==================================================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_007/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(165587:281472958316336,MainProcess):2026-01-29-17:39:46.154.69 [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 = 0.174862, [21] [bootstrap]: 0.00053907 [type_inference]: 0.159133 [event_method]: 1.308e-05 [auto_monad]: 0.00018481 [graph_reusing]: 5.74999e-06 [inline]: 2.73998e-06 [add_attr]: 0.00863339, [1] [add_attr_with_inline]: 0.00861724, [1] [Cycle 1]: 9.658e-05, [2] [tag_attr]: 1.789e-05 [meta_addattr_fg_expand]: 4.50001e-06 [parallel-infer-symbol]: 3.34001e-06 [pre_auto_parallel]: 4.342e-05 [insert-virtual-dataset]: 2.32999e-06 [parallel-infer-symbol-second]: 8.89995e-07 [dataset_repeat_opt]: 2.32999e-06 [pipeline_split]: 1.71998e-06 [optimize]: 0.00551067, [53] [py_interpret_to_execute]: 2.137e-05 [rewriter_before_opt_a]: 6.61e-05 [opt_a]: 0.00288405, [2] [Cycle 1]: 0.00204111, [45] [expand_dump_flag]: 3.05998e-06 [switch_simplify]: 2.736e-05 [loop_unroll]: 1.323e-05 [a_1]: 0.00039859 [with_stream_mark]: 2.191e-05 [recompute_prepare]: 1.01e-05 [updatestate_depend_eliminate]: 6.90998e-06 [updatestate_assign_eliminate]: 6.59001e-06 [updatestate_loads_eliminate]: 5.21998e-06 [parameter_eliminate]: 1.74998e-06 [a_2]: 0.00012357 [accelerated_algorithm]: 9.13002e-06 [shard]: 2.46e-06 [meta_shard_fg_expand]: 2.19001e-06 [shard_inline]: 8.67e-06 [merge_send_recv]: 1.828e-05 [auto_parallel]: 8.69e-06 [parallel]: 4.701e-05 [flash_sp]: 1.799e-05 [merge_comm]: 5.84e-06 [allreduce_fusion]: 5.69999e-06 [matmul_add_comm_reduction]: 1.192e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 1.117e-05 [virtual_dataset]: 8.27998e-06 [get_grad_eliminate_]: 7.87e-06 [virtual_output]: 7.78001e-06 [merge_forward]: 5.24998e-06 [cell_reuse_recompute_pass]: 1.34998e-06 [offload_activation]: 1.325e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.753e-05 [merge_recompute_call_nodes]: 1.45001e-06 [before_grad]: 1.508e-05 [set_forward_comm_id_for_comm_node_pass]: 4.99e-06 [meta_fg_expand]: 3.82998e-06 [flash_sp_send_recv_attached]: 2.58e-06 [receive_attached]: 1.102e-05 [after_resolve]: 1.266e-05 [a_after_grad]: 1.244e-05 [renormalize]: 0.00073373 [add_forward_monad_depend]: 5.79e-06 [auto_monad_grad]: 2.36998e-06 [auto_monad_eliminator]: 2.168e-05 [cse]: 4.991e-05 [a_3]: 6.367e-05 [Cycle 2]: 0.00083084, [45] [expand_dump_flag]: 1.42999e-06 [switch_simplify]: 9.99999e-06 [loop_unroll]: 8.32e-06 [a_1]: 0.00019369 [with_stream_mark]: 1.502e-05 [recompute_prepare]: 8.95999e-06 [updatestate_depend_eliminate]: 5.08002e-06 [updatestate_assign_eliminate]: 4.55001e-06 [updatestate_loads_eliminate]: 4.42e-06 [parameter_eliminate]: 1.17e-06 [a_2]: 0.00010761 [accelerated_algorithm]: 8.16002e-06 [shard]: 1.17999e-06 [meta_shard_fg_expand]: 1.67001e-06 [shard_inline]: 8.08999e-06 [merge_send_recv]: 7.3e-06 [auto_parallel]: 7.85e-06 [parallel]: 5.54e-06 [flash_sp]: 3.41001e-06 [merge_comm]: 4.65001e-06 [allreduce_fusion]: 4.55001e-06 [matmul_add_comm_reduction]: 8.01001e-06 [allreduce_slice_to_reducescatter]: 9.79984e-07 [virtual_shard_identity]: 8.92e-06 [virtual_dataset]: 7.68999e-06 [get_grad_eliminate_]: 7.27002e-06 [virtual_output]: 7.19001e-06 [merge_forward]: 4.45999e-06 [cell_reuse_recompute_pass]: 1.55001e-06 [offload_activation]: 9.87999e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.708e-05 [merge_recompute_call_nodes]: 9.20001e-07 [before_grad]: 1.412e-05 [set_forward_comm_id_for_comm_node_pass]: 5.32001e-06 [meta_fg_expand]: 2.86999e-06 [flash_sp_send_recv_attached]: 7.59988e-07 [receive_attached]: 1.50999e-06 [after_resolve]: 1.06e-05 [a_after_grad]: 1.175e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.94e-06 [auto_monad_grad]: 1.55999e-06 [auto_monad_eliminator]: 1.408e-05 [cse]: 2.038e-05 [a_3]: 5.165e-05 [py_interpret_to_execute_after_opt_a]: 1.485e-05 [slice_cell_reuse_recomputed_activation]: 2.68e-06 [rewriter_after_opt_a]: 0.00015296 [convert_after_rewriter]: 2.256e-05 [order_py_execute_after_rewriter]: 6.94999e-06 [mutable_eliminate]: 0.00069789 [opt_b]: 0.00028474, [1] [Cycle 1]: 0.00027714, [7] [b_1]: 0.00018181 [b_2]: 1.028e-05 [updatestate_depend_eliminate]: 9.61003e-06 [updatestate_assign_eliminate]: 5.03002e-06 [updatestate_loads_eliminate]: 4.42e-06 [renormalize]: 1.27e-06 [cse]: 2.786e-05 [optimize_parallel_all_gather_comm]: 2.171e-05 [overlap_param_gather]: 2.28998e-06 [cconv]: 3.203e-05 [loop_unroll]: 0.00047941 [opt_after_cconv]: 0.00013793, [1] [Cycle 1]: 0.00013147, [7] [c_1]: 5.195e-05 [parameter_eliminate]: 4.05e-06 [updatestate_depend_eliminate]: 7.93001e-06 [updatestate_assign_eliminate]: 4.52e-06 [updatestate_loads_eliminate]: 4.18001e-06 [cse]: 2.329e-05 [renormalize]: 5.8001e-07 [remove_dup_value]: 1.455e-05 [tuple_transform]: 8.862e-05, [1] [Cycle 1]: 8.389e-05, [4] [d_1]: 5.555e-05 [none_parameter_eliminate]: 1.60001e-06 [renormalize]: 1.70025e-07 [switch_simplify]: 8.80999e-06 [partial_unused_args_eliminate]: 1.68002e-06 [add_recomputation]: 7.453e-05 [cse_after_recomputation]: 2.523e-05, [1] [Cycle 1]: 2.039e-05, [1] [cse]: 1.519e-05 [environ_conv]: 1.79e-05 [swap_dp_allreduce_reducescatter]: 7.60998e-06 [bias_add_comm_swap]: 2.71e-06 [label_micro_interleaved_index]: 4.74002e-06 [label_fine_grained_interleaved_index]: 2.66e-06 [merge_cast_opt]: 1.35001e-06 [slice_recompute_activation]: 2.09999e-06 [micro_interleaved_order_control]: 2.45002e-06 [assign_add_opt]: 1.20001e-06 [ForceFp32Comm]: 1.16997e-06 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.49001e-06 [reorder_send_recv_between_fp_bp]: 3.31001e-06 [comm_op_add_attrs]: 1.17999e-06 [add_comm_op_reuse_tag]: 1.32999e-06 [interleave_split_concat_branches]: 1.09998e-06 [interleave_parallel_branches]: 1.06002e-06 [overlap_opt_shard_in_pipeline]: 2.173e-05 [overlap_opt_shard_grad_in_pipeline]: 1.70001e-06 [control_data_broadcast_order]: 1.817e-05 [grouped_pairwise_exchange_alltoall]: 1.55001e-06 [offloading_packed_experts]: 4.97e-06 [overlap_recompute_and_grad_model_parallel]: 5.71e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.14e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.44999e-06 [overlap_grad_ring_attention]: 5.04e-06 [overlap_grad_flash_sp]: 2.971e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 1.89e-06 [split_layernorm_comm]: 2.07999e-06 [handle_group_info]: 1.62001e-06 [symbol_engine_optimizer]: 8.977e-05, [1] [Cycle 1]: 8.561e-05, [6] [build]: 4.35e-06 [elim_shapecalc]: 1.283e-05 [elim_not_effective]: 1.634e-05 [opt_reshape]: 8.77999e-06 [fold_const_symbol]: 1.387e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.19999e-06 [pipeline_parallel_scheduler]: 1.40001e-06 [auto_monad_reorder]: 3.422e-05 [get_jit_bprop_graph]: 1.81e-06 [rewriter_after_jit_bprop_graph]: 4.82e-06 [opt_after_jit_grad]: 0.00050235 [validate]: 6.605e-05 Sums bootstrap : 0.000539s : 0.33% type_inference : 0.159133s : 96.33% event_method : 0.000013s : 0.01% auto_monad : 0.000185s : 0.11% 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 : 0.000005s : 0.00% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000043s : 0.03% insert-virtual-dataset : 0.000002s : 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 : 0.000021s : 0.01% optimize.rewriter_before_opt_a : 0.000066s : 0.04% optimize.opt_a.expand_dump_flag : 0.000004s : 0.00% optimize.opt_a.switch_simplify : 0.000037s : 0.02% optimize.opt_a.loop_unroll : 0.000022s : 0.01% optimize.opt_a.a_1 : 0.000592s : 0.36% optimize.opt_a.with_stream_mark : 0.000037s : 0.02% optimize.opt_a.recompute_prepare : 0.000019s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000231s : 0.14% optimize.opt_a.accelerated_algorithm : 0.000017s : 0.01% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000017s : 0.01% optimize.opt_a.merge_send_recv : 0.000026s : 0.02% optimize.opt_a.auto_parallel : 0.000017s : 0.01% optimize.opt_a.parallel : 0.000053s : 0.03% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000010s : 0.01% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000020s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000020s : 0.01% optimize.opt_a.virtual_dataset : 0.000016s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000015s : 0.01% optimize.opt_a.virtual_output : 0.000015s : 0.01% optimize.opt_a.merge_forward : 0.000010s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000023s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000035s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.00% optimize.opt_a.before_grad : 0.000029s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000010s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000003s : 0.00% optimize.opt_a.receive_attached : 0.000013s : 0.01% optimize.opt_a.after_resolve : 0.000023s : 0.01% optimize.opt_a.a_after_grad : 0.000024s : 0.01% optimize.opt_a.renormalize : 0.000734s : 0.44% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000036s : 0.02% optimize.opt_a.cse : 0.000070s : 0.04% optimize.opt_a.a_3 : 0.000115s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000015s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000153s : 0.09% optimize.convert_after_rewriter : 0.000023s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000698s : 0.42% optimize.opt_b.b_1 : 0.000182s : 0.11% optimize.opt_b.b_2 : 0.000010s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000028s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000032s : 0.02% optimize.loop_unroll : 0.000479s : 0.29% optimize.opt_after_cconv.c_1 : 0.000052s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% 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 : 0.000023s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000015s : 0.01% optimize.tuple_transform.d_1 : 0.000056s : 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 : 0.000009s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000075s : 0.05% optimize.cse_after_recomputation.cse : 0.000015s : 0.01% optimize.environ_conv : 0.000018s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000022s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000018s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000030s : 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000016s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000009s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000014s : 0.01% 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 : 0.000034s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000502s : 0.30% validate : 0.000066s : 0.04% Time group info: ------[substitution.] 0.000171 55 4.68% : 0.000008s : 2: substitution.depend_value_elim 1.58% : 0.000003s : 5: substitution.elim_not_effective 1.25% : 0.000002s : 5: substitution.fold_const_symbol 3.88% : 0.000007s : 6: substitution.graph_param_transform 62.53% : 0.000107s : 1: substitution.inline 3.24% : 0.000006s : 10: substitution.j_node_and_user_rematch 4.88% : 0.000008s : 10: substitution.remove_not_recompute_node 2.25% : 0.000004s : 2: substitution.replace_old_param 8.87% : 0.000015s : 6: substitution.updatestate_pure_node_eliminater 6.84% : 0.000012s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.159076 2 99.75% : 0.158674s : 1: type_inference.infer 0.25% : 0.000402s : 1: type_inference.specialize ------[replace.] 0.000016 1 100.00% : 0.000016s : 1: replace.inline ------[match.] 0.000106 1 100.00% : 0.000106s : 1: match.inline ------[predicate.] 0.000227 1419 0.85% : 0.000002s : 13: predicate.accumulaten_eliminater 1.13% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 12: predicate.addn_check_dump 0.79% : 0.000002s : 13: predicate.addn_zero_filter 0.78% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 2.09% : 0.000005s : 25: predicate.arithmetic_simplify 0.87% : 0.000002s : 13: predicate.cast_eliminate 0.91% : 0.000002s : 12: predicate.check_bprop_eliminate 0.68% : 0.000002s : 12: predicate.compare_switch_simplify 0.23% : 0.000001s : 6: predicate.const_output_eliminate 0.81% : 0.000002s : 12: predicate.depend_value_elim 0.81% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.85% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.87% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.30% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 6: predicate.elim_not_effective 0.53% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.09% : 0.000002s : 19: predicate.environ_get_add_eliminate 1.09% : 0.000002s : 19: predicate.environ_get_depend_swap 1.89% : 0.000004s : 31: predicate.environ_get_eliminate 1.08% : 0.000002s : 19: predicate.environ_get_set_eliminate 0.86% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.53% : 0.000003s : 14: predicate.float_depend_g_call 0.89% : 0.000002s : 12: predicate.float_environ_get_switch 1.06% : 0.000002s : 18: predicate.float_tuple_getitem_switch 0.21% : 0.000000s : 6: predicate.fold_const_symbol 0.79% : 0.000002s : 12: predicate.get_grad_eliminate 0.24% : 0.000001s : 6: predicate.graph_param_transform 0.76% : 0.000002s : 12: predicate.incorporate_call 0.68% : 0.000002s : 12: predicate.incorporate_call_switch 5.60% : 0.000013s : 63: predicate.inline 0.97% : 0.000002s : 12: predicate.inline_without_move 0.41% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.02% : 0.000002s : 12: predicate.less_batch_normalization 1.69% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.29% : 0.000005s : 38: predicate.load_eliminater 1.16% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.29% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.75% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.79% : 0.000002s : 12: predicate.merge_addn 0.89% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.81% : 0.000002s : 13: predicate.minmaximum_grad 1.32% : 0.000003s : 6: predicate.mutable_eliminate 0.45% : 0.000001s : 6: predicate.opt_reshape 0.48% : 0.000001s : 6: predicate.parallel_virtual_node 1.07% : 0.000002s : 14: predicate.partial_defer_inline 1.31% : 0.000003s : 19: predicate.partial_eliminate 0.97% : 0.000002s : 13: predicate.print_const_string_wrapper 0.83% : 0.000002s : 12: predicate.reduce_all_const_elim 1.18% : 0.000003s : 13: predicate.reduce_eliminate 2.41% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.80% : 0.000002s : 12: predicate.remove_not_recompute_node 1.13% : 0.000003s : 25: predicate.replace_applicator 0.69% : 0.000002s : 12: predicate.replace_old_param 0.41% : 0.000001s : 6: predicate.reset_defer_inline 0.87% : 0.000002s : 13: predicate.reshape_eliminate 0.82% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.44% : 0.000001s : 6: predicate.row_tensor_eliminate 0.91% : 0.000002s : 12: predicate.same_eliminate 0.58% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.87% : 0.000002s : 12: predicate.shard_identity_eliminate 1.02% : 0.000002s : 12: predicate.special_op_eliminate 0.97% : 0.000002s : 12: predicate.specialize_transform 1.15% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.47% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.87% : 0.000002s : 14: predicate.switch_defer_inline 1.65% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.47% : 0.000008s : 49: predicate.switch_simplify 0.90% : 0.000002s : 13: predicate.tile_eliminate 0.85% : 0.000002s : 13: predicate.transpose_eliminate 1.65% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.17% : 0.000007s : 37: predicate.tuple_list_get_item_eliminator 1.58% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.67% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.78% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.40% : 0.000005s : 38: predicate.updatestate_pure_node_eliminater 3.28% : 0.000007s : 50: predicate.updatestate_useless_node_eliminater 0.48% : 0.000001s : 6: predicate.value_based_eliminate 0.85% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.80% : 0.000002s : 12: predicate.virtual_output_eliminate 0.36% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.54% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000240 4 8.80% : 0.000021s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.20% : 0.000219s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.191110 192 0.00% : 0.000004s : 1: ForceFp32Comm 4.52% : 0.008640s : 1: add_attr 4.51% : 0.008621s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000079s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.10% : 0.000192s : 1: auto_monad 0.02% : 0.000038s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.30% : 0.000575s : 1: bootstrap 0.02% : 0.000035s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000021s : 1: control_data_broadcast_order 0.01% : 0.000027s : 1: convert_after_rewriter 0.01% : 0.000028s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.01% : 0.000021s : 1: environ_conv 0.01% : 0.000019s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 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 0.26% : 0.000488s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.37% : 0.000707s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000021s : 1: opt.transform.mutable_eliminate 0.60% : 0.001141s : 78: opt.transform.opt_a 0.03% : 0.000051s : 1: opt.transform.opt_after_cconv 0.02% : 0.000033s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000166s : 28: opt.transform.opt_b 0.03% : 0.000062s : 2: opt.transform.opt_trans_graph 0.03% : 0.000048s : 4: opt.transform.symbol_engine_opt 1.51% : 0.002887s : 1: opt_a 0.07% : 0.000142s : 1: opt_after_cconv 0.27% : 0.000513s : 1: opt_after_jit_grad 0.15% : 0.000288s : 1: opt_b 2.89% : 0.005517s : 1: optimize 0.01% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.02% : 0.000033s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000025s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000004s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.03% : 0.000048s : 1: pre_auto_parallel 0.01% : 0.000026s : 1: py_interpret_to_execute 0.01% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000018s : 1: remove_dup_value 0.24% : 0.000455s : 1: renormalize.infer 0.14% : 0.000270s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.08% : 0.000159s : 1: rewriter_after_opt_a 0.04% : 0.000070s : 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 0.01% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000092s : 1: symbol_engine_optimizer 0.05% : 0.000092s : 1: tuple_transform 83.28% : 0.159153s : 1: type_inference TotalTime = 0.016497, [21] [bootstrap]: 0.00050895 [type_inference]: 0.00401042 [event_method]: 1.561e-05 [auto_monad]: 0.00014352 [graph_reusing]: 6.03002e-06 [inline]: 2.64999e-06 [add_attr]: 0.00486827, [1] [add_attr_with_inline]: 0.0048547, [1] [Cycle 1]: 6.413e-05, [2] [tag_attr]: 1.724e-05 [meta_addattr_fg_expand]: 3.71999e-06 [parallel-infer-symbol]: 3.75998e-06 [pre_auto_parallel]: 3.33e-05 [insert-virtual-dataset]: 2.51998e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 2.07001e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.00609224, [53] [py_interpret_to_execute]: 2.378e-05 [rewriter_before_opt_a]: 5.702e-05 [opt_a]: 0.00311938, [2] [Cycle 1]: 0.00217464, [45] [expand_dump_flag]: 2.70002e-06 [switch_simplify]: 2.44e-05 [loop_unroll]: 1.335e-05 [a_1]: 0.00038142 [with_stream_mark]: 2.038e-05 [recompute_prepare]: 9.56e-06 [updatestate_depend_eliminate]: 6.57002e-06 [updatestate_assign_eliminate]: 5.72999e-06 [updatestate_loads_eliminate]: 6.49001e-06 [parameter_eliminate]: 2.24999e-06 [a_2]: 0.0001203 [accelerated_algorithm]: 9.53002e-06 [shard]: 2.68e-06 [meta_shard_fg_expand]: 2.01e-06 [shard_inline]: 8.80999e-06 [merge_send_recv]: 1.057e-05 [auto_parallel]: 8.67998e-06 [parallel]: 3.029e-05 [flash_sp]: 9.63002e-06 [merge_comm]: 5.53002e-06 [allreduce_fusion]: 5.29e-06 [matmul_add_comm_reduction]: 1.31e-05 [allreduce_slice_to_reducescatter]: 6.79982e-07 [virtual_shard_identity]: 1.034e-05 [virtual_dataset]: 8.57998e-06 [get_grad_eliminate_]: 8.03001e-06 [virtual_output]: 8.2e-06 [merge_forward]: 5.91e-06 [cell_reuse_recompute_pass]: 1.31002e-06 [offload_activation]: 1.698e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.83e-05 [merge_recompute_call_nodes]: 1.69998e-06 [before_grad]: 1.653e-05 [set_forward_comm_id_for_comm_node_pass]: 5.76e-06 [meta_fg_expand]: 3.76999e-06 [flash_sp_send_recv_attached]: 2.27999e-06 [receive_attached]: 2.73998e-06 [after_resolve]: 1.142e-05 [a_after_grad]: 1.258e-05 [renormalize]: 0.00091354 [add_forward_monad_depend]: 6.46e-06 [auto_monad_grad]: 2.86999e-06 [auto_monad_eliminator]: 2.361e-05 [cse]: 4.032e-05 [a_3]: 6.861e-05 [Cycle 2]: 0.00093136, [45] [expand_dump_flag]: 1.32e-06 [switch_simplify]: 1.004e-05 [loop_unroll]: 8.64e-06 [a_1]: 0.00020425 [with_stream_mark]: 1.875e-05 [recompute_prepare]: 8.63001e-06 [updatestate_depend_eliminate]: 5.93998e-06 [updatestate_assign_eliminate]: 4.99e-06 [updatestate_loads_eliminate]: 6.08002e-06 [parameter_eliminate]: 2.19001e-06 [a_2]: 0.00011406 [accelerated_algorithm]: 9.24e-06 [shard]: 2.16e-06 [meta_shard_fg_expand]: 1.94e-06 [shard_inline]: 8.40999e-06 [merge_send_recv]: 9.69e-06 [auto_parallel]: 9.41e-06 [parallel]: 7.35e-06 [flash_sp]: 4e-06 [merge_comm]: 5.27001e-06 [allreduce_fusion]: 5.35999e-06 [matmul_add_comm_reduction]: 1.015e-05 [allreduce_slice_to_reducescatter]: 5.19998e-07 [virtual_shard_identity]: 9.44998e-06 [virtual_dataset]: 8.06001e-06 [get_grad_eliminate_]: 8.77999e-06 [virtual_output]: 8.33999e-06 [merge_forward]: 5.82999e-06 [cell_reuse_recompute_pass]: 1.77001e-06 [offload_activation]: 1.262e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.847e-05 [merge_recompute_call_nodes]: 1.51002e-06 [before_grad]: 1.523e-05 [set_forward_comm_id_for_comm_node_pass]: 5.75001e-06 [meta_fg_expand]: 3.46001e-06 [flash_sp_send_recv_attached]: 1.41998e-06 [receive_attached]: 1.92001e-06 [after_resolve]: 1.226e-05 [a_after_grad]: 1.324e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.49998e-06 [auto_monad_grad]: 1.80001e-06 [auto_monad_eliminator]: 1.352e-05 [cse]: 2.403e-05 [a_3]: 4.996e-05 [py_interpret_to_execute_after_opt_a]: 1.622e-05 [slice_cell_reuse_recomputed_activation]: 2.49001e-06 [rewriter_after_opt_a]: 0.00019467 [convert_after_rewriter]: 1.156e-05 [order_py_execute_after_rewriter]: 6.71999e-06 [mutable_eliminate]: 0.00091838 [opt_b]: 0.00030982, [1] [Cycle 1]: 0.00030127, [7] [b_1]: 0.00019398 [b_2]: 1.064e-05 [updatestate_depend_eliminate]: 1.07e-05 [updatestate_assign_eliminate]: 5.94e-06 [updatestate_loads_eliminate]: 5.04e-06 [renormalize]: 3.00002e-07 [cse]: 3.199e-05 [optimize_parallel_all_gather_comm]: 2.344e-05 [overlap_param_gather]: 1.82001e-06 [cconv]: 3.722e-05 [loop_unroll]: 0.00051235 [opt_after_cconv]: 0.00014957, [1] [Cycle 1]: 0.00014117, [7] [c_1]: 5.357e-05 [parameter_eliminate]: 4.05998e-06 [updatestate_depend_eliminate]: 8.47e-06 [updatestate_assign_eliminate]: 4.65001e-06 [updatestate_loads_eliminate]: 4.38001e-06 [cse]: 2.524e-05 [renormalize]: 4.60015e-07 [remove_dup_value]: 1.789e-05 [tuple_transform]: 9.472e-05, [1] [Cycle 1]: 8.932e-05, [4] [d_1]: 5.692e-05 [none_parameter_eliminate]: 1.71002e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 9.23002e-06 [partial_unused_args_eliminate]: 1.97001e-06 [add_recomputation]: 7.751e-05 [cse_after_recomputation]: 2.761e-05, [1] [Cycle 1]: 2.273e-05, [1] [cse]: 1.686e-05 [environ_conv]: 6.71999e-06 [swap_dp_allreduce_reducescatter]: 8.35001e-06 [bias_add_comm_swap]: 3.03e-06 [label_micro_interleaved_index]: 6.02001e-06 [label_fine_grained_interleaved_index]: 2.78998e-06 [merge_cast_opt]: 1.71e-06 [slice_recompute_activation]: 2.12999e-06 [micro_interleaved_order_control]: 2.28998e-06 [assign_add_opt]: 2.29999e-06 [ForceFp32Comm]: 1.03001e-06 [remove_cast_before_assign_add]: 1.08001e-06 [full_micro_interleaved_order_control]: 2.20002e-06 [reorder_send_recv_between_fp_bp]: 2.71e-06 [comm_op_add_attrs]: 9.90025e-07 [add_comm_op_reuse_tag]: 1.14998e-06 [interleave_split_concat_branches]: 1.19998e-06 [interleave_parallel_branches]: 1.20999e-06 [overlap_opt_shard_in_pipeline]: 1.54998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.96998e-06 [control_data_broadcast_order]: 1.9e-05 [grouped_pairwise_exchange_alltoall]: 1.78002e-06 [offloading_packed_experts]: 5.47001e-06 [overlap_recompute_and_grad_model_parallel]: 6.24999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.45001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52999e-06 [overlap_recompute_comm]: 2.85002e-06 [overlap_grad_ring_attention]: 5.94e-06 [overlap_grad_flash_sp]: 2.833e-05 [begin_end_overlap_inline]: 4.59986e-07 [split_matmul_comm_elemetwise]: 2.49999e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 1.10001e-06 [symbol_engine_optimizer]: 0.00010056, [1] [Cycle 1]: 9.549e-05, [6] [build]: 5.20001e-06 [elim_shapecalc]: 1.369e-05 [elim_not_effective]: 1.702e-05 [opt_reshape]: 1.119e-05 [fold_const_symbol]: 1.417e-05 [renormalize]: 2.19996e-07 [detach_backward]: 2.07001e-06 [pipeline_parallel_scheduler]: 1.44998e-06 [auto_monad_reorder]: 2.941e-05 [get_jit_bprop_graph]: 2.11e-06 [rewriter_after_jit_bprop_graph]: 5.58002e-06 [opt_after_jit_grad]: 0.00053075 [validate]: 6.223e-05 Sums bootstrap : 0.000509s : 4.85% type_inference : 0.004010s : 38.23% event_method : 0.000016s : 0.15% auto_monad : 0.000144s : 1.37% graph_reusing : 0.000006s : 0.06% inline : 0.000003s : 0.03% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 0.16% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.04% parallel-infer-symbol : 0.000004s : 0.04% pre_auto_parallel : 0.000033s : 0.32% insert-virtual-dataset : 0.000003s : 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 : 0.000024s : 0.23% optimize.rewriter_before_opt_a : 0.000057s : 0.54% optimize.opt_a.expand_dump_flag : 0.000004s : 0.04% optimize.opt_a.switch_simplify : 0.000034s : 0.33% optimize.opt_a.loop_unroll : 0.000022s : 0.21% optimize.opt_a.a_1 : 0.000586s : 5.58% optimize.opt_a.with_stream_mark : 0.000039s : 0.37% optimize.opt_a.recompute_prepare : 0.000018s : 0.17% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.12% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.10% optimize.opt_a.updatestate_loads_eliminate : 0.000013s : 0.12% optimize.opt_a.parameter_eliminate : 0.000004s : 0.04% optimize.opt_a.a_2 : 0.000234s : 2.23% optimize.opt_a.accelerated_algorithm : 0.000019s : 0.18% optimize.opt_a.shard : 0.000005s : 0.05% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.04% optimize.opt_a.shard_inline : 0.000017s : 0.16% optimize.opt_a.merge_send_recv : 0.000020s : 0.19% optimize.opt_a.auto_parallel : 0.000018s : 0.17% optimize.opt_a.parallel : 0.000038s : 0.36% optimize.opt_a.flash_sp : 0.000014s : 0.13% optimize.opt_a.merge_comm : 0.000011s : 0.10% optimize.opt_a.allreduce_fusion : 0.000011s : 0.10% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.22% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000020s : 0.19% optimize.opt_a.virtual_dataset : 0.000017s : 0.16% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.16% optimize.opt_a.virtual_output : 0.000017s : 0.16% optimize.opt_a.merge_forward : 0.000012s : 0.11% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.03% optimize.opt_a.offload_activation : 0.000030s : 0.28% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000037s : 0.35% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.03% optimize.opt_a.before_grad : 0.000032s : 0.30% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.11% optimize.opt_a.meta_fg_expand : 0.000007s : 0.07% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.04% optimize.opt_a.receive_attached : 0.000005s : 0.04% optimize.opt_a.after_resolve : 0.000024s : 0.23% optimize.opt_a.a_after_grad : 0.000026s : 0.25% optimize.opt_a.renormalize : 0.000914s : 8.71% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.08% optimize.opt_a.auto_monad_grad : 0.000005s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000037s : 0.35% optimize.opt_a.cse : 0.000064s : 0.61% optimize.opt_a.a_3 : 0.000119s : 1.13% optimize.py_interpret_to_execute_after_opt_a : 0.000016s : 0.15% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.02% optimize.rewriter_after_opt_a : 0.000195s : 1.86% optimize.convert_after_rewriter : 0.000012s : 0.11% optimize.order_py_execute_after_rewriter : 0.000007s : 0.06% optimize.mutable_eliminate : 0.000918s : 8.75% optimize.opt_b.b_1 : 0.000194s : 1.85% optimize.opt_b.b_2 : 0.000011s : 0.10% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.10% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.06% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.05% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000032s : 0.30% optimize.optimize_parallel_all_gather_comm : 0.000023s : 0.22% optimize.overlap_param_gather : 0.000002s : 0.02% optimize.cconv : 0.000037s : 0.35% optimize.loop_unroll : 0.000512s : 4.88% optimize.opt_after_cconv.c_1 : 0.000054s : 0.51% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.08% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.04% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.cse : 0.000025s : 0.24% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000018s : 0.17% optimize.tuple_transform.d_1 : 0.000057s : 0.54% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.02% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.09% optimize.partial_unused_args_eliminate : 0.000002s : 0.02% optimize.add_recomputation : 0.000078s : 0.74% optimize.cse_after_recomputation.cse : 0.000017s : 0.16% optimize.environ_conv : 0.000007s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.08% optimize.bias_add_comm_swap : 0.000003s : 0.03% optimize.label_micro_interleaved_index : 0.000006s : 0.06% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.03% optimize.merge_cast_opt : 0.000002s : 0.02% optimize.slice_recompute_activation : 0.000002s : 0.02% optimize.micro_interleaved_order_control : 0.000002s : 0.02% optimize.assign_add_opt : 0.000002s : 0.02% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000002s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.03% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.02% optimize.control_data_broadcast_order : 0.000019s : 0.18% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.02% optimize.offloading_packed_experts : 0.000005s : 0.05% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.06% 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 : 0.03% optimize.overlap_grad_ring_attention : 0.000006s : 0.06% optimize.overlap_grad_flash_sp : 0.000028s : 0.27% optimize.begin_end_overlap_inline : 0.000000s : 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 : 0.000005s : 0.05% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000014s : 0.13% optimize.symbol_engine_optimizer.elim_not_effective : 0.000017s : 0.16% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.11% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000014s : 0.14% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000001s : 0.01% auto_monad_reorder : 0.000029s : 0.28% get_jit_bprop_graph : 0.000002s : 0.02% rewriter_after_jit_bprop_graph : 0.000006s : 0.05% opt_after_jit_grad : 0.000531s : 5.06% validate : 0.000062s : 0.59% Time group info: ------[substitution.] 0.000172 55 5.01% : 0.000009s : 2: substitution.depend_value_elim 1.57% : 0.000003s : 5: substitution.elim_not_effective 1.15% : 0.000002s : 5: substitution.fold_const_symbol 4.39% : 0.000008s : 6: substitution.graph_param_transform 60.67% : 0.000104s : 1: substitution.inline 2.94% : 0.000005s : 10: substitution.j_node_and_user_rematch 4.72% : 0.000008s : 10: substitution.remove_not_recompute_node 2.09% : 0.000004s : 2: substitution.replace_old_param 10.12% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 7.34% : 0.000013s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.003954 2 88.36% : 0.003494s : 1: type_inference.infer 11.64% : 0.000460s : 1: type_inference.specialize ------[replace.] 0.000016 1 100.00% : 0.000016s : 1: replace.inline ------[match.] 0.000103 1 100.00% : 0.000103s : 1: match.inline ------[predicate.] 0.000234 1419 1.03% : 0.000002s : 13: predicate.accumulaten_eliminater 1.06% : 0.000002s : 6: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 12: predicate.addn_check_dump 0.83% : 0.000002s : 13: predicate.addn_zero_filter 0.76% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 2.01% : 0.000005s : 25: predicate.arithmetic_simplify 0.89% : 0.000002s : 13: predicate.cast_eliminate 0.77% : 0.000002s : 12: predicate.check_bprop_eliminate 0.74% : 0.000002s : 12: predicate.compare_switch_simplify 0.21% : 0.000000s : 6: predicate.const_output_eliminate 0.95% : 0.000002s : 12: predicate.depend_value_elim 0.89% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.99% : 0.000002s : 13: predicate.dict_get_item_eliminator 1.01% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.15% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 6: predicate.elim_not_effective 0.51% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.08% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.04% : 0.000002s : 19: predicate.environ_get_depend_swap 1.93% : 0.000005s : 31: predicate.environ_get_eliminate 1.09% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.83% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.46% : 0.000003s : 14: predicate.float_depend_g_call 0.72% : 0.000002s : 12: predicate.float_environ_get_switch 1.10% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.21% : 0.000000s : 6: predicate.fold_const_symbol 0.98% : 0.000002s : 12: predicate.get_grad_eliminate 0.35% : 0.000001s : 6: predicate.graph_param_transform 0.73% : 0.000002s : 12: predicate.incorporate_call 0.64% : 0.000002s : 12: predicate.incorporate_call_switch 5.50% : 0.000013s : 63: predicate.inline 1.01% : 0.000002s : 12: predicate.inline_without_move 0.40% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.92% : 0.000002s : 12: predicate.less_batch_normalization 1.67% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.33% : 0.000005s : 38: predicate.load_eliminater 1.18% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.17% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.74% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.71% : 0.000002s : 12: predicate.merge_addn 0.78% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.76% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.78% : 0.000002s : 13: predicate.minmaximum_grad 1.87% : 0.000004s : 6: predicate.mutable_eliminate 0.64% : 0.000001s : 6: predicate.opt_reshape 0.55% : 0.000001s : 6: predicate.parallel_virtual_node 1.05% : 0.000002s : 14: predicate.partial_defer_inline 1.25% : 0.000003s : 19: predicate.partial_eliminate 0.84% : 0.000002s : 13: predicate.print_const_string_wrapper 0.75% : 0.000002s : 12: predicate.reduce_all_const_elim 1.02% : 0.000002s : 13: predicate.reduce_eliminate 2.36% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.60% : 0.000001s : 12: predicate.remove_not_recompute_node 1.11% : 0.000003s : 25: predicate.replace_applicator 0.65% : 0.000002s : 12: predicate.replace_old_param 0.30% : 0.000001s : 6: predicate.reset_defer_inline 0.83% : 0.000002s : 13: predicate.reshape_eliminate 0.82% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.52% : 0.000001s : 6: predicate.row_tensor_eliminate 0.95% : 0.000002s : 12: predicate.same_eliminate 0.45% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.87% : 0.000002s : 12: predicate.shard_identity_eliminate 1.02% : 0.000002s : 12: predicate.special_op_eliminate 0.82% : 0.000002s : 12: predicate.specialize_transform 1.35% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.51% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.96% : 0.000002s : 14: predicate.switch_defer_inline 1.65% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.59% : 0.000008s : 49: predicate.switch_simplify 1.16% : 0.000003s : 13: predicate.tile_eliminate 0.79% : 0.000002s : 13: predicate.transpose_eliminate 1.67% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.51% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.10% : 0.000007s : 37: predicate.tuple_list_get_item_eliminator 1.66% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.56% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.68% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.37% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.30% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.51% : 0.000001s : 6: predicate.value_based_eliminate 0.80% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.83% : 0.000002s : 12: predicate.virtual_output_eliminate 0.36% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.60% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000306 4 7.42% : 0.000023s : 1: func_graph_cloner_run.FuncGraphClonerGraph 92.58% : 0.000283s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.029781 192 0.01% : 0.000004s : 1: ForceFp32Comm 16.37% : 0.004875s : 1: add_attr 16.32% : 0.004860s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.28% : 0.000082s : 1: add_recomputation 0.02% : 0.000005s : 1: assign_add_opt 0.51% : 0.000151s : 1: auto_monad 0.11% : 0.000033s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.02% : 0.000006s : 1: bias_add_comm_swap 1.81% : 0.000540s : 1: bootstrap 0.14% : 0.000041s : 1: cconv 0.02% : 0.000005s : 1: comm_op_add_attrs 0.08% : 0.000022s : 1: control_data_broadcast_order 0.05% : 0.000016s : 1: convert_after_rewriter 0.10% : 0.000031s : 1: cse_after_recomputation 0.02% : 0.000005s : 1: dataset_repeat_opt 0.02% : 0.000005s : 1: detach_backward 0.03% : 0.000010s : 1: environ_conv 0.08% : 0.000023s : 1: event_method 0.02% : 0.000005s : 1: full_micro_interleaved_order_control 0.02% : 0.000005s : 1: get_jit_bprop_graph 0.03% : 0.000010s : 1: graph_reusing 0.02% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.02% : 0.000005s : 1: handle_group_info 0.02% : 0.000006s : 1: inline 0.02% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.02% : 0.000006s : 1: interleave_split_concat_branches 0.02% : 0.000006s : 1: label_fine_grained_interleaved_index 0.03% : 0.000010s : 1: label_micro_interleaved_index 1.76% : 0.000523s : 1: loop_unroll 0.02% : 0.000006s : 1: merge_cast_opt 0.02% : 0.000005s : 1: micro_interleaved_order_control 3.13% : 0.000931s : 1: mutable_eliminate 0.03% : 0.000010s : 1: offloading_packed_experts 0.06% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.09% : 0.000026s : 1: opt.transform.mutable_eliminate 3.86% : 0.001151s : 78: opt.transform.opt_a 0.17% : 0.000052s : 1: opt.transform.opt_after_cconv 0.11% : 0.000032s : 1: opt.transform.opt_after_jit_grad 0.58% : 0.000174s : 28: opt.transform.opt_b 0.22% : 0.000064s : 2: opt.transform.opt_trans_graph 0.18% : 0.000052s : 4: opt.transform.symbol_engine_opt 10.49% : 0.003124s : 1: opt_a 0.52% : 0.000154s : 1: opt_after_cconv 1.82% : 0.000541s : 1: opt_after_jit_grad 1.06% : 0.000314s : 1: opt_b 20.48% : 0.006098s : 1: optimize 0.09% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.04% : 0.000011s : 1: order_py_execute_after_rewriter 0.11% : 0.000032s : 1: overlap_grad_flash_sp 0.01% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.03% : 0.000009s : 1: overlap_grad_ring_attention 0.02% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.02% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.02% : 0.000005s : 1: overlap_param_gather 0.02% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.03% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.02% : 0.000006s : 1: overlap_recompute_comm 0.03% : 0.000008s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.02% : 0.000005s : 1: partial_unused_args_eliminate 0.02% : 0.000005s : 1: pipeline_parallel_scheduler 0.02% : 0.000005s : 1: pipeline_split 0.12% : 0.000037s : 1: pre_auto_parallel 0.09% : 0.000028s : 1: py_interpret_to_execute 0.07% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.08% : 0.000023s : 1: remove_dup_value 1.79% : 0.000533s : 1: renormalize.infer 1.25% : 0.000372s : 1: renormalize.specialize 0.02% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.03% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.68% : 0.000202s : 1: rewriter_after_opt_a 0.21% : 0.000062s : 1: rewriter_before_opt_a 0.02% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.02% : 0.000005s : 1: slice_recompute_activation 0.02% : 0.000005s : 1: split_layernorm_comm 0.02% : 0.000006s : 1: split_matmul_comm_elemetwise 0.04% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.35% : 0.000104s : 1: symbol_engine_optimizer 0.33% : 0.000098s : 1: tuple_transform 13.54% : 0.004032s : 1: type_inference TotalTime = 0.950814, [21] [bootstrap]: 0.00051149 [type_inference]: 0.203734 [event_method]: 7.434e-05 [auto_monad]: 0.00031594 [graph_reusing]: 1.059e-05 [inline]: 3.01001e-06 [add_attr]: 0.004293, [1] [add_attr_with_inline]: 0.00427775, [1] [Cycle 1]: 0.00011461, [2] [tag_attr]: 5.065e-05 [meta_addattr_fg_expand]: 9.47001e-06 [parallel-infer-symbol]: 4.28001e-06 [pre_auto_parallel]: 6.906e-05 [insert-virtual-dataset]: 2.32999e-06 [parallel-infer-symbol-second]: 6.59988e-07 [dataset_repeat_opt]: 2.02001e-06 [pipeline_split]: 1.94999e-06 [optimize]: 0.740481, [53] [py_interpret_to_execute]: 5.599e-05 [rewriter_before_opt_a]: 0.00018004 [opt_a]: 0.582475, [3] [Cycle 1]: 0.5743, [45] [expand_dump_flag]: 9.45001e-06 [switch_simplify]: 7.763e-05 [loop_unroll]: 7.307e-05 [a_1]: 0.194417 [with_stream_mark]: 6.515e-05 [recompute_prepare]: 4.915e-05 [updatestate_depend_eliminate]: 1.525e-05 [updatestate_assign_eliminate]: 1.258e-05 [updatestate_loads_eliminate]: 1.193e-05 [parameter_eliminate]: 4.51002e-06 [a_2]: 0.00034731 [accelerated_algorithm]: 4.882e-05 [shard]: 2.40002e-06 [meta_shard_fg_expand]: 1.11e-05 [shard_inline]: 2.035e-05 [merge_send_recv]: 2.725e-05 [auto_parallel]: 2.068e-05 [parallel]: 2.562e-05 [flash_sp]: 1.957e-05 [merge_comm]: 1.51e-05 [allreduce_fusion]: 1.269e-05 [matmul_add_comm_reduction]: 4.688e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 2.806e-05 [virtual_dataset]: 2.457e-05 [get_grad_eliminate_]: 2.281e-05 [virtual_output]: 2.326e-05 [merge_forward]: 1.544e-05 [cell_reuse_recompute_pass]: 1.80001e-06 [offload_activation]: 3.01e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.017e-05 [merge_recompute_call_nodes]: 1.90001e-06 [before_grad]: 4.465e-05 [set_forward_comm_id_for_comm_node_pass]: 1.571e-05 [meta_fg_expand]: 0.150972 [flash_sp_send_recv_attached]: 7.13998e-06 [receive_attached]: 3.59002e-06 [after_resolve]: 0.00016121 [a_after_grad]: 0.00022264 [renormalize]: 0.224493 [add_forward_monad_depend]: 2.842e-05 [auto_monad_grad]: 1.785e-05 [auto_monad_eliminator]: 0.00016364 [cse]: 0.00035643 [a_3]: 0.00176708 [Cycle 2]: 0.0069463, [45] [expand_dump_flag]: 6.22001e-06 [switch_simplify]: 0.00012062 [loop_unroll]: 0.00010573 [a_1]: 0.00312942 [with_stream_mark]: 3.868e-05 [recompute_prepare]: 2.437e-05 [updatestate_depend_eliminate]: 4.048e-05 [updatestate_assign_eliminate]: 7.41999e-06 [updatestate_loads_eliminate]: 6.36998e-06 [parameter_eliminate]: 3.11001e-06 [a_2]: 0.00019958 [accelerated_algorithm]: 1.998e-05 [shard]: 2.67001e-06 [meta_shard_fg_expand]: 7.77e-06 [shard_inline]: 1.146e-05 [merge_send_recv]: 1.344e-05 [auto_parallel]: 1.417e-05 [parallel]: 1.168e-05 [flash_sp]: 4.79998e-06 [merge_comm]: 6.74999e-06 [allreduce_fusion]: 6.59001e-06 [matmul_add_comm_reduction]: 1.437e-05 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 1.588e-05 [virtual_dataset]: 1.143e-05 [get_grad_eliminate_]: 1.118e-05 [virtual_output]: 1.079e-05 [merge_forward]: 7.39002e-06 [cell_reuse_recompute_pass]: 2.32001e-06 [offload_activation]: 1.707e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.6e-05 [merge_recompute_call_nodes]: 1.97999e-06 [before_grad]: 2.051e-05 [set_forward_comm_id_for_comm_node_pass]: 7.25e-06 [meta_fg_expand]: 0.00010233 [flash_sp_send_recv_attached]: 1.97001e-06 [receive_attached]: 2.78e-06 [after_resolve]: 2.05e-05 [a_after_grad]: 1.907e-05 [renormalize]: 0.00227858 [add_forward_monad_depend]: 1.019e-05 [auto_monad_grad]: 2.94999e-06 [auto_monad_eliminator]: 3.296e-05 [cse]: 0.0001224 [a_3]: 9.592e-05 [Cycle 3]: 0.00120446, [45] [expand_dump_flag]: 2.91e-06 [switch_simplify]: 1.331e-05 [loop_unroll]: 1.128e-05 [a_1]: 0.00030546 [with_stream_mark]: 2.001e-05 [recompute_prepare]: 1.143e-05 [updatestate_depend_eliminate]: 8.42998e-06 [updatestate_assign_eliminate]: 6.26e-06 [updatestate_loads_eliminate]: 5.80002e-06 [parameter_eliminate]: 1.73002e-06 [a_2]: 0.00017705 [accelerated_algorithm]: 1.823e-05 [shard]: 1.89e-06 [meta_shard_fg_expand]: 3.95e-06 [shard_inline]: 1.222e-05 [merge_send_recv]: 1.329e-05 [auto_parallel]: 1.215e-05 [parallel]: 1.004e-05 [flash_sp]: 1.20001e-06 [merge_comm]: 3.226e-05 [allreduce_fusion]: 6.38998e-06 [matmul_add_comm_reduction]: 1.309e-05 [allreduce_slice_to_reducescatter]: 6.90023e-07 [virtual_shard_identity]: 1.438e-05 [virtual_dataset]: 1.196e-05 [get_grad_eliminate_]: 1.036e-05 [virtual_output]: 1.071e-05 [merge_forward]: 6.30002e-06 [cell_reuse_recompute_pass]: 2.84999e-06 [offload_activation]: 1.446e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.319e-05 [merge_recompute_call_nodes]: 1.17999e-06 [before_grad]: 1.899e-05 [set_forward_comm_id_for_comm_node_pass]: 8.67e-06 [meta_fg_expand]: 4.52e-06 [flash_sp_send_recv_attached]: 1.60001e-06 [receive_attached]: 1.97999e-06 [after_resolve]: 1.757e-05 [a_after_grad]: 1.8e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.34001e-06 [auto_monad_grad]: 1.79998e-06 [auto_monad_eliminator]: 1.854e-05 [cse]: 3.328e-05 [a_3]: 6.825e-05 [py_interpret_to_execute_after_opt_a]: 2.201e-05 [slice_cell_reuse_recomputed_activation]: 2.09e-06 [rewriter_after_opt_a]: 8.057e-05 [convert_after_rewriter]: 1.167e-05 [order_py_execute_after_rewriter]: 8.69e-06 [mutable_eliminate]: 0.00087168 [opt_b]: 0.00040194, [1] [Cycle 1]: 0.00039211, [7] [b_1]: 0.00025316 [b_2]: 1.342e-05 [updatestate_depend_eliminate]: 1.321e-05 [updatestate_assign_eliminate]: 6.36e-06 [updatestate_loads_eliminate]: 5.85002e-06 [renormalize]: 4.69998e-07 [cse]: 5.226e-05 [optimize_parallel_all_gather_comm]: 5.749e-05 [overlap_param_gather]: 2.37001e-06 [cconv]: 3.49e-05 [loop_unroll]: 0.00060327 [opt_after_cconv]: 0.00020275, [1] [Cycle 1]: 0.00019483, [7] [c_1]: 7.508e-05 [parameter_eliminate]: 4.75999e-06 [updatestate_depend_eliminate]: 1.02e-05 [updatestate_assign_eliminate]: 5.91e-06 [updatestate_loads_eliminate]: 5.74999e-06 [cse]: 4.805e-05 [renormalize]: 9.50007e-07 [remove_dup_value]: 2.16e-05 [tuple_transform]: 0.154483, [1] [Cycle 1]: 0.15445, [4] [d_1]: 8.549e-05 [none_parameter_eliminate]: 1.86003e-06 [renormalize]: 3.20026e-07 [switch_simplify]: 1.232e-05 [partial_unused_args_eliminate]: 1.013e-05 [add_recomputation]: 0.00017489 [cse_after_recomputation]: 0.00011027, [1] [Cycle 1]: 9.895e-05, [1] [cse]: 8.019e-05 [environ_conv]: 1.91e-05 [swap_dp_allreduce_reducescatter]: 1.162e-05 [bias_add_comm_swap]: 4.19002e-06 [label_micro_interleaved_index]: 9.31e-06 [label_fine_grained_interleaved_index]: 2.84001e-06 [merge_cast_opt]: 1.84e-06 [slice_recompute_activation]: 2.61999e-06 [micro_interleaved_order_control]: 2.57001e-06 [assign_add_opt]: 1.89e-06 [ForceFp32Comm]: 9.89996e-07 [remove_cast_before_assign_add]: 1.52999e-06 [full_micro_interleaved_order_control]: 2.82002e-06 [reorder_send_recv_between_fp_bp]: 3.59002e-06 [comm_op_add_attrs]: 1.19e-06 [add_comm_op_reuse_tag]: 1.19998e-06 [interleave_split_concat_branches]: 1.47001e-06 [interleave_parallel_branches]: 1.54e-06 [overlap_opt_shard_in_pipeline]: 1.28002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.67999e-06 [control_data_broadcast_order]: 2.819e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 6.79999e-06 [overlap_recompute_and_grad_model_parallel]: 7.31999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.54e-06 [overlap_recompute_allgather_and_fa_grad]: 1.59e-06 [overlap_recompute_comm]: 2.62001e-06 [overlap_grad_ring_attention]: 7.21001e-06 [overlap_grad_flash_sp]: 3.965e-05 [begin_end_overlap_inline]: 7.30011e-07 [split_matmul_comm_elemetwise]: 2.12999e-06 [split_layernorm_comm]: 1.72001e-06 [handle_group_info]: 1.02998e-06 [symbol_engine_optimizer]: 0.00019643, [1] [Cycle 1]: 0.00018958, [6] [build]: 3.392e-05 [elim_shapecalc]: 3.751e-05 [elim_not_effective]: 3.702e-05 [opt_reshape]: 1.466e-05 [fold_const_symbol]: 2.195e-05 [renormalize]: 3.59985e-07 [detach_backward]: 2.58e-06 [pipeline_parallel_scheduler]: 1.70001e-06 [auto_monad_reorder]: 4.554e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 9.36998e-06 [opt_after_jit_grad]: 0.00096278 [validate]: 8.341e-05 Sums bootstrap : 0.000511s : 0.06% type_inference : 0.203734s : 25.78% event_method : 0.000074s : 0.01% auto_monad : 0.000316s : 0.04% graph_reusing : 0.000011s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000051s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000069s : 0.01% insert-virtual-dataset : 0.000002s : 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 : 0.000056s : 0.01% optimize.rewriter_before_opt_a : 0.000180s : 0.02% optimize.opt_a.expand_dump_flag : 0.000019s : 0.00% optimize.opt_a.switch_simplify : 0.000212s : 0.03% optimize.opt_a.loop_unroll : 0.000190s : 0.02% optimize.opt_a.a_1 : 0.197851s : 25.03% optimize.opt_a.with_stream_mark : 0.000124s : 0.02% optimize.opt_a.recompute_prepare : 0.000085s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000064s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000026s : 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 : 0.000724s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000087s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000023s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.01% optimize.opt_a.merge_send_recv : 0.000054s : 0.01% optimize.opt_a.auto_parallel : 0.000047s : 0.01% optimize.opt_a.parallel : 0.000047s : 0.01% optimize.opt_a.flash_sp : 0.000026s : 0.00% optimize.opt_a.merge_comm : 0.000054s : 0.01% optimize.opt_a.allreduce_fusion : 0.000026s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000074s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000058s : 0.01% optimize.opt_a.virtual_dataset : 0.000048s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000044s : 0.01% optimize.opt_a.virtual_output : 0.000045s : 0.01% optimize.opt_a.merge_forward : 0.000029s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000062s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000099s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000084s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000032s : 0.00% optimize.opt_a.meta_fg_expand : 0.151079s : 19.11% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.00% optimize.opt_a.after_resolve : 0.000199s : 0.03% optimize.opt_a.a_after_grad : 0.000260s : 0.03% optimize.opt_a.renormalize : 0.226772s : 28.69% optimize.opt_a.add_forward_monad_depend : 0.000041s : 0.01% optimize.opt_a.auto_monad_grad : 0.000023s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000215s : 0.03% optimize.opt_a.cse : 0.000512s : 0.06% optimize.opt_a.a_3 : 0.001931s : 0.24% 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 : 0.000081s : 0.01% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000872s : 0.11% optimize.opt_b.b_1 : 0.000253s : 0.03% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000052s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000057s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000603s : 0.08% optimize.opt_after_cconv.c_1 : 0.000075s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000048s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.00% optimize.tuple_transform.d_1 : 0.000085s : 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 : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000010s : 0.00% optimize.add_recomputation : 0.000175s : 0.02% optimize.cse_after_recomputation.cse : 0.000080s : 0.01% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 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 : 0.000007s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000040s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000034s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000046s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000963s : 0.12% validate : 0.000083s : 0.01% Time group info: ------[substitution.] 0.002845 310 0.64% : 0.000018s : 4: substitution.depend_value_elim 0.15% : 0.000004s : 7: substitution.elim_not_effective 0.32% : 0.000009s : 7: substitution.float_depend_g_call 0.17% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000003s : 7: substitution.fold_const_symbol 30.70% : 0.000873s : 4: substitution.getattr_setattr_resolve 0.32% : 0.000009s : 9: substitution.graph_param_transform 0.14% : 0.000004s : 2: substitution.incorporate_call 0.08% : 0.000002s : 2: substitution.incorporate_call_switch 44.95% : 0.001279s : 24: substitution.inline 1.93% : 0.000055s : 5: substitution.inline_without_move 0.54% : 0.000015s : 28: substitution.j_node_and_user_rematch 0.83% : 0.000023s : 3: substitution.less_batch_normalization 0.65% : 0.000019s : 9: substitution.minmaximum_grad 0.44% : 0.000012s : 7: substitution.partial_eliminate 0.69% : 0.000020s : 28: substitution.remove_not_recompute_node 4.26% : 0.000121s : 38: substitution.replace_applicator 0.69% : 0.000020s : 19: substitution.replace_old_param 0.23% : 0.000007s : 1: substitution.set_cell_output_no_recompute 1.37% : 0.000039s : 9: substitution.tuple_list_convert_item_index_to_positive 0.58% : 0.000016s : 9: substitution.tuple_list_get_item_const_eliminator 0.85% : 0.000024s : 9: substitution.tuple_list_get_item_depend_reorder 5.29% : 0.000150s : 31: substitution.tuple_list_get_item_eliminator 0.84% : 0.000024s : 9: substitution.tuple_list_get_set_item_eliminator 1.41% : 0.000040s : 16: substitution.updatestate_pure_node_eliminater 1.86% : 0.000053s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.203625 2 98.96% : 0.201518s : 1: type_inference.infer 1.04% : 0.002108s : 1: type_inference.specialize ------[replace.] 0.000641 49 10.93% : 0.000070s : 3: replace.getattr_setattr_resolve 44.65% : 0.000286s : 24: replace.inline 9.86% : 0.000063s : 1: replace.replace_applicator 32.60% : 0.000209s : 20: replace.tuple_list_get_item_eliminator 1.97% : 0.000013s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002185 49 37.66% : 0.000823s : 3: match.getattr_setattr_resolve 57.56% : 0.001258s : 24: match.inline 0.96% : 0.000021s : 1: match.replace_applicator 2.97% : 0.000065s : 20: match.tuple_list_get_item_eliminator 0.85% : 0.000019s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001368 8683 0.93% : 0.000013s : 85: predicate.accumulaten_eliminater 0.43% : 0.000006s : 9: predicate.ad_related_special_op_eliminate 0.38% : 0.000005s : 37: predicate.addn_check_dump 0.84% : 0.000012s : 85: predicate.addn_zero_filter 0.79% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 1.70% : 0.000023s : 122: predicate.arithmetic_simplify 0.89% : 0.000012s : 85: predicate.cast_eliminate 2.59% : 0.000035s : 260: predicate.check_bprop_eliminate 0.36% : 0.000005s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.41% : 0.000006s : 37: predicate.depend_value_elim 0.86% : 0.000012s : 85: predicate.dict_get_item_const_eliminator 0.93% : 0.000013s : 85: predicate.dict_get_item_eliminator 0.87% : 0.000012s : 85: predicate.dict_set_item_eliminator 0.41% : 0.000006s : 18: predicate.dumpgradient_eliminate 0.10% : 0.000001s : 9: predicate.elim_not_effective 0.17% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 0.96% : 0.000013s : 94: predicate.environ_add_const_eliminate 0.91% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.92% : 0.000013s : 94: predicate.environ_get_depend_swap 1.36% : 0.000019s : 131: predicate.environ_get_eliminate 0.90% : 0.000012s : 94: predicate.environ_get_set_eliminate 1.32% : 0.000018s : 130: predicate.exchange_switch_depend_value 2.08% : 0.000029s : 130: predicate.float_depend_g_call 0.39% : 0.000005s : 37: predicate.float_environ_get_switch 0.49% : 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 0.51% : 0.000007s : 20: predicate.getattr_setattr_resolve 0.07% : 0.000001s : 9: predicate.graph_param_transform 0.40% : 0.000005s : 37: predicate.incorporate_call 0.36% : 0.000005s : 37: predicate.incorporate_call_switch 4.51% : 0.000062s : 307: predicate.inline 1.58% : 0.000022s : 111: predicate.inline_without_move 0.19% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.56% : 0.000008s : 37: predicate.less_batch_normalization 1.40% : 0.000019s : 123: predicate.list_to_tuple_eliminator_ 2.01% : 0.000027s : 208: predicate.load_eliminater 0.30% : 0.000004s : 9: predicate.loop_unroll_after_grad 2.13% : 0.000029s : 197: predicate.loop_unroll_before_grad 1.07% : 0.000015s : 103: predicate.make_slice_get_slice_eliminator 0.38% : 0.000005s : 37: predicate.merge_addn 2.51% : 0.000034s : 256: predicate.micro_step_allgather_replace 6.98% : 0.000096s : 256: predicate.mini_step_allgather_replace 0.81% : 0.000011s : 85: predicate.minmaximum_grad 0.33% : 0.000005s : 9: predicate.mutable_eliminate 0.12% : 0.000002s : 9: predicate.opt_reshape 0.12% : 0.000002s : 9: predicate.parallel_virtual_node 2.41% : 0.000033s : 130: predicate.partial_defer_inline 1.24% : 0.000017s : 114: predicate.partial_eliminate 0.83% : 0.000011s : 85: predicate.print_const_string_wrapper 0.40% : 0.000005s : 37: predicate.reduce_all_const_elim 1.06% : 0.000014s : 85: predicate.reduce_eliminate 2.06% : 0.000028s : 208: predicate.redundant_stop_gradient_eliminater 0.29% : 0.000004s : 37: predicate.remove_not_recompute_node 2.35% : 0.000032s : 363: predicate.replace_applicator 0.72% : 0.000010s : 111: predicate.replace_old_param 0.09% : 0.000001s : 9: predicate.reset_defer_inline 0.88% : 0.000012s : 85: predicate.reshape_eliminate 2.65% : 0.000036s : 256: predicate.row_tensor_add_zeros_like 0.13% : 0.000002s : 9: predicate.row_tensor_eliminate 2.65% : 0.000036s : 260: predicate.same_eliminate 0.28% : 0.000004s : 39: predicate.set_cell_output_no_recompute 0.54% : 0.000007s : 37: predicate.shard_identity_eliminate 0.26% : 0.000004s : 18: predicate.special_op_eliminate 0.45% : 0.000006s : 37: predicate.specialize_transform 2.76% : 0.000038s : 256: predicate.split_environ_get_set_with_tuple_value 1.39% : 0.000019s : 111: predicate.stack_unstack_eliminate 0.12% : 0.000002s : 9: predicate.switch_call_monad_eliminater 1.46% : 0.000020s : 130: predicate.switch_defer_inline 4.01% : 0.000055s : 390: predicate.switch_layer_defer_inline 4.33% : 0.000059s : 373: predicate.switch_simplify 0.86% : 0.000012s : 85: predicate.tile_eliminate 0.84% : 0.000011s : 85: predicate.transpose_eliminate 1.16% : 0.000016s : 103: predicate.tuple_list_convert_item_index_to_positive 1.20% : 0.000016s : 103: predicate.tuple_list_get_item_const_eliminator 1.04% : 0.000014s : 103: predicate.tuple_list_get_item_depend_reorder 2.61% : 0.000036s : 160: predicate.tuple_list_get_item_eliminator 1.29% : 0.000018s : 103: predicate.tuple_list_get_set_item_eliminator 1.63% : 0.000022s : 140: predicate.tuple_list_set_item_eliminator 1.31% : 0.000018s : 123: predicate.tuple_to_list_eliminator_ 1.99% : 0.000027s : 208: predicate.updatestate_pure_node_eliminater 2.66% : 0.000036s : 246: predicate.updatestate_useless_node_eliminater 0.11% : 0.000001s : 9: predicate.value_based_eliminate 0.44% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.40% : 0.000006s : 37: predicate.virtual_output_eliminate 0.10% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.12% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004678 53 53.82% : 0.002518s : 23: func_graph_cloner_run.FuncGraphClonerGraph 46.18% : 0.002160s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.125471 243 0.00% : 0.000004s : 1: ForceFp32Comm 0.20% : 0.004301s : 1: add_attr 0.20% : 0.004283s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000183s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000328s : 1: auto_monad 0.00% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000544s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000015s : 1: convert_after_rewriter 0.01% : 0.000115s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.00% : 0.000085s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000015s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000013s : 1: label_micro_interleaved_index 0.03% : 0.000614s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000884s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 9.49% : 0.201730s : 125: opt.transform.opt_a 0.00% : 0.000074s : 1: opt.transform.opt_after_cconv 0.00% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000233s : 28: opt.transform.opt_b 0.05% : 0.001015s : 2: opt.transform.opt_resolve 0.00% : 0.000095s : 2: opt.transform.opt_trans_graph 0.00% : 0.000104s : 4: opt.transform.symbol_engine_opt 27.40% : 0.582479s : 1: opt_a 0.01% : 0.000207s : 1: opt_after_cconv 0.05% : 0.000979s : 1: opt_after_jit_grad 0.02% : 0.000406s : 1: opt_b 34.84% : 0.740488s : 1: optimize 0.00% : 0.000064s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.00% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 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% : 0.000004s : 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% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000019s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000076s : 1: pre_auto_parallel 0.00% : 0.000061s : 1: py_interpret_to_execute 0.00% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000025s : 1: remove_dup_value 0.49% : 0.010341s : 2: renormalize.infer 10.18% : 0.216394s : 2: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000086s : 1: rewriter_after_opt_a 0.01% : 0.000187s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000200s : 1: symbol_engine_optimizer 7.27% : 0.154492s : 1: tuple_transform 9.59% : 0.203760s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__single_element[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__single_element[0],max_mem:4.0M [WARNING] ME(165587:281472958316336,MainProcess):2026-01-29-17:40:25.680.775 [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__single_element[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__single_element[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 214.76s (0:03:34) ==================