==================================================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_007/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(170592:281473379729200,MainProcess):2026-01-29-17:37:43.260.62 [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 = 1.62657, [21] [bootstrap]: 0.0148258 [type_inference]: 1.51111 [event_method]: 1.787e-05 [auto_monad]: 0.00140907 [graph_reusing]: 8.01001e-06 [inline]: 3.43e-06 [add_attr]: 0.00805085, [1] [add_attr_with_inline]: 0.00803466, [1] [Cycle 1]: 0.00010028, [2] [tag_attr]: 2.373e-05 [meta_addattr_fg_expand]: 5.14e-06 [parallel-infer-symbol]: 4.08999e-06 [pre_auto_parallel]: 4.976e-05 [insert-virtual-dataset]: 2.81999e-06 [parallel-infer-symbol-second]: 9.09989e-07 [dataset_repeat_opt]: 2.04999e-06 [pipeline_split]: 1.68002e-06 [optimize]: 0.0900148, [53] [py_interpret_to_execute]: 3.266e-05 [rewriter_before_opt_a]: 9.847e-05 [opt_a]: 0.0857917, [2] [Cycle 1]: 0.0836211, [45] [expand_dump_flag]: 3.14001e-06 [switch_simplify]: 3.82e-05 [loop_unroll]: 2.318e-05 [a_1]: 0.00078835 [with_stream_mark]: 2.844e-05 [recompute_prepare]: 2.044e-05 [updatestate_depend_eliminate]: 1.246e-05 [updatestate_assign_eliminate]: 1.412e-05 [updatestate_loads_eliminate]: 9.04e-05 [parameter_eliminate]: 2.29001e-06 [a_2]: 0.00030265 [accelerated_algorithm]: 4.922e-05 [shard]: 2.89999e-06 [meta_shard_fg_expand]: 3.85e-06 [shard_inline]: 2.045e-05 [merge_send_recv]: 3.258e-05 [auto_parallel]: 1.498e-05 [parallel]: 4.101e-05 [flash_sp]: 1.953e-05 [merge_comm]: 1.12e-05 [allreduce_fusion]: 9.86e-06 [matmul_add_comm_reduction]: 1.951e-05 [allreduce_slice_to_reducescatter]: 7.40023e-07 [virtual_shard_identity]: 2.349e-05 [virtual_dataset]: 2.009e-05 [get_grad_eliminate_]: 1.953e-05 [virtual_output]: 1.954e-05 [merge_forward]: 1.063e-05 [cell_reuse_recompute_pass]: 2.11e-06 [offload_activation]: 1.885e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.642e-05 [merge_recompute_call_nodes]: 2.16e-06 [before_grad]: 3.223e-05 [set_forward_comm_id_for_comm_node_pass]: 1.112e-05 [meta_fg_expand]: 7.43999e-06 [flash_sp_send_recv_attached]: 5.56002e-06 [receive_attached]: 1.122e-05 [after_resolve]: 2.962e-05 [a_after_grad]: 3.1e-05 [renormalize]: 0.0807239 [add_forward_monad_depend]: 1.854e-05 [auto_monad_grad]: 2.87002e-06 [auto_monad_eliminator]: 6.739e-05 [cse]: 0.00040294 [a_3]: 0.00017397 [Cycle 2]: 0.00215574, [45] [expand_dump_flag]: 2.83e-06 [switch_simplify]: 2.447e-05 [loop_unroll]: 2.167e-05 [a_1]: 0.00065934 [with_stream_mark]: 3.044e-05 [recompute_prepare]: 2.216e-05 [updatestate_depend_eliminate]: 1.287e-05 [updatestate_assign_eliminate]: 1.216e-05 [updatestate_loads_eliminate]: 5.017e-05 [parameter_eliminate]: 3.14999e-06 [a_2]: 0.00031776 [accelerated_algorithm]: 3.054e-05 [shard]: 2.58998e-06 [meta_shard_fg_expand]: 7.00998e-06 [shard_inline]: 2.047e-05 [merge_send_recv]: 1.913e-05 [auto_parallel]: 1.846e-05 [parallel]: 1.058e-05 [flash_sp]: 5.02e-06 [merge_comm]: 1.164e-05 [allreduce_fusion]: 1.041e-05 [matmul_add_comm_reduction]: 2.062e-05 [allreduce_slice_to_reducescatter]: 1.02e-06 [virtual_shard_identity]: 2.018e-05 [virtual_dataset]: 2.059e-05 [get_grad_eliminate_]: 1.987e-05 [virtual_output]: 1.796e-05 [merge_forward]: 1.126e-05 [cell_reuse_recompute_pass]: 3.76999e-06 [offload_activation]: 2.033e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.812e-05 [merge_recompute_call_nodes]: 2.26998e-06 [before_grad]: 3.432e-05 [set_forward_comm_id_for_comm_node_pass]: 1.146e-05 [meta_fg_expand]: 8.13999e-06 [flash_sp_send_recv_attached]: 1.83002e-06 [receive_attached]: 2.44001e-06 [after_resolve]: 2.94e-05 [a_after_grad]: 3.064e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.51e-06 [auto_monad_grad]: 2.04e-06 [auto_monad_eliminator]: 4.394e-05 [cse]: 0.00014382 [a_3]: 0.00012619 [py_interpret_to_execute_after_opt_a]: 3.285e-05 [slice_cell_reuse_recomputed_activation]: 2.59999e-06 [rewriter_after_opt_a]: 0.00024862 [convert_after_rewriter]: 1.992e-05 [order_py_execute_after_rewriter]: 1.2e-05 [mutable_eliminate]: 0.0008646 [opt_b]: 0.00072366, [1] [Cycle 1]: 0.00071454, [7] [b_1]: 0.00049493 [b_2]: 2.447e-05 [updatestate_depend_eliminate]: 1.739e-05 [updatestate_assign_eliminate]: 1.184e-05 [updatestate_loads_eliminate]: 1.653e-05 [renormalize]: 9.00007e-07 [cse]: 0.00010382 [optimize_parallel_all_gather_comm]: 3.858e-05 [overlap_param_gather]: 2.16e-06 [cconv]: 3.77e-05 [loop_unroll]: 0.00058444 [opt_after_cconv]: 0.00030012, [1] [Cycle 1]: 0.00029154, [7] [c_1]: 0.00013988 [parameter_eliminate]: 5.03002e-06 [updatestate_depend_eliminate]: 1.408e-05 [updatestate_assign_eliminate]: 1.029e-05 [updatestate_loads_eliminate]: 1.233e-05 [cse]: 6.979e-05 [renormalize]: 6.39993e-07 [remove_dup_value]: 7.905e-05 [tuple_transform]: 0.00026206, [1] [Cycle 1]: 0.00025552, [4] [d_1]: 0.00020273 [none_parameter_eliminate]: 2.89999e-06 [renormalize]: 4.09986e-07 [switch_simplify]: 2.269e-05 [partial_unused_args_eliminate]: 2.14e-06 [add_recomputation]: 0.00013961 [cse_after_recomputation]: 7.371e-05, [1] [Cycle 1]: 6.771e-05, [1] [cse]: 5.931e-05 [environ_conv]: 3.376e-05 [swap_dp_allreduce_reducescatter]: 1.563e-05 [bias_add_comm_swap]: 3.36999e-06 [label_micro_interleaved_index]: 4.60001e-06 [label_fine_grained_interleaved_index]: 2.96999e-06 [merge_cast_opt]: 1.81e-06 [slice_recompute_activation]: 2.14999e-06 [micro_interleaved_order_control]: 2.64999e-06 [assign_add_opt]: 1.45999e-06 [ForceFp32Comm]: 1.21002e-06 [remove_cast_before_assign_add]: 1.52001e-06 [full_micro_interleaved_order_control]: 2.14e-06 [reorder_send_recv_between_fp_bp]: 2.63998e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 9.49978e-07 [interleave_split_concat_branches]: 1.32999e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 2.376e-05 [overlap_opt_shard_grad_in_pipeline]: 1.84e-06 [control_data_broadcast_order]: 3.41e-05 [grouped_pairwise_exchange_alltoall]: 1.42e-06 [offloading_packed_experts]: 9.29e-06 [overlap_recompute_and_grad_model_parallel]: 9.32999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.55999e-06 [overlap_recompute_comm]: 2.12001e-06 [overlap_grad_ring_attention]: 8.48001e-06 [overlap_grad_flash_sp]: 5.706e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.01998e-06 [split_layernorm_comm]: 1.90001e-06 [handle_group_info]: 1.10001e-06 [symbol_engine_optimizer]: 0.00017767, [1] [Cycle 1]: 0.00017169, [6] [build]: 1.812e-05 [elim_shapecalc]: 2.674e-05 [elim_not_effective]: 3.718e-05 [opt_reshape]: 2.433e-05 [fold_const_symbol]: 3.043e-05 [renormalize]: 3.30008e-07 [detach_backward]: 2.31e-06 [pipeline_parallel_scheduler]: 1.50001e-06 [auto_monad_reorder]: 6.745e-05 [get_jit_bprop_graph]: 1.67999e-06 [rewriter_after_jit_bprop_graph]: 5.84e-06 [opt_after_jit_grad]: 0.00065139 [validate]: 0.00011305 Sums bootstrap : 0.014826s : 0.92% type_inference : 1.511112s : 93.44% event_method : 0.000018s : 0.00% auto_monad : 0.001409s : 0.09% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000033s : 0.00% optimize.rewriter_before_opt_a : 0.000098s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000063s : 0.00% optimize.opt_a.loop_unroll : 0.000045s : 0.00% optimize.opt_a.a_1 : 0.001448s : 0.09% optimize.opt_a.with_stream_mark : 0.000059s : 0.00% optimize.opt_a.recompute_prepare : 0.000043s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000141s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000620s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000080s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.00% optimize.opt_a.shard_inline : 0.000041s : 0.00% optimize.opt_a.merge_send_recv : 0.000052s : 0.00% optimize.opt_a.auto_parallel : 0.000033s : 0.00% optimize.opt_a.parallel : 0.000052s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000023s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000040s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000044s : 0.00% optimize.opt_a.virtual_dataset : 0.000041s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000039s : 0.00% optimize.opt_a.virtual_output : 0.000037s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000075s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000067s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000023s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000014s : 0.00% optimize.opt_a.after_resolve : 0.000059s : 0.00% optimize.opt_a.a_after_grad : 0.000062s : 0.00% optimize.opt_a.renormalize : 0.080724s : 4.99% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000111s : 0.01% optimize.opt_a.cse : 0.000547s : 0.03% optimize.opt_a.a_3 : 0.000300s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000249s : 0.02% optimize.convert_after_rewriter : 0.000020s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000865s : 0.05% optimize.opt_b.b_1 : 0.000495s : 0.03% optimize.opt_b.b_2 : 0.000024s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000104s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000039s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.00% optimize.loop_unroll : 0.000584s : 0.04% optimize.opt_after_cconv.c_1 : 0.000140s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000070s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000079s : 0.00% optimize.tuple_transform.d_1 : 0.000203s : 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 : 0.000023s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000140s : 0.01% optimize.cse_after_recomputation.cse : 0.000059s : 0.00% optimize.environ_conv : 0.000034s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 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 : 0.000024s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000034s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000057s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000027s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000024s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000030s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000067s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000651s : 0.04% validate : 0.000113s : 0.01% Time group info: ------[substitution.] 0.000405 138 9.16% : 0.000037s : 4: substitution.arithmetic_simplify 2.69% : 0.000011s : 2: substitution.depend_value_elim 1.32% : 0.000005s : 11: substitution.elim_not_effective 1.09% : 0.000004s : 11: substitution.fold_const_symbol 4.15% : 0.000017s : 17: substitution.graph_param_transform 28.44% : 0.000115s : 1: substitution.inline 2.80% : 0.000011s : 22: substitution.j_node_and_user_rematch 6.62% : 0.000027s : 6: substitution.less_batch_normalization 2.20% : 0.000009s : 12: substitution.load_eliminater 0.56% : 0.000002s : 2: substitution.opt_reshape 4.00% : 0.000016s : 22: substitution.remove_not_recompute_node 2.39% : 0.000010s : 6: substitution.replace_old_param 9.81% : 0.000040s : 4: substitution.reshape_eliminate 3.59% : 0.000015s : 8: substitution.updatestate_pure_node_eliminater 21.17% : 0.000086s : 10: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.511010 2 99.73% : 1.506921s : 1: type_inference.infer 0.27% : 0.004089s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000114 1 100.00% : 0.000114s : 1: match.inline ------[predicate.] 0.000570 3905 0.80% : 0.000005s : 35: predicate.accumulaten_eliminater 0.88% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.78% : 0.000004s : 34: predicate.addn_check_dump 0.85% : 0.000005s : 35: predicate.addn_zero_filter 0.73% : 0.000004s : 35: predicate.adjust_all_reduce_mul_add 2.22% : 0.000013s : 69: predicate.arithmetic_simplify 0.83% : 0.000005s : 35: predicate.cast_eliminate 0.83% : 0.000005s : 34: predicate.check_bprop_eliminate 0.84% : 0.000005s : 34: predicate.compare_switch_simplify 0.27% : 0.000002s : 17: predicate.const_output_eliminate 0.88% : 0.000005s : 34: predicate.depend_value_elim 0.84% : 0.000005s : 35: predicate.dict_get_item_const_eliminator 0.96% : 0.000005s : 35: predicate.dict_get_item_eliminator 0.76% : 0.000004s : 35: predicate.dict_set_item_eliminator 1.04% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.28% : 0.000002s : 17: predicate.elim_not_effective 0.57% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000007s : 52: predicate.environ_add_const_eliminate 1.11% : 0.000006s : 52: predicate.environ_get_add_eliminate 1.14% : 0.000006s : 52: predicate.environ_get_depend_swap 2.05% : 0.000012s : 86: predicate.environ_get_eliminate 1.14% : 0.000006s : 52: predicate.environ_get_set_eliminate 0.84% : 0.000005s : 36: predicate.exchange_switch_depend_value 1.27% : 0.000007s : 36: predicate.float_depend_g_call 0.81% : 0.000005s : 34: predicate.float_environ_get_switch 1.21% : 0.000007s : 51: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 17: predicate.fold_const_symbol 0.91% : 0.000005s : 34: predicate.get_grad_eliminate 0.30% : 0.000002s : 17: predicate.graph_param_transform 0.82% : 0.000005s : 34: predicate.incorporate_call 0.75% : 0.000004s : 34: predicate.incorporate_call_switch 5.48% : 0.000031s : 173: predicate.inline 1.01% : 0.000006s : 34: predicate.inline_without_move 0.48% : 0.000003s : 34: predicate.j_node_and_user_rematch 1.28% : 0.000007s : 34: predicate.less_batch_normalization 1.69% : 0.000010s : 69: predicate.list_to_tuple_eliminator_ 2.45% : 0.000014s : 104: predicate.load_eliminater 0.98% : 0.000006s : 17: predicate.loop_unroll_after_grad 1.06% : 0.000006s : 39: predicate.loop_unroll_before_grad 1.74% : 0.000010s : 69: predicate.make_slice_get_slice_eliminator 0.81% : 0.000005s : 34: predicate.merge_addn 0.79% : 0.000004s : 34: predicate.micro_step_allgather_replace 0.77% : 0.000004s : 34: predicate.mini_step_allgather_replace 0.79% : 0.000004s : 35: predicate.minmaximum_grad 0.96% : 0.000005s : 17: predicate.mutable_eliminate 0.47% : 0.000003s : 17: predicate.opt_reshape 0.47% : 0.000003s : 17: predicate.parallel_virtual_node 1.03% : 0.000006s : 36: predicate.partial_defer_inline 1.30% : 0.000007s : 52: predicate.partial_eliminate 0.78% : 0.000004s : 35: predicate.print_const_string_wrapper 0.81% : 0.000005s : 34: predicate.reduce_all_const_elim 1.05% : 0.000006s : 35: predicate.reduce_eliminate 2.36% : 0.000013s : 104: predicate.redundant_stop_gradient_eliminater 0.50% : 0.000003s : 34: predicate.remove_not_recompute_node 1.38% : 0.000008s : 69: predicate.replace_applicator 0.58% : 0.000003s : 34: predicate.replace_old_param 0.36% : 0.000002s : 17: predicate.reset_defer_inline 0.91% : 0.000005s : 35: predicate.reshape_eliminate 0.83% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.53% : 0.000003s : 17: predicate.row_tensor_eliminate 1.33% : 0.000008s : 34: predicate.same_eliminate 0.56% : 0.000003s : 34: predicate.set_cell_output_no_recompute 0.88% : 0.000005s : 34: predicate.shard_identity_eliminate 0.99% : 0.000006s : 34: predicate.special_op_eliminate 0.96% : 0.000005s : 34: predicate.specialize_transform 1.23% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.94% : 0.000005s : 34: predicate.stack_unstack_eliminate 0.48% : 0.000003s : 17: predicate.switch_call_monad_eliminater 0.85% : 0.000005s : 36: predicate.switch_defer_inline 1.67% : 0.000010s : 70: predicate.switch_layer_defer_inline 3.44% : 0.000020s : 126: predicate.switch_simplify 0.80% : 0.000005s : 35: predicate.tile_eliminate 0.78% : 0.000004s : 35: predicate.transpose_eliminate 1.79% : 0.000010s : 69: predicate.tuple_list_convert_item_index_to_positive 1.65% : 0.000009s : 69: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000009s : 69: predicate.tuple_list_get_item_depend_reorder 3.05% : 0.000017s : 103: predicate.tuple_list_get_item_eliminator 1.81% : 0.000010s : 69: predicate.tuple_list_get_set_item_eliminator 2.76% : 0.000016s : 103: predicate.tuple_list_set_item_eliminator 1.65% : 0.000009s : 69: predicate.tuple_to_list_eliminator_ 2.33% : 0.000013s : 104: predicate.updatestate_pure_node_eliminater 3.38% : 0.000019s : 138: predicate.updatestate_useless_node_eliminater 0.49% : 0.000003s : 17: predicate.value_based_eliminate 0.90% : 0.000005s : 34: predicate.virtual_dataset_eliminate 0.84% : 0.000005s : 34: predicate.virtual_output_eliminate 0.39% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.58% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.010005 58 77.87% : 0.007791s : 55: func_graph_cloner_run.FuncGraphClonerGraph 22.13% : 0.002214s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.809157 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.45% : 0.008056s : 1: add_attr 0.44% : 0.008039s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000145s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.001432s : 1: auto_monad 0.00% : 0.000073s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.82% : 0.014877s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000038s : 1: control_data_broadcast_order 0.00% : 0.000024s : 1: convert_after_rewriter 0.00% : 0.000077s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000038s : 1: environ_conv 0.00% : 0.000025s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.03% : 0.000594s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.05% : 0.000877s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000042s : 1: opt.transform.mutable_eliminate 0.16% : 0.002938s : 78: opt.transform.opt_a 0.01% : 0.000138s : 1: opt.transform.opt_after_cconv 0.00% : 0.000071s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000479s : 28: opt.transform.opt_b 0.01% : 0.000222s : 2: opt.transform.opt_trans_graph 0.01% : 0.000114s : 4: opt.transform.symbol_engine_opt 4.74% : 0.085796s : 1: opt_a 0.02% : 0.000304s : 1: opt_after_cconv 0.04% : 0.000662s : 1: opt_after_jit_grad 0.04% : 0.000729s : 1: opt_b 4.98% : 0.090021s : 1: optimize 0.00% : 0.000043s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000061s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000055s : 1: pre_auto_parallel 0.00% : 0.000037s : 1: py_interpret_to_execute 0.00% : 0.000037s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000084s : 1: remove_dup_value 4.32% : 0.078090s : 1: renormalize.infer 0.14% : 0.002618s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000255s : 1: rewriter_after_opt_a 0.01% : 0.000103s : 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% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000181s : 1: symbol_engine_optimizer 0.01% : 0.000265s : 1: tuple_transform 83.53% : 1.511142s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[False-mstype0-1024-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[False-mstype0-1024-32],max_mem:102.0M [WARNING] ME(170592:281473379729200,MainProcess):2026-01-29-17:38:13.224.524 [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 = 3.2343, [21] [bootstrap]: 0.00062269 [type_inference]: 2.92255 [event_method]: 2.117e-05 [auto_monad]: 0.00037505 [graph_reusing]: 7.08998e-06 [inline]: 3.58e-06 [add_attr]: 0.00763229, [1] [add_attr_with_inline]: 0.00761266, [1] [Cycle 1]: 8.298e-05, [2] [tag_attr]: 2.669e-05 [meta_addattr_fg_expand]: 5.35001e-06 [parallel-infer-symbol]: 3.83999e-06 [pre_auto_parallel]: 4.005e-05 [insert-virtual-dataset]: 2.26998e-06 [parallel-infer-symbol-second]: 1.15999e-06 [dataset_repeat_opt]: 1.81998e-06 [pipeline_split]: 1.55001e-06 [optimize]: 0.301912, [53] [py_interpret_to_execute]: 3.824e-05 [rewriter_before_opt_a]: 9.447e-05 [opt_a]: 0.297922, [2] [Cycle 1]: 0.295926, [45] [expand_dump_flag]: 3.01999e-06 [switch_simplify]: 3.822e-05 [loop_unroll]: 2.472e-05 [a_1]: 0.00103202 [with_stream_mark]: 0.280081 [recompute_prepare]: 8.371e-05 [updatestate_depend_eliminate]: 2.949e-05 [updatestate_assign_eliminate]: 1.155e-05 [updatestate_loads_eliminate]: 0.00012732 [parameter_eliminate]: 5.52999e-06 [a_2]: 0.00037847 [accelerated_algorithm]: 6.786e-05 [shard]: 3.63e-06 [meta_shard_fg_expand]: 8.47e-06 [shard_inline]: 2.191e-05 [merge_send_recv]: 1.83e-05 [auto_parallel]: 1.851e-05 [parallel]: 3.289e-05 [flash_sp]: 1.442e-05 [merge_comm]: 1.162e-05 [allreduce_fusion]: 1.054e-05 [matmul_add_comm_reduction]: 2.15e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 2.86e-05 [virtual_dataset]: 1.981e-05 [get_grad_eliminate_]: 2.066e-05 [virtual_output]: 2.049e-05 [merge_forward]: 1.154e-05 [cell_reuse_recompute_pass]: 3.46001e-06 [offload_activation]: 2.085e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.744e-05 [merge_recompute_call_nodes]: 1.60001e-06 [before_grad]: 3.48e-05 [set_forward_comm_id_for_comm_node_pass]: 1.053e-05 [meta_fg_expand]: 8.15e-06 [flash_sp_send_recv_attached]: 6.36e-06 [receive_attached]: 2.07999e-06 [after_resolve]: 2.977e-05 [a_after_grad]: 3.206e-05 [renormalize]: 0.0117642 [add_forward_monad_depend]: 1.823e-05 [auto_monad_grad]: 3.13e-06 [auto_monad_eliminator]: 6.852e-05 [cse]: 0.00117217 [a_3]: 0.00016297 [Cycle 2]: 0.00198205, [45] [expand_dump_flag]: 3.65e-06 [switch_simplify]: 2.39e-05 [loop_unroll]: 1.977e-05 [a_1]: 0.00061503 [with_stream_mark]: 3.261e-05 [recompute_prepare]: 2.085e-05 [updatestate_depend_eliminate]: 1.307e-05 [updatestate_assign_eliminate]: 1.132e-05 [updatestate_loads_eliminate]: 1.574e-05 [parameter_eliminate]: 2.02001e-06 [a_2]: 0.00028066 [accelerated_algorithm]: 2.94e-05 [shard]: 2.64999e-06 [meta_shard_fg_expand]: 6.78e-06 [shard_inline]: 2.011e-05 [merge_send_recv]: 1.669e-05 [auto_parallel]: 3.29e-05 [parallel]: 9.64999e-06 [flash_sp]: 3.9e-06 [merge_comm]: 1.269e-05 [allreduce_fusion]: 9.94001e-06 [matmul_add_comm_reduction]: 2.27e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 2.419e-05 [virtual_dataset]: 1.893e-05 [get_grad_eliminate_]: 1.992e-05 [virtual_output]: 1.892e-05 [merge_forward]: 1.174e-05 [cell_reuse_recompute_pass]: 2.88e-06 [offload_activation]: 2.093e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.706e-05 [merge_recompute_call_nodes]: 1.51002e-06 [before_grad]: 3.33e-05 [set_forward_comm_id_for_comm_node_pass]: 1.126e-05 [meta_fg_expand]: 9.07001e-06 [flash_sp_send_recv_attached]: 2.35002e-06 [receive_attached]: 2.34999e-06 [after_resolve]: 2.822e-05 [a_after_grad]: 3.087e-05 [renormalize]: 1.30007e-07 [add_forward_monad_depend]: 3.23e-06 [auto_monad_grad]: 3.19001e-06 [auto_monad_eliminator]: 5.793e-05 [cse]: 7.464e-05 [a_3]: 0.00012534 [py_interpret_to_execute_after_opt_a]: 3.122e-05 [slice_cell_reuse_recomputed_activation]: 2.59999e-06 [rewriter_after_opt_a]: 0.00020769 [convert_after_rewriter]: 1.876e-05 [order_py_execute_after_rewriter]: 1.069e-05 [mutable_eliminate]: 0.00077824 [opt_b]: 0.00066516, [1] [Cycle 1]: 0.00065523, [7] [b_1]: 0.00046138 [b_2]: 2.454e-05 [updatestate_depend_eliminate]: 1.798e-05 [updatestate_assign_eliminate]: 1.19e-05 [updatestate_loads_eliminate]: 1.504e-05 [renormalize]: 8.79983e-07 [cse]: 7.85e-05 [optimize_parallel_all_gather_comm]: 3.456e-05 [overlap_param_gather]: 2.04e-06 [cconv]: 4.226e-05 [loop_unroll]: 0.0006002 [opt_after_cconv]: 0.00030755, [1] [Cycle 1]: 0.00029989, [7] [c_1]: 0.00014001 [parameter_eliminate]: 6.41998e-06 [updatestate_depend_eliminate]: 1.663e-05 [updatestate_assign_eliminate]: 1.027e-05 [updatestate_loads_eliminate]: 1.379e-05 [cse]: 7.356e-05 [renormalize]: 8.2e-07 [remove_dup_value]: 8.541e-05 [tuple_transform]: 0.00019698, [1] [Cycle 1]: 0.00018966, [4] [d_1]: 0.00014703 [none_parameter_eliminate]: 1.62001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 2e-05 [partial_unused_args_eliminate]: 2.39001e-06 [add_recomputation]: 0.00012789 [cse_after_recomputation]: 8.518e-05, [1] [Cycle 1]: 7.866e-05, [1] [cse]: 7.048e-05 [environ_conv]: 2.476e-05 [swap_dp_allreduce_reducescatter]: 1.502e-05 [bias_add_comm_swap]: 3.7e-06 [label_micro_interleaved_index]: 5.81998e-06 [label_fine_grained_interleaved_index]: 3.00002e-06 [merge_cast_opt]: 1.58997e-06 [slice_recompute_activation]: 2.56e-06 [micro_interleaved_order_control]: 2.68998e-06 [assign_add_opt]: 1.22e-06 [ForceFp32Comm]: 1.27e-06 [remove_cast_before_assign_add]: 1.13001e-06 [full_micro_interleaved_order_control]: 2.57001e-06 [reorder_send_recv_between_fp_bp]: 2.99001e-06 [comm_op_add_attrs]: 1.29e-06 [add_comm_op_reuse_tag]: 1.43002e-06 [interleave_split_concat_branches]: 1.50999e-06 [interleave_parallel_branches]: 1.19e-06 [overlap_opt_shard_in_pipeline]: 1.66e-06 [overlap_opt_shard_grad_in_pipeline]: 2.09999e-06 [control_data_broadcast_order]: 3.302e-05 [grouped_pairwise_exchange_alltoall]: 1.52999e-06 [offloading_packed_experts]: 9.00999e-06 [overlap_recompute_and_grad_model_parallel]: 9.20001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.30001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.74998e-06 [overlap_recompute_comm]: 2.47001e-06 [overlap_grad_ring_attention]: 7.81001e-06 [overlap_grad_flash_sp]: 4.613e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.46e-06 [split_layernorm_comm]: 1.84998e-06 [handle_group_info]: 1.05001e-06 [symbol_engine_optimizer]: 0.00020066, [1] [Cycle 1]: 0.00019354, [6] [build]: 2.109e-05 [elim_shapecalc]: 3.72e-05 [elim_not_effective]: 4.047e-05 [opt_reshape]: 2.788e-05 [fold_const_symbol]: 3.024e-05 [renormalize]: 3.80009e-07 [detach_backward]: 2.22999e-06 [pipeline_parallel_scheduler]: 1.68002e-06 [auto_monad_reorder]: 6.995e-05 [get_jit_bprop_graph]: 2.48e-06 [rewriter_after_jit_bprop_graph]: 7.13998e-06 [opt_after_jit_grad]: 0.00072394 [validate]: 0.00010298 Sums bootstrap : 0.000623s : 0.02% type_inference : 2.922554s : 90.61% event_method : 0.000021s : 0.00% auto_monad : 0.000375s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000040s : 0.00% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000094s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000062s : 0.00% optimize.opt_a.loop_unroll : 0.000044s : 0.00% optimize.opt_a.a_1 : 0.001647s : 0.05% optimize.opt_a.with_stream_mark : 0.280113s : 8.68% optimize.opt_a.recompute_prepare : 0.000105s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000143s : 0.00% optimize.opt_a.parameter_eliminate : 0.000008s : 0.00% optimize.opt_a.a_2 : 0.000659s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000097s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000015s : 0.00% optimize.opt_a.shard_inline : 0.000042s : 0.00% optimize.opt_a.merge_send_recv : 0.000035s : 0.00% optimize.opt_a.auto_parallel : 0.000051s : 0.00% optimize.opt_a.parallel : 0.000043s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000024s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000044s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000053s : 0.00% optimize.opt_a.virtual_dataset : 0.000039s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000041s : 0.00% optimize.opt_a.virtual_output : 0.000039s : 0.00% optimize.opt_a.merge_forward : 0.000023s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000042s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000074s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000068s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.00% optimize.opt_a.meta_fg_expand : 0.000017s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000058s : 0.00% optimize.opt_a.a_after_grad : 0.000063s : 0.00% optimize.opt_a.renormalize : 0.011764s : 0.36% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000126s : 0.00% optimize.opt_a.cse : 0.001247s : 0.04% optimize.opt_a.a_3 : 0.000288s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000208s : 0.01% optimize.convert_after_rewriter : 0.000019s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000778s : 0.02% optimize.opt_b.b_1 : 0.000461s : 0.01% optimize.opt_b.b_2 : 0.000025s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000078s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000600s : 0.02% optimize.opt_after_cconv.c_1 : 0.000140s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000074s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000085s : 0.00% optimize.tuple_transform.d_1 : 0.000147s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000020s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000128s : 0.00% optimize.cse_after_recomputation.cse : 0.000070s : 0.00% optimize.environ_conv : 0.000025s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000015s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 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 : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000033s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000046s : 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 : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000037s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000040s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000028s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000030s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000070s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000724s : 0.02% validate : 0.000103s : 0.00% Time group info: ------[substitution.] 0.000442 138 10.64% : 0.000047s : 4: substitution.arithmetic_simplify 2.70% : 0.000012s : 2: substitution.depend_value_elim 1.09% : 0.000005s : 11: substitution.elim_not_effective 0.90% : 0.000004s : 11: substitution.fold_const_symbol 3.25% : 0.000014s : 17: substitution.graph_param_transform 29.95% : 0.000132s : 1: substitution.inline 2.63% : 0.000012s : 22: substitution.j_node_and_user_rematch 8.84% : 0.000039s : 6: substitution.less_batch_normalization 1.97% : 0.000009s : 12: substitution.load_eliminater 0.81% : 0.000004s : 2: substitution.opt_reshape 3.44% : 0.000015s : 22: substitution.remove_not_recompute_node 2.57% : 0.000011s : 6: substitution.replace_old_param 7.14% : 0.000032s : 4: substitution.reshape_eliminate 3.73% : 0.000016s : 8: substitution.updatestate_pure_node_eliminater 20.36% : 0.000090s : 10: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.922430 2 99.79% : 2.916190s : 1: type_inference.infer 0.21% : 0.006240s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000131 1 100.00% : 0.000131s : 1: match.inline ------[predicate.] 0.000570 3905 0.81% : 0.000005s : 35: predicate.accumulaten_eliminater 0.84% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.82% : 0.000005s : 34: predicate.addn_check_dump 0.85% : 0.000005s : 35: predicate.addn_zero_filter 0.80% : 0.000005s : 35: predicate.adjust_all_reduce_mul_add 2.48% : 0.000014s : 69: predicate.arithmetic_simplify 0.80% : 0.000005s : 35: predicate.cast_eliminate 0.84% : 0.000005s : 34: predicate.check_bprop_eliminate 0.83% : 0.000005s : 34: predicate.compare_switch_simplify 0.24% : 0.000001s : 17: predicate.const_output_eliminate 0.87% : 0.000005s : 34: predicate.depend_value_elim 0.85% : 0.000005s : 35: predicate.dict_get_item_const_eliminator 0.87% : 0.000005s : 35: predicate.dict_get_item_eliminator 0.79% : 0.000004s : 35: predicate.dict_set_item_eliminator 1.00% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.32% : 0.000002s : 17: predicate.elim_not_effective 0.55% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000007s : 52: predicate.environ_add_const_eliminate 1.13% : 0.000006s : 52: predicate.environ_get_add_eliminate 1.11% : 0.000006s : 52: predicate.environ_get_depend_swap 1.92% : 0.000011s : 86: predicate.environ_get_eliminate 1.14% : 0.000006s : 52: predicate.environ_get_set_eliminate 0.79% : 0.000005s : 36: predicate.exchange_switch_depend_value 1.38% : 0.000008s : 36: predicate.float_depend_g_call 0.80% : 0.000005s : 34: predicate.float_environ_get_switch 1.19% : 0.000007s : 51: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 17: predicate.fold_const_symbol 0.89% : 0.000005s : 34: predicate.get_grad_eliminate 0.26% : 0.000001s : 17: predicate.graph_param_transform 0.81% : 0.000005s : 34: predicate.incorporate_call 0.72% : 0.000004s : 34: predicate.incorporate_call_switch 5.50% : 0.000031s : 173: predicate.inline 1.01% : 0.000006s : 34: predicate.inline_without_move 0.44% : 0.000003s : 34: predicate.j_node_and_user_rematch 1.15% : 0.000007s : 34: predicate.less_batch_normalization 1.78% : 0.000010s : 69: predicate.list_to_tuple_eliminator_ 2.42% : 0.000014s : 104: predicate.load_eliminater 1.01% : 0.000006s : 17: predicate.loop_unroll_after_grad 0.96% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.83% : 0.000010s : 69: predicate.make_slice_get_slice_eliminator 0.91% : 0.000005s : 34: predicate.merge_addn 0.78% : 0.000004s : 34: predicate.micro_step_allgather_replace 0.79% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.75% : 0.000004s : 35: predicate.minmaximum_grad 0.94% : 0.000005s : 17: predicate.mutable_eliminate 0.50% : 0.000003s : 17: predicate.opt_reshape 0.52% : 0.000003s : 17: predicate.parallel_virtual_node 1.11% : 0.000006s : 36: predicate.partial_defer_inline 1.29% : 0.000007s : 52: predicate.partial_eliminate 0.77% : 0.000004s : 35: predicate.print_const_string_wrapper 0.83% : 0.000005s : 34: predicate.reduce_all_const_elim 1.02% : 0.000006s : 35: predicate.reduce_eliminate 2.33% : 0.000013s : 104: predicate.redundant_stop_gradient_eliminater 0.52% : 0.000003s : 34: predicate.remove_not_recompute_node 1.32% : 0.000008s : 69: predicate.replace_applicator 0.59% : 0.000003s : 34: predicate.replace_old_param 0.42% : 0.000002s : 17: predicate.reset_defer_inline 0.90% : 0.000005s : 35: predicate.reshape_eliminate 0.81% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.54% : 0.000003s : 17: predicate.row_tensor_eliminate 1.17% : 0.000007s : 34: predicate.same_eliminate 0.73% : 0.000004s : 34: predicate.set_cell_output_no_recompute 1.02% : 0.000006s : 34: predicate.shard_identity_eliminate 0.94% : 0.000005s : 34: predicate.special_op_eliminate 1.03% : 0.000006s : 34: predicate.specialize_transform 1.24% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.99% : 0.000006s : 34: predicate.stack_unstack_eliminate 0.53% : 0.000003s : 17: predicate.switch_call_monad_eliminater 0.87% : 0.000005s : 36: predicate.switch_defer_inline 1.65% : 0.000009s : 70: predicate.switch_layer_defer_inline 3.58% : 0.000020s : 126: predicate.switch_simplify 0.81% : 0.000005s : 35: predicate.tile_eliminate 0.76% : 0.000004s : 35: predicate.transpose_eliminate 1.74% : 0.000010s : 69: predicate.tuple_list_convert_item_index_to_positive 1.94% : 0.000011s : 69: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000009s : 69: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000017s : 103: predicate.tuple_list_get_item_eliminator 1.65% : 0.000009s : 69: predicate.tuple_list_get_set_item_eliminator 2.59% : 0.000015s : 103: predicate.tuple_list_set_item_eliminator 1.62% : 0.000009s : 69: predicate.tuple_to_list_eliminator_ 2.26% : 0.000013s : 104: predicate.updatestate_pure_node_eliminater 3.38% : 0.000019s : 138: predicate.updatestate_useless_node_eliminater 0.46% : 0.000003s : 17: predicate.value_based_eliminate 0.93% : 0.000005s : 34: predicate.virtual_dataset_eliminate 0.85% : 0.000005s : 34: predicate.virtual_output_eliminate 0.39% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.50% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.269654 58 98.49% : 0.265578s : 55: func_graph_cloner_run.FuncGraphClonerGraph 1.51% : 0.004075s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.559652 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.21% : 0.007639s : 1: add_attr 0.21% : 0.007618s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000133s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000391s : 1: auto_monad 0.00% : 0.000077s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000653s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000036s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000088s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.00% : 0.000029s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000611s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000791s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000037s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000038s : 1: opt.transform.mutable_eliminate 0.09% : 0.003249s : 78: opt.transform.opt_a 0.00% : 0.000138s : 1: opt.transform.opt_after_cconv 0.00% : 0.000082s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000449s : 28: opt.transform.opt_b 0.00% : 0.000164s : 2: opt.transform.opt_trans_graph 0.00% : 0.000131s : 4: opt.transform.symbol_engine_opt 8.37% : 0.297926s : 1: opt_a 0.01% : 0.000312s : 1: opt_after_cconv 0.02% : 0.000737s : 1: opt_after_jit_grad 0.02% : 0.000669s : 1: opt_b 8.48% : 0.301918s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000051s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000045s : 1: pre_auto_parallel 0.00% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000091s : 1: remove_dup_value 0.21% : 0.007600s : 1: renormalize.infer 0.12% : 0.004147s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000215s : 1: rewriter_after_opt_a 0.00% : 0.000098s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000018s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000204s : 1: symbol_engine_optimizer 0.01% : 0.000200s : 1: tuple_transform 82.10% : 2.922586s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[False-mstype0-2048-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[False-mstype0-2048-32],max_mem:106.0M [WARNING] ME(170592:281473379729200,MainProcess):2026-01-29-17:38:26.376.163 [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 = 3.29057, [21] [bootstrap]: 0.00081542 [type_inference]: 3.05563 [event_method]: 1.537e-05 [auto_monad]: 0.00033072 [graph_reusing]: 5.49e-06 [inline]: 2.66e-06 [add_attr]: 0.00629004, [1] [add_attr_with_inline]: 0.00627329, [1] [Cycle 1]: 7.157e-05, [2] [tag_attr]: 2.381e-05 [meta_addattr_fg_expand]: 4.74002e-06 [parallel-infer-symbol]: 3.4e-06 [pre_auto_parallel]: 3.976e-05 [insert-virtual-dataset]: 2.76e-06 [parallel-infer-symbol-second]: 6.19999e-07 [dataset_repeat_opt]: 1.75001e-06 [pipeline_split]: 1.84e-06 [optimize]: 0.226239, [53] [py_interpret_to_execute]: 3.65e-05 [rewriter_before_opt_a]: 9.109e-05 [opt_a]: 0.220992, [2] [Cycle 1]: 0.219093, [45] [expand_dump_flag]: 3.55e-06 [switch_simplify]: 3.737e-05 [loop_unroll]: 2.492e-05 [a_1]: 0.00121378 [with_stream_mark]: 3.434e-05 [recompute_prepare]: 3.375e-05 [updatestate_depend_eliminate]: 1.293e-05 [updatestate_assign_eliminate]: 1.082e-05 [updatestate_loads_eliminate]: 8.066e-05 [parameter_eliminate]: 3.13998e-06 [a_2]: 0.00033792 [accelerated_algorithm]: 5.283e-05 [shard]: 2.56e-06 [meta_shard_fg_expand]: 4.48001e-06 [shard_inline]: 2.143e-05 [merge_send_recv]: 1.648e-05 [auto_parallel]: 1.518e-05 [parallel]: 3.549e-05 [flash_sp]: 1.235e-05 [merge_comm]: 1.058e-05 [allreduce_fusion]: 9.99999e-06 [matmul_add_comm_reduction]: 0.204616 [allreduce_slice_to_reducescatter]: 1.78002e-06 [virtual_shard_identity]: 8.079e-05 [virtual_dataset]: 2.531e-05 [get_grad_eliminate_]: 2.654e-05 [virtual_output]: 2.358e-05 [merge_forward]: 2.346e-05 [cell_reuse_recompute_pass]: 3.8e-06 [offload_activation]: 3.201e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.64e-05 [merge_recompute_call_nodes]: 2.93e-06 [before_grad]: 4.012e-05 [set_forward_comm_id_for_comm_node_pass]: 1.72e-05 [meta_fg_expand]: 1.207e-05 [flash_sp_send_recv_attached]: 1.395e-05 [receive_attached]: 2.54001e-06 [after_resolve]: 3.527e-05 [a_after_grad]: 3.865e-05 [renormalize]: 0.0104336 [add_forward_monad_depend]: 1.856e-05 [auto_monad_grad]: 3.11999e-06 [auto_monad_eliminator]: 6.486e-05 [cse]: 0.00097709 [a_3]: 0.00016061 [Cycle 2]: 0.00188488, [45] [expand_dump_flag]: 3.64002e-06 [switch_simplify]: 2.193e-05 [loop_unroll]: 1.936e-05 [a_1]: 0.00059962 [with_stream_mark]: 2.745e-05 [recompute_prepare]: 2.095e-05 [updatestate_depend_eliminate]: 1.116e-05 [updatestate_assign_eliminate]: 1.204e-05 [updatestate_loads_eliminate]: 1.61e-05 [parameter_eliminate]: 2.46998e-06 [a_2]: 0.00027538 [accelerated_algorithm]: 2.771e-05 [shard]: 2.24001e-06 [meta_shard_fg_expand]: 5.15999e-06 [shard_inline]: 1.803e-05 [merge_send_recv]: 1.687e-05 [auto_parallel]: 1.728e-05 [parallel]: 9.72999e-06 [flash_sp]: 5.27999e-06 [merge_comm]: 1.013e-05 [allreduce_fusion]: 9.92999e-06 [matmul_add_comm_reduction]: 1.962e-05 [allreduce_slice_to_reducescatter]: 8.30012e-07 [virtual_shard_identity]: 2.021e-05 [virtual_dataset]: 1.822e-05 [get_grad_eliminate_]: 1.819e-05 [virtual_output]: 1.881e-05 [merge_forward]: 1.058e-05 [cell_reuse_recompute_pass]: 1.744e-05 [offload_activation]: 1.985e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.614e-05 [merge_recompute_call_nodes]: 1.86998e-06 [before_grad]: 3.073e-05 [set_forward_comm_id_for_comm_node_pass]: 1.086e-05 [meta_fg_expand]: 8.86002e-06 [flash_sp_send_recv_attached]: 1.90001e-06 [receive_attached]: 2.41998e-06 [after_resolve]: 2.674e-05 [a_after_grad]: 3.03e-05 [renormalize]: 6.00121e-08 [add_forward_monad_depend]: 2.37001e-06 [auto_monad_grad]: 2.56998e-06 [auto_monad_eliminator]: 4.224e-05 [cse]: 6.171e-05 [a_3]: 0.00012476 [py_interpret_to_execute_after_opt_a]: 3.127e-05 [slice_cell_reuse_recomputed_activation]: 2.32001e-06 [rewriter_after_opt_a]: 0.00020497 [convert_after_rewriter]: 1.608e-05 [order_py_execute_after_rewriter]: 1.195e-05 [mutable_eliminate]: 0.00078386 [opt_b]: 0.00061365, [1] [Cycle 1]: 0.00060539, [7] [b_1]: 0.00043608 [b_2]: 2.19e-05 [updatestate_depend_eliminate]: 1.446e-05 [updatestate_assign_eliminate]: 1.01e-05 [updatestate_loads_eliminate]: 1.275e-05 [renormalize]: 8.49977e-07 [cse]: 6.838e-05 [optimize_parallel_all_gather_comm]: 3.295e-05 [overlap_param_gather]: 1.95001e-06 [cconv]: 3.508e-05 [loop_unroll]: 0.0007929 [opt_after_cconv]: 0.00034382, [1] [Cycle 1]: 0.0003325, [7] [c_1]: 0.00014887 [parameter_eliminate]: 5.45001e-06 [updatestate_depend_eliminate]: 2.02e-05 [updatestate_assign_eliminate]: 1.05e-05 [updatestate_loads_eliminate]: 1.516e-05 [cse]: 8.873e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 8.56e-05 [tuple_transform]: 0.00019572, [1] [Cycle 1]: 0.00019013, [4] [d_1]: 0.00014639 [none_parameter_eliminate]: 2.87002e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 2.057e-05 [partial_unused_args_eliminate]: 2.16998e-06 [add_recomputation]: 0.00013386 [cse_after_recomputation]: 7.209e-05, [1] [Cycle 1]: 6.511e-05, [1] [cse]: 5.725e-05 [environ_conv]: 2.202e-05 [swap_dp_allreduce_reducescatter]: 1.586e-05 [bias_add_comm_swap]: 3.42002e-06 [label_micro_interleaved_index]: 6.16e-06 [label_fine_grained_interleaved_index]: 2.66999e-06 [merge_cast_opt]: 1.53002e-06 [slice_recompute_activation]: 2.47001e-06 [micro_interleaved_order_control]: 2.43998e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 9.99979e-07 [remove_cast_before_assign_add]: 1.16002e-06 [full_micro_interleaved_order_control]: 2.31998e-06 [reorder_send_recv_between_fp_bp]: 2.78e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 9.70002e-07 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.02998e-06 [overlap_opt_shard_in_pipeline]: 1.27e-06 [overlap_opt_shard_grad_in_pipeline]: 2.04e-06 [control_data_broadcast_order]: 3.477e-05 [grouped_pairwise_exchange_alltoall]: 1.82001e-06 [offloading_packed_experts]: 8.3e-06 [overlap_recompute_and_grad_model_parallel]: 1.033e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.15001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.33002e-06 [overlap_recompute_comm]: 2.16998e-06 [overlap_grad_ring_attention]: 1.021e-05 [overlap_grad_flash_sp]: 4.502e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.26e-06 [split_layernorm_comm]: 1.79998e-06 [handle_group_info]: 1.02998e-06 [symbol_engine_optimizer]: 0.00018673, [1] [Cycle 1]: 0.00018093, [6] [build]: 2.093e-05 [elim_shapecalc]: 3.058e-05 [elim_not_effective]: 3.801e-05 [opt_reshape]: 2.402e-05 [fold_const_symbol]: 3.163e-05 [renormalize]: 1.8999e-07 [detach_backward]: 2.37999e-06 [pipeline_parallel_scheduler]: 1.54998e-06 [auto_monad_reorder]: 6.812e-05 [get_jit_bprop_graph]: 2.16998e-06 [rewriter_after_jit_bprop_graph]: 7.03998e-06 [opt_after_jit_grad]: 0.00078266 [validate]: 0.00011376 Sums bootstrap : 0.000815s : 0.02% type_inference : 3.055632s : 93.11% event_method : 0.000015s : 0.00% auto_monad : 0.000331s : 0.01% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000040s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000036s : 0.00% optimize.rewriter_before_opt_a : 0.000091s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000044s : 0.00% optimize.opt_a.a_1 : 0.001813s : 0.06% optimize.opt_a.with_stream_mark : 0.000062s : 0.00% optimize.opt_a.recompute_prepare : 0.000055s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000097s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000613s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000081s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000039s : 0.00% optimize.opt_a.merge_send_recv : 0.000033s : 0.00% optimize.opt_a.auto_parallel : 0.000032s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.204635s : 6.24% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000101s : 0.00% optimize.opt_a.virtual_dataset : 0.000044s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000045s : 0.00% optimize.opt_a.virtual_output : 0.000042s : 0.00% optimize.opt_a.merge_forward : 0.000034s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000021s : 0.00% optimize.opt_a.offload_activation : 0.000052s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000093s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000071s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000028s : 0.00% optimize.opt_a.meta_fg_expand : 0.000021s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000016s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000062s : 0.00% optimize.opt_a.a_after_grad : 0.000069s : 0.00% optimize.opt_a.renormalize : 0.010434s : 0.32% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000107s : 0.00% optimize.opt_a.cse : 0.001039s : 0.03% optimize.opt_a.a_3 : 0.000285s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000205s : 0.01% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000784s : 0.02% optimize.opt_b.b_1 : 0.000436s : 0.01% optimize.opt_b.b_2 : 0.000022s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000068s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000793s : 0.02% optimize.opt_after_cconv.c_1 : 0.000149s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.cse : 0.000089s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000086s : 0.00% optimize.tuple_transform.d_1 : 0.000146s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000021s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000134s : 0.00% optimize.cse_after_recomputation.cse : 0.000057s : 0.00% optimize.environ_conv : 0.000022s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000035s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000045s : 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 : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000031s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000038s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000024s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000032s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000068s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000783s : 0.02% validate : 0.000114s : 0.00% Time group info: ------[substitution.] 0.000442 138 7.85% : 0.000035s : 4: substitution.arithmetic_simplify 2.39% : 0.000011s : 2: substitution.depend_value_elim 1.45% : 0.000006s : 11: substitution.elim_not_effective 0.88% : 0.000004s : 11: substitution.fold_const_symbol 3.38% : 0.000015s : 17: substitution.graph_param_transform 28.52% : 0.000126s : 1: substitution.inline 2.50% : 0.000011s : 22: substitution.j_node_and_user_rematch 6.51% : 0.000029s : 6: substitution.less_batch_normalization 2.18% : 0.000010s : 12: substitution.load_eliminater 0.35% : 0.000002s : 2: substitution.opt_reshape 3.74% : 0.000017s : 22: substitution.remove_not_recompute_node 2.67% : 0.000012s : 6: substitution.replace_old_param 8.41% : 0.000037s : 4: substitution.reshape_eliminate 3.55% : 0.000016s : 8: substitution.updatestate_pure_node_eliminater 25.61% : 0.000113s : 10: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.055535 2 99.83% : 3.050291s : 1: type_inference.infer 0.17% : 0.005244s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000125 1 100.00% : 0.000125s : 1: match.inline ------[predicate.] 0.000579 3905 0.88% : 0.000005s : 35: predicate.accumulaten_eliminater 1.23% : 0.000007s : 17: predicate.ad_related_special_op_eliminate 0.77% : 0.000004s : 34: predicate.addn_check_dump 0.78% : 0.000005s : 35: predicate.addn_zero_filter 0.72% : 0.000004s : 35: predicate.adjust_all_reduce_mul_add 2.50% : 0.000014s : 69: predicate.arithmetic_simplify 0.82% : 0.000005s : 35: predicate.cast_eliminate 0.80% : 0.000005s : 34: predicate.check_bprop_eliminate 0.79% : 0.000005s : 34: predicate.compare_switch_simplify 0.23% : 0.000001s : 17: predicate.const_output_eliminate 0.83% : 0.000005s : 34: predicate.depend_value_elim 0.85% : 0.000005s : 35: predicate.dict_get_item_const_eliminator 0.92% : 0.000005s : 35: predicate.dict_get_item_eliminator 0.77% : 0.000004s : 35: predicate.dict_set_item_eliminator 1.16% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.28% : 0.000002s : 17: predicate.elim_not_effective 0.49% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000006s : 52: predicate.environ_add_const_eliminate 1.15% : 0.000007s : 52: predicate.environ_get_add_eliminate 1.14% : 0.000007s : 52: predicate.environ_get_depend_swap 1.94% : 0.000011s : 86: predicate.environ_get_eliminate 1.08% : 0.000006s : 52: predicate.environ_get_set_eliminate 0.83% : 0.000005s : 36: predicate.exchange_switch_depend_value 1.19% : 0.000007s : 36: predicate.float_depend_g_call 0.75% : 0.000004s : 34: predicate.float_environ_get_switch 1.09% : 0.000006s : 51: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 17: predicate.fold_const_symbol 1.04% : 0.000006s : 34: predicate.get_grad_eliminate 0.29% : 0.000002s : 17: predicate.graph_param_transform 0.83% : 0.000005s : 34: predicate.incorporate_call 0.72% : 0.000004s : 34: predicate.incorporate_call_switch 5.19% : 0.000030s : 173: predicate.inline 1.12% : 0.000006s : 34: predicate.inline_without_move 0.49% : 0.000003s : 34: predicate.j_node_and_user_rematch 1.10% : 0.000006s : 34: predicate.less_batch_normalization 1.67% : 0.000010s : 69: predicate.list_to_tuple_eliminator_ 2.30% : 0.000013s : 104: predicate.load_eliminater 1.63% : 0.000009s : 17: predicate.loop_unroll_after_grad 0.92% : 0.000005s : 39: predicate.loop_unroll_before_grad 1.67% : 0.000010s : 69: predicate.make_slice_get_slice_eliminator 0.79% : 0.000005s : 34: predicate.merge_addn 0.75% : 0.000004s : 34: predicate.micro_step_allgather_replace 0.75% : 0.000004s : 34: predicate.mini_step_allgather_replace 0.71% : 0.000004s : 35: predicate.minmaximum_grad 0.87% : 0.000005s : 17: predicate.mutable_eliminate 0.48% : 0.000003s : 17: predicate.opt_reshape 0.45% : 0.000003s : 17: predicate.parallel_virtual_node 1.07% : 0.000006s : 36: predicate.partial_defer_inline 1.28% : 0.000007s : 52: predicate.partial_eliminate 0.81% : 0.000005s : 35: predicate.print_const_string_wrapper 0.76% : 0.000004s : 34: predicate.reduce_all_const_elim 1.10% : 0.000006s : 35: predicate.reduce_eliminate 2.29% : 0.000013s : 104: predicate.redundant_stop_gradient_eliminater 0.59% : 0.000003s : 34: predicate.remove_not_recompute_node 1.29% : 0.000007s : 69: predicate.replace_applicator 0.53% : 0.000003s : 34: predicate.replace_old_param 0.32% : 0.000002s : 17: predicate.reset_defer_inline 0.92% : 0.000005s : 35: predicate.reshape_eliminate 0.78% : 0.000004s : 34: predicate.row_tensor_add_zeros_like 0.45% : 0.000003s : 17: predicate.row_tensor_eliminate 1.06% : 0.000006s : 34: predicate.same_eliminate 0.56% : 0.000003s : 34: predicate.set_cell_output_no_recompute 2.55% : 0.000015s : 34: predicate.shard_identity_eliminate 0.86% : 0.000005s : 34: predicate.special_op_eliminate 0.94% : 0.000005s : 34: predicate.specialize_transform 1.20% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000006s : 34: predicate.stack_unstack_eliminate 0.46% : 0.000003s : 17: predicate.switch_call_monad_eliminater 0.87% : 0.000005s : 36: predicate.switch_defer_inline 1.61% : 0.000009s : 70: predicate.switch_layer_defer_inline 3.21% : 0.000019s : 126: predicate.switch_simplify 0.84% : 0.000005s : 35: predicate.tile_eliminate 0.77% : 0.000004s : 35: predicate.transpose_eliminate 1.73% : 0.000010s : 69: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000010s : 69: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000010s : 69: predicate.tuple_list_get_item_depend_reorder 2.86% : 0.000017s : 103: predicate.tuple_list_get_item_eliminator 1.75% : 0.000010s : 69: predicate.tuple_list_get_set_item_eliminator 2.59% : 0.000015s : 103: predicate.tuple_list_set_item_eliminator 1.70% : 0.000010s : 69: predicate.tuple_to_list_eliminator_ 2.39% : 0.000014s : 104: predicate.updatestate_pure_node_eliminater 3.40% : 0.000020s : 138: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 17: predicate.value_based_eliminate 0.86% : 0.000005s : 34: predicate.virtual_dataset_eliminate 0.87% : 0.000005s : 34: predicate.virtual_output_eliminate 0.40% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.47% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.012237 58 75.13% : 0.009193s : 55: func_graph_cloner_run.FuncGraphClonerGraph 24.87% : 0.003044s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.537681 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.18% : 0.006297s : 1: add_attr 0.18% : 0.006278s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000139s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.01% : 0.000342s : 1: auto_monad 0.00% : 0.000074s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.02% : 0.000859s : 1: bootstrap 0.03% : 0.001131s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000038s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000075s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000025s : 1: environ_conv 0.00% : 0.000023s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 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% : 0.000005s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000812s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000794s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000050s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.10% : 0.003387s : 78: opt.transform.opt_a 0.00% : 0.000147s : 1: opt.transform.opt_after_cconv 0.00% : 0.000085s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000426s : 28: opt.transform.opt_b 0.00% : 0.000164s : 2: opt.transform.opt_trans_graph 0.00% : 0.000120s : 4: opt.transform.symbol_engine_opt 6.25% : 0.220996s : 1: opt_a 0.01% : 0.000349s : 1: opt_after_cconv 0.02% : 0.000798s : 1: opt_after_jit_grad 0.02% : 0.000617s : 1: opt_b 6.40% : 0.226246s : 1: optimize 0.00% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000049s : 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% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000003s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000044s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000091s : 1: remove_dup_value 0.20% : 0.006911s : 1: renormalize.infer 0.10% : 0.003501s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000211s : 1: rewriter_after_opt_a 0.00% : 0.000095s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000190s : 1: symbol_engine_optimizer 0.01% : 0.000200s : 1: tuple_transform 86.37% : 3.055658s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[False-mstype0-128-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[False-mstype0-128-32],max_mem:106.0M [WARNING] ME(170592:281473379729200,MainProcess):2026-01-29-17:38:36.237.166 [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 = 3.48246, [21] [bootstrap]: 0.00067465 [type_inference]: 2.88553 [event_method]: 0.00023304 [auto_monad]: 0.00082449 [graph_reusing]: 5.893e-05 [inline]: 3.85e-06 [add_attr]: 0.00547792, [1] [add_attr_with_inline]: 0.00545999, [1] [Cycle 1]: 0.00031523, [2] [tag_attr]: 0.00020612 [meta_addattr_fg_expand]: 5.602e-05 [parallel-infer-symbol]: 4.25999e-06 [pre_auto_parallel]: 0.00025104 [insert-virtual-dataset]: 3.06999e-06 [parallel-infer-symbol-second]: 1.35001e-06 [dataset_repeat_opt]: 2.16e-06 [pipeline_split]: 1.71998e-06 [optimize]: 0.58803, [53] [py_interpret_to_execute]: 0.00026112 [rewriter_before_opt_a]: 0.00081164 [opt_a]: 0.464476, [2] [Cycle 1]: 0.461945, [45] [expand_dump_flag]: 2.118e-05 [switch_simplify]: 0.233534 [loop_unroll]: 0.00036852 [a_1]: 0.0567736 [with_stream_mark]: 6.641e-05 [recompute_prepare]: 4.899e-05 [updatestate_depend_eliminate]: 2.458e-05 [updatestate_assign_eliminate]: 1.808e-05 [updatestate_loads_eliminate]: 9.832e-05 [parameter_eliminate]: 3.07002e-06 [a_2]: 0.00111449 [accelerated_algorithm]: 8.137e-05 [shard]: 2.56e-06 [meta_shard_fg_expand]: 2.66e-05 [shard_inline]: 2.661e-05 [merge_send_recv]: 2.298e-05 [auto_parallel]: 2.378e-05 [parallel]: 4.104e-05 [flash_sp]: 1.83e-05 [merge_comm]: 1.745e-05 [allreduce_fusion]: 1.483e-05 [matmul_add_comm_reduction]: 2.769e-05 [allreduce_slice_to_reducescatter]: 9.10019e-07 [virtual_shard_identity]: 3.445e-05 [virtual_dataset]: 2.583e-05 [get_grad_eliminate_]: 2.59e-05 [virtual_output]: 2.672e-05 [merge_forward]: 1.464e-05 [cell_reuse_recompute_pass]: 2.37001e-06 [offload_activation]: 2.788e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.208e-05 [merge_recompute_call_nodes]: 1.72999e-06 [before_grad]: 4.784e-05 [set_forward_comm_id_for_comm_node_pass]: 1.737e-05 [meta_fg_expand]: 1.922e-05 [flash_sp_send_recv_attached]: 5.61e-06 [receive_attached]: 2.37999e-06 [after_resolve]: 3.267e-05 [a_after_grad]: 4.21e-05 [renormalize]: 0.167873 [add_forward_monad_depend]: 1.945e-05 [auto_monad_grad]: 3.55e-06 [auto_monad_eliminator]: 0.00010137 [cse]: 0.00050465 [a_3]: 0.00020404 [Cycle 2]: 0.00251266, [45] [expand_dump_flag]: 3.58e-06 [switch_simplify]: 2.832e-05 [loop_unroll]: 2.537e-05 [a_1]: 0.00080697 [with_stream_mark]: 3.443e-05 [recompute_prepare]: 2.706e-05 [updatestate_depend_eliminate]: 1.691e-05 [updatestate_assign_eliminate]: 1.564e-05 [updatestate_loads_eliminate]: 2.069e-05 [parameter_eliminate]: 2.81999e-06 [a_2]: 0.00037876 [accelerated_algorithm]: 3.906e-05 [shard]: 2.44001e-06 [meta_shard_fg_expand]: 8.62998e-06 [shard_inline]: 2.538e-05 [merge_send_recv]: 2.271e-05 [auto_parallel]: 2.191e-05 [parallel]: 9.89001e-06 [flash_sp]: 4.84e-06 [merge_comm]: 1.524e-05 [allreduce_fusion]: 1.552e-05 [matmul_add_comm_reduction]: 2.579e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 2.985e-05 [virtual_dataset]: 2.397e-05 [get_grad_eliminate_]: 2.372e-05 [virtual_output]: 2.362e-05 [merge_forward]: 1.384e-05 [cell_reuse_recompute_pass]: 3.66999e-06 [offload_activation]: 2.636e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.014e-05 [merge_recompute_call_nodes]: 1.68002e-06 [before_grad]: 4.16e-05 [set_forward_comm_id_for_comm_node_pass]: 1.745e-05 [meta_fg_expand]: 1.144e-05 [flash_sp_send_recv_attached]: 1.92001e-06 [receive_attached]: 2.39001e-06 [after_resolve]: 3.181e-05 [a_after_grad]: 4.037e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.20002e-06 [auto_monad_grad]: 2.64001e-06 [auto_monad_eliminator]: 8.214e-05 [cse]: 9.895e-05 [a_3]: 0.00018037 [py_interpret_to_execute_after_opt_a]: 3.716e-05 [slice_cell_reuse_recomputed_activation]: 2.32001e-06 [rewriter_after_opt_a]: 0.00092574 [convert_after_rewriter]: 2.901e-05 [order_py_execute_after_rewriter]: 1.542e-05 [mutable_eliminate]: 0.00087254 [opt_b]: 0.00094247, [1] [Cycle 1]: 0.00093177, [7] [b_1]: 0.00067917 [b_2]: 3.203e-05 [updatestate_depend_eliminate]: 2.425e-05 [updatestate_assign_eliminate]: 1.474e-05 [updatestate_loads_eliminate]: 2.1e-05 [renormalize]: 5.79981e-07 [cse]: 0.00010938 [optimize_parallel_all_gather_comm]: 4.787e-05 [overlap_param_gather]: 2.14e-06 [cconv]: 4.409e-05 [loop_unroll]: 0.117169 [opt_after_cconv]: 0.00052602, [1] [Cycle 1]: 0.00051192, [7] [c_1]: 0.00025379 [parameter_eliminate]: 6.46e-06 [updatestate_depend_eliminate]: 2.968e-05 [updatestate_assign_eliminate]: 1.558e-05 [updatestate_loads_eliminate]: 2.207e-05 [cse]: 0.00013053 [renormalize]: 8.90024e-07 [remove_dup_value]: 0.00012662 [tuple_transform]: 0.00030079, [1] [Cycle 1]: 0.00029408, [4] [d_1]: 0.00024195 [none_parameter_eliminate]: 2.93e-06 [renormalize]: 3.00002e-07 [switch_simplify]: 2.638e-05 [partial_unused_args_eliminate]: 3.08e-06 [add_recomputation]: 0.00017031 [cse_after_recomputation]: 7.931e-05, [1] [Cycle 1]: 7.28e-05, [1] [cse]: 6.569e-05 [environ_conv]: 2.792e-05 [swap_dp_allreduce_reducescatter]: 2.037e-05 [bias_add_comm_swap]: 3.08998e-06 [label_micro_interleaved_index]: 8.00999e-06 [label_fine_grained_interleaved_index]: 2.69999e-06 [merge_cast_opt]: 1.77999e-06 [slice_recompute_activation]: 2.30002e-06 [micro_interleaved_order_control]: 2.63e-06 [assign_add_opt]: 1.52001e-06 [ForceFp32Comm]: 1.12999e-06 [remove_cast_before_assign_add]: 1.09e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 2.74001e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 9.70002e-07 [interleave_split_concat_branches]: 1.14e-06 [interleave_parallel_branches]: 1.02998e-06 [overlap_opt_shard_in_pipeline]: 1.31998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.94e-06 [control_data_broadcast_order]: 4.451e-05 [grouped_pairwise_exchange_alltoall]: 1.60999e-06 [offloading_packed_experts]: 1.308e-05 [overlap_recompute_and_grad_model_parallel]: 1.173e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.31998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49e-06 [overlap_recompute_comm]: 2.71999e-06 [overlap_grad_ring_attention]: 1.042e-05 [overlap_grad_flash_sp]: 5.778e-05 [begin_end_overlap_inline]: 7.60017e-07 [split_matmul_comm_elemetwise]: 2.54001e-06 [split_layernorm_comm]: 1.66e-06 [handle_group_info]: 1.03001e-06 [symbol_engine_optimizer]: 0.00060922, [1] [Cycle 1]: 0.00060354, [6] [build]: 0.00033613 [elim_shapecalc]: 3.896e-05 [elim_not_effective]: 7.049e-05 [opt_reshape]: 3.823e-05 [fold_const_symbol]: 6.71e-05 [renormalize]: 3.29979e-07 [detach_backward]: 3.08998e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 8.243e-05 [get_jit_bprop_graph]: 2.54999e-06 [rewriter_after_jit_bprop_graph]: 6.91999e-06 [opt_after_jit_grad]: 0.00090354 [validate]: 0.00012387 Sums bootstrap : 0.000675s : 0.02% type_inference : 2.885535s : 83.02% event_method : 0.000233s : 0.01% auto_monad : 0.000824s : 0.02% graph_reusing : 0.000059s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000206s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000056s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000251s : 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 : 0.000261s : 0.01% optimize.rewriter_before_opt_a : 0.000812s : 0.02% optimize.opt_a.expand_dump_flag : 0.000025s : 0.00% optimize.opt_a.switch_simplify : 0.233562s : 6.72% optimize.opt_a.loop_unroll : 0.000394s : 0.01% optimize.opt_a.a_1 : 0.057581s : 1.66% optimize.opt_a.with_stream_mark : 0.000101s : 0.00% optimize.opt_a.recompute_prepare : 0.000076s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000041s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000034s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000119s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001493s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000120s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000035s : 0.00% optimize.opt_a.shard_inline : 0.000052s : 0.00% optimize.opt_a.merge_send_recv : 0.000046s : 0.00% optimize.opt_a.auto_parallel : 0.000046s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000023s : 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 : 0.000053s : 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 : 0.000050s : 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 : 0.000028s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000054s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000102s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000089s : 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 : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000064s : 0.00% optimize.opt_a.a_after_grad : 0.000082s : 0.00% optimize.opt_a.renormalize : 0.167873s : 4.83% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000184s : 0.01% optimize.opt_a.cse : 0.000604s : 0.02% optimize.opt_a.a_3 : 0.000384s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000926s : 0.03% optimize.convert_after_rewriter : 0.000029s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000873s : 0.03% optimize.opt_b.b_1 : 0.000679s : 0.02% optimize.opt_b.b_2 : 0.000032s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000109s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000048s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.117169s : 3.37% optimize.opt_after_cconv.c_1 : 0.000254s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000030s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_after_cconv.cse : 0.000131s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000127s : 0.00% optimize.tuple_transform.d_1 : 0.000242s : 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 : 0.000026s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000170s : 0.00% optimize.cse_after_recomputation.cse : 0.000066s : 0.00% optimize.environ_conv : 0.000028s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 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 : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000045s : 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 : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 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 : 0.000336s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000039s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000070s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000038s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000067s : 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 : 0.000082s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000904s : 0.03% validate : 0.000124s : 0.00% Time group info: ------[substitution.] 0.004489 612 1.13% : 0.000051s : 5: substitution.arithmetic_simplify 0.40% : 0.000018s : 8: substitution.depend_value_elim 0.63% : 0.000028s : 17: substitution.elim_not_effective 0.44% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.66% : 0.000030s : 17: substitution.fold_const_symbol 0.40% : 0.000018s : 21: substitution.graph_param_transform 68.42% : 0.003071s : 71: substitution.inline 0.39% : 0.000018s : 35: substitution.j_node_and_user_rematch 1.00% : 0.000045s : 10: substitution.less_batch_normalization 1.48% : 0.000067s : 2: substitution.list_to_tuple_eliminator_ 0.28% : 0.000013s : 12: substitution.load_eliminater 0.68% : 0.000030s : 21: substitution.minmaximum_grad 0.18% : 0.000008s : 2: substitution.opt_reshape 0.50% : 0.000023s : 35: substitution.remove_not_recompute_node 0.21% : 0.000010s : 6: substitution.replace_old_param 1.97% : 0.000088s : 18: substitution.reshape_eliminate 1.83% : 0.000082s : 24: substitution.switch_simplify 3.74% : 0.000168s : 51: substitution.tuple_list_convert_item_index_to_positive 2.07% : 0.000093s : 51: substitution.tuple_list_get_item_const_eliminator 2.71% : 0.000121s : 51: substitution.tuple_list_get_item_depend_reorder 5.15% : 0.000231s : 73: substitution.tuple_list_get_item_eliminator 2.65% : 0.000119s : 51: substitution.tuple_list_get_set_item_eliminator 0.42% : 0.000019s : 8: substitution.updatestate_pure_node_eliminater 2.66% : 0.000119s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.885149 2 99.33% : 2.865840s : 1: type_inference.infer 0.67% : 0.019309s : 1: type_inference.specialize ------[replace.] 0.279527 115 0.02% : 0.000044s : 5: replace.depend_value_elim 16.63% : 0.046496s : 71: replace.inline 0.02% : 0.000057s : 2: replace.list_to_tuple_eliminator_ 83.29% : 0.232820s : 24: replace.switch_simplify 0.04% : 0.000110s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003189 115 0.07% : 0.000002s : 5: match.depend_value_elim 94.78% : 0.003023s : 71: match.inline 1.98% : 0.000063s : 2: match.list_to_tuple_eliminator_ 2.00% : 0.000064s : 24: match.switch_simplify 1.17% : 0.000037s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001890 10672 1.21% : 0.000023s : 131: predicate.accumulaten_eliminater 0.36% : 0.000007s : 21: predicate.ad_related_special_op_eliminate 0.54% : 0.000010s : 70: predicate.addn_check_dump 1.16% : 0.000022s : 131: predicate.addn_zero_filter 1.01% : 0.000019s : 131: predicate.adjust_all_reduce_mul_add 2.45% : 0.000046s : 201: predicate.arithmetic_simplify 1.14% : 0.000022s : 131: predicate.cast_eliminate 0.35% : 0.000007s : 42: predicate.check_bprop_eliminate 0.57% : 0.000011s : 70: predicate.compare_switch_simplify 0.08% : 0.000002s : 21: predicate.const_output_eliminate 0.59% : 0.000011s : 73: predicate.depend_value_elim 1.07% : 0.000020s : 131: predicate.dict_get_item_const_eliminator 1.20% : 0.000023s : 131: predicate.dict_get_item_eliminator 1.02% : 0.000019s : 131: predicate.dict_set_item_eliminator 0.41% : 0.000008s : 42: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 21: predicate.elim_not_effective 0.21% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.22% : 0.000023s : 152: predicate.environ_add_const_eliminate 1.21% : 0.000023s : 152: predicate.environ_get_add_eliminate 1.16% : 0.000022s : 152: predicate.environ_get_depend_swap 1.79% : 0.000034s : 222: predicate.environ_get_eliminate 1.19% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.76% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.54% : 0.000048s : 217: predicate.float_depend_g_call 0.52% : 0.000010s : 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 0.11% : 0.000002s : 21: predicate.graph_param_transform 0.53% : 0.000010s : 70: predicate.incorporate_call 0.51% : 0.000010s : 70: predicate.incorporate_call_switch 6.30% : 0.000119s : 503: predicate.inline 0.41% : 0.000008s : 43: predicate.inline_without_move 0.17% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.51% : 0.000010s : 43: predicate.less_batch_normalization 1.61% : 0.000030s : 188: predicate.list_to_tuple_eliminator_ 2.44% : 0.000046s : 319: predicate.load_eliminater 0.42% : 0.000008s : 21: predicate.loop_unroll_after_grad 3.68% : 0.000070s : 322: predicate.loop_unroll_before_grad 1.55% : 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 0.33% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.08% : 0.000020s : 131: predicate.minmaximum_grad 0.44% : 0.000008s : 21: predicate.mutable_eliminate 0.20% : 0.000004s : 21: predicate.opt_reshape 0.20% : 0.000004s : 21: predicate.parallel_virtual_node 3.80% : 0.000072s : 217: predicate.partial_defer_inline 1.42% : 0.000027s : 167: predicate.partial_eliminate 1.04% : 0.000020s : 131: predicate.print_const_string_wrapper 0.48% : 0.000009s : 65: predicate.reduce_all_const_elim 1.46% : 0.000028s : 131: predicate.reduce_eliminate 2.52% : 0.000048s : 319: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 43: predicate.remove_not_recompute_node 1.02% : 0.000019s : 188: predicate.replace_applicator 0.19% : 0.000004s : 43: predicate.replace_old_param 0.10% : 0.000002s : 21: predicate.reset_defer_inline 1.20% : 0.000023s : 131: predicate.reshape_eliminate 0.32% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.20% : 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 0.41% : 0.000008s : 43: predicate.shard_identity_eliminate 0.38% : 0.000007s : 42: predicate.special_op_eliminate 0.62% : 0.000012s : 70: predicate.specialize_transform 0.40% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.37% : 0.000007s : 43: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.99% : 0.000038s : 217: predicate.switch_defer_inline 2.21% : 0.000042s : 259: predicate.switch_layer_defer_inline 9.03% : 0.000171s : 678: predicate.switch_simplify 1.07% : 0.000020s : 131: predicate.tile_eliminate 1.06% : 0.000020s : 131: predicate.transpose_eliminate 1.66% : 0.000031s : 173: predicate.tuple_list_convert_item_index_to_positive 1.65% : 0.000031s : 173: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000029s : 173: predicate.tuple_list_get_item_depend_reorder 3.11% : 0.000059s : 256: predicate.tuple_list_get_item_eliminator 1.56% : 0.000029s : 173: predicate.tuple_list_get_set_item_eliminator 2.20% : 0.000041s : 243: predicate.tuple_list_set_item_eliminator 1.58% : 0.000030s : 186: predicate.tuple_to_list_eliminator_ 2.45% : 0.000046s : 319: predicate.updatestate_pure_node_eliminater 3.22% : 0.000061s : 389: predicate.updatestate_useless_node_eliminater 0.18% : 0.000003s : 21: predicate.value_based_eliminate 0.36% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.35% : 0.000007s : 43: predicate.virtual_output_eliminate 0.16% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.24% : 0.000005s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.028443 135 34.30% : 0.009756s : 55: func_graph_cloner_run.FuncGraphClonerGraph 65.70% : 0.018688s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.539161 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.12% : 0.005485s : 1: add_attr 0.12% : 0.005465s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000176s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.02% : 0.000841s : 1: auto_monad 0.00% : 0.000087s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000707s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000048s : 1: control_data_broadcast_order 0.00% : 0.000035s : 1: convert_after_rewriter 0.00% : 0.000083s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.01% : 0.000248s : 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% : 0.000005s : 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% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 2.58% : 0.117205s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000884s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000044s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000051s : 1: opt.transform.mutable_eliminate 6.48% : 0.294052s : 95: opt.transform.opt_a 0.01% : 0.000245s : 1: opt.transform.opt_after_cconv 0.00% : 0.000092s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000665s : 28: opt.transform.opt_b 0.01% : 0.000266s : 2: opt.transform.opt_trans_graph 0.00% : 0.000209s : 4: opt.transform.symbol_engine_opt 10.23% : 0.464480s : 1: opt_a 0.01% : 0.000532s : 1: opt_after_cconv 0.02% : 0.000916s : 1: opt_after_jit_grad 0.02% : 0.000947s : 1: opt_b 12.95% : 0.588037s : 1: optimize 0.00% : 0.000053s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000062s : 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% : 0.000004s : 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% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000259s : 1: pre_auto_parallel 0.01% : 0.000271s : 1: py_interpret_to_execute 0.00% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000132s : 1: remove_dup_value 3.27% : 0.148387s : 1: renormalize.infer 0.43% : 0.019457s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000940s : 1: rewriter_after_opt_a 0.02% : 0.000823s : 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% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000613s : 1: symbol_engine_optimizer 0.01% : 0.000304s : 1: tuple_transform 63.57% : 2.885569s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[True-mstype0-1024-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[True-mstype0-1024-32],max_mem:106.0M [WARNING] ME(170592:281473379729200,MainProcess):2026-01-29-17:38:50.409.052 [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 = 3.417, [21] [bootstrap]: 0.00084713 [type_inference]: 2.93678 [event_method]: 0.00021887 [auto_monad]: 0.00079026 [graph_reusing]: 4.894e-05 [inline]: 3.31999e-06 [add_attr]: 0.116652, [1] [add_attr_with_inline]: 0.116634, [1] [Cycle 1]: 0.00033984, [2] [tag_attr]: 0.00022474 [meta_addattr_fg_expand]: 6e-05 [parallel-infer-symbol]: 4.52e-06 [pre_auto_parallel]: 0.00026583 [insert-virtual-dataset]: 2.91e-06 [parallel-infer-symbol-second]: 1.12e-06 [dataset_repeat_opt]: 2.24999e-06 [pipeline_split]: 1.77001e-06 [optimize]: 0.360102, [53] [py_interpret_to_execute]: 0.00032166 [rewriter_before_opt_a]: 0.00086101 [opt_a]: 0.353239, [2] [Cycle 1]: 0.313652, [45] [expand_dump_flag]: 2.35e-05 [switch_simplify]: 0.00084118 [loop_unroll]: 0.00036139 [a_1]: 0.00996255 [with_stream_mark]: 6.745e-05 [recompute_prepare]: 0.122912 [updatestate_depend_eliminate]: 5.259e-05 [updatestate_assign_eliminate]: 1.87e-05 [updatestate_loads_eliminate]: 0.00014241 [parameter_eliminate]: 6.36e-06 [a_2]: 0.00100827 [accelerated_algorithm]: 8.341e-05 [shard]: 3.08e-06 [meta_shard_fg_expand]: 3.377e-05 [shard_inline]: 2.756e-05 [merge_send_recv]: 2.347e-05 [auto_parallel]: 2.724e-05 [parallel]: 3.925e-05 [flash_sp]: 1.67e-05 [merge_comm]: 1.974e-05 [allreduce_fusion]: 1.549e-05 [matmul_add_comm_reduction]: 2.626e-05 [allreduce_slice_to_reducescatter]: 1.10999e-06 [virtual_shard_identity]: 3.289e-05 [virtual_dataset]: 2.649e-05 [get_grad_eliminate_]: 2.503e-05 [virtual_output]: 2.631e-05 [merge_forward]: 1.508e-05 [cell_reuse_recompute_pass]: 3.85e-06 [offload_activation]: 2.938e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.889e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 4.914e-05 [set_forward_comm_id_for_comm_node_pass]: 1.824e-05 [meta_fg_expand]: 2.108e-05 [flash_sp_send_recv_attached]: 6.44999e-06 [receive_attached]: 2.13002e-06 [after_resolve]: 3.455e-05 [a_after_grad]: 4.405e-05 [renormalize]: 0.176407 [add_forward_monad_depend]: 1.773e-05 [auto_monad_grad]: 2.67001e-06 [auto_monad_eliminator]: 9.532e-05 [cse]: 0.0003339 [a_3]: 0.00019715 [Cycle 2]: 0.039567, [45] [expand_dump_flag]: 3.28e-06 [switch_simplify]: 2.938e-05 [loop_unroll]: 2.497e-05 [a_1]: 0.0008079 [with_stream_mark]: 3.392e-05 [recompute_prepare]: 0.0368956 [updatestate_depend_eliminate]: 4.214e-05 [updatestate_assign_eliminate]: 1.851e-05 [updatestate_loads_eliminate]: 2.33e-05 [parameter_eliminate]: 7.14001e-06 [a_2]: 0.00045497 [accelerated_algorithm]: 4.163e-05 [shard]: 3.07002e-06 [meta_shard_fg_expand]: 1.339e-05 [shard_inline]: 2.597e-05 [merge_send_recv]: 2.301e-05 [auto_parallel]: 2.561e-05 [parallel]: 1.132e-05 [flash_sp]: 5.61003e-06 [merge_comm]: 1.55e-05 [allreduce_fusion]: 1.553e-05 [matmul_add_comm_reduction]: 2.846e-05 [allreduce_slice_to_reducescatter]: 1.15999e-06 [virtual_shard_identity]: 2.646e-05 [virtual_dataset]: 2.42e-05 [get_grad_eliminate_]: 2.365e-05 [virtual_output]: 2.472e-05 [merge_forward]: 1.486e-05 [cell_reuse_recompute_pass]: 3.08998e-06 [offload_activation]: 2.587e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.802e-05 [merge_recompute_call_nodes]: 1.76998e-06 [before_grad]: 4.113e-05 [set_forward_comm_id_for_comm_node_pass]: 1.534e-05 [meta_fg_expand]: 1.22e-05 [flash_sp_send_recv_attached]: 2.21e-06 [receive_attached]: 2.39999e-06 [after_resolve]: 3.414e-05 [a_after_grad]: 4.118e-05 [renormalize]: 2.19996e-07 [add_forward_monad_depend]: 4.80001e-06 [auto_monad_grad]: 3.49001e-06 [auto_monad_eliminator]: 8.199e-05 [cse]: 0.00011655 [a_3]: 0.00016717 [py_interpret_to_execute_after_opt_a]: 3.896e-05 [slice_cell_reuse_recomputed_activation]: 2.06e-06 [rewriter_after_opt_a]: 0.00087011 [convert_after_rewriter]: 2.556e-05 [order_py_execute_after_rewriter]: 1.433e-05 [mutable_eliminate]: 0.00086424 [opt_b]: 0.00094156, [1] [Cycle 1]: 0.00093191, [7] [b_1]: 0.00068847 [b_2]: 2.812e-05 [updatestate_depend_eliminate]: 2.242e-05 [updatestate_assign_eliminate]: 1.503e-05 [updatestate_loads_eliminate]: 2.028e-05 [renormalize]: 6.99976e-07 [cse]: 0.00010991 [optimize_parallel_all_gather_comm]: 4.449e-05 [overlap_param_gather]: 1.99e-06 [cconv]: 4.485e-05 [loop_unroll]: 0.00063117 [opt_after_cconv]: 0.00036936, [1] [Cycle 1]: 0.00036164, [7] [c_1]: 0.00016912 [parameter_eliminate]: 5.32001e-06 [updatestate_depend_eliminate]: 1.975e-05 [updatestate_assign_eliminate]: 1.484e-05 [updatestate_loads_eliminate]: 1.689e-05 [cse]: 9.395e-05 [renormalize]: 2.69996e-07 [remove_dup_value]: 0.00012078 [tuple_transform]: 0.00030791, [1] [Cycle 1]: 0.00030081, [4] [d_1]: 0.00024569 [none_parameter_eliminate]: 3.01999e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 2.823e-05 [partial_unused_args_eliminate]: 2.68e-06 [add_recomputation]: 0.00017623 [cse_after_recomputation]: 8.969e-05, [1] [Cycle 1]: 8.233e-05, [1] [cse]: 7.344e-05 [environ_conv]: 3.036e-05 [swap_dp_allreduce_reducescatter]: 2.33e-05 [bias_add_comm_swap]: 3.8e-06 [label_micro_interleaved_index]: 6.33e-06 [label_fine_grained_interleaved_index]: 3.03e-06 [merge_cast_opt]: 1.69e-06 [slice_recompute_activation]: 2.14e-06 [micro_interleaved_order_control]: 2.87002e-06 [assign_add_opt]: 1.31998e-06 [ForceFp32Comm]: 1.10999e-06 [remove_cast_before_assign_add]: 1.02998e-06 [full_micro_interleaved_order_control]: 2.01998e-06 [reorder_send_recv_between_fp_bp]: 2.91e-06 [comm_op_add_attrs]: 1.09998e-06 [add_comm_op_reuse_tag]: 1.06002e-06 [interleave_split_concat_branches]: 1.36002e-06 [interleave_parallel_branches]: 1.05001e-06 [overlap_opt_shard_in_pipeline]: 1.28002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.94999e-06 [control_data_broadcast_order]: 4.483e-05 [grouped_pairwise_exchange_alltoall]: 1.54998e-06 [offloading_packed_experts]: 1.278e-05 [overlap_recompute_and_grad_model_parallel]: 1.102e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.32e-06 [overlap_recompute_comm]: 2.34001e-06 [overlap_grad_ring_attention]: 1.008e-05 [overlap_grad_flash_sp]: 5.943e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.29001e-06 [split_layernorm_comm]: 2.14e-06 [handle_group_info]: 1.20001e-06 [symbol_engine_optimizer]: 0.00057562, [1] [Cycle 1]: 0.00056895, [6] [build]: 0.00031339 [elim_shapecalc]: 4.147e-05 [elim_not_effective]: 5.785e-05 [opt_reshape]: 3.706e-05 [fold_const_symbol]: 6.809e-05 [renormalize]: 5.8001e-07 [detach_backward]: 2.53e-06 [pipeline_parallel_scheduler]: 1.74e-06 [auto_monad_reorder]: 8.073e-05 [get_jit_bprop_graph]: 2.17999e-06 [rewriter_after_jit_bprop_graph]: 6.61e-06 [opt_after_jit_grad]: 0.00082228 [validate]: 0.00011669 Sums bootstrap : 0.000847s : 0.03% type_inference : 2.936782s : 89.02% event_method : 0.000219s : 0.01% auto_monad : 0.000790s : 0.02% graph_reusing : 0.000049s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000225s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000060s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000266s : 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 : 0.000322s : 0.01% optimize.rewriter_before_opt_a : 0.000861s : 0.03% optimize.opt_a.expand_dump_flag : 0.000027s : 0.00% optimize.opt_a.switch_simplify : 0.000871s : 0.03% optimize.opt_a.loop_unroll : 0.000386s : 0.01% optimize.opt_a.a_1 : 0.010770s : 0.33% optimize.opt_a.with_stream_mark : 0.000101s : 0.00% optimize.opt_a.recompute_prepare : 0.159807s : 4.84% optimize.opt_a.updatestate_depend_eliminate : 0.000095s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000037s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000166s : 0.01% optimize.opt_a.parameter_eliminate : 0.000014s : 0.00% optimize.opt_a.a_2 : 0.001463s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000125s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000047s : 0.00% optimize.opt_a.shard_inline : 0.000054s : 0.00% optimize.opt_a.merge_send_recv : 0.000046s : 0.00% optimize.opt_a.auto_parallel : 0.000053s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 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 : 0.000059s : 0.00% optimize.opt_a.virtual_dataset : 0.000051s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000049s : 0.00% optimize.opt_a.virtual_output : 0.000051s : 0.00% optimize.opt_a.merge_forward : 0.000030s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000055s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000107s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000090s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000034s : 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 : 0.000069s : 0.00% optimize.opt_a.a_after_grad : 0.000085s : 0.00% optimize.opt_a.renormalize : 0.176407s : 5.35% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000177s : 0.01% optimize.opt_a.cse : 0.000450s : 0.01% optimize.opt_a.a_3 : 0.000364s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000039s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000870s : 0.03% optimize.convert_after_rewriter : 0.000026s : 0.00% optimize.order_py_execute_after_rewriter : 0.000014s : 0.00% optimize.mutable_eliminate : 0.000864s : 0.03% optimize.opt_b.b_1 : 0.000688s : 0.02% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000020s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000110s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000044s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000631s : 0.02% optimize.opt_after_cconv.c_1 : 0.000169s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_after_cconv.cse : 0.000094s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000121s : 0.00% optimize.tuple_transform.d_1 : 0.000246s : 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 : 0.000028s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000176s : 0.01% optimize.cse_after_recomputation.cse : 0.000073s : 0.00% optimize.environ_conv : 0.000030s : 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 : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000045s : 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 : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000059s : 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 : 0.000313s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000058s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000037s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000068s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000081s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000822s : 0.02% validate : 0.000117s : 0.00% Time group info: ------[substitution.] 0.003932 612 1.61% : 0.000063s : 5: substitution.arithmetic_simplify 0.50% : 0.000020s : 8: substitution.depend_value_elim 0.39% : 0.000015s : 17: substitution.elim_not_effective 0.51% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.75% : 0.000029s : 17: substitution.fold_const_symbol 0.44% : 0.000017s : 21: substitution.graph_param_transform 65.85% : 0.002590s : 71: substitution.inline 0.45% : 0.000018s : 35: substitution.j_node_and_user_rematch 1.16% : 0.000046s : 10: substitution.less_batch_normalization 1.58% : 0.000062s : 2: substitution.list_to_tuple_eliminator_ 0.26% : 0.000010s : 12: substitution.load_eliminater 0.84% : 0.000033s : 21: substitution.minmaximum_grad 0.21% : 0.000008s : 2: substitution.opt_reshape 0.56% : 0.000022s : 35: substitution.remove_not_recompute_node 0.27% : 0.000011s : 6: substitution.replace_old_param 1.80% : 0.000071s : 18: substitution.reshape_eliminate 1.31% : 0.000052s : 24: substitution.switch_simplify 3.94% : 0.000155s : 51: substitution.tuple_list_convert_item_index_to_positive 2.15% : 0.000085s : 51: substitution.tuple_list_get_item_const_eliminator 2.86% : 0.000112s : 51: substitution.tuple_list_get_item_depend_reorder 5.78% : 0.000227s : 73: substitution.tuple_list_get_item_eliminator 2.75% : 0.000108s : 51: substitution.tuple_list_get_set_item_eliminator 0.45% : 0.000018s : 8: substitution.updatestate_pure_node_eliminater 3.57% : 0.000140s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.935724 2 96.31% : 2.827515s : 1: type_inference.infer 3.69% : 0.108209s : 1: type_inference.specialize ------[replace.] 0.001197 115 3.77% : 0.000045s : 5: replace.depend_value_elim 56.90% : 0.000681s : 71: replace.inline 4.26% : 0.000051s : 2: replace.list_to_tuple_eliminator_ 25.94% : 0.000311s : 24: replace.switch_simplify 9.12% : 0.000109s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002677 115 0.08% : 0.000002s : 5: match.depend_value_elim 95.04% : 0.002544s : 71: match.inline 2.22% : 0.000059s : 2: match.list_to_tuple_eliminator_ 1.32% : 0.000035s : 24: match.switch_simplify 1.35% : 0.000036s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001781 10672 1.14% : 0.000020s : 131: predicate.accumulaten_eliminater 0.39% : 0.000007s : 21: predicate.ad_related_special_op_eliminate 0.54% : 0.000010s : 70: predicate.addn_check_dump 1.17% : 0.000021s : 131: predicate.addn_zero_filter 1.06% : 0.000019s : 131: predicate.adjust_all_reduce_mul_add 2.63% : 0.000047s : 201: predicate.arithmetic_simplify 1.07% : 0.000019s : 131: predicate.cast_eliminate 0.34% : 0.000006s : 42: predicate.check_bprop_eliminate 0.53% : 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 1.15% : 0.000020s : 131: predicate.dict_get_item_const_eliminator 1.37% : 0.000024s : 131: predicate.dict_get_item_eliminator 1.16% : 0.000021s : 131: predicate.dict_set_item_eliminator 0.42% : 0.000008s : 42: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 21: predicate.elim_not_effective 0.21% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.26% : 0.000022s : 152: predicate.environ_add_const_eliminate 1.24% : 0.000022s : 152: predicate.environ_get_add_eliminate 1.22% : 0.000022s : 152: predicate.environ_get_depend_swap 1.95% : 0.000035s : 222: predicate.environ_get_eliminate 1.23% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.84% : 0.000033s : 217: predicate.exchange_switch_depend_value 2.56% : 0.000046s : 217: predicate.float_depend_g_call 0.57% : 0.000010s : 70: predicate.float_environ_get_switch 0.83% : 0.000015s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.38% : 0.000007s : 43: predicate.get_grad_eliminate 0.11% : 0.000002s : 21: predicate.graph_param_transform 0.57% : 0.000010s : 70: predicate.incorporate_call 0.51% : 0.000009s : 70: predicate.incorporate_call_switch 5.94% : 0.000106s : 503: predicate.inline 0.48% : 0.000009s : 43: predicate.inline_without_move 0.18% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.52% : 0.000009s : 43: predicate.less_batch_normalization 1.68% : 0.000030s : 188: predicate.list_to_tuple_eliminator_ 2.61% : 0.000046s : 319: predicate.load_eliminater 0.44% : 0.000008s : 21: predicate.loop_unroll_after_grad 3.28% : 0.000058s : 322: predicate.loop_unroll_before_grad 1.56% : 0.000028s : 173: predicate.make_slice_get_slice_eliminator 0.61% : 0.000011s : 70: predicate.merge_addn 0.32% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.34% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.12% : 0.000020s : 131: predicate.minmaximum_grad 0.42% : 0.000007s : 21: predicate.mutable_eliminate 0.19% : 0.000003s : 21: predicate.opt_reshape 0.20% : 0.000003s : 21: predicate.parallel_virtual_node 3.10% : 0.000055s : 217: predicate.partial_defer_inline 1.49% : 0.000027s : 167: predicate.partial_eliminate 1.15% : 0.000021s : 131: predicate.print_const_string_wrapper 0.55% : 0.000010s : 65: predicate.reduce_all_const_elim 1.60% : 0.000029s : 131: predicate.reduce_eliminate 2.71% : 0.000048s : 319: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 43: predicate.remove_not_recompute_node 1.11% : 0.000020s : 188: predicate.replace_applicator 0.22% : 0.000004s : 43: predicate.replace_old_param 0.12% : 0.000002s : 21: predicate.reset_defer_inline 1.25% : 0.000022s : 131: predicate.reshape_eliminate 0.35% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.22% : 0.000004s : 21: predicate.row_tensor_eliminate 0.40% : 0.000007s : 42: predicate.same_eliminate 0.62% : 0.000011s : 48: predicate.set_cell_output_no_recompute 0.39% : 0.000007s : 43: predicate.shard_identity_eliminate 0.39% : 0.000007s : 42: predicate.special_op_eliminate 0.66% : 0.000012s : 70: predicate.specialize_transform 0.44% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 0.46% : 0.000008s : 43: predicate.stack_unstack_eliminate 0.19% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.99% : 0.000036s : 217: predicate.switch_defer_inline 2.25% : 0.000040s : 259: predicate.switch_layer_defer_inline 6.46% : 0.000115s : 678: predicate.switch_simplify 1.17% : 0.000021s : 131: predicate.tile_eliminate 1.14% : 0.000020s : 131: predicate.transpose_eliminate 1.75% : 0.000031s : 173: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000031s : 173: predicate.tuple_list_get_item_const_eliminator 1.60% : 0.000028s : 173: predicate.tuple_list_get_item_depend_reorder 3.07% : 0.000055s : 256: predicate.tuple_list_get_item_eliminator 1.65% : 0.000029s : 173: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000044s : 243: predicate.tuple_list_set_item_eliminator 1.65% : 0.000029s : 186: predicate.tuple_to_list_eliminator_ 2.54% : 0.000045s : 319: predicate.updatestate_pure_node_eliminater 3.36% : 0.000060s : 389: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 21: predicate.value_based_eliminate 0.38% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.36% : 0.000006s : 43: predicate.virtual_output_eliminate 0.16% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.20% : 0.000004s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.106392 135 9.39% : 0.009992s : 55: func_graph_cloner_run.FuncGraphClonerGraph 90.61% : 0.096400s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.245587 209 0.00% : 0.000004s : 1: ForceFp32Comm 2.75% : 0.116661s : 1: add_attr 2.75% : 0.116639s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000183s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.02% : 0.000806s : 1: auto_monad 0.00% : 0.000086s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000889s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000050s : 1: control_data_broadcast_order 0.00% : 0.000033s : 1: convert_after_rewriter 0.00% : 0.000093s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000034s : 1: environ_conv 0.01% : 0.000231s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000055s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000642s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000875s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000045s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000049s : 1: opt.transform.mutable_eliminate 4.10% : 0.174215s : 95: opt.transform.opt_a 0.00% : 0.000167s : 1: opt.transform.opt_after_cconv 0.00% : 0.000089s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000675s : 28: opt.transform.opt_b 0.01% : 0.000270s : 2: opt.transform.opt_trans_graph 0.00% : 0.000198s : 4: opt.transform.symbol_engine_opt 8.32% : 0.353244s : 1: opt_a 0.01% : 0.000373s : 1: opt_after_cconv 0.02% : 0.000833s : 1: opt_after_jit_grad 0.02% : 0.000946s : 1: opt_b 8.48% : 0.360110s : 1: optimize 0.00% : 0.000050s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000018s : 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% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000012s : 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% : 0.000275s : 1: pre_auto_parallel 0.01% : 0.000335s : 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 0.00% : 0.000127s : 1: remove_dup_value 3.95% : 0.167537s : 1: renormalize.infer 0.21% : 0.008847s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000880s : 1: rewriter_after_opt_a 0.02% : 0.000872s : 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% : 0.000027s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000579s : 1: symbol_engine_optimizer 0.01% : 0.000311s : 1: tuple_transform 69.17% : 2.936820s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[True-mstype0-2048-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[True-mstype0-2048-32],max_mem:106.0M [WARNING] ME(170592:281473379729200,MainProcess):2026-01-29-17:39:09.131.473 [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 = 3.06203, [21] [bootstrap]: 0.00067696 [type_inference]: 2.72238 [event_method]: 0.00022046 [auto_monad]: 0.00081343 [graph_reusing]: 5.733e-05 [inline]: 2.85002e-06 [add_attr]: 0.00532439, [1] [add_attr_with_inline]: 0.00530727, [1] [Cycle 1]: 0.00031569, [2] [tag_attr]: 0.0002109 [meta_addattr_fg_expand]: 5.445e-05 [parallel-infer-symbol]: 3.63999e-06 [pre_auto_parallel]: 0.0582905 [insert-virtual-dataset]: 3.48e-06 [parallel-infer-symbol-second]: 3.6e-06 [dataset_repeat_opt]: 3.87002e-06 [pipeline_split]: 1.92001e-06 [optimize]: 0.272811, [53] [py_interpret_to_execute]: 0.00045562 [rewriter_before_opt_a]: 0.00088566 [opt_a]: 0.239324, [2] [Cycle 1]: 0.236745, [45] [expand_dump_flag]: 4.132e-05 [switch_simplify]: 0.00088065 [loop_unroll]: 0.00033493 [a_1]: 0.062568 [with_stream_mark]: 6.946e-05 [recompute_prepare]: 4.681e-05 [updatestate_depend_eliminate]: 2.383e-05 [updatestate_assign_eliminate]: 1.885e-05 [updatestate_loads_eliminate]: 9.22e-05 [parameter_eliminate]: 3.44001e-06 [a_2]: 0.00097865 [accelerated_algorithm]: 7.398e-05 [shard]: 2.99999e-06 [meta_shard_fg_expand]: 2.635e-05 [shard_inline]: 2.659e-05 [merge_send_recv]: 2.275e-05 [auto_parallel]: 2.452e-05 [parallel]: 3.482e-05 [flash_sp]: 1.602e-05 [merge_comm]: 1.809e-05 [allreduce_fusion]: 1.503e-05 [matmul_add_comm_reduction]: 2.624e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 3.096e-05 [virtual_dataset]: 2.525e-05 [get_grad_eliminate_]: 2.444e-05 [virtual_output]: 2.664e-05 [merge_forward]: 1.496e-05 [cell_reuse_recompute_pass]: 2.48e-06 [offload_activation]: 2.612e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.24e-05 [merge_recompute_call_nodes]: 1.40999e-06 [before_grad]: 4.884e-05 [set_forward_comm_id_for_comm_node_pass]: 1.696e-05 [meta_fg_expand]: 2.137e-05 [flash_sp_send_recv_attached]: 5.66e-06 [receive_attached]: 2.19001e-06 [after_resolve]: 3.546e-05 [a_after_grad]: 4.387e-05 [renormalize]: 0.169502 [add_forward_monad_depend]: 2.315e-05 [auto_monad_grad]: 3.6e-06 [auto_monad_eliminator]: 0.00011124 [cse]: 0.00070882 [a_3]: 0.0002066 [Cycle 2]: 0.00255565, [45] [expand_dump_flag]: 3.9e-06 [switch_simplify]: 3.067e-05 [loop_unroll]: 2.576e-05 [a_1]: 0.00081996 [with_stream_mark]: 4.243e-05 [recompute_prepare]: 2.734e-05 [updatestate_depend_eliminate]: 1.797e-05 [updatestate_assign_eliminate]: 1.538e-05 [updatestate_loads_eliminate]: 2.044e-05 [parameter_eliminate]: 3.35e-06 [a_2]: 0.00038156 [accelerated_algorithm]: 3.811e-05 [shard]: 3.01999e-06 [meta_shard_fg_expand]: 1.187e-05 [shard_inline]: 2.495e-05 [merge_send_recv]: 2.348e-05 [auto_parallel]: 2.267e-05 [parallel]: 1.055e-05 [flash_sp]: 4.40999e-06 [merge_comm]: 1.535e-05 [allreduce_fusion]: 1.64e-05 [matmul_add_comm_reduction]: 2.885e-05 [allreduce_slice_to_reducescatter]: 1.03001e-06 [virtual_shard_identity]: 2.796e-05 [virtual_dataset]: 2.462e-05 [get_grad_eliminate_]: 2.343e-05 [virtual_output]: 2.465e-05 [merge_forward]: 1.606e-05 [cell_reuse_recompute_pass]: 3.64002e-06 [offload_activation]: 2.599e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.051e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 4.359e-05 [set_forward_comm_id_for_comm_node_pass]: 1.562e-05 [meta_fg_expand]: 1.205e-05 [flash_sp_send_recv_attached]: 1.89e-06 [receive_attached]: 2.48e-06 [after_resolve]: 3.494e-05 [a_after_grad]: 4.175e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.57997e-06 [auto_monad_grad]: 2.93e-06 [auto_monad_eliminator]: 7.424e-05 [cse]: 0.0001089 [a_3]: 0.00016883 [py_interpret_to_execute_after_opt_a]: 4.438e-05 [slice_cell_reuse_recomputed_activation]: 2.36998e-06 [rewriter_after_opt_a]: 0.00093019 [convert_after_rewriter]: 3.19e-05 [order_py_execute_after_rewriter]: 1.484e-05 [mutable_eliminate]: 0.00109852 [opt_b]: 0.00115507, [1] [Cycle 1]: 0.00112586, [7] [b_1]: 0.00074439 [b_2]: 3.19e-05 [updatestate_depend_eliminate]: 2.886e-05 [updatestate_assign_eliminate]: 1.561e-05 [updatestate_loads_eliminate]: 2.317e-05 [renormalize]: 9.50007e-07 [cse]: 0.00020609 [optimize_parallel_all_gather_comm]: 5.285e-05 [overlap_param_gather]: 2.08998e-06 [cconv]: 4.966e-05 [loop_unroll]: 0.00088621 [opt_after_cconv]: 0.00037847, [1] [Cycle 1]: 0.00036944, [7] [c_1]: 0.00017361 [parameter_eliminate]: 6.63e-06 [updatestate_depend_eliminate]: 2.041e-05 [updatestate_assign_eliminate]: 1.45e-05 [updatestate_loads_eliminate]: 1.794e-05 [cse]: 9.575e-05 [renormalize]: 7.60017e-07 [remove_dup_value]: 0.00012218 [tuple_transform]: 0.0003027, [1] [Cycle 1]: 0.00029661, [4] [d_1]: 0.00024208 [none_parameter_eliminate]: 2.53e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 2.805e-05 [partial_unused_args_eliminate]: 2.56e-06 [add_recomputation]: 0.00017207 [cse_after_recomputation]: 8.232e-05, [1] [Cycle 1]: 7.535e-05, [1] [cse]: 6.794e-05 [environ_conv]: 2.962e-05 [swap_dp_allreduce_reducescatter]: 2.047e-05 [bias_add_comm_swap]: 3.7e-06 [label_micro_interleaved_index]: 6.43003e-06 [label_fine_grained_interleaved_index]: 2.58e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.34999e-06 [micro_interleaved_order_control]: 3.08998e-06 [assign_add_opt]: 1.54e-06 [ForceFp32Comm]: 9.29984e-07 [remove_cast_before_assign_add]: 1.14e-06 [full_micro_interleaved_order_control]: 2.06998e-06 [reorder_send_recv_between_fp_bp]: 2.84999e-06 [comm_op_add_attrs]: 1.14e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.10999e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 1.58002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.98002e-06 [control_data_broadcast_order]: 4.505e-05 [grouped_pairwise_exchange_alltoall]: 1.63002e-06 [offloading_packed_experts]: 1.408e-05 [overlap_recompute_and_grad_model_parallel]: 1.174e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.15999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.40002e-06 [overlap_grad_ring_attention]: 1.026e-05 [overlap_grad_flash_sp]: 5.775e-05 [begin_end_overlap_inline]: 6.60017e-07 [split_matmul_comm_elemetwise]: 2.33998e-06 [split_layernorm_comm]: 1.89999e-06 [handle_group_info]: 1.01002e-06 [symbol_engine_optimizer]: 0.00057894, [1] [Cycle 1]: 0.00057259, [6] [build]: 0.00031837 [elim_shapecalc]: 4.038e-05 [elim_not_effective]: 5.862e-05 [opt_reshape]: 3.834e-05 [fold_const_symbol]: 6.751e-05 [renormalize]: 6.19999e-07 [detach_backward]: 2.86999e-06 [pipeline_parallel_scheduler]: 1.51002e-06 [auto_monad_reorder]: 8.457e-05 [get_jit_bprop_graph]: 2.42001e-06 [rewriter_after_jit_bprop_graph]: 7.2e-06 [opt_after_jit_grad]: 0.00088406 [validate]: 0.00016106 Sums bootstrap : 0.000677s : 0.02% type_inference : 2.722382s : 89.86% event_method : 0.000220s : 0.01% auto_monad : 0.000813s : 0.03% graph_reusing : 0.000057s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000211s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000054s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.058291s : 1.92% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000004s : 0.00% dataset_repeat_opt : 0.000004s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000456s : 0.02% optimize.rewriter_before_opt_a : 0.000886s : 0.03% optimize.opt_a.expand_dump_flag : 0.000045s : 0.00% optimize.opt_a.switch_simplify : 0.000911s : 0.03% optimize.opt_a.loop_unroll : 0.000361s : 0.01% optimize.opt_a.a_1 : 0.063388s : 2.09% optimize.opt_a.with_stream_mark : 0.000112s : 0.00% optimize.opt_a.recompute_prepare : 0.000074s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000042s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000034s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000113s : 0.00% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.001360s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000112s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000038s : 0.00% optimize.opt_a.shard_inline : 0.000052s : 0.00% optimize.opt_a.merge_send_recv : 0.000046s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000033s : 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 : 0.000050s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000048s : 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 : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000052s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000103s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000092s : 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 : 0.000008s : 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 : 0.169502s : 5.59% optimize.opt_a.add_forward_monad_depend : 0.000027s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000185s : 0.01% optimize.opt_a.cse : 0.000818s : 0.03% optimize.opt_a.a_3 : 0.000375s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000044s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000930s : 0.03% optimize.convert_after_rewriter : 0.000032s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.001099s : 0.04% optimize.opt_b.b_1 : 0.000744s : 0.02% optimize.opt_b.b_2 : 0.000032s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000029s : 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 : 0.000206s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000053s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000050s : 0.00% optimize.loop_unroll : 0.000886s : 0.03% optimize.opt_after_cconv.c_1 : 0.000174s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 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 : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000096s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000122s : 0.00% optimize.tuple_transform.d_1 : 0.000242s : 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 : 0.000028s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000172s : 0.01% optimize.cse_after_recomputation.cse : 0.000068s : 0.00% optimize.environ_conv : 0.000030s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000020s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000045s : 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 : 0.000012s : 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 : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000058s : 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 : 0.000318s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000059s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000038s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000068s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000085s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000884s : 0.03% validate : 0.000161s : 0.01% Time group info: ------[substitution.] 0.004449 612 1.14% : 0.000051s : 5: substitution.arithmetic_simplify 0.43% : 0.000019s : 8: substitution.depend_value_elim 0.35% : 0.000016s : 17: substitution.elim_not_effective 0.46% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.67% : 0.000030s : 17: substitution.fold_const_symbol 0.43% : 0.000019s : 21: substitution.graph_param_transform 68.98% : 0.003069s : 71: substitution.inline 0.43% : 0.000019s : 35: substitution.j_node_and_user_rematch 0.95% : 0.000042s : 10: substitution.less_batch_normalization 1.57% : 0.000070s : 2: substitution.list_to_tuple_eliminator_ 0.23% : 0.000010s : 12: substitution.load_eliminater 0.68% : 0.000030s : 21: substitution.minmaximum_grad 0.18% : 0.000008s : 2: substitution.opt_reshape 0.51% : 0.000023s : 35: substitution.remove_not_recompute_node 0.23% : 0.000010s : 6: substitution.replace_old_param 1.60% : 0.000071s : 18: substitution.reshape_eliminate 1.22% : 0.000054s : 24: substitution.switch_simplify 3.81% : 0.000169s : 51: substitution.tuple_list_convert_item_index_to_positive 2.13% : 0.000095s : 51: substitution.tuple_list_get_item_const_eliminator 2.81% : 0.000125s : 51: substitution.tuple_list_get_item_depend_reorder 5.48% : 0.000244s : 73: substitution.tuple_list_get_item_eliminator 2.76% : 0.000123s : 51: substitution.tuple_list_get_set_item_eliminator 0.43% : 0.000019s : 8: substitution.updatestate_pure_node_eliminater 2.52% : 0.000112s : 11: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.721933 2 89.34% : 2.431871s : 1: type_inference.infer 10.66% : 0.290061s : 1: type_inference.specialize ------[replace.] 0.001383 115 3.09% : 0.000043s : 5: replace.depend_value_elim 59.56% : 0.000824s : 71: replace.inline 4.25% : 0.000059s : 2: replace.list_to_tuple_eliminator_ 24.52% : 0.000339s : 24: replace.switch_simplify 8.57% : 0.000118s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003161 115 0.07% : 0.000002s : 5: match.depend_value_elim 95.42% : 0.003016s : 71: match.inline 2.13% : 0.000067s : 2: match.list_to_tuple_eliminator_ 1.20% : 0.000038s : 24: match.switch_simplify 1.18% : 0.000037s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001794 10672 1.54% : 0.000028s : 131: predicate.accumulaten_eliminater 0.44% : 0.000008s : 21: predicate.ad_related_special_op_eliminate 0.53% : 0.000010s : 70: predicate.addn_check_dump 1.10% : 0.000020s : 131: predicate.addn_zero_filter 1.03% : 0.000018s : 131: predicate.adjust_all_reduce_mul_add 2.50% : 0.000045s : 201: predicate.arithmetic_simplify 1.16% : 0.000021s : 131: predicate.cast_eliminate 0.36% : 0.000007s : 42: predicate.check_bprop_eliminate 0.54% : 0.000010s : 70: predicate.compare_switch_simplify 0.09% : 0.000002s : 21: predicate.const_output_eliminate 0.64% : 0.000012s : 73: predicate.depend_value_elim 1.15% : 0.000021s : 131: predicate.dict_get_item_const_eliminator 1.17% : 0.000021s : 131: predicate.dict_get_item_eliminator 1.04% : 0.000019s : 131: predicate.dict_set_item_eliminator 0.43% : 0.000008s : 42: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 21: predicate.elim_not_effective 0.21% : 0.000004s : 21: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000022s : 152: predicate.environ_add_const_eliminate 1.32% : 0.000024s : 152: predicate.environ_get_add_eliminate 1.19% : 0.000021s : 152: predicate.environ_get_depend_swap 1.83% : 0.000033s : 222: predicate.environ_get_eliminate 1.21% : 0.000022s : 152: predicate.environ_get_set_eliminate 1.81% : 0.000032s : 217: predicate.exchange_switch_depend_value 2.76% : 0.000050s : 217: predicate.float_depend_g_call 0.55% : 0.000010s : 70: predicate.float_environ_get_switch 0.76% : 0.000014s : 91: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 21: predicate.fold_const_symbol 0.38% : 0.000007s : 43: predicate.get_grad_eliminate 0.12% : 0.000002s : 21: predicate.graph_param_transform 0.53% : 0.000010s : 70: predicate.incorporate_call 0.51% : 0.000009s : 70: predicate.incorporate_call_switch 6.12% : 0.000110s : 503: predicate.inline 0.52% : 0.000009s : 43: predicate.inline_without_move 0.17% : 0.000003s : 43: predicate.j_node_and_user_rematch 0.50% : 0.000009s : 43: predicate.less_batch_normalization 1.77% : 0.000032s : 188: predicate.list_to_tuple_eliminator_ 2.56% : 0.000046s : 319: predicate.load_eliminater 0.42% : 0.000008s : 21: predicate.loop_unroll_after_grad 2.99% : 0.000054s : 322: predicate.loop_unroll_before_grad 1.55% : 0.000028s : 173: predicate.make_slice_get_slice_eliminator 0.55% : 0.000010s : 70: predicate.merge_addn 0.33% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.33% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.05% : 0.000019s : 131: predicate.minmaximum_grad 0.65% : 0.000012s : 21: predicate.mutable_eliminate 0.21% : 0.000004s : 21: predicate.opt_reshape 0.20% : 0.000004s : 21: predicate.parallel_virtual_node 3.21% : 0.000058s : 217: predicate.partial_defer_inline 1.49% : 0.000027s : 167: predicate.partial_eliminate 1.10% : 0.000020s : 131: predicate.print_const_string_wrapper 0.52% : 0.000009s : 65: predicate.reduce_all_const_elim 1.52% : 0.000027s : 131: predicate.reduce_eliminate 2.57% : 0.000046s : 319: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 43: predicate.remove_not_recompute_node 1.09% : 0.000020s : 188: predicate.replace_applicator 0.20% : 0.000004s : 43: predicate.replace_old_param 0.12% : 0.000002s : 21: predicate.reset_defer_inline 1.26% : 0.000023s : 131: predicate.reshape_eliminate 0.36% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.22% : 0.000004s : 21: predicate.row_tensor_eliminate 0.50% : 0.000009s : 42: predicate.same_eliminate 0.22% : 0.000004s : 48: predicate.set_cell_output_no_recompute 0.43% : 0.000008s : 43: predicate.shard_identity_eliminate 0.38% : 0.000007s : 42: predicate.special_op_eliminate 0.63% : 0.000011s : 70: predicate.specialize_transform 0.51% : 0.000009s : 42: predicate.split_environ_get_set_with_tuple_value 0.43% : 0.000008s : 43: predicate.stack_unstack_eliminate 0.19% : 0.000003s : 21: predicate.switch_call_monad_eliminater 1.96% : 0.000035s : 217: predicate.switch_defer_inline 2.19% : 0.000039s : 259: predicate.switch_layer_defer_inline 6.38% : 0.000115s : 678: predicate.switch_simplify 1.15% : 0.000021s : 131: predicate.tile_eliminate 1.08% : 0.000019s : 131: predicate.transpose_eliminate 1.69% : 0.000030s : 173: predicate.tuple_list_convert_item_index_to_positive 1.75% : 0.000031s : 173: predicate.tuple_list_get_item_const_eliminator 1.60% : 0.000029s : 173: predicate.tuple_list_get_item_depend_reorder 3.29% : 0.000059s : 256: predicate.tuple_list_get_item_eliminator 1.63% : 0.000029s : 173: predicate.tuple_list_get_set_item_eliminator 2.38% : 0.000043s : 243: predicate.tuple_list_set_item_eliminator 1.61% : 0.000029s : 186: predicate.tuple_to_list_eliminator_ 2.51% : 0.000045s : 319: predicate.updatestate_pure_node_eliminater 3.30% : 0.000059s : 389: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 21: predicate.value_based_eliminate 0.39% : 0.000007s : 43: predicate.virtual_dataset_eliminate 0.37% : 0.000007s : 43: predicate.virtual_output_eliminate 0.16% : 0.000003s : 21: predicate.virtual_view_grad_eliminate 0.99% : 0.000018s : 21: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.136240 135 94.18% : 0.128307s : 55: func_graph_cloner_run.FuncGraphClonerGraph 5.82% : 0.007933s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.577905 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.15% : 0.005331s : 1: add_attr 0.15% : 0.005312s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000178s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000830s : 1: auto_monad 0.00% : 0.000091s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000710s : 1: bootstrap 0.00% : 0.000053s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000049s : 1: control_data_broadcast_order 0.00% : 0.000038s : 1: convert_after_rewriter 0.00% : 0.000086s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000033s : 1: environ_conv 0.01% : 0.000233s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000064s : 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% : 0.000012s : 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% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000898s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.75% : 0.026768s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000048s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000063s : 1: opt.transform.mutable_eliminate 1.87% : 0.067037s : 95: opt.transform.opt_a 0.00% : 0.000172s : 1: opt.transform.opt_after_cconv 0.00% : 0.000095s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000714s : 28: opt.transform.opt_b 0.01% : 0.000267s : 2: opt.transform.opt_trans_graph 0.01% : 0.000199s : 4: opt.transform.symbol_engine_opt 6.69% : 0.239328s : 1: opt_a 0.01% : 0.000383s : 1: opt_after_cconv 0.03% : 0.000898s : 1: opt_after_jit_grad 0.03% : 0.001165s : 1: opt_b 7.63% : 0.272819s : 1: optimize 0.00% : 0.000057s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000062s : 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% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000007s : 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 1.63% : 0.058341s : 1: pre_auto_parallel 0.01% : 0.000471s : 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 0.00% : 0.000128s : 1: remove_dup_value 0.57% : 0.020323s : 1: renormalize.infer 4.17% : 0.149155s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000944s : 1: rewriter_after_opt_a 0.03% : 0.000901s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000582s : 1: symbol_engine_optimizer 0.01% : 0.000306s : 1: tuple_transform 76.09% : 2.722415s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_qkv_1408_128_128[True-mstype0-128-32] tests/st/infer/ops/test_internal_ops/test_matmul_biasadd_split.py::test_matmul_qkv_1408_128_128[True-mstype0-128-32],max_mem:106.0M =============================== 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 146.85s (0:02:26) ==================