==================================================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_004/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(165933:281473430114096,MainProcess):2026-01-29-17:39:53.589.272 [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 = 32.5894, [24] [bootstrap]: 0.00062666 [type_inference]: 0.191825 [event_method]: 1.513e-05 [auto_monad]: 0.00017508 [graph_reusing]: 5.79999e-06 [inline]: 3.28998e-06 [add_attr]: 0.227079, [1] [add_attr_with_inline]: 0.227064, [1] [Cycle 1]: 9.952e-05, [2] [tag_attr]: 1.822e-05 [meta_addattr_fg_expand]: 4.05998e-06 [parallel-infer-symbol]: 3.95e-06 [pre_auto_parallel]: 5.125e-05 [insert-virtual-dataset]: 2.53998e-06 [parallel-infer-symbol-second]: 8.59989e-07 [dataset_repeat_opt]: 2.17001e-06 [pipeline_split]: 1.81998e-06 [optimize]: 0.00632147, [53] [py_interpret_to_execute]: 2.663e-05 [rewriter_before_opt_a]: 7.022e-05 [opt_a]: 0.00325374, [2] [Cycle 1]: 0.00228172, [45] [expand_dump_flag]: 2.71999e-06 [switch_simplify]: 3.027e-05 [loop_unroll]: 1.316e-05 [a_1]: 0.00038826 [with_stream_mark]: 2.299e-05 [recompute_prepare]: 1.468e-05 [updatestate_depend_eliminate]: 7.15e-06 [updatestate_assign_eliminate]: 5.92999e-06 [updatestate_loads_eliminate]: 5.24e-06 [parameter_eliminate]: 1.88002e-06 [a_2]: 0.00012952 [accelerated_algorithm]: 1.048e-05 [shard]: 3.02002e-06 [meta_shard_fg_expand]: 2.32999e-06 [shard_inline]: 1.026e-05 [merge_send_recv]: 2.455e-05 [auto_parallel]: 1.017e-05 [parallel]: 4.408e-05 [flash_sp]: 2.05e-05 [merge_comm]: 7.23e-06 [allreduce_fusion]: 5.34998e-06 [matmul_add_comm_reduction]: 1.428e-05 [allreduce_slice_to_reducescatter]: 7.60017e-07 [virtual_shard_identity]: 1.488e-05 [virtual_dataset]: 8.72e-06 [get_grad_eliminate_]: 8.94e-06 [virtual_output]: 8.31002e-06 [merge_forward]: 6.56999e-06 [cell_reuse_recompute_pass]: 1.66e-06 [offload_activation]: 1.461e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.275e-05 [merge_recompute_call_nodes]: 1.65001e-06 [before_grad]: 1.683e-05 [set_forward_comm_id_for_comm_node_pass]: 7.45e-06 [meta_fg_expand]: 3.85998e-06 [flash_sp_send_recv_attached]: 3.68999e-06 [receive_attached]: 1.133e-05 [after_resolve]: 1.559e-05 [a_after_grad]: 1.367e-05 [renormalize]: 0.00087291 [add_forward_monad_depend]: 1.601e-05 [auto_monad_grad]: 2.67001e-06 [auto_monad_eliminator]: 2.674e-05 [cse]: 5.469e-05 [a_3]: 7.315e-05 [Cycle 2]: 0.00095705, [45] [expand_dump_flag]: 1.78002e-06 [switch_simplify]: 1.091e-05 [loop_unroll]: 8.25999e-06 [a_1]: 0.0002016 [with_stream_mark]: 1.997e-05 [recompute_prepare]: 1.159e-05 [updatestate_depend_eliminate]: 6.69001e-06 [updatestate_assign_eliminate]: 5.59e-06 [updatestate_loads_eliminate]: 5.04998e-06 [parameter_eliminate]: 1.50999e-06 [a_2]: 0.00011526 [accelerated_algorithm]: 1.136e-05 [shard]: 2.51e-06 [meta_shard_fg_expand]: 2.43e-06 [shard_inline]: 9.65002e-06 [merge_send_recv]: 1.136e-05 [auto_parallel]: 1.061e-05 [parallel]: 7.35e-06 [flash_sp]: 4.02998e-06 [merge_comm]: 5.57999e-06 [allreduce_fusion]: 5.51e-06 [matmul_add_comm_reduction]: 1.019e-05 [allreduce_slice_to_reducescatter]: 3.4002e-07 [virtual_shard_identity]: 1.254e-05 [virtual_dataset]: 8.64e-06 [get_grad_eliminate_]: 8.37e-06 [virtual_output]: 8.45999e-06 [merge_forward]: 6.26e-06 [cell_reuse_recompute_pass]: 2.17001e-06 [offload_activation]: 1.271e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.145e-05 [merge_recompute_call_nodes]: 1.05999e-06 [before_grad]: 1.504e-05 [set_forward_comm_id_for_comm_node_pass]: 6.02999e-06 [meta_fg_expand]: 4.08999e-06 [flash_sp_send_recv_attached]: 1.71002e-06 [receive_attached]: 1.45999e-06 [after_resolve]: 1.317e-05 [a_after_grad]: 1.306e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.94999e-06 [auto_monad_grad]: 2.43998e-06 [auto_monad_eliminator]: 1.768e-05 [cse]: 2.916e-05 [a_3]: 5.691e-05 [py_interpret_to_execute_after_opt_a]: 1.996e-05 [slice_cell_reuse_recomputed_activation]: 2.37001e-06 [rewriter_after_opt_a]: 0.00018524 [convert_after_rewriter]: 3.138e-05 [order_py_execute_after_rewriter]: 6.89999e-06 [mutable_eliminate]: 0.00077129 [opt_b]: 0.00031514, [1] [Cycle 1]: 0.00030617, [7] [b_1]: 0.00019207 [b_2]: 1.167e-05 [updatestate_depend_eliminate]: 1.217e-05 [updatestate_assign_eliminate]: 5.36002e-06 [updatestate_loads_eliminate]: 5.52999e-06 [renormalize]: 9.40025e-07 [cse]: 3.754e-05 [optimize_parallel_all_gather_comm]: 2.623e-05 [overlap_param_gather]: 1.94e-06 [cconv]: 4.001e-05 [loop_unroll]: 0.00055866 [opt_after_cconv]: 0.0001662, [1] [Cycle 1]: 0.00015684, [7] [c_1]: 5.825e-05 [parameter_eliminate]: 5.57999e-06 [updatestate_depend_eliminate]: 1.12e-05 [updatestate_assign_eliminate]: 4.89e-06 [updatestate_loads_eliminate]: 4.48999e-06 [cse]: 3.157e-05 [renormalize]: 5.19998e-07 [remove_dup_value]: 1.653e-05 [tuple_transform]: 9.672e-05, [1] [Cycle 1]: 9.066e-05, [4] [d_1]: 5.851e-05 [none_parameter_eliminate]: 2.09e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 9.70002e-06 [partial_unused_args_eliminate]: 2.51e-06 [add_recomputation]: 8.112e-05 [cse_after_recomputation]: 3.055e-05, [1] [Cycle 1]: 2.455e-05, [1] [cse]: 1.773e-05 [environ_conv]: 2.535e-05 [swap_dp_allreduce_reducescatter]: 7.86001e-06 [bias_add_comm_swap]: 3.88999e-06 [label_micro_interleaved_index]: 4.79e-06 [label_fine_grained_interleaved_index]: 2.81999e-06 [merge_cast_opt]: 1.37e-06 [slice_recompute_activation]: 2.21998e-06 [micro_interleaved_order_control]: 2.17001e-06 [assign_add_opt]: 1.46002e-06 [ForceFp32Comm]: 9.00007e-07 [remove_cast_before_assign_add]: 1.40001e-06 [full_micro_interleaved_order_control]: 2.24001e-06 [reorder_send_recv_between_fp_bp]: 2.76999e-06 [comm_op_add_attrs]: 1.10001e-06 [add_comm_op_reuse_tag]: 1.20001e-06 [interleave_split_concat_branches]: 1.12999e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 2.792e-05 [overlap_opt_shard_grad_in_pipeline]: 1.80001e-06 [control_data_broadcast_order]: 2.143e-05 [grouped_pairwise_exchange_alltoall]: 1.66998e-06 [offloading_packed_experts]: 5.46998e-06 [overlap_recompute_and_grad_model_parallel]: 6.34001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37999e-06 [overlap_recompute_comm]: 2.22001e-06 [overlap_grad_ring_attention]: 5.79999e-06 [overlap_grad_flash_sp]: 3.136e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.32001e-06 [split_layernorm_comm]: 1.86e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 0.00011087, [1] [Cycle 1]: 0.0001047, [6] [build]: 6.17999e-06 [elim_shapecalc]: 1.814e-05 [elim_not_effective]: 1.902e-05 [opt_reshape]: 1.075e-05 [fold_const_symbol]: 1.445e-05 [renormalize]: 2.89991e-07 [detach_backward]: 2.64001e-06 [pipeline_parallel_scheduler]: 1.44e-06 [auto_monad_reorder]: 4.006e-05 [get_jit_bprop_graph]: 2.24001e-06 [rewriter_after_jit_bprop_graph]: 6.50002e-06 [opt_after_jit_grad]: 0.00065415 [validate]: 7.776e-05 [backend_pass]: 1.75001e-06 [task_emit]: 32.1622 [execute]: 1.067e-05 Sums bootstrap : 0.000627s : 0.00% type_inference : 0.191825s : 0.59% event_method : 0.000015s : 0.00% auto_monad : 0.000175s : 0.00% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000051s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000027s : 0.00% optimize.rewriter_before_opt_a : 0.000070s : 0.00% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000041s : 0.00% optimize.opt_a.loop_unroll : 0.000021s : 0.00% optimize.opt_a.a_1 : 0.000590s : 0.00% optimize.opt_a.with_stream_mark : 0.000043s : 0.00% optimize.opt_a.recompute_prepare : 0.000026s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000245s : 0.00% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000020s : 0.00% optimize.opt_a.merge_send_recv : 0.000036s : 0.00% optimize.opt_a.auto_parallel : 0.000021s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000013s : 0.00% optimize.opt_a.allreduce_fusion : 0.000011s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.00% optimize.opt_a.virtual_dataset : 0.000017s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.00% optimize.opt_a.virtual_output : 0.000017s : 0.00% optimize.opt_a.merge_forward : 0.000013s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000027s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000054s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000032s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.00% optimize.opt_a.meta_fg_expand : 0.000008s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000013s : 0.00% optimize.opt_a.after_resolve : 0.000029s : 0.00% optimize.opt_a.a_after_grad : 0.000027s : 0.00% optimize.opt_a.renormalize : 0.000873s : 0.00% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000044s : 0.00% optimize.opt_a.cse : 0.000084s : 0.00% optimize.opt_a.a_3 : 0.000130s : 0.00% 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 : 0.000185s : 0.00% optimize.convert_after_rewriter : 0.000031s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000771s : 0.00% optimize.opt_b.b_1 : 0.000192s : 0.00% optimize.opt_b.b_2 : 0.000012s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 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 : 0.000038s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.00% optimize.loop_unroll : 0.000559s : 0.00% optimize.opt_after_cconv.c_1 : 0.000058s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 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 : 0.000032s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000059s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000081s : 0.00% optimize.cse_after_recomputation.cse : 0.000018s : 0.00% optimize.environ_conv : 0.000025s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 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 : 0.000001s : 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 : 0.000028s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 0.00% 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000014s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000040s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000654s : 0.00% validate : 0.000078s : 0.00% backend_pass : 0.000002s : 0.00% task_emit : 32.162178s : 99.39% execute : 0.000011s : 0.00% Time group info: ------[substitution.] 0.000196 55 5.17% : 0.000010s : 2: substitution.depend_value_elim 1.51% : 0.000003s : 5: substitution.elim_not_effective 1.05% : 0.000002s : 5: substitution.fold_const_symbol 3.77% : 0.000007s : 6: substitution.graph_param_transform 54.41% : 0.000107s : 1: substitution.inline 3.54% : 0.000007s : 10: substitution.j_node_and_user_rematch 10.18% : 0.000020s : 10: substitution.remove_not_recompute_node 2.92% : 0.000006s : 2: substitution.replace_old_param 10.13% : 0.000020s : 6: substitution.updatestate_pure_node_eliminater 7.33% : 0.000014s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.191765 2 99.77% : 0.191332s : 1: type_inference.infer 0.23% : 0.000433s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000106 1 100.00% : 0.000106s : 1: match.inline ------[predicate.] 0.000242 1419 0.77% : 0.000002s : 13: predicate.accumulaten_eliminater 1.29% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.68% : 0.000002s : 12: predicate.addn_check_dump 0.83% : 0.000002s : 13: predicate.addn_zero_filter 0.70% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 2.50% : 0.000006s : 25: predicate.arithmetic_simplify 0.82% : 0.000002s : 13: predicate.cast_eliminate 0.78% : 0.000002s : 12: predicate.check_bprop_eliminate 0.63% : 0.000002s : 12: predicate.compare_switch_simplify 0.20% : 0.000000s : 6: predicate.const_output_eliminate 0.77% : 0.000002s : 12: predicate.depend_value_elim 0.81% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.86% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.82% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.37% : 0.000003s : 12: predicate.dumpgradient_eliminate 0.35% : 0.000001s : 6: predicate.elim_not_effective 0.56% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.07% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 19: predicate.environ_get_add_eliminate 1.07% : 0.000003s : 19: predicate.environ_get_depend_swap 1.77% : 0.000004s : 31: predicate.environ_get_eliminate 1.08% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.51% : 0.000004s : 14: predicate.float_depend_g_call 0.64% : 0.000002s : 12: predicate.float_environ_get_switch 1.14% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.19% : 0.000000s : 6: predicate.fold_const_symbol 0.77% : 0.000002s : 12: predicate.get_grad_eliminate 0.33% : 0.000001s : 6: predicate.graph_param_transform 0.82% : 0.000002s : 12: predicate.incorporate_call 0.65% : 0.000002s : 12: predicate.incorporate_call_switch 5.76% : 0.000014s : 63: predicate.inline 0.99% : 0.000002s : 12: predicate.inline_without_move 0.36% : 0.000001s : 12: predicate.j_node_and_user_rematch 0.99% : 0.000002s : 12: predicate.less_batch_normalization 1.72% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.37% : 0.000006s : 38: predicate.load_eliminater 1.25% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.12% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.82% : 0.000004s : 25: predicate.make_slice_get_slice_eliminator 0.79% : 0.000002s : 12: predicate.merge_addn 0.74% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.82% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 13: predicate.minmaximum_grad 1.37% : 0.000003s : 6: predicate.mutable_eliminate 0.92% : 0.000002s : 6: predicate.opt_reshape 0.48% : 0.000001s : 6: predicate.parallel_virtual_node 1.02% : 0.000002s : 14: predicate.partial_defer_inline 1.19% : 0.000003s : 19: predicate.partial_eliminate 0.82% : 0.000002s : 13: predicate.print_const_string_wrapper 0.74% : 0.000002s : 12: predicate.reduce_all_const_elim 1.18% : 0.000003s : 13: predicate.reduce_eliminate 2.13% : 0.000005s : 38: predicate.redundant_stop_gradient_eliminater 0.60% : 0.000001s : 12: predicate.remove_not_recompute_node 1.13% : 0.000003s : 25: predicate.replace_applicator 0.79% : 0.000002s : 12: predicate.replace_old_param 0.37% : 0.000001s : 6: predicate.reset_defer_inline 0.79% : 0.000002s : 13: predicate.reshape_eliminate 0.79% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.48% : 0.000001s : 6: predicate.row_tensor_eliminate 0.91% : 0.000002s : 12: predicate.same_eliminate 0.47% : 0.000001s : 12: predicate.set_cell_output_no_recompute 1.11% : 0.000003s : 12: predicate.shard_identity_eliminate 1.02% : 0.000002s : 12: predicate.special_op_eliminate 0.86% : 0.000002s : 12: predicate.specialize_transform 1.66% : 0.000004s : 12: predicate.split_environ_get_set_with_tuple_value 1.16% : 0.000003s : 12: predicate.stack_unstack_eliminate 0.43% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.82% : 0.000002s : 14: predicate.switch_defer_inline 1.51% : 0.000004s : 26: predicate.switch_layer_defer_inline 3.45% : 0.000008s : 49: predicate.switch_simplify 0.79% : 0.000002s : 13: predicate.tile_eliminate 1.02% : 0.000002s : 13: predicate.transpose_eliminate 1.68% : 0.000004s : 25: predicate.tuple_list_convert_item_index_to_positive 1.69% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.65% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 3.43% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.62% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.62% : 0.000006s : 37: predicate.tuple_list_set_item_eliminator 1.55% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.27% : 0.000005s : 38: predicate.updatestate_pure_node_eliminater 3.36% : 0.000008s : 50: predicate.updatestate_useless_node_eliminater 0.58% : 0.000001s : 6: predicate.value_based_eliminate 0.77% : 0.000002s : 12: predicate.virtual_dataset_eliminate 0.75% : 0.000002s : 12: predicate.virtual_output_eliminate 0.37% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000249 4 10.03% : 0.000025s : 1: func_graph_cloner_run.FuncGraphClonerGraph 89.97% : 0.000224s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 32.825189 196 0.00% : 0.000004s : 1: ForceFp32Comm 0.69% : 0.227087s : 1: add_attr 0.69% : 0.227069s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000088s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000183s : 1: auto_monad 0.00% : 0.000047s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: backend_pass 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.00% : 0.000671s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000037s : 1: convert_after_rewriter 0.00% : 0.000034s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000030s : 1: environ_conv 0.00% : 0.000022s : 1: event_method 0.00% : 0.000019s : 1: execute 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.00% : 0.000575s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.00% : 0.000788s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000026s : 1: opt.transform.mutable_eliminate 0.00% : 0.001212s : 78: opt.transform.opt_a 0.00% : 0.000057s : 1: opt.transform.opt_after_cconv 0.00% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000175s : 28: opt.transform.opt_b 0.00% : 0.000066s : 2: opt.transform.opt_trans_graph 0.00% : 0.000057s : 4: opt.transform.symbol_engine_opt 0.01% : 0.003258s : 1: opt_a 0.00% : 0.000218s : 1: opt_after_cconv 0.00% : 0.000673s : 1: opt_after_jit_grad 0.00% : 0.000319s : 1: opt_b 0.02% : 0.006327s : 1: optimize 0.00% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 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% : 0.000033s : 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% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000057s : 1: pre_auto_parallel 0.00% : 0.000031s : 1: py_interpret_to_execute 0.00% : 0.000024s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 0.00% : 0.000552s : 1: renormalize.infer 0.00% : 0.000308s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000196s : 1: rewriter_after_opt_a 0.00% : 0.000075s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000114s : 1: symbol_engine_optimizer 97.98% : 32.162207s : 1: task_emit 0.00% : 0.000100s : 1: tuple_transform 0.58% : 0.191846s : 1: type_inference 0.00% : 0.000124s : 1: validate TotalTime = 0.254766, [24] [bootstrap]: 0.00055149 [type_inference]: 0.00444491 [event_method]: 1.948e-05 [auto_monad]: 0.00017747 [graph_reusing]: 6.96999e-06 [inline]: 3.83999e-06 [add_attr]: 0.00582557, [1] [add_attr_with_inline]: 0.00581026, [1] [Cycle 1]: 7.249e-05, [2] [tag_attr]: 2.037e-05 [meta_addattr_fg_expand]: 3.88001e-06 [parallel-infer-symbol]: 4.15e-06 [pre_auto_parallel]: 4.239e-05 [insert-virtual-dataset]: 2.86e-06 [parallel-infer-symbol-second]: 9.09989e-07 [dataset_repeat_opt]: 2.44999e-06 [pipeline_split]: 1.95001e-06 [optimize]: 0.231574, [53] [py_interpret_to_execute]: 2.817e-05 [rewriter_before_opt_a]: 6.214e-05 [opt_a]: 0.22836, [2] [Cycle 1]: 0.227253, [45] [expand_dump_flag]: 3.46999e-06 [switch_simplify]: 2.846e-05 [loop_unroll]: 1.307e-05 [a_1]: 0.00041821 [with_stream_mark]: 2.272e-05 [recompute_prepare]: 1.319e-05 [updatestate_depend_eliminate]: 7e-06 [updatestate_assign_eliminate]: 5.81998e-06 [updatestate_loads_eliminate]: 6.41e-06 [parameter_eliminate]: 2.49001e-06 [a_2]: 0.00012714 [accelerated_algorithm]: 1.305e-05 [shard]: 3.13998e-06 [meta_shard_fg_expand]: 4.15e-06 [shard_inline]: 9.52999e-06 [merge_send_recv]: 1.48e-05 [auto_parallel]: 1.271e-05 [parallel]: 3.816e-05 [flash_sp]: 1.493e-05 [merge_comm]: 6.73998e-06 [allreduce_fusion]: 5.50001e-06 [matmul_add_comm_reduction]: 1.47e-05 [allreduce_slice_to_reducescatter]: 7.80012e-07 [virtual_shard_identity]: 1.828e-05 [virtual_dataset]: 8.69e-06 [get_grad_eliminate_]: 8.71002e-06 [virtual_output]: 9.14e-06 [merge_forward]: 7.16999e-06 [cell_reuse_recompute_pass]: 2.11998e-06 [offload_activation]: 1.686e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.642e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 2.049e-05 [set_forward_comm_id_for_comm_node_pass]: 6.84999e-06 [meta_fg_expand]: 5.56e-06 [flash_sp_send_recv_attached]: 3.09001e-06 [receive_attached]: 2.54999e-06 [after_resolve]: 0.224564 [a_after_grad]: 3.03e-05 [renormalize]: 0.00115743 [add_forward_monad_depend]: 1.776e-05 [auto_monad_grad]: 2.44001e-06 [auto_monad_eliminator]: 2.791e-05 [cse]: 4.453e-05 [a_3]: 7.826e-05 [Cycle 2]: 0.00109118, [45] [expand_dump_flag]: 2.59999e-06 [switch_simplify]: 1.164e-05 [loop_unroll]: 9.56e-06 [a_1]: 0.00022324 [with_stream_mark]: 2.365e-05 [recompute_prepare]: 1.04e-05 [updatestate_depend_eliminate]: 6.78e-06 [updatestate_assign_eliminate]: 5.86e-06 [updatestate_loads_eliminate]: 6.32001e-06 [parameter_eliminate]: 1.87999e-06 [a_2]: 0.00012088 [accelerated_algorithm]: 1.111e-05 [shard]: 3.25e-06 [meta_shard_fg_expand]: 3.63999e-06 [shard_inline]: 9.30001e-06 [merge_send_recv]: 1.244e-05 [auto_parallel]: 1.315e-05 [parallel]: 1.031e-05 [flash_sp]: 4.64002e-06 [merge_comm]: 6.43998e-06 [allreduce_fusion]: 6.24999e-06 [matmul_add_comm_reduction]: 1.396e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.159e-05 [virtual_dataset]: 1.026e-05 [get_grad_eliminate_]: 8.68001e-06 [virtual_output]: 9.52999e-06 [merge_forward]: 7.12002e-06 [cell_reuse_recompute_pass]: 3.93001e-06 [offload_activation]: 1.854e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.158e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 1.733e-05 [set_forward_comm_id_for_comm_node_pass]: 7.56999e-06 [meta_fg_expand]: 5.22e-06 [flash_sp_send_recv_attached]: 2.36998e-06 [receive_attached]: 2.48e-06 [after_resolve]: 1.601e-05 [a_after_grad]: 1.415e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.51e-06 [auto_monad_grad]: 2.14e-06 [auto_monad_eliminator]: 1.748e-05 [cse]: 2.626e-05 [a_3]: 5.394e-05 [py_interpret_to_execute_after_opt_a]: 2.317e-05 [slice_cell_reuse_recomputed_activation]: 2.48e-06 [rewriter_after_opt_a]: 0.00023006 [convert_after_rewriter]: 1.434e-05 [order_py_execute_after_rewriter]: 7.87e-06 [mutable_eliminate]: 0.00087085 [opt_b]: 0.00042757, [1] [Cycle 1]: 0.00041791, [7] [b_1]: 0.00029434 [b_2]: 1.232e-05 [updatestate_depend_eliminate]: 1.284e-05 [updatestate_assign_eliminate]: 5.77999e-06 [updatestate_loads_eliminate]: 5.29998e-06 [renormalize]: 5.39992e-07 [cse]: 3.563e-05 [optimize_parallel_all_gather_comm]: 2.685e-05 [overlap_param_gather]: 2.51e-06 [cconv]: 3.948e-05 [loop_unroll]: 0.00053924 [opt_after_cconv]: 0.00015493, [1] [Cycle 1]: 0.0001476, [7] [c_1]: 5.59e-05 [parameter_eliminate]: 5.54e-06 [updatestate_depend_eliminate]: 8.87999e-06 [updatestate_assign_eliminate]: 5.19e-06 [updatestate_loads_eliminate]: 4.49002e-06 [cse]: 2.622e-05 [renormalize]: 4.59986e-07 [remove_dup_value]: 1.719e-05 [tuple_transform]: 9.725e-05, [1] [Cycle 1]: 9.175e-05, [4] [d_1]: 5.863e-05 [none_parameter_eliminate]: 1.77001e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 9.46998e-06 [partial_unused_args_eliminate]: 1.92999e-06 [add_recomputation]: 0.00012565 [cse_after_recomputation]: 3.22e-05, [1] [Cycle 1]: 2.567e-05, [1] [cse]: 1.886e-05 [environ_conv]: 9.46998e-06 [swap_dp_allreduce_reducescatter]: 8.43001e-06 [bias_add_comm_swap]: 3.86001e-06 [label_micro_interleaved_index]: 4.83001e-06 [label_fine_grained_interleaved_index]: 2.84999e-06 [merge_cast_opt]: 1.59e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.43998e-06 [assign_add_opt]: 1.25999e-06 [ForceFp32Comm]: 9.39996e-07 [remove_cast_before_assign_add]: 1.12e-06 [full_micro_interleaved_order_control]: 2.48e-06 [reorder_send_recv_between_fp_bp]: 3.06001e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.37999e-06 [interleave_split_concat_branches]: 1.26997e-06 [interleave_parallel_branches]: 1.30001e-06 [overlap_opt_shard_in_pipeline]: 1.23002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.09e-06 [control_data_broadcast_order]: 1.913e-05 [grouped_pairwise_exchange_alltoall]: 1.72001e-06 [offloading_packed_experts]: 5.49e-06 [overlap_recompute_and_grad_model_parallel]: 6.54001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.45001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.64998e-06 [overlap_recompute_comm]: 2.34001e-06 [overlap_grad_ring_attention]: 5.46e-06 [overlap_grad_flash_sp]: 3.112e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 1.83002e-06 [handle_group_info]: 1.17999e-06 [symbol_engine_optimizer]: 0.00010501, [1] [Cycle 1]: 0.00010012, [6] [build]: 5.59e-06 [elim_shapecalc]: 1.524e-05 [elim_not_effective]: 1.841e-05 [opt_reshape]: 1.005e-05 [fold_const_symbol]: 1.587e-05 [renormalize]: 3.7998e-07 [detach_backward]: 2.70002e-06 [pipeline_parallel_scheduler]: 1.62001e-06 [auto_monad_reorder]: 3.22e-05 [get_jit_bprop_graph]: 1.96998e-06 [rewriter_after_jit_bprop_graph]: 8.10999e-06 [opt_after_jit_grad]: 0.00060435 [validate]: 7.235e-05 [backend_pass]: 1.56002e-06 [task_emit]: 0.0110747 [execute]: 1.152e-05 Sums bootstrap : 0.000551s : 0.22% type_inference : 0.004445s : 1.80% event_method : 0.000019s : 0.01% auto_monad : 0.000177s : 0.07% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 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 : 0.000042s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000028s : 0.01% optimize.rewriter_before_opt_a : 0.000062s : 0.03% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000040s : 0.02% optimize.opt_a.loop_unroll : 0.000023s : 0.01% optimize.opt_a.a_1 : 0.000641s : 0.26% optimize.opt_a.with_stream_mark : 0.000046s : 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 : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000013s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000248s : 0.10% optimize.opt_a.accelerated_algorithm : 0.000024s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000019s : 0.01% optimize.opt_a.merge_send_recv : 0.000027s : 0.01% optimize.opt_a.auto_parallel : 0.000026s : 0.01% optimize.opt_a.parallel : 0.000048s : 0.02% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000012s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000029s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.01% optimize.opt_a.virtual_dataset : 0.000019s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.01% optimize.opt_a.virtual_output : 0.000019s : 0.01% optimize.opt_a.merge_forward : 0.000014s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000035s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000038s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.01% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.224580s : 90.75% optimize.opt_a.a_after_grad : 0.000044s : 0.02% optimize.opt_a.renormalize : 0.001157s : 0.47% optimize.opt_a.add_forward_monad_depend : 0.000020s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000045s : 0.02% optimize.opt_a.cse : 0.000071s : 0.03% optimize.opt_a.a_3 : 0.000132s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000230s : 0.09% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000871s : 0.35% optimize.opt_b.b_1 : 0.000294s : 0.12% optimize.opt_b.b_2 : 0.000012s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000036s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000039s : 0.02% optimize.loop_unroll : 0.000539s : 0.22% optimize.opt_after_cconv.c_1 : 0.000056s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000026s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000017s : 0.01% optimize.tuple_transform.d_1 : 0.000059s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000126s : 0.05% optimize.cse_after_recomputation.cse : 0.000019s : 0.01% optimize.environ_conv : 0.000009s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 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 : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 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 : 0.000007s : 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 : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 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 : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000018s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000016s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000032s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000604s : 0.24% validate : 0.000072s : 0.03% backend_pass : 0.000002s : 0.00% task_emit : 0.011075s : 4.48% execute : 0.000012s : 0.00% Time group info: ------[substitution.] 0.000218 55 5.46% : 0.000012s : 2: substitution.depend_value_elim 1.42% : 0.000003s : 5: substitution.elim_not_effective 0.96% : 0.000002s : 5: substitution.fold_const_symbol 3.58% : 0.000008s : 6: substitution.graph_param_transform 60.36% : 0.000131s : 1: substitution.inline 3.21% : 0.000007s : 10: substitution.j_node_and_user_rematch 4.55% : 0.000010s : 10: substitution.remove_not_recompute_node 4.72% : 0.000010s : 2: substitution.replace_old_param 8.99% : 0.000020s : 6: substitution.updatestate_pure_node_eliminater 6.75% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.004379 2 86.52% : 0.003789s : 1: type_inference.infer 13.48% : 0.000590s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000130 1 100.00% : 0.000130s : 1: match.inline ------[predicate.] 0.000269 1419 0.79% : 0.000002s : 13: predicate.accumulaten_eliminater 1.23% : 0.000003s : 6: predicate.ad_related_special_op_eliminate 0.79% : 0.000002s : 12: predicate.addn_check_dump 0.91% : 0.000002s : 13: predicate.addn_zero_filter 0.65% : 0.000002s : 13: predicate.adjust_all_reduce_mul_add 1.94% : 0.000005s : 25: predicate.arithmetic_simplify 0.76% : 0.000002s : 13: predicate.cast_eliminate 0.74% : 0.000002s : 12: predicate.check_bprop_eliminate 0.75% : 0.000002s : 12: predicate.compare_switch_simplify 0.18% : 0.000000s : 6: predicate.const_output_eliminate 0.84% : 0.000002s : 12: predicate.depend_value_elim 0.77% : 0.000002s : 13: predicate.dict_get_item_const_eliminator 0.79% : 0.000002s : 13: predicate.dict_get_item_eliminator 0.79% : 0.000002s : 13: predicate.dict_set_item_eliminator 1.33% : 0.000004s : 12: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 6: predicate.elim_not_effective 0.42% : 0.000001s : 6: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000003s : 19: predicate.environ_add_const_eliminate 1.12% : 0.000003s : 19: predicate.environ_get_add_eliminate 0.98% : 0.000003s : 19: predicate.environ_get_depend_swap 1.71% : 0.000005s : 31: predicate.environ_get_eliminate 1.08% : 0.000003s : 19: predicate.environ_get_set_eliminate 0.89% : 0.000002s : 14: predicate.exchange_switch_depend_value 1.55% : 0.000004s : 14: predicate.float_depend_g_call 0.87% : 0.000002s : 12: predicate.float_environ_get_switch 1.06% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 6: predicate.fold_const_symbol 0.83% : 0.000002s : 12: predicate.get_grad_eliminate 0.22% : 0.000001s : 6: predicate.graph_param_transform 0.67% : 0.000002s : 12: predicate.incorporate_call 0.57% : 0.000002s : 12: predicate.incorporate_call_switch 4.97% : 0.000013s : 63: predicate.inline 1.81% : 0.000005s : 12: predicate.inline_without_move 0.32% : 0.000001s : 12: predicate.j_node_and_user_rematch 1.39% : 0.000004s : 12: predicate.less_batch_normalization 1.75% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.26% : 0.000006s : 38: predicate.load_eliminater 1.09% : 0.000003s : 6: predicate.loop_unroll_after_grad 1.23% : 0.000003s : 17: predicate.loop_unroll_before_grad 1.76% : 0.000005s : 25: predicate.make_slice_get_slice_eliminator 0.81% : 0.000002s : 12: predicate.merge_addn 0.66% : 0.000002s : 12: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 12: predicate.mini_step_allgather_replace 0.70% : 0.000002s : 13: predicate.minmaximum_grad 2.06% : 0.000006s : 6: predicate.mutable_eliminate 0.41% : 0.000001s : 6: predicate.opt_reshape 0.61% : 0.000002s : 6: predicate.parallel_virtual_node 1.02% : 0.000003s : 14: predicate.partial_defer_inline 1.09% : 0.000003s : 19: predicate.partial_eliminate 0.78% : 0.000002s : 13: predicate.print_const_string_wrapper 0.74% : 0.000002s : 12: predicate.reduce_all_const_elim 1.05% : 0.000003s : 13: predicate.reduce_eliminate 2.41% : 0.000006s : 38: predicate.redundant_stop_gradient_eliminater 0.61% : 0.000002s : 12: predicate.remove_not_recompute_node 1.09% : 0.000003s : 25: predicate.replace_applicator 1.15% : 0.000003s : 12: predicate.replace_old_param 0.33% : 0.000001s : 6: predicate.reset_defer_inline 0.82% : 0.000002s : 13: predicate.reshape_eliminate 0.82% : 0.000002s : 12: predicate.row_tensor_add_zeros_like 0.70% : 0.000002s : 6: predicate.row_tensor_eliminate 0.86% : 0.000002s : 12: predicate.same_eliminate 0.42% : 0.000001s : 12: predicate.set_cell_output_no_recompute 1.17% : 0.000003s : 12: predicate.shard_identity_eliminate 0.87% : 0.000002s : 12: predicate.special_op_eliminate 0.82% : 0.000002s : 12: predicate.specialize_transform 1.14% : 0.000003s : 12: predicate.split_environ_get_set_with_tuple_value 2.04% : 0.000005s : 12: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 6: predicate.switch_call_monad_eliminater 0.89% : 0.000002s : 14: predicate.switch_defer_inline 1.71% : 0.000005s : 26: predicate.switch_layer_defer_inline 3.37% : 0.000009s : 49: predicate.switch_simplify 0.74% : 0.000002s : 13: predicate.tile_eliminate 0.93% : 0.000003s : 13: predicate.transpose_eliminate 1.79% : 0.000005s : 25: predicate.tuple_list_convert_item_index_to_positive 1.61% : 0.000004s : 25: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000004s : 25: predicate.tuple_list_get_item_depend_reorder 2.99% : 0.000008s : 37: predicate.tuple_list_get_item_eliminator 1.50% : 0.000004s : 25: predicate.tuple_list_get_set_item_eliminator 2.64% : 0.000007s : 37: predicate.tuple_list_set_item_eliminator 1.87% : 0.000005s : 25: predicate.tuple_to_list_eliminator_ 2.12% : 0.000006s : 38: predicate.updatestate_pure_node_eliminater 3.36% : 0.000009s : 50: predicate.updatestate_useless_node_eliminater 0.59% : 0.000002s : 6: predicate.value_based_eliminate 1.00% : 0.000003s : 12: predicate.virtual_dataset_eliminate 0.85% : 0.000002s : 12: predicate.virtual_output_eliminate 0.34% : 0.000001s : 6: predicate.virtual_view_grad_eliminate 0.47% : 0.000001s : 6: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000393 4 6.32% : 0.000025s : 1: func_graph_cloner_run.FuncGraphClonerGraph 93.68% : 0.000368s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.719563 196 0.00% : 0.000004s : 1: ForceFp32Comm 0.81% : 0.005833s : 1: add_attr 0.81% : 0.005816s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000131s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000188s : 1: auto_monad 0.01% : 0.000036s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: backend_pass 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.08% : 0.000584s : 1: bootstrap 0.01% : 0.000045s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000023s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000035s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000013s : 1: environ_conv 0.00% : 0.000028s : 1: event_method 0.00% : 0.000021s : 1: execute 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000007s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.08% : 0.000549s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.12% : 0.000887s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 31.38% : 0.225831s : 78: opt.transform.opt_a 0.01% : 0.000054s : 1: opt.transform.opt_after_cconv 0.01% : 0.000038s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000273s : 28: opt.transform.opt_b 0.01% : 0.000065s : 2: opt.transform.opt_trans_graph 0.01% : 0.000055s : 4: opt.transform.symbol_engine_opt 31.74% : 0.228365s : 1: opt_a 0.02% : 0.000159s : 1: opt_after_cconv 0.09% : 0.000616s : 1: opt_after_jit_grad 0.06% : 0.000432s : 1: opt_b 32.18% : 0.231581s : 1: optimize 0.00% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 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% : 0.000004s : 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% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000048s : 1: pre_auto_parallel 0.00% : 0.000033s : 1: py_interpret_to_execute 0.00% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 0.09% : 0.000659s : 1: renormalize.infer 0.07% : 0.000484s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000240s : 1: rewriter_after_opt_a 0.01% : 0.000068s : 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% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000108s : 1: symbol_engine_optimizer 1.54% : 0.011099s : 1: task_emit 0.01% : 0.000101s : 1: tuple_transform 0.62% : 0.004472s : 1: type_inference 0.02% : 0.000124s : 1: validate TotalTime = 1.57879, [24] [bootstrap]: 0.00057858 [type_inference]: 0.218975 [event_method]: 8.942e-05 [auto_monad]: 0.00034057 [graph_reusing]: 1.155e-05 [inline]: 3.58e-06 [add_attr]: 0.0048512, [1] [add_attr_with_inline]: 0.00483837, [1] [Cycle 1]: 0.00012206, [2] [tag_attr]: 6.13e-05 [meta_addattr_fg_expand]: 1.075e-05 [parallel-infer-symbol]: 4.28001e-06 [pre_auto_parallel]: 7.607e-05 [insert-virtual-dataset]: 3.14999e-06 [parallel-infer-symbol-second]: 6.99976e-07 [dataset_repeat_opt]: 2.56998e-06 [pipeline_split]: 1.96e-06 [optimize]: 0.923408, [53] [py_interpret_to_execute]: 7.057e-05 [rewriter_before_opt_a]: 0.00023383 [opt_a]: 0.919352, [3] [Cycle 1]: 0.905912, [45] [expand_dump_flag]: 1.161e-05 [switch_simplify]: 7.683e-05 [loop_unroll]: 7.708e-05 [a_1]: 0.00290494 [with_stream_mark]: 6.059e-05 [recompute_prepare]: 6.006e-05 [updatestate_depend_eliminate]: 2.078e-05 [updatestate_assign_eliminate]: 1.504e-05 [updatestate_loads_eliminate]: 1.404e-05 [parameter_eliminate]: 5.41002e-06 [a_2]: 0.00041833 [accelerated_algorithm]: 6.464e-05 [shard]: 3.5e-06 [meta_shard_fg_expand]: 1.391e-05 [shard_inline]: 2.441e-05 [merge_send_recv]: 3.129e-05 [auto_parallel]: 2.545e-05 [parallel]: 2.657e-05 [flash_sp]: 1.815e-05 [merge_comm]: 1.669e-05 [allreduce_fusion]: 1.493e-05 [matmul_add_comm_reduction]: 5.268e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 3.493e-05 [virtual_dataset]: 2.844e-05 [get_grad_eliminate_]: 2.864e-05 [virtual_output]: 2.734e-05 [merge_forward]: 1.718e-05 [cell_reuse_recompute_pass]: 2.26e-06 [offload_activation]: 3.988e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.668e-05 [merge_recompute_call_nodes]: 2.66e-06 [before_grad]: 5.616e-05 [set_forward_comm_id_for_comm_node_pass]: 1.942e-05 [meta_fg_expand]: 0.581459 [flash_sp_send_recv_attached]: 6.94999e-06 [receive_attached]: 2.84001e-06 [after_resolve]: 0.0001843 [a_after_grad]: 0.00023276 [renormalize]: 0.316376 [add_forward_monad_depend]: 3.183e-05 [auto_monad_grad]: 2.082e-05 [auto_monad_eliminator]: 0.00017031 [cse]: 0.00052478 [a_3]: 0.00201113 [Cycle 2]: 0.0122533, [45] [expand_dump_flag]: 4.57998e-06 [switch_simplify]: 0.00010844 [loop_unroll]: 0.00010294 [a_1]: 0.00743352 [with_stream_mark]: 0.00022545 [recompute_prepare]: 2.787e-05 [updatestate_depend_eliminate]: 4.265e-05 [updatestate_assign_eliminate]: 7.48999e-06 [updatestate_loads_eliminate]: 6.04999e-06 [parameter_eliminate]: 2.96001e-06 [a_2]: 0.00017034 [accelerated_algorithm]: 2.011e-05 [shard]: 2.17001e-06 [meta_shard_fg_expand]: 6.93e-06 [shard_inline]: 1.212e-05 [merge_send_recv]: 1.346e-05 [auto_parallel]: 1.337e-05 [parallel]: 1.201e-05 [flash_sp]: 4.90001e-06 [merge_comm]: 7.33999e-06 [allreduce_fusion]: 6.75002e-06 [matmul_add_comm_reduction]: 1.654e-05 [allreduce_slice_to_reducescatter]: 1.39e-06 [virtual_shard_identity]: 1.804e-05 [virtual_dataset]: 1.329e-05 [get_grad_eliminate_]: 1.065e-05 [virtual_output]: 1.075e-05 [merge_forward]: 6.78e-06 [cell_reuse_recompute_pass]: 1.42999e-06 [offload_activation]: 1.58e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.421e-05 [merge_recompute_call_nodes]: 1.82001e-06 [before_grad]: 2.257e-05 [set_forward_comm_id_for_comm_node_pass]: 9.92999e-06 [meta_fg_expand]: 0.00011409 [flash_sp_send_recv_attached]: 2.11e-06 [receive_attached]: 2.43998e-06 [after_resolve]: 2.207e-05 [a_after_grad]: 1.909e-05 [renormalize]: 0.00305912 [add_forward_monad_depend]: 9.51998e-06 [auto_monad_grad]: 2.66e-06 [auto_monad_eliminator]: 2.919e-05 [cse]: 0.00015577 [a_3]: 9.813e-05 [Cycle 3]: 0.0011593, [45] [expand_dump_flag]: 2.12999e-06 [switch_simplify]: 1.487e-05 [loop_unroll]: 1.212e-05 [a_1]: 0.00030756 [with_stream_mark]: 1.832e-05 [recompute_prepare]: 1.265e-05 [updatestate_depend_eliminate]: 8.03999e-06 [updatestate_assign_eliminate]: 6.23002e-06 [updatestate_loads_eliminate]: 6.23e-06 [parameter_eliminate]: 1.94e-06 [a_2]: 0.00015451 [accelerated_algorithm]: 1.825e-05 [shard]: 1.69e-06 [meta_shard_fg_expand]: 3.75e-06 [shard_inline]: 1.301e-05 [merge_send_recv]: 1.105e-05 [auto_parallel]: 1.394e-05 [parallel]: 8.96002e-06 [flash_sp]: 1.62001e-06 [merge_comm]: 8.59e-06 [allreduce_fusion]: 6.38e-06 [matmul_add_comm_reduction]: 1.203e-05 [allreduce_slice_to_reducescatter]: 8.09989e-07 [virtual_shard_identity]: 1.346e-05 [virtual_dataset]: 1.238e-05 [get_grad_eliminate_]: 1.06e-05 [virtual_output]: 1.071e-05 [merge_forward]: 7.09001e-06 [cell_reuse_recompute_pass]: 2.46e-06 [offload_activation]: 1.322e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.248e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 1.982e-05 [set_forward_comm_id_for_comm_node_pass]: 8.63001e-06 [meta_fg_expand]: 5.17e-06 [flash_sp_send_recv_attached]: 1.30999e-06 [receive_attached]: 1.84e-06 [after_resolve]: 1.835e-05 [a_after_grad]: 1.833e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.131e-05 [auto_monad_grad]: 1.34998e-06 [auto_monad_eliminator]: 1.88e-05 [cse]: 3.108e-05 [a_3]: 6.841e-05 [py_interpret_to_execute_after_opt_a]: 2.655e-05 [slice_cell_reuse_recomputed_activation]: 1.87001e-06 [rewriter_after_opt_a]: 0.00010294 [convert_after_rewriter]: 1.038e-05 [order_py_execute_after_rewriter]: 0.00016061 [mutable_eliminate]: 0.00088842 [opt_b]: 0.00040239, [1] [Cycle 1]: 0.00039268, [7] [b_1]: 0.00025276 [b_2]: 1.435e-05 [updatestate_depend_eliminate]: 1.07e-05 [updatestate_assign_eliminate]: 6.83998e-06 [updatestate_loads_eliminate]: 6.58e-06 [renormalize]: 2.09984e-07 [cse]: 4.78e-05 [optimize_parallel_all_gather_comm]: 2.767e-05 [overlap_param_gather]: 2.22999e-06 [cconv]: 3.44e-05 [loop_unroll]: 0.00078807 [opt_after_cconv]: 0.00019015, [1] [Cycle 1]: 0.0001825, [7] [c_1]: 7.228e-05 [parameter_eliminate]: 3.03e-06 [updatestate_depend_eliminate]: 1.042e-05 [updatestate_assign_eliminate]: 5.82001e-06 [updatestate_loads_eliminate]: 5.87001e-06 [cse]: 4.15e-05 [renormalize]: 6.10016e-07 [remove_dup_value]: 1.967e-05 [tuple_transform]: 0.00012967, [1] [Cycle 1]: 0.00012386, [4] [d_1]: 8.598e-05 [none_parameter_eliminate]: 2.06e-06 [renormalize]: 2.09984e-07 [switch_simplify]: 1.205e-05 [partial_unused_args_eliminate]: 1.92999e-06 [add_recomputation]: 0.0001092 [cse_after_recomputation]: 4.434e-05, [1] [Cycle 1]: 3.838e-05, [1] [cse]: 3.126e-05 [environ_conv]: 1.159e-05 [swap_dp_allreduce_reducescatter]: 1.141e-05 [bias_add_comm_swap]: 3.21001e-06 [label_micro_interleaved_index]: 4.89e-06 [label_fine_grained_interleaved_index]: 2.88e-06 [merge_cast_opt]: 1.43002e-06 [slice_recompute_activation]: 2.39001e-06 [micro_interleaved_order_control]: 2.32001e-06 [assign_add_opt]: 1.60001e-06 [ForceFp32Comm]: 8.99978e-07 [remove_cast_before_assign_add]: 1.08001e-06 [full_micro_interleaved_order_control]: 2.06e-06 [reorder_send_recv_between_fp_bp]: 2.88e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.51002e-06 [interleave_parallel_branches]: 1.25001e-06 [overlap_opt_shard_in_pipeline]: 1.37e-06 [overlap_opt_shard_grad_in_pipeline]: 1.94e-06 [control_data_broadcast_order]: 2.404e-05 [grouped_pairwise_exchange_alltoall]: 1.47001e-06 [offloading_packed_experts]: 6.04999e-06 [overlap_recompute_and_grad_model_parallel]: 6.88e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.77999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.66e-06 [overlap_recompute_comm]: 2.76999e-06 [overlap_grad_ring_attention]: 6.90002e-06 [overlap_grad_flash_sp]: 3.578e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.56998e-06 [split_layernorm_comm]: 1.92001e-06 [handle_group_info]: 1.15001e-06 [symbol_engine_optimizer]: 0.00033385, [1] [Cycle 1]: 0.00032779, [6] [build]: 0.00020758 [elim_shapecalc]: 1.709e-05 [elim_not_effective]: 2.615e-05 [opt_reshape]: 1.277e-05 [fold_const_symbol]: 2.21e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.21e-06 [pipeline_parallel_scheduler]: 1.35999e-06 [auto_monad_reorder]: 3.829e-05 [get_jit_bprop_graph]: 1.84e-06 [rewriter_after_jit_bprop_graph]: 7.53999e-06 [opt_after_jit_grad]: 0.00055686 [validate]: 7.166e-05 [backend_pass]: 1.00999e-06 [task_emit]: 0.429445 [execute]: 1.323e-05 Sums bootstrap : 0.000579s : 0.04% type_inference : 0.218975s : 13.93% event_method : 0.000089s : 0.01% auto_monad : 0.000341s : 0.02% graph_reusing : 0.000012s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000061s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000011s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000076s : 0.00% 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 : 0.000071s : 0.00% optimize.rewriter_before_opt_a : 0.000234s : 0.01% optimize.opt_a.expand_dump_flag : 0.000018s : 0.00% optimize.opt_a.switch_simplify : 0.000200s : 0.01% optimize.opt_a.loop_unroll : 0.000192s : 0.01% optimize.opt_a.a_1 : 0.010646s : 0.68% optimize.opt_a.with_stream_mark : 0.000304s : 0.02% optimize.opt_a.recompute_prepare : 0.000101s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000071s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000029s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000026s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000743s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000103s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000025s : 0.00% optimize.opt_a.shard_inline : 0.000050s : 0.00% optimize.opt_a.merge_send_recv : 0.000056s : 0.00% optimize.opt_a.auto_parallel : 0.000053s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000033s : 0.00% optimize.opt_a.allreduce_fusion : 0.000028s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000081s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000066s : 0.00% optimize.opt_a.virtual_dataset : 0.000054s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000049s : 0.00% optimize.opt_a.merge_forward : 0.000031s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000069s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000113s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000006s : 0.00% optimize.opt_a.before_grad : 0.000099s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000038s : 0.00% optimize.opt_a.meta_fg_expand : 0.581578s : 37.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000007s : 0.00% optimize.opt_a.after_resolve : 0.000225s : 0.01% optimize.opt_a.a_after_grad : 0.000270s : 0.02% optimize.opt_a.renormalize : 0.319435s : 20.32% optimize.opt_a.add_forward_monad_depend : 0.000053s : 0.00% optimize.opt_a.auto_monad_grad : 0.000025s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000218s : 0.01% optimize.opt_a.cse : 0.000712s : 0.05% optimize.opt_a.a_3 : 0.002178s : 0.14% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000103s : 0.01% optimize.convert_after_rewriter : 0.000010s : 0.00% optimize.order_py_execute_after_rewriter : 0.000161s : 0.01% optimize.mutable_eliminate : 0.000888s : 0.06% optimize.opt_b.b_1 : 0.000253s : 0.02% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000048s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000034s : 0.00% optimize.loop_unroll : 0.000788s : 0.05% optimize.opt_after_cconv.c_1 : 0.000072s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 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 : 0.000041s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000020s : 0.00% optimize.tuple_transform.d_1 : 0.000086s : 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 : 0.000002s : 0.00% optimize.add_recomputation : 0.000109s : 0.01% optimize.cse_after_recomputation.cse : 0.000031s : 0.00% optimize.environ_conv : 0.000012s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 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 : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000208s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 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 : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000038s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000557s : 0.04% validate : 0.000072s : 0.00% backend_pass : 0.000001s : 0.00% task_emit : 0.429445s : 27.32% execute : 0.000013s : 0.00% Time group info: ------[substitution.] 0.004081 310 0.43% : 0.000018s : 4: substitution.depend_value_elim 0.08% : 0.000003s : 7: substitution.elim_not_effective 0.20% : 0.000008s : 7: substitution.float_depend_g_call 0.16% : 0.000007s : 2: substitution.float_tuple_getitem_switch 0.08% : 0.000003s : 7: substitution.fold_const_symbol 43.89% : 0.001791s : 4: substitution.getattr_setattr_resolve 0.24% : 0.000010s : 9: substitution.graph_param_transform 0.10% : 0.000004s : 2: substitution.incorporate_call 0.07% : 0.000003s : 2: substitution.incorporate_call_switch 38.38% : 0.001566s : 24: substitution.inline 1.55% : 0.000063s : 5: substitution.inline_without_move 0.39% : 0.000016s : 28: substitution.j_node_and_user_rematch 0.74% : 0.000030s : 3: substitution.less_batch_normalization 0.42% : 0.000017s : 9: substitution.minmaximum_grad 0.27% : 0.000011s : 7: substitution.partial_eliminate 0.47% : 0.000019s : 28: substitution.remove_not_recompute_node 4.08% : 0.000166s : 38: substitution.replace_applicator 0.53% : 0.000021s : 19: substitution.replace_old_param 0.18% : 0.000007s : 1: substitution.set_cell_output_no_recompute 0.93% : 0.000038s : 9: substitution.tuple_list_convert_item_index_to_positive 0.48% : 0.000020s : 9: substitution.tuple_list_get_item_const_eliminator 0.58% : 0.000024s : 9: substitution.tuple_list_get_item_depend_reorder 3.06% : 0.000125s : 31: substitution.tuple_list_get_item_eliminator 0.59% : 0.000024s : 9: substitution.tuple_list_get_set_item_eliminator 0.83% : 0.000034s : 16: substitution.updatestate_pure_node_eliminater 1.27% : 0.000052s : 21: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.218868 2 99.05% : 0.216788s : 1: type_inference.infer 0.95% : 0.002080s : 1: type_inference.specialize ------[replace.] 0.001323 49 5.66% : 0.000075s : 3: replace.getattr_setattr_resolve 65.73% : 0.000870s : 24: replace.inline 4.18% : 0.000055s : 1: replace.replace_applicator 23.59% : 0.000312s : 20: replace.tuple_list_get_item_eliminator 0.85% : 0.000011s : 1: replace.updatestate_useless_node_eliminater ------[match.] 0.003384 49 51.33% : 0.001737s : 3: match.getattr_setattr_resolve 45.68% : 0.001546s : 24: match.inline 0.54% : 0.000018s : 1: match.replace_applicator 2.02% : 0.000068s : 20: match.tuple_list_get_item_eliminator 0.42% : 0.000014s : 1: match.updatestate_useless_node_eliminater ------[predicate.] 0.004347 8683 0.27% : 0.000012s : 85: predicate.accumulaten_eliminater 0.07% : 0.000003s : 9: predicate.ad_related_special_op_eliminate 0.11% : 0.000005s : 37: predicate.addn_check_dump 0.28% : 0.000012s : 85: predicate.addn_zero_filter 0.25% : 0.000011s : 85: predicate.adjust_all_reduce_mul_add 0.51% : 0.000022s : 122: predicate.arithmetic_simplify 0.26% : 0.000011s : 85: predicate.cast_eliminate 0.76% : 0.000033s : 260: predicate.check_bprop_eliminate 0.12% : 0.000005s : 37: predicate.compare_switch_simplify 0.02% : 0.000001s : 9: predicate.const_output_eliminate 0.13% : 0.000006s : 37: predicate.depend_value_elim 0.28% : 0.000012s : 85: predicate.dict_get_item_const_eliminator 0.30% : 0.000013s : 85: predicate.dict_get_item_eliminator 0.27% : 0.000012s : 85: predicate.dict_set_item_eliminator 0.08% : 0.000003s : 18: predicate.dumpgradient_eliminate 0.02% : 0.000001s : 9: predicate.elim_not_effective 0.04% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 0.28% : 0.000012s : 94: predicate.environ_add_const_eliminate 0.28% : 0.000012s : 94: predicate.environ_get_add_eliminate 0.28% : 0.000012s : 94: predicate.environ_get_depend_swap 0.39% : 0.000017s : 131: predicate.environ_get_eliminate 0.27% : 0.000012s : 94: predicate.environ_get_set_eliminate 0.41% : 0.000018s : 130: predicate.exchange_switch_depend_value 0.59% : 0.000026s : 130: predicate.float_depend_g_call 0.11% : 0.000005s : 37: predicate.float_environ_get_switch 0.15% : 0.000007s : 46: predicate.float_tuple_getitem_switch 0.02% : 0.000001s : 9: predicate.fold_const_symbol 0.13% : 0.000005s : 37: predicate.get_grad_eliminate 0.17% : 0.000007s : 20: predicate.getattr_setattr_resolve 0.02% : 0.000001s : 9: predicate.graph_param_transform 0.11% : 0.000005s : 37: predicate.incorporate_call 0.11% : 0.000005s : 37: predicate.incorporate_call_switch 1.36% : 0.000059s : 307: predicate.inline 0.51% : 0.000022s : 111: predicate.inline_without_move 0.06% : 0.000003s : 37: predicate.j_node_and_user_rematch 0.19% : 0.000008s : 37: predicate.less_batch_normalization 0.46% : 0.000020s : 123: predicate.list_to_tuple_eliminator_ 1.72% : 0.000075s : 208: predicate.load_eliminater 0.08% : 0.000003s : 9: predicate.loop_unroll_after_grad 0.61% : 0.000027s : 197: predicate.loop_unroll_before_grad 0.35% : 0.000015s : 103: predicate.make_slice_get_slice_eliminator 0.12% : 0.000005s : 37: predicate.merge_addn 0.75% : 0.000033s : 256: predicate.micro_step_allgather_replace 0.75% : 0.000032s : 256: predicate.mini_step_allgather_replace 0.25% : 0.000011s : 85: predicate.minmaximum_grad 0.11% : 0.000005s : 9: predicate.mutable_eliminate 0.03% : 0.000001s : 9: predicate.opt_reshape 0.04% : 0.000002s : 9: predicate.parallel_virtual_node 0.70% : 0.000031s : 130: predicate.partial_defer_inline 0.40% : 0.000017s : 114: predicate.partial_eliminate 0.26% : 0.000011s : 85: predicate.print_const_string_wrapper 0.12% : 0.000005s : 37: predicate.reduce_all_const_elim 0.33% : 0.000014s : 85: predicate.reduce_eliminate 0.63% : 0.000027s : 208: predicate.redundant_stop_gradient_eliminater 0.08% : 0.000004s : 37: predicate.remove_not_recompute_node 0.77% : 0.000033s : 363: predicate.replace_applicator 0.22% : 0.000010s : 111: predicate.replace_old_param 0.02% : 0.000001s : 9: predicate.reset_defer_inline 0.26% : 0.000011s : 85: predicate.reshape_eliminate 0.78% : 0.000034s : 256: predicate.row_tensor_add_zeros_like 0.04% : 0.000002s : 9: predicate.row_tensor_eliminate 0.83% : 0.000036s : 260: predicate.same_eliminate 0.09% : 0.000004s : 39: predicate.set_cell_output_no_recompute 0.15% : 0.000006s : 37: predicate.shard_identity_eliminate 0.07% : 0.000003s : 18: predicate.special_op_eliminate 0.15% : 0.000006s : 37: predicate.specialize_transform 0.83% : 0.000036s : 256: predicate.split_environ_get_set_with_tuple_value 0.44% : 0.000019s : 111: predicate.stack_unstack_eliminate 0.03% : 0.000001s : 9: predicate.switch_call_monad_eliminater 0.45% : 0.000020s : 130: predicate.switch_defer_inline 1.20% : 0.000052s : 390: predicate.switch_layer_defer_inline 1.25% : 0.000054s : 373: predicate.switch_simplify 0.25% : 0.000011s : 85: predicate.tile_eliminate 0.26% : 0.000011s : 85: predicate.transpose_eliminate 0.36% : 0.000015s : 103: predicate.tuple_list_convert_item_index_to_positive 0.37% : 0.000016s : 103: predicate.tuple_list_get_item_const_eliminator 0.34% : 0.000015s : 103: predicate.tuple_list_get_item_depend_reorder 0.77% : 0.000033s : 160: predicate.tuple_list_get_item_eliminator 0.37% : 0.000016s : 103: predicate.tuple_list_get_set_item_eliminator 0.58% : 0.000025s : 140: predicate.tuple_list_set_item_eliminator 0.45% : 0.000019s : 123: predicate.tuple_to_list_eliminator_ 1.96% : 0.000085s : 208: predicate.updatestate_pure_node_eliminater 69.31% : 0.003013s : 246: predicate.updatestate_useless_node_eliminater 0.04% : 0.000002s : 9: predicate.value_based_eliminate 0.14% : 0.000006s : 37: predicate.virtual_dataset_eliminate 0.13% : 0.000006s : 37: predicate.virtual_output_eliminate 0.03% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.04% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.037997 53 86.68% : 0.032936s : 23: func_graph_cloner_run.FuncGraphClonerGraph 13.32% : 0.005061s : 30: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.843751 247 0.00% : 0.000004s : 1: ForceFp32Comm 0.17% : 0.004859s : 1: add_attr 0.17% : 0.004843s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000117s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000354s : 1: auto_monad 0.00% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: backend_pass 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000618s : 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% : 0.000014s : 1: convert_after_rewriter 0.00% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000015s : 1: environ_conv 0.00% : 0.000099s : 1: event_method 0.00% : 0.000022s : 1: execute 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000006s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.03% : 0.000799s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000899s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000024s : 1: opt.transform.mutable_eliminate 0.52% : 0.014914s : 125: opt.transform.opt_a 0.00% : 0.000071s : 1: opt.transform.opt_after_cconv 0.00% : 0.000042s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000235s : 28: opt.transform.opt_b 0.07% : 0.001941s : 2: opt.transform.opt_resolve 0.00% : 0.000095s : 2: opt.transform.opt_trans_graph 0.00% : 0.000074s : 4: opt.transform.symbol_engine_opt 32.33% : 0.919357s : 1: opt_a 0.01% : 0.000194s : 1: opt_after_cconv 0.02% : 0.000568s : 1: opt_after_jit_grad 0.01% : 0.000407s : 1: opt_b 32.47% : 0.923415s : 1: optimize 0.00% : 0.000084s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000168s : 1: order_py_execute_after_rewriter 0.00% : 0.000040s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000081s : 1: pre_auto_parallel 0.00% : 0.000076s : 1: py_interpret_to_execute 0.00% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000023s : 1: remove_dup_value 1.68% : 0.047810s : 2: renormalize.infer 9.55% : 0.271588s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000107s : 1: rewriter_after_opt_a 0.01% : 0.000242s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000337s : 1: symbol_engine_optimizer 15.10% : 0.429476s : 1: task_emit 0.00% : 0.000133s : 1: tuple_transform 7.70% : 0.219002s : 1: type_inference 0.00% : 0.000118s : 1: validate . [hook] pytest_runtest_teardown:test_sigmoid__large_values[0] tests/st/tensor/test_sigmoid_.py::test_sigmoid__large_values[0],max_mem:4.0M [WARNING] ME(165933:281473430114096,MainProcess):2026-01-29-17:40:47.655.305 [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__large_values[1] tests/st/tensor/test_sigmoid_.py::test_sigmoid__large_values[1],max_mem:4.0M =============================== warnings summary =============================== ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 2 passed, 25 warnings in 242.14s (0:04:02) ==================