==================================================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/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_001/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 6 items test_reshape_and_cache.py [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:37:17.794.681 [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 = 0.138107, [21] [bootstrap]: 0.00067 [type_inference]: 0.017389 [event_method]: 1.138e-05 [auto_monad]: 0.00011361 [graph_reusing]: 4.79e-06 [inline]: 2.73e-06 [add_attr]: 0.112441, [1] [add_attr_with_inline]: 0.112428, [1] [Cycle 1]: 9.903e-05, [2] [tag_attr]: 1.994e-05 [meta_addattr_fg_expand]: 3.91001e-06 [parallel-infer-symbol]: 3.68999e-06 [pre_auto_parallel]: 4.664e-05 [insert-virtual-dataset]: 2.36e-06 [parallel-infer-symbol-second]: 8.89995e-07 [dataset_repeat_opt]: 1.92999e-06 [pipeline_split]: 2.06003e-06 [optimize]: 0.00644983, [53] [py_interpret_to_execute]: 2.635e-05 [rewriter_before_opt_a]: 7.557e-05 [opt_a]: 0.00335004, [2] [Cycle 1]: 0.00236988, [45] [expand_dump_flag]: 2.89001e-06 [switch_simplify]: 2.969e-05 [loop_unroll]: 1.515e-05 [a_1]: 0.0004076 [with_stream_mark]: 2.214e-05 [recompute_prepare]: 1.306e-05 [updatestate_depend_eliminate]: 6.49999e-06 [updatestate_assign_eliminate]: 7.38e-06 [updatestate_loads_eliminate]: 5.28002e-06 [parameter_eliminate]: 2.26e-06 [a_2]: 0.00013934 [accelerated_algorithm]: 1.054e-05 [shard]: 2.68e-06 [meta_shard_fg_expand]: 2.44999e-06 [shard_inline]: 9.48997e-06 [merge_send_recv]: 1.097e-05 [auto_parallel]: 8.09002e-06 [parallel]: 5.654e-05 [flash_sp]: 1.322e-05 [merge_comm]: 5.97001e-06 [allreduce_fusion]: 5.32001e-06 [matmul_add_comm_reduction]: 1.211e-05 [allreduce_slice_to_reducescatter]: 1.09e-06 [virtual_shard_identity]: 1.362e-05 [virtual_dataset]: 9.00999e-06 [get_grad_eliminate_]: 9.04998e-06 [virtual_output]: 9.71e-06 [merge_forward]: 6.43e-06 [cell_reuse_recompute_pass]: 1.27999e-06 [offload_activation]: 1.284e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.92e-05 [merge_recompute_call_nodes]: 1.81e-06 [before_grad]: 1.58e-05 [set_forward_comm_id_for_comm_node_pass]: 5.82001e-06 [meta_fg_expand]: 3.92002e-06 [flash_sp_send_recv_attached]: 3.45e-06 [receive_attached]: 1.223e-05 [after_resolve]: 1.901e-05 [a_after_grad]: 1.494e-05 [renormalize]: 0.00095369 [add_forward_monad_depend]: 9.27001e-06 [auto_monad_grad]: 2.59999e-06 [auto_monad_eliminator]: 2.703e-05 [cse]: 8.097e-05 [a_3]: 7.636e-05 [Cycle 2]: 0.00096604, [45] [expand_dump_flag]: 2.74999e-06 [switch_simplify]: 1.119e-05 [loop_unroll]: 8.94e-06 [a_1]: 0.0002199 [with_stream_mark]: 2.092e-05 [recompute_prepare]: 1.065e-05 [updatestate_depend_eliminate]: 6.06e-06 [updatestate_assign_eliminate]: 5.14998e-06 [updatestate_loads_eliminate]: 4.94e-06 [parameter_eliminate]: 1.89999e-06 [a_2]: 0.00012527 [accelerated_algorithm]: 1.07e-05 [shard]: 2.18998e-06 [meta_shard_fg_expand]: 2.96001e-06 [shard_inline]: 8.57e-06 [merge_send_recv]: 9.91e-06 [auto_parallel]: 1.127e-05 [parallel]: 8.79e-06 [flash_sp]: 3.93001e-06 [merge_comm]: 5.08002e-06 [allreduce_fusion]: 4.87998e-06 [matmul_add_comm_reduction]: 1.143e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.135e-05 [virtual_dataset]: 9.46003e-06 [get_grad_eliminate_]: 8.22998e-06 [virtual_output]: 8.35001e-06 [merge_forward]: 6.29001e-06 [cell_reuse_recompute_pass]: 2.48002e-06 [offload_activation]: 1.287e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.892e-05 [merge_recompute_call_nodes]: 1.49e-06 [before_grad]: 1.445e-05 [set_forward_comm_id_for_comm_node_pass]: 5.62999e-06 [meta_fg_expand]: 3.33e-06 [flash_sp_send_recv_attached]: 1.66e-06 [receive_attached]: 2.21e-06 [after_resolve]: 1.736e-05 [a_after_grad]: 1.357e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 2.49001e-06 [auto_monad_grad]: 1.81e-06 [auto_monad_eliminator]: 1.789e-05 [cse]: 3.365e-05 [a_3]: 5.9e-05 [py_interpret_to_execute_after_opt_a]: 2.082e-05 [slice_cell_reuse_recomputed_activation]: 2.74001e-06 [rewriter_after_opt_a]: 0.00020616 [convert_after_rewriter]: 1.52e-05 [order_py_execute_after_rewriter]: 7.66001e-06 [mutable_eliminate]: 0.00076975 [opt_b]: 0.0003385, [1] [Cycle 1]: 0.00032818, [7] [b_1]: 0.00020758 [b_2]: 1.167e-05 [updatestate_depend_eliminate]: 1.215e-05 [updatestate_assign_eliminate]: 4.62e-06 [updatestate_loads_eliminate]: 4.97e-06 [renormalize]: 1.00999e-06 [cse]: 4.693e-05 [optimize_parallel_all_gather_comm]: 2.36e-05 [overlap_param_gather]: 1.96e-06 [cconv]: 3.884e-05 [loop_unroll]: 0.00054859 [opt_after_cconv]: 0.00017122, [1] [Cycle 1]: 0.0001627, [7] [c_1]: 6.167e-05 [parameter_eliminate]: 5.14e-06 [updatestate_depend_eliminate]: 1.04e-05 [updatestate_assign_eliminate]: 5.32001e-06 [updatestate_loads_eliminate]: 4.58001e-06 [cse]: 3.9e-05 [renormalize]: 1.08001e-06 [remove_dup_value]: 1.764e-05 [tuple_transform]: 9.734e-05, [1] [Cycle 1]: 9.164e-05, [4] [d_1]: 6.015e-05 [none_parameter_eliminate]: 1.88997e-06 [renormalize]: 3.60014e-07 [switch_simplify]: 9.90002e-06 [partial_unused_args_eliminate]: 2.57001e-06 [add_recomputation]: 8.716e-05 [cse_after_recomputation]: 7.573e-05, [1] [Cycle 1]: 6.941e-05, [1] [cse]: 6.27e-05 [environ_conv]: 2.146e-05 [swap_dp_allreduce_reducescatter]: 8.38999e-06 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 7.15e-06 [label_fine_grained_interleaved_index]: 2.85002e-06 [merge_cast_opt]: 1.71e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.74001e-06 [assign_add_opt]: 1.37999e-06 [ForceFp32Comm]: 1.18001e-06 [remove_cast_before_assign_add]: 1.15999e-06 [full_micro_interleaved_order_control]: 2.55002e-06 [reorder_send_recv_between_fp_bp]: 2.74999e-06 [comm_op_add_attrs]: 1.22e-06 [add_comm_op_reuse_tag]: 9.99979e-07 [interleave_split_concat_branches]: 1.52001e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 2.589e-05 [overlap_opt_shard_grad_in_pipeline]: 1.87001e-06 [control_data_broadcast_order]: 2.216e-05 [grouped_pairwise_exchange_alltoall]: 1.54998e-06 [offloading_packed_experts]: 5.99e-06 [overlap_recompute_and_grad_model_parallel]: 6.26998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.34999e-06 [overlap_grad_ring_attention]: 5.52001e-06 [overlap_grad_flash_sp]: 4.548e-05 [begin_end_overlap_inline]: 6.09987e-07 [split_matmul_comm_elemetwise]: 2.73e-06 [split_layernorm_comm]: 2.01e-06 [handle_group_info]: 1.25001e-06 [symbol_engine_optimizer]: 0.00010914, [1] [Cycle 1]: 0.00010255, [6] [build]: 6.06e-06 [elim_shapecalc]: 1.79e-05 [elim_not_effective]: 1.893e-05 [opt_reshape]: 1.028e-05 [fold_const_symbol]: 1.444e-05 [renormalize]: 4.00003e-07 [detach_backward]: 2.95998e-06 [pipeline_parallel_scheduler]: 1.60001e-06 [auto_monad_reorder]: 4.2e-05 [get_jit_bprop_graph]: 2.98e-06 [rewriter_after_jit_bprop_graph]: 6.14001e-06 [opt_after_jit_grad]: 0.00065604 [validate]: 7.85e-05 Sums bootstrap : 0.000670s : 2.73% type_inference : 0.017389s : 70.79% event_method : 0.000011s : 0.05% auto_monad : 0.000114s : 0.46% graph_reusing : 0.000005s : 0.02% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.08% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.02% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000047s : 0.19% insert-virtual-dataset : 0.000002s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000026s : 0.11% optimize.rewriter_before_opt_a : 0.000076s : 0.31% optimize.opt_a.expand_dump_flag : 0.000006s : 0.02% optimize.opt_a.switch_simplify : 0.000041s : 0.17% optimize.opt_a.loop_unroll : 0.000024s : 0.10% optimize.opt_a.a_1 : 0.000627s : 2.55% optimize.opt_a.with_stream_mark : 0.000043s : 0.18% optimize.opt_a.recompute_prepare : 0.000024s : 0.10% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.05% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.05% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.04% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000265s : 1.08% optimize.opt_a.accelerated_algorithm : 0.000021s : 0.09% optimize.opt_a.shard : 0.000005s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.02% optimize.opt_a.shard_inline : 0.000018s : 0.07% optimize.opt_a.merge_send_recv : 0.000021s : 0.08% optimize.opt_a.auto_parallel : 0.000019s : 0.08% optimize.opt_a.parallel : 0.000065s : 0.27% optimize.opt_a.flash_sp : 0.000017s : 0.07% optimize.opt_a.merge_comm : 0.000011s : 0.04% optimize.opt_a.allreduce_fusion : 0.000010s : 0.04% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.10% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000025s : 0.10% optimize.opt_a.virtual_dataset : 0.000018s : 0.08% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.07% optimize.opt_a.virtual_output : 0.000018s : 0.07% optimize.opt_a.merge_forward : 0.000013s : 0.05% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.02% optimize.opt_a.offload_activation : 0.000026s : 0.10% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000038s : 0.16% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000030s : 0.12% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.05% optimize.opt_a.meta_fg_expand : 0.000007s : 0.03% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.02% optimize.opt_a.receive_attached : 0.000014s : 0.06% optimize.opt_a.after_resolve : 0.000036s : 0.15% optimize.opt_a.a_after_grad : 0.000029s : 0.12% optimize.opt_a.renormalize : 0.000954s : 3.88% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.05% optimize.opt_a.auto_monad_grad : 0.000004s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000045s : 0.18% optimize.opt_a.cse : 0.000115s : 0.47% optimize.opt_a.a_3 : 0.000135s : 0.55% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.08% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.01% optimize.rewriter_after_opt_a : 0.000206s : 0.84% optimize.convert_after_rewriter : 0.000015s : 0.06% optimize.order_py_execute_after_rewriter : 0.000008s : 0.03% optimize.mutable_eliminate : 0.000770s : 3.13% optimize.opt_b.b_1 : 0.000208s : 0.85% optimize.opt_b.b_2 : 0.000012s : 0.05% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.05% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000047s : 0.19% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.10% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000039s : 0.16% optimize.loop_unroll : 0.000549s : 2.23% optimize.opt_after_cconv.c_1 : 0.000062s : 0.25% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.04% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.cse : 0.000039s : 0.16% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000018s : 0.07% optimize.tuple_transform.d_1 : 0.000060s : 0.24% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.04% optimize.partial_unused_args_eliminate : 0.000003s : 0.01% optimize.add_recomputation : 0.000087s : 0.35% optimize.cse_after_recomputation.cse : 0.000063s : 0.26% optimize.environ_conv : 0.000021s : 0.09% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.03% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000007s : 0.03% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% 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 : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000026s : 0.11% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000022s : 0.09% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.03% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.01% optimize.overlap_grad_ring_attention : 0.000006s : 0.02% optimize.overlap_grad_flash_sp : 0.000045s : 0.19% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.07% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.08% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.04% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000014s : 0.06% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000042s : 0.17% get_jit_bprop_graph : 0.000003s : 0.01% rewriter_after_jit_bprop_graph : 0.000006s : 0.02% opt_after_jit_grad : 0.000656s : 2.67% validate : 0.000078s : 0.32% Time group info: ------[substitution.] 0.000191 54 5.60% : 0.000011s : 2: substitution.depend_value_elim 1.33% : 0.000003s : 4: substitution.elim_not_effective 1.05% : 0.000002s : 4: substitution.fold_const_symbol 3.94% : 0.000008s : 7: substitution.graph_param_transform 57.91% : 0.000110s : 1: substitution.inline 3.31% : 0.000006s : 8: substitution.j_node_and_user_rematch 4.16% : 0.000008s : 8: substitution.remove_not_recompute_node 4.25% : 0.000008s : 6: substitution.replace_old_param 10.58% : 0.000020s : 6: substitution.updatestate_pure_node_eliminater 7.87% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.017310 2 97.77% : 0.016924s : 1: type_inference.infer 2.23% : 0.000386s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000109 1 100.00% : 0.000109s : 1: match.inline ------[predicate.] 0.000238 1649 0.83% : 0.000002s : 15: predicate.accumulaten_eliminater 1.41% : 0.000003s : 7: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 14: predicate.addn_check_dump 0.93% : 0.000002s : 15: predicate.addn_zero_filter 0.68% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.63% : 0.000006s : 29: predicate.arithmetic_simplify 0.84% : 0.000002s : 15: predicate.cast_eliminate 0.76% : 0.000002s : 14: predicate.check_bprop_eliminate 0.79% : 0.000002s : 14: predicate.compare_switch_simplify 0.25% : 0.000001s : 7: predicate.const_output_eliminate 0.76% : 0.000002s : 14: predicate.depend_value_elim 0.81% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.93% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.56% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 7: predicate.elim_not_effective 0.48% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.04% : 0.000002s : 22: predicate.environ_get_depend_swap 1.83% : 0.000004s : 36: predicate.environ_get_eliminate 1.04% : 0.000002s : 22: predicate.environ_get_set_eliminate 0.81% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.47% : 0.000004s : 16: predicate.float_depend_g_call 0.74% : 0.000002s : 14: predicate.float_environ_get_switch 1.14% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 7: predicate.fold_const_symbol 0.87% : 0.000002s : 14: predicate.get_grad_eliminate 0.34% : 0.000001s : 7: predicate.graph_param_transform 0.74% : 0.000002s : 14: predicate.incorporate_call 0.65% : 0.000002s : 14: predicate.incorporate_call_switch 5.73% : 0.000014s : 73: predicate.inline 1.00% : 0.000002s : 14: predicate.inline_without_move 0.41% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.23% : 0.000003s : 14: predicate.less_batch_normalization 1.56% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.28% : 0.000005s : 44: predicate.load_eliminater 1.19% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.30% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.63% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.76% : 0.000002s : 14: predicate.merge_addn 0.78% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.74% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.68% : 0.000002s : 15: predicate.minmaximum_grad 1.40% : 0.000003s : 7: predicate.mutable_eliminate 0.49% : 0.000001s : 7: predicate.opt_reshape 0.43% : 0.000001s : 7: predicate.parallel_virtual_node 0.99% : 0.000002s : 16: predicate.partial_defer_inline 1.19% : 0.000003s : 22: predicate.partial_eliminate 0.81% : 0.000002s : 15: predicate.print_const_string_wrapper 0.81% : 0.000002s : 14: predicate.reduce_all_const_elim 1.23% : 0.000003s : 15: predicate.reduce_eliminate 2.17% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.79% : 0.000002s : 14: predicate.remove_not_recompute_node 1.46% : 0.000003s : 29: predicate.replace_applicator 0.89% : 0.000002s : 14: predicate.replace_old_param 0.60% : 0.000001s : 7: predicate.reset_defer_inline 0.76% : 0.000002s : 15: predicate.reshape_eliminate 0.80% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.45% : 0.000001s : 7: predicate.row_tensor_eliminate 0.99% : 0.000002s : 14: predicate.same_eliminate 0.66% : 0.000002s : 14: predicate.set_cell_output_no_recompute 1.03% : 0.000002s : 14: predicate.shard_identity_eliminate 0.89% : 0.000002s : 14: predicate.special_op_eliminate 0.88% : 0.000002s : 14: predicate.specialize_transform 1.32% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 1.10% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.47% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.80% : 0.000002s : 16: predicate.switch_defer_inline 1.65% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.70% : 0.000009s : 58: predicate.switch_simplify 0.73% : 0.000002s : 15: predicate.tile_eliminate 0.76% : 0.000002s : 15: predicate.transpose_eliminate 1.53% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.62% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.32% : 0.000003s : 29: predicate.tuple_list_get_item_depend_reorder 2.99% : 0.000007s : 43: predicate.tuple_list_get_item_eliminator 1.37% : 0.000003s : 29: predicate.tuple_list_get_set_item_eliminator 2.33% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.69% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.29% : 0.000005s : 44: predicate.updatestate_pure_node_eliminater 3.57% : 0.000009s : 58: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 7: predicate.value_based_eliminate 1.08% : 0.000003s : 14: predicate.virtual_dataset_eliminate 0.84% : 0.000002s : 14: predicate.virtual_output_eliminate 0.36% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.56% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000422 6 54.38% : 0.000230s : 3: func_graph_cloner_run.FuncGraphClonerGraph 45.62% : 0.000193s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.259496 192 0.00% : 0.000004s : 1: ForceFp32Comm 43.33% : 0.112447s : 1: add_attr 43.33% : 0.112433s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000092s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.05% : 0.000120s : 1: auto_monad 0.02% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.27% : 0.000702s : 1: bootstrap 0.02% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000027s : 1: control_data_broadcast_order 0.01% : 0.000020s : 1: convert_after_rewriter 0.03% : 0.000079s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000026s : 1: environ_conv 0.01% : 0.000018s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000008s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.22% : 0.000561s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.30% : 0.000784s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000029s : 1: opt.transform.mutable_eliminate 0.49% : 0.001268s : 78: opt.transform.opt_a 0.02% : 0.000060s : 1: opt.transform.opt_after_cconv 0.02% : 0.000042s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000190s : 28: opt.transform.opt_b 0.03% : 0.000067s : 2: opt.transform.opt_trans_graph 0.02% : 0.000058s : 4: opt.transform.symbol_engine_opt 1.29% : 0.003354s : 1: opt_a 0.07% : 0.000175s : 1: opt_after_cconv 0.26% : 0.000673s : 1: opt_after_jit_grad 0.13% : 0.000342s : 1: opt_b 2.49% : 0.006455s : 1: optimize 0.01% : 0.000027s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000051s : 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 0.01% : 0.000031s : 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% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000052s : 1: pre_auto_parallel 0.01% : 0.000031s : 1: py_interpret_to_execute 0.01% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.01% : 0.000022s : 1: remove_dup_value 0.18% : 0.000460s : 1: renormalize.infer 0.19% : 0.000484s : 1: renormalize.specialize 0.00% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.08% : 0.000218s : 1: rewriter_after_opt_a 0.03% : 0.000080s : 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% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000112s : 1: symbol_engine_optimizer 0.04% : 0.000101s : 1: tuple_transform 6.71% : 0.017409s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[2-float16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[2-float16],max_mem:240.0M [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:38:38.806.440 [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 = 0.258259, [21] [bootstrap]: 0.00069878 [type_inference]: 0.00571468 [event_method]: 1.355e-05 [auto_monad]: 0.00014526 [graph_reusing]: 5.29998e-06 [inline]: 2.61e-06 [add_attr]: 0.149788, [1] [add_attr_with_inline]: 0.149767, [1] [Cycle 1]: 9.759e-05, [2] [tag_attr]: 2.683e-05 [meta_addattr_fg_expand]: 5.34998e-06 [parallel-infer-symbol]: 4.95001e-06 [pre_auto_parallel]: 5.251e-05 [insert-virtual-dataset]: 3.46999e-06 [parallel-infer-symbol-second]: 7.59988e-07 [dataset_repeat_opt]: 3.78001e-06 [pipeline_split]: 1.94e-06 [optimize]: 0.00817642, [53] [py_interpret_to_execute]: 7.224e-05 [rewriter_before_opt_a]: 0.00011466 [opt_a]: 0.00447254, [2] [Cycle 1]: 0.00335506, [45] [expand_dump_flag]: 3.30003e-06 [switch_simplify]: 3.105e-05 [loop_unroll]: 2.162e-05 [a_1]: 0.0006082 [with_stream_mark]: 2.738e-05 [recompute_prepare]: 1.35e-05 [updatestate_depend_eliminate]: 6.83e-06 [updatestate_assign_eliminate]: 7.09001e-06 [updatestate_loads_eliminate]: 1.157e-05 [parameter_eliminate]: 2.63e-06 [a_2]: 0.00014358 [accelerated_algorithm]: 1.147e-05 [shard]: 2.93e-06 [meta_shard_fg_expand]: 2.89001e-06 [shard_inline]: 9.92001e-06 [merge_send_recv]: 1.136e-05 [auto_parallel]: 1.093e-05 [parallel]: 4.343e-05 [flash_sp]: 1.319e-05 [merge_comm]: 6.24001e-06 [allreduce_fusion]: 9.01002e-06 [matmul_add_comm_reduction]: 1.858e-05 [allreduce_slice_to_reducescatter]: 6.89994e-07 [virtual_shard_identity]: 2.495e-05 [virtual_dataset]: 1.802e-05 [get_grad_eliminate_]: 1.633e-05 [virtual_output]: 1.404e-05 [merge_forward]: 7.1e-06 [cell_reuse_recompute_pass]: 1.95001e-06 [offload_activation]: 3.118e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.14e-05 [merge_recompute_call_nodes]: 1.51998e-06 [before_grad]: 3.035e-05 [set_forward_comm_id_for_comm_node_pass]: 1.008e-05 [meta_fg_expand]: 4.38001e-06 [flash_sp_send_recv_attached]: 4.05998e-06 [receive_attached]: 4.69998e-06 [after_resolve]: 2.874e-05 [a_after_grad]: 1.945e-05 [renormalize]: 0.00123132 [add_forward_monad_depend]: 6.12999e-06 [auto_monad_grad]: 2.68998e-06 [auto_monad_eliminator]: 2.833e-05 [cse]: 5.787e-05 [a_3]: 8.084e-05 [Cycle 2]: 0.00109097, [45] [expand_dump_flag]: 5.24e-06 [switch_simplify]: 1.531e-05 [loop_unroll]: 1.012e-05 [a_1]: 0.00023579 [with_stream_mark]: 1.91e-05 [recompute_prepare]: 9.97999e-06 [updatestate_depend_eliminate]: 5.94e-06 [updatestate_assign_eliminate]: 4.65999e-06 [updatestate_loads_eliminate]: 5.59998e-06 [parameter_eliminate]: 1.27999e-06 [a_2]: 0.00012844 [accelerated_algorithm]: 1.039e-05 [shard]: 1.86003e-06 [meta_shard_fg_expand]: 2.94001e-06 [shard_inline]: 9.69999e-06 [merge_send_recv]: 8.37998e-06 [auto_parallel]: 1.241e-05 [parallel]: 1.062e-05 [flash_sp]: 3.63999e-06 [merge_comm]: 6.06e-06 [allreduce_fusion]: 7.33999e-06 [matmul_add_comm_reduction]: 1.002e-05 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 1.172e-05 [virtual_dataset]: 9.09e-06 [get_grad_eliminate_]: 9.32001e-06 [virtual_output]: 9.41e-06 [merge_forward]: 6.04999e-06 [cell_reuse_recompute_pass]: 2.37999e-06 [offload_activation]: 1.128e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.682e-05 [merge_recompute_call_nodes]: 1.61998e-06 [before_grad]: 1.496e-05 [set_forward_comm_id_for_comm_node_pass]: 5.40001e-06 [meta_fg_expand]: 3.58e-06 [flash_sp_send_recv_attached]: 1.03001e-06 [receive_attached]: 1.81e-06 [after_resolve]: 1.494e-05 [a_after_grad]: 1.511e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.91e-06 [auto_monad_grad]: 1.36002e-06 [auto_monad_eliminator]: 1.418e-05 [cse]: 6.238e-05 [a_3]: 6.103e-05 [py_interpret_to_execute_after_opt_a]: 1.99e-05 [slice_cell_reuse_recomputed_activation]: 2.10002e-06 [rewriter_after_opt_a]: 0.00018727 [convert_after_rewriter]: 1.212e-05 [order_py_execute_after_rewriter]: 6.99001e-06 [mutable_eliminate]: 0.00115444 [opt_b]: 0.000378, [1] [Cycle 1]: 0.00036753, [7] [b_1]: 0.00022529 [b_2]: 1.247e-05 [updatestate_depend_eliminate]: 1.139e-05 [updatestate_assign_eliminate]: 5.39998e-06 [updatestate_loads_eliminate]: 5.22999e-06 [renormalize]: 8.70001e-07 [cse]: 6.234e-05 [optimize_parallel_all_gather_comm]: 2.661e-05 [overlap_param_gather]: 2.14e-06 [cconv]: 3.655e-05 [loop_unroll]: 0.00060742 [opt_after_cconv]: 0.00019233, [1] [Cycle 1]: 0.00018418, [7] [c_1]: 6.226e-05 [parameter_eliminate]: 5.82999e-06 [updatestate_depend_eliminate]: 9.91e-06 [updatestate_assign_eliminate]: 4.45e-06 [updatestate_loads_eliminate]: 5.23002e-06 [cse]: 5.064e-05 [renormalize]: 9.30013e-07 [remove_dup_value]: 2.3e-05 [tuple_transform]: 0.00011394, [1] [Cycle 1]: 0.00010821, [4] [d_1]: 7.062e-05 [none_parameter_eliminate]: 2.03997e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 1.123e-05 [partial_unused_args_eliminate]: 2.51e-06 [add_recomputation]: 0.00010471 [cse_after_recomputation]: 4.414e-05, [1] [Cycle 1]: 3.902e-05, [1] [cse]: 3.125e-05 [environ_conv]: 1.052e-05 [swap_dp_allreduce_reducescatter]: 8.1e-06 [bias_add_comm_swap]: 3.26001e-06 [label_micro_interleaved_index]: 5.39998e-06 [label_fine_grained_interleaved_index]: 2.84999e-06 [merge_cast_opt]: 1.62999e-06 [slice_recompute_activation]: 2.17999e-06 [micro_interleaved_order_control]: 2.98998e-06 [assign_add_opt]: 1.32999e-06 [ForceFp32Comm]: 1.06002e-06 [remove_cast_before_assign_add]: 1.02e-06 [full_micro_interleaved_order_control]: 2.56998e-06 [reorder_send_recv_between_fp_bp]: 2.94001e-06 [comm_op_add_attrs]: 9.80013e-07 [add_comm_op_reuse_tag]: 9.50007e-07 [interleave_split_concat_branches]: 1.37999e-06 [interleave_parallel_branches]: 1.19003e-06 [overlap_opt_shard_in_pipeline]: 2.06e-06 [overlap_opt_shard_grad_in_pipeline]: 1.62999e-06 [control_data_broadcast_order]: 2.211e-05 [grouped_pairwise_exchange_alltoall]: 1.55001e-06 [offloading_packed_experts]: 7.56001e-06 [overlap_recompute_and_grad_model_parallel]: 6.77002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.67001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52999e-06 [overlap_recompute_comm]: 2.29001e-06 [overlap_grad_ring_attention]: 5.05999e-06 [overlap_grad_flash_sp]: 3.017e-05 [begin_end_overlap_inline]: 7.50006e-07 [split_matmul_comm_elemetwise]: 2.41e-06 [split_layernorm_comm]: 1.92001e-06 [handle_group_info]: 1.36998e-06 [symbol_engine_optimizer]: 0.00012269, [1] [Cycle 1]: 0.00011714, [6] [build]: 5.66e-06 [elim_shapecalc]: 2.158e-05 [elim_not_effective]: 2.068e-05 [opt_reshape]: 1.234e-05 [fold_const_symbol]: 1.599e-05 [renormalize]: 3.39991e-07 [detach_backward]: 2.15002e-06 [pipeline_parallel_scheduler]: 1.64998e-06 [auto_monad_reorder]: 4.155e-05 [get_jit_bprop_graph]: 1.75001e-06 [rewriter_after_jit_bprop_graph]: 6.88e-06 [opt_after_jit_grad]: 0.0932916 [validate]: 7.979e-05 Sums bootstrap : 0.000699s : 0.65% type_inference : 0.005715s : 5.35% event_method : 0.000014s : 0.01% auto_monad : 0.000145s : 0.14% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.01% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000053s : 0.05% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000004s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000072s : 0.07% optimize.rewriter_before_opt_a : 0.000115s : 0.11% optimize.opt_a.expand_dump_flag : 0.000009s : 0.01% optimize.opt_a.switch_simplify : 0.000046s : 0.04% optimize.opt_a.loop_unroll : 0.000032s : 0.03% optimize.opt_a.a_1 : 0.000844s : 0.79% optimize.opt_a.with_stream_mark : 0.000046s : 0.04% optimize.opt_a.recompute_prepare : 0.000023s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.02% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000272s : 0.25% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.01% optimize.opt_a.shard_inline : 0.000020s : 0.02% optimize.opt_a.merge_send_recv : 0.000020s : 0.02% optimize.opt_a.auto_parallel : 0.000023s : 0.02% optimize.opt_a.parallel : 0.000054s : 0.05% optimize.opt_a.flash_sp : 0.000017s : 0.02% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000016s : 0.02% optimize.opt_a.matmul_add_comm_reduction : 0.000029s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.03% optimize.opt_a.virtual_dataset : 0.000027s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.02% optimize.opt_a.virtual_output : 0.000023s : 0.02% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000042s : 0.04% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000045s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000007s : 0.01% optimize.opt_a.after_resolve : 0.000044s : 0.04% optimize.opt_a.a_after_grad : 0.000035s : 0.03% optimize.opt_a.renormalize : 0.001231s : 1.15% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000043s : 0.04% optimize.opt_a.cse : 0.000120s : 0.11% optimize.opt_a.a_3 : 0.000142s : 0.13% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000187s : 0.18% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.001154s : 1.08% optimize.opt_b.b_1 : 0.000225s : 0.21% optimize.opt_b.b_2 : 0.000012s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000062s : 0.06% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.03% optimize.loop_unroll : 0.000607s : 0.57% optimize.opt_after_cconv.c_1 : 0.000062s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000051s : 0.05% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000023s : 0.02% optimize.tuple_transform.d_1 : 0.000071s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000105s : 0.10% optimize.cse_after_recomputation.cse : 0.000031s : 0.03% optimize.environ_conv : 0.000011s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 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 : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000030s : 0.03% 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 : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000021s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000016s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000042s : 0.04% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.01% opt_after_jit_grad : 0.093292s : 87.40% validate : 0.000080s : 0.07% Time group info: ------[substitution.] 0.000317 54 2.98% : 0.000009s : 2: substitution.depend_value_elim 0.72% : 0.000002s : 4: substitution.elim_not_effective 0.67% : 0.000002s : 4: substitution.fold_const_symbol 2.52% : 0.000008s : 7: substitution.graph_param_transform 76.95% : 0.000244s : 1: substitution.inline 1.71% : 0.000005s : 8: substitution.j_node_and_user_rematch 2.10% : 0.000007s : 8: substitution.remove_not_recompute_node 2.24% : 0.000007s : 6: substitution.replace_old_param 5.45% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 4.65% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.005614 2 88.38% : 0.004961s : 1: type_inference.infer 11.62% : 0.000652s : 1: type_inference.specialize ------[replace.] 0.000032 1 100.00% : 0.000032s : 1: replace.inline ------[match.] 0.000240 1 100.00% : 0.000240s : 1: match.inline ------[predicate.] 0.000250 1649 0.79% : 0.000002s : 15: predicate.accumulaten_eliminater 2.48% : 0.000006s : 7: predicate.ad_related_special_op_eliminate 0.70% : 0.000002s : 14: predicate.addn_check_dump 0.81% : 0.000002s : 15: predicate.addn_zero_filter 0.67% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.27% : 0.000006s : 29: predicate.arithmetic_simplify 0.79% : 0.000002s : 15: predicate.cast_eliminate 0.78% : 0.000002s : 14: predicate.check_bprop_eliminate 0.71% : 0.000002s : 14: predicate.compare_switch_simplify 0.23% : 0.000001s : 7: predicate.const_output_eliminate 0.78% : 0.000002s : 14: predicate.depend_value_elim 0.76% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.86% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.80% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.79% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.34% : 0.000001s : 7: predicate.elim_not_effective 0.60% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.02% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.07% : 0.000003s : 22: predicate.environ_get_depend_swap 1.79% : 0.000004s : 36: predicate.environ_get_eliminate 1.02% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.74% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.48% : 0.000004s : 16: predicate.float_depend_g_call 0.69% : 0.000002s : 14: predicate.float_environ_get_switch 1.00% : 0.000002s : 21: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 7: predicate.fold_const_symbol 0.79% : 0.000002s : 14: predicate.get_grad_eliminate 0.26% : 0.000001s : 7: predicate.graph_param_transform 0.73% : 0.000002s : 14: predicate.incorporate_call 0.65% : 0.000002s : 14: predicate.incorporate_call_switch 5.64% : 0.000014s : 73: predicate.inline 1.30% : 0.000003s : 14: predicate.inline_without_move 0.42% : 0.000001s : 14: predicate.j_node_and_user_rematch 0.95% : 0.000002s : 14: predicate.less_batch_normalization 1.61% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.07% : 0.000005s : 44: predicate.load_eliminater 1.24% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.25% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.69% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.73% : 0.000002s : 14: predicate.merge_addn 0.78% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.71% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.82% : 0.000002s : 15: predicate.minmaximum_grad 1.72% : 0.000004s : 7: predicate.mutable_eliminate 0.47% : 0.000001s : 7: predicate.opt_reshape 1.50% : 0.000004s : 7: predicate.parallel_virtual_node 0.98% : 0.000002s : 16: predicate.partial_defer_inline 1.15% : 0.000003s : 22: predicate.partial_eliminate 0.69% : 0.000002s : 15: predicate.print_const_string_wrapper 0.76% : 0.000002s : 14: predicate.reduce_all_const_elim 1.15% : 0.000003s : 15: predicate.reduce_eliminate 2.15% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.60% : 0.000002s : 14: predicate.remove_not_recompute_node 1.29% : 0.000003s : 29: predicate.replace_applicator 0.63% : 0.000002s : 14: predicate.replace_old_param 0.54% : 0.000001s : 7: predicate.reset_defer_inline 0.77% : 0.000002s : 15: predicate.reshape_eliminate 0.77% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.51% : 0.000001s : 7: predicate.row_tensor_eliminate 1.06% : 0.000003s : 14: predicate.same_eliminate 0.52% : 0.000001s : 14: predicate.set_cell_output_no_recompute 1.07% : 0.000003s : 14: predicate.shard_identity_eliminate 1.01% : 0.000003s : 14: predicate.special_op_eliminate 0.87% : 0.000002s : 14: predicate.specialize_transform 1.14% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 0.93% : 0.000002s : 14: predicate.stack_unstack_eliminate 0.48% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.81% : 0.000002s : 16: predicate.switch_defer_inline 1.52% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.46% : 0.000009s : 58: predicate.switch_simplify 0.91% : 0.000002s : 15: predicate.tile_eliminate 0.74% : 0.000002s : 15: predicate.transpose_eliminate 1.60% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.43% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.00% : 0.000008s : 43: predicate.tuple_list_get_item_eliminator 1.53% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.51% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.50% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.17% : 0.000005s : 44: predicate.updatestate_pure_node_eliminater 3.25% : 0.000008s : 58: predicate.updatestate_useless_node_eliminater 0.45% : 0.000001s : 7: predicate.value_based_eliminate 0.91% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.81% : 0.000002s : 14: predicate.virtual_output_eliminate 0.37% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.53% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000808 6 44.80% : 0.000362s : 3: func_graph_cloner_run.FuncGraphClonerGraph 55.20% : 0.000446s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.419352 192 0.00% : 0.000004s : 1: ForceFp32Comm 35.72% : 0.149800s : 1: add_attr 35.72% : 0.149772s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000110s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.04% : 0.000153s : 1: auto_monad 0.01% : 0.000047s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.18% : 0.000745s : 1: bootstrap 0.01% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000026s : 1: control_data_broadcast_order 0.00% : 0.000017s : 1: convert_after_rewriter 0.01% : 0.000048s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000015s : 1: environ_conv 0.01% : 0.000021s : 1: event_method 0.00% : 0.000008s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 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% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000007s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000010s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.15% : 0.000620s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000009s : 1: micro_interleaved_order_control 0.28% : 0.001176s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.01% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000034s : 1: opt.transform.mutable_eliminate 0.38% : 0.001582s : 78: opt.transform.opt_a 0.01% : 0.000061s : 1: opt.transform.opt_after_cconv 0.02% : 0.000072s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000207s : 28: opt.transform.opt_b 0.02% : 0.000079s : 2: opt.transform.opt_trans_graph 0.02% : 0.000067s : 4: opt.transform.symbol_engine_opt 1.07% : 0.004479s : 1: opt_a 0.05% : 0.000196s : 1: opt_after_cconv 22.25% : 0.093316s : 1: opt_after_jit_grad 0.09% : 0.000386s : 1: opt_b 1.95% : 0.008183s : 1: optimize 0.01% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000037s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000008s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000057s : 1: pre_auto_parallel 0.02% : 0.000078s : 1: py_interpret_to_execute 0.01% : 0.000024s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000027s : 1: remove_dup_value 0.14% : 0.000576s : 1: renormalize.infer 0.15% : 0.000642s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000194s : 1: rewriter_after_opt_a 0.03% : 0.000130s : 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% : 0.000007s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000128s : 1: symbol_engine_optimizer 0.03% : 0.000117s : 1: tuple_transform 1.37% : 0.005740s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[2-int8] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[2-int8],max_mem:240.0M [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:39:19.740.383 [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 = 0.037372, [21] [bootstrap]: 0.00079077 [type_inference]: 0.00626793 [event_method]: 2.032e-05 [auto_monad]: 0.00023081 [graph_reusing]: 6.01e-06 [inline]: 2.58e-06 [add_attr]: 0.0203947, [1] [add_attr_with_inline]: 0.0203708, [1] [Cycle 1]: 8.62e-05, [2] [tag_attr]: 2.322e-05 [meta_addattr_fg_expand]: 4.36002e-06 [parallel-infer-symbol]: 4.4e-06 [pre_auto_parallel]: 4.404e-05 [insert-virtual-dataset]: 2.49999e-06 [parallel-infer-symbol-second]: 7.30011e-07 [dataset_repeat_opt]: 2.24001e-06 [pipeline_split]: 2.02999e-06 [optimize]: 0.00848896, [53] [py_interpret_to_execute]: 4.541e-05 [rewriter_before_opt_a]: 9.054e-05 [opt_a]: 0.00486528, [2] [Cycle 1]: 0.00360509, [45] [expand_dump_flag]: 3.07002e-06 [switch_simplify]: 2.891e-05 [loop_unroll]: 1.582e-05 [a_1]: 0.00050925 [with_stream_mark]: 2.567e-05 [recompute_prepare]: 1.383e-05 [updatestate_depend_eliminate]: 7.18e-06 [updatestate_assign_eliminate]: 5.50001e-06 [updatestate_loads_eliminate]: 6.26e-06 [parameter_eliminate]: 2.06e-06 [a_2]: 0.00014883 [accelerated_algorithm]: 1.227e-05 [shard]: 4.2e-06 [meta_shard_fg_expand]: 3.02002e-06 [shard_inline]: 1.109e-05 [merge_send_recv]: 1.312e-05 [auto_parallel]: 1.529e-05 [parallel]: 3.329e-05 [flash_sp]: 1.434e-05 [merge_comm]: 6.29001e-06 [allreduce_fusion]: 5.13002e-06 [matmul_add_comm_reduction]: 1.443e-05 [allreduce_slice_to_reducescatter]: 1.07998e-06 [virtual_shard_identity]: 1.625e-05 [virtual_dataset]: 1.045e-05 [get_grad_eliminate_]: 9.92999e-06 [virtual_output]: 1.021e-05 [merge_forward]: 6.74001e-06 [cell_reuse_recompute_pass]: 2.58998e-06 [offload_activation]: 1.815e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.355e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 0.00062145 [set_forward_comm_id_for_comm_node_pass]: 1.741e-05 [meta_fg_expand]: 6.05002e-06 [flash_sp_send_recv_attached]: 7.16001e-06 [receive_attached]: 2.38002e-06 [after_resolve]: 2.772e-05 [a_after_grad]: 1.969e-05 [renormalize]: 0.00119323 [add_forward_monad_depend]: 9.79999e-06 [auto_monad_grad]: 3.04999e-06 [auto_monad_eliminator]: 3.134e-05 [cse]: 8.049e-05 [a_3]: 8.658e-05 [Cycle 2]: 0.00123576, [45] [expand_dump_flag]: 5.46e-06 [switch_simplify]: 1.592e-05 [loop_unroll]: 1.287e-05 [a_1]: 0.00024274 [with_stream_mark]: 2.625e-05 [recompute_prepare]: 1.223e-05 [updatestate_depend_eliminate]: 6.79001e-06 [updatestate_assign_eliminate]: 6.61999e-06 [updatestate_loads_eliminate]: 6.02999e-06 [parameter_eliminate]: 2.07001e-06 [a_2]: 0.00013771 [accelerated_algorithm]: 1.406e-05 [shard]: 2.53998e-06 [meta_shard_fg_expand]: 2.95998e-06 [shard_inline]: 9.94999e-06 [merge_send_recv]: 1.122e-05 [auto_parallel]: 1.207e-05 [parallel]: 1.037e-05 [flash_sp]: 4.49998e-06 [merge_comm]: 6.01e-06 [allreduce_fusion]: 6.30002e-06 [matmul_add_comm_reduction]: 1.764e-05 [allreduce_slice_to_reducescatter]: 7.39994e-07 [virtual_shard_identity]: 1.427e-05 [virtual_dataset]: 1.019e-05 [get_grad_eliminate_]: 1.015e-05 [virtual_output]: 1.019e-05 [merge_forward]: 7.38999e-06 [cell_reuse_recompute_pass]: 4.22e-06 [offload_activation]: 1.841e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.668e-05 [merge_recompute_call_nodes]: 1.94e-06 [before_grad]: 1.93e-05 [set_forward_comm_id_for_comm_node_pass]: 6.91999e-06 [meta_fg_expand]: 3.4e-06 [flash_sp_send_recv_attached]: 2.52001e-06 [receive_attached]: 3.41001e-06 [after_resolve]: 2.146e-05 [a_after_grad]: 2.013e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 2.85998e-06 [auto_monad_grad]: 2.40002e-06 [auto_monad_eliminator]: 1.697e-05 [cse]: 4.957e-05 [a_3]: 6.186e-05 [py_interpret_to_execute_after_opt_a]: 2.714e-05 [slice_cell_reuse_recomputed_activation]: 2.09999e-06 [rewriter_after_opt_a]: 0.00016678 [convert_after_rewriter]: 1.187e-05 [order_py_execute_after_rewriter]: 7.1e-06 [mutable_eliminate]: 0.00083915 [opt_b]: 0.00040068, [1] [Cycle 1]: 0.00039103, [7] [b_1]: 0.00022979 [b_2]: 1.282e-05 [updatestate_depend_eliminate]: 1.371e-05 [updatestate_assign_eliminate]: 6.04001e-06 [updatestate_loads_eliminate]: 5.54e-06 [renormalize]: 7.89994e-07 [cse]: 6.543e-05 [optimize_parallel_all_gather_comm]: 2.416e-05 [overlap_param_gather]: 2.71999e-06 [cconv]: 3.803e-05 [loop_unroll]: 0.00077054 [opt_after_cconv]: 0.00021664, [1] [Cycle 1]: 0.00020747, [7] [c_1]: 6.716e-05 [parameter_eliminate]: 6.53e-06 [updatestate_depend_eliminate]: 1.142e-05 [updatestate_assign_eliminate]: 7.43999e-06 [updatestate_loads_eliminate]: 4.88001e-06 [cse]: 5.593e-05 [renormalize]: 1.19e-06 [remove_dup_value]: 1.905e-05 [tuple_transform]: 0.00013607, [1] [Cycle 1]: 0.00012987, [4] [d_1]: 8.382e-05 [none_parameter_eliminate]: 2.01998e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.593e-05 [partial_unused_args_eliminate]: 2.10002e-06 [add_recomputation]: 9.809e-05 [cse_after_recomputation]: 4.808e-05, [1] [Cycle 1]: 4.269e-05, [1] [cse]: 3.162e-05 [environ_conv]: 1.281e-05 [swap_dp_allreduce_reducescatter]: 1.127e-05 [bias_add_comm_swap]: 3.4e-06 [label_micro_interleaved_index]: 6.63998e-06 [label_fine_grained_interleaved_index]: 3.14999e-06 [merge_cast_opt]: 1.76e-06 [slice_recompute_activation]: 2.26998e-06 [micro_interleaved_order_control]: 2.84001e-06 [assign_add_opt]: 1.49e-06 [ForceFp32Comm]: 8.89995e-07 [remove_cast_before_assign_add]: 1.10001e-06 [full_micro_interleaved_order_control]: 5.19e-06 [reorder_send_recv_between_fp_bp]: 2.71999e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 9.5999e-07 [interleave_split_concat_branches]: 2.10002e-06 [interleave_parallel_branches]: 1.24e-06 [overlap_opt_shard_in_pipeline]: 1.24003e-06 [overlap_opt_shard_grad_in_pipeline]: 1.61998e-06 [control_data_broadcast_order]: 2.192e-05 [grouped_pairwise_exchange_alltoall]: 2.06e-06 [offloading_packed_experts]: 6.56e-06 [overlap_recompute_and_grad_model_parallel]: 6.44999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.75001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.58997e-06 [overlap_recompute_comm]: 2.91999e-06 [overlap_grad_ring_attention]: 6.44999e-06 [overlap_grad_flash_sp]: 2.948e-05 [begin_end_overlap_inline]: 7.79983e-07 [split_matmul_comm_elemetwise]: 2.19001e-06 [split_layernorm_comm]: 1.79998e-06 [handle_group_info]: 1.20999e-06 [symbol_engine_optimizer]: 0.00014627, [1] [Cycle 1]: 0.00013827, [6] [build]: 6.11998e-06 [elim_shapecalc]: 2.276e-05 [elim_not_effective]: 2.279e-05 [opt_reshape]: 1.868e-05 [fold_const_symbol]: 2.248e-05 [renormalize]: 1.99972e-07 [detach_backward]: 2.96999e-06 [pipeline_parallel_scheduler]: 1.60001e-06 [auto_monad_reorder]: 4.716e-05 [get_jit_bprop_graph]: 1.88002e-06 [rewriter_after_jit_bprop_graph]: 7e-06 [opt_after_jit_grad]: 0.00076383 [validate]: 6.863e-05 Sums bootstrap : 0.000791s : 5.17% type_inference : 0.006268s : 40.97% event_method : 0.000020s : 0.13% auto_monad : 0.000231s : 1.51% graph_reusing : 0.000006s : 0.04% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.15% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000004s : 0.03% pre_auto_parallel : 0.000044s : 0.29% insert-virtual-dataset : 0.000002s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000045s : 0.30% optimize.rewriter_before_opt_a : 0.000091s : 0.59% optimize.opt_a.expand_dump_flag : 0.000009s : 0.06% optimize.opt_a.switch_simplify : 0.000045s : 0.29% optimize.opt_a.loop_unroll : 0.000029s : 0.19% optimize.opt_a.a_1 : 0.000752s : 4.92% optimize.opt_a.with_stream_mark : 0.000052s : 0.34% optimize.opt_a.recompute_prepare : 0.000026s : 0.17% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.09% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.08% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.08% optimize.opt_a.parameter_eliminate : 0.000004s : 0.03% optimize.opt_a.a_2 : 0.000287s : 1.87% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.17% optimize.opt_a.shard : 0.000007s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.04% optimize.opt_a.shard_inline : 0.000021s : 0.14% optimize.opt_a.merge_send_recv : 0.000024s : 0.16% optimize.opt_a.auto_parallel : 0.000027s : 0.18% optimize.opt_a.parallel : 0.000044s : 0.29% optimize.opt_a.flash_sp : 0.000019s : 0.12% optimize.opt_a.merge_comm : 0.000012s : 0.08% optimize.opt_a.allreduce_fusion : 0.000011s : 0.07% optimize.opt_a.matmul_add_comm_reduction : 0.000032s : 0.21% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.20% optimize.opt_a.virtual_dataset : 0.000021s : 0.13% optimize.opt_a.get_grad_eliminate_ : 0.000020s : 0.13% optimize.opt_a.virtual_output : 0.000020s : 0.13% optimize.opt_a.merge_forward : 0.000014s : 0.09% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.04% optimize.opt_a.offload_activation : 0.000037s : 0.24% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000050s : 0.33% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.02% optimize.opt_a.before_grad : 0.000641s : 4.19% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000024s : 0.16% optimize.opt_a.meta_fg_expand : 0.000009s : 0.06% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.06% optimize.opt_a.receive_attached : 0.000006s : 0.04% optimize.opt_a.after_resolve : 0.000049s : 0.32% optimize.opt_a.a_after_grad : 0.000040s : 0.26% optimize.opt_a.renormalize : 0.001193s : 7.80% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.08% optimize.opt_a.auto_monad_grad : 0.000005s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000048s : 0.32% optimize.opt_a.cse : 0.000130s : 0.85% optimize.opt_a.a_3 : 0.000148s : 0.97% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.18% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000167s : 1.09% optimize.convert_after_rewriter : 0.000012s : 0.08% optimize.order_py_execute_after_rewriter : 0.000007s : 0.05% optimize.mutable_eliminate : 0.000839s : 5.49% optimize.opt_b.b_1 : 0.000230s : 1.50% optimize.opt_b.b_2 : 0.000013s : 0.08% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.04% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.04% optimize.opt_b.renormalize : 0.000001s : 0.01% optimize.opt_b.cse : 0.000065s : 0.43% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.16% optimize.overlap_param_gather : 0.000003s : 0.02% optimize.cconv : 0.000038s : 0.25% optimize.loop_unroll : 0.000771s : 5.04% optimize.opt_after_cconv.c_1 : 0.000067s : 0.44% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.07% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.05% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.cse : 0.000056s : 0.37% optimize.opt_after_cconv.renormalize : 0.000001s : 0.01% optimize.remove_dup_value : 0.000019s : 0.12% optimize.tuple_transform.d_1 : 0.000084s : 0.55% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.10% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000098s : 0.64% optimize.cse_after_recomputation.cse : 0.000032s : 0.21% optimize.environ_conv : 0.000013s : 0.08% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.07% optimize.bias_add_comm_swap : 0.000003s : 0.02% optimize.label_micro_interleaved_index : 0.000007s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000005s : 0.03% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000002s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000022s : 0.14% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000007s : 0.04% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.04% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000006s : 0.04% optimize.overlap_grad_flash_sp : 0.000029s : 0.19% optimize.begin_end_overlap_inline : 0.000001s : 0.01% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.15% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.15% optimize.symbol_engine_optimizer.opt_reshape : 0.000019s : 0.12% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.15% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000047s : 0.31% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000007s : 0.05% opt_after_jit_grad : 0.000764s : 4.99% validate : 0.000069s : 0.45% Time group info: ------[substitution.] 0.000246 54 4.11% : 0.000010s : 2: substitution.depend_value_elim 0.94% : 0.000002s : 4: substitution.elim_not_effective 0.87% : 0.000002s : 4: substitution.fold_const_symbol 3.29% : 0.000008s : 7: substitution.graph_param_transform 63.04% : 0.000155s : 1: substitution.inline 5.43% : 0.000013s : 8: substitution.j_node_and_user_rematch 3.37% : 0.000008s : 8: substitution.remove_not_recompute_node 4.25% : 0.000010s : 6: substitution.replace_old_param 7.89% : 0.000019s : 6: substitution.updatestate_pure_node_eliminater 6.80% : 0.000017s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.006154 2 87.44% : 0.005381s : 1: type_inference.infer 12.56% : 0.000773s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000154 1 100.00% : 0.000154s : 1: match.inline ------[predicate.] 0.000262 1649 0.76% : 0.000002s : 15: predicate.accumulaten_eliminater 0.98% : 0.000003s : 7: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 14: predicate.addn_check_dump 0.89% : 0.000002s : 15: predicate.addn_zero_filter 0.63% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.46% : 0.000006s : 29: predicate.arithmetic_simplify 0.71% : 0.000002s : 15: predicate.cast_eliminate 0.78% : 0.000002s : 14: predicate.check_bprop_eliminate 0.84% : 0.000002s : 14: predicate.compare_switch_simplify 0.22% : 0.000001s : 7: predicate.const_output_eliminate 0.89% : 0.000002s : 14: predicate.depend_value_elim 0.70% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.87% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.72% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.13% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 7: predicate.elim_not_effective 0.48% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.07% : 0.000003s : 22: predicate.environ_add_const_eliminate 0.99% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.02% : 0.000003s : 22: predicate.environ_get_depend_swap 1.85% : 0.000005s : 36: predicate.environ_get_eliminate 1.05% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.74% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.40% : 0.000004s : 16: predicate.float_depend_g_call 0.62% : 0.000002s : 14: predicate.float_environ_get_switch 0.97% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 7: predicate.fold_const_symbol 0.88% : 0.000002s : 14: predicate.get_grad_eliminate 0.35% : 0.000001s : 7: predicate.graph_param_transform 0.69% : 0.000002s : 14: predicate.incorporate_call 0.64% : 0.000002s : 14: predicate.incorporate_call_switch 6.01% : 0.000016s : 73: predicate.inline 1.62% : 0.000004s : 14: predicate.inline_without_move 0.58% : 0.000002s : 14: predicate.j_node_and_user_rematch 1.13% : 0.000003s : 14: predicate.less_batch_normalization 1.60% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.06% : 0.000005s : 44: predicate.load_eliminater 1.48% : 0.000004s : 7: predicate.loop_unroll_after_grad 1.14% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.83% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.73% : 0.000002s : 14: predicate.merge_addn 0.71% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.72% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.65% : 0.000002s : 15: predicate.minmaximum_grad 1.90% : 0.000005s : 7: predicate.mutable_eliminate 0.55% : 0.000001s : 7: predicate.opt_reshape 0.47% : 0.000001s : 7: predicate.parallel_virtual_node 1.01% : 0.000003s : 16: predicate.partial_defer_inline 1.12% : 0.000003s : 22: predicate.partial_eliminate 0.93% : 0.000002s : 15: predicate.print_const_string_wrapper 0.84% : 0.000002s : 14: predicate.reduce_all_const_elim 0.99% : 0.000003s : 15: predicate.reduce_eliminate 2.27% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.65% : 0.000002s : 14: predicate.remove_not_recompute_node 1.34% : 0.000004s : 29: predicate.replace_applicator 0.64% : 0.000002s : 14: predicate.replace_old_param 0.44% : 0.000001s : 7: predicate.reset_defer_inline 0.81% : 0.000002s : 15: predicate.reshape_eliminate 0.77% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.48% : 0.000001s : 7: predicate.row_tensor_eliminate 1.14% : 0.000003s : 14: predicate.same_eliminate 0.51% : 0.000001s : 14: predicate.set_cell_output_no_recompute 0.98% : 0.000003s : 14: predicate.shard_identity_eliminate 1.00% : 0.000003s : 14: predicate.special_op_eliminate 0.88% : 0.000002s : 14: predicate.specialize_transform 1.34% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 0.98% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.88% : 0.000002s : 16: predicate.switch_defer_inline 1.53% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.72% : 0.000010s : 58: predicate.switch_simplify 0.77% : 0.000002s : 15: predicate.tile_eliminate 0.75% : 0.000002s : 15: predicate.transpose_eliminate 1.82% : 0.000005s : 29: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000005s : 29: predicate.tuple_list_get_item_const_eliminator 1.51% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.51% : 0.000009s : 43: predicate.tuple_list_get_item_eliminator 1.48% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.53% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.55% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.31% : 0.000006s : 44: predicate.updatestate_pure_node_eliminater 3.31% : 0.000009s : 58: predicate.updatestate_useless_node_eliminater 0.51% : 0.000001s : 7: predicate.value_based_eliminate 0.88% : 0.000002s : 14: predicate.virtual_dataset_eliminate 1.04% : 0.000003s : 14: predicate.virtual_output_eliminate 0.35% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.50% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000892 6 45.98% : 0.000410s : 3: func_graph_cloner_run.FuncGraphClonerGraph 54.02% : 0.000482s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.069877 192 0.01% : 0.000008s : 1: ForceFp32Comm 29.20% : 0.020402s : 1: add_attr 29.17% : 0.020380s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.15% : 0.000103s : 1: add_recomputation 0.01% : 0.000005s : 1: assign_add_opt 0.34% : 0.000240s : 1: auto_monad 0.08% : 0.000053s : 1: auto_monad_reorder 0.01% : 0.000007s : 1: begin_end_overlap_inline 0.01% : 0.000010s : 1: bias_add_comm_swap 1.21% : 0.000844s : 1: bootstrap 0.06% : 0.000043s : 1: cconv 0.01% : 0.000006s : 1: comm_op_add_attrs 0.04% : 0.000026s : 1: control_data_broadcast_order 0.03% : 0.000019s : 1: convert_after_rewriter 0.08% : 0.000054s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000007s : 1: detach_backward 0.02% : 0.000017s : 1: environ_conv 0.04% : 0.000028s : 1: event_method 0.01% : 0.000009s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.02% : 0.000011s : 1: graph_reusing 0.01% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000005s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000005s : 1: interleave_parallel_branches 0.01% : 0.000005s : 1: interleave_split_concat_branches 0.01% : 0.000007s : 1: label_fine_grained_interleaved_index 0.02% : 0.000011s : 1: label_micro_interleaved_index 1.13% : 0.000787s : 1: loop_unroll 0.01% : 0.000005s : 1: merge_cast_opt 0.01% : 0.000007s : 1: micro_interleaved_order_control 1.22% : 0.000852s : 1: mutable_eliminate 0.02% : 0.000011s : 1: offloading_packed_experts 0.04% : 0.000029s : 1: opt.transform.loop_unroll_optimizer 0.04% : 0.000029s : 1: opt.transform.mutable_eliminate 3.00% : 0.002096s : 78: opt.transform.opt_a 0.09% : 0.000066s : 1: opt.transform.opt_after_cconv 0.07% : 0.000046s : 1: opt.transform.opt_after_jit_grad 0.30% : 0.000207s : 28: opt.transform.opt_b 0.14% : 0.000097s : 2: opt.transform.opt_trans_graph 0.12% : 0.000082s : 4: opt.transform.symbol_engine_opt 6.97% : 0.004870s : 1: opt_a 0.32% : 0.000227s : 1: opt_after_cconv 1.11% : 0.000778s : 1: opt_after_jit_grad 0.58% : 0.000405s : 1: opt_b 12.16% : 0.008498s : 1: optimize 0.05% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000014s : 1: order_py_execute_after_rewriter 0.05% : 0.000037s : 1: overlap_grad_flash_sp 0.01% : 0.000008s : 1: overlap_grad_matmul_and_grad_allreduce 0.02% : 0.000014s : 1: overlap_grad_ring_attention 0.01% : 0.000009s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000009s : 1: overlap_param_gather 0.01% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000009s : 1: overlap_recompute_comm 0.01% : 0.000008s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000009s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.07% : 0.000049s : 1: pre_auto_parallel 0.08% : 0.000053s : 1: py_interpret_to_execute 0.05% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000009s : 1: remove_cast_before_assign_add 0.04% : 0.000026s : 1: remove_dup_value 0.80% : 0.000558s : 1: renormalize.infer 0.89% : 0.000623s : 1: renormalize.specialize 0.01% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.02% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.25% : 0.000175s : 1: rewriter_after_opt_a 0.14% : 0.000096s : 1: rewriter_before_opt_a 0.01% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.01% : 0.000008s : 1: split_layernorm_comm 0.01% : 0.000009s : 1: split_matmul_comm_elemetwise 0.02% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.21% : 0.000149s : 1: symbol_engine_optimizer 0.20% : 0.000140s : 1: tuple_transform 9.01% : 0.006296s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[2-bfloat16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[2-bfloat16],max_mem:490.0M [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:40:14.540.972 [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 = 1.01453, [21] [bootstrap]: 0.00068969 [type_inference]: 0.144523 [event_method]: 1.436e-05 [auto_monad]: 0.00122591 [graph_reusing]: 6.05002e-06 [inline]: 3.3e-06 [add_attr]: 0.450812, [1] [add_attr_with_inline]: 0.45064, [1] [Cycle 1]: 0.00020872, [2] [tag_attr]: 6.596e-05 [meta_addattr_fg_expand]: 4.07e-06 [parallel-infer-symbol]: 4.2e-06 [pre_auto_parallel]: 8.291e-05 [insert-virtual-dataset]: 2.59001e-06 [parallel-infer-symbol-second]: 1.01002e-06 [dataset_repeat_opt]: 2.61e-06 [pipeline_split]: 1.62001e-06 [optimize]: 0.198849, [53] [py_interpret_to_execute]: 3.439e-05 [rewriter_before_opt_a]: 6.516e-05 [opt_a]: 0.178583, [2] [Cycle 1]: 0.175942, [45] [expand_dump_flag]: 2.79001e-06 [switch_simplify]: 3.044e-05 [loop_unroll]: 1.573e-05 [a_1]: 0.00110322 [with_stream_mark]: 2.335e-05 [recompute_prepare]: 1.421e-05 [updatestate_depend_eliminate]: 6.43e-06 [updatestate_assign_eliminate]: 5.42999e-06 [updatestate_loads_eliminate]: 5.58002e-06 [parameter_eliminate]: 2.28002e-06 [a_2]: 0.00036937 [accelerated_algorithm]: 1.11e-05 [shard]: 2.16e-06 [meta_shard_fg_expand]: 2.66e-06 [shard_inline]: 9.76e-06 [merge_send_recv]: 1.153e-05 [auto_parallel]: 5.26e-05 [parallel]: 0.00014205 [flash_sp]: 1.13e-05 [merge_comm]: 6.16e-06 [allreduce_fusion]: 5.76998e-06 [matmul_add_comm_reduction]: 1.317e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 1.389e-05 [virtual_dataset]: 1.122e-05 [get_grad_eliminate_]: 1.188e-05 [virtual_output]: 1.04e-05 [merge_forward]: 6.70998e-06 [cell_reuse_recompute_pass]: 1.42e-06 [offload_activation]: 1.393e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.041e-05 [merge_recompute_call_nodes]: 1.95001e-06 [before_grad]: 1.991e-05 [set_forward_comm_id_for_comm_node_pass]: 6.39001e-06 [meta_fg_expand]: 4.28999e-06 [flash_sp_send_recv_attached]: 2.91e-06 [receive_attached]: 2.85002e-06 [after_resolve]: 1.998e-05 [a_after_grad]: 1.771e-05 [renormalize]: 0.173013 [add_forward_monad_depend]: 9.70002e-06 [auto_monad_grad]: 2.86999e-06 [auto_monad_eliminator]: 2.89e-05 [cse]: 0.00022168 [a_3]: 9.409e-05 [Cycle 2]: 0.00262462, [45] [expand_dump_flag]: 3.03998e-06 [switch_simplify]: 1.343e-05 [loop_unroll]: 9.77999e-06 [a_1]: 0.00024465 [with_stream_mark]: 2.038e-05 [recompute_prepare]: 1.068e-05 [updatestate_depend_eliminate]: 5.91e-06 [updatestate_assign_eliminate]: 5.69e-06 [updatestate_loads_eliminate]: 4.84003e-06 [parameter_eliminate]: 1.86e-06 [a_2]: 0.00013655 [accelerated_algorithm]: 1.177e-05 [shard]: 2.49999e-06 [meta_shard_fg_expand]: 2.59999e-06 [shard_inline]: 1.034e-05 [merge_send_recv]: 1.133e-05 [auto_parallel]: 1.09e-05 [parallel]: 9.68002e-06 [flash_sp]: 4.58999e-06 [merge_comm]: 6.01e-06 [allreduce_fusion]: 5.08002e-06 [matmul_add_comm_reduction]: 1.318e-05 [allreduce_slice_to_reducescatter]: 6.29982e-07 [virtual_shard_identity]: 1.183e-05 [virtual_dataset]: 1.11e-05 [get_grad_eliminate_]: 1.004e-05 [virtual_output]: 1.039e-05 [merge_forward]: 6.05002e-06 [cell_reuse_recompute_pass]: 3.88001e-06 [offload_activation]: 7.243e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.933e-05 [merge_recompute_call_nodes]: 1.42999e-06 [before_grad]: 1.654e-05 [set_forward_comm_id_for_comm_node_pass]: 5.92999e-06 [meta_fg_expand]: 3.93999e-06 [flash_sp_send_recv_attached]: 1.60999e-06 [receive_attached]: 2.71e-06 [after_resolve]: 1.873e-05 [a_after_grad]: 1.819e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 1.64e-06 [auto_monad_grad]: 2.23002e-06 [auto_monad_eliminator]: 1.501e-05 [cse]: 0.00028467 [a_3]: 0.00099102 [py_interpret_to_execute_after_opt_a]: 2.165e-05 [slice_cell_reuse_recomputed_activation]: 2.48e-06 [rewriter_after_opt_a]: 0.00158217 [convert_after_rewriter]: 1.355e-05 [order_py_execute_after_rewriter]: 7.09001e-06 [mutable_eliminate]: 0.00335672 [opt_b]: 0.00895348, [1] [Cycle 1]: 0.0089412, [7] [b_1]: 0.00763113 [b_2]: 0.0003569 [updatestate_depend_eliminate]: 0.00028932 [updatestate_assign_eliminate]: 0.0003007 [updatestate_loads_eliminate]: 5.67001e-06 [renormalize]: 9.50007e-07 [cse]: 0.00018961 [optimize_parallel_all_gather_comm]: 0.00033081 [overlap_param_gather]: 2.49001e-06 [cconv]: 4.08e-05 [loop_unroll]: 0.00184838 [opt_after_cconv]: 0.00092295, [1] [Cycle 1]: 0.00091264, [7] [c_1]: 0.00052712 [parameter_eliminate]: 4.85999e-06 [updatestate_depend_eliminate]: 9.87999e-06 [updatestate_assign_eliminate]: 4.75999e-06 [updatestate_loads_eliminate]: 4.60999e-06 [cse]: 0.00031638 [renormalize]: 6.29982e-07 [remove_dup_value]: 1.744e-05 [tuple_transform]: 0.0006715, [1] [Cycle 1]: 0.00066559, [4] [d_1]: 0.00062546 [none_parameter_eliminate]: 2.36e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.197e-05 [partial_unused_args_eliminate]: 1.84e-06 [add_recomputation]: 0.00023932 [cse_after_recomputation]: 0.00013748, [1] [Cycle 1]: 0.00013242, [1] [cse]: 0.00012516 [environ_conv]: 0.00010543 [swap_dp_allreduce_reducescatter]: 7.46999e-06 [bias_add_comm_swap]: 3.02002e-06 [label_micro_interleaved_index]: 6.07999e-06 [label_fine_grained_interleaved_index]: 3.21999e-06 [merge_cast_opt]: 1.48002e-06 [slice_recompute_activation]: 2.20002e-06 [micro_interleaved_order_control]: 2.74999e-06 [assign_add_opt]: 1.40001e-06 [ForceFp32Comm]: 8.29983e-07 [remove_cast_before_assign_add]: 1.00999e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 3.03998e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 9.80013e-07 [interleave_split_concat_branches]: 1.38002e-06 [interleave_parallel_branches]: 1.35999e-06 [overlap_opt_shard_in_pipeline]: 1.22999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.69e-06 [control_data_broadcast_order]: 7.245e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 5.59e-06 [overlap_recompute_and_grad_model_parallel]: 6.968e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.79e-06 [overlap_recompute_allgather_and_fa_grad]: 1.56002e-06 [overlap_recompute_comm]: 2.43e-06 [overlap_grad_ring_attention]: 9.605e-05 [overlap_grad_flash_sp]: 2.689e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.56e-06 [split_layernorm_comm]: 1.91e-06 [handle_group_info]: 1.15001e-06 [symbol_engine_optimizer]: 0.00046462, [1] [Cycle 1]: 0.0004584, [6] [build]: 5.86e-06 [elim_shapecalc]: 0.00019134 [elim_not_effective]: 1.881e-05 [opt_reshape]: 1.072e-05 [fold_const_symbol]: 1.596e-05 [renormalize]: 2.09984e-07 [detach_backward]: 2.69999e-06 [pipeline_parallel_scheduler]: 1.59e-06 [auto_monad_reorder]: 0.00018056 [get_jit_bprop_graph]: 1.99999e-06 [rewriter_after_jit_bprop_graph]: 5.41998e-06 [opt_after_jit_grad]: 0.0021286 [validate]: 0.215722 Sums bootstrap : 0.000690s : 0.12% type_inference : 0.144523s : 25.77% event_method : 0.000014s : 0.00% auto_monad : 0.001226s : 0.22% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000066s : 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 : 0.000083s : 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 : 0.000034s : 0.01% optimize.rewriter_before_opt_a : 0.000065s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000044s : 0.01% optimize.opt_a.loop_unroll : 0.000026s : 0.00% optimize.opt_a.a_1 : 0.001348s : 0.24% optimize.opt_a.with_stream_mark : 0.000044s : 0.01% optimize.opt_a.recompute_prepare : 0.000025s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000506s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000023s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000020s : 0.00% optimize.opt_a.merge_send_recv : 0.000023s : 0.00% optimize.opt_a.auto_parallel : 0.000064s : 0.01% optimize.opt_a.parallel : 0.000152s : 0.03% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000012s : 0.00% optimize.opt_a.allreduce_fusion : 0.000011s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000026s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.00% optimize.opt_a.virtual_dataset : 0.000022s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000022s : 0.00% optimize.opt_a.virtual_output : 0.000021s : 0.00% optimize.opt_a.merge_forward : 0.000013s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000086s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000070s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000036s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 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 : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000039s : 0.01% optimize.opt_a.a_after_grad : 0.000036s : 0.01% optimize.opt_a.renormalize : 0.173014s : 30.85% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000044s : 0.01% optimize.opt_a.cse : 0.000506s : 0.09% optimize.opt_a.a_3 : 0.001085s : 0.19% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001582s : 0.28% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.003357s : 0.60% optimize.opt_b.b_1 : 0.007631s : 1.36% optimize.opt_b.b_2 : 0.000357s : 0.06% optimize.opt_b.updatestate_depend_eliminate : 0.000289s : 0.05% optimize.opt_b.updatestate_assign_eliminate : 0.000301s : 0.05% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000190s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000331s : 0.06% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.001848s : 0.33% optimize.opt_after_cconv.c_1 : 0.000527s : 0.09% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000316s : 0.06% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000625s : 0.11% 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 : 0.000239s : 0.04% optimize.cse_after_recomputation.cse : 0.000125s : 0.02% optimize.environ_conv : 0.000105s : 0.02% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 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 : 0.000072s : 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 : 0.000070s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000096s : 0.02% optimize.overlap_grad_flash_sp : 0.000027s : 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 : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000191s : 0.03% 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 : 0.000016s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000181s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.002129s : 0.38% validate : 0.215722s : 38.47% Time group info: ------[substitution.] 0.000513 54 2.25% : 0.000012s : 2: substitution.depend_value_elim 0.46% : 0.000002s : 4: substitution.elim_not_effective 0.36% : 0.000002s : 4: substitution.fold_const_symbol 1.66% : 0.000009s : 7: substitution.graph_param_transform 83.32% : 0.000428s : 1: substitution.inline 1.17% : 0.000006s : 8: substitution.j_node_and_user_rematch 1.47% : 0.000008s : 8: substitution.remove_not_recompute_node 1.55% : 0.000008s : 6: substitution.replace_old_param 4.19% : 0.000022s : 6: substitution.updatestate_pure_node_eliminater 3.57% : 0.000018s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.144188 2 95.50% : 0.137693s : 1: type_inference.infer 4.50% : 0.006495s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000427 1 100.00% : 0.000427s : 1: match.inline ------[predicate.] 0.000274 1649 0.87% : 0.000002s : 15: predicate.accumulaten_eliminater 0.80% : 0.000002s : 7: predicate.ad_related_special_op_eliminate 0.68% : 0.000002s : 14: predicate.addn_check_dump 0.77% : 0.000002s : 15: predicate.addn_zero_filter 0.68% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.29% : 0.000006s : 29: predicate.arithmetic_simplify 0.87% : 0.000002s : 15: predicate.cast_eliminate 0.75% : 0.000002s : 14: predicate.check_bprop_eliminate 0.68% : 0.000002s : 14: predicate.compare_switch_simplify 0.37% : 0.000001s : 7: predicate.const_output_eliminate 0.83% : 0.000002s : 14: predicate.depend_value_elim 0.74% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.84% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.77% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.14% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 7: predicate.elim_not_effective 0.59% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.35% : 0.000004s : 22: predicate.environ_get_add_eliminate 1.36% : 0.000004s : 22: predicate.environ_get_depend_swap 1.98% : 0.000005s : 36: predicate.environ_get_eliminate 1.45% : 0.000004s : 22: predicate.environ_get_set_eliminate 0.75% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.31% : 0.000004s : 16: predicate.float_depend_g_call 0.71% : 0.000002s : 14: predicate.float_environ_get_switch 1.04% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.27% : 0.000001s : 7: predicate.fold_const_symbol 0.77% : 0.000002s : 14: predicate.get_grad_eliminate 0.24% : 0.000001s : 7: predicate.graph_param_transform 0.67% : 0.000002s : 14: predicate.incorporate_call 0.57% : 0.000002s : 14: predicate.incorporate_call_switch 5.55% : 0.000015s : 73: predicate.inline 1.19% : 0.000003s : 14: predicate.inline_without_move 0.39% : 0.000001s : 14: predicate.j_node_and_user_rematch 0.98% : 0.000003s : 14: predicate.less_batch_normalization 1.66% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.18% : 0.000006s : 44: predicate.load_eliminater 1.20% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.07% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.98% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.71% : 0.000002s : 14: predicate.merge_addn 1.74% : 0.000005s : 14: predicate.micro_step_allgather_replace 0.68% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.67% : 0.000002s : 15: predicate.minmaximum_grad 1.53% : 0.000004s : 7: predicate.mutable_eliminate 0.46% : 0.000001s : 7: predicate.opt_reshape 0.65% : 0.000002s : 7: predicate.parallel_virtual_node 0.91% : 0.000002s : 16: predicate.partial_defer_inline 1.07% : 0.000003s : 22: predicate.partial_eliminate 0.79% : 0.000002s : 15: predicate.print_const_string_wrapper 0.72% : 0.000002s : 14: predicate.reduce_all_const_elim 1.11% : 0.000003s : 15: predicate.reduce_eliminate 2.16% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 14: predicate.remove_not_recompute_node 1.17% : 0.000003s : 29: predicate.replace_applicator 0.69% : 0.000002s : 14: predicate.replace_old_param 0.46% : 0.000001s : 7: predicate.reset_defer_inline 0.85% : 0.000002s : 15: predicate.reshape_eliminate 0.75% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.57% : 0.000002s : 7: predicate.row_tensor_eliminate 1.00% : 0.000003s : 14: predicate.same_eliminate 0.50% : 0.000001s : 14: predicate.set_cell_output_no_recompute 0.91% : 0.000002s : 14: predicate.shard_identity_eliminate 1.02% : 0.000003s : 14: predicate.special_op_eliminate 0.74% : 0.000002s : 14: predicate.specialize_transform 1.22% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 1.04% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.46% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.78% : 0.000002s : 16: predicate.switch_defer_inline 1.49% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.47% : 0.000009s : 58: predicate.switch_simplify 0.82% : 0.000002s : 15: predicate.tile_eliminate 0.74% : 0.000002s : 15: predicate.transpose_eliminate 1.56% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.53% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.42% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.63% : 0.000010s : 43: predicate.tuple_list_get_item_eliminator 1.56% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.37% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.82% : 0.000005s : 29: predicate.tuple_to_list_eliminator_ 2.93% : 0.000008s : 44: predicate.updatestate_pure_node_eliminater 3.89% : 0.000011s : 58: predicate.updatestate_useless_node_eliminater 0.69% : 0.000002s : 7: predicate.value_based_eliminate 0.79% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.78% : 0.000002s : 14: predicate.virtual_output_eliminate 0.36% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.48% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003942 6 8.07% : 0.000318s : 3: func_graph_cloner_run.FuncGraphClonerGraph 91.93% : 0.003624s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.633056 192 0.00% : 0.000004s : 1: ForceFp32Comm 27.61% : 0.450819s : 1: add_attr 27.60% : 0.450644s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000246s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.001235s : 1: auto_monad 0.01% : 0.000186s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000726s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000077s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000141s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000109s : 1: environ_conv 0.00% : 0.000022s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 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% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000092s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.11% : 0.001862s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.21% : 0.003372s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000182s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000030s : 1: opt.transform.mutable_eliminate 0.19% : 0.003099s : 78: opt.transform.opt_a 0.03% : 0.000525s : 1: opt.transform.opt_after_cconv 0.02% : 0.000253s : 1: opt.transform.opt_after_jit_grad 0.44% : 0.007120s : 28: opt.transform.opt_b 0.04% : 0.000635s : 2: opt.transform.opt_trans_graph 0.01% : 0.000233s : 4: opt.transform.symbol_engine_opt 10.94% : 0.178588s : 1: opt_a 0.06% : 0.000927s : 1: opt_after_cconv 0.13% : 0.002142s : 1: opt_after_jit_grad 0.55% : 0.008959s : 1: opt_b 12.18% : 0.198855s : 1: optimize 0.02% : 0.000337s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000291s : 1: order_py_execute_after_rewriter 0.00% : 0.000031s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000100s : 1: overlap_grad_ring_attention 0.01% : 0.000097s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000155s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000088s : 1: pre_auto_parallel 0.00% : 0.000039s : 1: py_interpret_to_execute 0.00% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000089s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 10.47% : 0.170950s : 1: renormalize.infer 0.13% : 0.002044s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.10% : 0.001592s : 1: rewriter_after_opt_a 0.00% : 0.000069s : 1: rewriter_before_opt_a 0.00% : 0.000078s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000467s : 1: symbol_engine_optimizer 0.04% : 0.000675s : 1: tuple_transform 8.85% : 0.144551s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[3-float16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[3-float16],max_mem:490.0M [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:41:39.917.911 [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 = 0.14129, [21] [bootstrap]: 0.00092929 [type_inference]: 0.00932005 [event_method]: 1.587e-05 [auto_monad]: 0.00017923 [graph_reusing]: 5.66998e-06 [inline]: 2.16e-06 [add_attr]: 0.00639747, [1] [add_attr_with_inline]: 0.00637894, [1] [Cycle 1]: 8.956e-05, [2] [tag_attr]: 2.21e-05 [meta_addattr_fg_expand]: 4.68001e-06 [parallel-infer-symbol]: 3.77002e-06 [pre_auto_parallel]: 4.031e-05 [insert-virtual-dataset]: 2.46e-06 [parallel-infer-symbol-second]: 7.30011e-07 [dataset_repeat_opt]: 1.81e-06 [pipeline_split]: 1.39998e-06 [optimize]: 0.122536, [53] [py_interpret_to_execute]: 4.021e-05 [rewriter_before_opt_a]: 6.981e-05 [opt_a]: 0.00412484, [2] [Cycle 1]: 0.0028207, [45] [expand_dump_flag]: 2.46e-06 [switch_simplify]: 3.325e-05 [loop_unroll]: 1.554e-05 [a_1]: 0.00048652 [with_stream_mark]: 2.501e-05 [recompute_prepare]: 1.488e-05 [updatestate_depend_eliminate]: 6.60002e-06 [updatestate_assign_eliminate]: 6.84999e-06 [updatestate_loads_eliminate]: 5.39e-06 [parameter_eliminate]: 1.88997e-06 [a_2]: 0.00015369 [accelerated_algorithm]: 1.348e-05 [shard]: 2.66e-06 [meta_shard_fg_expand]: 2.91e-06 [shard_inline]: 1.533e-05 [merge_send_recv]: 1.161e-05 [auto_parallel]: 1.218e-05 [parallel]: 3.643e-05 [flash_sp]: 1.22e-05 [merge_comm]: 6.03998e-06 [allreduce_fusion]: 5.40999e-06 [matmul_add_comm_reduction]: 1.408e-05 [allreduce_slice_to_reducescatter]: 7.10017e-07 [virtual_shard_identity]: 1.568e-05 [virtual_dataset]: 1.544e-05 [get_grad_eliminate_]: 1.379e-05 [virtual_output]: 1.287e-05 [merge_forward]: 6.38e-06 [cell_reuse_recompute_pass]: 1.62001e-06 [offload_activation]: 1.432e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.323e-05 [merge_recompute_call_nodes]: 1.62999e-06 [before_grad]: 3.031e-05 [set_forward_comm_id_for_comm_node_pass]: 6.12999e-06 [meta_fg_expand]: 4.28999e-06 [flash_sp_send_recv_attached]: 3.75e-06 [receive_attached]: 2.99999e-06 [after_resolve]: 2.783e-05 [a_after_grad]: 2.654e-05 [renormalize]: 0.00109754 [add_forward_monad_depend]: 7.92e-06 [auto_monad_grad]: 2.67001e-06 [auto_monad_eliminator]: 8.052e-05 [cse]: 7.618e-05 [a_3]: 8.415e-05 [Cycle 2]: 0.00128849, [45] [expand_dump_flag]: 2.73998e-06 [switch_simplify]: 1.614e-05 [loop_unroll]: 1.014e-05 [a_1]: 0.00024488 [with_stream_mark]: 2.512e-05 [recompute_prepare]: 1.429e-05 [updatestate_depend_eliminate]: 6.48e-06 [updatestate_assign_eliminate]: 6.44001e-06 [updatestate_loads_eliminate]: 8.43001e-06 [parameter_eliminate]: 2.24001e-06 [a_2]: 0.00013052 [accelerated_algorithm]: 1.421e-05 [shard]: 2.49999e-06 [meta_shard_fg_expand]: 3.18998e-06 [shard_inline]: 1.405e-05 [merge_send_recv]: 1.059e-05 [auto_parallel]: 1.183e-05 [parallel]: 9.30001e-06 [flash_sp]: 4.74e-06 [merge_comm]: 6.17999e-06 [allreduce_fusion]: 5.17999e-06 [matmul_add_comm_reduction]: 1.694e-05 [allreduce_slice_to_reducescatter]: 5.50004e-07 [virtual_shard_identity]: 1.295e-05 [virtual_dataset]: 1.248e-05 [get_grad_eliminate_]: 9.44e-06 [virtual_output]: 1.051e-05 [merge_forward]: 6.49999e-06 [cell_reuse_recompute_pass]: 3.03e-06 [offload_activation]: 2.311e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.308e-05 [merge_recompute_call_nodes]: 1.86003e-06 [before_grad]: 1.55e-05 [set_forward_comm_id_for_comm_node_pass]: 5.76e-06 [meta_fg_expand]: 3.44001e-06 [flash_sp_send_recv_attached]: 1.72001e-06 [receive_attached]: 5.37001e-06 [after_resolve]: 2.521e-05 [a_after_grad]: 1.527e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.90998e-06 [auto_monad_grad]: 2.09e-06 [auto_monad_eliminator]: 2.069e-05 [cse]: 5.354e-05 [a_3]: 6.612e-05 [py_interpret_to_execute_after_opt_a]: 2.688e-05 [slice_cell_reuse_recomputed_activation]: 1.96e-06 [rewriter_after_opt_a]: 0.00016434 [convert_after_rewriter]: 1.239e-05 [order_py_execute_after_rewriter]: 6.73e-06 [mutable_eliminate]: 0.115244 [opt_b]: 0.0006152, [1] [Cycle 1]: 0.00059973, [7] [b_1]: 0.00037681 [b_2]: 1.368e-05 [updatestate_depend_eliminate]: 1.694e-05 [updatestate_assign_eliminate]: 1.126e-05 [updatestate_loads_eliminate]: 5.25001e-06 [renormalize]: 1.07e-06 [cse]: 8.785e-05 [optimize_parallel_all_gather_comm]: 2.93e-05 [overlap_param_gather]: 5.04e-06 [cconv]: 4.618e-05 [loop_unroll]: 0.00075913 [opt_after_cconv]: 0.00027342, [1] [Cycle 1]: 0.00026378, [7] [c_1]: 9.601e-05 [parameter_eliminate]: 6.93e-06 [updatestate_depend_eliminate]: 1.206e-05 [updatestate_assign_eliminate]: 4.67e-06 [updatestate_loads_eliminate]: 7.20998e-06 [cse]: 5.525e-05 [renormalize]: 7.59988e-07 [remove_dup_value]: 2.231e-05 [tuple_transform]: 0.00021933, [1] [Cycle 1]: 0.00020588, [4] [d_1]: 0.0001373 [none_parameter_eliminate]: 2.68e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.388e-05 [partial_unused_args_eliminate]: 2.57001e-06 [add_recomputation]: 0.00010392 [cse_after_recomputation]: 6.077e-05, [1] [Cycle 1]: 5.22e-05, [1] [cse]: 3.969e-05 [environ_conv]: 1.341e-05 [swap_dp_allreduce_reducescatter]: 8.67998e-06 [bias_add_comm_swap]: 3.08e-06 [label_micro_interleaved_index]: 7.22002e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.91e-06 [slice_recompute_activation]: 2.09999e-06 [micro_interleaved_order_control]: 2.50002e-06 [assign_add_opt]: 1.29e-06 [ForceFp32Comm]: 1.25999e-06 [remove_cast_before_assign_add]: 9.89996e-07 [full_micro_interleaved_order_control]: 6.07001e-06 [reorder_send_recv_between_fp_bp]: 2.63e-06 [comm_op_add_attrs]: 1.05999e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.33002e-06 [interleave_parallel_branches]: 1.15001e-06 [overlap_opt_shard_in_pipeline]: 3.06999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.81998e-06 [control_data_broadcast_order]: 2.443e-05 [grouped_pairwise_exchange_alltoall]: 1.59998e-06 [offloading_packed_experts]: 6.14001e-06 [overlap_recompute_and_grad_model_parallel]: 8.17e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 4.03001e-06 [overlap_recompute_comm]: 2.39001e-06 [overlap_grad_ring_attention]: 1.046e-05 [overlap_grad_flash_sp]: 3.124e-05 [begin_end_overlap_inline]: 5.50004e-07 [split_matmul_comm_elemetwise]: 2.21e-06 [split_layernorm_comm]: 1.82999e-06 [handle_group_info]: 1.00999e-06 [symbol_engine_optimizer]: 0.00018932, [1] [Cycle 1]: 0.00017916, [6] [build]: 5.39e-06 [elim_shapecalc]: 3.78e-05 [elim_not_effective]: 2.377e-05 [opt_reshape]: 1.463e-05 [fold_const_symbol]: 1.989e-05 [renormalize]: 2.09984e-07 [detach_backward]: 2.43e-06 [pipeline_parallel_scheduler]: 1.62999e-06 [auto_monad_reorder]: 4.356e-05 [get_jit_bprop_graph]: 2.41998e-06 [rewriter_after_jit_bprop_graph]: 2.062e-05 [opt_after_jit_grad]: 0.00146854 [validate]: 7.673e-05 Sums bootstrap : 0.000929s : 0.70% type_inference : 0.009320s : 7.00% event_method : 0.000016s : 0.01% auto_monad : 0.000179s : 0.13% graph_reusing : 0.000006s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000022s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000040s : 0.03% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000001s : 0.00% optimize.py_interpret_to_execute : 0.000040s : 0.03% optimize.rewriter_before_opt_a : 0.000070s : 0.05% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000049s : 0.04% optimize.opt_a.loop_unroll : 0.000026s : 0.02% optimize.opt_a.a_1 : 0.000731s : 0.55% optimize.opt_a.with_stream_mark : 0.000050s : 0.04% optimize.opt_a.recompute_prepare : 0.000029s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000014s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000284s : 0.21% optimize.opt_a.accelerated_algorithm : 0.000028s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000029s : 0.02% optimize.opt_a.merge_send_recv : 0.000022s : 0.02% optimize.opt_a.auto_parallel : 0.000024s : 0.02% optimize.opt_a.parallel : 0.000046s : 0.03% 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 : 0.000031s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000029s : 0.02% optimize.opt_a.virtual_dataset : 0.000028s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.02% optimize.opt_a.virtual_output : 0.000023s : 0.02% 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 : 0.000037s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000056s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000046s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.01% optimize.opt_a.after_resolve : 0.000053s : 0.04% optimize.opt_a.a_after_grad : 0.000042s : 0.03% optimize.opt_a.renormalize : 0.001098s : 0.82% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000101s : 0.08% optimize.opt_a.cse : 0.000130s : 0.10% optimize.opt_a.a_3 : 0.000150s : 0.11% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000164s : 0.12% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.115244s : 86.54% optimize.opt_b.b_1 : 0.000377s : 0.28% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000088s : 0.07% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.02% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000046s : 0.03% optimize.loop_unroll : 0.000759s : 0.57% optimize.opt_after_cconv.c_1 : 0.000096s : 0.07% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.01% optimize.opt_after_cconv.cse : 0.000055s : 0.04% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.02% optimize.tuple_transform.d_1 : 0.000137s : 0.10% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000104s : 0.08% optimize.cse_after_recomputation.cse : 0.000040s : 0.03% optimize.environ_conv : 0.000013s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000006s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000004s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.01% optimize.overlap_grad_flash_sp : 0.000031s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000024s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000044s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000021s : 0.02% opt_after_jit_grad : 0.001469s : 1.10% validate : 0.000077s : 0.06% Time group info: ------[substitution.] 0.000228 54 4.37% : 0.000010s : 2: substitution.depend_value_elim 1.25% : 0.000003s : 4: substitution.elim_not_effective 0.79% : 0.000002s : 4: substitution.fold_const_symbol 3.84% : 0.000009s : 7: substitution.graph_param_transform 61.62% : 0.000140s : 1: substitution.inline 2.24% : 0.000005s : 8: substitution.j_node_and_user_rematch 3.62% : 0.000008s : 8: substitution.remove_not_recompute_node 3.70% : 0.000008s : 6: substitution.replace_old_param 10.87% : 0.000025s : 6: substitution.updatestate_pure_node_eliminater 7.70% : 0.000018s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.009220 2 91.01% : 0.008391s : 1: type_inference.infer 8.99% : 0.000829s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000139 1 100.00% : 0.000139s : 1: match.inline ------[predicate.] 0.000266 1649 0.73% : 0.000002s : 15: predicate.accumulaten_eliminater 1.37% : 0.000004s : 7: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 14: predicate.addn_check_dump 0.77% : 0.000002s : 15: predicate.addn_zero_filter 0.76% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.22% : 0.000006s : 29: predicate.arithmetic_simplify 0.78% : 0.000002s : 15: predicate.cast_eliminate 0.75% : 0.000002s : 14: predicate.check_bprop_eliminate 0.66% : 0.000002s : 14: predicate.compare_switch_simplify 0.24% : 0.000001s : 7: predicate.const_output_eliminate 0.80% : 0.000002s : 14: predicate.depend_value_elim 0.76% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.92% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.77% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.46% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 7: predicate.elim_not_effective 0.73% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.08% : 0.000003s : 22: predicate.environ_add_const_eliminate 0.99% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.05% : 0.000003s : 22: predicate.environ_get_depend_swap 1.80% : 0.000005s : 36: predicate.environ_get_eliminate 1.17% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.78% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.52% : 0.000004s : 16: predicate.float_depend_g_call 0.68% : 0.000002s : 14: predicate.float_environ_get_switch 1.02% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 7: predicate.fold_const_symbol 0.83% : 0.000002s : 14: predicate.get_grad_eliminate 0.29% : 0.000001s : 7: predicate.graph_param_transform 0.71% : 0.000002s : 14: predicate.incorporate_call 0.62% : 0.000002s : 14: predicate.incorporate_call_switch 5.91% : 0.000016s : 73: predicate.inline 1.15% : 0.000003s : 14: predicate.inline_without_move 0.40% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.01% : 0.000003s : 14: predicate.less_batch_normalization 1.78% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.13% : 0.000006s : 44: predicate.load_eliminater 1.48% : 0.000004s : 7: predicate.loop_unroll_after_grad 1.15% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.64% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.68% : 0.000002s : 14: predicate.merge_addn 0.72% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.70% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.66% : 0.000002s : 15: predicate.minmaximum_grad 3.07% : 0.000008s : 7: predicate.mutable_eliminate 0.45% : 0.000001s : 7: predicate.opt_reshape 0.45% : 0.000001s : 7: predicate.parallel_virtual_node 0.96% : 0.000003s : 16: predicate.partial_defer_inline 1.22% : 0.000003s : 22: predicate.partial_eliminate 0.76% : 0.000002s : 15: predicate.print_const_string_wrapper 0.74% : 0.000002s : 14: predicate.reduce_all_const_elim 0.98% : 0.000003s : 15: predicate.reduce_eliminate 2.28% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 14: predicate.remove_not_recompute_node 1.31% : 0.000003s : 29: predicate.replace_applicator 0.66% : 0.000002s : 14: predicate.replace_old_param 0.50% : 0.000001s : 7: predicate.reset_defer_inline 0.81% : 0.000002s : 15: predicate.reshape_eliminate 0.85% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.50% : 0.000001s : 7: predicate.row_tensor_eliminate 1.02% : 0.000003s : 14: predicate.same_eliminate 0.49% : 0.000001s : 14: predicate.set_cell_output_no_recompute 1.03% : 0.000003s : 14: predicate.shard_identity_eliminate 0.92% : 0.000002s : 14: predicate.special_op_eliminate 0.83% : 0.000002s : 14: predicate.specialize_transform 1.53% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 1.02% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.44% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.84% : 0.000002s : 16: predicate.switch_defer_inline 1.43% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.51% : 0.000009s : 58: predicate.switch_simplify 0.71% : 0.000002s : 15: predicate.tile_eliminate 0.72% : 0.000002s : 15: predicate.transpose_eliminate 1.60% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.58% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.39% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.15% : 0.000008s : 43: predicate.tuple_list_get_item_eliminator 1.57% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.60% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.54% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.25% : 0.000006s : 44: predicate.updatestate_pure_node_eliminater 3.62% : 0.000010s : 58: predicate.updatestate_useless_node_eliminater 0.47% : 0.000001s : 7: predicate.value_based_eliminate 0.97% : 0.000003s : 14: predicate.virtual_dataset_eliminate 0.76% : 0.000002s : 14: predicate.virtual_output_eliminate 0.35% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.50% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001097 6 54.43% : 0.000597s : 3: func_graph_cloner_run.FuncGraphClonerGraph 45.57% : 0.000500s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.273459 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.34% : 0.006404s : 1: add_attr 2.33% : 0.006384s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000113s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.07% : 0.000187s : 1: auto_monad 0.02% : 0.000051s : 1: auto_monad_reorder 0.00% : 0.000012s : 1: begin_end_overlap_inline 0.00% : 0.000010s : 1: bias_add_comm_swap 0.36% : 0.000998s : 1: bootstrap 0.02% : 0.000054s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000029s : 1: control_data_broadcast_order 0.01% : 0.000017s : 1: convert_after_rewriter 0.02% : 0.000064s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000017s : 1: environ_conv 0.01% : 0.000023s : 1: event_method 0.00% : 0.000012s : 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% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000008s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.28% : 0.000773s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000009s : 1: micro_interleaved_order_control 42.15% : 0.115274s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000049s : 1: opt.transform.mutable_eliminate 0.56% : 0.001521s : 78: opt.transform.opt_a 0.03% : 0.000094s : 1: opt.transform.opt_after_cconv 0.03% : 0.000075s : 1: opt.transform.opt_after_jit_grad 0.12% : 0.000333s : 28: opt.transform.opt_b 0.05% : 0.000148s : 2: opt.transform.opt_trans_graph 0.03% : 0.000091s : 4: opt.transform.symbol_engine_opt 1.51% : 0.004130s : 1: opt_a 0.10% : 0.000278s : 1: opt_after_cconv 0.54% : 0.001487s : 1: opt_after_jit_grad 0.23% : 0.000620s : 1: opt_b 44.81% : 0.122544s : 1: optimize 0.01% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000037s : 1: overlap_grad_flash_sp 0.00% : 0.000010s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000020s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000010s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000008s : 1: overlap_recompute_comm 0.00% : 0.000011s : 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% : 0.000004s : 1: pipeline_split 0.02% : 0.000045s : 1: pre_auto_parallel 0.02% : 0.000044s : 1: py_interpret_to_execute 0.01% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.01% : 0.000026s : 1: remove_dup_value 0.20% : 0.000551s : 1: renormalize.infer 0.19% : 0.000533s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000026s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000173s : 1: rewriter_after_opt_a 0.03% : 0.000075s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000008s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000196s : 1: symbol_engine_optimizer 0.08% : 0.000229s : 1: tuple_transform 3.42% : 0.009345s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[3-int8] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[3-int8],max_mem:240.0M [WARNING] ME(156361:281473094885168,MainProcess):2026-01-29-17:42:17.488.371 [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 = 0.12565, [21] [bootstrap]: 0.00071705 [type_inference]: 0.00555871 [event_method]: 1.28e-05 [auto_monad]: 0.00019815 [graph_reusing]: 5.66998e-06 [inline]: 2.68998e-06 [add_attr]: 0.110134, [1] [add_attr_with_inline]: 0.110113, [1] [Cycle 1]: 7.225e-05, [2] [tag_attr]: 2.018e-05 [meta_addattr_fg_expand]: 4.22e-06 [parallel-infer-symbol]: 3.73999e-06 [pre_auto_parallel]: 4.599e-05 [insert-virtual-dataset]: 2.36e-06 [parallel-infer-symbol-second]: 7.30011e-07 [dataset_repeat_opt]: 2.01e-06 [pipeline_split]: 2.12001e-06 [optimize]: 0.00797315, [53] [py_interpret_to_execute]: 4.944e-05 [rewriter_before_opt_a]: 8.837e-05 [opt_a]: 0.0043538, [2] [Cycle 1]: 0.00307001, [45] [expand_dump_flag]: 2.86999e-06 [switch_simplify]: 3.852e-05 [loop_unroll]: 2.547e-05 [a_1]: 0.0007322 [with_stream_mark]: 2.223e-05 [recompute_prepare]: 1.87e-05 [updatestate_depend_eliminate]: 7.46999e-06 [updatestate_assign_eliminate]: 6.69999e-06 [updatestate_loads_eliminate]: 5.29e-06 [parameter_eliminate]: 1.79998e-06 [a_2]: 0.00017388 [accelerated_algorithm]: 1.255e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 2.73e-06 [shard_inline]: 1.099e-05 [merge_send_recv]: 1.101e-05 [auto_parallel]: 9.54e-06 [parallel]: 3.096e-05 [flash_sp]: 1.055e-05 [merge_comm]: 5.61e-06 [allreduce_fusion]: 5.62999e-06 [matmul_add_comm_reduction]: 1.226e-05 [allreduce_slice_to_reducescatter]: 7.59988e-07 [virtual_shard_identity]: 1.382e-05 [virtual_dataset]: 1.116e-05 [get_grad_eliminate_]: 1.082e-05 [virtual_output]: 1.067e-05 [merge_forward]: 6.31e-06 [cell_reuse_recompute_pass]: 2.19999e-06 [offload_activation]: 3.999e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.692e-05 [merge_recompute_call_nodes]: 2.14999e-06 [before_grad]: 2.421e-05 [set_forward_comm_id_for_comm_node_pass]: 9.02e-06 [meta_fg_expand]: 4.73001e-06 [flash_sp_send_recv_attached]: 2.74001e-06 [receive_attached]: 2.17999e-06 [after_resolve]: 1.982e-05 [a_after_grad]: 2.646e-05 [renormalize]: 0.00108135 [add_forward_monad_depend]: 8.70999e-06 [auto_monad_grad]: 3.06999e-06 [auto_monad_eliminator]: 2.642e-05 [cse]: 7.456e-05 [a_3]: 8.009e-05 [Cycle 2]: 0.00126986, [45] [expand_dump_flag]: 2.06e-06 [switch_simplify]: 1.232e-05 [loop_unroll]: 9.87999e-06 [a_1]: 0.00024396 [with_stream_mark]: 1.889e-05 [recompute_prepare]: 1.125e-05 [updatestate_depend_eliminate]: 6.48e-06 [updatestate_assign_eliminate]: 7.83001e-06 [updatestate_loads_eliminate]: 4.90001e-06 [parameter_eliminate]: 1.47001e-06 [a_2]: 0.00013028 [accelerated_algorithm]: 1.006e-05 [shard]: 2.11998e-06 [meta_shard_fg_expand]: 3.20002e-06 [shard_inline]: 9.76e-06 [merge_send_recv]: 8.47998e-06 [auto_parallel]: 1.182e-05 [parallel]: 1.219e-05 [flash_sp]: 4.38999e-06 [merge_comm]: 5.22e-06 [allreduce_fusion]: 5.07e-06 [matmul_add_comm_reduction]: 1.399e-05 [allreduce_slice_to_reducescatter]: 7.39994e-07 [virtual_shard_identity]: 1.594e-05 [virtual_dataset]: 1.259e-05 [get_grad_eliminate_]: 1.068e-05 [virtual_output]: 1.209e-05 [merge_forward]: 8.16002e-06 [cell_reuse_recompute_pass]: 2.17999e-06 [offload_activation]: 3.028e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.635e-05 [merge_recompute_call_nodes]: 1.10999e-06 [before_grad]: 1.856e-05 [set_forward_comm_id_for_comm_node_pass]: 6.09001e-06 [meta_fg_expand]: 3.84002e-06 [flash_sp_send_recv_attached]: 1.46998e-06 [receive_attached]: 1.81e-06 [after_resolve]: 2.03e-05 [a_after_grad]: 1.797e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 1.59e-06 [auto_monad_grad]: 1.71e-06 [auto_monad_eliminator]: 1.537e-05 [cse]: 5.178e-05 [a_3]: 6.59e-05 [py_interpret_to_execute_after_opt_a]: 2.231e-05 [slice_cell_reuse_recomputed_activation]: 2.86999e-06 [rewriter_after_opt_a]: 0.00016856 [convert_after_rewriter]: 1.241e-05 [order_py_execute_after_rewriter]: 9.97999e-06 [mutable_eliminate]: 0.00084605 [opt_b]: 0.00060114, [1] [Cycle 1]: 0.00059125, [7] [b_1]: 0.00040526 [b_2]: 1.574e-05 [updatestate_depend_eliminate]: 1.242e-05 [updatestate_assign_eliminate]: 5.72001e-06 [updatestate_loads_eliminate]: 7.75998e-06 [renormalize]: 4.80009e-07 [cse]: 7.587e-05 [optimize_parallel_all_gather_comm]: 2.439e-05 [overlap_param_gather]: 4.62e-06 [cconv]: 3.82e-05 [loop_unroll]: 0.00061569 [opt_after_cconv]: 0.00021429, [1] [Cycle 1]: 0.00020694, [7] [c_1]: 8.099e-05 [parameter_eliminate]: 5.15999e-06 [updatestate_depend_eliminate]: 8.73001e-06 [updatestate_assign_eliminate]: 4.77e-06 [updatestate_loads_eliminate]: 4.34997e-06 [cse]: 5.322e-05 [renormalize]: 6.69999e-07 [remove_dup_value]: 1.68e-05 [tuple_transform]: 0.00015121, [1] [Cycle 1]: 0.00014543, [4] [d_1]: 0.00010364 [none_parameter_eliminate]: 1.94999e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.524e-05 [partial_unused_args_eliminate]: 2.18998e-06 [add_recomputation]: 8.78e-05 [cse_after_recomputation]: 4.656e-05, [1] [Cycle 1]: 4.118e-05, [1] [cse]: 3.154e-05 [environ_conv]: 1.244e-05 [swap_dp_allreduce_reducescatter]: 8.12003e-06 [bias_add_comm_swap]: 3.88999e-06 [label_micro_interleaved_index]: 5.97001e-06 [label_fine_grained_interleaved_index]: 3.08e-06 [merge_cast_opt]: 1.67999e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 2.67001e-06 [assign_add_opt]: 1.54998e-06 [ForceFp32Comm]: 1.14998e-06 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 3.31001e-06 [comm_op_add_attrs]: 1.07e-06 [add_comm_op_reuse_tag]: 9.80013e-07 [interleave_split_concat_branches]: 1.36998e-06 [interleave_parallel_branches]: 1.22999e-06 [overlap_opt_shard_in_pipeline]: 1.96e-06 [overlap_opt_shard_grad_in_pipeline]: 1.76e-06 [control_data_broadcast_order]: 1.914e-05 [grouped_pairwise_exchange_alltoall]: 1.49e-06 [offloading_packed_experts]: 5.32001e-06 [overlap_recompute_and_grad_model_parallel]: 6.71e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47001e-06 [overlap_recompute_comm]: 2.74999e-06 [overlap_grad_ring_attention]: 5.84999e-06 [overlap_grad_flash_sp]: 2.791e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.14e-06 [split_layernorm_comm]: 1.86003e-06 [handle_group_info]: 1.00001e-06 [symbol_engine_optimizer]: 0.00012786, [1] [Cycle 1]: 0.00012256, [6] [build]: 6.16e-06 [elim_shapecalc]: 1.96e-05 [elim_not_effective]: 2.291e-05 [opt_reshape]: 1.255e-05 [fold_const_symbol]: 1.854e-05 [renormalize]: 2.50002e-07 [detach_backward]: 2.19999e-06 [pipeline_parallel_scheduler]: 1.60999e-06 [auto_monad_reorder]: 4.439e-05 [get_jit_bprop_graph]: 2.05002e-06 [rewriter_after_jit_bprop_graph]: 7.48999e-06 [opt_after_jit_grad]: 0.00067003 [validate]: 6.698e-05 Sums bootstrap : 0.000717s : 5.15% type_inference : 0.005559s : 39.96% event_method : 0.000013s : 0.09% auto_monad : 0.000198s : 1.42% graph_reusing : 0.000006s : 0.04% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.15% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000004s : 0.03% pre_auto_parallel : 0.000046s : 0.33% insert-virtual-dataset : 0.000002s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.02% optimize.py_interpret_to_execute : 0.000049s : 0.36% optimize.rewriter_before_opt_a : 0.000088s : 0.64% optimize.opt_a.expand_dump_flag : 0.000005s : 0.04% optimize.opt_a.switch_simplify : 0.000051s : 0.37% optimize.opt_a.loop_unroll : 0.000035s : 0.25% optimize.opt_a.a_1 : 0.000976s : 7.02% optimize.opt_a.with_stream_mark : 0.000041s : 0.30% optimize.opt_a.recompute_prepare : 0.000030s : 0.22% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.10% optimize.opt_a.updatestate_assign_eliminate : 0.000015s : 0.10% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.07% optimize.opt_a.parameter_eliminate : 0.000003s : 0.02% optimize.opt_a.a_2 : 0.000304s : 2.19% optimize.opt_a.accelerated_algorithm : 0.000023s : 0.16% optimize.opt_a.shard : 0.000005s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.04% optimize.opt_a.shard_inline : 0.000021s : 0.15% optimize.opt_a.merge_send_recv : 0.000019s : 0.14% optimize.opt_a.auto_parallel : 0.000021s : 0.15% optimize.opt_a.parallel : 0.000043s : 0.31% optimize.opt_a.flash_sp : 0.000015s : 0.11% optimize.opt_a.merge_comm : 0.000011s : 0.08% optimize.opt_a.allreduce_fusion : 0.000011s : 0.08% optimize.opt_a.matmul_add_comm_reduction : 0.000026s : 0.19% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.21% optimize.opt_a.virtual_dataset : 0.000024s : 0.17% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.15% optimize.opt_a.virtual_output : 0.000023s : 0.16% optimize.opt_a.merge_forward : 0.000014s : 0.10% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.03% optimize.opt_a.offload_activation : 0.000070s : 0.51% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000053s : 0.38% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.02% optimize.opt_a.before_grad : 0.000043s : 0.31% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.11% optimize.opt_a.meta_fg_expand : 0.000009s : 0.06% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.03% optimize.opt_a.receive_attached : 0.000004s : 0.03% optimize.opt_a.after_resolve : 0.000040s : 0.29% optimize.opt_a.a_after_grad : 0.000044s : 0.32% optimize.opt_a.renormalize : 0.001081s : 7.77% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.07% optimize.opt_a.auto_monad_grad : 0.000005s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.30% optimize.opt_a.cse : 0.000126s : 0.91% optimize.opt_a.a_3 : 0.000146s : 1.05% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.16% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.02% optimize.rewriter_after_opt_a : 0.000169s : 1.21% optimize.convert_after_rewriter : 0.000012s : 0.09% optimize.order_py_execute_after_rewriter : 0.000010s : 0.07% optimize.mutable_eliminate : 0.000846s : 6.08% optimize.opt_b.b_1 : 0.000405s : 2.91% optimize.opt_b.b_2 : 0.000016s : 0.11% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.04% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.06% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000076s : 0.55% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.18% optimize.overlap_param_gather : 0.000005s : 0.03% optimize.cconv : 0.000038s : 0.27% optimize.loop_unroll : 0.000616s : 4.43% optimize.opt_after_cconv.c_1 : 0.000081s : 0.58% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.06% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.03% optimize.opt_after_cconv.cse : 0.000053s : 0.38% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.12% optimize.tuple_transform.d_1 : 0.000104s : 0.75% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.11% optimize.partial_unused_args_eliminate : 0.000002s : 0.02% optimize.add_recomputation : 0.000088s : 0.63% optimize.cse_after_recomputation.cse : 0.000032s : 0.23% optimize.environ_conv : 0.000012s : 0.09% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.06% optimize.bias_add_comm_swap : 0.000004s : 0.03% optimize.label_micro_interleaved_index : 0.000006s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000002s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000002s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000019s : 0.14% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.04% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.05% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000006s : 0.04% optimize.overlap_grad_flash_sp : 0.000028s : 0.20% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.14% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.16% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.09% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.13% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000044s : 0.32% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000007s : 0.05% opt_after_jit_grad : 0.000670s : 4.82% validate : 0.000067s : 0.48% Time group info: ------[substitution.] 0.000251 54 3.54% : 0.000009s : 2: substitution.depend_value_elim 1.15% : 0.000003s : 4: substitution.elim_not_effective 0.70% : 0.000002s : 4: substitution.fold_const_symbol 3.30% : 0.000008s : 7: substitution.graph_param_transform 69.95% : 0.000175s : 1: substitution.inline 2.26% : 0.000006s : 8: substitution.j_node_and_user_rematch 3.08% : 0.000008s : 8: substitution.remove_not_recompute_node 2.83% : 0.000007s : 6: substitution.replace_old_param 7.19% : 0.000018s : 6: substitution.updatestate_pure_node_eliminater 6.01% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.005463 2 87.55% : 0.004783s : 1: type_inference.infer 12.45% : 0.000680s : 1: type_inference.specialize ------[replace.] 0.000035 1 100.00% : 0.000035s : 1: replace.inline ------[match.] 0.000174 1 100.00% : 0.000174s : 1: match.inline ------[predicate.] 0.000259 1649 0.75% : 0.000002s : 15: predicate.accumulaten_eliminater 0.96% : 0.000002s : 7: predicate.ad_related_special_op_eliminate 0.73% : 0.000002s : 14: predicate.addn_check_dump 1.02% : 0.000003s : 15: predicate.addn_zero_filter 0.73% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.10% : 0.000005s : 29: predicate.arithmetic_simplify 1.01% : 0.000003s : 15: predicate.cast_eliminate 0.89% : 0.000002s : 14: predicate.check_bprop_eliminate 0.75% : 0.000002s : 14: predicate.compare_switch_simplify 0.25% : 0.000001s : 7: predicate.const_output_eliminate 0.87% : 0.000002s : 14: predicate.depend_value_elim 0.87% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.87% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.76% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.09% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 7: predicate.elim_not_effective 0.55% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.16% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.27% : 0.000003s : 22: predicate.environ_get_depend_swap 1.88% : 0.000005s : 36: predicate.environ_get_eliminate 1.10% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.87% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.36% : 0.000004s : 16: predicate.float_depend_g_call 0.71% : 0.000002s : 14: predicate.float_environ_get_switch 1.13% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 7: predicate.fold_const_symbol 0.91% : 0.000002s : 14: predicate.get_grad_eliminate 0.35% : 0.000001s : 7: predicate.graph_param_transform 0.73% : 0.000002s : 14: predicate.incorporate_call 0.67% : 0.000002s : 14: predicate.incorporate_call_switch 5.58% : 0.000014s : 73: predicate.inline 1.15% : 0.000003s : 14: predicate.inline_without_move 0.41% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.01% : 0.000003s : 14: predicate.less_batch_normalization 1.60% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.22% : 0.000006s : 44: predicate.load_eliminater 1.09% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.33% : 0.000003s : 21: predicate.loop_unroll_before_grad 1.93% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.85% : 0.000002s : 14: predicate.merge_addn 0.77% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.80% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.67% : 0.000002s : 15: predicate.minmaximum_grad 1.47% : 0.000004s : 7: predicate.mutable_eliminate 0.46% : 0.000001s : 7: predicate.opt_reshape 0.48% : 0.000001s : 7: predicate.parallel_virtual_node 1.00% : 0.000003s : 16: predicate.partial_defer_inline 1.14% : 0.000003s : 22: predicate.partial_eliminate 0.82% : 0.000002s : 15: predicate.print_const_string_wrapper 0.67% : 0.000002s : 14: predicate.reduce_all_const_elim 1.08% : 0.000003s : 15: predicate.reduce_eliminate 2.16% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.65% : 0.000002s : 14: predicate.remove_not_recompute_node 1.19% : 0.000003s : 29: predicate.replace_applicator 0.72% : 0.000002s : 14: predicate.replace_old_param 0.36% : 0.000001s : 7: predicate.reset_defer_inline 0.96% : 0.000002s : 15: predicate.reshape_eliminate 0.97% : 0.000003s : 14: predicate.row_tensor_add_zeros_like 0.48% : 0.000001s : 7: predicate.row_tensor_eliminate 0.96% : 0.000002s : 14: predicate.same_eliminate 0.52% : 0.000001s : 14: predicate.set_cell_output_no_recompute 0.93% : 0.000002s : 14: predicate.shard_identity_eliminate 0.93% : 0.000002s : 14: predicate.special_op_eliminate 0.90% : 0.000002s : 14: predicate.specialize_transform 1.31% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 1.02% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.46% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.85% : 0.000002s : 16: predicate.switch_defer_inline 1.56% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.48% : 0.000009s : 58: predicate.switch_simplify 0.80% : 0.000002s : 15: predicate.tile_eliminate 0.86% : 0.000002s : 15: predicate.transpose_eliminate 1.67% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.34% : 0.000009s : 43: predicate.tuple_list_get_item_eliminator 1.63% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.58% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.65% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.51% : 0.000007s : 44: predicate.updatestate_pure_node_eliminater 3.47% : 0.000009s : 58: predicate.updatestate_useless_node_eliminater 0.60% : 0.000002s : 7: predicate.value_based_eliminate 0.87% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.77% : 0.000002s : 14: predicate.virtual_output_eliminate 0.39% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000872 6 44.30% : 0.000386s : 3: func_graph_cloner_run.FuncGraphClonerGraph 55.70% : 0.000486s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.247106 192 0.00% : 0.000004s : 1: ForceFp32Comm 44.57% : 0.110142s : 1: add_attr 44.56% : 0.110121s : 1: add_attr_with_inline 0.00% : 0.000007s : 1: add_comm_op_reuse_tag 0.04% : 0.000093s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.09% : 0.000210s : 1: auto_monad 0.02% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.31% : 0.000755s : 1: bootstrap 0.02% : 0.000043s : 1: cconv 0.00% : 0.000007s : 1: comm_op_add_attrs 0.01% : 0.000023s : 1: control_data_broadcast_order 0.01% : 0.000023s : 1: convert_after_rewriter 0.02% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000017s : 1: environ_conv 0.01% : 0.000019s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000007s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.25% : 0.000627s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.35% : 0.000875s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000035s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000025s : 1: opt.transform.mutable_eliminate 0.71% : 0.001754s : 78: opt.transform.opt_a 0.03% : 0.000080s : 1: opt.transform.opt_after_cconv 0.02% : 0.000041s : 1: opt.transform.opt_after_jit_grad 0.14% : 0.000354s : 28: opt.transform.opt_b 0.05% : 0.000116s : 2: opt.transform.opt_trans_graph 0.03% : 0.000069s : 4: opt.transform.symbol_engine_opt 1.77% : 0.004362s : 1: opt_a 0.09% : 0.000218s : 1: opt_after_cconv 0.28% : 0.000685s : 1: opt_after_jit_grad 0.25% : 0.000608s : 1: opt_b 3.23% : 0.007980s : 1: optimize 0.01% : 0.000029s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000032s : 1: overlap_grad_flash_sp 0.00% : 0.000007s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000008s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000011s : 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% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000051s : 1: pre_auto_parallel 0.02% : 0.000054s : 1: py_interpret_to_execute 0.01% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000008s : 1: remove_cast_before_assign_add 0.01% : 0.000021s : 1: remove_dup_value 0.21% : 0.000513s : 1: renormalize.infer 0.22% : 0.000554s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000179s : 1: rewriter_after_opt_a 0.04% : 0.000094s : 1: rewriter_before_opt_a 0.00% : 0.000009s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000134s : 1: symbol_engine_optimizer 0.06% : 0.000155s : 1: tuple_transform 2.26% : 0.005580s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_key[3-bfloat16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_key[3-bfloat16],max_mem:490.0M =============================== 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 ================== 6 passed, 25 warnings in 364.94s (0:06:04) ==================