==================================================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 6 items test_matmul_biasadd_split.py [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:37:41.946.926 [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 = 1.69705, [21] [bootstrap]: 0.00063179 [type_inference]: 1.50437 [event_method]: 0.000227 [auto_monad]: 0.00089672 [graph_reusing]: 5.947e-05 [inline]: 3.58999e-06 [add_attr]: 0.00894698, [1] [add_attr_with_inline]: 0.00892793, [1] [Cycle 1]: 0.00034262, [2] [tag_attr]: 0.00019583 [meta_addattr_fg_expand]: 5.865e-05 [parallel-infer-symbol]: 4.45e-06 [pre_auto_parallel]: 0.00025984 [insert-virtual-dataset]: 2.83e-06 [parallel-infer-symbol-second]: 1.15999e-06 [dataset_repeat_opt]: 2.51e-06 [pipeline_split]: 1.84e-06 [optimize]: 0.180035, [53] [py_interpret_to_execute]: 0.0388182 [rewriter_before_opt_a]: 0.00100992 [opt_a]: 0.0456415, [2] [Cycle 1]: 0.0430187, [45] [expand_dump_flag]: 3.619e-05 [switch_simplify]: 0.00087376 [loop_unroll]: 0.00033556 [a_1]: 0.0263997 [with_stream_mark]: 6.617e-05 [recompute_prepare]: 4.556e-05 [updatestate_depend_eliminate]: 2.364e-05 [updatestate_assign_eliminate]: 2.246e-05 [updatestate_loads_eliminate]: 8.37e-05 [parameter_eliminate]: 3.73001e-06 [a_2]: 0.00105631 [accelerated_algorithm]: 7.264e-05 [shard]: 3.01001e-06 [meta_shard_fg_expand]: 2.757e-05 [shard_inline]: 2.796e-05 [merge_send_recv]: 4.534e-05 [auto_parallel]: 2.333e-05 [parallel]: 4.725e-05 [flash_sp]: 2.651e-05 [merge_comm]: 1.667e-05 [allreduce_fusion]: 1.555e-05 [matmul_add_comm_reduction]: 2.736e-05 [allreduce_slice_to_reducescatter]: 7.10017e-07 [virtual_shard_identity]: 3.147e-05 [virtual_dataset]: 2.737e-05 [get_grad_eliminate_]: 2.538e-05 [virtual_output]: 2.547e-05 [merge_forward]: 1.581e-05 [cell_reuse_recompute_pass]: 2.33998e-06 [offload_activation]: 2.763e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.428e-05 [merge_recompute_call_nodes]: 1.96e-06 [before_grad]: 4.603e-05 [set_forward_comm_id_for_comm_node_pass]: 1.619e-05 [meta_fg_expand]: 2.129e-05 [flash_sp_send_recv_attached]: 7.04001e-06 [receive_attached]: 1.202e-05 [after_resolve]: 3.553e-05 [a_after_grad]: 4.331e-05 [renormalize]: 0.0121576 [add_forward_monad_depend]: 1.427e-05 [auto_monad_grad]: 3.55e-06 [auto_monad_eliminator]: 0.00010195 [cse]: 0.00040033 [a_3]: 0.0001991 [Cycle 2]: 0.00259804, [45] [expand_dump_flag]: 3.50003e-06 [switch_simplify]: 2.978e-05 [loop_unroll]: 2.521e-05 [a_1]: 0.00081503 [with_stream_mark]: 3.661e-05 [recompute_prepare]: 2.69e-05 [updatestate_depend_eliminate]: 1.637e-05 [updatestate_assign_eliminate]: 1.504e-05 [updatestate_loads_eliminate]: 2.041e-05 [parameter_eliminate]: 2.71e-06 [a_2]: 0.00044254 [accelerated_algorithm]: 4.08e-05 [shard]: 2.86e-06 [meta_shard_fg_expand]: 1.122e-05 [shard_inline]: 2.534e-05 [merge_send_recv]: 2.395e-05 [auto_parallel]: 2.258e-05 [parallel]: 1.024e-05 [flash_sp]: 4.99003e-06 [merge_comm]: 1.495e-05 [allreduce_fusion]: 1.568e-05 [matmul_add_comm_reduction]: 2.672e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.79e-05 [virtual_dataset]: 2.467e-05 [get_grad_eliminate_]: 2.414e-05 [virtual_output]: 2.418e-05 [merge_forward]: 1.455e-05 [cell_reuse_recompute_pass]: 2.74001e-06 [offload_activation]: 2.617e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.152e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 4.111e-05 [set_forward_comm_id_for_comm_node_pass]: 1.519e-05 [meta_fg_expand]: 1.151e-05 [flash_sp_send_recv_attached]: 2.26998e-06 [receive_attached]: 2.71e-06 [after_resolve]: 3.43e-05 [a_after_grad]: 4.082e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.48001e-06 [auto_monad_grad]: 3.75998e-06 [auto_monad_eliminator]: 7.387e-05 [cse]: 0.00010152 [a_3]: 0.00016535 [py_interpret_to_execute_after_opt_a]: 4.08e-05 [slice_cell_reuse_recomputed_activation]: 2.61999e-06 [rewriter_after_opt_a]: 0.00095211 [convert_after_rewriter]: 3.591e-05 [order_py_execute_after_rewriter]: 1.491e-05 [mutable_eliminate]: 0.00084872 [opt_b]: 0.0891694, [1] [Cycle 1]: 0.0891554, [7] [b_1]: 0.0887271 [b_2]: 6.215e-05 [updatestate_depend_eliminate]: 3.578e-05 [updatestate_assign_eliminate]: 1.842e-05 [updatestate_loads_eliminate]: 2.475e-05 [renormalize]: 8.89995e-07 [cse]: 0.00018524 [optimize_parallel_all_gather_comm]: 6.096e-05 [overlap_param_gather]: 7.84997e-06 [cconv]: 5.131e-05 [loop_unroll]: 0.00087246 [opt_after_cconv]: 0.00044728, [1] [Cycle 1]: 0.00043448, [7] [c_1]: 0.00020372 [parameter_eliminate]: 6.78998e-06 [updatestate_depend_eliminate]: 2.647e-05 [updatestate_assign_eliminate]: 1.45e-05 [updatestate_loads_eliminate]: 1.869e-05 [cse]: 0.00012097 [renormalize]: 7.00005e-07 [remove_dup_value]: 0.00013409 [tuple_transform]: 0.00031476, [1] [Cycle 1]: 0.00030716, [4] [d_1]: 0.00024994 [none_parameter_eliminate]: 3.81999e-06 [renormalize]: 3.50003e-07 [switch_simplify]: 2.864e-05 [partial_unused_args_eliminate]: 2.27999e-06 [add_recomputation]: 0.00019952 [cse_after_recomputation]: 9.117e-05, [1] [Cycle 1]: 8.361e-05, [1] [cse]: 7.577e-05 [environ_conv]: 4.033e-05 [swap_dp_allreduce_reducescatter]: 2.162e-05 [bias_add_comm_swap]: 3.55998e-06 [label_micro_interleaved_index]: 8.72e-06 [label_fine_grained_interleaved_index]: 3.18e-06 [merge_cast_opt]: 1.87999e-06 [slice_recompute_activation]: 2.51e-06 [micro_interleaved_order_control]: 2.61999e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 9.10019e-07 [remove_cast_before_assign_add]: 1.50999e-06 [full_micro_interleaved_order_control]: 2.62001e-06 [reorder_send_recv_between_fp_bp]: 2.74999e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.25001e-06 [interleave_split_concat_branches]: 1.18001e-06 [interleave_parallel_branches]: 1.37999e-06 [overlap_opt_shard_in_pipeline]: 2.648e-05 [overlap_opt_shard_grad_in_pipeline]: 1.86998e-06 [control_data_broadcast_order]: 4.75e-05 [grouped_pairwise_exchange_alltoall]: 1.69998e-06 [offloading_packed_experts]: 1.217e-05 [overlap_recompute_and_grad_model_parallel]: 1.2e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.55999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.32001e-06 [overlap_grad_ring_attention]: 1.153e-05 [overlap_grad_flash_sp]: 7.732e-05 [begin_end_overlap_inline]: 6.09987e-07 [split_matmul_comm_elemetwise]: 2.76e-06 [split_layernorm_comm]: 1.99e-06 [handle_group_info]: 1.37999e-06 [symbol_engine_optimizer]: 0.00062481, [1] [Cycle 1]: 0.0006165, [6] [build]: 0.0003435 [elim_shapecalc]: 4.135e-05 [elim_not_effective]: 7.08e-05 [opt_reshape]: 3.866e-05 [fold_const_symbol]: 6.947e-05 [renormalize]: 2.50002e-07 [detach_backward]: 3.31999e-06 [pipeline_parallel_scheduler]: 2.04999e-06 [auto_monad_reorder]: 9.109e-05 [get_jit_bprop_graph]: 2.62001e-06 [rewriter_after_jit_bprop_graph]: 5.92001e-06 [opt_after_jit_grad]: 0.00110015 [validate]: 0.00014758 Sums bootstrap : 0.000632s : 0.04% type_inference : 1.504370s : 89.19% event_method : 0.000227s : 0.01% auto_monad : 0.000897s : 0.05% graph_reusing : 0.000059s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000196s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000059s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000260s : 0.02% 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 : 0.038818s : 2.30% optimize.rewriter_before_opt_a : 0.001010s : 0.06% optimize.opt_a.expand_dump_flag : 0.000040s : 0.00% optimize.opt_a.switch_simplify : 0.000904s : 0.05% optimize.opt_a.loop_unroll : 0.000361s : 0.02% optimize.opt_a.a_1 : 0.027215s : 1.61% optimize.opt_a.with_stream_mark : 0.000103s : 0.01% optimize.opt_a.recompute_prepare : 0.000072s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000040s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000037s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000104s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001499s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000113s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000039s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000069s : 0.00% optimize.opt_a.auto_parallel : 0.000046s : 0.00% optimize.opt_a.parallel : 0.000057s : 0.00% optimize.opt_a.flash_sp : 0.000032s : 0.00% optimize.opt_a.merge_comm : 0.000032s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000054s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000059s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000050s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000054s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000106s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000087s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.00% optimize.opt_a.meta_fg_expand : 0.000033s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000015s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.00% optimize.opt_a.a_after_grad : 0.000084s : 0.00% optimize.opt_a.renormalize : 0.012158s : 0.72% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000176s : 0.01% optimize.opt_a.cse : 0.000502s : 0.03% optimize.opt_a.a_3 : 0.000364s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000041s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000952s : 0.06% optimize.convert_after_rewriter : 0.000036s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000849s : 0.05% optimize.opt_b.b_1 : 0.088727s : 5.26% optimize.opt_b.b_2 : 0.000062s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000036s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000018s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000025s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000185s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000061s : 0.00% optimize.overlap_param_gather : 0.000008s : 0.00% optimize.cconv : 0.000051s : 0.00% optimize.loop_unroll : 0.000872s : 0.05% optimize.opt_after_cconv.c_1 : 0.000204s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.cse : 0.000121s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000134s : 0.01% optimize.tuple_transform.d_1 : 0.000250s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000004s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000029s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000200s : 0.01% optimize.cse_after_recomputation.cse : 0.000076s : 0.00% optimize.environ_conv : 0.000040s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000022s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 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 : 0.000026s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000048s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 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 : 0.000012s : 0.00% optimize.overlap_grad_flash_sp : 0.000077s : 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 : 0.000343s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000071s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000039s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000069s : 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 : 0.000091s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.001100s : 0.07% validate : 0.000148s : 0.01% Time group info: ------[substitution.] 0.020952 612 0.26% : 0.000055s : 5: substitution.arithmetic_simplify 0.10% : 0.000020s : 8: substitution.depend_value_elim 0.12% : 0.000024s : 17: substitution.elim_not_effective 0.08% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.15% : 0.000032s : 17: substitution.fold_const_symbol 0.09% : 0.000019s : 21: substitution.graph_param_transform 94.06% : 0.019708s : 71: substitution.inline 0.07% : 0.000015s : 35: substitution.j_node_and_user_rematch 0.19% : 0.000041s : 10: substitution.less_batch_normalization 0.33% : 0.000070s : 2: substitution.list_to_tuple_eliminator_ 0.05% : 0.000010s : 12: substitution.load_eliminater 0.14% : 0.000030s : 21: substitution.minmaximum_grad 0.04% : 0.000009s : 2: substitution.opt_reshape 0.11% : 0.000022s : 35: substitution.remove_not_recompute_node 0.05% : 0.000010s : 6: substitution.replace_old_param 0.29% : 0.000061s : 18: substitution.reshape_eliminate 0.28% : 0.000058s : 24: substitution.switch_simplify 0.68% : 0.000143s : 51: substitution.tuple_list_convert_item_index_to_positive 0.34% : 0.000070s : 51: substitution.tuple_list_get_item_const_eliminator 0.46% : 0.000096s : 51: substitution.tuple_list_get_item_depend_reorder 0.99% : 0.000208s : 73: substitution.tuple_list_get_item_eliminator 0.46% : 0.000096s : 51: substitution.tuple_list_get_set_item_eliminator 0.09% : 0.000018s : 8: substitution.updatestate_pure_node_eliminater 0.56% : 0.000118s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.503837 2 96.04% : 1.444336s : 1: type_inference.infer 3.96% : 0.059502s : 1: type_inference.specialize ------[replace.] 0.001315 115 4.80% : 0.000063s : 5: replace.depend_value_elim 53.34% : 0.000701s : 71: replace.inline 4.21% : 0.000055s : 2: replace.list_to_tuple_eliminator_ 28.74% : 0.000378s : 24: replace.switch_simplify 8.90% : 0.000117s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.019807 115 0.01% : 0.000002s : 5: match.depend_value_elim 99.24% : 0.019656s : 71: match.inline 0.34% : 0.000067s : 2: match.list_to_tuple_eliminator_ 0.21% : 0.000042s : 24: match.switch_simplify 0.20% : 0.000040s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001834 10672 1.10% : 0.000020s : 131: predicate.accumulaten_eliminater 0.54% : 0.000010s : 21: predicate.ad_related_special_op_eliminate 0.59% : 0.000011s : 70: predicate.addn_check_dump 1.15% : 0.000021s : 131: predicate.addn_zero_filter 1.11% : 0.000020s : 131: predicate.adjust_all_reduce_mul_add 2.34% : 0.000043s : 201: predicate.arithmetic_simplify 1.26% : 0.000023s : 131: predicate.cast_eliminate 0.32% : 0.000006s : 42: predicate.check_bprop_eliminate 0.52% : 0.000010s : 70: predicate.compare_switch_simplify 0.21% : 0.000004s : 21: predicate.const_output_eliminate 0.70% : 0.000013s : 73: predicate.depend_value_elim 1.25% : 0.000023s : 131: predicate.dict_get_item_const_eliminator 1.25% : 0.000023s : 131: predicate.dict_get_item_eliminator 1.32% : 0.000024s : 131: predicate.dict_set_item_eliminator 0.41% : 0.000007s : 42: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 21: predicate.elim_not_effective 0.20% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.22% : 0.000022s : 152: predicate.environ_add_const_eliminate 1.25% : 0.000023s : 152: predicate.environ_get_add_eliminate 1.35% : 0.000025s : 152: predicate.environ_get_depend_swap 1.82% : 0.000033s : 222: predicate.environ_get_eliminate 1.19% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.81% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.58% : 0.000047s : 217: predicate.float_depend_g_call 0.54% : 0.000010s : 70: predicate.float_environ_get_switch 0.72% : 0.000013s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.39% : 0.000007s : 43: predicate.get_grad_eliminate 0.11% : 0.000002s : 21: predicate.graph_param_transform 0.55% : 0.000010s : 70: predicate.incorporate_call 0.49% : 0.000009s : 70: predicate.incorporate_call_switch 5.85% : 0.000107s : 503: predicate.inline 0.45% : 0.000008s : 43: predicate.inline_without_move 0.17% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.51% : 0.000009s : 43: predicate.less_batch_normalization 1.65% : 0.000030s : 188: predicate.list_to_tuple_eliminator_ 2.60% : 0.000048s : 319: predicate.load_eliminater 0.40% : 0.000007s : 21: predicate.loop_unroll_after_grad 3.29% : 0.000060s : 322: predicate.loop_unroll_before_grad 1.45% : 0.000027s : 173: predicate.make_slice_get_slice_eliminator 0.58% : 0.000011s : 70: predicate.merge_addn 0.30% : 0.000005s : 42: predicate.micro_step_allgather_replace 0.34% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.08% : 0.000020s : 131: predicate.minmaximum_grad 0.41% : 0.000008s : 21: predicate.mutable_eliminate 0.21% : 0.000004s : 21: predicate.opt_reshape 0.20% : 0.000004s : 21: predicate.parallel_virtual_node 3.24% : 0.000059s : 217: predicate.partial_defer_inline 1.43% : 0.000026s : 167: predicate.partial_eliminate 1.31% : 0.000024s : 131: predicate.print_const_string_wrapper 0.48% : 0.000009s : 65: predicate.reduce_all_const_elim 1.57% : 0.000029s : 131: predicate.reduce_eliminate 2.68% : 0.000049s : 319: predicate.redundant_stop_gradient_eliminater 0.20% : 0.000004s : 43: predicate.remove_not_recompute_node 1.06% : 0.000019s : 188: predicate.replace_applicator 0.18% : 0.000003s : 43: predicate.replace_old_param 0.11% : 0.000002s : 21: predicate.reset_defer_inline 1.20% : 0.000022s : 131: predicate.reshape_eliminate 0.34% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.73% : 0.000013s : 21: predicate.row_tensor_eliminate 0.42% : 0.000008s : 42: predicate.same_eliminate 0.24% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.38% : 0.000007s : 43: predicate.shard_identity_eliminate 0.35% : 0.000006s : 42: predicate.special_op_eliminate 0.65% : 0.000012s : 70: predicate.specialize_transform 0.44% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.41% : 0.000008s : 43: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.99% : 0.000037s : 217: predicate.switch_defer_inline 2.57% : 0.000047s : 259: predicate.switch_layer_defer_inline 6.65% : 0.000122s : 678: predicate.switch_simplify 1.08% : 0.000020s : 131: predicate.tile_eliminate 1.05% : 0.000019s : 131: predicate.transpose_eliminate 1.87% : 0.000034s : 173: predicate.tuple_list_convert_item_index_to_positive 1.86% : 0.000034s : 173: predicate.tuple_list_get_item_const_eliminator 1.74% : 0.000032s : 173: predicate.tuple_list_get_item_depend_reorder 3.03% : 0.000056s : 256: predicate.tuple_list_get_item_eliminator 1.72% : 0.000031s : 173: predicate.tuple_list_get_set_item_eliminator 2.38% : 0.000044s : 243: predicate.tuple_list_set_item_eliminator 1.52% : 0.000028s : 186: predicate.tuple_to_list_eliminator_ 2.51% : 0.000046s : 319: predicate.updatestate_pure_node_eliminater 3.12% : 0.000057s : 389: predicate.updatestate_useless_node_eliminater 0.18% : 0.000003s : 21: predicate.value_based_eliminate 0.42% : 0.000008s : 43: predicate.virtual_dataset_eliminate 0.37% : 0.000007s : 43: predicate.virtual_output_eliminate 0.16% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.23% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.014493 133 60.28% : 0.008736s : 53: func_graph_cloner_run.FuncGraphClonerGraph 39.72% : 0.005757s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.018454 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.44% : 0.008954s : 1: add_attr 0.44% : 0.008933s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000207s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.05% : 0.000916s : 1: auto_monad 0.00% : 0.000098s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000675s : 1: bootstrap 0.00% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000052s : 1: control_data_broadcast_order 0.00% : 0.000043s : 1: convert_after_rewriter 0.00% : 0.000095s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000045s : 1: environ_conv 0.01% : 0.000242s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000067s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000012s : 1: label_micro_interleaved_index 0.04% : 0.000886s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000863s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000046s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000050s : 1: opt.transform.mutable_eliminate 1.53% : 0.030963s : 95: opt.transform.opt_a 0.01% : 0.000201s : 1: opt.transform.opt_after_cconv 0.01% : 0.000101s : 1: opt.transform.opt_after_jit_grad 4.40% : 0.088729s : 28: opt.transform.opt_b 0.01% : 0.000275s : 2: opt.transform.opt_trans_graph 0.01% : 0.000213s : 4: opt.transform.symbol_engine_opt 2.26% : 0.045647s : 1: opt_a 0.02% : 0.000452s : 1: opt_after_cconv 0.06% : 0.001119s : 1: opt_after_jit_grad 4.42% : 0.089176s : 1: opt_b 8.92% : 0.180042s : 1: optimize 0.00% : 0.000066s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000084s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000031s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 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% : 0.000269s : 1: pre_auto_parallel 1.93% : 0.038873s : 1: py_interpret_to_execute 0.00% : 0.000046s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000143s : 1: remove_dup_value 0.31% : 0.006288s : 1: renormalize.infer 0.29% : 0.005851s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000969s : 1: rewriter_after_opt_a 0.05% : 0.001035s : 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% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000629s : 1: symbol_engine_optimizer 0.02% : 0.000318s : 1: tuple_transform 74.53% : 1.504407s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape0-16] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape0-16],max_mem:274.0M [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:39:08.662.731 [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 = 1.35929, [21] [bootstrap]: 0.00065522 [type_inference]: 1.24136 [event_method]: 0.00022118 [auto_monad]: 0.00088015 [graph_reusing]: 5.885e-05 [inline]: 4.47e-06 [add_attr]: 0.00636392, [1] [add_attr_with_inline]: 0.00634252, [1] [Cycle 1]: 0.00033444, [2] [tag_attr]: 0.00021974 [meta_addattr_fg_expand]: 5.377e-05 [parallel-infer-symbol]: 4.06001e-06 [pre_auto_parallel]: 0.00027309 [insert-virtual-dataset]: 2.93e-06 [parallel-infer-symbol-second]: 9.79984e-07 [dataset_repeat_opt]: 2.57001e-06 [pipeline_split]: 1.86e-06 [optimize]: 0.107795, [53] [py_interpret_to_execute]: 0.00024816 [rewriter_before_opt_a]: 0.00087657 [opt_a]: 0.0906783, [2] [Cycle 1]: 0.0879485, [45] [expand_dump_flag]: 2.823e-05 [switch_simplify]: 0.0008211 [loop_unroll]: 0.00031831 [a_1]: 0.0654093 [with_stream_mark]: 7.612e-05 [recompute_prepare]: 4.93e-05 [updatestate_depend_eliminate]: 2.387e-05 [updatestate_assign_eliminate]: 2.349e-05 [updatestate_loads_eliminate]: 0.00010224 [parameter_eliminate]: 3.4e-06 [a_2]: 0.00103256 [accelerated_algorithm]: 8.769e-05 [shard]: 3.04999e-06 [meta_shard_fg_expand]: 3.05e-05 [shard_inline]: 2.904e-05 [merge_send_recv]: 2.314e-05 [auto_parallel]: 2.609e-05 [parallel]: 4.885e-05 [flash_sp]: 1.973e-05 [merge_comm]: 1.777e-05 [allreduce_fusion]: 1.48e-05 [matmul_add_comm_reduction]: 2.876e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 3.238e-05 [virtual_dataset]: 2.643e-05 [get_grad_eliminate_]: 2.571e-05 [virtual_output]: 2.659e-05 [merge_forward]: 1.69e-05 [cell_reuse_recompute_pass]: 3.62998e-06 [offload_activation]: 2.866e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.82e-05 [merge_recompute_call_nodes]: 2.06e-06 [before_grad]: 4.778e-05 [set_forward_comm_id_for_comm_node_pass]: 1.818e-05 [meta_fg_expand]: 2.166e-05 [flash_sp_send_recv_attached]: 8.28999e-06 [receive_attached]: 3.01999e-06 [after_resolve]: 3.754e-05 [a_after_grad]: 4.46e-05 [renormalize]: 0.0179185 [add_forward_monad_depend]: 1.73e-05 [auto_monad_grad]: 4.1e-06 [auto_monad_eliminator]: 0.00011451 [cse]: 0.00046787 [a_3]: 0.00027018 [Cycle 2]: 0.00270692, [45] [expand_dump_flag]: 4.53999e-06 [switch_simplify]: 3.598e-05 [loop_unroll]: 2.62e-05 [a_1]: 0.00087234 [with_stream_mark]: 4.084e-05 [recompute_prepare]: 3.1e-05 [updatestate_depend_eliminate]: 1.673e-05 [updatestate_assign_eliminate]: 1.594e-05 [updatestate_loads_eliminate]: 2.054e-05 [parameter_eliminate]: 2.93e-06 [a_2]: 0.00039677 [accelerated_algorithm]: 3.958e-05 [shard]: 3.63999e-06 [meta_shard_fg_expand]: 9.39e-06 [shard_inline]: 2.548e-05 [merge_send_recv]: 2.392e-05 [auto_parallel]: 2.303e-05 [parallel]: 1.235e-05 [flash_sp]: 5.57999e-06 [merge_comm]: 1.652e-05 [allreduce_fusion]: 1.599e-05 [matmul_add_comm_reduction]: 2.849e-05 [allreduce_slice_to_reducescatter]: 9.99979e-07 [virtual_shard_identity]: 3.162e-05 [virtual_dataset]: 2.531e-05 [get_grad_eliminate_]: 2.511e-05 [virtual_output]: 2.726e-05 [merge_forward]: 1.631e-05 [cell_reuse_recompute_pass]: 4.33999e-06 [offload_activation]: 2.671e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.743e-05 [merge_recompute_call_nodes]: 1.81e-06 [before_grad]: 4.603e-05 [set_forward_comm_id_for_comm_node_pass]: 1.726e-05 [meta_fg_expand]: 1.24e-05 [flash_sp_send_recv_attached]: 2.24999e-06 [receive_attached]: 2.45002e-06 [after_resolve]: 3.522e-05 [a_after_grad]: 4.102e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 6.02999e-06 [auto_monad_grad]: 3.63e-06 [auto_monad_eliminator]: 7.862e-05 [cse]: 0.00010378 [a_3]: 0.00017059 [py_interpret_to_execute_after_opt_a]: 4.451e-05 [slice_cell_reuse_recomputed_activation]: 2.58e-06 [rewriter_after_opt_a]: 0.00098926 [convert_after_rewriter]: 4.038e-05 [order_py_execute_after_rewriter]: 1.515e-05 [mutable_eliminate]: 0.00090233 [opt_b]: 0.00095619, [1] [Cycle 1]: 0.00094592, [7] [b_1]: 0.00066697 [b_2]: 3.48e-05 [updatestate_depend_eliminate]: 2.281e-05 [updatestate_assign_eliminate]: 1.564e-05 [updatestate_loads_eliminate]: 2.276e-05 [renormalize]: 8.59989e-07 [cse]: 0.00011891 [optimize_parallel_all_gather_comm]: 5.42e-05 [overlap_param_gather]: 2.61e-06 [cconv]: 5.083e-05 [loop_unroll]: 0.0103562 [opt_after_cconv]: 0.00050024, [1] [Cycle 1]: 0.00048745, [7] [c_1]: 0.00022964 [parameter_eliminate]: 8.77999e-06 [updatestate_depend_eliminate]: 2.996e-05 [updatestate_assign_eliminate]: 1.544e-05 [updatestate_loads_eliminate]: 2.183e-05 [cse]: 0.00013203 [renormalize]: 1.12e-06 [remove_dup_value]: 0.00013446 [tuple_transform]: 0.0003239, [1] [Cycle 1]: 0.00031668, [4] [d_1]: 0.00025426 [none_parameter_eliminate]: 3.98999e-06 [renormalize]: 1.20024e-07 [switch_simplify]: 2.806e-05 [partial_unused_args_eliminate]: 2.82002e-06 [add_recomputation]: 0.00020445 [cse_after_recomputation]: 9.262e-05, [1] [Cycle 1]: 8.511e-05, [1] [cse]: 7.296e-05 [environ_conv]: 3.316e-05 [swap_dp_allreduce_reducescatter]: 2.429e-05 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 8.69e-06 [label_fine_grained_interleaved_index]: 3.81999e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.59001e-06 [micro_interleaved_order_control]: 2.98998e-06 [assign_add_opt]: 1.45999e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 1.15001e-06 [full_micro_interleaved_order_control]: 2.54001e-06 [reorder_send_recv_between_fp_bp]: 3.25e-06 [comm_op_add_attrs]: 1.47001e-06 [add_comm_op_reuse_tag]: 1.00999e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 2.63e-06 [overlap_opt_shard_grad_in_pipeline]: 2.07999e-06 [control_data_broadcast_order]: 4.85e-05 [grouped_pairwise_exchange_alltoall]: 1.71e-06 [offloading_packed_experts]: 1.4e-05 [overlap_recompute_and_grad_model_parallel]: 1.301e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.21002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40999e-06 [overlap_recompute_comm]: 2.59999e-06 [overlap_grad_ring_attention]: 1.06e-05 [overlap_grad_flash_sp]: 6.594e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.53e-06 [split_layernorm_comm]: 2.37999e-06 [handle_group_info]: 1.66002e-06 [symbol_engine_optimizer]: 0.0006668, [1] [Cycle 1]: 0.00065814, [6] [build]: 0.00035946 [elim_shapecalc]: 4.969e-05 [elim_not_effective]: 6.919e-05 [opt_reshape]: 4.067e-05 [fold_const_symbol]: 7.209e-05 [renormalize]: 2.30008e-07 [detach_backward]: 4.77998e-06 [pipeline_parallel_scheduler]: 2.53e-06 [auto_monad_reorder]: 9.406e-05 [get_jit_bprop_graph]: 2.88e-06 [rewriter_after_jit_bprop_graph]: 7.78001e-06 [opt_after_jit_grad]: 0.00104749 [validate]: 0.00022834 Sums bootstrap : 0.000655s : 0.05% type_inference : 1.241362s : 91.86% event_method : 0.000221s : 0.02% auto_monad : 0.000880s : 0.07% graph_reusing : 0.000059s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000220s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000054s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000273s : 0.02% 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 : 0.000248s : 0.02% optimize.rewriter_before_opt_a : 0.000877s : 0.06% optimize.opt_a.expand_dump_flag : 0.000033s : 0.00% optimize.opt_a.switch_simplify : 0.000857s : 0.06% optimize.opt_a.loop_unroll : 0.000345s : 0.03% optimize.opt_a.a_1 : 0.066282s : 4.90% optimize.opt_a.with_stream_mark : 0.000117s : 0.01% optimize.opt_a.recompute_prepare : 0.000080s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000041s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000039s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000123s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001429s : 0.11% optimize.opt_a.accelerated_algorithm : 0.000127s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000040s : 0.00% optimize.opt_a.shard_inline : 0.000055s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000049s : 0.00% optimize.opt_a.parallel : 0.000061s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000034s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000057s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000064s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000051s : 0.00% optimize.opt_a.virtual_output : 0.000054s : 0.00% optimize.opt_a.merge_forward : 0.000033s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000055s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000116s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000094s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000035s : 0.00% optimize.opt_a.meta_fg_expand : 0.000034s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000073s : 0.01% optimize.opt_a.a_after_grad : 0.000086s : 0.01% optimize.opt_a.renormalize : 0.017919s : 1.33% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000008s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000193s : 0.01% optimize.opt_a.cse : 0.000572s : 0.04% optimize.opt_a.a_3 : 0.000441s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000045s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000989s : 0.07% optimize.convert_after_rewriter : 0.000040s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000902s : 0.07% optimize.opt_b.b_1 : 0.000667s : 0.05% optimize.opt_b.b_2 : 0.000035s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000023s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000119s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000054s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000051s : 0.00% optimize.loop_unroll : 0.010356s : 0.77% optimize.opt_after_cconv.c_1 : 0.000230s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000030s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_after_cconv.cse : 0.000132s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000134s : 0.01% optimize.tuple_transform.d_1 : 0.000254s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000004s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000028s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000204s : 0.02% optimize.cse_after_recomputation.cse : 0.000073s : 0.01% optimize.environ_conv : 0.000033s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000024s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000004s : 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 : 0.000048s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000014s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000066s : 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000359s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000050s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000069s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000041s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000072s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000003s : 0.00% auto_monad_reorder : 0.000094s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.001047s : 0.08% validate : 0.000228s : 0.02% Time group info: ------[substitution.] 0.017985 612 0.32% : 0.000057s : 5: substitution.arithmetic_simplify 0.11% : 0.000019s : 8: substitution.depend_value_elim 0.10% : 0.000019s : 17: substitution.elim_not_effective 0.12% : 0.000021s : 12: substitution.float_tuple_getitem_switch 0.19% : 0.000033s : 17: substitution.fold_const_symbol 0.11% : 0.000020s : 21: substitution.graph_param_transform 91.59% : 0.016472s : 71: substitution.inline 0.10% : 0.000018s : 35: substitution.j_node_and_user_rematch 0.26% : 0.000047s : 10: substitution.less_batch_normalization 0.50% : 0.000090s : 2: substitution.list_to_tuple_eliminator_ 0.06% : 0.000011s : 12: substitution.load_eliminater 0.22% : 0.000039s : 21: substitution.minmaximum_grad 0.05% : 0.000009s : 2: substitution.opt_reshape 0.13% : 0.000023s : 35: substitution.remove_not_recompute_node 0.06% : 0.000011s : 6: substitution.replace_old_param 0.40% : 0.000072s : 18: substitution.reshape_eliminate 0.28% : 0.000050s : 24: substitution.switch_simplify 1.02% : 0.000184s : 51: substitution.tuple_list_convert_item_index_to_positive 0.60% : 0.000107s : 51: substitution.tuple_list_get_item_const_eliminator 0.77% : 0.000139s : 51: substitution.tuple_list_get_item_depend_reorder 1.44% : 0.000260s : 73: substitution.tuple_list_get_item_eliminator 0.73% : 0.000131s : 51: substitution.tuple_list_get_set_item_eliminator 0.13% : 0.000024s : 8: substitution.updatestate_pure_node_eliminater 0.73% : 0.000131s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.240905 2 91.30% : 1.132989s : 1: type_inference.infer 8.70% : 0.107916s : 1: type_inference.specialize ------[replace.] 0.001373 115 3.30% : 0.000045s : 5: replace.depend_value_elim 60.13% : 0.000825s : 71: replace.inline 4.25% : 0.000058s : 2: replace.list_to_tuple_eliminator_ 23.29% : 0.000320s : 24: replace.switch_simplify 9.03% : 0.000124s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.016585 115 0.01% : 0.000002s : 5: match.depend_value_elim 99.00% : 0.016420s : 71: match.inline 0.52% : 0.000087s : 2: match.list_to_tuple_eliminator_ 0.22% : 0.000036s : 24: match.switch_simplify 0.24% : 0.000040s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001922 10672 1.20% : 0.000023s : 131: predicate.accumulaten_eliminater 0.53% : 0.000010s : 21: predicate.ad_related_special_op_eliminate 0.51% : 0.000010s : 70: predicate.addn_check_dump 1.15% : 0.000022s : 131: predicate.addn_zero_filter 0.99% : 0.000019s : 131: predicate.adjust_all_reduce_mul_add 2.38% : 0.000046s : 201: predicate.arithmetic_simplify 1.14% : 0.000022s : 131: predicate.cast_eliminate 0.32% : 0.000006s : 42: predicate.check_bprop_eliminate 0.49% : 0.000009s : 70: predicate.compare_switch_simplify 0.09% : 0.000002s : 21: predicate.const_output_eliminate 0.60% : 0.000012s : 73: predicate.depend_value_elim 1.14% : 0.000022s : 131: predicate.dict_get_item_const_eliminator 1.18% : 0.000023s : 131: predicate.dict_get_item_eliminator 1.22% : 0.000023s : 131: predicate.dict_set_item_eliminator 0.48% : 0.000009s : 42: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 21: predicate.elim_not_effective 0.32% : 0.000006s : 21: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000024s : 152: predicate.environ_add_const_eliminate 1.12% : 0.000021s : 152: predicate.environ_get_add_eliminate 1.12% : 0.000021s : 152: predicate.environ_get_depend_swap 1.74% : 0.000034s : 222: predicate.environ_get_eliminate 1.17% : 0.000023s : 152: predicate.environ_get_set_eliminate 1.72% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.61% : 0.000050s : 217: predicate.float_depend_g_call 0.52% : 0.000010s : 70: predicate.float_environ_get_switch 0.76% : 0.000015s : 91: predicate.float_tuple_getitem_switch 0.08% : 0.000002s : 21: predicate.fold_const_symbol 0.41% : 0.000008s : 43: predicate.get_grad_eliminate 0.09% : 0.000002s : 21: predicate.graph_param_transform 0.54% : 0.000010s : 70: predicate.incorporate_call 0.47% : 0.000009s : 70: predicate.incorporate_call_switch 5.60% : 0.000108s : 503: predicate.inline 0.51% : 0.000010s : 43: predicate.inline_without_move 0.15% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.49% : 0.000009s : 43: predicate.less_batch_normalization 1.57% : 0.000030s : 188: predicate.list_to_tuple_eliminator_ 2.36% : 0.000045s : 319: predicate.load_eliminater 4.08% : 0.000078s : 21: predicate.loop_unroll_after_grad 3.02% : 0.000058s : 322: predicate.loop_unroll_before_grad 1.58% : 0.000030s : 173: predicate.make_slice_get_slice_eliminator 0.53% : 0.000010s : 70: predicate.merge_addn 0.33% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.34% : 0.000006s : 42: predicate.mini_step_allgather_replace 0.99% : 0.000019s : 131: predicate.minmaximum_grad 0.53% : 0.000010s : 21: predicate.mutable_eliminate 0.23% : 0.000004s : 21: predicate.opt_reshape 0.17% : 0.000003s : 21: predicate.parallel_virtual_node 3.50% : 0.000067s : 217: predicate.partial_defer_inline 1.40% : 0.000027s : 167: predicate.partial_eliminate 1.10% : 0.000021s : 131: predicate.print_const_string_wrapper 0.53% : 0.000010s : 65: predicate.reduce_all_const_elim 1.36% : 0.000026s : 131: predicate.reduce_eliminate 2.69% : 0.000052s : 319: predicate.redundant_stop_gradient_eliminater 0.21% : 0.000004s : 43: predicate.remove_not_recompute_node 1.03% : 0.000020s : 188: predicate.replace_applicator 0.18% : 0.000004s : 43: predicate.replace_old_param 0.11% : 0.000002s : 21: predicate.reset_defer_inline 1.18% : 0.000023s : 131: predicate.reshape_eliminate 0.31% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.22% : 0.000004s : 21: predicate.row_tensor_eliminate 0.54% : 0.000010s : 42: predicate.same_eliminate 0.24% : 0.000005s : 48: predicate.set_cell_output_no_recompute 0.38% : 0.000007s : 43: predicate.shard_identity_eliminate 0.34% : 0.000006s : 42: predicate.special_op_eliminate 0.66% : 0.000013s : 70: predicate.specialize_transform 0.41% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.45% : 0.000009s : 43: predicate.stack_unstack_eliminate 0.19% : 0.000004s : 21: predicate.switch_call_monad_eliminater 1.91% : 0.000037s : 217: predicate.switch_defer_inline 2.34% : 0.000045s : 259: predicate.switch_layer_defer_inline 6.35% : 0.000122s : 678: predicate.switch_simplify 1.17% : 0.000023s : 131: predicate.tile_eliminate 1.00% : 0.000019s : 131: predicate.transpose_eliminate 1.76% : 0.000034s : 173: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000033s : 173: predicate.tuple_list_get_item_const_eliminator 1.51% : 0.000029s : 173: predicate.tuple_list_get_item_depend_reorder 2.97% : 0.000057s : 256: predicate.tuple_list_get_item_eliminator 1.64% : 0.000032s : 173: predicate.tuple_list_get_set_item_eliminator 2.16% : 0.000042s : 243: predicate.tuple_list_set_item_eliminator 1.49% : 0.000029s : 186: predicate.tuple_to_list_eliminator_ 2.44% : 0.000047s : 319: predicate.updatestate_pure_node_eliminater 3.23% : 0.000062s : 389: predicate.updatestate_useless_node_eliminater 0.19% : 0.000004s : 21: predicate.value_based_eliminate 0.37% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.41% : 0.000008s : 43: predicate.virtual_output_eliminate 0.14% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.22% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.051810 133 86.33% : 0.044729s : 53: func_graph_cloner_run.FuncGraphClonerGraph 13.67% : 0.007081s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.562734 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.41% : 0.006372s : 1: add_attr 0.41% : 0.006348s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000215s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.06% : 0.000902s : 1: auto_monad 0.01% : 0.000103s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000691s : 1: bootstrap 0.00% : 0.000056s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000054s : 1: control_data_broadcast_order 0.00% : 0.000049s : 1: convert_after_rewriter 0.01% : 0.000096s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000039s : 1: environ_conv 0.02% : 0.000237s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000067s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000012s : 1: label_micro_interleaved_index 0.66% : 0.010388s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.06% : 0.000921s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.01% : 0.000150s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000057s : 1: opt.transform.mutable_eliminate 4.48% : 0.070021s : 95: opt.transform.opt_a 0.01% : 0.000228s : 1: opt.transform.opt_after_cconv 0.01% : 0.000163s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000655s : 28: opt.transform.opt_b 0.02% : 0.000278s : 2: opt.transform.opt_trans_graph 0.01% : 0.000223s : 4: opt.transform.symbol_engine_opt 5.80% : 0.090684s : 1: opt_a 0.03% : 0.000506s : 1: opt_after_cconv 0.07% : 0.001071s : 1: opt_after_jit_grad 0.06% : 0.000961s : 1: opt_b 6.90% : 0.107803s : 1: optimize 0.00% : 0.000062s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.00% : 0.000076s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 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% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000282s : 1: pre_auto_parallel 0.02% : 0.000257s : 1: py_interpret_to_execute 0.00% : 0.000051s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000142s : 1: remove_dup_value 0.48% : 0.007567s : 1: renormalize.infer 0.66% : 0.010327s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.001010s : 1: rewriter_after_opt_a 0.06% : 0.000892s : 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% : 0.000028s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000671s : 1: symbol_engine_optimizer 0.02% : 0.000328s : 1: tuple_transform 79.44% : 1.241408s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape0-256] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape0-256],max_mem:306.0M [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:40:17.859.940 [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 = 3.095, [21] [bootstrap]: 0.0008352 [type_inference]: 2.50128 [event_method]: 0.0002147 [auto_monad]: 0.00080896 [graph_reusing]: 5.514e-05 [inline]: 3.33e-06 [add_attr]: 0.188345, [1] [add_attr_with_inline]: 0.18832, [1] [Cycle 1]: 0.18308, [2] [tag_attr]: 0.00022878 [meta_addattr_fg_expand]: 0.182734 [parallel-infer-symbol]: 7.33999e-06 [pre_auto_parallel]: 0.00043512 [insert-virtual-dataset]: 3.55e-06 [parallel-infer-symbol-second]: 1.85001e-06 [dataset_repeat_opt]: 3.8e-06 [pipeline_split]: 1.81998e-06 [optimize]: 0.401827, [53] [py_interpret_to_execute]: 0.00033437 [rewriter_before_opt_a]: 0.00089815 [opt_a]: 0.235542, [2] [Cycle 1]: 0.232496, [45] [expand_dump_flag]: 2.515e-05 [switch_simplify]: 0.00090202 [loop_unroll]: 0.00031473 [a_1]: 0.0144398 [with_stream_mark]: 7.395e-05 [recompute_prepare]: 5.368e-05 [updatestate_depend_eliminate]: 2.554e-05 [updatestate_assign_eliminate]: 2.195e-05 [updatestate_loads_eliminate]: 0.00010452 [parameter_eliminate]: 4.18999e-06 [a_2]: 0.00097474 [accelerated_algorithm]: 8.127e-05 [shard]: 2.24001e-06 [meta_shard_fg_expand]: 3.048e-05 [shard_inline]: 2.787e-05 [merge_send_recv]: 2.337e-05 [auto_parallel]: 2.307e-05 [parallel]: 4.763e-05 [flash_sp]: 1.815e-05 [merge_comm]: 1.774e-05 [allreduce_fusion]: 1.526e-05 [matmul_add_comm_reduction]: 2.635e-05 [allreduce_slice_to_reducescatter]: 1.30001e-06 [virtual_shard_identity]: 3.152e-05 [virtual_dataset]: 2.481e-05 [get_grad_eliminate_]: 2.478e-05 [virtual_output]: 2.639e-05 [merge_forward]: 1.525e-05 [cell_reuse_recompute_pass]: 2.36e-06 [offload_activation]: 2.728e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.47e-05 [merge_recompute_call_nodes]: 2.23998e-06 [before_grad]: 4.678e-05 [set_forward_comm_id_for_comm_node_pass]: 1.697e-05 [meta_fg_expand]: 2.145e-05 [flash_sp_send_recv_attached]: 6.96999e-06 [receive_attached]: 2.66e-06 [after_resolve]: 3.387e-05 [a_after_grad]: 4.223e-05 [renormalize]: 0.213521 [add_forward_monad_depend]: 1.541e-05 [auto_monad_grad]: 4.08001e-06 [auto_monad_eliminator]: 0.00011341 [cse]: 0.00042318 [a_3]: 0.00020426 [Cycle 2]: 0.00302041, [45] [expand_dump_flag]: 3.36001e-06 [switch_simplify]: 2.941e-05 [loop_unroll]: 2.484e-05 [a_1]: 0.00097633 [with_stream_mark]: 3.817e-05 [recompute_prepare]: 2.881e-05 [updatestate_depend_eliminate]: 1.751e-05 [updatestate_assign_eliminate]: 1.658e-05 [updatestate_loads_eliminate]: 2.025e-05 [parameter_eliminate]: 2.82002e-06 [a_2]: 0.00056881 [accelerated_algorithm]: 4.514e-05 [shard]: 2.47001e-06 [meta_shard_fg_expand]: 9.25999e-06 [shard_inline]: 2.561e-05 [merge_send_recv]: 2.72e-05 [auto_parallel]: 2.38e-05 [parallel]: 1.277e-05 [flash_sp]: 5.52001e-06 [merge_comm]: 1.6e-05 [allreduce_fusion]: 1.528e-05 [matmul_add_comm_reduction]: 2.905e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.718e-05 [virtual_dataset]: 2.467e-05 [get_grad_eliminate_]: 2.384e-05 [virtual_output]: 2.404e-05 [merge_forward]: 1.429e-05 [cell_reuse_recompute_pass]: 3.22002e-06 [offload_activation]: 2.913e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.999e-05 [merge_recompute_call_nodes]: 1.66002e-06 [before_grad]: 4.254e-05 [set_forward_comm_id_for_comm_node_pass]: 1.614e-05 [meta_fg_expand]: 1.168e-05 [flash_sp_send_recv_attached]: 2.19001e-06 [receive_attached]: 2.54001e-06 [after_resolve]: 3.661e-05 [a_after_grad]: 3.991e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 6.58e-06 [auto_monad_grad]: 3.4e-06 [auto_monad_eliminator]: 7.957e-05 [cse]: 0.0001113 [a_3]: 0.00022699 [py_interpret_to_execute_after_opt_a]: 4.564e-05 [slice_cell_reuse_recomputed_activation]: 3.51999e-06 [rewriter_after_opt_a]: 0.00099331 [convert_after_rewriter]: 3.383e-05 [order_py_execute_after_rewriter]: 1.547e-05 [mutable_eliminate]: 0.00088564 [opt_b]: 0.159867, [1] [Cycle 1]: 0.159855, [7] [b_1]: 0.159431 [b_2]: 5.357e-05 [updatestate_depend_eliminate]: 3.111e-05 [updatestate_assign_eliminate]: 2.808e-05 [updatestate_loads_eliminate]: 2.284e-05 [renormalize]: 1.10001e-06 [cse]: 0.00015411 [optimize_parallel_all_gather_comm]: 5.668e-05 [overlap_param_gather]: 3.42002e-06 [cconv]: 5.032e-05 [loop_unroll]: 0.00085457 [opt_after_cconv]: 0.00036299, [1] [Cycle 1]: 0.00035255, [7] [c_1]: 0.00016241 [parameter_eliminate]: 6.23998e-06 [updatestate_depend_eliminate]: 2.017e-05 [updatestate_assign_eliminate]: 1.396e-05 [updatestate_loads_eliminate]: 1.639e-05 [cse]: 8.997e-05 [renormalize]: 5.79981e-07 [remove_dup_value]: 0.00012968 [tuple_transform]: 0.00029369, [1] [Cycle 1]: 0.00028687, [4] [d_1]: 0.00023609 [none_parameter_eliminate]: 2.34001e-06 [renormalize]: 2.30008e-07 [switch_simplify]: 2.485e-05 [partial_unused_args_eliminate]: 2.78e-06 [add_recomputation]: 0.00020635 [cse_after_recomputation]: 8.06e-05, [1] [Cycle 1]: 7.327e-05, [1] [cse]: 6.565e-05 [environ_conv]: 3.167e-05 [swap_dp_allreduce_reducescatter]: 2.258e-05 [bias_add_comm_swap]: 3.58e-06 [label_micro_interleaved_index]: 6.78e-06 [label_fine_grained_interleaved_index]: 3.06001e-06 [merge_cast_opt]: 1.65001e-06 [slice_recompute_activation]: 2.59001e-06 [micro_interleaved_order_control]: 2.39001e-06 [assign_add_opt]: 1.31998e-06 [ForceFp32Comm]: 8.89995e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.41e-06 [reorder_send_recv_between_fp_bp]: 2.93998e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.27999e-06 [interleave_parallel_branches]: 1.12e-06 [overlap_opt_shard_in_pipeline]: 2.36998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.21e-06 [control_data_broadcast_order]: 4.265e-05 [grouped_pairwise_exchange_alltoall]: 1.63002e-06 [offloading_packed_experts]: 1.323e-05 [overlap_recompute_and_grad_model_parallel]: 1.12e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.77001e-06 [overlap_recompute_comm]: 2.30002e-06 [overlap_grad_ring_attention]: 1.039e-05 [overlap_grad_flash_sp]: 6.026e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.93998e-06 [split_layernorm_comm]: 1.76998e-06 [handle_group_info]: 1.29e-06 [symbol_engine_optimizer]: 0.00058371, [1] [Cycle 1]: 0.00057722, [6] [build]: 0.00033343 [elim_shapecalc]: 3.641e-05 [elim_not_effective]: 5.986e-05 [opt_reshape]: 3.767e-05 [fold_const_symbol]: 6.455e-05 [renormalize]: 3.00002e-07 [detach_backward]: 4.50001e-06 [pipeline_parallel_scheduler]: 1.56002e-06 [auto_monad_reorder]: 7.86e-05 [get_jit_bprop_graph]: 2.52001e-06 [rewriter_after_jit_bprop_graph]: 6.41e-06 [opt_after_jit_grad]: 0.00070608 [validate]: 0.0001174 Sums bootstrap : 0.000835s : 0.03% type_inference : 2.501278s : 81.00% event_method : 0.000215s : 0.01% auto_monad : 0.000809s : 0.03% graph_reusing : 0.000055s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000229s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.182734s : 5.92% parallel-infer-symbol : 0.000007s : 0.00% pre_auto_parallel : 0.000435s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000004s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000334s : 0.01% optimize.rewriter_before_opt_a : 0.000898s : 0.03% optimize.opt_a.expand_dump_flag : 0.000029s : 0.00% optimize.opt_a.switch_simplify : 0.000931s : 0.03% optimize.opt_a.loop_unroll : 0.000340s : 0.01% optimize.opt_a.a_1 : 0.015416s : 0.50% optimize.opt_a.with_stream_mark : 0.000112s : 0.00% optimize.opt_a.recompute_prepare : 0.000082s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000039s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000125s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001544s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000126s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000040s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000051s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000060s : 0.00% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000034s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000055s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000059s : 0.00% optimize.opt_a.virtual_dataset : 0.000049s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000049s : 0.00% optimize.opt_a.virtual_output : 0.000050s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000056s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000105s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000089s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000033s : 0.00% optimize.opt_a.meta_fg_expand : 0.000033s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.00% optimize.opt_a.a_after_grad : 0.000082s : 0.00% optimize.opt_a.renormalize : 0.213521s : 6.91% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000193s : 0.01% optimize.opt_a.cse : 0.000534s : 0.02% optimize.opt_a.a_3 : 0.000431s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000046s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000993s : 0.03% optimize.convert_after_rewriter : 0.000034s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000886s : 0.03% optimize.opt_b.b_1 : 0.159431s : 5.16% optimize.opt_b.b_2 : 0.000054s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000031s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000028s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000023s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000154s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000057s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000050s : 0.00% optimize.loop_unroll : 0.000855s : 0.03% optimize.opt_after_cconv.c_1 : 0.000162s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_after_cconv.cse : 0.000090s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000130s : 0.00% optimize.tuple_transform.d_1 : 0.000236s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000206s : 0.01% optimize.cse_after_recomputation.cse : 0.000066s : 0.00% optimize.environ_conv : 0.000032s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000023s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000043s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 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 : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000060s : 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 : 0.000333s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000036s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000060s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000038s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000065s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000079s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000706s : 0.02% validate : 0.000117s : 0.00% Time group info: ------[substitution.] 0.007388 612 0.81% : 0.000060s : 5: substitution.arithmetic_simplify 0.25% : 0.000019s : 8: substitution.depend_value_elim 0.23% : 0.000017s : 17: substitution.elim_not_effective 0.28% : 0.000021s : 12: substitution.float_tuple_getitem_switch 0.39% : 0.000029s : 17: substitution.fold_const_symbol 0.23% : 0.000017s : 21: substitution.graph_param_transform 79.83% : 0.005898s : 71: substitution.inline 0.25% : 0.000018s : 35: substitution.j_node_and_user_rematch 0.59% : 0.000044s : 10: substitution.less_batch_normalization 0.94% : 0.000069s : 2: substitution.list_to_tuple_eliminator_ 0.15% : 0.000011s : 12: substitution.load_eliminater 0.48% : 0.000036s : 21: substitution.minmaximum_grad 0.11% : 0.000008s : 2: substitution.opt_reshape 0.30% : 0.000022s : 35: substitution.remove_not_recompute_node 0.14% : 0.000011s : 6: substitution.replace_old_param 1.01% : 0.000074s : 18: substitution.reshape_eliminate 0.72% : 0.000053s : 24: substitution.switch_simplify 2.44% : 0.000180s : 51: substitution.tuple_list_convert_item_index_to_positive 1.35% : 0.000100s : 51: substitution.tuple_list_get_item_const_eliminator 1.77% : 0.000131s : 51: substitution.tuple_list_get_item_depend_reorder 4.18% : 0.000309s : 73: substitution.tuple_list_get_item_eliminator 1.69% : 0.000125s : 51: substitution.tuple_list_get_set_item_eliminator 0.32% : 0.000024s : 8: substitution.updatestate_pure_node_eliminater 1.54% : 0.000114s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.500867 2 98.53% : 2.464142s : 1: type_inference.infer 1.47% : 0.036725s : 1: type_inference.specialize ------[replace.] 0.001523 115 3.27% : 0.000050s : 5: replace.depend_value_elim 62.77% : 0.000956s : 71: replace.inline 3.43% : 0.000052s : 2: replace.list_to_tuple_eliminator_ 22.58% : 0.000344s : 24: replace.switch_simplify 7.96% : 0.000121s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.006030 115 0.04% : 0.000002s : 5: match.depend_value_elim 96.80% : 0.005837s : 71: match.inline 1.09% : 0.000066s : 2: match.list_to_tuple_eliminator_ 0.64% : 0.000038s : 24: match.switch_simplify 1.43% : 0.000086s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001985 10672 1.00% : 0.000020s : 131: predicate.accumulaten_eliminater 0.32% : 0.000006s : 21: predicate.ad_related_special_op_eliminate 0.50% : 0.000010s : 70: predicate.addn_check_dump 1.05% : 0.000021s : 131: predicate.addn_zero_filter 1.00% : 0.000020s : 131: predicate.adjust_all_reduce_mul_add 2.16% : 0.000043s : 201: predicate.arithmetic_simplify 0.98% : 0.000019s : 131: predicate.cast_eliminate 0.34% : 0.000007s : 42: predicate.check_bprop_eliminate 0.49% : 0.000010s : 70: predicate.compare_switch_simplify 0.08% : 0.000002s : 21: predicate.const_output_eliminate 0.60% : 0.000012s : 73: predicate.depend_value_elim 1.05% : 0.000021s : 131: predicate.dict_get_item_const_eliminator 1.18% : 0.000023s : 131: predicate.dict_get_item_eliminator 0.96% : 0.000019s : 131: predicate.dict_set_item_eliminator 0.35% : 0.000007s : 42: predicate.dumpgradient_eliminate 0.09% : 0.000002s : 21: predicate.elim_not_effective 0.17% : 0.000003s : 21: predicate.elim_shapecalc_of_broadcastargs 1.10% : 0.000022s : 152: predicate.environ_add_const_eliminate 1.07% : 0.000021s : 152: predicate.environ_get_add_eliminate 1.08% : 0.000022s : 152: predicate.environ_get_depend_swap 1.59% : 0.000032s : 222: predicate.environ_get_eliminate 1.10% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.60% : 0.000032s : 217: predicate.exchange_switch_depend_value 2.63% : 0.000052s : 217: predicate.float_depend_g_call 0.49% : 0.000010s : 70: predicate.float_environ_get_switch 0.70% : 0.000014s : 91: predicate.float_tuple_getitem_switch 0.08% : 0.000002s : 21: predicate.fold_const_symbol 0.36% : 0.000007s : 43: predicate.get_grad_eliminate 0.10% : 0.000002s : 21: predicate.graph_param_transform 0.51% : 0.000010s : 70: predicate.incorporate_call 0.47% : 0.000009s : 70: predicate.incorporate_call_switch 5.48% : 0.000109s : 503: predicate.inline 0.46% : 0.000009s : 43: predicate.inline_without_move 0.15% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.52% : 0.000010s : 43: predicate.less_batch_normalization 2.45% : 0.000049s : 188: predicate.list_to_tuple_eliminator_ 2.29% : 0.000045s : 319: predicate.load_eliminater 0.38% : 0.000008s : 21: predicate.loop_unroll_after_grad 2.81% : 0.000056s : 322: predicate.loop_unroll_before_grad 1.44% : 0.000029s : 173: predicate.make_slice_get_slice_eliminator 0.50% : 0.000010s : 70: predicate.merge_addn 0.32% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.33% : 0.000006s : 42: predicate.mini_step_allgather_replace 0.98% : 0.000019s : 131: predicate.minmaximum_grad 0.39% : 0.000008s : 21: predicate.mutable_eliminate 0.18% : 0.000004s : 21: predicate.opt_reshape 0.18% : 0.000004s : 21: predicate.parallel_virtual_node 5.71% : 0.000113s : 217: predicate.partial_defer_inline 1.34% : 0.000027s : 167: predicate.partial_eliminate 1.03% : 0.000020s : 131: predicate.print_const_string_wrapper 0.47% : 0.000009s : 65: predicate.reduce_all_const_elim 1.29% : 0.000026s : 131: predicate.reduce_eliminate 2.44% : 0.000048s : 319: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 43: predicate.remove_not_recompute_node 0.96% : 0.000019s : 188: predicate.replace_applicator 0.18% : 0.000004s : 43: predicate.replace_old_param 0.11% : 0.000002s : 21: predicate.reset_defer_inline 7.62% : 0.000151s : 131: predicate.reshape_eliminate 0.31% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.21% : 0.000004s : 21: predicate.row_tensor_eliminate 0.44% : 0.000009s : 42: predicate.same_eliminate 0.24% : 0.000005s : 48: predicate.set_cell_output_no_recompute 0.36% : 0.000007s : 43: predicate.shard_identity_eliminate 0.34% : 0.000007s : 42: predicate.special_op_eliminate 0.64% : 0.000013s : 70: predicate.specialize_transform 0.44% : 0.000009s : 42: predicate.split_environ_get_set_with_tuple_value 0.37% : 0.000007s : 43: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.89% : 0.000038s : 217: predicate.switch_defer_inline 2.06% : 0.000041s : 259: predicate.switch_layer_defer_inline 5.92% : 0.000118s : 678: predicate.switch_simplify 1.00% : 0.000020s : 131: predicate.tile_eliminate 0.95% : 0.000019s : 131: predicate.transpose_eliminate 1.53% : 0.000030s : 173: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000031s : 173: predicate.tuple_list_get_item_const_eliminator 1.45% : 0.000029s : 173: predicate.tuple_list_get_item_depend_reorder 2.99% : 0.000059s : 256: predicate.tuple_list_get_item_eliminator 1.71% : 0.000034s : 173: predicate.tuple_list_get_set_item_eliminator 2.11% : 0.000042s : 243: predicate.tuple_list_set_item_eliminator 1.62% : 0.000032s : 186: predicate.tuple_to_list_eliminator_ 2.28% : 0.000045s : 319: predicate.updatestate_pure_node_eliminater 2.85% : 0.000057s : 389: predicate.updatestate_useless_node_eliminater 0.17% : 0.000003s : 21: predicate.value_based_eliminate 0.36% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.33% : 0.000007s : 43: predicate.virtual_output_eliminate 0.14% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.019579 133 56.25% : 0.011013s : 53: func_graph_cloner_run.FuncGraphClonerGraph 43.75% : 0.008566s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.077866 209 0.00% : 0.000003s : 1: ForceFp32Comm 4.62% : 0.188356s : 1: add_attr 4.62% : 0.188325s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000214s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000828s : 1: auto_monad 0.00% : 0.000084s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000875s : 1: bootstrap 0.00% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000047s : 1: control_data_broadcast_order 0.00% : 0.000041s : 1: convert_after_rewriter 0.00% : 0.000084s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000035s : 1: environ_conv 0.01% : 0.000229s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000062s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 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% : 0.000010s : 1: label_micro_interleaved_index 0.02% : 0.000868s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000900s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000043s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000050s : 1: opt.transform.mutable_eliminate 0.47% : 0.019298s : 95: opt.transform.opt_a 0.00% : 0.000160s : 1: opt.transform.opt_after_cconv 0.00% : 0.000087s : 1: opt.transform.opt_after_jit_grad 3.91% : 0.159388s : 28: opt.transform.opt_b 0.01% : 0.000258s : 2: opt.transform.opt_trans_graph 0.00% : 0.000191s : 4: opt.transform.symbol_engine_opt 5.78% : 0.235547s : 1: opt_a 0.01% : 0.000366s : 1: opt_after_cconv 0.02% : 0.000721s : 1: opt_after_jit_grad 3.92% : 0.159873s : 1: opt_b 9.85% : 0.401835s : 1: optimize 0.00% : 0.000062s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.00% : 0.000064s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000017s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000449s : 1: pre_auto_parallel 0.01% : 0.000348s : 1: py_interpret_to_execute 0.00% : 0.000053s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000137s : 1: remove_dup_value 4.99% : 0.203380s : 1: renormalize.infer 0.25% : 0.010116s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.001007s : 1: rewriter_after_opt_a 0.02% : 0.000919s : 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% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000587s : 1: symbol_engine_optimizer 0.01% : 0.000297s : 1: tuple_transform 61.34% : 2.501314s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape0-1024] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape0-1024],max_mem:408.0M [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:41:25.433.717 [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 = 3.55557, [21] [bootstrap]: 0.00193904 [type_inference]: 3.1962 [event_method]: 0.00021339 [auto_monad]: 0.00081666 [graph_reusing]: 5.578e-05 [inline]: 3.71999e-06 [add_attr]: 0.00556427, [1] [add_attr_with_inline]: 0.00554367, [1] [Cycle 1]: 0.00034178, [2] [tag_attr]: 0.000222 [meta_addattr_fg_expand]: 5.513e-05 [parallel-infer-symbol]: 4.35e-06 [pre_auto_parallel]: 0.00026917 [insert-virtual-dataset]: 2.78998e-06 [parallel-infer-symbol-second]: 1.44998e-06 [dataset_repeat_opt]: 2.73998e-06 [pipeline_split]: 1.64998e-06 [optimize]: 0.348986, [53] [py_interpret_to_execute]: 0.00027244 [rewriter_before_opt_a]: 0.164992 [opt_a]: 0.177199, [2] [Cycle 1]: 0.174301, [45] [expand_dump_flag]: 4.484e-05 [switch_simplify]: 0.00106826 [loop_unroll]: 0.00035006 [a_1]: 0.011167 [with_stream_mark]: 7.348e-05 [recompute_prepare]: 5.405e-05 [updatestate_depend_eliminate]: 2.597e-05 [updatestate_assign_eliminate]: 2.33e-05 [updatestate_loads_eliminate]: 0.00010542 [parameter_eliminate]: 3.97e-06 [a_2]: 0.00099119 [accelerated_algorithm]: 8.917e-05 [shard]: 2.64001e-06 [meta_shard_fg_expand]: 3.083e-05 [shard_inline]: 2.828e-05 [merge_send_recv]: 2.423e-05 [auto_parallel]: 2.368e-05 [parallel]: 4.734e-05 [flash_sp]: 1.72e-05 [merge_comm]: 1.707e-05 [allreduce_fusion]: 1.499e-05 [matmul_add_comm_reduction]: 3.136e-05 [allreduce_slice_to_reducescatter]: 9.90025e-07 [virtual_shard_identity]: 3.587e-05 [virtual_dataset]: 2.554e-05 [get_grad_eliminate_]: 2.602e-05 [virtual_output]: 2.667e-05 [merge_forward]: 1.617e-05 [cell_reuse_recompute_pass]: 2.39001e-06 [offload_activation]: 2.996e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.907e-05 [merge_recompute_call_nodes]: 1.88997e-06 [before_grad]: 0.00013545 [set_forward_comm_id_for_comm_node_pass]: 2.336e-05 [meta_fg_expand]: 2.709e-05 [flash_sp_send_recv_attached]: 8.15e-06 [receive_attached]: 2.84999e-06 [after_resolve]: 4.357e-05 [a_after_grad]: 4.99e-05 [renormalize]: 0.157914 [add_forward_monad_depend]: 1.633e-05 [auto_monad_grad]: 3.66999e-06 [auto_monad_eliminator]: 0.00011211 [cse]: 0.00076718 [a_3]: 0.00020499 [Cycle 2]: 0.00287265, [45] [expand_dump_flag]: 3.39001e-06 [switch_simplify]: 2.926e-05 [loop_unroll]: 2.566e-05 [a_1]: 0.00082769 [with_stream_mark]: 4.316e-05 [recompute_prepare]: 2.839e-05 [updatestate_depend_eliminate]: 1.74e-05 [updatestate_assign_eliminate]: 1.624e-05 [updatestate_loads_eliminate]: 2.044e-05 [parameter_eliminate]: 3.38999e-06 [a_2]: 0.0006162 [accelerated_algorithm]: 4.361e-05 [shard]: 3.18e-06 [meta_shard_fg_expand]: 1.417e-05 [shard_inline]: 2.436e-05 [merge_send_recv]: 2.626e-05 [auto_parallel]: 2.312e-05 [parallel]: 1.208e-05 [flash_sp]: 5.19998e-06 [merge_comm]: 1.573e-05 [allreduce_fusion]: 1.54e-05 [matmul_add_comm_reduction]: 2.904e-05 [allreduce_slice_to_reducescatter]: 1.00001e-06 [virtual_shard_identity]: 2.726e-05 [virtual_dataset]: 2.583e-05 [get_grad_eliminate_]: 2.436e-05 [virtual_output]: 2.329e-05 [merge_forward]: 1.478e-05 [cell_reuse_recompute_pass]: 4.31002e-06 [offload_activation]: 2.629e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.087e-05 [merge_recompute_call_nodes]: 2.02999e-06 [before_grad]: 4.352e-05 [set_forward_comm_id_for_comm_node_pass]: 1.639e-05 [meta_fg_expand]: 1.367e-05 [flash_sp_send_recv_attached]: 1.50999e-06 [receive_attached]: 2.63e-06 [after_resolve]: 3.532e-05 [a_after_grad]: 4.13e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 6.22001e-06 [auto_monad_grad]: 3.73999e-06 [auto_monad_eliminator]: 7.843e-05 [cse]: 0.00011446 [a_3]: 0.00016846 [py_interpret_to_execute_after_opt_a]: 4.375e-05 [slice_cell_reuse_recomputed_activation]: 2.71e-06 [rewriter_after_opt_a]: 0.00095049 [convert_after_rewriter]: 3.792e-05 [order_py_execute_after_rewriter]: 1.575e-05 [mutable_eliminate]: 0.00096242 [opt_b]: 0.00099918, [1] [Cycle 1]: 0.00098658, [7] [b_1]: 0.0007058 [b_2]: 2.786e-05 [updatestate_depend_eliminate]: 2.517e-05 [updatestate_assign_eliminate]: 1.481e-05 [updatestate_loads_eliminate]: 2.181e-05 [renormalize]: 1.14998e-06 [cse]: 0.0001321 [optimize_parallel_all_gather_comm]: 5.402e-05 [overlap_param_gather]: 3.14999e-06 [cconv]: 5.047e-05 [loop_unroll]: 0.00084528 [opt_after_cconv]: 0.00043407, [1] [Cycle 1]: 0.00042341, [7] [c_1]: 0.00018766 [parameter_eliminate]: 7.54002e-06 [updatestate_depend_eliminate]: 2.495e-05 [updatestate_assign_eliminate]: 1.454e-05 [updatestate_loads_eliminate]: 2.063e-05 [cse]: 0.00011943 [renormalize]: 1.02e-06 [remove_dup_value]: 0.00012986 [tuple_transform]: 0.00032516, [1] [Cycle 1]: 0.00031743, [4] [d_1]: 0.00025227 [none_parameter_eliminate]: 4.90001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 2.679e-05 [partial_unused_args_eliminate]: 3.30998e-06 [add_recomputation]: 0.00020249 [cse_after_recomputation]: 0.00010544, [1] [Cycle 1]: 9.568e-05, [1] [cse]: 8.193e-05 [environ_conv]: 3.336e-05 [swap_dp_allreduce_reducescatter]: 2.686e-05 [bias_add_comm_swap]: 3.61999e-06 [label_micro_interleaved_index]: 8.60001e-06 [label_fine_grained_interleaved_index]: 2.86999e-06 [merge_cast_opt]: 1.45999e-06 [slice_recompute_activation]: 2.53e-06 [micro_interleaved_order_control]: 2.86999e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 1.64e-06 [remove_cast_before_assign_add]: 1.12999e-06 [full_micro_interleaved_order_control]: 2.61e-06 [reorder_send_recv_between_fp_bp]: 2.83e-06 [comm_op_add_attrs]: 1.32e-06 [add_comm_op_reuse_tag]: 1.29e-06 [interleave_split_concat_branches]: 1.32999e-06 [interleave_parallel_branches]: 1.23002e-06 [overlap_opt_shard_in_pipeline]: 2.86e-06 [overlap_opt_shard_grad_in_pipeline]: 1.84998e-06 [control_data_broadcast_order]: 4.662e-05 [grouped_pairwise_exchange_alltoall]: 1.81003e-06 [offloading_packed_experts]: 1.311e-05 [overlap_recompute_and_grad_model_parallel]: 1.227e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.40999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42999e-06 [overlap_recompute_comm]: 2.85002e-06 [overlap_grad_ring_attention]: 1.103e-05 [overlap_grad_flash_sp]: 6.287e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.58e-06 [split_layernorm_comm]: 1.79e-06 [handle_group_info]: 9.90025e-07 [symbol_engine_optimizer]: 0.00068265, [1] [Cycle 1]: 0.00067489, [6] [build]: 0.00035518 [elim_shapecalc]: 5.043e-05 [elim_not_effective]: 6.852e-05 [opt_reshape]: 4.278e-05 [fold_const_symbol]: 8.925e-05 [renormalize]: 7.00005e-07 [detach_backward]: 4.76002e-06 [pipeline_parallel_scheduler]: 2.23998e-06 [auto_monad_reorder]: 9.373e-05 [get_jit_bprop_graph]: 2.56e-06 [rewriter_after_jit_bprop_graph]: 1.002e-05 [opt_after_jit_grad]: 0.00094167 [validate]: 0.00013906 Sums bootstrap : 0.001939s : 0.05% type_inference : 3.196202s : 90.07% event_method : 0.000213s : 0.01% auto_monad : 0.000817s : 0.02% graph_reusing : 0.000056s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000222s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000055s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000269s : 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 : 0.000272s : 0.01% optimize.rewriter_before_opt_a : 0.164992s : 4.65% optimize.opt_a.expand_dump_flag : 0.000048s : 0.00% optimize.opt_a.switch_simplify : 0.001098s : 0.03% optimize.opt_a.loop_unroll : 0.000376s : 0.01% optimize.opt_a.a_1 : 0.011995s : 0.34% optimize.opt_a.with_stream_mark : 0.000117s : 0.00% optimize.opt_a.recompute_prepare : 0.000082s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000040s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000126s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001607s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000133s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000045s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000050s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000059s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000033s : 0.00% optimize.opt_a.allreduce_fusion : 0.000030s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000060s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000063s : 0.00% optimize.opt_a.virtual_dataset : 0.000051s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000050s : 0.00% optimize.opt_a.merge_forward : 0.000031s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000056s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000110s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000179s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000040s : 0.00% optimize.opt_a.meta_fg_expand : 0.000041s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000079s : 0.00% optimize.opt_a.a_after_grad : 0.000091s : 0.00% optimize.opt_a.renormalize : 0.157914s : 4.45% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000191s : 0.01% optimize.opt_a.cse : 0.000882s : 0.02% optimize.opt_a.a_3 : 0.000373s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000044s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000950s : 0.03% optimize.convert_after_rewriter : 0.000038s : 0.00% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.000962s : 0.03% optimize.opt_b.b_1 : 0.000706s : 0.02% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000132s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000054s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000050s : 0.00% optimize.loop_unroll : 0.000845s : 0.02% optimize.opt_after_cconv.c_1 : 0.000188s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_after_cconv.cse : 0.000119s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000130s : 0.00% optimize.tuple_transform.d_1 : 0.000252s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000005s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000027s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000202s : 0.01% optimize.cse_after_recomputation.cse : 0.000082s : 0.00% optimize.environ_conv : 0.000033s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000027s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 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 : 0.000002s : 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 : 0.000047s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000063s : 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 : 0.000355s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000050s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000069s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000043s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000089s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000094s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.00% opt_after_jit_grad : 0.000942s : 0.03% validate : 0.000139s : 0.00% Time group info: ------[substitution.] 0.004505 612 1.33% : 0.000060s : 5: substitution.arithmetic_simplify 0.43% : 0.000019s : 8: substitution.depend_value_elim 0.41% : 0.000018s : 17: substitution.elim_not_effective 0.44% : 0.000020s : 12: substitution.float_tuple_getitem_switch 1.07% : 0.000048s : 17: substitution.fold_const_symbol 0.44% : 0.000020s : 21: substitution.graph_param_transform 66.69% : 0.003004s : 71: substitution.inline 0.43% : 0.000019s : 35: substitution.j_node_and_user_rematch 1.00% : 0.000045s : 10: substitution.less_batch_normalization 1.52% : 0.000068s : 2: substitution.list_to_tuple_eliminator_ 0.24% : 0.000011s : 12: substitution.load_eliminater 0.82% : 0.000037s : 21: substitution.minmaximum_grad 0.20% : 0.000009s : 2: substitution.opt_reshape 0.50% : 0.000022s : 35: substitution.remove_not_recompute_node 0.29% : 0.000013s : 6: substitution.replace_old_param 1.63% : 0.000073s : 18: substitution.reshape_eliminate 1.50% : 0.000068s : 24: substitution.switch_simplify 3.98% : 0.000179s : 51: substitution.tuple_list_convert_item_index_to_positive 2.25% : 0.000101s : 51: substitution.tuple_list_get_item_const_eliminator 2.80% : 0.000126s : 51: substitution.tuple_list_get_item_depend_reorder 5.84% : 0.000263s : 73: substitution.tuple_list_get_item_eliminator 2.76% : 0.000125s : 51: substitution.tuple_list_get_set_item_eliminator 0.47% : 0.000021s : 8: substitution.updatestate_pure_node_eliminater 2.98% : 0.000134s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.195768 2 96.02% : 3.068567s : 1: type_inference.infer 3.98% : 0.127201s : 1: type_inference.specialize ------[replace.] 0.001400 115 3.50% : 0.000049s : 5: replace.depend_value_elim 57.21% : 0.000801s : 71: replace.inline 3.79% : 0.000053s : 2: replace.list_to_tuple_eliminator_ 26.87% : 0.000376s : 24: replace.switch_simplify 8.62% : 0.000121s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003111 115 0.09% : 0.000003s : 5: match.depend_value_elim 94.88% : 0.002952s : 71: match.inline 2.10% : 0.000065s : 2: match.list_to_tuple_eliminator_ 1.64% : 0.000051s : 24: match.switch_simplify 1.29% : 0.000040s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001918 10672 1.04% : 0.000020s : 131: predicate.accumulaten_eliminater 0.44% : 0.000008s : 21: predicate.ad_related_special_op_eliminate 0.52% : 0.000010s : 70: predicate.addn_check_dump 1.03% : 0.000020s : 131: predicate.addn_zero_filter 1.01% : 0.000019s : 131: predicate.adjust_all_reduce_mul_add 2.27% : 0.000044s : 201: predicate.arithmetic_simplify 1.05% : 0.000020s : 131: predicate.cast_eliminate 0.32% : 0.000006s : 42: predicate.check_bprop_eliminate 0.50% : 0.000010s : 70: predicate.compare_switch_simplify 0.09% : 0.000002s : 21: predicate.const_output_eliminate 0.58% : 0.000011s : 73: predicate.depend_value_elim 1.08% : 0.000021s : 131: predicate.dict_get_item_const_eliminator 1.17% : 0.000023s : 131: predicate.dict_get_item_eliminator 0.98% : 0.000019s : 131: predicate.dict_set_item_eliminator 0.41% : 0.000008s : 42: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 21: predicate.elim_not_effective 0.22% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000023s : 152: predicate.environ_add_const_eliminate 1.13% : 0.000022s : 152: predicate.environ_get_add_eliminate 1.12% : 0.000021s : 152: predicate.environ_get_depend_swap 1.71% : 0.000033s : 222: predicate.environ_get_eliminate 1.20% : 0.000023s : 152: predicate.environ_get_set_eliminate 1.73% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.57% : 0.000049s : 217: predicate.float_depend_g_call 0.65% : 0.000012s : 70: predicate.float_environ_get_switch 0.72% : 0.000014s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.37% : 0.000007s : 43: predicate.get_grad_eliminate 0.12% : 0.000002s : 21: predicate.graph_param_transform 0.54% : 0.000010s : 70: predicate.incorporate_call 0.47% : 0.000009s : 70: predicate.incorporate_call_switch 5.60% : 0.000107s : 503: predicate.inline 0.50% : 0.000010s : 43: predicate.inline_without_move 0.16% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.50% : 0.000010s : 43: predicate.less_batch_normalization 1.53% : 0.000029s : 188: predicate.list_to_tuple_eliminator_ 2.32% : 0.000044s : 319: predicate.load_eliminater 0.75% : 0.000014s : 21: predicate.loop_unroll_after_grad 3.26% : 0.000063s : 322: predicate.loop_unroll_before_grad 1.44% : 0.000028s : 173: predicate.make_slice_get_slice_eliminator 0.53% : 0.000010s : 70: predicate.merge_addn 0.30% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.31% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.04% : 0.000020s : 131: predicate.minmaximum_grad 0.74% : 0.000014s : 21: predicate.mutable_eliminate 0.20% : 0.000004s : 21: predicate.opt_reshape 0.17% : 0.000003s : 21: predicate.parallel_virtual_node 3.38% : 0.000065s : 217: predicate.partial_defer_inline 1.39% : 0.000027s : 167: predicate.partial_eliminate 1.11% : 0.000021s : 131: predicate.print_const_string_wrapper 0.51% : 0.000010s : 65: predicate.reduce_all_const_elim 1.30% : 0.000025s : 131: predicate.reduce_eliminate 2.51% : 0.000048s : 319: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000004s : 43: predicate.remove_not_recompute_node 1.02% : 0.000020s : 188: predicate.replace_applicator 0.21% : 0.000004s : 43: predicate.replace_old_param 0.10% : 0.000002s : 21: predicate.reset_defer_inline 1.18% : 0.000023s : 131: predicate.reshape_eliminate 0.32% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.21% : 0.000004s : 21: predicate.row_tensor_eliminate 0.46% : 0.000009s : 42: predicate.same_eliminate 0.21% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.37% : 0.000007s : 43: predicate.shard_identity_eliminate 0.38% : 0.000007s : 42: predicate.special_op_eliminate 0.66% : 0.000013s : 70: predicate.specialize_transform 0.43% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.43% : 0.000008s : 43: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.86% : 0.000036s : 217: predicate.switch_defer_inline 2.09% : 0.000040s : 259: predicate.switch_layer_defer_inline 8.97% : 0.000172s : 678: predicate.switch_simplify 0.96% : 0.000018s : 131: predicate.tile_eliminate 0.98% : 0.000019s : 131: predicate.transpose_eliminate 1.62% : 0.000031s : 173: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000033s : 173: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000030s : 173: predicate.tuple_list_get_item_depend_reorder 2.99% : 0.000057s : 256: predicate.tuple_list_get_item_eliminator 1.63% : 0.000031s : 173: predicate.tuple_list_get_set_item_eliminator 2.34% : 0.000045s : 243: predicate.tuple_list_set_item_eliminator 1.46% : 0.000028s : 186: predicate.tuple_to_list_eliminator_ 2.40% : 0.000046s : 319: predicate.updatestate_pure_node_eliminater 5.89% : 0.000113s : 389: predicate.updatestate_useless_node_eliminater 0.19% : 0.000004s : 21: predicate.value_based_eliminate 0.38% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.34% : 0.000006s : 43: predicate.virtual_output_eliminate 0.15% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.019962 133 55.79% : 0.011137s : 53: func_graph_cloner_run.FuncGraphClonerGraph 44.21% : 0.008825s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.085514 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.14% : 0.005572s : 1: add_attr 0.14% : 0.005549s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.01% : 0.000216s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.02% : 0.000842s : 1: auto_monad 0.00% : 0.000101s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.002001s : 1: bootstrap 0.00% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000052s : 1: control_data_broadcast_order 0.00% : 0.000045s : 1: convert_after_rewriter 0.00% : 0.000110s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000038s : 1: environ_conv 0.01% : 0.000226s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000065s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000012s : 1: label_micro_interleaved_index 0.02% : 0.000866s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000984s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000061s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000070s : 1: opt.transform.mutable_eliminate 0.40% : 0.016201s : 95: opt.transform.opt_a 0.00% : 0.000186s : 1: opt.transform.opt_after_cconv 0.00% : 0.000099s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000688s : 28: opt.transform.opt_b 0.01% : 0.000274s : 2: opt.transform.opt_trans_graph 0.01% : 0.000240s : 4: opt.transform.symbol_engine_opt 4.34% : 0.177206s : 1: opt_a 0.01% : 0.000439s : 1: opt_after_cconv 0.02% : 0.000959s : 1: opt_after_jit_grad 0.02% : 0.001005s : 1: opt_b 8.54% : 0.348996s : 1: optimize 0.00% : 0.000060s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000069s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 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 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000281s : 1: pre_auto_parallel 0.01% : 0.000283s : 1: py_interpret_to_execute 0.00% : 0.000048s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000139s : 1: remove_dup_value 3.63% : 0.148454s : 1: renormalize.infer 0.23% : 0.009429s : 1: renormalize.specialize 0.00% : 0.000009s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000969s : 1: rewriter_after_opt_a 4.04% : 0.165030s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000032s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000687s : 1: symbol_engine_optimizer 0.01% : 0.000329s : 1: tuple_transform 78.23% : 3.196255s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape1-16] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape1-16],max_mem:408.0M [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:42:15.860.64 [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 = 2.22841, [21] [bootstrap]: 0.073025 [type_inference]: 1.90106 [event_method]: 0.00023105 [auto_monad]: 0.00084218 [graph_reusing]: 5.542e-05 [inline]: 2.89001e-06 [add_attr]: 0.00604955, [1] [add_attr_with_inline]: 0.00603182, [1] [Cycle 1]: 0.00048173, [2] [tag_attr]: 0.00035831 [meta_addattr_fg_expand]: 6.439e-05 [parallel-infer-symbol]: 3.87002e-06 [pre_auto_parallel]: 0.00027587 [insert-virtual-dataset]: 2.69999e-06 [parallel-infer-symbol-second]: 1.16997e-06 [dataset_repeat_opt]: 2.27999e-06 [pipeline_split]: 1.75001e-06 [optimize]: 0.245404, [53] [py_interpret_to_execute]: 0.0002544 [rewriter_before_opt_a]: 0.00080958 [opt_a]: 0.238434, [2] [Cycle 1]: 0.156346, [45] [expand_dump_flag]: 2.448e-05 [switch_simplify]: 0.00084929 [loop_unroll]: 0.00037922 [a_1]: 0.0835052 [with_stream_mark]: 7.176e-05 [recompute_prepare]: 5.008e-05 [updatestate_depend_eliminate]: 2.363e-05 [updatestate_assign_eliminate]: 2.229e-05 [updatestate_loads_eliminate]: 0.00010757 [parameter_eliminate]: 3.75e-06 [a_2]: 0.00100524 [accelerated_algorithm]: 8.057e-05 [shard]: 3.31001e-06 [meta_shard_fg_expand]: 3.753e-05 [shard_inline]: 2.785e-05 [merge_send_recv]: 2.66e-05 [auto_parallel]: 2.428e-05 [parallel]: 5.042e-05 [flash_sp]: 1.849e-05 [merge_comm]: 1.942e-05 [allreduce_fusion]: 1.555e-05 [matmul_add_comm_reduction]: 3.02e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 3.509e-05 [virtual_dataset]: 2.498e-05 [get_grad_eliminate_]: 2.431e-05 [virtual_output]: 2.789e-05 [merge_forward]: 1.636e-05 [cell_reuse_recompute_pass]: 3.77998e-06 [offload_activation]: 2.742e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.722e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 4.894e-05 [set_forward_comm_id_for_comm_node_pass]: 1.708e-05 [meta_fg_expand]: 3.04e-05 [flash_sp_send_recv_attached]: 6.74001e-06 [receive_attached]: 2.29999e-06 [after_resolve]: 3.64e-05 [a_after_grad]: 4.447e-05 [renormalize]: 0.0683371 [add_forward_monad_depend]: 1.41e-05 [auto_monad_grad]: 3.81999e-06 [auto_monad_eliminator]: 0.00010003 [cse]: 0.00043841 [a_3]: 0.00019842 [Cycle 2]: 0.0820713, [45] [expand_dump_flag]: 2.87002e-06 [switch_simplify]: 2.848e-05 [loop_unroll]: 2.482e-05 [a_1]: 0.0008104 [with_stream_mark]: 3.653e-05 [recompute_prepare]: 2.651e-05 [updatestate_depend_eliminate]: 1.638e-05 [updatestate_assign_eliminate]: 1.552e-05 [updatestate_loads_eliminate]: 1.983e-05 [parameter_eliminate]: 2.91e-06 [a_2]: 0.00038184 [accelerated_algorithm]: 3.896e-05 [shard]: 2.56998e-06 [meta_shard_fg_expand]: 7.18998e-06 [shard_inline]: 2.517e-05 [merge_send_recv]: 2.24e-05 [auto_parallel]: 2.121e-05 [parallel]: 0.0792147 [flash_sp]: 1.381e-05 [merge_comm]: 6.676e-05 [allreduce_fusion]: 1.873e-05 [matmul_add_comm_reduction]: 3.37e-05 [allreduce_slice_to_reducescatter]: 1.25999e-06 [virtual_shard_identity]: 6.132e-05 [virtual_dataset]: 2.738e-05 [get_grad_eliminate_]: 2.704e-05 [virtual_output]: 2.489e-05 [merge_forward]: 1.541e-05 [cell_reuse_recompute_pass]: 4.30999e-06 [offload_activation]: 2.796e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.695e-05 [merge_recompute_call_nodes]: 2.12999e-06 [before_grad]: 4.787e-05 [set_forward_comm_id_for_comm_node_pass]: 1.707e-05 [meta_fg_expand]: 1.957e-05 [flash_sp_send_recv_attached]: 2.02001e-06 [receive_attached]: 2.69999e-06 [after_resolve]: 3.386e-05 [a_after_grad]: 4.128e-05 [renormalize]: 1.40019e-07 [add_forward_monad_depend]: 6.86001e-06 [auto_monad_grad]: 3.65e-06 [auto_monad_eliminator]: 0.00015547 [cse]: 0.00012137 [a_3]: 0.00017087 [py_interpret_to_execute_after_opt_a]: 4.328e-05 [slice_cell_reuse_recomputed_activation]: 2.24001e-06 [rewriter_after_opt_a]: 0.00092392 [convert_after_rewriter]: 2.998e-05 [order_py_execute_after_rewriter]: 1.49e-05 [mutable_eliminate]: 0.0008981 [opt_b]: 0.00094073, [1] [Cycle 1]: 0.00092873, [7] [b_1]: 0.00067065 [b_2]: 2.86e-05 [updatestate_depend_eliminate]: 2.256e-05 [updatestate_assign_eliminate]: 1.625e-05 [updatestate_loads_eliminate]: 2.149e-05 [renormalize]: 1.23002e-06 [cse]: 0.00011498 [optimize_parallel_all_gather_comm]: 4.899e-05 [overlap_param_gather]: 3.37002e-06 [cconv]: 4.527e-05 [loop_unroll]: 0.00061765 [opt_after_cconv]: 0.00037218, [1] [Cycle 1]: 0.00036421, [7] [c_1]: 0.00017184 [parameter_eliminate]: 5.92999e-06 [updatestate_depend_eliminate]: 1.866e-05 [updatestate_assign_eliminate]: 1.37e-05 [updatestate_loads_eliminate]: 1.769e-05 [cse]: 9.235e-05 [renormalize]: 6.30011e-07 [remove_dup_value]: 0.00012783 [tuple_transform]: 0.00031606, [1] [Cycle 1]: 0.00030865, [4] [d_1]: 0.0002485 [none_parameter_eliminate]: 2.94999e-06 [renormalize]: 1.30007e-07 [switch_simplify]: 2.967e-05 [partial_unused_args_eliminate]: 2.56998e-06 [add_recomputation]: 0.00019585 [cse_after_recomputation]: 9.504e-05, [1] [Cycle 1]: 8.606e-05, [1] [cse]: 7.552e-05 [environ_conv]: 3.491e-05 [swap_dp_allreduce_reducescatter]: 2.411e-05 [bias_add_comm_swap]: 4.27e-06 [label_micro_interleaved_index]: 8.28999e-06 [label_fine_grained_interleaved_index]: 2.97002e-06 [merge_cast_opt]: 1.34e-06 [slice_recompute_activation]: 2.44999e-06 [micro_interleaved_order_control]: 3.36001e-06 [assign_add_opt]: 1.53002e-06 [ForceFp32Comm]: 9.80013e-07 [remove_cast_before_assign_add]: 1.37999e-06 [full_micro_interleaved_order_control]: 2.17001e-06 [reorder_send_recv_between_fp_bp]: 3.03998e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.05001e-06 [interleave_split_concat_branches]: 1.42e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 2.87002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.99e-06 [control_data_broadcast_order]: 4.917e-05 [grouped_pairwise_exchange_alltoall]: 1.89999e-06 [offloading_packed_experts]: 1.491e-05 [overlap_recompute_and_grad_model_parallel]: 1.191e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.53002e-06 [overlap_recompute_comm]: 2.44999e-06 [overlap_grad_ring_attention]: 1.182e-05 [overlap_grad_flash_sp]: 6.254e-05 [begin_end_overlap_inline]: 6.30011e-07 [split_matmul_comm_elemetwise]: 2.34999e-06 [split_layernorm_comm]: 2.36e-06 [handle_group_info]: 1.02998e-06 [symbol_engine_optimizer]: 0.00063028, [1] [Cycle 1]: 0.00062301, [6] [build]: 0.00034759 [elim_shapecalc]: 4.409e-05 [elim_not_effective]: 6.487e-05 [opt_reshape]: 3.917e-05 [fold_const_symbol]: 6.998e-05 [renormalize]: 6.00005e-07 [detach_backward]: 4.67e-06 [pipeline_parallel_scheduler]: 2.63e-06 [auto_monad_reorder]: 9.025e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 7.71999e-06 [opt_after_jit_grad]: 0.00092647 [validate]: 0.00012978 Sums bootstrap : 0.073025s : 3.29% type_inference : 1.901064s : 85.59% event_method : 0.000231s : 0.01% auto_monad : 0.000842s : 0.04% graph_reusing : 0.000055s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000358s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000064s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000276s : 0.01% 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 : 0.000254s : 0.01% optimize.rewriter_before_opt_a : 0.000810s : 0.04% optimize.opt_a.expand_dump_flag : 0.000027s : 0.00% optimize.opt_a.switch_simplify : 0.000878s : 0.04% optimize.opt_a.loop_unroll : 0.000404s : 0.02% optimize.opt_a.a_1 : 0.084316s : 3.80% optimize.opt_a.with_stream_mark : 0.000108s : 0.00% optimize.opt_a.recompute_prepare : 0.000077s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000040s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000038s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000127s : 0.01% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001387s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000120s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000045s : 0.00% optimize.opt_a.shard_inline : 0.000053s : 0.00% optimize.opt_a.merge_send_recv : 0.000049s : 0.00% optimize.opt_a.auto_parallel : 0.000045s : 0.00% optimize.opt_a.parallel : 0.079265s : 3.57% optimize.opt_a.flash_sp : 0.000032s : 0.00% optimize.opt_a.merge_comm : 0.000086s : 0.00% optimize.opt_a.allreduce_fusion : 0.000034s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000064s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000096s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000051s : 0.00% optimize.opt_a.virtual_output : 0.000053s : 0.00% optimize.opt_a.merge_forward : 0.000032s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000055s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000124s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000097s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000034s : 0.00% optimize.opt_a.meta_fg_expand : 0.000050s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.00% optimize.opt_a.a_after_grad : 0.000086s : 0.00% optimize.opt_a.renormalize : 0.068337s : 3.08% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000256s : 0.01% optimize.opt_a.cse : 0.000560s : 0.03% optimize.opt_a.a_3 : 0.000369s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000043s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000924s : 0.04% optimize.convert_after_rewriter : 0.000030s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000898s : 0.04% optimize.opt_b.b_1 : 0.000671s : 0.03% optimize.opt_b.b_2 : 0.000029s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000115s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000049s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000618s : 0.03% optimize.opt_after_cconv.c_1 : 0.000172s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000092s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000128s : 0.01% optimize.tuple_transform.d_1 : 0.000249s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000030s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000196s : 0.01% optimize.cse_after_recomputation.cse : 0.000076s : 0.00% optimize.environ_conv : 0.000035s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000024s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000049s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000015s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 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 : 0.000012s : 0.00% optimize.overlap_grad_flash_sp : 0.000063s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000348s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000044s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000065s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000039s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000070s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000003s : 0.00% auto_monad_reorder : 0.000090s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000926s : 0.04% validate : 0.000130s : 0.01% Time group info: ------[substitution.] 0.004498 612 1.21% : 0.000054s : 5: substitution.arithmetic_simplify 0.44% : 0.000020s : 8: substitution.depend_value_elim 0.40% : 0.000018s : 17: substitution.elim_not_effective 0.40% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.70% : 0.000031s : 17: substitution.fold_const_symbol 0.42% : 0.000019s : 21: substitution.graph_param_transform 68.80% : 0.003094s : 71: substitution.inline 0.42% : 0.000019s : 35: substitution.j_node_and_user_rematch 1.01% : 0.000045s : 10: substitution.less_batch_normalization 1.50% : 0.000067s : 2: substitution.list_to_tuple_eliminator_ 0.22% : 0.000010s : 12: substitution.load_eliminater 0.84% : 0.000038s : 21: substitution.minmaximum_grad 0.19% : 0.000009s : 2: substitution.opt_reshape 0.50% : 0.000022s : 35: substitution.remove_not_recompute_node 0.27% : 0.000012s : 6: substitution.replace_old_param 1.67% : 0.000075s : 18: substitution.reshape_eliminate 1.16% : 0.000052s : 24: substitution.switch_simplify 3.87% : 0.000174s : 51: substitution.tuple_list_convert_item_index_to_positive 2.20% : 0.000099s : 51: substitution.tuple_list_get_item_const_eliminator 2.74% : 0.000123s : 51: substitution.tuple_list_get_item_depend_reorder 5.57% : 0.000251s : 73: substitution.tuple_list_get_item_eliminator 2.66% : 0.000120s : 51: substitution.tuple_list_get_set_item_eliminator 0.42% : 0.000019s : 8: substitution.updatestate_pure_node_eliminater 2.40% : 0.000108s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.900453 2 91.58% : 1.740463s : 1: type_inference.infer 8.42% : 0.159990s : 1: type_inference.specialize ------[replace.] 0.001358 115 3.62% : 0.000049s : 5: replace.depend_value_elim 60.44% : 0.000821s : 71: replace.inline 4.19% : 0.000057s : 2: replace.list_to_tuple_eliminator_ 23.14% : 0.000314s : 24: replace.switch_simplify 8.62% : 0.000117s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003185 115 0.07% : 0.000002s : 5: match.depend_value_elim 95.47% : 0.003041s : 71: match.inline 2.02% : 0.000064s : 2: match.list_to_tuple_eliminator_ 1.13% : 0.000036s : 24: match.switch_simplify 1.31% : 0.000042s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001809 10672 1.24% : 0.000023s : 131: predicate.accumulaten_eliminater 0.43% : 0.000008s : 21: predicate.ad_related_special_op_eliminate 0.53% : 0.000010s : 70: predicate.addn_check_dump 1.25% : 0.000023s : 131: predicate.addn_zero_filter 1.09% : 0.000020s : 131: predicate.adjust_all_reduce_mul_add 2.40% : 0.000043s : 201: predicate.arithmetic_simplify 1.13% : 0.000020s : 131: predicate.cast_eliminate 0.34% : 0.000006s : 42: predicate.check_bprop_eliminate 0.52% : 0.000009s : 70: predicate.compare_switch_simplify 0.09% : 0.000002s : 21: predicate.const_output_eliminate 0.63% : 0.000011s : 73: predicate.depend_value_elim 1.18% : 0.000021s : 131: predicate.dict_get_item_const_eliminator 1.22% : 0.000022s : 131: predicate.dict_get_item_eliminator 1.05% : 0.000019s : 131: predicate.dict_set_item_eliminator 0.48% : 0.000009s : 42: predicate.dumpgradient_eliminate 0.09% : 0.000002s : 21: predicate.elim_not_effective 0.23% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000022s : 152: predicate.environ_add_const_eliminate 1.24% : 0.000022s : 152: predicate.environ_get_add_eliminate 1.29% : 0.000023s : 152: predicate.environ_get_depend_swap 1.75% : 0.000032s : 222: predicate.environ_get_eliminate 1.19% : 0.000022s : 152: predicate.environ_get_set_eliminate 2.26% : 0.000041s : 217: predicate.exchange_switch_depend_value 3.08% : 0.000056s : 217: predicate.float_depend_g_call 0.61% : 0.000011s : 70: predicate.float_environ_get_switch 0.77% : 0.000014s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.39% : 0.000007s : 43: predicate.get_grad_eliminate 0.11% : 0.000002s : 21: predicate.graph_param_transform 0.56% : 0.000010s : 70: predicate.incorporate_call 0.50% : 0.000009s : 70: predicate.incorporate_call_switch 5.85% : 0.000106s : 503: predicate.inline 0.47% : 0.000009s : 43: predicate.inline_without_move 0.17% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.47% : 0.000008s : 43: predicate.less_batch_normalization 1.63% : 0.000029s : 188: predicate.list_to_tuple_eliminator_ 2.51% : 0.000045s : 319: predicate.load_eliminater 0.45% : 0.000008s : 21: predicate.loop_unroll_after_grad 2.98% : 0.000054s : 322: predicate.loop_unroll_before_grad 1.57% : 0.000028s : 173: predicate.make_slice_get_slice_eliminator 0.55% : 0.000010s : 70: predicate.merge_addn 0.32% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.33% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.14% : 0.000021s : 131: predicate.minmaximum_grad 0.48% : 0.000009s : 21: predicate.mutable_eliminate 0.22% : 0.000004s : 21: predicate.opt_reshape 0.21% : 0.000004s : 21: predicate.parallel_virtual_node 3.46% : 0.000063s : 217: predicate.partial_defer_inline 1.45% : 0.000026s : 167: predicate.partial_eliminate 1.14% : 0.000021s : 131: predicate.print_const_string_wrapper 0.62% : 0.000011s : 65: predicate.reduce_all_const_elim 1.51% : 0.000027s : 131: predicate.reduce_eliminate 2.57% : 0.000046s : 319: predicate.redundant_stop_gradient_eliminater 0.21% : 0.000004s : 43: predicate.remove_not_recompute_node 1.04% : 0.000019s : 188: predicate.replace_applicator 0.22% : 0.000004s : 43: predicate.replace_old_param 0.11% : 0.000002s : 21: predicate.reset_defer_inline 1.19% : 0.000022s : 131: predicate.reshape_eliminate 0.35% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.21% : 0.000004s : 21: predicate.row_tensor_eliminate 0.48% : 0.000009s : 42: predicate.same_eliminate 0.21% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.50% : 0.000009s : 43: predicate.shard_identity_eliminate 0.38% : 0.000007s : 42: predicate.special_op_eliminate 0.70% : 0.000013s : 70: predicate.specialize_transform 0.46% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.39% : 0.000007s : 43: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.98% : 0.000036s : 217: predicate.switch_defer_inline 2.24% : 0.000041s : 259: predicate.switch_layer_defer_inline 6.70% : 0.000121s : 678: predicate.switch_simplify 1.07% : 0.000019s : 131: predicate.tile_eliminate 1.07% : 0.000019s : 131: predicate.transpose_eliminate 1.76% : 0.000032s : 173: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000032s : 173: predicate.tuple_list_get_item_const_eliminator 1.68% : 0.000030s : 173: predicate.tuple_list_get_item_depend_reorder 3.29% : 0.000059s : 256: predicate.tuple_list_get_item_eliminator 1.72% : 0.000031s : 173: predicate.tuple_list_get_set_item_eliminator 2.40% : 0.000043s : 243: predicate.tuple_list_set_item_eliminator 1.57% : 0.000028s : 186: predicate.tuple_to_list_eliminator_ 2.51% : 0.000045s : 319: predicate.updatestate_pure_node_eliminater 3.19% : 0.000058s : 389: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 21: predicate.value_based_eliminate 0.39% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.35% : 0.000006s : 43: predicate.virtual_output_eliminate 0.16% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.23% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.097474 133 90.35% : 0.088066s : 53: func_graph_cloner_run.FuncGraphClonerGraph 9.65% : 0.009407s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.637446 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.23% : 0.006057s : 1: add_attr 0.23% : 0.006036s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000204s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.03% : 0.000862s : 1: auto_monad 0.00% : 0.000099s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 2.77% : 0.073087s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000053s : 1: control_data_broadcast_order 0.00% : 0.000037s : 1: convert_after_rewriter 0.00% : 0.000099s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000040s : 1: environ_conv 0.01% : 0.000246s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000063s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 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 0.02% : 0.000631s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000916s : 1: mutable_eliminate 0.00% : 0.000018s : 1: offloading_packed_experts 0.00% : 0.000043s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000052s : 1: opt.transform.mutable_eliminate 3.34% : 0.088050s : 95: opt.transform.opt_a 0.01% : 0.000170s : 1: opt.transform.opt_after_cconv 0.00% : 0.000097s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000657s : 28: opt.transform.opt_b 0.01% : 0.000275s : 2: opt.transform.opt_trans_graph 0.01% : 0.000210s : 4: opt.transform.symbol_engine_opt 9.04% : 0.238439s : 1: opt_a 0.01% : 0.000376s : 1: opt_after_cconv 0.04% : 0.000943s : 1: opt_after_jit_grad 0.04% : 0.000944s : 1: opt_b 9.30% : 0.245412s : 1: optimize 0.00% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000067s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 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 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 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% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000285s : 1: pre_auto_parallel 0.01% : 0.000263s : 1: py_interpret_to_execute 0.00% : 0.000048s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000134s : 1: remove_dup_value 2.25% : 0.059352s : 1: renormalize.infer 0.34% : 0.008960s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000941s : 1: rewriter_after_opt_a 0.03% : 0.000822s : 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% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000029s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000634s : 1: symbol_engine_optimizer 0.01% : 0.000319s : 1: tuple_transform 72.08% : 1.901102s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape1-256] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape1-256],max_mem:272.0M [WARNING] ME(164796:281473778974512,MainProcess):2026-01-29-17:42:56.419.990 [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 = 1.88231, [21] [bootstrap]: 0.0007356 [type_inference]: 1.54085 [event_method]: 0.00021721 [auto_monad]: 0.0008371 [graph_reusing]: 5.296e-05 [inline]: 6.39001e-06 [add_attr]: 0.0176576, [1] [add_attr_with_inline]: 0.0176352, [1] [Cycle 1]: 0.0125109, [2] [tag_attr]: 0.0122618 [meta_addattr_fg_expand]: 0.00014842 [parallel-infer-symbol]: 6.34999e-06 [pre_auto_parallel]: 0.0003357 [insert-virtual-dataset]: 3.09999e-06 [parallel-infer-symbol-second]: 2.79999e-06 [dataset_repeat_opt]: 3.07002e-06 [pipeline_split]: 1.69998e-06 [optimize]: 0.320134, [53] [py_interpret_to_execute]: 0.00028586 [rewriter_before_opt_a]: 0.00080977 [opt_a]: 0.217122, [2] [Cycle 1]: 0.214534, [45] [expand_dump_flag]: 2.218e-05 [switch_simplify]: 0.0940325 [loop_unroll]: 0.00050423 [a_1]: 0.0117976 [with_stream_mark]: 6.703e-05 [recompute_prepare]: 4.876e-05 [updatestate_depend_eliminate]: 2.318e-05 [updatestate_assign_eliminate]: 2.284e-05 [updatestate_loads_eliminate]: 0.00010132 [parameter_eliminate]: 3.81999e-06 [a_2]: 0.00102436 [accelerated_algorithm]: 9.312e-05 [shard]: 2.31e-06 [meta_shard_fg_expand]: 2.828e-05 [shard_inline]: 3.178e-05 [merge_send_recv]: 2.443e-05 [auto_parallel]: 2.551e-05 [parallel]: 4.618e-05 [flash_sp]: 1.806e-05 [merge_comm]: 1.932e-05 [allreduce_fusion]: 1.499e-05 [matmul_add_comm_reduction]: 2.706e-05 [allreduce_slice_to_reducescatter]: 1.27e-06 [virtual_shard_identity]: 3.494e-05 [virtual_dataset]: 2.799e-05 [get_grad_eliminate_]: 2.707e-05 [virtual_output]: 2.755e-05 [merge_forward]: 1.693e-05 [cell_reuse_recompute_pass]: 2.00002e-06 [offload_activation]: 2.856e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.511e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 4.988e-05 [set_forward_comm_id_for_comm_node_pass]: 1.871e-05 [meta_fg_expand]: 1.903e-05 [flash_sp_send_recv_attached]: 7.19001e-06 [receive_attached]: 2.52001e-06 [after_resolve]: 3.898e-05 [a_after_grad]: 4.55e-05 [renormalize]: 0.104772 [add_forward_monad_depend]: 1.842e-05 [auto_monad_grad]: 3.97e-06 [auto_monad_eliminator]: 0.00011036 [cse]: 0.00047603 [a_3]: 0.00020816 [Cycle 2]: 0.00256655, [45] [expand_dump_flag]: 3.45e-06 [switch_simplify]: 2.858e-05 [loop_unroll]: 2.764e-05 [a_1]: 0.00084983 [with_stream_mark]: 3.843e-05 [recompute_prepare]: 2.627e-05 [updatestate_depend_eliminate]: 1.536e-05 [updatestate_assign_eliminate]: 1.576e-05 [updatestate_loads_eliminate]: 2.05e-05 [parameter_eliminate]: 2.69999e-06 [a_2]: 0.00038199 [accelerated_algorithm]: 4.052e-05 [shard]: 2.79001e-06 [meta_shard_fg_expand]: 8.23001e-06 [shard_inline]: 2.51e-05 [merge_send_recv]: 2.268e-05 [auto_parallel]: 2.184e-05 [parallel]: 1.151e-05 [flash_sp]: 4.47e-06 [merge_comm]: 1.536e-05 [allreduce_fusion]: 1.555e-05 [matmul_add_comm_reduction]: 2.755e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 2.878e-05 [virtual_dataset]: 2.41e-05 [get_grad_eliminate_]: 2.337e-05 [virtual_output]: 2.332e-05 [merge_forward]: 1.393e-05 [cell_reuse_recompute_pass]: 3.4e-06 [offload_activation]: 2.473e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.979e-05 [merge_recompute_call_nodes]: 2.12999e-06 [before_grad]: 4.22e-05 [set_forward_comm_id_for_comm_node_pass]: 1.662e-05 [meta_fg_expand]: 1.17e-05 [flash_sp_send_recv_attached]: 1.79998e-06 [receive_attached]: 2.80002e-06 [after_resolve]: 3.36e-05 [a_after_grad]: 4.074e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.97999e-06 [auto_monad_grad]: 3.5e-06 [auto_monad_eliminator]: 7.03e-05 [cse]: 0.0001006 [a_3]: 0.00016805 [py_interpret_to_execute_after_opt_a]: 3.773e-05 [slice_cell_reuse_recomputed_activation]: 2.90998e-06 [rewriter_after_opt_a]: 0.00092694 [convert_after_rewriter]: 3.306e-05 [order_py_execute_after_rewriter]: 1.529e-05 [mutable_eliminate]: 0.00081729 [opt_b]: 0.00091146, [1] [Cycle 1]: 0.00090142, [7] [b_1]: 0.00064491 [b_2]: 3.1e-05 [updatestate_depend_eliminate]: 2.335e-05 [updatestate_assign_eliminate]: 1.518e-05 [updatestate_loads_eliminate]: 2.153e-05 [renormalize]: 6.09987e-07 [cse]: 0.00010671 [optimize_parallel_all_gather_comm]: 5.067e-05 [overlap_param_gather]: 3.21999e-06 [cconv]: 4.584e-05 [loop_unroll]: 0.00064667 [opt_after_cconv]: 0.00035545, [1] [Cycle 1]: 0.00034732, [7] [c_1]: 0.00016546 [parameter_eliminate]: 6.28e-06 [updatestate_depend_eliminate]: 1.852e-05 [updatestate_assign_eliminate]: 1.351e-05 [updatestate_loads_eliminate]: 1.781e-05 [cse]: 8.554e-05 [renormalize]: 6.29982e-07 [remove_dup_value]: 0.00011901 [tuple_transform]: 0.00028421, [1] [Cycle 1]: 0.00027841, [4] [d_1]: 0.00022784 [none_parameter_eliminate]: 2.68e-06 [renormalize]: 1.40019e-07 [switch_simplify]: 2.521e-05 [partial_unused_args_eliminate]: 2.66e-06 [add_recomputation]: 0.00017712 [cse_after_recomputation]: 8.122e-05, [1] [Cycle 1]: 7.424e-05, [1] [cse]: 6.673e-05 [environ_conv]: 2.74e-05 [swap_dp_allreduce_reducescatter]: 2.27e-05 [bias_add_comm_swap]: 3.2e-06 [label_micro_interleaved_index]: 6.61e-06 [label_fine_grained_interleaved_index]: 3.39001e-06 [merge_cast_opt]: 1.37e-06 [slice_recompute_activation]: 2.34001e-06 [micro_interleaved_order_control]: 0.0960434 [assign_add_opt]: 2.86999e-06 [ForceFp32Comm]: 1.01002e-06 [remove_cast_before_assign_add]: 1.14e-06 [full_micro_interleaved_order_control]: 5.17999e-06 [reorder_send_recv_between_fp_bp]: 3.51999e-06 [comm_op_add_attrs]: 1.32e-06 [add_comm_op_reuse_tag]: 1.27e-06 [interleave_split_concat_branches]: 1.79e-06 [interleave_parallel_branches]: 1.47999e-06 [overlap_opt_shard_in_pipeline]: 6.73e-06 [overlap_opt_shard_grad_in_pipeline]: 2.02999e-06 [control_data_broadcast_order]: 8.57e-05 [grouped_pairwise_exchange_alltoall]: 1.86e-06 [offloading_packed_experts]: 1.303e-05 [overlap_recompute_and_grad_model_parallel]: 1.22e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.40001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.17999e-06 [overlap_grad_ring_attention]: 1.067e-05 [overlap_grad_flash_sp]: 7.541e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.49001e-06 [split_layernorm_comm]: 2.21998e-06 [handle_group_info]: 9.80013e-07 [symbol_engine_optimizer]: 0.00067136, [1] [Cycle 1]: 0.00065851, [6] [build]: 0.0003522 [elim_shapecalc]: 5.783e-05 [elim_not_effective]: 7.725e-05 [opt_reshape]: 4.252e-05 [fold_const_symbol]: 6.997e-05 [renormalize]: 5.59987e-07 [detach_backward]: 4.68999e-06 [pipeline_parallel_scheduler]: 1.71e-06 [auto_monad_reorder]: 9.376e-05 [get_jit_bprop_graph]: 2.34001e-06 [rewriter_after_jit_bprop_graph]: 7.25e-06 [opt_after_jit_grad]: 0.00094615 [validate]: 0.00013183 Sums bootstrap : 0.000736s : 0.04% type_inference : 1.540855s : 82.16% event_method : 0.000217s : 0.01% auto_monad : 0.000837s : 0.04% graph_reusing : 0.000053s : 0.00% inline : 0.000006s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.012262s : 0.65% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000148s : 0.01% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000336s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000003s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000286s : 0.02% optimize.rewriter_before_opt_a : 0.000810s : 0.04% optimize.opt_a.expand_dump_flag : 0.000026s : 0.00% optimize.opt_a.switch_simplify : 0.094061s : 5.02% optimize.opt_a.loop_unroll : 0.000532s : 0.03% optimize.opt_a.a_1 : 0.012647s : 0.67% optimize.opt_a.with_stream_mark : 0.000105s : 0.01% optimize.opt_a.recompute_prepare : 0.000075s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000039s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000039s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000122s : 0.01% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001406s : 0.07% optimize.opt_a.accelerated_algorithm : 0.000134s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000037s : 0.00% optimize.opt_a.shard_inline : 0.000057s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000058s : 0.00% optimize.opt_a.flash_sp : 0.000023s : 0.00% optimize.opt_a.merge_comm : 0.000035s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000055s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000064s : 0.00% optimize.opt_a.virtual_dataset : 0.000052s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000051s : 0.00% optimize.opt_a.merge_forward : 0.000031s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000053s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000105s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000092s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000035s : 0.00% optimize.opt_a.meta_fg_expand : 0.000031s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000073s : 0.00% optimize.opt_a.a_after_grad : 0.000086s : 0.00% optimize.opt_a.renormalize : 0.104772s : 5.59% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000181s : 0.01% optimize.opt_a.cse : 0.000577s : 0.03% optimize.opt_a.a_3 : 0.000376s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000927s : 0.05% optimize.convert_after_rewriter : 0.000033s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000817s : 0.04% optimize.opt_b.b_1 : 0.000645s : 0.03% optimize.opt_b.b_2 : 0.000031s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000107s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000051s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000046s : 0.00% optimize.loop_unroll : 0.000647s : 0.03% optimize.opt_after_cconv.c_1 : 0.000165s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000086s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000119s : 0.01% optimize.tuple_transform.d_1 : 0.000228s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000177s : 0.01% optimize.cse_after_recomputation.cse : 0.000067s : 0.00% optimize.environ_conv : 0.000027s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000023s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 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 : 0.096043s : 5.12% optimize.assign_add_opt : 0.000003s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000005s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000007s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000086s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 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 : 0.00% optimize.overlap_grad_flash_sp : 0.000075s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000352s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000058s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000077s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000043s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000070s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000094s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000946s : 0.05% validate : 0.000132s : 0.01% Time group info: ------[substitution.] 0.004916 612 1.17% : 0.000058s : 5: substitution.arithmetic_simplify 0.40% : 0.000020s : 8: substitution.depend_value_elim 0.39% : 0.000019s : 17: substitution.elim_not_effective 0.37% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.56% : 0.000027s : 17: substitution.fold_const_symbol 0.35% : 0.000017s : 21: substitution.graph_param_transform 70.81% : 0.003481s : 71: substitution.inline 0.36% : 0.000018s : 35: substitution.j_node_and_user_rematch 1.00% : 0.000049s : 10: substitution.less_batch_normalization 1.40% : 0.000069s : 2: substitution.list_to_tuple_eliminator_ 0.23% : 0.000011s : 12: substitution.load_eliminater 0.64% : 0.000031s : 21: substitution.minmaximum_grad 0.21% : 0.000010s : 2: substitution.opt_reshape 0.46% : 0.000023s : 35: substitution.remove_not_recompute_node 0.22% : 0.000011s : 6: substitution.replace_old_param 1.73% : 0.000085s : 18: substitution.reshape_eliminate 1.40% : 0.000069s : 24: substitution.switch_simplify 3.48% : 0.000171s : 51: substitution.tuple_list_convert_item_index_to_positive 1.94% : 0.000095s : 51: substitution.tuple_list_get_item_const_eliminator 2.60% : 0.000128s : 51: substitution.tuple_list_get_item_depend_reorder 5.23% : 0.000257s : 73: substitution.tuple_list_get_item_eliminator 2.41% : 0.000118s : 51: substitution.tuple_list_get_set_item_eliminator 0.40% : 0.000020s : 8: substitution.updatestate_pure_node_eliminater 2.25% : 0.000111s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.540426 2 93.35% : 1.438028s : 1: type_inference.infer 6.65% : 0.102397s : 1: type_inference.specialize ------[replace.] 0.001496 115 3.52% : 0.000053s : 5: replace.depend_value_elim 59.47% : 0.000890s : 71: replace.inline 4.03% : 0.000060s : 2: replace.list_to_tuple_eliminator_ 24.32% : 0.000364s : 24: replace.switch_simplify 8.66% : 0.000130s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003591 115 0.08% : 0.000003s : 5: match.depend_value_elim 95.52% : 0.003430s : 71: match.inline 1.80% : 0.000065s : 2: match.list_to_tuple_eliminator_ 1.45% : 0.000052s : 24: match.switch_simplify 1.16% : 0.000042s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001921 10672 1.07% : 0.000021s : 131: predicate.accumulaten_eliminater 0.36% : 0.000007s : 21: predicate.ad_related_special_op_eliminate 0.50% : 0.000010s : 70: predicate.addn_check_dump 1.03% : 0.000020s : 131: predicate.addn_zero_filter 1.09% : 0.000021s : 131: predicate.adjust_all_reduce_mul_add 2.46% : 0.000047s : 201: predicate.arithmetic_simplify 1.13% : 0.000022s : 131: predicate.cast_eliminate 0.32% : 0.000006s : 42: predicate.check_bprop_eliminate 0.52% : 0.000010s : 70: predicate.compare_switch_simplify 0.08% : 0.000002s : 21: predicate.const_output_eliminate 0.60% : 0.000011s : 73: predicate.depend_value_elim 1.16% : 0.000022s : 131: predicate.dict_get_item_const_eliminator 1.12% : 0.000022s : 131: predicate.dict_get_item_eliminator 1.20% : 0.000023s : 131: predicate.dict_set_item_eliminator 0.41% : 0.000008s : 42: predicate.dumpgradient_eliminate 0.12% : 0.000002s : 21: predicate.elim_not_effective 0.24% : 0.000005s : 21: predicate.elim_shapecalc_of_broadcastargs 1.42% : 0.000027s : 152: predicate.environ_add_const_eliminate 1.14% : 0.000022s : 152: predicate.environ_get_add_eliminate 1.11% : 0.000021s : 152: predicate.environ_get_depend_swap 1.94% : 0.000037s : 222: predicate.environ_get_eliminate 1.13% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.72% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.65% : 0.000051s : 217: predicate.float_depend_g_call 0.51% : 0.000010s : 70: predicate.float_environ_get_switch 0.75% : 0.000014s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.35% : 0.000007s : 43: predicate.get_grad_eliminate 0.10% : 0.000002s : 21: predicate.graph_param_transform 0.54% : 0.000010s : 70: predicate.incorporate_call 0.49% : 0.000009s : 70: predicate.incorporate_call_switch 5.46% : 0.000105s : 503: predicate.inline 0.46% : 0.000009s : 43: predicate.inline_without_move 0.16% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.52% : 0.000010s : 43: predicate.less_batch_normalization 1.50% : 0.000029s : 188: predicate.list_to_tuple_eliminator_ 2.41% : 0.000046s : 319: predicate.load_eliminater 0.42% : 0.000008s : 21: predicate.loop_unroll_after_grad 6.80% : 0.000131s : 322: predicate.loop_unroll_before_grad 1.52% : 0.000029s : 173: predicate.make_slice_get_slice_eliminator 0.51% : 0.000010s : 70: predicate.merge_addn 0.31% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.32% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.15% : 0.000022s : 131: predicate.minmaximum_grad 0.35% : 0.000007s : 21: predicate.mutable_eliminate 0.18% : 0.000003s : 21: predicate.opt_reshape 0.17% : 0.000003s : 21: predicate.parallel_virtual_node 3.99% : 0.000077s : 217: predicate.partial_defer_inline 1.36% : 0.000026s : 167: predicate.partial_eliminate 1.08% : 0.000021s : 131: predicate.print_const_string_wrapper 0.52% : 0.000010s : 65: predicate.reduce_all_const_elim 1.44% : 0.000028s : 131: predicate.reduce_eliminate 2.53% : 0.000049s : 319: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 43: predicate.remove_not_recompute_node 1.01% : 0.000019s : 188: predicate.replace_applicator 0.20% : 0.000004s : 43: predicate.replace_old_param 0.12% : 0.000002s : 21: predicate.reset_defer_inline 1.09% : 0.000021s : 131: predicate.reshape_eliminate 0.33% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.20% : 0.000004s : 21: predicate.row_tensor_eliminate 0.43% : 0.000008s : 42: predicate.same_eliminate 0.22% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.43% : 0.000008s : 43: predicate.shard_identity_eliminate 0.37% : 0.000007s : 42: predicate.special_op_eliminate 0.66% : 0.000013s : 70: predicate.specialize_transform 0.45% : 0.000009s : 42: predicate.split_environ_get_set_with_tuple_value 0.42% : 0.000008s : 43: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.93% : 0.000037s : 217: predicate.switch_defer_inline 2.19% : 0.000042s : 259: predicate.switch_layer_defer_inline 6.54% : 0.000126s : 678: predicate.switch_simplify 0.99% : 0.000019s : 131: predicate.tile_eliminate 1.08% : 0.000021s : 131: predicate.transpose_eliminate 1.58% : 0.000030s : 173: predicate.tuple_list_convert_item_index_to_positive 1.80% : 0.000035s : 173: predicate.tuple_list_get_item_const_eliminator 1.51% : 0.000029s : 173: predicate.tuple_list_get_item_depend_reorder 3.63% : 0.000070s : 256: predicate.tuple_list_get_item_eliminator 1.63% : 0.000031s : 173: predicate.tuple_list_get_set_item_eliminator 2.21% : 0.000043s : 243: predicate.tuple_list_set_item_eliminator 1.55% : 0.000030s : 186: predicate.tuple_to_list_eliminator_ 2.33% : 0.000045s : 319: predicate.updatestate_pure_node_eliminater 2.98% : 0.000057s : 389: predicate.updatestate_useless_node_eliminater 0.18% : 0.000004s : 21: predicate.value_based_eliminate 0.37% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.35% : 0.000007s : 43: predicate.virtual_output_eliminate 0.15% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.018094 133 54.93% : 0.009939s : 53: func_graph_cloner_run.FuncGraphClonerGraph 45.07% : 0.008156s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.435702 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.73% : 0.017665s : 1: add_attr 0.72% : 0.017641s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000183s : 1: add_recomputation 0.00% : 0.000013s : 1: assign_add_opt 0.04% : 0.000859s : 1: auto_monad 0.00% : 0.000101s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.03% : 0.000775s : 1: bootstrap 0.00% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000090s : 1: control_data_broadcast_order 0.00% : 0.000040s : 1: convert_after_rewriter 0.00% : 0.000084s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.01% : 0.000232s : 1: event_method 0.00% : 0.000010s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000061s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000010s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000658s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 3.94% : 0.096081s : 1: micro_interleaved_order_control 0.03% : 0.000831s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000045s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 4.50% : 0.109682s : 95: opt.transform.opt_a 0.01% : 0.000164s : 1: opt.transform.opt_after_cconv 0.00% : 0.000092s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000633s : 28: opt.transform.opt_b 0.01% : 0.000250s : 2: opt.transform.opt_trans_graph 0.01% : 0.000237s : 4: opt.transform.symbol_engine_opt 8.91% : 0.217127s : 1: opt_a 0.01% : 0.000359s : 1: opt_after_cconv 0.04% : 0.000963s : 1: opt_after_jit_grad 0.04% : 0.000916s : 1: opt_b 13.14% : 0.320142s : 1: optimize 0.00% : 0.000056s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.00% : 0.000080s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 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% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000014s : 1: parallel-infer-symbol 0.00% : 0.000009s : 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 0.01% : 0.000347s : 1: pre_auto_parallel 0.01% : 0.000296s : 1: py_interpret_to_execute 0.00% : 0.000043s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000124s : 1: remove_dup_value 3.90% : 0.094887s : 1: renormalize.infer 0.40% : 0.009860s : 1: renormalize.specialize 0.00% : 0.000011s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000941s : 1: rewriter_after_opt_a 0.03% : 0.000825s : 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% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000675s : 1: symbol_engine_optimizer 0.01% : 0.000288s : 1: tuple_transform 63.26% : 1.540899s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_0[True-mstype0-k_n_shape1-1024] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_ffn_0[True-mstype0-k_n_shape1-1024],max_mem:234.0M =============================== 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 397.23s (0:06:37) ==================