==================================================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_006/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 2 items test_sigmoid_.py [WARNING] ME(169876:281473380167472,MainProcess):2026-01-29-17:39:50.978.465 [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 = 0.548349, [21] [bootstrap]: 0.00696392 [type_inference]: 0.206617 [event_method]: 1.914e-05 [auto_monad]: 0.0168312 [graph_reusing]: 7.56001e-06 [inline]: 2.89999e-06 [add_attr]: 0.179297, [1] [add_attr_with_inline]: 0.179279, [1] [Cycle 1]: 0.00010691, [2] [tag_attr]: 2.026e-05 [meta_addattr_fg_expand]: 4.11001e-06 [parallel-infer-symbol]: 4.06001e-06 [pre_auto_parallel]: 4.701e-05 [insert-virtual-dataset]: 2.79999e-06 [parallel-infer-symbol-second]: 1.26997e-06 [dataset_repeat_opt]: 2.61999e-06 [pipeline_split]: 1.81e-06 [optimize]: 0.125888, [53] [py_interpret_to_execute]: 2.801e-05 [rewriter_before_opt_a]: 0.00993727 [opt_a]: 0.0482571, [2] [Cycle 1]: 0.0381201, [45] [expand_dump_flag]: 6.89999e-06 [switch_simplify]: 4.451e-05 [loop_unroll]: 1.565e-05 [a_1]: 0.00047343 [with_stream_mark]: 3.009e-05 [recompute_prepare]: 1.239e-05 [updatestate_depend_eliminate]: 6.81999e-06 [updatestate_assign_eliminate]: 1.17e-05 [updatestate_loads_eliminate]: 5.77001e-06 [parameter_eliminate]: 2.54999e-06 [a_2]: 0.0100595 [accelerated_algorithm]: 2.281e-05 [shard]: 6.33e-06 [meta_shard_fg_expand]: 6.15002e-06 [shard_inline]: 1.263e-05 [merge_send_recv]: 4.989e-05 [auto_parallel]: 2.011e-05 [parallel]: 5.549e-05 [flash_sp]: 2.805e-05 [merge_comm]: 7.13998e-06 [allreduce_fusion]: 5.89999e-06 [matmul_add_comm_reduction]: 1.808e-05 [allreduce_slice_to_reducescatter]: 1.24e-06 [virtual_shard_identity]: 1.818e-05 [virtual_dataset]: 1.204e-05 [get_grad_eliminate_]: 1.058e-05 [virtual_output]: 1.153e-05 [merge_forward]: 6.89001e-06 [cell_reuse_recompute_pass]: 4.48999e-06 [offload_activation]: 5.64e-05 [cell_reuse_handle_not_recompute_node_pass]: 7.722e-05 [merge_recompute_call_nodes]: 3.24001e-06 [before_grad]: 2.54e-05 [set_forward_comm_id_for_comm_node_pass]: 1.454e-05 [meta_fg_expand]: 8.40001e-06 [flash_sp_send_recv_attached]: 9.37999e-06 [receive_attached]: 1.866e-05 [after_resolve]: 2.177e-05 [a_after_grad]: 1.832e-05 [renormalize]: 0.00880804 [add_forward_monad_depend]: 3.005e-05 [auto_monad_grad]: 3.53999e-06 [auto_monad_eliminator]: 6.798e-05 [cse]: 6.782e-05 [a_3]: 0.00010898 [Cycle 2]: 0.0101124, [45] [expand_dump_flag]: 3.4e-06 [switch_simplify]: 1.551e-05 [loop_unroll]: 1.117e-05 [a_1]: 0.00026415 [with_stream_mark]: 3.041e-05 [recompute_prepare]: 1.329e-05 [updatestate_depend_eliminate]: 7.61999e-06 [updatestate_assign_eliminate]: 7.26999e-06 [updatestate_loads_eliminate]: 4.94e-06 [parameter_eliminate]: 2.68e-06 [a_2]: 0.00893243 [accelerated_algorithm]: 2.495e-05 [shard]: 5.72999e-06 [meta_shard_fg_expand]: 7.26001e-06 [shard_inline]: 1.26e-05 [merge_send_recv]: 2.462e-05 [auto_parallel]: 1.887e-05 [parallel]: 1.28e-05 [flash_sp]: 6.75002e-06 [merge_comm]: 6.51e-06 [allreduce_fusion]: 5.91998e-06 [matmul_add_comm_reduction]: 1.837e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 1.489e-05 [virtual_dataset]: 1.286e-05 [get_grad_eliminate_]: 1.167e-05 [virtual_output]: 1.042e-05 [merge_forward]: 7.55e-06 [cell_reuse_recompute_pass]: 4.99998e-06 [offload_activation]: 1.692e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.947e-05 [merge_recompute_call_nodes]: 2.04999e-06 [before_grad]: 1.963e-05 [set_forward_comm_id_for_comm_node_pass]: 6.54001e-06 [meta_fg_expand]: 5.37001e-06 [flash_sp_send_recv_attached]: 2.51e-06 [receive_attached]: 2.68e-06 [after_resolve]: 1.815e-05 [a_after_grad]: 1.721e-05 [renormalize]: 5.89993e-07 [add_forward_monad_depend]: 8.02998e-06 [auto_monad_grad]: 3.61001e-06 [auto_monad_eliminator]: 3.473e-05 [cse]: 5.135e-05 [a_3]: 7.356e-05 [py_interpret_to_execute_after_opt_a]: 2.874e-05 [slice_cell_reuse_recomputed_activation]: 2.93e-06 [rewriter_after_opt_a]: 0.011467 [convert_after_rewriter]: 4.522e-05 [order_py_execute_after_rewriter]: 8.33001e-06 [mutable_eliminate]: 0.0175796 [opt_b]: 0.00052796, [1] [Cycle 1]: 0.00051041, [7] [b_1]: 0.0003105 [b_2]: 1.913e-05 [updatestate_depend_eliminate]: 2.014e-05 [updatestate_assign_eliminate]: 6.51999e-06 [updatestate_loads_eliminate]: 5.50001e-06 [renormalize]: 1.19e-06 [cse]: 5.881e-05 [optimize_parallel_all_gather_comm]: 3.456e-05 [overlap_param_gather]: 2.36e-06 [cconv]: 4.681e-05 [loop_unroll]: 0.0119482 [opt_after_cconv]: 0.00903512, [1] [Cycle 1]: 0.00901945, [7] [c_1]: 8.295e-05 [parameter_eliminate]: 0.00871478 [updatestate_depend_eliminate]: 3.872e-05 [updatestate_assign_eliminate]: 7.35e-06 [updatestate_loads_eliminate]: 5.77001e-06 [cse]: 6.148e-05 [renormalize]: 7.79983e-07 [remove_dup_value]: 2.624e-05 [tuple_transform]: 0.00016646, [1] [Cycle 1]: 0.0001533, [4] [d_1]: 0.00011354 [none_parameter_eliminate]: 3.13e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 1.35e-05 [partial_unused_args_eliminate]: 2.91e-06 [add_recomputation]: 0.00010284 [cse_after_recomputation]: 3.045e-05, [1] [Cycle 1]: 2.412e-05, [1] [cse]: 1.733e-05 [environ_conv]: 2.508e-05 [swap_dp_allreduce_reducescatter]: 8.43001e-06 [bias_add_comm_swap]: 3.78001e-06 [label_micro_interleaved_index]: 9.27999e-06 [label_fine_grained_interleaved_index]: 3.11999e-06 [merge_cast_opt]: 1.55999e-06 [slice_recompute_activation]: 2.54001e-06 [micro_interleaved_order_control]: 3.14001e-06 [assign_add_opt]: 1.62999e-06 [ForceFp32Comm]: 1.10001e-06 [remove_cast_before_assign_add]: 9.5999e-07 [full_micro_interleaved_order_control]: 2.37999e-06 [reorder_send_recv_between_fp_bp]: 3.05002e-06 [comm_op_add_attrs]: 1.52999e-06 [add_comm_op_reuse_tag]: 1.39e-06 [interleave_split_concat_branches]: 2.29001e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 2.488e-05 [overlap_opt_shard_grad_in_pipeline]: 2.11998e-06 [control_data_broadcast_order]: 2.221e-05 [grouped_pairwise_exchange_alltoall]: 1.99999e-06 [offloading_packed_experts]: 6.41e-06 [overlap_recompute_and_grad_model_parallel]: 6.59001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49e-06 [overlap_recompute_comm]: 3.11001e-06 [overlap_grad_ring_attention]: 6.29999e-06 [overlap_grad_flash_sp]: 4.389e-05 [begin_end_overlap_inline]: 5.79981e-07 [split_matmul_comm_elemetwise]: 2.49001e-06 [split_layernorm_comm]: 1.05e-05 [handle_group_info]: 1.79998e-06 [symbol_engine_optimizer]: 0.00086726, [1] [Cycle 1]: 0.00085351, [6] [build]: 1.542e-05 [elim_shapecalc]: 5.559e-05 [elim_not_effective]: 3.369e-05 [opt_reshape]: 1.362e-05 [fold_const_symbol]: 1.968e-05 [renormalize]: 7.50006e-07 [detach_backward]: 3.73001e-06 [pipeline_parallel_scheduler]: 2.16e-06 [auto_monad_reorder]: 6.505e-05 [get_jit_bprop_graph]: 1.91998e-06 [rewriter_after_jit_bprop_graph]: 7.28e-06 [opt_after_jit_grad]: 0.0121344 [validate]: 0.00010559 Sums bootstrap : 0.006964s : 2.08% type_inference : 0.206617s : 61.85% event_method : 0.000019s : 0.01% auto_monad : 0.016831s : 5.04% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 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 : 0.000047s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000028s : 0.01% optimize.rewriter_before_opt_a : 0.009937s : 2.97% optimize.opt_a.expand_dump_flag : 0.000010s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.02% optimize.opt_a.loop_unroll : 0.000027s : 0.01% optimize.opt_a.a_1 : 0.000738s : 0.22% optimize.opt_a.with_stream_mark : 0.000060s : 0.02% optimize.opt_a.recompute_prepare : 0.000026s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000019s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.018992s : 5.69% optimize.opt_a.accelerated_algorithm : 0.000048s : 0.01% optimize.opt_a.shard : 0.000012s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000013s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.01% optimize.opt_a.merge_send_recv : 0.000075s : 0.02% optimize.opt_a.auto_parallel : 0.000039s : 0.01% optimize.opt_a.parallel : 0.000068s : 0.02% optimize.opt_a.flash_sp : 0.000035s : 0.01% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000033s : 0.01% optimize.opt_a.virtual_dataset : 0.000025s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000022s : 0.01% optimize.opt_a.virtual_output : 0.000022s : 0.01% optimize.opt_a.merge_forward : 0.000014s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000009s : 0.00% optimize.opt_a.offload_activation : 0.000073s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000107s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000045s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.01% optimize.opt_a.meta_fg_expand : 0.000014s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000012s : 0.00% optimize.opt_a.receive_attached : 0.000021s : 0.01% optimize.opt_a.after_resolve : 0.000040s : 0.01% optimize.opt_a.a_after_grad : 0.000036s : 0.01% optimize.opt_a.renormalize : 0.008809s : 2.64% optimize.opt_a.add_forward_monad_depend : 0.000038s : 0.01% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000103s : 0.03% optimize.opt_a.cse : 0.000119s : 0.04% optimize.opt_a.a_3 : 0.000183s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.011467s : 3.43% optimize.convert_after_rewriter : 0.000045s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.017580s : 5.26% optimize.opt_b.b_1 : 0.000311s : 0.09% optimize.opt_b.b_2 : 0.000019s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000059s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000047s : 0.01% optimize.loop_unroll : 0.011948s : 3.58% optimize.opt_after_cconv.c_1 : 0.000083s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.008715s : 2.61% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000039s : 0.01% 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 : 0.000061s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000026s : 0.01% optimize.tuple_transform.d_1 : 0.000114s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000103s : 0.03% optimize.cse_after_recomputation.cse : 0.000017s : 0.01% optimize.environ_conv : 0.000025s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 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 : 0.000001s : 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 : 0.000002s : 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 : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 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 : 0.000044s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000010s : 0.00% optimize.handle_group_info : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000015s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000056s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000034s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000065s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.012134s : 3.63% validate : 0.000106s : 0.03% Time group info: ------[substitution.] 0.008980 55 97.33% : 0.008740s : 2: substitution.depend_value_elim 0.05% : 0.000004s : 5: substitution.elim_not_effective 0.03% : 0.000003s : 5: substitution.fold_const_symbol 0.11% : 0.000010s : 6: substitution.graph_param_transform 1.50% : 0.000134s : 1: substitution.inline 0.10% : 0.000009s : 10: substitution.j_node_and_user_rematch 0.20% : 0.000018s : 10: substitution.remove_not_recompute_node 0.12% : 0.000011s : 2: substitution.replace_old_param 0.33% : 0.000029s : 6: substitution.updatestate_pure_node_eliminater 0.23% : 0.000021s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.206535 2 94.42% : 0.195014s : 1: type_inference.infer 5.58% : 0.011521s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000133 1 100.00% : 0.000133s : 1: match.inline ------[predicate.] 0.000399 1419 0.67% : 0.000003s : 13: predicate.accumulaten_eliminater 2.02% : 0.000008s : 6: predicate.ad_related_special_op_eliminate 0.52% : 0.000002s : 12: predicate.addn_check_dump 0.59% : 0.000002s : 13: predicate.addn_zero_filter 0.55% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.71% : 0.000007s : 25: predicate.arithmetic_simplify 0.61% : 0.000002s : 13: predicate.cast_eliminate 0.68% : 0.000003s : 12: predicate.check_bprop_eliminate 0.52% : 0.000002s : 12: predicate.compare_switch_simplify 0.15% : 0.000001s : 6: predicate.const_output_eliminate 1.39% : 0.000006s : 12: predicate.depend_value_elim 0.56% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.68% : 0.000003s : 13: predicate.dict_get_item_eliminator 0.71% : 0.000003s : 13: predicate.dict_set_item_eliminator 1.25% : 0.000005s : 12: predicate.dumpgradient_eliminate 0.33% : 0.000001s : 6: predicate.elim_not_effective 2.36% : 0.000009s : 6: predicate.elim_shapecalc_of_broadcastargs 0.86% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.06% : 0.000004s : 19: predicate.environ_get_add_eliminate 1.00% : 0.000004s : 19: predicate.environ_get_depend_swap 2.41% : 0.000010s : 31: predicate.environ_get_eliminate 0.80% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.60% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.22% : 0.000005s : 14: predicate.float_depend_g_call 0.59% : 0.000002s : 12: predicate.float_environ_get_switch 0.88% : 0.000004s : 18: predicate.float_tuple_getitem_switch 0.15% : 0.000001s : 6: predicate.fold_const_symbol 0.79% : 0.000003s : 12: predicate.get_grad_eliminate 0.32% : 0.000001s : 6: predicate.graph_param_transform 0.94% : 0.000004s : 12: predicate.incorporate_call 0.49% : 0.000002s : 12: predicate.incorporate_call_switch 4.99% : 0.000020s : 63: predicate.inline 0.86% : 0.000003s : 12: predicate.inline_without_move 0.30% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.45% : 0.000006s : 12: predicate.less_batch_normalization 1.60% : 0.000006s : 25: predicate.list_to_tuple_eliminator_ 1.72% : 0.000007s : 38: predicate.load_eliminater 2.80% : 0.000011s : 6: predicate.loop_unroll_after_grad 0.78% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.89% : 0.000008s : 25: predicate.make_slice_get_slice_eliminator 0.53% : 0.000002s : 12: predicate.merge_addn 0.78% : 0.000003s : 12: predicate.micro_step_allgather_replace 0.78% : 0.000003s : 12: predicate.mini_step_allgather_replace 0.65% : 0.000003s : 13: predicate.minmaximum_grad 2.79% : 0.000011s : 6: predicate.mutable_eliminate 0.34% : 0.000001s : 6: predicate.opt_reshape 0.42% : 0.000002s : 6: predicate.parallel_virtual_node 0.71% : 0.000003s : 14: predicate.partial_defer_inline 0.92% : 0.000004s : 19: predicate.partial_eliminate 0.71% : 0.000003s : 13: predicate.print_const_string_wrapper 1.11% : 0.000004s : 12: predicate.reduce_all_const_elim 0.89% : 0.000004s : 13: predicate.reduce_eliminate 2.03% : 0.000008s : 38: predicate.redundant_stop_gradient_eliminater 0.61% : 0.000002s : 12: predicate.remove_not_recompute_node 1.08% : 0.000004s : 25: predicate.replace_applicator 0.49% : 0.000002s : 12: predicate.replace_old_param 0.38% : 0.000002s : 6: predicate.reset_defer_inline 0.78% : 0.000003s : 13: predicate.reshape_eliminate 0.79% : 0.000003s : 12: predicate.row_tensor_add_zeros_like 0.39% : 0.000002s : 6: predicate.row_tensor_eliminate 0.89% : 0.000004s : 12: predicate.same_eliminate 0.39% : 0.000002s : 12: predicate.set_cell_output_no_recompute 0.93% : 0.000004s : 12: predicate.shard_identity_eliminate 0.88% : 0.000004s : 12: predicate.special_op_eliminate 0.65% : 0.000003s : 12: predicate.specialize_transform 1.27% : 0.000005s : 12: predicate.split_environ_get_set_with_tuple_value 0.98% : 0.000004s : 12: predicate.stack_unstack_eliminate 0.34% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.64% : 0.000003s : 14: predicate.switch_defer_inline 1.47% : 0.000006s : 26: predicate.switch_layer_defer_inline 2.87% : 0.000011s : 49: predicate.switch_simplify 0.64% : 0.000003s : 13: predicate.tile_eliminate 0.66% : 0.000003s : 13: predicate.transpose_eliminate 1.67% : 0.000007s : 25: predicate.tuple_list_convert_item_index_to_positive 1.38% : 0.000006s : 25: predicate.tuple_list_get_item_const_eliminator 1.43% : 0.000006s : 25: predicate.tuple_list_get_item_depend_reorder 3.41% : 0.000014s : 37: predicate.tuple_list_get_item_eliminator 1.30% : 0.000005s : 25: predicate.tuple_list_get_set_item_eliminator 6.19% : 0.000025s : 37: predicate.tuple_list_set_item_eliminator 1.68% : 0.000007s : 25: predicate.tuple_to_list_eliminator_ 1.81% : 0.000007s : 38: predicate.updatestate_pure_node_eliminater 2.52% : 0.000010s : 50: predicate.updatestate_useless_node_eliminater 0.36% : 0.000001s : 6: predicate.value_based_eliminate 0.85% : 0.000003s : 12: predicate.virtual_dataset_eliminate 0.68% : 0.000003s : 12: predicate.virtual_output_eliminate 0.29% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 2.84% : 0.000011s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.011204 4 0.26% : 0.000029s : 1: func_graph_cloner_run.FuncGraphClonerGraph 99.74% : 0.011175s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.882964 192 0.00% : 0.000004s : 1: ForceFp32Comm 20.31% : 0.179304s : 1: add_attr 20.30% : 0.179284s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000107s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 1.91% : 0.016874s : 1: auto_monad 0.01% : 0.000071s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.80% : 0.007021s : 1: bootstrap 0.01% : 0.000052s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.00% : 0.000026s : 1: control_data_broadcast_order 0.01% : 0.000053s : 1: convert_after_rewriter 0.00% : 0.000034s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.00% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.01% : 0.000049s : 1: insert-virtual-dataset 0.00% : 0.000004s : 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 1.36% : 0.011974s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 2.00% : 0.017631s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000048s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000050s : 1: opt.transform.mutable_eliminate 2.29% : 0.020202s : 78: opt.transform.opt_a 0.01% : 0.000080s : 1: opt.transform.opt_after_cconv 0.01% : 0.000075s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000262s : 28: opt.transform.opt_b 0.01% : 0.000119s : 2: opt.transform.opt_trans_graph 0.01% : 0.000110s : 4: opt.transform.symbol_engine_opt 5.47% : 0.048264s : 1: opt_a 1.02% : 0.009045s : 1: opt_after_cconv 1.38% : 0.012163s : 1: opt_after_jit_grad 0.06% : 0.000535s : 1: opt_b 14.26% : 0.125896s : 1: optimize 0.00% : 0.000038s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000029s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 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% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000052s : 1: pre_auto_parallel 0.00% : 0.000032s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000031s : 1: remove_dup_value 0.95% : 0.008375s : 1: renormalize.infer 0.05% : 0.000415s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 1.30% : 0.011495s : 1: rewriter_after_opt_a 1.13% : 0.009983s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000020s : 1: split_layernorm_comm 1.71% : 0.015059s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.10% : 0.000872s : 1: symbol_engine_optimizer 0.02% : 0.000169s : 1: tuple_transform 23.40% : 0.206653s : 1: type_inference TotalTime = 0.206993, [21] [bootstrap]: 0.025728 [type_inference]: 0.16679 [event_method]: 2.049e-05 [auto_monad]: 0.00017186 [graph_reusing]: 6.18998e-06 [inline]: 2.79999e-06 [add_attr]: 0.00556942, [1] [add_attr_with_inline]: 0.00555531, [1] [Cycle 1]: 6.965e-05, [2] [tag_attr]: 2.021e-05 [meta_addattr_fg_expand]: 4.02e-06 [parallel-infer-symbol]: 4.2e-06 [pre_auto_parallel]: 0.00086225 [insert-virtual-dataset]: 3.67002e-06 [parallel-infer-symbol-second]: 2.06e-06 [dataset_repeat_opt]: 2.99999e-06 [pipeline_split]: 2.01003e-06 [optimize]: 0.00690746, [53] [py_interpret_to_execute]: 3.021e-05 [rewriter_before_opt_a]: 6.551e-05 [opt_a]: 0.0037986, [2] [Cycle 1]: 0.00271602, [45] [expand_dump_flag]: 4.08999e-06 [switch_simplify]: 3.11e-05 [loop_unroll]: 1.634e-05 [a_1]: 0.00046697 [with_stream_mark]: 2.303e-05 [recompute_prepare]: 1.309e-05 [updatestate_depend_eliminate]: 7.06999e-06 [updatestate_assign_eliminate]: 6.31e-06 [updatestate_loads_eliminate]: 6.05002e-06 [parameter_eliminate]: 2.58e-06 [a_2]: 0.00014831 [accelerated_algorithm]: 1.107e-05 [shard]: 2.80002e-06 [meta_shard_fg_expand]: 2.96001e-06 [shard_inline]: 9.92001e-06 [merge_send_recv]: 1.206e-05 [auto_parallel]: 9.25001e-06 [parallel]: 3.686e-05 [flash_sp]: 1.21e-05 [merge_comm]: 6.03002e-06 [allreduce_fusion]: 5.72001e-06 [matmul_add_comm_reduction]: 1.371e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.158e-05 [virtual_dataset]: 9.57001e-06 [get_grad_eliminate_]: 9.47001e-06 [virtual_output]: 9.73002e-06 [merge_forward]: 7.06001e-06 [cell_reuse_recompute_pass]: 2.15002e-06 [offload_activation]: 1.539e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.045e-05 [merge_recompute_call_nodes]: 1.66998e-06 [before_grad]: 1.671e-05 [set_forward_comm_id_for_comm_node_pass]: 5.99999e-06 [meta_fg_expand]: 4.63999e-06 [flash_sp_send_recv_attached]: 2.77002e-06 [receive_attached]: 2.77002e-06 [after_resolve]: 1.505e-05 [a_after_grad]: 1.438e-05 [renormalize]: 0.00127321 [add_forward_monad_depend]: 8.52e-06 [auto_monad_grad]: 2.56e-06 [auto_monad_eliminator]: 2.779e-05 [cse]: 4.44e-05 [a_3]: 8.077e-05 [Cycle 2]: 0.00106609, [45] [expand_dump_flag]: 2.73e-06 [switch_simplify]: 1.309e-05 [loop_unroll]: 9.54999e-06 [a_1]: 0.00030051 [with_stream_mark]: 2.101e-05 [recompute_prepare]: 1.1e-05 [updatestate_depend_eliminate]: 6.48e-06 [updatestate_assign_eliminate]: 5.17e-06 [updatestate_loads_eliminate]: 5.30999e-06 [parameter_eliminate]: 1.92999e-06 [a_2]: 0.00012951 [accelerated_algorithm]: 1.027e-05 [shard]: 2.41e-06 [meta_shard_fg_expand]: 2.44001e-06 [shard_inline]: 9.65002e-06 [merge_send_recv]: 1.017e-05 [auto_parallel]: 1.187e-05 [parallel]: 8.92999e-06 [flash_sp]: 4.67998e-06 [merge_comm]: 5.94999e-06 [allreduce_fusion]: 5.74e-06 [matmul_add_comm_reduction]: 1.149e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.085e-05 [virtual_dataset]: 9.67001e-06 [get_grad_eliminate_]: 9.39e-06 [virtual_output]: 9.12999e-06 [merge_forward]: 6.11e-06 [cell_reuse_recompute_pass]: 3.18998e-06 [offload_activation]: 1.272e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.005e-05 [merge_recompute_call_nodes]: 1.30001e-06 [before_grad]: 1.615e-05 [set_forward_comm_id_for_comm_node_pass]: 6.00002e-06 [meta_fg_expand]: 3.94002e-06 [flash_sp_send_recv_attached]: 1.86998e-06 [receive_attached]: 1.68002e-06 [after_resolve]: 1.261e-05 [a_after_grad]: 1.415e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.52001e-06 [auto_monad_grad]: 1.49e-06 [auto_monad_eliminator]: 1.442e-05 [cse]: 2.563e-05 [a_3]: 5.932e-05 [py_interpret_to_execute_after_opt_a]: 1.709e-05 [slice_cell_reuse_recomputed_activation]: 2.75002e-06 [rewriter_after_opt_a]: 0.00015864 [convert_after_rewriter]: 1.273e-05 [order_py_execute_after_rewriter]: 7.55003e-06 [mutable_eliminate]: 0.00087661 [opt_b]: 0.00034992, [1] [Cycle 1]: 0.00034149, [7] [b_1]: 0.00021213 [b_2]: 1.26e-05 [updatestate_depend_eliminate]: 8.85001e-06 [updatestate_assign_eliminate]: 4.63999e-06 [updatestate_loads_eliminate]: 5.42001e-06 [renormalize]: 5.8001e-07 [cse]: 5.49e-05 [optimize_parallel_all_gather_comm]: 2.548e-05 [overlap_param_gather]: 2.04e-06 [cconv]: 2.731e-05 [loop_unroll]: 0.0005249 [opt_after_cconv]: 0.00015224, [1] [Cycle 1]: 0.00014478, [7] [c_1]: 5.927e-05 [parameter_eliminate]: 3.43e-06 [updatestate_depend_eliminate]: 8.47e-06 [updatestate_assign_eliminate]: 4.68999e-06 [updatestate_loads_eliminate]: 4.51002e-06 [cse]: 2.647e-05 [renormalize]: 3.20026e-07 [remove_dup_value]: 1.889e-05 [tuple_transform]: 0.00010132, [1] [Cycle 1]: 9.597e-05, [4] [d_1]: 6.358e-05 [none_parameter_eliminate]: 1.72001e-06 [renormalize]: 5.39992e-07 [switch_simplify]: 1.061e-05 [partial_unused_args_eliminate]: 1.82999e-06 [add_recomputation]: 7.632e-05 [cse_after_recomputation]: 2.691e-05, [1] [Cycle 1]: 2.187e-05, [1] [cse]: 1.57e-05 [environ_conv]: 7.41999e-06 [swap_dp_allreduce_reducescatter]: 7.38e-06 [bias_add_comm_swap]: 3.81999e-06 [label_micro_interleaved_index]: 4.95999e-06 [label_fine_grained_interleaved_index]: 2.89001e-06 [merge_cast_opt]: 1.62999e-06 [slice_recompute_activation]: 2.48e-06 [micro_interleaved_order_control]: 2.46e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 1.27e-06 [remove_cast_before_assign_add]: 9.50007e-07 [full_micro_interleaved_order_control]: 2.79999e-06 [reorder_send_recv_between_fp_bp]: 3.838e-05 [comm_op_add_attrs]: 1.31002e-06 [add_comm_op_reuse_tag]: 1.09998e-06 [interleave_split_concat_branches]: 1.55999e-06 [interleave_parallel_branches]: 1.15999e-06 [overlap_opt_shard_in_pipeline]: 1.81e-06 [overlap_opt_shard_grad_in_pipeline]: 2.527e-05 [control_data_broadcast_order]: 2.206e-05 [grouped_pairwise_exchange_alltoall]: 1.82999e-06 [offloading_packed_experts]: 6.38003e-06 [overlap_recompute_and_grad_model_parallel]: 7.00998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.55001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.79998e-06 [overlap_recompute_comm]: 2.84999e-06 [overlap_grad_ring_attention]: 6.04001e-06 [overlap_grad_flash_sp]: 3.252e-05 [begin_end_overlap_inline]: 8.49977e-07 [split_matmul_comm_elemetwise]: 2.64999e-06 [split_layernorm_comm]: 2.14e-06 [handle_group_info]: 1.12e-06 [symbol_engine_optimizer]: 0.00011072, [1] [Cycle 1]: 0.00010524, [6] [build]: 5.97999e-06 [elim_shapecalc]: 1.493e-05 [elim_not_effective]: 2.16e-05 [opt_reshape]: 1.103e-05 [fold_const_symbol]: 1.689e-05 [renormalize]: 4.7998e-07 [detach_backward]: 2.59999e-06 [pipeline_parallel_scheduler]: 1.75001e-06 [auto_monad_reorder]: 3.36e-05 [get_jit_bprop_graph]: 1.91003e-06 [rewriter_after_jit_bprop_graph]: 5.45001e-06 [opt_after_jit_grad]: 0.00058276 [validate]: 5.606e-05 Sums bootstrap : 0.025728s : 12.85% type_inference : 0.166790s : 83.32% event_method : 0.000020s : 0.01% auto_monad : 0.000172s : 0.09% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 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 : 0.000862s : 0.43% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000030s : 0.02% optimize.rewriter_before_opt_a : 0.000066s : 0.03% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000044s : 0.02% optimize.opt_a.loop_unroll : 0.000026s : 0.01% optimize.opt_a.a_1 : 0.000767s : 0.38% optimize.opt_a.with_stream_mark : 0.000044s : 0.02% optimize.opt_a.recompute_prepare : 0.000024s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000278s : 0.14% optimize.opt_a.accelerated_algorithm : 0.000021s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000020s : 0.01% optimize.opt_a.merge_send_recv : 0.000022s : 0.01% optimize.opt_a.auto_parallel : 0.000021s : 0.01% optimize.opt_a.parallel : 0.000046s : 0.02% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000025s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000022s : 0.01% optimize.opt_a.virtual_dataset : 0.000019s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000019s : 0.01% optimize.opt_a.virtual_output : 0.000019s : 0.01% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000028s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000033s : 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 : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000028s : 0.01% optimize.opt_a.a_after_grad : 0.000029s : 0.01% optimize.opt_a.renormalize : 0.001273s : 0.64% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.02% optimize.opt_a.cse : 0.000070s : 0.03% optimize.opt_a.a_3 : 0.000140s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000017s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000159s : 0.08% optimize.convert_after_rewriter : 0.000013s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000877s : 0.44% optimize.opt_b.b_1 : 0.000212s : 0.11% optimize.opt_b.b_2 : 0.000013s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000055s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000025s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000027s : 0.01% optimize.loop_unroll : 0.000525s : 0.26% optimize.opt_after_cconv.c_1 : 0.000059s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 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 : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000026s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000019s : 0.01% optimize.tuple_transform.d_1 : 0.000064s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000076s : 0.04% optimize.cse_after_recomputation.cse : 0.000016s : 0.01% optimize.environ_conv : 0.000007s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 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 : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000038s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000025s : 0.01% optimize.control_data_broadcast_order : 0.000022s : 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 : 0.000002s : 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 : 0.000006s : 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 : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000022s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 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 : 0.000034s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000583s : 0.29% validate : 0.000056s : 0.03% Time group info: ------[substitution.] 0.000202 55 5.49% : 0.000011s : 2: substitution.depend_value_elim 1.75% : 0.000004s : 5: substitution.elim_not_effective 1.52% : 0.000003s : 5: substitution.fold_const_symbol 4.36% : 0.000009s : 6: substitution.graph_param_transform 60.49% : 0.000122s : 1: substitution.inline 3.17% : 0.000006s : 10: substitution.j_node_and_user_rematch 4.97% : 0.000010s : 10: substitution.remove_not_recompute_node 2.66% : 0.000005s : 2: substitution.replace_old_param 8.40% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 7.19% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.166715 2 99.60% : 0.166052s : 1: type_inference.infer 0.40% : 0.000663s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000121 1 100.00% : 0.000121s : 1: match.inline ------[predicate.] 0.000352 1419 0.78% : 0.000003s : 13: predicate.accumulaten_eliminater 0.80% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.71% : 0.000002s : 12: predicate.addn_check_dump 0.79% : 0.000003s : 13: predicate.addn_zero_filter 0.72% : 0.000003s : 13: predicate.adjust_all_reduce_mul_add 1.91% : 0.000007s : 25: predicate.arithmetic_simplify 0.77% : 0.000003s : 13: predicate.cast_eliminate 0.60% : 0.000002s : 12: predicate.check_bprop_eliminate 0.69% : 0.000002s : 12: predicate.compare_switch_simplify 0.17% : 0.000001s : 6: predicate.const_output_eliminate 0.68% : 0.000002s : 12: predicate.depend_value_elim 0.67% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.72% : 0.000003s : 13: predicate.dict_get_item_eliminator 18.28% : 0.000064s : 13: predicate.dict_set_item_eliminator 0.90% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 6: predicate.elim_not_effective 0.42% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 0.92% : 0.000003s : 19: predicate.environ_add_const_eliminate 0.96% : 0.000003s : 19: predicate.environ_get_add_eliminate 0.90% : 0.000003s : 19: predicate.environ_get_depend_swap 1.52% : 0.000005s : 31: predicate.environ_get_eliminate 0.90% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.70% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.13% : 0.000004s : 14: predicate.float_depend_g_call 0.59% : 0.000002s : 12: predicate.float_environ_get_switch 0.82% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 6: predicate.fold_const_symbol 0.77% : 0.000003s : 12: predicate.get_grad_eliminate 0.19% : 0.000001s : 6: predicate.graph_param_transform 0.61% : 0.000002s : 12: predicate.incorporate_call 0.53% : 0.000002s : 12: predicate.incorporate_call_switch 4.74% : 0.000017s : 63: predicate.inline 0.85% : 0.000003s : 12: predicate.inline_without_move 0.32% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.90% : 0.000003s : 12: predicate.less_batch_normalization 1.45% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.10% : 0.000007s : 38: predicate.load_eliminater 0.92% : 0.000003s : 6: predicate.loop_unroll_after_grad 0.92% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.60% : 0.000006s : 25: predicate.make_slice_get_slice_eliminator 0.61% : 0.000002s : 12: predicate.merge_addn 0.77% : 0.000003s : 12: predicate.micro_step_allgather_replace 0.61% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.61% : 0.000002s : 13: predicate.minmaximum_grad 1.09% : 0.000004s : 6: predicate.mutable_eliminate 0.35% : 0.000001s : 6: predicate.opt_reshape 0.45% : 0.000002s : 6: predicate.parallel_virtual_node 0.87% : 0.000003s : 14: predicate.partial_defer_inline 1.14% : 0.000004s : 19: predicate.partial_eliminate 0.77% : 0.000003s : 13: predicate.print_const_string_wrapper 0.61% : 0.000002s : 12: predicate.reduce_all_const_elim 1.06% : 0.000004s : 13: predicate.reduce_eliminate 1.88% : 0.000007s : 38: predicate.redundant_stop_gradient_eliminater 0.52% : 0.000002s : 12: predicate.remove_not_recompute_node 0.94% : 0.000003s : 25: predicate.replace_applicator 0.46% : 0.000002s : 12: predicate.replace_old_param 0.22% : 0.000001s : 6: predicate.reset_defer_inline 0.82% : 0.000003s : 13: predicate.reshape_eliminate 0.63% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.43% : 0.000002s : 6: predicate.row_tensor_eliminate 0.72% : 0.000003s : 12: predicate.same_eliminate 0.40% : 0.000001s : 12: predicate.set_cell_output_no_recompute 0.73% : 0.000003s : 12: predicate.shard_identity_eliminate 0.84% : 0.000003s : 12: predicate.special_op_eliminate 0.76% : 0.000003s : 12: predicate.specialize_transform 0.91% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 0.68% : 0.000002s : 12: predicate.stack_unstack_eliminate 0.35% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.78% : 0.000003s : 14: predicate.switch_defer_inline 1.44% : 0.000005s : 26: predicate.switch_layer_defer_inline 3.02% : 0.000011s : 49: predicate.switch_simplify 0.75% : 0.000003s : 13: predicate.tile_eliminate 0.73% : 0.000003s : 13: predicate.transpose_eliminate 1.42% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.39% : 0.000005s : 25: predicate.tuple_list_get_item_const_eliminator 1.35% : 0.000005s : 25: predicate.tuple_list_get_item_depend_reorder 2.48% : 0.000009s : 37: predicate.tuple_list_get_item_eliminator 1.40% : 0.000005s : 25: predicate.tuple_list_get_set_item_eliminator 2.18% : 0.000008s : 37: predicate.tuple_list_set_item_eliminator 1.44% : 0.000005s : 25: predicate.tuple_to_list_eliminator_ 1.80% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 2.68% : 0.000009s : 50: predicate.updatestate_useless_node_eliminater 0.36% : 0.000001s : 6: predicate.value_based_eliminate 0.76% : 0.000003s : 12: predicate.virtual_dataset_eliminate 0.68% : 0.000002s : 12: predicate.virtual_output_eliminate 0.34% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000322 4 6.09% : 0.000020s : 1: func_graph_cloner_run.FuncGraphClonerGraph 93.91% : 0.000302s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.222400 192 0.00% : 0.000005s : 1: ForceFp32Comm 2.51% : 0.005577s : 1: add_attr 2.50% : 0.005560s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000081s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.08% : 0.000181s : 1: auto_monad 0.02% : 0.000038s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 11.59% : 0.025771s : 1: bootstrap 0.01% : 0.000031s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.01% : 0.000027s : 1: control_data_broadcast_order 0.01% : 0.000017s : 1: convert_after_rewriter 0.01% : 0.000030s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000011s : 1: environ_conv 0.01% : 0.000028s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.01% : 0.000011s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.24% : 0.000534s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.40% : 0.000889s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000024s : 1: opt.transform.mutable_eliminate 0.64% : 0.001427s : 78: opt.transform.opt_a 0.03% : 0.000057s : 1: opt.transform.opt_after_cconv 0.02% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000193s : 28: opt.transform.opt_b 0.03% : 0.000072s : 2: opt.transform.opt_trans_graph 0.03% : 0.000060s : 4: opt.transform.symbol_engine_opt 1.71% : 0.003802s : 1: opt_a 0.07% : 0.000157s : 1: opt_after_cconv 0.27% : 0.000593s : 1: opt_after_jit_grad 0.16% : 0.000354s : 1: opt_b 3.11% : 0.006914s : 1: optimize 0.01% : 0.000030s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000036s : 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 0.01% : 0.000032s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 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% : 0.000006s : 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 0.40% : 0.000883s : 1: pre_auto_parallel 0.02% : 0.000036s : 1: py_interpret_to_execute 0.01% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000023s : 1: remove_dup_value 0.34% : 0.000748s : 1: renormalize.infer 0.23% : 0.000513s : 1: renormalize.specialize 0.02% : 0.000045s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000165s : 1: rewriter_after_opt_a 0.03% : 0.000071s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000114s : 1: symbol_engine_optimizer 0.05% : 0.000104s : 1: tuple_transform 75.01% : 0.166825s : 1: type_inference TotalTime = 0.907038, [21] [bootstrap]: 0.00070026 [type_inference]: 0.244518 [event_method]: 5.124e-05 [auto_monad]: 0.0141205 [graph_reusing]: 1.143e-05 [inline]: 3.91001e-06 [add_attr]: 0.0170249, [1] [add_attr_with_inline]: 0.0170075, [1] [Cycle 1]: 0.00011217, [2] [tag_attr]: 4.76e-05 [meta_addattr_fg_expand]: 1.074e-05 [parallel-infer-symbol]: 4.55999e-06 [pre_auto_parallel]: 6.829e-05 [insert-virtual-dataset]: 3.01001e-06 [parallel-infer-symbol-second]: 1.20001e-06 [dataset_repeat_opt]: 2.89999e-06 [pipeline_split]: 2.06998e-06 [optimize]: 0.629614, [53] [py_interpret_to_execute]: 5.267e-05 [rewriter_before_opt_a]: 0.00017894 [opt_a]: 0.626469, [3] [Cycle 1]: 0.422711, [45] [expand_dump_flag]: 6.44999e-06 [switch_simplify]: 8.047e-05 [loop_unroll]: 6.822e-05 [a_1]: 0.00231713 [with_stream_mark]: 5.14e-05 [recompute_prepare]: 3.878e-05 [updatestate_depend_eliminate]: 9.879e-05 [updatestate_assign_eliminate]: 1.271e-05 [updatestate_loads_eliminate]: 1.062e-05 [parameter_eliminate]: 5.32999e-06 [a_2]: 0.00037084 [accelerated_algorithm]: 4.368e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 1.079e-05 [shard_inline]: 0.00010843 [merge_send_recv]: 0.00048943 [auto_parallel]: 2.488e-05 [parallel]: 2.465e-05 [flash_sp]: 2.095e-05 [merge_comm]: 1.401e-05 [allreduce_fusion]: 1.25e-05 [matmul_add_comm_reduction]: 4.826e-05 [allreduce_slice_to_reducescatter]: 9.70002e-07 [virtual_shard_identity]: 8.79e-05 [virtual_dataset]: 2.503e-05 [get_grad_eliminate_]: 2.268e-05 [virtual_output]: 2.174e-05 [merge_forward]: 1.503e-05 [cell_reuse_recompute_pass]: 5.224e-05 [offload_activation]: 0.00373485 [cell_reuse_handle_not_recompute_node_pass]: 9.574e-05 [merge_recompute_call_nodes]: 4.07e-06 [before_grad]: 5.573e-05 [set_forward_comm_id_for_comm_node_pass]: 2.895e-05 [meta_fg_expand]: 0.280057 [flash_sp_send_recv_attached]: 6.62002e-06 [receive_attached]: 3.06001e-06 [after_resolve]: 0.00015201 [a_after_grad]: 0.00021364 [renormalize]: 0.131023 [add_forward_monad_depend]: 2.738e-05 [auto_monad_grad]: 1.392e-05 [auto_monad_eliminator]: 0.0001489 [cse]: 0.00032354 [a_3]: 0.00188532 [Cycle 2]: 0.20251, [45] [expand_dump_flag]: 5.34e-06 [switch_simplify]: 0.00012296 [loop_unroll]: 0.00011852 [a_1]: 0.00443089 [with_stream_mark]: 0.00019108 [recompute_prepare]: 0.0001481 [updatestate_depend_eliminate]: 0.00030346 [updatestate_assign_eliminate]: 4.55e-05 [updatestate_loads_eliminate]: 3.998e-05 [parameter_eliminate]: 3.666e-05 [a_2]: 0.00027915 [accelerated_algorithm]: 3.707e-05 [shard]: 3.46001e-06 [meta_shard_fg_expand]: 8.45001e-06 [shard_inline]: 1.536e-05 [merge_send_recv]: 2.73e-05 [auto_parallel]: 2.018e-05 [parallel]: 1.37e-05 [flash_sp]: 7.01001e-06 [merge_comm]: 1.81e-05 [allreduce_fusion]: 7.13e-06 [matmul_add_comm_reduction]: 2.827e-05 [allreduce_slice_to_reducescatter]: 1.30999e-06 [virtual_shard_identity]: 1.679e-05 [virtual_dataset]: 2.525e-05 [get_grad_eliminate_]: 1.206e-05 [virtual_output]: 1.173e-05 [merge_forward]: 7.25e-06 [cell_reuse_recompute_pass]: 4.27998e-06 [offload_activation]: 1.653e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.702e-05 [merge_recompute_call_nodes]: 1.65001e-06 [before_grad]: 2.276e-05 [set_forward_comm_id_for_comm_node_pass]: 8.69998e-06 [meta_fg_expand]: 8.857e-05 [flash_sp_send_recv_attached]: 2.39001e-06 [receive_attached]: 2.41e-06 [after_resolve]: 2.256e-05 [a_after_grad]: 1.952e-05 [renormalize]: 0.00170352 [add_forward_monad_depend]: 1.018e-05 [auto_monad_grad]: 3.06999e-06 [auto_monad_eliminator]: 2.944e-05 [cse]: 0.00010528 [a_3]: 0.00010009 [Cycle 3]: 0.00122212, [45] [expand_dump_flag]: 2.99999e-06 [switch_simplify]: 1.586e-05 [loop_unroll]: 2.046e-05 [a_1]: 0.00033791 [with_stream_mark]: 2.112e-05 [recompute_prepare]: 1.318e-05 [updatestate_depend_eliminate]: 7.54002e-06 [updatestate_assign_eliminate]: 7.19001e-06 [updatestate_loads_eliminate]: 5.91e-06 [parameter_eliminate]: 1.89999e-06 [a_2]: 0.00016516 [accelerated_algorithm]: 1.724e-05 [shard]: 2.02999e-06 [meta_shard_fg_expand]: 3.08e-06 [shard_inline]: 1.208e-05 [merge_send_recv]: 1.151e-05 [auto_parallel]: 1.141e-05 [parallel]: 9.94999e-06 [flash_sp]: 1.71e-06 [merge_comm]: 7.77998e-06 [allreduce_fusion]: 6.97002e-06 [matmul_add_comm_reduction]: 1.349e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 1.362e-05 [virtual_dataset]: 1.22e-05 [get_grad_eliminate_]: 1.097e-05 [virtual_output]: 1.13e-05 [merge_forward]: 6.98998e-06 [cell_reuse_recompute_pass]: 3.28998e-06 [offload_activation]: 1.429e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.323e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 2.111e-05 [set_forward_comm_id_for_comm_node_pass]: 7.36001e-06 [meta_fg_expand]: 4.72e-06 [flash_sp_send_recv_attached]: 1.50001e-06 [receive_attached]: 2.19001e-06 [after_resolve]: 1.961e-05 [a_after_grad]: 1.857e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 2.59001e-06 [auto_monad_grad]: 1.92001e-06 [auto_monad_eliminator]: 1.744e-05 [cse]: 3.076e-05 [a_3]: 7.346e-05 [py_interpret_to_execute_after_opt_a]: 2.035e-05 [slice_cell_reuse_recomputed_activation]: 2.46e-06 [rewriter_after_opt_a]: 8.534e-05 [convert_after_rewriter]: 1.172e-05 [order_py_execute_after_rewriter]: 8.26002e-06 [mutable_eliminate]: 0.00082876 [opt_b]: 0.00039126, [1] [Cycle 1]: 0.00038167, [7] [b_1]: 0.00026509 [b_2]: 1.477e-05 [updatestate_depend_eliminate]: 1.064e-05 [updatestate_assign_eliminate]: 5.46e-06 [updatestate_loads_eliminate]: 6.29999e-06 [renormalize]: 5.8001e-07 [cse]: 3.878e-05 [optimize_parallel_all_gather_comm]: 2.46e-05 [overlap_param_gather]: 1.89e-06 [cconv]: 3.536e-05 [loop_unroll]: 0.00047804 [opt_after_cconv]: 0.00017664, [1] [Cycle 1]: 0.00016949, [7] [c_1]: 7.534e-05 [parameter_eliminate]: 3.22002e-06 [updatestate_depend_eliminate]: 9.32999e-06 [updatestate_assign_eliminate]: 5.82001e-06 [updatestate_loads_eliminate]: 5.10001e-06 [cse]: 3.245e-05 [renormalize]: 5.8001e-07 [remove_dup_value]: 2.093e-05 [tuple_transform]: 0.00012849, [1] [Cycle 1]: 0.00012287, [4] [d_1]: 8.823e-05 [none_parameter_eliminate]: 2.07999e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 1.253e-05 [partial_unused_args_eliminate]: 2.16e-06 [add_recomputation]: 9.603e-05 [cse_after_recomputation]: 3.855e-05, [1] [Cycle 1]: 3.32e-05, [1] [cse]: 2.679e-05 [environ_conv]: 1.296e-05 [swap_dp_allreduce_reducescatter]: 1.04e-05 [bias_add_comm_swap]: 2.63e-06 [label_micro_interleaved_index]: 5.42999e-06 [label_fine_grained_interleaved_index]: 3.23e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 3.11001e-06 [assign_add_opt]: 1.50999e-06 [ForceFp32Comm]: 1.03001e-06 [remove_cast_before_assign_add]: 1.47001e-06 [full_micro_interleaved_order_control]: 3.08998e-06 [reorder_send_recv_between_fp_bp]: 2.88998e-06 [comm_op_add_attrs]: 1.37e-06 [add_comm_op_reuse_tag]: 1.12999e-06 [interleave_split_concat_branches]: 1.80001e-06 [interleave_parallel_branches]: 1.22e-06 [overlap_opt_shard_in_pipeline]: 1.28002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.58e-06 [control_data_broadcast_order]: 2.368e-05 [grouped_pairwise_exchange_alltoall]: 1.96998e-06 [offloading_packed_experts]: 6.47001e-06 [overlap_recompute_and_grad_model_parallel]: 6.74001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.34998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.81e-06 [overlap_grad_ring_attention]: 6.89001e-06 [overlap_grad_flash_sp]: 3.556e-05 [begin_end_overlap_inline]: 6.30011e-07 [split_matmul_comm_elemetwise]: 2.48e-06 [split_layernorm_comm]: 1.97999e-06 [handle_group_info]: 1.15001e-06 [symbol_engine_optimizer]: 0.00014603, [1] [Cycle 1]: 0.0001403, [6] [build]: 3.018e-05 [elim_shapecalc]: 1.754e-05 [elim_not_effective]: 2.581e-05 [opt_reshape]: 1.275e-05 [fold_const_symbol]: 2.189e-05 [renormalize]: 1.80007e-07 [detach_backward]: 2.80997e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 3.519e-05 [get_jit_bprop_graph]: 1.88002e-06 [rewriter_after_jit_bprop_graph]: 6.09001e-06 [opt_after_jit_grad]: 0.00054254 [validate]: 7.07e-05 Sums bootstrap : 0.000700s : 0.10% type_inference : 0.244518s : 35.24% event_method : 0.000051s : 0.01% auto_monad : 0.014120s : 2.03% graph_reusing : 0.000011s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000048s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000011s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000068s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000053s : 0.01% optimize.rewriter_before_opt_a : 0.000179s : 0.03% optimize.opt_a.expand_dump_flag : 0.000015s : 0.00% optimize.opt_a.switch_simplify : 0.000219s : 0.03% optimize.opt_a.loop_unroll : 0.000207s : 0.03% optimize.opt_a.a_1 : 0.007086s : 1.02% optimize.opt_a.with_stream_mark : 0.000264s : 0.04% optimize.opt_a.recompute_prepare : 0.000200s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000410s : 0.06% optimize.opt_a.updatestate_assign_eliminate : 0.000065s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000057s : 0.01% optimize.opt_a.parameter_eliminate : 0.000044s : 0.01% optimize.opt_a.a_2 : 0.000815s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000098s : 0.01% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000022s : 0.00% optimize.opt_a.shard_inline : 0.000136s : 0.02% optimize.opt_a.merge_send_recv : 0.000528s : 0.08% optimize.opt_a.auto_parallel : 0.000056s : 0.01% optimize.opt_a.parallel : 0.000048s : 0.01% optimize.opt_a.flash_sp : 0.000030s : 0.00% optimize.opt_a.merge_comm : 0.000040s : 0.01% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000090s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000118s : 0.02% optimize.opt_a.virtual_dataset : 0.000062s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 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 : 0.000060s : 0.01% optimize.opt_a.offload_activation : 0.003766s : 0.54% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000146s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000007s : 0.00% optimize.opt_a.before_grad : 0.000100s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000045s : 0.01% optimize.opt_a.meta_fg_expand : 0.280150s : 40.37% 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 : 0.000194s : 0.03% optimize.opt_a.a_after_grad : 0.000252s : 0.04% optimize.opt_a.renormalize : 0.132726s : 19.13% optimize.opt_a.add_forward_monad_depend : 0.000040s : 0.01% optimize.opt_a.auto_monad_grad : 0.000019s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000196s : 0.03% optimize.opt_a.cse : 0.000460s : 0.07% optimize.opt_a.a_3 : 0.002059s : 0.30% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000085s : 0.01% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000829s : 0.12% optimize.opt_b.b_1 : 0.000265s : 0.04% optimize.opt_b.b_2 : 0.000015s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000039s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000025s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.01% optimize.loop_unroll : 0.000478s : 0.07% optimize.opt_after_cconv.c_1 : 0.000075s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000032s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000021s : 0.00% optimize.tuple_transform.d_1 : 0.000088s : 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 : 0.000096s : 0.01% optimize.cse_after_recomputation.cse : 0.000027s : 0.00% optimize.environ_conv : 0.000013s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 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 : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 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 : 0.000030s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 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 : 0.000035s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000543s : 0.08% validate : 0.000071s : 0.01% Time group info: ------[substitution.] 0.002784 310 0.81% : 0.000023s : 4: substitution.depend_value_elim 0.15% : 0.000004s : 7: substitution.elim_not_effective 0.39% : 0.000011s : 7: substitution.float_depend_g_call 0.19% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.14% : 0.000004s : 7: substitution.fold_const_symbol 33.56% : 0.000934s : 4: substitution.getattr_setattr_resolve 0.38% : 0.000011s : 9: substitution.graph_param_transform 0.13% : 0.000004s : 2: substitution.incorporate_call 0.10% : 0.000003s : 2: substitution.incorporate_call_switch 41.53% : 0.001156s : 24: substitution.inline 1.49% : 0.000041s : 5: substitution.inline_without_move 0.79% : 0.000022s : 28: substitution.j_node_and_user_rematch 0.92% : 0.000026s : 3: substitution.less_batch_normalization 0.58% : 0.000016s : 9: substitution.minmaximum_grad 0.48% : 0.000013s : 7: substitution.partial_eliminate 1.02% : 0.000028s : 28: substitution.remove_not_recompute_node 4.39% : 0.000122s : 38: substitution.replace_applicator 0.82% : 0.000023s : 19: substitution.replace_old_param 0.22% : 0.000006s : 1: substitution.set_cell_output_no_recompute 1.18% : 0.000033s : 9: substitution.tuple_list_convert_item_index_to_positive 0.56% : 0.000016s : 9: substitution.tuple_list_get_item_const_eliminator 0.82% : 0.000023s : 9: substitution.tuple_list_get_item_depend_reorder 5.04% : 0.000140s : 31: substitution.tuple_list_get_item_eliminator 0.77% : 0.000022s : 9: substitution.tuple_list_get_set_item_eliminator 1.19% : 0.000033s : 16: substitution.updatestate_pure_node_eliminater 2.35% : 0.000065s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.244408 2 62.49% : 0.152738s : 1: type_inference.infer 37.51% : 0.091670s : 1: type_inference.specialize ------[replace.] 0.000803 49 8.82% : 0.000071s : 3: replace.getattr_setattr_resolve 33.55% : 0.000269s : 24: replace.inline 7.68% : 0.000062s : 1: replace.replace_applicator 48.32% : 0.000388s : 20: replace.tuple_list_get_item_eliminator 1.64% : 0.000013s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.002136 49 41.25% : 0.000881s : 3: match.getattr_setattr_resolve 53.18% : 0.001136s : 24: match.inline 0.84% : 0.000018s : 1: match.replace_applicator 3.97% : 0.000085s : 20: match.tuple_list_get_item_eliminator 0.76% : 0.000016s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.001655 8683 0.81% : 0.000013s : 85: predicate.accumulaten_eliminater 0.19% : 0.000003s : 9: predicate.ad_related_special_op_eliminate 0.36% : 0.000006s : 37: predicate.addn_check_dump 1.03% : 0.000017s : 85: predicate.addn_zero_filter 0.95% : 0.000016s : 85: predicate.adjust_all_reduce_mul_add 1.63% : 0.000027s : 122: predicate.arithmetic_simplify 0.83% : 0.000014s : 85: predicate.cast_eliminate 2.37% : 0.000039s : 260: predicate.check_bprop_eliminate 0.39% : 0.000007s : 37: predicate.compare_switch_simplify 0.05% : 0.000001s : 9: predicate.const_output_eliminate 0.40% : 0.000007s : 37: predicate.depend_value_elim 1.00% : 0.000017s : 85: predicate.dict_get_item_const_eliminator 0.99% : 0.000016s : 85: predicate.dict_get_item_eliminator 1.05% : 0.000017s : 85: predicate.dict_set_item_eliminator 0.23% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.07% : 0.000001s : 9: predicate.elim_not_effective 0.11% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 0.91% : 0.000015s : 94: predicate.environ_add_const_eliminate 1.31% : 0.000022s : 94: predicate.environ_get_add_eliminate 0.86% : 0.000014s : 94: predicate.environ_get_depend_swap 1.25% : 0.000021s : 131: predicate.environ_get_eliminate 0.93% : 0.000015s : 94: predicate.environ_get_set_eliminate 1.30% : 0.000022s : 130: predicate.exchange_switch_depend_value 2.04% : 0.000034s : 130: predicate.float_depend_g_call 0.37% : 0.000006s : 37: predicate.float_environ_get_switch 0.48% : 0.000008s : 46: predicate.float_tuple_getitem_switch 0.06% : 0.000001s : 9: predicate.fold_const_symbol 0.40% : 0.000007s : 37: predicate.get_grad_eliminate 0.47% : 0.000008s : 20: predicate.getattr_setattr_resolve 0.07% : 0.000001s : 9: predicate.graph_param_transform 0.39% : 0.000007s : 37: predicate.incorporate_call 0.34% : 0.000006s : 37: predicate.incorporate_call_switch 5.86% : 0.000097s : 307: predicate.inline 1.52% : 0.000025s : 111: predicate.inline_without_move 0.22% : 0.000004s : 37: predicate.j_node_and_user_rematch 0.55% : 0.000009s : 37: predicate.less_batch_normalization 1.45% : 0.000024s : 123: predicate.list_to_tuple_eliminator_ 2.93% : 0.000048s : 208: predicate.load_eliminater 0.20% : 0.000003s : 9: predicate.loop_unroll_after_grad 2.04% : 0.000034s : 197: predicate.loop_unroll_before_grad 1.23% : 0.000020s : 103: predicate.make_slice_get_slice_eliminator 0.44% : 0.000007s : 37: predicate.merge_addn 2.46% : 0.000041s : 256: predicate.micro_step_allgather_replace 2.48% : 0.000041s : 256: predicate.mini_step_allgather_replace 0.86% : 0.000014s : 85: predicate.minmaximum_grad 0.28% : 0.000005s : 9: predicate.mutable_eliminate 0.10% : 0.000002s : 9: predicate.opt_reshape 0.11% : 0.000002s : 9: predicate.parallel_virtual_node 1.95% : 0.000032s : 130: predicate.partial_defer_inline 1.62% : 0.000027s : 114: predicate.partial_eliminate 1.97% : 0.000033s : 85: predicate.print_const_string_wrapper 0.37% : 0.000006s : 37: predicate.reduce_all_const_elim 1.07% : 0.000018s : 85: predicate.reduce_eliminate 2.19% : 0.000036s : 208: predicate.redundant_stop_gradient_eliminater 0.29% : 0.000005s : 37: predicate.remove_not_recompute_node 2.39% : 0.000039s : 363: predicate.replace_applicator 0.71% : 0.000012s : 111: predicate.replace_old_param 0.06% : 0.000001s : 9: predicate.reset_defer_inline 0.90% : 0.000015s : 85: predicate.reshape_eliminate 2.59% : 0.000043s : 256: predicate.row_tensor_add_zeros_like 0.11% : 0.000002s : 9: predicate.row_tensor_eliminate 2.53% : 0.000042s : 260: predicate.same_eliminate 0.29% : 0.000005s : 39: predicate.set_cell_output_no_recompute 0.55% : 0.000009s : 37: predicate.shard_identity_eliminate 0.19% : 0.000003s : 18: predicate.special_op_eliminate 0.62% : 0.000010s : 37: predicate.specialize_transform 2.42% : 0.000040s : 256: predicate.split_environ_get_set_with_tuple_value 1.21% : 0.000020s : 111: predicate.stack_unstack_eliminate 0.10% : 0.000002s : 9: predicate.switch_call_monad_eliminater 1.58% : 0.000026s : 130: predicate.switch_defer_inline 3.77% : 0.000062s : 390: predicate.switch_layer_defer_inline 4.78% : 0.000079s : 373: predicate.switch_simplify 0.98% : 0.000016s : 85: predicate.tile_eliminate 1.10% : 0.000018s : 85: predicate.transpose_eliminate 1.15% : 0.000019s : 103: predicate.tuple_list_convert_item_index_to_positive 1.39% : 0.000023s : 103: predicate.tuple_list_get_item_const_eliminator 1.22% : 0.000020s : 103: predicate.tuple_list_get_item_depend_reorder 2.45% : 0.000041s : 160: predicate.tuple_list_get_item_eliminator 1.68% : 0.000028s : 103: predicate.tuple_list_get_set_item_eliminator 1.70% : 0.000028s : 140: predicate.tuple_list_set_item_eliminator 1.40% : 0.000023s : 123: predicate.tuple_to_list_eliminator_ 2.51% : 0.000042s : 208: predicate.updatestate_pure_node_eliminater 2.67% : 0.000044s : 246: predicate.updatestate_useless_node_eliminater 0.12% : 0.000002s : 9: predicate.value_based_eliminate 0.42% : 0.000007s : 37: predicate.virtual_dataset_eliminate 0.40% : 0.000007s : 37: predicate.virtual_output_eliminate 0.09% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.11% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003576 53 60.17% : 0.002151s : 23: func_graph_cloner_run.FuncGraphClonerGraph 39.83% : 0.001424s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.699357 243 0.00% : 0.000004s : 1: ForceFp32Comm 1.00% : 0.017033s : 1: add_attr 1.00% : 0.017012s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000101s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.83% : 0.014166s : 1: auto_monad 0.00% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000738s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000016s : 1: convert_after_rewriter 0.00% : 0.000042s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.00% : 0.000061s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000020s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000010s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000488s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.05% : 0.000842s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000025s : 1: opt.transform.mutable_eliminate 0.68% : 0.011513s : 125: opt.transform.opt_a 0.00% : 0.000074s : 1: opt.transform.opt_after_cconv 0.00% : 0.000042s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000248s : 28: opt.transform.opt_b 0.06% : 0.001073s : 2: opt.transform.opt_resolve 0.01% : 0.000098s : 2: opt.transform.opt_trans_graph 0.00% : 0.000073s : 4: opt.transform.symbol_engine_opt 36.87% : 0.626473s : 1: opt_a 0.01% : 0.000180s : 1: opt_after_cconv 0.03% : 0.000553s : 1: opt_after_jit_grad 0.02% : 0.000395s : 1: opt_b 37.05% : 0.629620s : 1: optimize 0.00% : 0.000029s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.00% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 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% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000074s : 1: pre_auto_parallel 0.00% : 0.000057s : 1: py_interpret_to_execute 0.00% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000025s : 1: remove_dup_value 7.54% : 0.128121s : 2: renormalize.infer 0.27% : 0.004576s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000092s : 1: rewriter_after_opt_a 0.01% : 0.000190s : 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% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000149s : 1: symbol_engine_optimizer 0.01% : 0.000132s : 1: tuple_transform 14.39% : 0.244546s : 1: type_inference . [hook] pytest_runtest_teardown:test_sigmoid__empty_tensor[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__empty_tensor[0],max_mem:4.0M [WARNING] ME(169876:281473380167472,MainProcess):2026-01-29-17:40:39.843.211 [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__empty_tensor[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__empty_tensor[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 226.96s (0:03:46) ==================