate : 0.000004s : 0.03% optimize.opt_a.a_2 : 0.000274s : 2.19% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.17% optimize.opt_a.shard : 0.000005s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.05% optimize.opt_a.shard_inline : 0.000019s : 0.16% optimize.opt_a.merge_send_recv : 0.000024s : 0.19% optimize.opt_a.auto_parallel : 0.000023s : 0.19% optimize.opt_a.parallel : 0.000044s : 0.35% optimize.opt_a.flash_sp : 0.000016s : 0.13% optimize.opt_a.merge_comm : 0.000013s : 0.11% optimize.opt_a.allreduce_fusion : 0.000011s : 0.09% optimize.opt_a.matmul_add_comm_reduction : 0.000026s : 0.21% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.22% optimize.opt_a.virtual_dataset : 0.000020s : 0.16% optimize.opt_a.get_grad_eliminate_ : 0.000018s : 0.15% optimize.opt_a.virtual_output : 0.000019s : 0.15% optimize.opt_a.merge_forward : 0.000013s : 0.10% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.04% optimize.opt_a.offload_activation : 0.000031s : 0.25% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.38% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.03% optimize.opt_a.before_grad : 0.000039s : 0.31% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.10% optimize.opt_a.meta_fg_expand : 0.000008s : 0.07% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.04% optimize.opt_a.receive_attached : 0.000005s : 0.04% optimize.opt_a.after_resolve : 0.000029s : 0.23% optimize.opt_a.a_after_grad : 0.000029s : 0.23% optimize.opt_a.renormalize : 0.000974s : 7.77% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.09% optimize.opt_a.auto_monad_grad : 0.000005s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000047s : 0.37% optimize.opt_a.cse : 0.000070s : 0.56% optimize.opt_a.a_3 : 0.000142s : 1.14% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.16% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.02% optimize.rewriter_after_opt_a : 0.000197s : 1.57% optimize.convert_after_rewriter : 0.000013s : 0.11% optimize.order_py_execute_after_rewriter : 0.000007s : 0.06% optimize.mutable_eliminate : 0.000865s : 6.90% optimize.opt_b.b_1 : 0.000219s : 1.75% optimize.opt_b.b_2 : 0.000012s : 0.09% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.04% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.04% optimize.opt_b.renormalize : 0.000001s : 0.01% optimize.opt_b.cse : 0.000033s : 0.27% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.19% optimize.overlap_param_gather : 0.000002s : 0.02% optimize.cconv : 0.000038s : 0.30% optimize.loop_unroll : 0.000545s : 4.35% optimize.opt_after_cconv.c_1 : 0.000061s : 0.49% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.07% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.04% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.04% optimize.opt_after_cconv.cse : 0.000026s : 0.21% optimize.opt_after_cconv.renormalize : 0.000001s : 0.01% optimize.remove_dup_value : 0.000018s : 0.14% optimize.tuple_transform.d_1 : 0.000066s : 0.52% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.08% optimize.partial_unused_args_eliminate : 0.000002s : 0.02% optimize.add_recomputation : 0.000084s : 0.67% optimize.cse_after_recomputation.cse : 0.000016s : 0.13% optimize.environ_conv : 0.000008s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.07% optimize.bias_add_comm_swap : 0.000003s : 0.03% optimize.label_micro_interleaved_index : 0.000005s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 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 : 0.000002s : 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 : 0.000020s : 0.16% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.05% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.05% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000006s : 0.05% optimize.overlap_grad_flash_sp : 0.000030s : 0.24% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.02% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.12% optimize.symbol_engine_optimizer.elim_not_effective : 0.000020s : 0.16% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.09% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000017s : 0.13% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000031s : 0.24% get_jit_bprop_graph : 0.000002s : 0.02% rewriter_after_jit_bprop_graph : 0.000005s : 0.04% opt_after_jit_grad : 0.000629s : 5.02% validate : 0.000066s : 0.52% Time group info: ------[substitution.] 0.000196 55 5.24% : 0.000010s : 2: substitution.depend_value_elim 1.60% : 0.000003s : 5: substitution.elim_not_effective 1.23% : 0.000002s : 5: substitution.fold_const_symbol 4.22% : 0.000008s : 6: substitution.graph_param_transform 60.30% : 0.000118s : 1: substitution.inline 3.19% : 0.000006s : 10: substitution.j_node_and_user_rematch 5.25% : 0.000010s : 10: substitution.remove_not_recompute_node 2.52% : 0.000005s : 2: substitution.replace_old_param 8.81% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 7.64% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.005005 2 89.90% : 0.004499s : 1: type_inference.infer 10.10% : 0.000506s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000117 1 100.00% : 0.000117s : 1: match.inline ------[predicate.] 0.000287 1419 0.92% : 0.000003s : 13: predicate.accumulaten_eliminater 1.01% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.83% : 0.000002s : 12: predicate.addn_check_dump 0.79% : 0.000002s : 13: predicate.addn_zero_filter 0.97% : 0.000003s : 13: predicate.adjust_all_reduce_mul_add 1.94% : 0.000006s : 25: predicate.arithmetic_simplify 0.81% : 0.000002s : 13: predicate.cast_eliminate 0.78% : 0.000002s : 12: predicate.check_bprop_eliminate 0.78% : 0.000002s : 12: predicate.compare_switch_simplify 0.22% : 0.000001s : 6: predicate.const_output_eliminate 0.80% : 0.000002s : 12: predicate.depend_value_elim 0.80% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.83% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.88% : 0.000003s : 13: predicate.dict_set_item_eliminator 1.34% : 0.000004s : 12: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 6: predicate.elim_not_effective 0.49% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.10% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.17% : 0.000003s : 19: predicate.environ_get_depend_swap 2.00% : 0.000006s : 31: predicate.environ_get_eliminate 1.26% : 0.000004s : 19: predicate.environ_get_set_eliminate 0.97% : 0.000003s : 14: predicate.exchange_switch_depend_value 1.54% : 0.000004s : 14: predicate.float_depend_g_call 0.66% : 0.000002s : 12: predicate.float_environ_get_switch 1.01% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 6: predicate.fold_const_symbol 0.84% : 0.000002s : 12: predicate.get_grad_eliminate 0.24% : 0.000001s : 6: predicate.graph_param_transform 0.74% : 0.000002s : 12: predicate.incorporate_call 0.65% : 0.000002s : 12: predicate.incorporate_call_switch 5.80% : 0.000017s : 63: predicate.inline 0.95% : 0.000003s : 12: predicate.inline_without_move 0.38% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.91% : 0.000003s : 12: predicate.less_batch_normalization 2.05% : 0.000006s : 25: predicate.list_to_tuple_eliminator_ 2.22% : 0.000006s : 38: predicate.load_eliminater 1.07% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.18% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.86% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.76% : 0.000002s : 12: predicate.merge_addn 0.84% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.76% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.76% : 0.000002s : 13: predicate.minmaximum_grad 1.65% : 0.000005s : 6: predicate.mutable_eliminate 0.46% : 0.000001s : 6: predicate.opt_reshape 0.47% : 0.000001s : 6: predicate.parallel_virtual_node 1.07% : 0.000003s : 14: predicate.partial_defer_inline 1.23% : 0.000004s : 19: predicate.partial_eliminate 0.77% : 0.000002s : 13: predicate.print_const_string_wrapper 0.78% : 0.000002s : 12: predicate.reduce_all_const_elim 1.11% : 0.000003s : 13: predicate.reduce_eliminate 2.18% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 12: predicate.remove_not_recompute_node 1.08% : 0.000003s : 25: predicate.replace_applicator 0.60% : 0.000002s : 12: predicate.replace_old_param 0.31% : 0.000001s : 6: predicate.reset_defer_inline 0.84% : 0.000002s : 13: predicate.reshape_eliminate 0.87% : 0.000003s : 12: predicate.row_tensor_add_zeros_like 0.52% : 0.000001s : 6: predicate.row_tensor_eliminate 1.07% : 0.000003s : 12: predicate.same_eliminate 0.65% : 0.000002s : 12: predicate.set_cell_output_no_recompute 1.02% : 0.000003s : 12: predicate.shard_identity_eliminate 1.05% : 0.000003s : 12: predicate.special_op_eliminate 0.94% : 0.000003s : 12: predicate.specialize_transform 1.09% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 1.02% : 0.000003s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.92% : 0.000003s : 14: predicate.switch_defer_inline 1.60% : 0.000005s : 26: predicate.switch_layer_defer_inline 3.49% : 0.000010s : 49: predicate.switch_simplify 0.96% : 0.000003s : 13: predicate.tile_eliminate 0.83% : 0.000002s : 13: predicate.transpose_eliminate 1.76% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.81% : 0.000005s : 25: predicate.tuple_list_get_item_const_eliminator 1.61% : 0.000005s : 25: predicate.tuple_list_get_item_depend_reorder 3.14% : 0.000009s : 37: predicate.tuple_list_get_item_eliminator 1.60% : 0.000005s : 25: predicate.tuple_list_get_set_item_eliminator 2.57% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.67% : 0.000005s : 25: predicate.tuple_to_list_eliminator_ 2.29% : 0.000007s : 38: predicate.updatestate_pure_node_eliminater 3.36% : 0.000010s : 50: predicate.updatestate_useless_node_eliminater 0.52% : 0.000001s : 6: predicate.value_based_eliminate 0.89% : 0.000003s : 12: predicate.virtual_dataset_eliminate 0.75% : 0.000002s : 12: predicate.virtual_output_eliminate 0.43% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.48% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000320 4 7.46% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 92.54% : 0.000296s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.311726 192 0.00% : 0.000004s : 1: ForceFp32Comm 46.31% : 0.144364s : 1: add_attr 46.31% : 0.144346s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000089s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.000235s : 1: auto_monad 0.01% : 0.000036s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.29% : 0.000895s : 1: bootstrap 0.01% : 0.000042s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000024s : 1: control_data_broadcast_order 0.01% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000032s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000012s : 1: environ_conv 0.01% : 0.000026s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 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% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.18% : 0.000557s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.28% : 0.000878s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000026s : 1: opt.transform.mutable_eliminate 0.44% : 0.001370s : 78: opt.transform.opt_a 0.02% : 0.000059s : 1: opt.transform.opt_after_cconv 0.01% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.06% : 0.000199s : 28: opt.transform.opt_b 0.02% : 0.000073s : 2: opt.transform.opt_trans_graph 0.02% : 0.000060s : 4: opt.transform.symbol_engine_opt 1.13% : 0.003537s : 1: opt_a 0.05% : 0.000164s : 1: opt_after_cconv 0.21% : 0.000646s : 1: opt_after_jit_grad 0.11% : 0.000346s : 1: opt_b 2.12% : 0.006601s : 1: optimize 0.01% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000033s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000006s : 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% : 0.000009s : 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 0.02% : 0.000048s : 1: pre_auto_parallel 0.01% : 0.000032s : 1: py_interpret_to_execute 0.01% : 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 0.18% : 0.000563s : 1: renormalize.infer 0.13% : 0.000399s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000206s : 1: rewriter_after_opt_a 0.02% : 0.000071s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000114s : 1: symbol_engine_optimizer 0.03% : 0.000109s : 1: tuple_transform 1.64% : 0.005102s : 1: type_inference TotalTime = 0.828943, [21] [bootstrap]: 0.00054455 [type_inference]: 0.308996 [event_method]: 7.828e-05 [auto_monad]: 0.00032569 [graph_reusing]: 1.127e-05 [inline]: 3.2e-06 [add_attr]: 0.00435093, [1] [add_attr_with_inline]: 0.00433656, [1] [Cycle 1]: 0.00010709, [2] [tag_attr]: 4.673e-05 [meta_addattr_fg_expand]: 1.093e-05 [parallel-infer-symbol]: 3.85998e-06 [pre_auto_parallel]: 6.736e-05 [insert-virtual-dataset]: 2.61999e-06 [parallel-infer-symbol-second]: 1.17999e-06 [dataset_repeat_opt]: 2.44001e-06 [pipeline_split]: 1.78997e-06 [optimize]: 0.513593, [53] [py_interpret_to_execute]: 5.255e-05 [rewriter_before_opt_a]: 0.00018136 [opt_a]: 0.36975, [3] [Cycle 1]: 0.360609, [45] [expand_dump_flag]: 8.50001e-06 [switch_simplify]: 8.167e-05 [loop_unroll]: 6.452e-05 [a_1]: 0.00229412 [with_stream_mark]: 5.076e-05 [recompute_prepare]: 4.479e-05 [updatestate_depend_eliminate]: 1.676e-05 [updatestate_assign_eliminate]: 1.24e-05 [updatestate_loads_eliminate]: 1.217e-05 [parameter_eliminate]: 4.53999e-06 [a_2]: 0.00057321 [accelerated_algorithm]: 5.479e-05 [shard]: 2.68e-06 [meta_shard_fg_expand]: 8.44998e-06 [shard_inline]: 2.66e-05 [merge_send_recv]: 2.817e-05 [auto_parallel]: 2.214e-05 [parallel]: 2.443e-05 [flash_sp]: 1.711e-05 [merge_comm]: 1.489e-05 [allreduce_fusion]: 1.335e-05 [matmul_add_comm_reduction]: 4.49e-05 [allreduce_slice_to_reducescatter]: 1.22e-06 [virtual_shard_identity]: 3.057e-05 [virtual_dataset]: 2.597e-05 [get_grad_eliminate_]: 2.511e-05 [virtual_output]: 2.399e-05 [merge_forward]: 1.452e-05 [cell_reuse_recompute_pass]: 1.82999e-06 [offload_activation]: 3.114e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.651e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 5.081e-05 [set_forward_comm_id_for_comm_node_pass]: 1.471e-05 [meta_fg_expand]: 0.179482 [flash_sp_send_recv_attached]: 6.71999e-06 [receive_attached]: 3.03e-06 [after_resolve]: 0.00016745 [a_after_grad]: 0.00024367 [renormalize]: 0.173742 [add_forward_monad_depend]: 3.516e-05 [auto_monad_grad]: 2.021e-05 [auto_monad_eliminator]: 0.00020573 [cse]: 0.00042759 [a_3]: 0.00206796 [Cycle 2]: 0.00782812, [45] [expand_dump_flag]: 8.59e-06 [switch_simplify]: 0.00012867 [loop_unroll]: 0.00011488 [a_1]: 0.00413333 [with_stream_mark]: 4.003e-05 [recompute_prepare]: 2.571e-05 [updatestate_depend_eliminate]: 4.845e-05 [updatestate_assign_eliminate]: 8.22e-06 [updatestate_loads_eliminate]: 6.42001e-06 [parameter_eliminate]: 2.72001e-06 [a_2]: 0.00025997 [accelerated_algorithm]: 2.321e-05 [shard]: 2.93998e-06 [meta_shard_fg_expand]: 5.27001e-06 [shard_inline]: 1.434e-05 [merge_send_recv]: 1.663e-05 [auto_parallel]: 1.47e-05 [parallel]: 1.219e-05 [flash_sp]: 5.14e-06 [merge_comm]: 7.33999e-06 [allreduce_fusion]: 6.59001e-06 [matmul_add_comm_reduction]: 1.558e-05 [allreduce_slice_to_reducescatter]: 9.89996e-07 [virtual_shard_identity]: 1.674e-05 [virtual_dataset]: 1.22e-05 [get_grad_eliminate_]: 1.23e-05 [virtual_output]: 1.155e-05 [merge_forward]: 7.34002e-06 [cell_reuse_recompute_pass]: 2.60002e-06 [offload_activation]: 1.681e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.827e-05 [merge_recompute_call_nodes]: 2.08998e-06 [before_grad]: 2.481e-05 [set_forward_comm_id_for_comm_node_pass]: 8.57998e-06 [meta_fg_expand]: 9.651e-05 [flash_sp_send_recv_attached]: 1.88002e-06 [receive_attached]: 2.34999e-06 [after_resolve]: 2.503e-05 [a_after_grad]: 2.13e-05 [renormalize]: 0.00199015 [add_forward_monad_depend]: 1.24e-05 [auto_monad_grad]: 3.08998e-06 [auto_monad_eliminator]: 3.134e-05 [cse]: 0.00013548 [a_3]: 0.00010744 [Cycle 3]: 0.00128791, [45] [expand_dump_flag]: 2.44001e-06 [switch_simplify]: 1.679e-05 [loop_unroll]: 1.258e-05 [a_1]: 0.00033946 [with_stream_mark]: 2.238e-05 [recompute_prepare]: 1.376e-05 [updatestate_depend_eliminate]: 7.71999e-06 [updatestate_assign_eliminate]: 6.84999e-06 [updatestate_loads_eliminate]: 6.33e-06 [parameter_eliminate]: 1.80001e-06 [a_2]: 0.00017253 [accelerated_algorithm]: 2.065e-05 [shard]: 2.78e-06 [meta_shard_fg_expand]: 3.69002e-06 [shard_inline]: 1.318e-05 [merge_send_recv]: 1.264e-05 [auto_parallel]: 1.426e-05 [parallel]: 1.163e-05 [flash_sp]: 1.87001e-06 [merge_comm]: 8.45999e-06 [allreduce_fusion]: 6.99001e-06 [matmul_add_comm_reduction]: 1.484e-05 [allreduce_slice_to_reducescatter]: 1.71998e-06 [virtual_shard_identity]: 1.515e-05 [virtual_dataset]: 1.337e-05 [get_grad_eliminate_]: 1.215e-05 [virtual_output]: 1.118e-05 [merge_forward]: 8.07e-06 [cell_reuse_recompute_pass]: 3.46999e-06 [offload_activation]: 1.508e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.679e-05 [merge_recompute_call_nodes]: 1.93002e-06 [before_grad]: 2.325e-05 [set_forward_comm_id_for_comm_node_pass]: 9.59e-06 [meta_fg_expand]: 5.30001e-06 [flash_sp_send_recv_attached]: 1.86e-06 [receive_attached]: 2.11998e-06 [after_resolve]: 2.092e-05 [a_after_grad]: 1.989e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 2.80997e-06 [auto_monad_grad]: 2.41e-06 [auto_monad_eliminator]: 2.293e-05 [cse]: 3.851e-05 [a_3]: 7.919e-05 [py_interpret_to_execute_after_opt_a]: 2.547e-05 [slice_cell_reuse_recomputed_activation]: 2.64999e-06 [rewriter_after_opt_a]: 9.227e-05 [convert_after_rewriter]: 1.214e-05 [order_py_execute_after_rewriter]: 9.32001e-06 [mutable_eliminate]: 0.141079 [opt_b]: 0.00050049, [1] [Cycle 1]: 0.00048741, [7] [b_1]: 0.00030907 [b_2]: 1.564e-05 [updatestate_depend_eliminate]: 2.03e-05 [updatestate_assign_eliminate]: 7.53e-06 [updatestate_loads_eliminate]: 7.10998e-06 [renormalize]: 9.60019e-07 [cse]: 7.31e-05 [optimize_parallel_all_gather_comm]: 3.594e-05 [overlap_param_gather]: 2.14e-06 [cconv]: 4.295e-05 [loop_unroll]: 0.00065485 [opt_after_cconv]: 0.00021088, [1] [Cycle 1]: 0.00020254, [7] [c_1]: 8.168e-05 [parameter_eliminate]: 7.26001e-06 [updatestate_depend_eliminate]: 1.161e-05 [updatestate_assign_eliminate]: 6.56999e-06 [updatestate_loads_eliminate]: 5.84999e-06 [cse]: 4.384e-05 [renormalize]: 1.16002e-06 [remove_dup_value]: 2.218e-05 [tuple_transform]: 0.0001409, [1] [Cycle 1]: 0.00013459, [4] [d_1]: 9.655e-05 [none_parameter_eliminate]: 2.01e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.347e-05 [partial_unused_args_eliminate]: 2.16e-06 [add_recomputation]: 0.00012149 [cse_after_recomputation]: 4.606e-05, [1] [Cycle 1]: 3.982e-05, [1] [cse]: 3.205e-05 [environ_conv]: 1.434e-05 [swap_dp_allreduce_reducescatter]: 1.114e-05 [bias_add_comm_swap]: 3.57997e-06 [label_micro_interleaved_index]: 7.75e-06 [label_fine_grained_interleaved_index]: 3.05002e-06 [merge_cast_opt]: 1.91998e-06 [slice_recompute_activation]: 2.22999e-06 [micro_interleaved_order_control]: 2.42001e-06 [assign_add_opt]: 1.59998e-06 [ForceFp32Comm]: 9.99979e-07 [remove_cast_before_assign_add]: 8.70001e-07 [full_micro_interleaved_order_control]: 2.59001e-06 [reorder_send_recv_between_fp_bp]: 3.12002e-06 [comm_op_add_attrs]: 1.19e-06 [add_comm_op_reuse_tag]: 9.90025e-07 [interleave_split_concat_branches]: 1.30999e-06 [interleave_parallel_branches]: 1.29e-06 [overlap_opt_shard_in_pipeline]: 1.17e-06 [overlap_opt_shard_grad_in_pipeline]: 1.64e-06 [control_data_broadcast_order]: 2.418e-05 [grouped_pairwise_exchange_alltoall]: 1.86e-06 [offloading_packed_experts]: 6.66e-06 [overlap_recompute_and_grad_model_parallel]: 8.50001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.57999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.69998e-06 [overlap_recompute_comm]: 2.54999e-06 [overlap_grad_ring_attention]: 6.96999e-06 [overlap_grad_flash_sp]: 3.703e-05 [begin_end_overlap_inline]: 9.20001e-07 [split_matmul_comm_elemetwise]: 2.71e-06 [split_layernorm_comm]: 2.17001e-06 [handle_group_info]: 1.00999e-06 [symbol_engine_optimizer]: 0.000162, [1] [Cycle 1]: 0.00015635, [6] [build]: 3.11e-05 [elim_shapecalc]: 1.952e-05 [elim_not_effective]: 2.855e-05 [opt_reshape]: 1.362e-05 [fold_const_symbol]: 2.387e-05 [renormalize]: 4.19997e-07 [detach_backward]: 2.21e-06 [pipeline_parallel_scheduler]: 1.49e-06 [auto_monad_reorder]: 3.839e-05 [get_jit_bprop_graph]: 2.22999e-06 [rewriter_after_jit_bprop_graph]: 7.9e-06 [opt_after_jit_grad]: 0.00062357 [validate]: 7.654e-05 Sums bootstrap : 0.000545s : 0.07% type_inference : 0.308996s : 37.55% event_method : 0.000078s : 0.01% auto_monad : 0.000326s : 0.04% graph_reusing : 0.000011s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000047s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000011s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000067s : 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 : 0.000053s : 0.01% optimize.rewriter_before_opt_a : 0.000181s : 0.02% optimize.opt_a.expand_dump_flag : 0.000020s : 0.00% optimize.opt_a.switch_simplify : 0.000227s : 0.03% optimize.opt_a.loop_unroll : 0.000192s : 0.02% optimize.opt_a.a_1 : 0.006767s : 0.82% optimize.opt_a.with_stream_mark : 0.000113s : 0.01% optimize.opt_a.recompute_prepare : 0.000084s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000073s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000027s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000025s : 0.00% optimize.opt_a.parameter_eliminate : 0.000009s : 0.00% optimize.opt_a.a_2 : 0.001006s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000099s : 0.01% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000017s : 0.00% optimize.opt_a.shard_inline : 0.000054s : 0.01% optimize.opt_a.merge_send_recv : 0.000057s : 0.01% optimize.opt_a.auto_parallel : 0.000051s : 0.01% optimize.opt_a.parallel : 0.000048s : 0.01% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000031s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000075s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000004s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000062s : 0.01% optimize.opt_a.virtual_dataset : 0.000052s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.01% optimize.opt_a.virtual_output : 0.000047s : 0.01% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000063s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000112s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000006s : 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 : 0.179583s : 21.83% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000007s : 0.00% optimize.opt_a.after_resolve : 0.000213s : 0.03% optimize.opt_a.a_after_grad : 0.000285s : 0.03% optimize.opt_a.renormalize : 0.175732s : 21.36% optimize.opt_a.add_forward_monad_depend : 0.000050s : 0.01% optimize.opt_a.auto_monad_grad : 0.000026s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000260s : 0.03% optimize.opt_a.cse : 0.000602s : 0.07% optimize.opt_a.a_3 : 0.002255s : 0.27% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000092s : 0.01% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.141079s : 17.15% optimize.opt_b.b_1 : 0.000309s : 0.04% optimize.opt_b.b_2 : 0.000016s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000073s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.01% optimize.loop_unroll : 0.000655s : 0.08% optimize.opt_after_cconv.c_1 : 0.000082s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000044s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.00% optimize.tuple_transform.d_1 : 0.000097s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000121s : 0.01% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 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 : 0.000002s : 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 : 0.000001s : 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 : 0.000024s : 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 : 0.000009s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000037s : 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 : 0.000031s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000029s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000038s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000624s : 0.08% validate : 0.000077s : 0.01% Time group info: ------[substitution.] 0.002920 310 0.69% : 0.000020s : 4: substitution.depend_value_elim 0.14% : 0.000004s : 7: substitution.elim_not_effective 0.31% : 0.000009s : 7: substitution.float_depend_g_call 0.15% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.11% : 0.000003s : 7: substitution.fold_const_symbol 31.62% : 0.000923s : 4: substitution.getattr_setattr_resolve 0.36% : 0.000011s : 9: substitution.graph_param_transform 0.15% : 0.000004s : 2: substitution.incorporate_call 0.09% : 0.000002s : 2: substitution.incorporate_call_switch 43.26% : 0.001263s : 24: substitution.inline 1.83% : 0.000053s : 5: substitution.inline_without_move 0.63% : 0.000018s : 28: substitution.j_node_and_user_rematch 0.95% : 0.000028s : 3: substitution.less_batch_normalization 0.63% : 0.000018s : 9: substitution.minmaximum_grad 0.37% : 0.000011s : 7: substitution.partial_eliminate 0.79% : 0.000023s : 28: substitution.remove_not_recompute_node 5.22% : 0.000152s : 38: substitution.replace_applicator 0.78% : 0.000023s : 19: substitution.replace_old_param 0.17% : 0.000005s : 1: substitution.set_cell_output_no_recompute 1.37% : 0.000040s : 9: substitution.tuple_list_convert_item_index_to_positive 0.66% : 0.000019s : 9: substitution.tuple_list_get_item_const_eliminator 0.84% : 0.000025s : 9: substitution.tuple_list_get_item_depend_reorder 4.45% : 0.000130s : 31: substitution.tuple_list_get_item_eliminator 0.86% : 0.000025s : 9: substitution.tuple_list_get_set_item_eliminator 1.43% : 0.000042s : 16: substitution.updatestate_pure_node_eliminater 2.13% : 0.000062s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.308887 2 99.41% : 0.307060s : 1: type_inference.infer 0.59% : 0.001827s : 1: type_inference.specialize ------[replace.] 0.000708 49 9.79% : 0.000069s : 3: replace.getattr_setattr_resolve 40.83% : 0.000289s : 24: replace.inline 11.28% : 0.000080s : 1: replace.replace_applicator 35.49% : 0.000251s : 20: replace.tuple_list_get_item_eliminator 2.62% : 0.000019s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002240 49 39.02% : 0.000874s : 3: match.getattr_setattr_resolve 55.44% : 0.001242s : 24: match.inline 1.17% : 0.000026s : 1: match.replace_applicator 3.41% : 0.000076s : 20: match.tuple_list_get_item_eliminator 0.96% : 0.000022s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001543 8683 0.90% : 0.000014s : 85: predicate.accumulaten_eliminater 0.26% : 0.000004s : 9: predicate.ad_related_special_op_eliminate 0.41% : 0.000006s : 37: predicate.addn_check_dump 0.88% : 0.000014s : 85: predicate.addn_zero_filter 0.85% : 0.000013s : 85: predicate.adjust_all_reduce_mul_add 1.67% : 0.000026s : 122: predicate.arithmetic_simplify 0.91% : 0.000014s : 85: predicate.cast_eliminate 2.66% : 0.000041s : 260: predicate.check_bprop_eliminate 0.40% : 0.000006s : 37: predicate.compare_switch_simplify 0.06% : 0.000001s : 9: predicate.const_output_eliminate 0.47% : 0.000007s : 37: predicate.depend_value_elim 0.92% : 0.000014s : 85: predicate.dict_get_item_const_eliminator 0.99% : 0.000015s : 85: predicate.dict_get_item_eliminator 0.88% : 0.000014s : 85: predicate.dict_set_item_eliminator 0.26% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.07% : 0.000001s : 9: predicate.elim_not_effective 0.14% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 0.99% : 0.000015s : 94: predicate.environ_add_const_eliminate 0.95% : 0.000015s : 94: predicate.environ_get_add_eliminate 0.94% : 0.000014s : 94: predicate.environ_get_depend_swap 1.45% : 0.000022s : 131: predicate.environ_get_eliminate 0.98% : 0.000015s : 94: predicate.environ_get_set_eliminate 1.42% : 0.000022s : 130: predicate.exchange_switch_depend_value 2.17% : 0.000033s : 130: predicate.float_depend_g_call 0.51% : 0.000008s : 37: predicate.float_environ_get_switch 0.50% : 0.000008s : 46: predicate.float_tuple_getitem_switch 0.06% : 0.000001s : 9: predicate.fold_const_symbol 0.44% : 0.000007s : 37: predicate.get_grad_eliminate 0.50% : 0.000008s : 20: predicate.getattr_setattr_resolve 0.06% : 0.000001s : 9: predicate.graph_param_transform 0.44% : 0.000007s : 37: predicate.incorporate_call 0.38% : 0.000006s : 37: predicate.incorporate_call_switch 5.13% : 0.000079s : 307: predicate.inline 1.73% : 0.000027s : 111: predicate.inline_without_move 0.22% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.64% : 0.000010s : 37: predicate.less_batch_normalization 1.36% : 0.000021s : 123: predicate.list_to_tuple_eliminator_ 2.17% : 0.000034s : 208: predicate.load_eliminater 0.27% : 0.000004s : 9: predicate.loop_unroll_after_grad 2.07% : 0.000032s : 197: predicate.loop_unroll_before_grad 1.12% : 0.000017s : 103: predicate.make_slice_get_slice_eliminator 0.40% : 0.000006s : 37: predicate.merge_addn 2.54% : 0.000039s : 256: predicate.micro_step_allgather_replace 2.62% : 0.000040s : 256: predicate.mini_step_allgather_replace 0.86% : 0.000013s : 85: predicate.minmaximum_grad 0.69% : 0.000011s : 9: predicate.mutable_eliminate 0.11% : 0.000002s : 9: predicate.opt_reshape 0.11% : 0.000002s : 9: predicate.parallel_virtual_node 2.19% : 0.000034s : 130: predicate.partial_defer_inline 1.40% : 0.000022s : 114: predicate.partial_eliminate 0.94% : 0.000014s : 85: predicate.print_const_string_wrapper 0.41% : 0.000006s : 37: predicate.reduce_all_const_elim 1.10% : 0.000017s : 85: predicate.reduce_eliminate 2.16% : 0.000033s : 208: predicate.redundant_stop_gradient_eliminater 0.27% : 0.000004s : 37: predicate.remove_not_recompute_node 2.60% : 0.000040s : 363: predicate.replace_applicator 0.74% : 0.000011s : 111: predicate.replace_old_param 0.11% : 0.000002s : 9: predicate.reset_defer_inline 0.89% : 0.000014s : 85: predicate.reshape_eliminate 2.75% : 0.000043s : 256: predicate.row_tensor_add_zeros_like 0.12% : 0.000002s : 9: predicate.row_tensor_eliminate 2.92% : 0.000045s : 260: predicate.same_eliminate 0.30% : 0.000005s : 39: predicate.set_cell_output_no_recompute 0.44% : 0.000007s : 37: predicate.shard_identity_eliminate 0.25% : 0.000004s : 18: predicate.special_op_eliminate 0.52% : 0.000008s : 37: predicate.specialize_transform 3.05% : 0.000047s : 256: predicate.split_environ_get_set_with_tuple_value 1.45% : 0.000022s : 111: predicate.stack_unstack_eliminate 0.12% : 0.000002s : 9: predicate.switch_call_monad_eliminater 1.54% : 0.000024s : 130: predicate.switch_defer_inline 4.10% : 0.000063s : 390: predicate.switch_layer_defer_inline 4.33% : 0.000067s : 373: predicate.switch_simplify 0.88% : 0.000014s : 85: predicate.tile_eliminate 0.88% : 0.000014s : 85: predicate.transpose_eliminate 1.21% : 0.000019s : 103: predicate.tuple_list_convert_item_index_to_positive 1.28% : 0.000020s : 103: predicate.tuple_list_get_item_const_eliminator 1.20% : 0.000019s : 103: predicate.tuple_list_get_item_depend_reorder 2.52% : 0.000039s : 160: predicate.tuple_list_get_item_eliminator 1.46% : 0.000023s : 103: predicate.tuple_list_get_set_item_eliminator 1.71% : 0.000026s : 140: predicate.tuple_list_set_item_eliminator 1.35% : 0.000021s : 123: predicate.tuple_to_list_eliminator_ 2.17% : 0.000033s : 208: predicate.updatestate_pure_node_eliminater 2.88% : 0.000044s : 246: predicate.updatestate_useless_node_eliminater 0.11% : 0.000002s : 9: predicate.value_based_eliminate 0.43% : 0.000007s : 37: predicate.virtual_dataset_eliminate 0.42% : 0.000006s : 37: predicate.virtual_output_eliminate 0.11% : 0.000002s : 9: predicate.virtual_view_grad_eliminate 0.17% : 0.000003s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004299 53 56.44% : 0.002427s : 23: func_graph_cloner_run.FuncGraphClonerGraph 43.56% : 0.001873s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.535514 243 0.00% : 0.000004s : 1: ForceFp32Comm 0.28% : 0.004358s : 1: add_attr 0.28% : 0.004342s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000127s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000339s : 1: auto_monad 0.00% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000581s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000017s : 1: convert_after_rewriter 0.00% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.01% : 0.000089s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000017s : 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% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.04% : 0.000668s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 9.19% : 0.141107s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000052s : 1: opt.transform.mutable_eliminate 0.74% : 0.011363s : 125: opt.transform.opt_a 0.01% : 0.000080s : 1: opt.transform.opt_after_cconv 0.00% : 0.000049s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000284s : 28: opt.transform.opt_b 0.07% : 0.001066s : 2: opt.transform.opt_resolve 0.01% : 0.000107s : 2: opt.transform.opt_trans_graph 0.01% : 0.000081s : 4: opt.transform.symbol_engine_opt 24.08% : 0.369754s : 1: opt_a 0.01% : 0.000215s : 1: opt_after_cconv 0.04% : 0.000637s : 1: opt_after_jit_grad 0.03% : 0.000506s : 1: opt_b 33.45% : 0.513600s : 1: optimize 0.00% : 0.000040s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000041s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 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% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 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 0.00% : 0.000073s : 1: pre_auto_parallel 0.00% : 0.000058s : 1: py_interpret_to_execute 0.00% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000026s : 1: remove_dup_value 11.06% : 0.169756s : 2: renormalize.infer 0.39% : 0.005944s : 2: 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% : 0.000100s : 1: rewriter_after_opt_a 0.01% : 0.000187s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000165s : 1: symbol_engine_optimizer 0.01% : 0.000144s : 1: tuple_transform 20.13% : 0.309026s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__zero_values[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__zero_values[0],max_mem:4.0M [WARNING] ME(168463:281473373822768,MainProcess):2026-01-29-17:40:18.492.533 [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__zero_values[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__zero_values[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 208.75s (0:03:28) ==================