==================================================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_002/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 1 item test_quant_bmm.py [WARNING] ME(168598:281473140318000,MainProcess):2026-01-29-17:37:31.322.917 [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 = 0.311264, [21] [bootstrap]: 0.00065541 [type_inference]: 0.293198 [event_method]: 1.746e-05 [auto_monad]: 0.00024637 [graph_reusing]: 6.41e-06 [inline]: 3.11999e-06 [add_attr]: 0.00834044, [1] [add_attr_with_inline]: 0.00832456, [1] [Cycle 1]: 0.00010431, [2] [tag_attr]: 2.287e-05 [meta_addattr_fg_expand]: 4.61002e-06 [parallel-infer-symbol]: 4.02e-06 [pre_auto_parallel]: 4.965e-05 [insert-virtual-dataset]: 2.51e-06 [parallel-infer-symbol-second]: 7.29982e-07 [dataset_repeat_opt]: 1.97001e-06 [pipeline_split]: 1.72001e-06 [optimize]: 0.00786368, [53] [py_interpret_to_execute]: 2.873e-05 [rewriter_before_opt_a]: 8.932e-05 [opt_a]: 0.00459181, [2] [Cycle 1]: 0.00315096, [45] [expand_dump_flag]: 2.73998e-06 [switch_simplify]: 3.392e-05 [loop_unroll]: 1.882e-05 [a_1]: 0.00061461 [with_stream_mark]: 2.822e-05 [recompute_prepare]: 1.922e-05 [updatestate_depend_eliminate]: 1.094e-05 [updatestate_assign_eliminate]: 1.133e-05 [updatestate_loads_eliminate]: 1.612e-05 [parameter_eliminate]: 2.34001e-06 [a_2]: 0.00023573 [accelerated_algorithm]: 4.547e-05 [shard]: 2.23002e-06 [meta_shard_fg_expand]: 3.50998e-06 [shard_inline]: 1.639e-05 [merge_send_recv]: 1.517e-05 [auto_parallel]: 1.225e-05 [parallel]: 4.163e-05 [flash_sp]: 1.29e-05 [merge_comm]: 9.35001e-06 [allreduce_fusion]: 8.50001e-06 [matmul_add_comm_reduction]: 1.81e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.842e-05 [virtual_dataset]: 1.427e-05 [get_grad_eliminate_]: 1.411e-05 [virtual_output]: 1.332e-05 [merge_forward]: 9.19e-06 [cell_reuse_recompute_pass]: 2.34001e-06 [offload_activation]: 1.735e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.77e-05 [merge_recompute_call_nodes]: 1.56002e-06 [before_grad]: 3.006e-05 [set_forward_comm_id_for_comm_node_pass]: 1.016e-05 [meta_fg_expand]: 5.56e-06 [flash_sp_send_recv_attached]: 5.74999e-06 [receive_attached]: 1.385e-05 [after_resolve]: 2.235e-05 [a_after_grad]: 2.357e-05 [renormalize]: 0.00116856 [add_forward_monad_depend]: 1.387e-05 [auto_monad_grad]: 2.91e-06 [auto_monad_eliminator]: 5.179e-05 [cse]: 0.00010402 [a_3]: 0.0001121 [Cycle 2]: 0.00142632, [45] [expand_dump_flag]: 2.67001e-06 [switch_simplify]: 1.627e-05 [loop_unroll]: 1.392e-05 [a_1]: 0.00039063 [with_stream_mark]: 2.134e-05 [recompute_prepare]: 1.448e-05 [updatestate_depend_eliminate]: 9.78002e-06 [updatestate_assign_eliminate]: 1.07e-05 [updatestate_loads_eliminate]: 1.384e-05 [parameter_eliminate]: 2.00002e-06 [a_2]: 0.0002152 [accelerated_algorithm]: 2.012e-05 [shard]: 2.32001e-06 [meta_shard_fg_expand]: 3.79002e-06 [shard_inline]: 1.501e-05 [merge_send_recv]: 1.451e-05 [auto_parallel]: 1.348e-05 [parallel]: 9.29e-06 [flash_sp]: 4.22e-06 [merge_comm]: 8.59e-06 [allreduce_fusion]: 8.52e-06 [matmul_add_comm_reduction]: 1.704e-05 [allreduce_slice_to_reducescatter]: 7.00005e-07 [virtual_shard_identity]: 1.667e-05 [virtual_dataset]: 1.326e-05 [get_grad_eliminate_]: 1.348e-05 [virtual_output]: 1.285e-05 [merge_forward]: 9.69999e-06 [cell_reuse_recompute_pass]: 2.21e-06 [offload_activation]: 1.621e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.627e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 2.293e-05 [set_forward_comm_id_for_comm_node_pass]: 9.27001e-06 [meta_fg_expand]: 5.76998e-06 [flash_sp_send_recv_attached]: 1.66998e-06 [receive_attached]: 2.41e-06 [after_resolve]: 1.99e-05 [a_after_grad]: 2.08e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.40002e-06 [auto_monad_grad]: 2.02999e-06 [auto_monad_eliminator]: 3.62e-05 [cse]: 5.233e-05 [a_3]: 9.084e-05 [py_interpret_to_execute_after_opt_a]: 2.198e-05 [slice_cell_reuse_recomputed_activation]: 2.01e-06 [rewriter_after_opt_a]: 0.000221 [convert_after_rewriter]: 1.593e-05 [order_py_execute_after_rewriter]: 9.75002e-06 [mutable_eliminate]: 0.0006455 [opt_b]: 0.00047387, [1] [Cycle 1]: 0.00046638, [7] [b_1]: 0.00032222 [b_2]: 1.711e-05 [updatestate_depend_eliminate]: 1.342e-05 [updatestate_assign_eliminate]: 8.40001e-06 [updatestate_loads_eliminate]: 1.242e-05 [renormalize]: 1.02998e-06 [cse]: 5.421e-05 [optimize_parallel_all_gather_comm]: 2.921e-05 [overlap_param_gather]: 2.11e-06 [cconv]: 3.488e-05 [loop_unroll]: 0.00051593 [opt_after_cconv]: 0.00022979, [1] [Cycle 1]: 0.00022213, [7] [c_1]: 9.754e-05 [parameter_eliminate]: 4.37e-06 [updatestate_depend_eliminate]: 1.294e-05 [updatestate_assign_eliminate]: 8.13999e-06 [updatestate_loads_eliminate]: 1.104e-05 [cse]: 5.103e-05 [renormalize]: 3.89991e-07 [remove_dup_value]: 6.932e-05 [tuple_transform]: 0.00013383, [1] [Cycle 1]: 0.00012852, [4] [d_1]: 9.353e-05 [none_parameter_eliminate]: 1.85001e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.468e-05 [partial_unused_args_eliminate]: 1.81e-06 [add_recomputation]: 0.00010159 [cse_after_recomputation]: 4.611e-05, [1] [Cycle 1]: 4.115e-05, [1] [cse]: 3.46e-05 [environ_conv]: 2.733e-05 [swap_dp_allreduce_reducescatter]: 1.099e-05 [bias_add_comm_swap]: 2.76e-06 [label_micro_interleaved_index]: 5.37999e-06 [label_fine_grained_interleaved_index]: 3.31001e-06 [merge_cast_opt]: 1.45999e-06 [slice_recompute_activation]: 2.34001e-06 [micro_interleaved_order_control]: 2.54001e-06 [assign_add_opt]: 1.37e-06 [ForceFp32Comm]: 1.18001e-06 [remove_cast_before_assign_add]: 1.24e-06 [full_micro_interleaved_order_control]: 2.53e-06 [reorder_send_recv_between_fp_bp]: 3.00002e-06 [comm_op_add_attrs]: 1.20999e-06 [add_comm_op_reuse_tag]: 1.08001e-06 [interleave_split_concat_branches]: 1.32999e-06 [interleave_parallel_branches]: 1.35001e-06 [overlap_opt_shard_in_pipeline]: 2.302e-05 [overlap_opt_shard_grad_in_pipeline]: 1.79e-06 [control_data_broadcast_order]: 2.823e-05 [grouped_pairwise_exchange_alltoall]: 2.09999e-06 [offloading_packed_experts]: 7.31001e-06 [overlap_recompute_and_grad_model_parallel]: 8.13001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.29999e-06 [overlap_grad_ring_attention]: 6.86001e-06 [overlap_grad_flash_sp]: 6.289e-05 [begin_end_overlap_inline]: 5.89993e-07 [split_matmul_comm_elemetwise]: 2.69001e-06 [split_layernorm_comm]: 2.33998e-06 [handle_group_info]: 1.00001e-06 [symbol_engine_optimizer]: 0.00012873, [1] [Cycle 1]: 0.00012367, [6] [build]: 1.24e-05 [elim_shapecalc]: 1.986e-05 [elim_not_effective]: 2.606e-05 [opt_reshape]: 1.435e-05 [fold_const_symbol]: 2.21e-05 [renormalize]: 2.20025e-07 [detach_backward]: 2.77002e-06 [pipeline_parallel_scheduler]: 1.67999e-06 [auto_monad_reorder]: 5.898e-05 [get_jit_bprop_graph]: 2.25002e-06 [rewriter_after_jit_bprop_graph]: 5.14998e-06 [opt_after_jit_grad]: 0.00052535 [validate]: 7.858e-05 Sums bootstrap : 0.000655s : 0.22% type_inference : 0.293198s : 97.14% event_method : 0.000017s : 0.01% auto_monad : 0.000246s : 0.08% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000029s : 0.01% optimize.rewriter_before_opt_a : 0.000089s : 0.03% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000050s : 0.02% optimize.opt_a.loop_unroll : 0.000033s : 0.01% optimize.opt_a.a_1 : 0.001005s : 0.33% optimize.opt_a.with_stream_mark : 0.000050s : 0.02% optimize.opt_a.recompute_prepare : 0.000034s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000022s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000451s : 0.15% optimize.opt_a.accelerated_algorithm : 0.000066s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.01% optimize.opt_a.merge_send_recv : 0.000030s : 0.01% optimize.opt_a.auto_parallel : 0.000026s : 0.01% optimize.opt_a.parallel : 0.000051s : 0.02% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000018s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000035s : 0.01% optimize.opt_a.virtual_dataset : 0.000028s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.01% optimize.opt_a.virtual_output : 0.000026s : 0.01% optimize.opt_a.merge_forward : 0.000019s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000054s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000053s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.01% optimize.opt_a.meta_fg_expand : 0.000011s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000016s : 0.01% optimize.opt_a.after_resolve : 0.000042s : 0.01% optimize.opt_a.a_after_grad : 0.000044s : 0.01% optimize.opt_a.renormalize : 0.001169s : 0.39% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000088s : 0.03% optimize.opt_a.cse : 0.000156s : 0.05% optimize.opt_a.a_3 : 0.000203s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000221s : 0.07% optimize.convert_after_rewriter : 0.000016s : 0.01% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000645s : 0.21% optimize.opt_b.b_1 : 0.000322s : 0.11% optimize.opt_b.b_2 : 0.000017s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000054s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.01% optimize.loop_unroll : 0.000516s : 0.17% optimize.opt_after_cconv.c_1 : 0.000098s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000051s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000069s : 0.02% optimize.tuple_transform.d_1 : 0.000094s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000102s : 0.03% optimize.cse_after_recomputation.cse : 0.000035s : 0.01% optimize.environ_conv : 0.000027s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 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 : 0.000023s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000063s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000012s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000059s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000525s : 0.17% validate : 0.000079s : 0.03% Time group info: ------[substitution.] 0.000404 102 26.31% : 0.000106s : 4: substitution.arithmetic_simplify 2.69% : 0.000011s : 2: substitution.depend_value_elim 0.89% : 0.000004s : 8: substitution.elim_not_effective 0.77% : 0.000003s : 8: substitution.fold_const_symbol 2.50% : 0.000010s : 11: substitution.graph_param_transform 29.07% : 0.000117s : 1: substitution.inline 2.19% : 0.000009s : 16: substitution.j_node_and_user_rematch 6.57% : 0.000027s : 4: substitution.less_batch_normalization 1.96% : 0.000008s : 12: substitution.load_eliminater 2.91% : 0.000012s : 16: substitution.remove_not_recompute_node 1.83% : 0.000007s : 6: substitution.replace_old_param 2.11% : 0.000009s : 6: substitution.updatestate_pure_node_eliminater 20.19% : 0.000082s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.293114 2 99.77% : 0.292441s : 1: type_inference.infer 0.23% : 0.000673s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000116 1 100.00% : 0.000116s : 1: match.inline ------[predicate.] 0.000363 2549 0.79% : 0.000003s : 23: predicate.accumulaten_eliminater 0.83% : 0.000003s : 11: predicate.ad_related_special_op_eliminate 0.77% : 0.000003s : 22: predicate.addn_check_dump 0.79% : 0.000003s : 23: predicate.addn_zero_filter 0.74% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.29% : 0.000008s : 45: predicate.arithmetic_simplify 0.84% : 0.000003s : 23: predicate.cast_eliminate 0.84% : 0.000003s : 22: predicate.check_bprop_eliminate 0.78% : 0.000003s : 22: predicate.compare_switch_simplify 0.25% : 0.000001s : 11: predicate.const_output_eliminate 0.80% : 0.000003s : 22: predicate.depend_value_elim 0.97% : 0.000004s : 23: predicate.dict_get_item_const_eliminator 0.90% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.79% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.06% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 11: predicate.elim_not_effective 0.45% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.15% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.14% : 0.000004s : 34: predicate.environ_get_depend_swap 2.01% : 0.000007s : 56: predicate.environ_get_eliminate 1.13% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.82% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.40% : 0.000005s : 24: predicate.float_depend_g_call 0.76% : 0.000003s : 22: predicate.float_environ_get_switch 1.14% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 11: predicate.fold_const_symbol 0.84% : 0.000003s : 22: predicate.get_grad_eliminate 0.47% : 0.000002s : 11: predicate.graph_param_transform 0.84% : 0.000003s : 22: predicate.incorporate_call 0.75% : 0.000003s : 22: predicate.incorporate_call_switch 5.85% : 0.000021s : 113: predicate.inline 1.25% : 0.000005s : 22: predicate.inline_without_move 0.45% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.24% : 0.000005s : 22: predicate.less_batch_normalization 1.73% : 0.000006s : 45: predicate.list_to_tuple_eliminator_ 2.47% : 0.000009s : 68: predicate.load_eliminater 0.96% : 0.000003s : 11: predicate.loop_unroll_after_grad 1.08% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.80% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.80% : 0.000003s : 22: predicate.merge_addn 0.78% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.81% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.74% : 0.000003s : 23: predicate.minmaximum_grad 1.03% : 0.000004s : 11: predicate.mutable_eliminate 0.44% : 0.000002s : 11: predicate.opt_reshape 0.44% : 0.000002s : 11: predicate.parallel_virtual_node 0.96% : 0.000003s : 24: predicate.partial_defer_inline 1.36% : 0.000005s : 34: predicate.partial_eliminate 0.81% : 0.000003s : 23: predicate.print_const_string_wrapper 0.81% : 0.000003s : 22: predicate.reduce_all_const_elim 1.20% : 0.000004s : 23: predicate.reduce_eliminate 2.32% : 0.000008s : 68: predicate.redundant_stop_gradient_eliminater 0.67% : 0.000002s : 22: predicate.remove_not_recompute_node 1.30% : 0.000005s : 45: predicate.replace_applicator 0.70% : 0.000003s : 22: predicate.replace_old_param 0.30% : 0.000001s : 11: predicate.reset_defer_inline 0.80% : 0.000003s : 23: predicate.reshape_eliminate 0.83% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.50% : 0.000002s : 11: predicate.row_tensor_eliminate 0.95% : 0.000003s : 22: predicate.same_eliminate 0.59% : 0.000002s : 22: predicate.set_cell_output_no_recompute 1.01% : 0.000004s : 22: predicate.shard_identity_eliminate 0.95% : 0.000003s : 22: predicate.special_op_eliminate 1.00% : 0.000004s : 22: predicate.specialize_transform 1.11% : 0.000004s : 22: predicate.split_environ_get_set_with_tuple_value 1.02% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.55% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.86% : 0.000003s : 24: predicate.switch_defer_inline 1.71% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.53% : 0.000013s : 84: predicate.switch_simplify 0.80% : 0.000003s : 23: predicate.tile_eliminate 0.79% : 0.000003s : 23: predicate.transpose_eliminate 1.69% : 0.000006s : 45: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000006s : 45: predicate.tuple_list_get_item_const_eliminator 1.58% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 3.07% : 0.000011s : 67: predicate.tuple_list_get_item_eliminator 1.60% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.59% : 0.000009s : 67: predicate.tuple_list_set_item_eliminator 1.62% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.40% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.35% : 0.000012s : 90: predicate.updatestate_useless_node_eliminater 0.43% : 0.000002s : 11: predicate.value_based_eliminate 0.89% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.84% : 0.000003s : 22: predicate.virtual_output_eliminate 0.41% : 0.000001s : 11: predicate.virtual_view_grad_eliminate 0.53% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000347 4 6.83% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 93.17% : 0.000323s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.331206 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.52% : 0.008346s : 1: add_attr 2.51% : 0.008329s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000106s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.000255s : 1: auto_monad 0.02% : 0.000064s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000693s : 1: bootstrap 0.01% : 0.000038s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000032s : 1: control_data_broadcast_order 0.01% : 0.000020s : 1: convert_after_rewriter 0.01% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000031s : 1: environ_conv 0.01% : 0.000026s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 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 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.16% : 0.000527s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.20% : 0.000656s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000027s : 1: opt.transform.mutable_eliminate 0.63% : 0.002081s : 78: opt.transform.opt_a 0.03% : 0.000096s : 1: opt.transform.opt_after_cconv 0.01% : 0.000048s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000312s : 28: opt.transform.opt_b 0.03% : 0.000106s : 2: opt.transform.opt_trans_graph 0.02% : 0.000079s : 4: opt.transform.symbol_engine_opt 1.39% : 0.004595s : 1: opt_a 0.07% : 0.000234s : 1: opt_after_cconv 0.16% : 0.000536s : 1: opt_after_jit_grad 0.14% : 0.000477s : 1: opt_b 2.38% : 0.007869s : 1: optimize 0.01% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.02% : 0.000067s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000026s : 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% : 0.000011s : 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% : 0.000005s : 1: pipeline_split 0.02% : 0.000055s : 1: pre_auto_parallel 0.01% : 0.000033s : 1: py_interpret_to_execute 0.01% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000074s : 1: remove_dup_value 0.21% : 0.000692s : 1: renormalize.infer 0.14% : 0.000465s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000227s : 1: rewriter_after_opt_a 0.03% : 0.000094s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000131s : 1: symbol_engine_optimizer 0.04% : 0.000137s : 1: tuple_transform 88.53% : 0.293224s : 1: type_inference [WARNING] ME(168598:281473140318000,MainProcess):2026-01-29-17:38:14.567.899 [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 = 0.1967, [21] [bootstrap]: 0.00055514 [type_inference]: 0.160087 [event_method]: 2.356e-05 [auto_monad]: 0.00031076 [graph_reusing]: 6.59999e-06 [inline]: 2.40002e-06 [add_attr]: 0.00539617, [1] [add_attr_with_inline]: 0.0053714, [1] [Cycle 1]: 8.158e-05, [2] [tag_attr]: 2.528e-05 [meta_addattr_fg_expand]: 4.81002e-06 [parallel-infer-symbol]: 4.2e-06 [pre_auto_parallel]: 4.979e-05 [insert-virtual-dataset]: 3.58e-06 [parallel-infer-symbol-second]: 8.29983e-07 [dataset_repeat_opt]: 2.24001e-06 [pipeline_split]: 2.60002e-06 [optimize]: 0.0292, [53] [py_interpret_to_execute]: 4.77e-05 [rewriter_before_opt_a]: 8.288e-05 [opt_a]: 0.0252936, [2] [Cycle 1]: 0.0235514, [45] [expand_dump_flag]: 2.93e-06 [switch_simplify]: 3.395e-05 [loop_unroll]: 2.273e-05 [a_1]: 0.00081329 [with_stream_mark]: 3.264e-05 [recompute_prepare]: 1.962e-05 [updatestate_depend_eliminate]: 1.114e-05 [updatestate_assign_eliminate]: 1.381e-05 [updatestate_loads_eliminate]: 2.44e-05 [parameter_eliminate]: 2.46998e-06 [a_2]: 0.00027251 [accelerated_algorithm]: 4.493e-05 [shard]: 3.16001e-06 [meta_shard_fg_expand]: 5.19e-06 [shard_inline]: 1.854e-05 [merge_send_recv]: 2.013e-05 [auto_parallel]: 1.792e-05 [parallel]: 4.62e-05 [flash_sp]: 1.308e-05 [merge_comm]: 9.64e-06 [allreduce_fusion]: 9.31e-06 [matmul_add_comm_reduction]: 2.079e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 2.304e-05 [virtual_dataset]: 1.491e-05 [get_grad_eliminate_]: 1.422e-05 [virtual_output]: 2.19e-05 [merge_forward]: 1.064e-05 [cell_reuse_recompute_pass]: 2.34001e-06 [offload_activation]: 2.325e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.035e-05 [merge_recompute_call_nodes]: 1.98997e-06 [before_grad]: 2.637e-05 [set_forward_comm_id_for_comm_node_pass]: 1.007e-05 [meta_fg_expand]: 7.15998e-06 [flash_sp_send_recv_attached]: 5.87001e-06 [receive_attached]: 2.89001e-06 [after_resolve]: 2.487e-05 [a_after_grad]: 2.586e-05 [renormalize]: 0.0211552 [add_forward_monad_depend]: 1.669e-05 [auto_monad_grad]: 3.76999e-06 [auto_monad_eliminator]: 7.517e-05 [cse]: 0.00011193 [a_3]: 0.00013341 [Cycle 2]: 0.00172427, [45] [expand_dump_flag]: 2.79001e-06 [switch_simplify]: 1.93e-05 [loop_unroll]: 1.578e-05 [a_1]: 0.00045725 [with_stream_mark]: 2.995e-05 [recompute_prepare]: 1.784e-05 [updatestate_depend_eliminate]: 1.156e-05 [updatestate_assign_eliminate]: 1.15e-05 [updatestate_loads_eliminate]: 1.563e-05 [parameter_eliminate]: 2.12001e-06 [a_2]: 0.00026882 [accelerated_algorithm]: 2.599e-05 [shard]: 2.79999e-06 [meta_shard_fg_expand]: 6.89999e-06 [shard_inline]: 1.5e-05 [merge_send_recv]: 1.798e-05 [auto_parallel]: 1.709e-05 [parallel]: 1.123e-05 [flash_sp]: 5.25001e-06 [merge_comm]: 9.97999e-06 [allreduce_fusion]: 8.52998e-06 [matmul_add_comm_reduction]: 2.252e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.98e-05 [virtual_dataset]: 1.475e-05 [get_grad_eliminate_]: 1.426e-05 [virtual_output]: 1.438e-05 [merge_forward]: 9.29e-06 [cell_reuse_recompute_pass]: 3.39001e-06 [offload_activation]: 1.875e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.185e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 3.006e-05 [set_forward_comm_id_for_comm_node_pass]: 9.97001e-06 [meta_fg_expand]: 7.92e-06 [flash_sp_send_recv_attached]: 2.31e-06 [receive_attached]: 3.2e-06 [after_resolve]: 2.252e-05 [a_after_grad]: 2.248e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 4e-06 [auto_monad_grad]: 2.52001e-06 [auto_monad_eliminator]: 4.844e-05 [cse]: 6.662e-05 [a_3]: 9.571e-05 [py_interpret_to_execute_after_opt_a]: 3.136e-05 [slice_cell_reuse_recomputed_activation]: 2.67001e-06 [rewriter_after_opt_a]: 0.00022011 [convert_after_rewriter]: 1.629e-05 [order_py_execute_after_rewriter]: 1.528e-05 [mutable_eliminate]: 0.00085718 [opt_b]: 0.00055551, [1] [Cycle 1]: 0.00054596, [7] [b_1]: 0.00037134 [b_2]: 1.908e-05 [updatestate_depend_eliminate]: 1.821e-05 [updatestate_assign_eliminate]: 9.58002e-06 [updatestate_loads_eliminate]: 1.448e-05 [renormalize]: 9.00007e-07 [cse]: 6.581e-05 [optimize_parallel_all_gather_comm]: 3.634e-05 [overlap_param_gather]: 2.24999e-06 [cconv]: 4.316e-05 [loop_unroll]: 0.00054326 [opt_after_cconv]: 0.00024853, [1] [Cycle 1]: 0.00024106, [7] [c_1]: 0.00010077 [parameter_eliminate]: 6.19999e-06 [updatestate_depend_eliminate]: 1.314e-05 [updatestate_assign_eliminate]: 8.52e-06 [updatestate_loads_eliminate]: 1.522e-05 [cse]: 5.642e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 7.719e-05 [tuple_transform]: 0.00017031, [1] [Cycle 1]: 0.00016429, [4] [d_1]: 0.00011698 [none_parameter_eliminate]: 2.57001e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.629e-05 [partial_unused_args_eliminate]: 2.99999e-06 [add_recomputation]: 0.00012178 [cse_after_recomputation]: 5.056e-05, [1] [Cycle 1]: 4.424e-05, [1] [cse]: 3.797e-05 [environ_conv]: 9.53e-05 [swap_dp_allreduce_reducescatter]: 1.575e-05 [bias_add_comm_swap]: 3.55e-06 [label_micro_interleaved_index]: 5.06002e-06 [label_fine_grained_interleaved_index]: 3.31001e-06 [merge_cast_opt]: 1.35001e-06 [slice_recompute_activation]: 2.81e-06 [micro_interleaved_order_control]: 2.71e-06 [assign_add_opt]: 1.35001e-06 [ForceFp32Comm]: 9.10019e-07 [remove_cast_before_assign_add]: 1.17999e-06 [full_micro_interleaved_order_control]: 2.74001e-06 [reorder_send_recv_between_fp_bp]: 3.43e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 1.24e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 3.48999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.26998e-06 [control_data_broadcast_order]: 3.448e-05 [grouped_pairwise_exchange_alltoall]: 1.72001e-06 [offloading_packed_experts]: 1.207e-05 [overlap_recompute_and_grad_model_parallel]: 8.60001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.75001e-06 [overlap_recompute_comm]: 2.46998e-06 [overlap_grad_ring_attention]: 1.142e-05 [overlap_grad_flash_sp]: 4.356e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.34001e-06 [split_layernorm_comm]: 2.31e-06 [handle_group_info]: 1.30001e-06 [symbol_engine_optimizer]: 0.00020006, [1] [Cycle 1]: 0.00019406, [6] [build]: 1.819e-05 [elim_shapecalc]: 3.643e-05 [elim_not_effective]: 3.701e-05 [opt_reshape]: 3.155e-05 [fold_const_symbol]: 2.911e-05 [renormalize]: 2.19996e-07 [detach_backward]: 2.64999e-06 [pipeline_parallel_scheduler]: 1.85001e-06 [auto_monad_reorder]: 6.338e-05 [get_jit_bprop_graph]: 2.88998e-06 [rewriter_after_jit_bprop_graph]: 6.75002e-06 [opt_after_jit_grad]: 0.00066248 [validate]: 8.606e-05 Sums bootstrap : 0.000555s : 0.29% type_inference : 0.160087s : 84.28% event_method : 0.000024s : 0.01% auto_monad : 0.000311s : 0.16% graph_reusing : 0.000007s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.03% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000048s : 0.03% optimize.rewriter_before_opt_a : 0.000083s : 0.04% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.03% optimize.opt_a.loop_unroll : 0.000039s : 0.02% optimize.opt_a.a_1 : 0.001271s : 0.67% optimize.opt_a.with_stream_mark : 0.000063s : 0.03% optimize.opt_a.recompute_prepare : 0.000037s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000023s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000025s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000040s : 0.02% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000541s : 0.28% optimize.opt_a.accelerated_algorithm : 0.000071s : 0.04% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.01% optimize.opt_a.shard_inline : 0.000034s : 0.02% optimize.opt_a.merge_send_recv : 0.000038s : 0.02% optimize.opt_a.auto_parallel : 0.000035s : 0.02% optimize.opt_a.parallel : 0.000057s : 0.03% optimize.opt_a.flash_sp : 0.000018s : 0.01% optimize.opt_a.merge_comm : 0.000020s : 0.01% optimize.opt_a.allreduce_fusion : 0.000018s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000043s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000043s : 0.02% optimize.opt_a.virtual_dataset : 0.000030s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.01% optimize.opt_a.virtual_output : 0.000036s : 0.02% optimize.opt_a.merge_forward : 0.000020s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000042s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000062s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000056s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.01% optimize.opt_a.meta_fg_expand : 0.000015s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000047s : 0.02% optimize.opt_a.a_after_grad : 0.000048s : 0.03% optimize.opt_a.renormalize : 0.021155s : 11.14% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000124s : 0.07% optimize.opt_a.cse : 0.000179s : 0.09% optimize.opt_a.a_3 : 0.000229s : 0.12% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000220s : 0.12% optimize.convert_after_rewriter : 0.000016s : 0.01% optimize.order_py_execute_after_rewriter : 0.000015s : 0.01% optimize.mutable_eliminate : 0.000857s : 0.45% optimize.opt_b.b_1 : 0.000371s : 0.20% optimize.opt_b.b_2 : 0.000019s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000018s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000066s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.02% optimize.loop_unroll : 0.000543s : 0.29% optimize.opt_after_cconv.c_1 : 0.000101s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.01% optimize.opt_after_cconv.cse : 0.000056s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000077s : 0.04% optimize.tuple_transform.d_1 : 0.000117s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000122s : 0.06% optimize.cse_after_recomputation.cse : 0.000038s : 0.02% optimize.environ_conv : 0.000095s : 0.05% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000034s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.01% optimize.overlap_grad_flash_sp : 0.000044s : 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 : 0.000018s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000036s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000032s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000029s : 0.02% 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 : 0.000063s : 0.03% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000662s : 0.35% validate : 0.000086s : 0.05% Time group info: ------[substitution.] 0.000539 102 21.67% : 0.000117s : 4: substitution.arithmetic_simplify 9.90% : 0.000053s : 2: substitution.depend_value_elim 0.71% : 0.000004s : 8: substitution.elim_not_effective 1.13% : 0.000006s : 8: substitution.fold_const_symbol 2.02% : 0.000011s : 11: substitution.graph_param_transform 23.89% : 0.000129s : 1: substitution.inline 1.70% : 0.000009s : 16: substitution.j_node_and_user_rematch 4.89% : 0.000026s : 4: substitution.less_batch_normalization 1.53% : 0.000008s : 12: substitution.load_eliminater 2.41% : 0.000013s : 16: substitution.remove_not_recompute_node 1.77% : 0.000010s : 6: substitution.replace_old_param 1.85% : 0.000010s : 6: substitution.updatestate_pure_node_eliminater 26.52% : 0.000143s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.160012 2 99.55% : 0.159299s : 1: type_inference.infer 0.45% : 0.000714s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000128 1 100.00% : 0.000128s : 1: match.inline ------[predicate.] 0.000400 2549 0.82% : 0.000003s : 23: predicate.accumulaten_eliminater 1.17% : 0.000005s : 11: predicate.ad_related_special_op_eliminate 0.80% : 0.000003s : 22: predicate.addn_check_dump 0.83% : 0.000003s : 23: predicate.addn_zero_filter 0.71% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.52% : 0.000010s : 45: predicate.arithmetic_simplify 0.90% : 0.000004s : 23: predicate.cast_eliminate 0.75% : 0.000003s : 22: predicate.check_bprop_eliminate 0.73% : 0.000003s : 22: predicate.compare_switch_simplify 0.21% : 0.000001s : 11: predicate.const_output_eliminate 0.83% : 0.000003s : 22: predicate.depend_value_elim 0.82% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.83% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.77% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.01% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 11: predicate.elim_not_effective 0.53% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.08% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.13% : 0.000005s : 34: predicate.environ_get_depend_swap 1.88% : 0.000008s : 56: predicate.environ_get_eliminate 1.08% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.86% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.32% : 0.000005s : 24: predicate.float_depend_g_call 0.80% : 0.000003s : 22: predicate.float_environ_get_switch 1.08% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 11: predicate.fold_const_symbol 0.92% : 0.000004s : 22: predicate.get_grad_eliminate 0.31% : 0.000001s : 11: predicate.graph_param_transform 0.77% : 0.000003s : 22: predicate.incorporate_call 0.70% : 0.000003s : 22: predicate.incorporate_call_switch 5.79% : 0.000023s : 113: predicate.inline 1.11% : 0.000004s : 22: predicate.inline_without_move 0.45% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.29% : 0.000005s : 22: predicate.less_batch_normalization 1.71% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.32% : 0.000009s : 68: predicate.load_eliminater 1.16% : 0.000005s : 11: predicate.loop_unroll_after_grad 1.07% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.83% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.81% : 0.000003s : 22: predicate.merge_addn 0.76% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.82% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.76% : 0.000003s : 23: predicate.minmaximum_grad 1.50% : 0.000006s : 11: predicate.mutable_eliminate 0.46% : 0.000002s : 11: predicate.opt_reshape 0.58% : 0.000002s : 11: predicate.parallel_virtual_node 0.96% : 0.000004s : 24: predicate.partial_defer_inline 1.25% : 0.000005s : 34: predicate.partial_eliminate 0.76% : 0.000003s : 23: predicate.print_const_string_wrapper 0.76% : 0.000003s : 22: predicate.reduce_all_const_elim 1.20% : 0.000005s : 23: predicate.reduce_eliminate 2.26% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.57% : 0.000002s : 22: predicate.remove_not_recompute_node 1.16% : 0.000005s : 45: predicate.replace_applicator 0.60% : 0.000002s : 22: predicate.replace_old_param 0.36% : 0.000001s : 11: predicate.reset_defer_inline 0.87% : 0.000003s : 23: predicate.reshape_eliminate 0.86% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.52% : 0.000002s : 11: predicate.row_tensor_eliminate 1.07% : 0.000004s : 22: predicate.same_eliminate 0.51% : 0.000002s : 22: predicate.set_cell_output_no_recompute 0.89% : 0.000004s : 22: predicate.shard_identity_eliminate 1.00% : 0.000004s : 22: predicate.special_op_eliminate 0.87% : 0.000004s : 22: predicate.specialize_transform 1.26% : 0.000005s : 22: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.41% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.80% : 0.000003s : 24: predicate.switch_defer_inline 1.55% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.56% : 0.000014s : 84: predicate.switch_simplify 0.89% : 0.000004s : 23: predicate.tile_eliminate 0.77% : 0.000003s : 23: predicate.transpose_eliminate 1.69% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000007s : 45: predicate.tuple_list_get_item_depend_reorder 3.07% : 0.000012s : 67: predicate.tuple_list_get_item_eliminator 1.57% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.62% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.70% : 0.000007s : 45: predicate.tuple_to_list_eliminator_ 2.38% : 0.000010s : 68: predicate.updatestate_pure_node_eliminater 3.17% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.59% : 0.000002s : 11: predicate.value_based_eliminate 0.96% : 0.000004s : 22: predicate.virtual_dataset_eliminate 0.90% : 0.000004s : 22: predicate.virtual_output_eliminate 0.38% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.57% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000544 4 5.10% : 0.000028s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.90% : 0.000517s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.255540 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.11% : 0.005404s : 1: add_attr 2.10% : 0.005376s : 1: add_attr_with_inline 0.00% : 0.000008s : 1: add_comm_op_reuse_tag 0.05% : 0.000127s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.13% : 0.000321s : 1: auto_monad 0.03% : 0.000069s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.24% : 0.000601s : 1: bootstrap 0.02% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000038s : 1: control_data_broadcast_order 0.01% : 0.000021s : 1: convert_after_rewriter 0.02% : 0.000054s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.04% : 0.000100s : 1: environ_conv 0.01% : 0.000031s : 1: event_method 0.00% : 0.000009s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000008s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.22% : 0.000555s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000010s : 1: micro_interleaved_order_control 0.34% : 0.000873s : 1: mutable_eliminate 0.01% : 0.000016s : 1: offloading_packed_experts 0.01% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000040s : 1: opt.transform.mutable_eliminate 0.98% : 0.002505s : 78: opt.transform.opt_a 0.04% : 0.000099s : 1: opt.transform.opt_after_cconv 0.02% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.14% : 0.000355s : 28: opt.transform.opt_b 0.05% : 0.000130s : 2: opt.transform.opt_trans_graph 0.05% : 0.000129s : 4: opt.transform.symbol_engine_opt 9.90% : 0.025298s : 1: opt_a 0.10% : 0.000253s : 1: opt_after_cconv 0.27% : 0.000678s : 1: opt_after_jit_grad 0.22% : 0.000560s : 1: opt_b 11.43% : 0.029208s : 1: optimize 0.02% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000019s : 1: order_py_execute_after_rewriter 0.02% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 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% : 0.000006s : 1: pipeline_split 0.02% : 0.000055s : 1: pre_auto_parallel 0.02% : 0.000052s : 1: py_interpret_to_execute 0.01% : 0.000036s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000082s : 1: remove_dup_value 7.90% : 0.020184s : 1: renormalize.infer 0.37% : 0.000948s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.09% : 0.000229s : 1: rewriter_after_opt_a 0.03% : 0.000087s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000009s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000203s : 1: symbol_engine_optimizer 0.07% : 0.000173s : 1: tuple_transform 62.66% : 0.160113s : 1: type_inference [WARNING] ME(168598:281473140318000,MainProcess):2026-01-29-17:38:18.676.994 [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 = 0.0941628, [21] [bootstrap]: 0.00052026 [type_inference]: 0.0785434 [event_method]: 1.913e-05 [auto_monad]: 0.00019615 [graph_reusing]: 6.17001e-06 [inline]: 2.42001e-06 [add_attr]: 0.00432255, [1] [add_attr_with_inline]: 0.0043075, [1] [Cycle 1]: 7.648e-05, [2] [tag_attr]: 2.609e-05 [meta_addattr_fg_expand]: 4.50999e-06 [parallel-infer-symbol]: 4.25999e-06 [pre_auto_parallel]: 4.191e-05 [insert-virtual-dataset]: 3.08998e-06 [parallel-infer-symbol-second]: 6.69999e-07 [dataset_repeat_opt]: 2.17999e-06 [pipeline_split]: 3.21001e-06 [optimize]: 0.00943096, [53] [py_interpret_to_execute]: 3.811e-05 [rewriter_before_opt_a]: 8.597e-05 [opt_a]: 0.00535552, [2] [Cycle 1]: 0.00366999, [45] [expand_dump_flag]: 2.94001e-06 [switch_simplify]: 3.631e-05 [loop_unroll]: 1.994e-05 [a_1]: 0.00079577 [with_stream_mark]: 2.91e-05 [recompute_prepare]: 2.105e-05 [updatestate_depend_eliminate]: 1.079e-05 [updatestate_assign_eliminate]: 1.119e-05 [updatestate_loads_eliminate]: 1.637e-05 [parameter_eliminate]: 2.54001e-06 [a_2]: 0.00025562 [accelerated_algorithm]: 4.242e-05 [shard]: 2.51e-06 [meta_shard_fg_expand]: 5.79e-06 [shard_inline]: 1.689e-05 [merge_send_recv]: 1.605e-05 [auto_parallel]: 1.354e-05 [parallel]: 2.865e-05 [flash_sp]: 1.384e-05 [merge_comm]: 9.27999e-06 [allreduce_fusion]: 8.92e-06 [matmul_add_comm_reduction]: 2.228e-05 [allreduce_slice_to_reducescatter]: 7.90023e-07 [virtual_shard_identity]: 2.124e-05 [virtual_dataset]: 1.513e-05 [get_grad_eliminate_]: 1.613e-05 [virtual_output]: 1.615e-05 [merge_forward]: 1.03e-05 [cell_reuse_recompute_pass]: 1.66e-06 [offload_activation]: 2.079e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.157e-05 [merge_recompute_call_nodes]: 2.12001e-06 [before_grad]: 2.807e-05 [set_forward_comm_id_for_comm_node_pass]: 1.031e-05 [meta_fg_expand]: 7.13998e-06 [flash_sp_send_recv_attached]: 5.28002e-06 [receive_attached]: 2.40002e-06 [after_resolve]: 2.493e-05 [a_after_grad]: 2.494e-05 [renormalize]: 0.00142679 [add_forward_monad_depend]: 9.95002e-06 [auto_monad_grad]: 3.26001e-06 [auto_monad_eliminator]: 5.597e-05 [cse]: 0.00011111 [a_3]: 0.00012432 [Cycle 2]: 0.00166936, [45] [expand_dump_flag]: 2.39001e-06 [switch_simplify]: 1.8e-05 [loop_unroll]: 1.456e-05 [a_1]: 0.00043647 [with_stream_mark]: 2.302e-05 [recompute_prepare]: 1.647e-05 [updatestate_depend_eliminate]: 9.81e-06 [updatestate_assign_eliminate]: 9.47999e-06 [updatestate_loads_eliminate]: 1.467e-05 [parameter_eliminate]: 1.91e-06 [a_2]: 0.00028834 [accelerated_algorithm]: 2.37e-05 [shard]: 1.70001e-06 [meta_shard_fg_expand]: 5.74e-06 [shard_inline]: 1.824e-05 [merge_send_recv]: 1.651e-05 [auto_parallel]: 1.596e-05 [parallel]: 9.81e-06 [flash_sp]: 4.45e-06 [merge_comm]: 8.99e-06 [allreduce_fusion]: 8.13999e-06 [matmul_add_comm_reduction]: 1.672e-05 [allreduce_slice_to_reducescatter]: 6.29982e-07 [virtual_shard_identity]: 1.801e-05 [virtual_dataset]: 1.455e-05 [get_grad_eliminate_]: 1.515e-05 [virtual_output]: 1.374e-05 [merge_forward]: 1.147e-05 [cell_reuse_recompute_pass]: 2.22001e-06 [offload_activation]: 1.752e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.074e-05 [merge_recompute_call_nodes]: 2.36e-06 [before_grad]: 2.694e-05 [set_forward_comm_id_for_comm_node_pass]: 1.003e-05 [meta_fg_expand]: 6.61e-06 [flash_sp_send_recv_attached]: 1.95001e-06 [receive_attached]: 2.36e-06 [after_resolve]: 2.429e-05 [a_after_grad]: 2.23e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.58999e-06 [auto_monad_grad]: 2.51e-06 [auto_monad_eliminator]: 4.665e-05 [cse]: 7.471e-05 [a_3]: 0.00010438 [py_interpret_to_execute_after_opt_a]: 2.78e-05 [slice_cell_reuse_recomputed_activation]: 2.37999e-06 [rewriter_after_opt_a]: 0.00020237 [convert_after_rewriter]: 1.757e-05 [order_py_execute_after_rewriter]: 1.128e-05 [mutable_eliminate]: 0.00086462 [opt_b]: 0.00056108, [1] [Cycle 1]: 0.00055044, [7] [b_1]: 0.00036209 [b_2]: 1.907e-05 [updatestate_depend_eliminate]: 1.533e-05 [updatestate_assign_eliminate]: 9.71e-06 [updatestate_loads_eliminate]: 1.597e-05 [renormalize]: 1.19e-06 [cse]: 7.888e-05 [optimize_parallel_all_gather_comm]: 3.443e-05 [overlap_param_gather]: 2.24999e-06 [cconv]: 4.372e-05 [loop_unroll]: 0.0005689 [opt_after_cconv]: 0.00025969, [1] [Cycle 1]: 0.00025058, [7] [c_1]: 0.00010179 [parameter_eliminate]: 4.38001e-06 [updatestate_depend_eliminate]: 1.222e-05 [updatestate_assign_eliminate]: 8.67998e-06 [updatestate_loads_eliminate]: 1.243e-05 [cse]: 6.463e-05 [renormalize]: 6.80011e-07 [remove_dup_value]: 9.041e-05 [tuple_transform]: 0.00016691, [1] [Cycle 1]: 0.00015976, [4] [d_1]: 0.00011663 [none_parameter_eliminate]: 1.97999e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.669e-05 [partial_unused_args_eliminate]: 2.84001e-06 [add_recomputation]: 0.00016141 [cse_after_recomputation]: 6.796e-05, [1] [Cycle 1]: 6.091e-05, [1] [cse]: 5.388e-05 [environ_conv]: 1.798e-05 [swap_dp_allreduce_reducescatter]: 1.247e-05 [bias_add_comm_swap]: 3.3e-06 [label_micro_interleaved_index]: 5.24e-06 [label_fine_grained_interleaved_index]: 2.78e-06 [merge_cast_opt]: 1.50999e-06 [slice_recompute_activation]: 2.50002e-06 [micro_interleaved_order_control]: 2.54999e-06 [assign_add_opt]: 1.59e-06 [ForceFp32Comm]: 9.09989e-07 [remove_cast_before_assign_add]: 1.35999e-06 [full_micro_interleaved_order_control]: 2.86e-06 [reorder_send_recv_between_fp_bp]: 3.18e-06 [comm_op_add_attrs]: 1.40001e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.51998e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 1.45999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.34999e-06 [control_data_broadcast_order]: 3.232e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 1.074e-05 [overlap_recompute_and_grad_model_parallel]: 8.55001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.58002e-06 [overlap_recompute_allgather_and_fa_grad]: 2.09999e-06 [overlap_recompute_comm]: 2.53998e-06 [overlap_grad_ring_attention]: 7.77e-06 [overlap_grad_flash_sp]: 3.979e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.78998e-06 [split_layernorm_comm]: 1.92999e-06 [handle_group_info]: 1.24e-06 [symbol_engine_optimizer]: 0.00039002, [1] [Cycle 1]: 0.00038314, [6] [build]: 0.00019323 [elim_shapecalc]: 3.045e-05 [elim_not_effective]: 4.374e-05 [opt_reshape]: 2.441e-05 [fold_const_symbol]: 3.751e-05 [renormalize]: 2.89991e-07 [detach_backward]: 4.19002e-06 [pipeline_parallel_scheduler]: 1.74e-06 [auto_monad_reorder]: 6.695e-05 [get_jit_bprop_graph]: 2.64001e-06 [rewriter_after_jit_bprop_graph]: 8.76002e-06 [opt_after_jit_grad]: 0.00068639 [validate]: 7.696e-05 Sums bootstrap : 0.000520s : 0.59% type_inference : 0.078543s : 88.70% event_method : 0.000019s : 0.02% auto_monad : 0.000196s : 0.22% graph_reusing : 0.000006s : 0.01% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000042s : 0.05% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.04% optimize.rewriter_before_opt_a : 0.000086s : 0.10% optimize.opt_a.expand_dump_flag : 0.000005s : 0.01% optimize.opt_a.switch_simplify : 0.000054s : 0.06% optimize.opt_a.loop_unroll : 0.000035s : 0.04% optimize.opt_a.a_1 : 0.001232s : 1.39% optimize.opt_a.with_stream_mark : 0.000052s : 0.06% optimize.opt_a.recompute_prepare : 0.000038s : 0.04% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.02% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.02% optimize.opt_a.updatestate_loads_eliminate : 0.000031s : 0.04% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.000544s : 0.61% optimize.opt_a.accelerated_algorithm : 0.000066s : 0.07% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.01% optimize.opt_a.shard_inline : 0.000035s : 0.04% optimize.opt_a.merge_send_recv : 0.000033s : 0.04% optimize.opt_a.auto_parallel : 0.000029s : 0.03% optimize.opt_a.parallel : 0.000038s : 0.04% optimize.opt_a.flash_sp : 0.000018s : 0.02% optimize.opt_a.merge_comm : 0.000018s : 0.02% optimize.opt_a.allreduce_fusion : 0.000017s : 0.02% optimize.opt_a.matmul_add_comm_reduction : 0.000039s : 0.04% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.04% optimize.opt_a.virtual_dataset : 0.000030s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000031s : 0.04% optimize.opt_a.virtual_output : 0.000030s : 0.03% optimize.opt_a.merge_forward : 0.000022s : 0.02% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.04% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000062s : 0.07% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.01% optimize.opt_a.before_grad : 0.000055s : 0.06% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.02% optimize.opt_a.meta_fg_expand : 0.000014s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.01% optimize.opt_a.receive_attached : 0.000005s : 0.01% optimize.opt_a.after_resolve : 0.000049s : 0.06% optimize.opt_a.a_after_grad : 0.000047s : 0.05% optimize.opt_a.renormalize : 0.001427s : 1.61% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.02% optimize.opt_a.auto_monad_grad : 0.000006s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000103s : 0.12% optimize.opt_a.cse : 0.000186s : 0.21% optimize.opt_a.a_3 : 0.000229s : 0.26% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.03% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000202s : 0.23% optimize.convert_after_rewriter : 0.000018s : 0.02% optimize.order_py_execute_after_rewriter : 0.000011s : 0.01% optimize.mutable_eliminate : 0.000865s : 0.98% optimize.opt_b.b_1 : 0.000362s : 0.41% optimize.opt_b.b_2 : 0.000019s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.02% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000016s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000079s : 0.09% optimize.optimize_parallel_all_gather_comm : 0.000034s : 0.04% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.05% optimize.loop_unroll : 0.000569s : 0.64% optimize.opt_after_cconv.c_1 : 0.000102s : 0.11% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.cse : 0.000065s : 0.07% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000090s : 0.10% optimize.tuple_transform.d_1 : 0.000117s : 0.13% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.02% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000161s : 0.18% optimize.cse_after_recomputation.cse : 0.000054s : 0.06% optimize.environ_conv : 0.000018s : 0.02% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 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 : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000032s : 0.04% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.01% optimize.overlap_grad_flash_sp : 0.000040s : 0.04% 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 : 0.000193s : 0.22% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000030s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000044s : 0.05% optimize.symbol_engine_optimizer.opt_reshape : 0.000024s : 0.03% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000038s : 0.04% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000067s : 0.08% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.01% opt_after_jit_grad : 0.000686s : 0.78% validate : 0.000077s : 0.09% Time group info: ------[substitution.] 0.000533 102 31.79% : 0.000170s : 4: substitution.arithmetic_simplify 2.15% : 0.000011s : 2: substitution.depend_value_elim 2.78% : 0.000015s : 8: substitution.elim_not_effective 2.49% : 0.000013s : 8: substitution.fold_const_symbol 2.48% : 0.000013s : 11: substitution.graph_param_transform 26.10% : 0.000139s : 1: substitution.inline 1.85% : 0.000010s : 16: substitution.j_node_and_user_rematch 4.18% : 0.000022s : 4: substitution.less_batch_normalization 1.71% : 0.000009s : 12: substitution.load_eliminater 2.69% : 0.000014s : 16: substitution.remove_not_recompute_node 1.74% : 0.000009s : 6: substitution.replace_old_param 2.14% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 17.92% : 0.000096s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.078474 2 99.19% : 0.077840s : 1: type_inference.infer 0.81% : 0.000635s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000138 1 100.00% : 0.000138s : 1: match.inline ------[predicate.] 0.000396 2549 0.83% : 0.000003s : 23: predicate.accumulaten_eliminater 1.25% : 0.000005s : 11: predicate.ad_related_special_op_eliminate 0.74% : 0.000003s : 22: predicate.addn_check_dump 0.77% : 0.000003s : 23: predicate.addn_zero_filter 0.70% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.58% : 0.000010s : 45: predicate.arithmetic_simplify 0.79% : 0.000003s : 23: predicate.cast_eliminate 0.81% : 0.000003s : 22: predicate.check_bprop_eliminate 0.73% : 0.000003s : 22: predicate.compare_switch_simplify 0.23% : 0.000001s : 11: predicate.const_output_eliminate 0.89% : 0.000004s : 22: predicate.depend_value_elim 0.78% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 1.15% : 0.000005s : 23: predicate.dict_get_item_eliminator 0.79% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.07% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.24% : 0.000001s : 11: predicate.elim_not_effective 0.52% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.05% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.04% : 0.000004s : 34: predicate.environ_get_depend_swap 1.86% : 0.000007s : 56: predicate.environ_get_eliminate 1.05% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.76% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.40% : 0.000006s : 24: predicate.float_depend_g_call 0.72% : 0.000003s : 22: predicate.float_environ_get_switch 1.10% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 11: predicate.fold_const_symbol 0.81% : 0.000003s : 22: predicate.get_grad_eliminate 0.32% : 0.000001s : 11: predicate.graph_param_transform 0.82% : 0.000003s : 22: predicate.incorporate_call 0.70% : 0.000003s : 22: predicate.incorporate_call_switch 5.69% : 0.000023s : 113: predicate.inline 0.97% : 0.000004s : 22: predicate.inline_without_move 0.42% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.18% : 0.000005s : 22: predicate.less_batch_normalization 1.75% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.31% : 0.000009s : 68: predicate.load_eliminater 1.56% : 0.000006s : 11: predicate.loop_unroll_after_grad 1.15% : 0.000005s : 27: predicate.loop_unroll_before_grad 1.76% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.82% : 0.000003s : 22: predicate.merge_addn 0.73% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.74% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.73% : 0.000003s : 23: predicate.minmaximum_grad 1.64% : 0.000006s : 11: predicate.mutable_eliminate 0.51% : 0.000002s : 11: predicate.opt_reshape 0.49% : 0.000002s : 11: predicate.parallel_virtual_node 1.16% : 0.000005s : 24: predicate.partial_defer_inline 1.23% : 0.000005s : 34: predicate.partial_eliminate 0.74% : 0.000003s : 23: predicate.print_const_string_wrapper 0.74% : 0.000003s : 22: predicate.reduce_all_const_elim 1.09% : 0.000004s : 23: predicate.reduce_eliminate 2.26% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.73% : 0.000003s : 22: predicate.remove_not_recompute_node 1.15% : 0.000005s : 45: predicate.replace_applicator 0.68% : 0.000003s : 22: predicate.replace_old_param 0.39% : 0.000002s : 11: predicate.reset_defer_inline 0.76% : 0.000003s : 23: predicate.reshape_eliminate 0.88% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.53% : 0.000002s : 11: predicate.row_tensor_eliminate 1.02% : 0.000004s : 22: predicate.same_eliminate 0.51% : 0.000002s : 22: predicate.set_cell_output_no_recompute 0.85% : 0.000003s : 22: predicate.shard_identity_eliminate 0.94% : 0.000004s : 22: predicate.special_op_eliminate 0.90% : 0.000004s : 22: predicate.specialize_transform 1.42% : 0.000006s : 22: predicate.split_environ_get_set_with_tuple_value 1.06% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.42% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.88% : 0.000003s : 24: predicate.switch_defer_inline 1.60% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.39% : 0.000013s : 84: predicate.switch_simplify 0.84% : 0.000003s : 23: predicate.tile_eliminate 0.77% : 0.000003s : 23: predicate.transpose_eliminate 1.77% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.75% : 0.000007s : 45: predicate.tuple_list_get_item_depend_reorder 3.10% : 0.000012s : 67: predicate.tuple_list_get_item_eliminator 1.63% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.66% : 0.000011s : 67: predicate.tuple_list_set_item_eliminator 1.67% : 0.000007s : 45: predicate.tuple_to_list_eliminator_ 2.25% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.23% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.47% : 0.000002s : 11: predicate.value_based_eliminate 0.79% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.81% : 0.000003s : 22: predicate.virtual_output_eliminate 0.43% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.53% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000373 4 7.62% : 0.000028s : 1: func_graph_cloner_run.FuncGraphClonerGraph 92.38% : 0.000345s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.112407 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.85% : 0.004331s : 1: add_attr 3.84% : 0.004312s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.15% : 0.000167s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.18% : 0.000204s : 1: auto_monad 0.07% : 0.000074s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000007s : 1: bias_add_comm_swap 0.50% : 0.000559s : 1: bootstrap 0.04% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.03% : 0.000036s : 1: control_data_broadcast_order 0.02% : 0.000023s : 1: convert_after_rewriter 0.06% : 0.000071s : 1: cse_after_recomputation 0.01% : 0.000006s : 1: dataset_repeat_opt 0.01% : 0.000008s : 1: detach_backward 0.02% : 0.000023s : 1: environ_conv 0.02% : 0.000028s : 1: event_method 0.01% : 0.000006s : 1: full_micro_interleaved_order_control 0.01% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.01% : 0.000007s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000006s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.01% : 0.000006s : 1: label_fine_grained_interleaved_index 0.01% : 0.000008s : 1: label_micro_interleaved_index 0.52% : 0.000583s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.78% : 0.000882s : 1: mutable_eliminate 0.01% : 0.000014s : 1: offloading_packed_experts 0.03% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.03% : 0.000038s : 1: opt.transform.mutable_eliminate 2.18% : 0.002454s : 78: opt.transform.opt_a 0.09% : 0.000100s : 1: opt.transform.opt_after_cconv 0.05% : 0.000059s : 1: opt.transform.opt_after_jit_grad 0.30% : 0.000339s : 28: opt.transform.opt_b 0.12% : 0.000129s : 2: opt.transform.opt_trans_graph 0.12% : 0.000130s : 4: opt.transform.symbol_engine_opt 4.77% : 0.005360s : 1: opt_a 0.24% : 0.000264s : 1: opt_after_cconv 0.63% : 0.000705s : 1: opt_after_jit_grad 0.50% : 0.000565s : 1: opt_b 8.40% : 0.009439s : 1: optimize 0.03% : 0.000038s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000015s : 1: order_py_execute_after_rewriter 0.04% : 0.000043s : 1: overlap_grad_flash_sp 0.01% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000006s : 1: overlap_param_gather 0.01% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000006s : 1: pipeline_split 0.04% : 0.000046s : 1: pre_auto_parallel 0.04% : 0.000042s : 1: py_interpret_to_execute 0.03% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.09% : 0.000096s : 1: remove_dup_value 0.71% : 0.000794s : 1: renormalize.infer 0.55% : 0.000619s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.19% : 0.000211s : 1: rewriter_after_opt_a 0.08% : 0.000091s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.01% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.35% : 0.000394s : 1: symbol_engine_optimizer 0.15% : 0.000170s : 1: tuple_transform 69.90% : 0.078569s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add_continuous tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add_continuous,max_mem:20.0M =============================== 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 ================== 1 passed, 25 warnings in 90.86s (0:01:30) ===================