==================================================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_split.py [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:37:30.304.576 [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 = 3.84978, [21] [bootstrap]: 0.00064493 [type_inference]: 3.39161 [event_method]: 0.00020817 [auto_monad]: 0.00176725 [graph_reusing]: 5.956e-05 [inline]: 3.75e-06 [add_attr]: 0.00873521, [1] [add_attr_with_inline]: 0.00871595, [1] [Cycle 1]: 0.00034903, [2] [tag_attr]: 0.00020319 [meta_addattr_fg_expand]: 5.664e-05 [parallel-infer-symbol]: 4.64002e-06 [pre_auto_parallel]: 0.00026513 [insert-virtual-dataset]: 3.76001e-06 [parallel-infer-symbol-second]: 1.79e-06 [dataset_repeat_opt]: 2.24001e-06 [pipeline_split]: 2.02001e-06 [optimize]: 0.445165, [53] [py_interpret_to_execute]: 0.0002051 [rewriter_before_opt_a]: 0.000869 [opt_a]: 0.271112, [2] [Cycle 1]: 0.268926, [45] [expand_dump_flag]: 1.825e-05 [switch_simplify]: 0.00078014 [loop_unroll]: 0.00027153 [a_1]: 0.25446 [with_stream_mark]: 6.123e-05 [recompute_prepare]: 4.572e-05 [updatestate_depend_eliminate]: 2.152e-05 [updatestate_assign_eliminate]: 2.119e-05 [updatestate_loads_eliminate]: 1.919e-05 [parameter_eliminate]: 2.78e-06 [a_2]: 0.00092097 [accelerated_algorithm]: 6.978e-05 [shard]: 2.89001e-06 [meta_shard_fg_expand]: 2.579e-05 [shard_inline]: 2.568e-05 [merge_send_recv]: 2.192e-05 [auto_parallel]: 2.219e-05 [parallel]: 5.101e-05 [flash_sp]: 1.53e-05 [merge_comm]: 1.503e-05 [allreduce_fusion]: 1.373e-05 [matmul_add_comm_reduction]: 3.087e-05 [allreduce_slice_to_reducescatter]: 1.20001e-06 [virtual_shard_identity]: 3.234e-05 [virtual_dataset]: 2.596e-05 [get_grad_eliminate_]: 2.467e-05 [virtual_output]: 2.35e-05 [merge_forward]: 1.421e-05 [cell_reuse_recompute_pass]: 2.01e-06 [offload_activation]: 2.646e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.697e-05 [merge_recompute_call_nodes]: 1.89e-06 [before_grad]: 4.4e-05 [set_forward_comm_id_for_comm_node_pass]: 1.618e-05 [meta_fg_expand]: 2.164e-05 [flash_sp_send_recv_attached]: 6.93e-06 [receive_attached]: 1.525e-05 [after_resolve]: 3.43e-05 [a_after_grad]: 3.965e-05 [renormalize]: 0.00997039 [add_forward_monad_depend]: 1.405e-05 [auto_monad_grad]: 2.87002e-06 [auto_monad_eliminator]: 8.327e-05 [cse]: 0.00092842 [a_3]: 0.00018317 [Cycle 2]: 0.00216864, [45] [expand_dump_flag]: 3.28998e-06 [switch_simplify]: 2.614e-05 [loop_unroll]: 2.121e-05 [a_1]: 0.00067629 [with_stream_mark]: 3.087e-05 [recompute_prepare]: 2.178e-05 [updatestate_depend_eliminate]: 1.475e-05 [updatestate_assign_eliminate]: 1.218e-05 [updatestate_loads_eliminate]: 1.413e-05 [parameter_eliminate]: 2.29001e-06 [a_2]: 0.00033082 [accelerated_algorithm]: 3.077e-05 [shard]: 2.58003e-06 [meta_shard_fg_expand]: 7.20998e-06 [shard_inline]: 2.197e-05 [merge_send_recv]: 1.97e-05 [auto_parallel]: 2.064e-05 [parallel]: 1.205e-05 [flash_sp]: 4.94e-06 [merge_comm]: 1.337e-05 [allreduce_fusion]: 1.272e-05 [matmul_add_comm_reduction]: 2.181e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 2.33e-05 [virtual_dataset]: 2.099e-05 [get_grad_eliminate_]: 2.129e-05 [virtual_output]: 2.079e-05 [merge_forward]: 1.231e-05 [cell_reuse_recompute_pass]: 3.15998e-06 [offload_activation]: 2.346e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.346e-05 [merge_recompute_call_nodes]: 1.76e-06 [before_grad]: 3.797e-05 [set_forward_comm_id_for_comm_node_pass]: 1.342e-05 [meta_fg_expand]: 1.065e-05 [flash_sp_send_recv_attached]: 2.29999e-06 [receive_attached]: 2.44999e-06 [after_resolve]: 2.837e-05 [a_after_grad]: 3.624e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 2.64001e-06 [auto_monad_grad]: 2.29001e-06 [auto_monad_eliminator]: 4.996e-05 [cse]: 0.00011032 [a_3]: 0.00015041 [py_interpret_to_execute_after_opt_a]: 3.001e-05 [slice_cell_reuse_recomputed_activation]: 2.34001e-06 [rewriter_after_opt_a]: 0.00088923 [convert_after_rewriter]: 2.393e-05 [order_py_execute_after_rewriter]: 1.491e-05 [mutable_eliminate]: 0.00083956 [opt_b]: 0.168037, [1] [Cycle 1]: 0.168026, [7] [b_1]: 0.167665 [b_2]: 3.509e-05 [updatestate_depend_eliminate]: 2.868e-05 [updatestate_assign_eliminate]: 1.235e-05 [updatestate_loads_eliminate]: 1.727e-05 [renormalize]: 1.04e-06 [cse]: 0.00017364 [optimize_parallel_all_gather_comm]: 4.813e-05 [overlap_param_gather]: 7.85e-06 [cconv]: 5.075e-05 [loop_unroll]: 0.00083709 [opt_after_cconv]: 0.0003793, [1] [Cycle 1]: 0.00036855, [7] [c_1]: 0.0001617 [parameter_eliminate]: 6.06e-06 [updatestate_depend_eliminate]: 2.282e-05 [updatestate_assign_eliminate]: 1.504e-05 [updatestate_loads_eliminate]: 1.76e-05 [cse]: 9.827e-05 [renormalize]: 1.39e-06 [remove_dup_value]: 0.00010704 [tuple_transform]: 0.00029027, [1] [Cycle 1]: 0.00028355, [4] [d_1]: 0.00023004 [none_parameter_eliminate]: 2.66999e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 2.492e-05 [partial_unused_args_eliminate]: 3.18998e-06 [add_recomputation]: 0.00017606 [cse_after_recomputation]: 8.069e-05, [1] [Cycle 1]: 7.413e-05, [1] [cse]: 6.524e-05 [environ_conv]: 3.975e-05 [swap_dp_allreduce_reducescatter]: 1.904e-05 [bias_add_comm_swap]: 3.58e-06 [label_micro_interleaved_index]: 6.29999e-06 [label_fine_grained_interleaved_index]: 3.04001e-06 [merge_cast_opt]: 1.79e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.87002e-06 [assign_add_opt]: 1.40999e-06 [ForceFp32Comm]: 9.89996e-07 [remove_cast_before_assign_add]: 1.37999e-06 [full_micro_interleaved_order_control]: 2.27001e-06 [reorder_send_recv_between_fp_bp]: 3.04001e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.19e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 2.616e-05 [overlap_opt_shard_grad_in_pipeline]: 2.14e-06 [control_data_broadcast_order]: 4.304e-05 [grouped_pairwise_exchange_alltoall]: 1.99e-06 [offloading_packed_experts]: 1.166e-05 [overlap_recompute_and_grad_model_parallel]: 1.108e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.25001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.66999e-06 [overlap_grad_ring_attention]: 9.96998e-06 [overlap_grad_flash_sp]: 8.147e-05 [begin_end_overlap_inline]: 8.59989e-07 [split_matmul_comm_elemetwise]: 2.82002e-06 [split_layernorm_comm]: 1.64e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00057298, [1] [Cycle 1]: 0.00056589, [6] [build]: 0.00031251 [elim_shapecalc]: 3.853e-05 [elim_not_effective]: 6.423e-05 [opt_reshape]: 3.683e-05 [fold_const_symbol]: 6.154e-05 [renormalize]: 4.19997e-07 [detach_backward]: 3.31999e-06 [pipeline_parallel_scheduler]: 2.21e-06 [auto_monad_reorder]: 7.218e-05 [get_jit_bprop_graph]: 2.61e-06 [rewriter_after_jit_bprop_graph]: 6.43998e-06 [opt_after_jit_grad]: 0.00084823 [validate]: 0.00013355 Sums bootstrap : 0.000645s : 0.02% type_inference : 3.391606s : 88.33% event_method : 0.000208s : 0.01% auto_monad : 0.001767s : 0.05% graph_reusing : 0.000060s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000203s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000057s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000265s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000205s : 0.01% optimize.rewriter_before_opt_a : 0.000869s : 0.02% optimize.opt_a.expand_dump_flag : 0.000022s : 0.00% optimize.opt_a.switch_simplify : 0.000806s : 0.02% optimize.opt_a.loop_unroll : 0.000293s : 0.01% optimize.opt_a.a_1 : 0.255136s : 6.64% optimize.opt_a.with_stream_mark : 0.000092s : 0.00% optimize.opt_a.recompute_prepare : 0.000068s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000036s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000033s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000033s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001252s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000101s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000033s : 0.00% optimize.opt_a.shard_inline : 0.000048s : 0.00% optimize.opt_a.merge_send_recv : 0.000042s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000063s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000028s : 0.00% optimize.opt_a.allreduce_fusion : 0.000026s : 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 : 0.000056s : 0.00% optimize.opt_a.virtual_dataset : 0.000047s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000044s : 0.00% optimize.opt_a.merge_forward : 0.000027s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000050s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000100s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000082s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000030s : 0.00% optimize.opt_a.meta_fg_expand : 0.000032s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000018s : 0.00% optimize.opt_a.after_resolve : 0.000063s : 0.00% optimize.opt_a.a_after_grad : 0.000076s : 0.00% optimize.opt_a.renormalize : 0.009970s : 0.26% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000133s : 0.00% optimize.opt_a.cse : 0.001039s : 0.03% optimize.opt_a.a_3 : 0.000334s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000889s : 0.02% optimize.convert_after_rewriter : 0.000024s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000840s : 0.02% optimize.opt_b.b_1 : 0.167665s : 4.37% optimize.opt_b.b_2 : 0.000035s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000029s : 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 : 0.000174s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000048s : 0.00% optimize.overlap_param_gather : 0.000008s : 0.00% optimize.cconv : 0.000051s : 0.00% optimize.loop_unroll : 0.000837s : 0.02% optimize.opt_after_cconv.c_1 : 0.000162s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000098s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000107s : 0.00% optimize.tuple_transform.d_1 : 0.000230s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000176s : 0.00% optimize.cse_after_recomputation.cse : 0.000065s : 0.00% optimize.environ_conv : 0.000040s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 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 : 0.000026s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000043s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000012s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000081s : 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 : 0.000313s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000039s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000064s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000037s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000062s : 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 : 0.000072s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000848s : 0.02% validate : 0.000134s : 0.00% Time group info: ------[substitution.] 0.003154 569 0.65% : 0.000020s : 8: substitution.depend_value_elim 0.72% : 0.000023s : 14: substitution.elim_not_effective 0.58% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.88% : 0.000028s : 14: substitution.fold_const_symbol 0.56% : 0.000018s : 17: substitution.graph_param_transform 65.68% : 0.002071s : 71: substitution.inline 0.46% : 0.000014s : 29: substitution.j_node_and_user_rematch 1.15% : 0.000036s : 6: substitution.less_batch_normalization 1.97% : 0.000062s : 2: substitution.list_to_tuple_eliminator_ 0.21% : 0.000007s : 6: substitution.load_eliminater 1.10% : 0.000035s : 21: substitution.minmaximum_grad 0.26% : 0.000008s : 2: substitution.opt_reshape 0.71% : 0.000022s : 29: substitution.remove_not_recompute_node 0.26% : 0.000008s : 4: substitution.replace_old_param 1.69% : 0.000053s : 18: substitution.reshape_eliminate 1.73% : 0.000055s : 24: substitution.switch_simplify 4.65% : 0.000147s : 51: substitution.tuple_list_convert_item_index_to_positive 2.24% : 0.000071s : 51: substitution.tuple_list_get_item_const_eliminator 3.20% : 0.000101s : 51: substitution.tuple_list_get_item_depend_reorder 6.71% : 0.000212s : 73: substitution.tuple_list_get_item_eliminator 3.15% : 0.000099s : 51: substitution.tuple_list_get_set_item_eliminator 0.77% : 0.000024s : 6: substitution.updatestate_pure_node_eliminater 0.66% : 0.000021s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.391244 2 94.23% : 3.195625s : 1: type_inference.infer 5.77% : 0.195619s : 1: type_inference.specialize ------[replace.] 0.247211 115 0.02% : 0.000045s : 5: replace.depend_value_elim 99.78% : 0.246661s : 71: replace.inline 0.02% : 0.000044s : 2: replace.list_to_tuple_eliminator_ 0.13% : 0.000315s : 24: replace.switch_simplify 0.06% : 0.000146s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002175 115 0.11% : 0.000002s : 5: match.depend_value_elim 93.24% : 0.002028s : 71: match.inline 2.74% : 0.000060s : 2: match.list_to_tuple_eliminator_ 1.94% : 0.000042s : 24: match.switch_simplify 1.97% : 0.000043s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001665 9701 1.13% : 0.000019s : 123: predicate.accumulaten_eliminater 0.33% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.49% : 0.000008s : 58: predicate.addn_check_dump 1.10% : 0.000018s : 123: predicate.addn_zero_filter 1.03% : 0.000017s : 123: predicate.adjust_all_reduce_mul_add 2.14% : 0.000036s : 181: predicate.arithmetic_simplify 1.14% : 0.000019s : 123: predicate.cast_eliminate 0.31% : 0.000005s : 34: predicate.check_bprop_eliminate 0.53% : 0.000009s : 58: predicate.compare_switch_simplify 0.14% : 0.000002s : 17: predicate.const_output_eliminate 0.61% : 0.000010s : 61: predicate.depend_value_elim 1.17% : 0.000019s : 123: predicate.dict_get_item_const_eliminator 1.26% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.10% : 0.000018s : 123: predicate.dict_set_item_eliminator 0.46% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.12% : 0.000002s : 17: predicate.elim_not_effective 0.23% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000021s : 140: predicate.environ_add_const_eliminate 1.20% : 0.000020s : 140: predicate.environ_get_add_eliminate 2.06% : 0.000034s : 140: predicate.environ_get_depend_swap 1.73% : 0.000029s : 198: predicate.environ_get_eliminate 1.24% : 0.000021s : 140: predicate.environ_get_set_eliminate 1.89% : 0.000032s : 209: predicate.exchange_switch_depend_value 3.00% : 0.000050s : 209: predicate.float_depend_g_call 0.50% : 0.000008s : 58: predicate.float_environ_get_switch 0.73% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.40% : 0.000007s : 35: predicate.get_grad_eliminate 0.12% : 0.000002s : 17: predicate.graph_param_transform 0.55% : 0.000009s : 58: predicate.incorporate_call 0.51% : 0.000008s : 58: predicate.incorporate_call_switch 6.54% : 0.000109s : 459: predicate.inline 0.49% : 0.000008s : 35: predicate.inline_without_move 0.17% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.47% : 0.000008s : 36: predicate.less_batch_normalization 1.64% : 0.000027s : 172: predicate.list_to_tuple_eliminator_ 2.54% : 0.000042s : 295: predicate.load_eliminater 0.44% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.12% : 0.000052s : 314: predicate.loop_unroll_before_grad 1.47% : 0.000024s : 157: predicate.make_slice_get_slice_eliminator 0.52% : 0.000009s : 58: predicate.merge_addn 0.29% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.31% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.13% : 0.000019s : 123: predicate.minmaximum_grad 0.43% : 0.000007s : 17: predicate.mutable_eliminate 0.18% : 0.000003s : 17: predicate.opt_reshape 0.20% : 0.000003s : 17: predicate.parallel_virtual_node 3.21% : 0.000054s : 209: predicate.partial_defer_inline 1.64% : 0.000027s : 155: predicate.partial_eliminate 1.12% : 0.000019s : 123: predicate.print_const_string_wrapper 0.47% : 0.000008s : 53: predicate.reduce_all_const_elim 1.45% : 0.000024s : 123: predicate.reduce_eliminate 2.57% : 0.000043s : 295: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 35: predicate.remove_not_recompute_node 1.12% : 0.000019s : 172: predicate.replace_applicator 0.19% : 0.000003s : 35: predicate.replace_old_param 0.09% : 0.000002s : 17: predicate.reset_defer_inline 1.23% : 0.000020s : 123: predicate.reshape_eliminate 0.32% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.20% : 0.000003s : 17: predicate.row_tensor_eliminate 0.44% : 0.000007s : 34: predicate.same_eliminate 0.22% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.42% : 0.000007s : 35: predicate.shard_identity_eliminate 0.35% : 0.000006s : 34: predicate.special_op_eliminate 0.70% : 0.000012s : 58: predicate.specialize_transform 0.40% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.42% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.13% : 0.000036s : 209: predicate.switch_defer_inline 2.28% : 0.000038s : 243: predicate.switch_layer_defer_inline 6.61% : 0.000110s : 646: predicate.switch_simplify 1.17% : 0.000019s : 123: predicate.tile_eliminate 1.07% : 0.000018s : 123: predicate.transpose_eliminate 1.84% : 0.000031s : 157: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000030s : 157: predicate.tuple_list_get_item_const_eliminator 1.73% : 0.000029s : 157: predicate.tuple_list_get_item_depend_reorder 3.32% : 0.000055s : 228: predicate.tuple_list_get_item_eliminator 1.66% : 0.000028s : 157: predicate.tuple_list_get_set_item_eliminator 2.35% : 0.000039s : 215: predicate.tuple_list_set_item_eliminator 1.55% : 0.000026s : 170: predicate.tuple_to_list_eliminator_ 2.58% : 0.000043s : 295: predicate.updatestate_pure_node_eliminater 3.14% : 0.000052s : 353: predicate.updatestate_useless_node_eliminater 0.27% : 0.000004s : 17: predicate.value_based_eliminate 0.36% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.37% : 0.000006s : 35: predicate.virtual_output_eliminate 0.15% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.22% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.040743 133 88.50% : 0.036059s : 53: func_graph_cloner_run.FuncGraphClonerGraph 11.50% : 0.004684s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.573172 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.19% : 0.008743s : 1: add_attr 0.19% : 0.008721s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000182s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.001795s : 1: auto_monad 0.00% : 0.000078s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.01% : 0.000680s : 1: bootstrap 0.00% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000047s : 1: control_data_broadcast_order 0.00% : 0.000029s : 1: convert_after_rewriter 0.00% : 0.000084s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000045s : 1: environ_conv 0.00% : 0.000220s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000069s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000848s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000851s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000046s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000044s : 1: opt.transform.mutable_eliminate 5.65% : 0.258390s : 95: opt.transform.opt_a 0.00% : 0.000160s : 1: opt.transform.opt_after_cconv 0.00% : 0.000083s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000640s : 28: opt.transform.opt_b 0.01% : 0.000251s : 2: opt.transform.opt_trans_graph 0.00% : 0.000195s : 4: opt.transform.symbol_engine_opt 5.93% : 0.271117s : 1: opt_a 0.01% : 0.000384s : 1: opt_after_cconv 0.02% : 0.000860s : 1: opt_after_jit_grad 3.67% : 0.168042s : 1: opt_b 9.73% : 0.445171s : 1: optimize 0.00% : 0.000052s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000086s : 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% : 0.000031s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000012s : 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% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000274s : 1: pre_auto_parallel 0.00% : 0.000212s : 1: py_interpret_to_execute 0.00% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000114s : 1: remove_dup_value 0.12% : 0.005546s : 1: renormalize.infer 0.10% : 0.004405s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000898s : 1: rewriter_after_opt_a 0.02% : 0.000881s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000577s : 1: symbol_engine_optimizer 0.01% : 0.000294s : 1: tuple_transform 74.16% : 3.391642s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape0-256] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape0-256],max_mem:306.0M [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:39:05.736.345 [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 = 3.4445, [21] [bootstrap]: 0.0007316 [type_inference]: 2.90132 [event_method]: 0.0002182 [auto_monad]: 0.0370412 [graph_reusing]: 0.00012834 [inline]: 4.05998e-06 [add_attr]: 0.0116831, [1] [add_attr_with_inline]: 0.0116663, [1] [Cycle 1]: 0.00033397, [2] [tag_attr]: 0.00021394 [meta_addattr_fg_expand]: 6.22e-05 [parallel-infer-symbol]: 3.74002e-06 [pre_auto_parallel]: 0.0002533 [insert-virtual-dataset]: 2.76e-06 [parallel-infer-symbol-second]: 1.42e-06 [dataset_repeat_opt]: 2.41998e-06 [pipeline_split]: 1.81998e-06 [optimize]: 0.491592, [53] [py_interpret_to_execute]: 0.00026333 [rewriter_before_opt_a]: 0.00087266 [opt_a]: 0.3433, [2] [Cycle 1]: 0.340855, [45] [expand_dump_flag]: 3.648e-05 [switch_simplify]: 0.00076973 [loop_unroll]: 0.00027798 [a_1]: 0.18859 [with_stream_mark]: 6.496e-05 [recompute_prepare]: 4.853e-05 [updatestate_depend_eliminate]: 2.16e-05 [updatestate_assign_eliminate]: 1.655e-05 [updatestate_loads_eliminate]: 1.925e-05 [parameter_eliminate]: 3.11999e-06 [a_2]: 0.00092279 [accelerated_algorithm]: 8.04e-05 [shard]: 2.94001e-06 [meta_shard_fg_expand]: 2.81e-05 [shard_inline]: 2.737e-05 [merge_send_recv]: 2.351e-05 [auto_parallel]: 2.286e-05 [parallel]: 3.894e-05 [flash_sp]: 1.548e-05 [merge_comm]: 1.712e-05 [allreduce_fusion]: 1.323e-05 [matmul_add_comm_reduction]: 2.36e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 3.115e-05 [virtual_dataset]: 2.347e-05 [get_grad_eliminate_]: 2.279e-05 [virtual_output]: 2.463e-05 [merge_forward]: 1.343e-05 [cell_reuse_recompute_pass]: 3.23e-06 [offload_activation]: 2.484e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.216e-05 [merge_recompute_call_nodes]: 1.50999e-06 [before_grad]: 4.645e-05 [set_forward_comm_id_for_comm_node_pass]: 1.618e-05 [meta_fg_expand]: 2.171e-05 [flash_sp_send_recv_attached]: 6.01e-06 [receive_attached]: 2.65997e-06 [after_resolve]: 3.443e-05 [a_after_grad]: 3.966e-05 [renormalize]: 0.146695 [add_forward_monad_depend]: 1.444e-05 [auto_monad_grad]: 3.51999e-06 [auto_monad_eliminator]: 9.445e-05 [cse]: 0.00191723 [a_3]: 0.00020224 [Cycle 2]: 0.0024245, [45] [expand_dump_flag]: 3.75e-06 [switch_simplify]: 2.938e-05 [loop_unroll]: 2.315e-05 [a_1]: 0.00072638 [with_stream_mark]: 4.368e-05 [recompute_prepare]: 2.65e-05 [updatestate_depend_eliminate]: 1.608e-05 [updatestate_assign_eliminate]: 1.171e-05 [updatestate_loads_eliminate]: 1.395e-05 [parameter_eliminate]: 2.90998e-06 [a_2]: 0.00039639 [accelerated_algorithm]: 3.722e-05 [shard]: 3.10002e-06 [meta_shard_fg_expand]: 9.84001e-06 [shard_inline]: 2.474e-05 [merge_send_recv]: 2.258e-05 [auto_parallel]: 2.145e-05 [parallel]: 1.051e-05 [flash_sp]: 4.80001e-06 [merge_comm]: 1.424e-05 [allreduce_fusion]: 1.245e-05 [matmul_add_comm_reduction]: 2.392e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 2.626e-05 [virtual_dataset]: 2.186e-05 [get_grad_eliminate_]: 2.313e-05 [virtual_output]: 2.154e-05 [merge_forward]: 1.345e-05 [cell_reuse_recompute_pass]: 3.24001e-06 [offload_activation]: 2.712e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.876e-05 [merge_recompute_call_nodes]: 2.14999e-06 [before_grad]: 4.086e-05 [set_forward_comm_id_for_comm_node_pass]: 1.461e-05 [meta_fg_expand]: 1.228e-05 [flash_sp_send_recv_attached]: 2.10002e-06 [receive_attached]: 2.12001e-06 [after_resolve]: 3.246e-05 [a_after_grad]: 3.605e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 3.98999e-06 [auto_monad_grad]: 3.38e-06 [auto_monad_eliminator]: 7.736e-05 [cse]: 9.963e-05 [a_3]: 0.00015425 [py_interpret_to_execute_after_opt_a]: 3.74e-05 [slice_cell_reuse_recomputed_activation]: 2.69001e-06 [rewriter_after_opt_a]: 0.0009036 [convert_after_rewriter]: 2.849e-05 [order_py_execute_after_rewriter]: 1.736e-05 [mutable_eliminate]: 0.00087363 [opt_b]: 0.00085165, [1] [Cycle 1]: 0.00084119, [7] [b_1]: 0.0006066 [b_2]: 2.637e-05 [updatestate_depend_eliminate]: 2.073e-05 [updatestate_assign_eliminate]: 1.266e-05 [updatestate_loads_eliminate]: 1.628e-05 [renormalize]: 1.04e-06 [cse]: 0.00010891 [optimize_parallel_all_gather_comm]: 6.026e-05 [overlap_param_gather]: 2.49999e-06 [cconv]: 4.396e-05 [loop_unroll]: 0.00066532 [opt_after_cconv]: 0.00032352, [1] [Cycle 1]: 0.0003156, [7] [c_1]: 0.00013852 [parameter_eliminate]: 7.16999e-06 [updatestate_depend_eliminate]: 1.99e-05 [updatestate_assign_eliminate]: 1.147e-05 [updatestate_loads_eliminate]: 1.383e-05 [cse]: 8.337e-05 [renormalize]: 5.8001e-07 [remove_dup_value]: 0.00011053 [tuple_transform]: 0.00027849, [1] [Cycle 1]: 0.00027195, [4] [d_1]: 0.00022064 [none_parameter_eliminate]: 3.14999e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 2.614e-05 [partial_unused_args_eliminate]: 2.45997e-06 [add_recomputation]: 0.00034074 [cse_after_recomputation]: 7.785e-05, [1] [Cycle 1]: 7.212e-05, [1] [cse]: 6.251e-05 [environ_conv]: 2.885e-05 [swap_dp_allreduce_reducescatter]: 1.943e-05 [bias_add_comm_swap]: 3.60998e-06 [label_micro_interleaved_index]: 6.83e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.40999e-06 [slice_recompute_activation]: 2.21003e-06 [micro_interleaved_order_control]: 3.01001e-06 [assign_add_opt]: 1.27e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.09999e-06 [reorder_send_recv_between_fp_bp]: 2.74999e-06 [comm_op_add_attrs]: 1.39e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.37e-06 [interleave_parallel_branches]: 1.39e-06 [overlap_opt_shard_in_pipeline]: 1.26002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.39001e-06 [control_data_broadcast_order]: 4.145e-05 [grouped_pairwise_exchange_alltoall]: 1.74998e-06 [offloading_packed_experts]: 1.114e-05 [overlap_recompute_and_grad_model_parallel]: 1.093e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.30001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.28002e-06 [overlap_recompute_comm]: 2.71e-06 [overlap_grad_ring_attention]: 1.001e-05 [overlap_grad_flash_sp]: 5.453e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.71e-06 [split_layernorm_comm]: 1.60001e-06 [handle_group_info]: 1.03001e-06 [symbol_engine_optimizer]: 0.141991, [1] [Cycle 1]: 0.141982, [6] [build]: 0.00030521 [elim_shapecalc]: 3.943e-05 [elim_not_effective]: 0.00010394 [opt_reshape]: 3.764e-05 [fold_const_symbol]: 0.141392 [renormalize]: 1.05999e-06 [detach_backward]: 5.05001e-06 [pipeline_parallel_scheduler]: 2.06003e-06 [auto_monad_reorder]: 9.432e-05 [get_jit_bprop_graph]: 2.54001e-06 [rewriter_after_jit_bprop_graph]: 8.50001e-06 [opt_after_jit_grad]: 0.00089856 [validate]: 0.00023328 Sums bootstrap : 0.000732s : 0.02% type_inference : 2.901320s : 84.55% event_method : 0.000218s : 0.01% auto_monad : 0.037041s : 1.08% graph_reusing : 0.000128s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000214s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000062s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000253s : 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 : 0.000263s : 0.01% optimize.rewriter_before_opt_a : 0.000873s : 0.03% optimize.opt_a.expand_dump_flag : 0.000040s : 0.00% optimize.opt_a.switch_simplify : 0.000799s : 0.02% optimize.opt_a.loop_unroll : 0.000301s : 0.01% optimize.opt_a.a_1 : 0.189317s : 5.52% optimize.opt_a.with_stream_mark : 0.000109s : 0.00% optimize.opt_a.recompute_prepare : 0.000075s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000033s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001319s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000118s : 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 : 0.000044s : 0.00% optimize.opt_a.parallel : 0.000049s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000031s : 0.00% optimize.opt_a.allreduce_fusion : 0.000026s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000048s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000057s : 0.00% optimize.opt_a.virtual_dataset : 0.000045s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000046s : 0.00% optimize.opt_a.merge_forward : 0.000027s : 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 : 0.000101s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000087s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000031s : 0.00% optimize.opt_a.meta_fg_expand : 0.000034s : 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 : 0.000067s : 0.00% optimize.opt_a.a_after_grad : 0.000076s : 0.00% optimize.opt_a.renormalize : 0.146696s : 4.28% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000172s : 0.01% optimize.opt_a.cse : 0.002017s : 0.06% optimize.opt_a.a_3 : 0.000356s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000904s : 0.03% optimize.convert_after_rewriter : 0.000028s : 0.00% optimize.order_py_execute_after_rewriter : 0.000017s : 0.00% optimize.mutable_eliminate : 0.000874s : 0.03% optimize.opt_b.b_1 : 0.000607s : 0.02% optimize.opt_b.b_2 : 0.000026s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000109s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000060s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000665s : 0.02% optimize.opt_after_cconv.c_1 : 0.000139s : 0.00% 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 : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000083s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000111s : 0.00% optimize.tuple_transform.d_1 : 0.000221s : 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 : 0.000002s : 0.00% optimize.add_recomputation : 0.000341s : 0.01% optimize.cse_after_recomputation.cse : 0.000063s : 0.00% optimize.environ_conv : 0.000029s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000041s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 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 : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000055s : 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 : 0.000305s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000039s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000104s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000038s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.141392s : 4.12% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000094s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000899s : 0.03% validate : 0.000233s : 0.01% Time group info: ------[substitution.] 0.003267 569 0.57% : 0.000019s : 8: substitution.depend_value_elim 1.85% : 0.000060s : 14: substitution.elim_not_effective 0.58% : 0.000019s : 12: substitution.float_tuple_getitem_switch 1.81% : 0.000059s : 14: substitution.fold_const_symbol 0.53% : 0.000017s : 17: substitution.graph_param_transform 63.50% : 0.002075s : 71: substitution.inline 0.52% : 0.000017s : 29: substitution.j_node_and_user_rematch 1.30% : 0.000042s : 6: substitution.less_batch_normalization 1.81% : 0.000059s : 2: substitution.list_to_tuple_eliminator_ 0.20% : 0.000007s : 6: substitution.load_eliminater 1.28% : 0.000042s : 21: substitution.minmaximum_grad 0.24% : 0.000008s : 2: substitution.opt_reshape 0.63% : 0.000021s : 29: substitution.remove_not_recompute_node 0.25% : 0.000008s : 4: substitution.replace_old_param 1.57% : 0.000051s : 18: substitution.reshape_eliminate 1.58% : 0.000052s : 24: substitution.switch_simplify 5.00% : 0.000163s : 51: substitution.tuple_list_convert_item_index_to_positive 2.17% : 0.000071s : 51: substitution.tuple_list_get_item_const_eliminator 3.31% : 0.000108s : 51: substitution.tuple_list_get_item_depend_reorder 6.85% : 0.000224s : 73: substitution.tuple_list_get_item_eliminator 2.97% : 0.000097s : 51: substitution.tuple_list_get_set_item_eliminator 0.81% : 0.000026s : 6: substitution.updatestate_pure_node_eliminater 0.67% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.900857 2 93.41% : 2.709731s : 1: type_inference.infer 6.59% : 0.191127s : 1: type_inference.specialize ------[replace.] 0.181237 115 0.03% : 0.000063s : 5: replace.depend_value_elim 99.71% : 0.180716s : 71: replace.inline 0.02% : 0.000041s : 2: replace.list_to_tuple_eliminator_ 0.16% : 0.000297s : 24: replace.switch_simplify 0.07% : 0.000121s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002167 115 0.12% : 0.000003s : 5: match.depend_value_elim 93.62% : 0.002029s : 71: match.inline 2.64% : 0.000057s : 2: match.list_to_tuple_eliminator_ 1.91% : 0.000041s : 24: match.switch_simplify 1.71% : 0.000037s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001701 9701 1.16% : 0.000020s : 123: predicate.accumulaten_eliminater 0.45% : 0.000008s : 17: predicate.ad_related_special_op_eliminate 0.50% : 0.000009s : 58: predicate.addn_check_dump 1.24% : 0.000021s : 123: predicate.addn_zero_filter 1.05% : 0.000018s : 123: predicate.adjust_all_reduce_mul_add 2.31% : 0.000039s : 181: predicate.arithmetic_simplify 1.09% : 0.000019s : 123: predicate.cast_eliminate 0.34% : 0.000006s : 34: predicate.check_bprop_eliminate 0.58% : 0.000010s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.66% : 0.000011s : 61: predicate.depend_value_elim 1.22% : 0.000021s : 123: predicate.dict_get_item_const_eliminator 1.25% : 0.000021s : 123: predicate.dict_get_item_eliminator 1.09% : 0.000019s : 123: predicate.dict_set_item_eliminator 0.39% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.21% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.22% : 0.000021s : 140: predicate.environ_add_const_eliminate 1.22% : 0.000021s : 140: predicate.environ_get_add_eliminate 1.21% : 0.000021s : 140: predicate.environ_get_depend_swap 1.75% : 0.000030s : 198: predicate.environ_get_eliminate 1.19% : 0.000020s : 140: predicate.environ_get_set_eliminate 1.92% : 0.000033s : 209: predicate.exchange_switch_depend_value 2.91% : 0.000050s : 209: predicate.float_depend_g_call 0.51% : 0.000009s : 58: predicate.float_environ_get_switch 0.74% : 0.000013s : 75: predicate.float_tuple_getitem_switch 0.15% : 0.000003s : 17: predicate.fold_const_symbol 0.34% : 0.000006s : 35: predicate.get_grad_eliminate 0.11% : 0.000002s : 17: predicate.graph_param_transform 0.54% : 0.000009s : 58: predicate.incorporate_call 0.48% : 0.000008s : 58: predicate.incorporate_call_switch 6.60% : 0.000112s : 459: predicate.inline 0.51% : 0.000009s : 35: predicate.inline_without_move 0.17% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.54% : 0.000009s : 36: predicate.less_batch_normalization 1.59% : 0.000027s : 172: predicate.list_to_tuple_eliminator_ 2.67% : 0.000045s : 295: predicate.load_eliminater 0.46% : 0.000008s : 17: predicate.loop_unroll_after_grad 3.15% : 0.000054s : 314: predicate.loop_unroll_before_grad 1.58% : 0.000027s : 157: predicate.make_slice_get_slice_eliminator 0.56% : 0.000010s : 58: predicate.merge_addn 0.31% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.32% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.10% : 0.000019s : 123: predicate.minmaximum_grad 0.55% : 0.000009s : 17: predicate.mutable_eliminate 0.21% : 0.000003s : 17: predicate.opt_reshape 0.17% : 0.000003s : 17: predicate.parallel_virtual_node 3.16% : 0.000054s : 209: predicate.partial_defer_inline 1.62% : 0.000028s : 155: predicate.partial_eliminate 1.06% : 0.000018s : 123: predicate.print_const_string_wrapper 0.48% : 0.000008s : 53: predicate.reduce_all_const_elim 1.50% : 0.000025s : 123: predicate.reduce_eliminate 2.54% : 0.000043s : 295: predicate.redundant_stop_gradient_eliminater 0.17% : 0.000003s : 35: predicate.remove_not_recompute_node 1.09% : 0.000019s : 172: predicate.replace_applicator 0.19% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.19% : 0.000020s : 123: predicate.reshape_eliminate 0.32% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.22% : 0.000004s : 17: predicate.row_tensor_eliminate 0.48% : 0.000008s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.38% : 0.000006s : 35: predicate.shard_identity_eliminate 0.33% : 0.000006s : 34: predicate.special_op_eliminate 0.66% : 0.000011s : 58: predicate.specialize_transform 0.42% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.37% : 0.000006s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.13% : 0.000036s : 209: predicate.switch_defer_inline 2.37% : 0.000040s : 243: predicate.switch_layer_defer_inline 6.65% : 0.000113s : 646: predicate.switch_simplify 1.17% : 0.000020s : 123: predicate.tile_eliminate 1.05% : 0.000018s : 123: predicate.transpose_eliminate 1.75% : 0.000030s : 157: predicate.tuple_list_convert_item_index_to_positive 1.91% : 0.000033s : 157: predicate.tuple_list_get_item_const_eliminator 1.71% : 0.000029s : 157: predicate.tuple_list_get_item_depend_reorder 3.16% : 0.000054s : 228: predicate.tuple_list_get_item_eliminator 1.76% : 0.000030s : 157: predicate.tuple_list_get_set_item_eliminator 2.42% : 0.000041s : 215: predicate.tuple_list_set_item_eliminator 1.55% : 0.000026s : 170: predicate.tuple_to_list_eliminator_ 2.63% : 0.000045s : 295: predicate.updatestate_pure_node_eliminater 3.24% : 0.000055s : 353: predicate.updatestate_useless_node_eliminater 0.17% : 0.000003s : 17: predicate.value_based_eliminate 0.36% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.36% : 0.000006s : 35: predicate.virtual_output_eliminate 0.17% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.017719 133 59.84% : 0.010604s : 53: func_graph_cloner_run.FuncGraphClonerGraph 40.16% : 0.007116s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.429470 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.26% : 0.011691s : 1: add_attr 0.26% : 0.011671s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000348s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.84% : 0.037078s : 1: auto_monad 0.00% : 0.000100s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000770s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000045s : 1: control_data_broadcast_order 0.00% : 0.000034s : 1: convert_after_rewriter 0.00% : 0.000081s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000033s : 1: environ_conv 0.01% : 0.000230s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000139s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000008s : 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% : 0.000011s : 1: label_micro_interleaved_index 0.02% : 0.000676s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000889s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000046s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000056s : 1: opt.transform.mutable_eliminate 4.35% : 0.192689s : 95: opt.transform.opt_a 0.00% : 0.000137s : 1: opt.transform.opt_after_cconv 0.00% : 0.000092s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000590s : 28: opt.transform.opt_b 0.01% : 0.000243s : 2: opt.transform.opt_trans_graph 3.20% : 0.141561s : 4: opt.transform.symbol_engine_opt 7.75% : 0.343305s : 1: opt_a 0.01% : 0.000327s : 1: opt_after_cconv 0.02% : 0.000912s : 1: opt_after_jit_grad 0.02% : 0.000857s : 1: opt_b 11.10% : 0.491601s : 1: optimize 0.00% : 0.000065s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000023s : 1: order_py_execute_after_rewriter 0.00% : 0.000058s : 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% : 0.000006s : 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% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000262s : 1: pre_auto_parallel 0.01% : 0.000272s : 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% : 0.000116s : 1: remove_dup_value 3.16% : 0.139847s : 1: renormalize.infer 0.15% : 0.006825s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000919s : 1: rewriter_after_opt_a 0.02% : 0.000885s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 3.21% : 0.141997s : 1: symbol_engine_optimizer 0.01% : 0.000282s : 1: tuple_transform 65.50% : 2.901350s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape0-1024] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape0-1024],max_mem:408.0M [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:40:48.191.760 [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 = 3.93546, [21] [bootstrap]: 0.00084415 [type_inference]: 3.33469 [event_method]: 0.00021073 [auto_monad]: 0.00080995 [graph_reusing]: 4.799e-05 [inline]: 3.23998e-06 [add_attr]: 0.125988, [1] [add_attr_with_inline]: 0.125966, [1] [Cycle 1]: 0.00036119, [2] [tag_attr]: 0.00021872 [meta_addattr_fg_expand]: 6.657e-05 [parallel-infer-symbol]: 4.68001e-06 [pre_auto_parallel]: 0.00027309 [insert-virtual-dataset]: 3.12002e-06 [parallel-infer-symbol-second]: 1.39e-06 [dataset_repeat_opt]: 2.39001e-06 [pipeline_split]: 1.80001e-06 [optimize]: 0.233208, [53] [py_interpret_to_execute]: 0.00027802 [rewriter_before_opt_a]: 0.00088369 [opt_a]: 0.22652, [2] [Cycle 1]: 0.223996, [45] [expand_dump_flag]: 4.016e-05 [switch_simplify]: 0.00089247 [loop_unroll]: 0.00094608 [a_1]: 0.0104241 [with_stream_mark]: 6.25e-05 [recompute_prepare]: 4.525e-05 [updatestate_depend_eliminate]: 2.158e-05 [updatestate_assign_eliminate]: 1.577e-05 [updatestate_loads_eliminate]: 1.976e-05 [parameter_eliminate]: 2.98e-06 [a_2]: 0.00090807 [accelerated_algorithm]: 6.854e-05 [shard]: 2.58e-06 [meta_shard_fg_expand]: 3.01e-05 [shard_inline]: 2.605e-05 [merge_send_recv]: 2.115e-05 [auto_parallel]: 2.204e-05 [parallel]: 3.708e-05 [flash_sp]: 1.56e-05 [merge_comm]: 1.432e-05 [allreduce_fusion]: 1.404e-05 [matmul_add_comm_reduction]: 2.369e-05 [allreduce_slice_to_reducescatter]: 1.29e-06 [virtual_shard_identity]: 3.083e-05 [virtual_dataset]: 2.49e-05 [get_grad_eliminate_]: 2.24e-05 [virtual_output]: 2.217e-05 [merge_forward]: 1.293e-05 [cell_reuse_recompute_pass]: 3.28e-06 [offload_activation]: 2.478e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.065e-05 [merge_recompute_call_nodes]: 2.16e-06 [before_grad]: 4.365e-05 [set_forward_comm_id_for_comm_node_pass]: 1.484e-05 [meta_fg_expand]: 2.174e-05 [flash_sp_send_recv_attached]: 5.97999e-06 [receive_attached]: 2.54999e-06 [after_resolve]: 3.217e-05 [a_after_grad]: 3.954e-05 [renormalize]: 0.207671 [add_forward_monad_depend]: 1.663e-05 [auto_monad_grad]: 3.21001e-06 [auto_monad_eliminator]: 9.818e-05 [cse]: 0.00150594 [a_3]: 0.0002102 [Cycle 2]: 0.00250257, [45] [expand_dump_flag]: 3.63e-06 [switch_simplify]: 2.931e-05 [loop_unroll]: 2.544e-05 [a_1]: 0.00076962 [with_stream_mark]: 4.254e-05 [recompute_prepare]: 2.789e-05 [updatestate_depend_eliminate]: 1.572e-05 [updatestate_assign_eliminate]: 1.352e-05 [updatestate_loads_eliminate]: 1.493e-05 [parameter_eliminate]: 3.03e-06 [a_2]: 0.00038372 [accelerated_algorithm]: 3.679e-05 [shard]: 2.68e-06 [meta_shard_fg_expand]: 1.12e-05 [shard_inline]: 2.464e-05 [merge_send_recv]: 2.324e-05 [auto_parallel]: 2.115e-05 [parallel]: 1.086e-05 [flash_sp]: 5.94e-06 [merge_comm]: 1.492e-05 [allreduce_fusion]: 1.363e-05 [matmul_add_comm_reduction]: 2.588e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 2.655e-05 [virtual_dataset]: 2.305e-05 [get_grad_eliminate_]: 2.38e-05 [virtual_output]: 2.236e-05 [merge_forward]: 1.479e-05 [cell_reuse_recompute_pass]: 4e-06 [offload_activation]: 2.778e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.066e-05 [merge_recompute_call_nodes]: 2.07001e-06 [before_grad]: 4.389e-05 [set_forward_comm_id_for_comm_node_pass]: 1.457e-05 [meta_fg_expand]: 1.298e-05 [flash_sp_send_recv_attached]: 2.58e-06 [receive_attached]: 2.74001e-06 [after_resolve]: 3.237e-05 [a_after_grad]: 3.795e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 4.80999e-06 [auto_monad_grad]: 2.69999e-06 [auto_monad_eliminator]: 7.977e-05 [cse]: 9.815e-05 [a_3]: 0.00016743 [py_interpret_to_execute_after_opt_a]: 4.671e-05 [slice_cell_reuse_recomputed_activation]: 2.76999e-06 [rewriter_after_opt_a]: 0.00090979 [convert_after_rewriter]: 2.913e-05 [order_py_execute_after_rewriter]: 1.491e-05 [mutable_eliminate]: 0.00086569 [opt_b]: 0.00086257, [1] [Cycle 1]: 0.00085195, [7] [b_1]: 0.00059855 [b_2]: 4.218e-05 [updatestate_depend_eliminate]: 2.249e-05 [updatestate_assign_eliminate]: 1.242e-05 [updatestate_loads_eliminate]: 1.52e-05 [renormalize]: 9.89996e-07 [cse]: 0.00011276 [optimize_parallel_all_gather_comm]: 4.428e-05 [overlap_param_gather]: 7.88001e-06 [cconv]: 4.686e-05 [loop_unroll]: 0.00062819 [opt_after_cconv]: 0.00032115, [1] [Cycle 1]: 0.00031059, [7] [c_1]: 0.00013592 [parameter_eliminate]: 6.21998e-06 [updatestate_depend_eliminate]: 1.938e-05 [updatestate_assign_eliminate]: 1.112e-05 [updatestate_loads_eliminate]: 1.483e-05 [cse]: 8.191e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 0.00010899 [tuple_transform]: 0.00027791, [1] [Cycle 1]: 0.00027208, [4] [d_1]: 0.00022226 [none_parameter_eliminate]: 2.29001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 2.382e-05 [partial_unused_args_eliminate]: 1.99999e-06 [add_recomputation]: 0.00016315 [cse_after_recomputation]: 7.474e-05, [1] [Cycle 1]: 6.764e-05, [1] [cse]: 6.003e-05 [environ_conv]: 2.77e-05 [swap_dp_allreduce_reducescatter]: 2.008e-05 [bias_add_comm_swap]: 3.09999e-06 [label_micro_interleaved_index]: 6.26e-06 [label_fine_grained_interleaved_index]: 3.01001e-06 [merge_cast_opt]: 1.46002e-06 [slice_recompute_activation]: 2.28998e-06 [micro_interleaved_order_control]: 2.17999e-06 [assign_add_opt]: 1.55001e-06 [ForceFp32Comm]: 1.15999e-06 [remove_cast_before_assign_add]: 1.10999e-06 [full_micro_interleaved_order_control]: 2.27999e-06 [reorder_send_recv_between_fp_bp]: 3.01001e-06 [comm_op_add_attrs]: 1.01997e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.32999e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 6.11998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.89e-06 [control_data_broadcast_order]: 4.155e-05 [grouped_pairwise_exchange_alltoall]: 1.78002e-06 [offloading_packed_experts]: 1.328e-05 [overlap_recompute_and_grad_model_parallel]: 1.171e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.25999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.41e-06 [overlap_grad_ring_attention]: 1.027e-05 [overlap_grad_flash_sp]: 5.476e-05 [begin_end_overlap_inline]: 7.40023e-07 [split_matmul_comm_elemetwise]: 2.56998e-06 [split_layernorm_comm]: 2.04999e-06 [handle_group_info]: 1.15999e-06 [symbol_engine_optimizer]: 0.00056424, [1] [Cycle 1]: 0.00055718, [6] [build]: 0.00030589 [elim_shapecalc]: 4.107e-05 [elim_not_effective]: 5.883e-05 [opt_reshape]: 3.713e-05 [fold_const_symbol]: 6.309e-05 [renormalize]: 2.29978e-07 [detach_backward]: 3.29001e-06 [pipeline_parallel_scheduler]: 1.70001e-06 [auto_monad_reorder]: 6.972e-05 [get_jit_bprop_graph]: 2.37999e-06 [rewriter_after_jit_bprop_graph]: 7.48999e-06 [opt_after_jit_grad]: 0.00082158 [validate]: 0.238185 Sums bootstrap : 0.000844s : 0.02% type_inference : 3.334690s : 87.57% event_method : 0.000211s : 0.01% auto_monad : 0.000810s : 0.02% graph_reusing : 0.000048s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000219s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000067s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000273s : 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 : 0.000278s : 0.01% optimize.rewriter_before_opt_a : 0.000884s : 0.02% optimize.opt_a.expand_dump_flag : 0.000044s : 0.00% optimize.opt_a.switch_simplify : 0.000922s : 0.02% optimize.opt_a.loop_unroll : 0.000972s : 0.03% optimize.opt_a.a_1 : 0.011194s : 0.29% optimize.opt_a.with_stream_mark : 0.000105s : 0.00% optimize.opt_a.recompute_prepare : 0.000073s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000029s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000035s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001292s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000105s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000041s : 0.00% optimize.opt_a.shard_inline : 0.000051s : 0.00% optimize.opt_a.merge_send_recv : 0.000044s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000029s : 0.00% optimize.opt_a.allreduce_fusion : 0.000028s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000050s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000057s : 0.00% optimize.opt_a.virtual_dataset : 0.000048s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000045s : 0.00% optimize.opt_a.merge_forward : 0.000028s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000053s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000101s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000088s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000035s : 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 : 0.000065s : 0.00% optimize.opt_a.a_after_grad : 0.000077s : 0.00% optimize.opt_a.renormalize : 0.207671s : 5.45% 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 : 0.000178s : 0.00% optimize.opt_a.cse : 0.001604s : 0.04% optimize.opt_a.a_3 : 0.000378s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000047s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000910s : 0.02% optimize.convert_after_rewriter : 0.000029s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000866s : 0.02% optimize.opt_b.b_1 : 0.000599s : 0.02% optimize.opt_b.b_2 : 0.000042s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 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 : 0.000113s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000044s : 0.00% optimize.overlap_param_gather : 0.000008s : 0.00% optimize.cconv : 0.000047s : 0.00% optimize.loop_unroll : 0.000628s : 0.02% optimize.opt_after_cconv.c_1 : 0.000136s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.cse : 0.000082s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000109s : 0.00% optimize.tuple_transform.d_1 : 0.000222s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000163s : 0.00% optimize.cse_after_recomputation.cse : 0.000060s : 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 : 0.000006s : 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 : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000006s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000042s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000055s : 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 : 0.000306s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000059s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000037s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 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 : 0.000070s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000822s : 0.02% validate : 0.238185s : 6.25% Time group info: ------[substitution.] 0.003931 569 0.48% : 0.000019s : 8: substitution.depend_value_elim 0.45% : 0.000018s : 14: substitution.elim_not_effective 0.48% : 0.000019s : 12: substitution.float_tuple_getitem_switch 0.73% : 0.000029s : 14: substitution.fold_const_symbol 0.44% : 0.000017s : 17: substitution.graph_param_transform 67.80% : 0.002665s : 71: substitution.inline 0.39% : 0.000015s : 29: substitution.j_node_and_user_rematch 0.94% : 0.000037s : 6: substitution.less_batch_normalization 1.72% : 0.000068s : 2: substitution.list_to_tuple_eliminator_ 0.16% : 0.000006s : 6: substitution.load_eliminater 0.85% : 0.000033s : 21: substitution.minmaximum_grad 0.25% : 0.000010s : 2: substitution.opt_reshape 0.54% : 0.000021s : 29: substitution.remove_not_recompute_node 0.22% : 0.000009s : 4: substitution.replace_old_param 1.92% : 0.000075s : 18: substitution.reshape_eliminate 1.28% : 0.000050s : 24: substitution.switch_simplify 4.57% : 0.000180s : 51: substitution.tuple_list_convert_item_index_to_positive 2.53% : 0.000099s : 51: substitution.tuple_list_get_item_const_eliminator 3.41% : 0.000134s : 51: substitution.tuple_list_get_item_depend_reorder 6.29% : 0.000247s : 73: substitution.tuple_list_get_item_eliminator 3.31% : 0.000130s : 51: substitution.tuple_list_get_set_item_eliminator 0.66% : 0.000026s : 6: substitution.updatestate_pure_node_eliminater 0.58% : 0.000023s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.334288 2 89.39% : 2.980568s : 1: type_inference.infer 10.61% : 0.353720s : 1: type_inference.specialize ------[replace.] 0.001319 115 6.29% : 0.000083s : 5: replace.depend_value_elim 54.80% : 0.000723s : 71: replace.inline 4.35% : 0.000057s : 2: replace.list_to_tuple_eliminator_ 25.32% : 0.000334s : 24: replace.switch_simplify 9.24% : 0.000122s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002766 115 0.10% : 0.000003s : 5: match.depend_value_elim 94.68% : 0.002619s : 71: match.inline 2.33% : 0.000065s : 2: match.list_to_tuple_eliminator_ 1.39% : 0.000038s : 24: match.switch_simplify 1.50% : 0.000042s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001956 9701 1.04% : 0.000020s : 123: predicate.accumulaten_eliminater 0.36% : 0.000007s : 17: predicate.ad_related_special_op_eliminate 0.44% : 0.000009s : 58: predicate.addn_check_dump 1.01% : 0.000020s : 123: predicate.addn_zero_filter 0.94% : 0.000018s : 123: predicate.adjust_all_reduce_mul_add 2.03% : 0.000040s : 181: predicate.arithmetic_simplify 1.01% : 0.000020s : 123: predicate.cast_eliminate 0.31% : 0.000006s : 34: predicate.check_bprop_eliminate 0.44% : 0.000009s : 58: predicate.compare_switch_simplify 0.07% : 0.000001s : 17: predicate.const_output_eliminate 0.56% : 0.000011s : 61: predicate.depend_value_elim 1.13% : 0.000022s : 123: predicate.dict_get_item_const_eliminator 1.14% : 0.000022s : 123: predicate.dict_get_item_eliminator 0.96% : 0.000019s : 123: predicate.dict_set_item_eliminator 0.40% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 17: predicate.elim_not_effective 0.19% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.06% : 0.000021s : 140: predicate.environ_add_const_eliminate 1.07% : 0.000021s : 140: predicate.environ_get_add_eliminate 1.05% : 0.000021s : 140: predicate.environ_get_depend_swap 1.56% : 0.000031s : 198: predicate.environ_get_eliminate 1.06% : 0.000021s : 140: predicate.environ_get_set_eliminate 1.68% : 0.000033s : 209: predicate.exchange_switch_depend_value 2.80% : 0.000055s : 209: predicate.float_depend_g_call 0.46% : 0.000009s : 58: predicate.float_environ_get_switch 0.61% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.07% : 0.000001s : 17: predicate.fold_const_symbol 0.34% : 0.000007s : 35: predicate.get_grad_eliminate 0.09% : 0.000002s : 17: predicate.graph_param_transform 0.47% : 0.000009s : 58: predicate.incorporate_call 0.44% : 0.000009s : 58: predicate.incorporate_call_switch 5.80% : 0.000113s : 459: predicate.inline 0.44% : 0.000009s : 35: predicate.inline_without_move 0.14% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.41% : 0.000008s : 36: predicate.less_batch_normalization 1.54% : 0.000030s : 172: predicate.list_to_tuple_eliminator_ 2.39% : 0.000047s : 295: predicate.load_eliminater 0.39% : 0.000008s : 17: predicate.loop_unroll_after_grad 4.19% : 0.000082s : 314: predicate.loop_unroll_before_grad 1.37% : 0.000027s : 157: predicate.make_slice_get_slice_eliminator 0.48% : 0.000009s : 58: predicate.merge_addn 0.28% : 0.000006s : 34: predicate.micro_step_allgather_replace 0.29% : 0.000006s : 34: predicate.mini_step_allgather_replace 0.98% : 0.000019s : 123: predicate.minmaximum_grad 0.41% : 0.000008s : 17: predicate.mutable_eliminate 0.17% : 0.000003s : 17: predicate.opt_reshape 0.16% : 0.000003s : 17: predicate.parallel_virtual_node 3.11% : 0.000061s : 209: predicate.partial_defer_inline 1.40% : 0.000027s : 155: predicate.partial_eliminate 1.06% : 0.000021s : 123: predicate.print_const_string_wrapper 0.44% : 0.000009s : 53: predicate.reduce_all_const_elim 1.42% : 0.000028s : 123: predicate.reduce_eliminate 5.90% : 0.000115s : 295: predicate.redundant_stop_gradient_eliminater 0.15% : 0.000003s : 35: predicate.remove_not_recompute_node 0.98% : 0.000019s : 172: predicate.replace_applicator 0.16% : 0.000003s : 35: predicate.replace_old_param 0.09% : 0.000002s : 17: predicate.reset_defer_inline 1.17% : 0.000023s : 123: predicate.reshape_eliminate 0.29% : 0.000006s : 34: predicate.row_tensor_add_zeros_like 0.18% : 0.000003s : 17: predicate.row_tensor_eliminate 0.51% : 0.000010s : 34: predicate.same_eliminate 0.19% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.37% : 0.000007s : 35: predicate.shard_identity_eliminate 0.30% : 0.000006s : 34: predicate.special_op_eliminate 0.59% : 0.000012s : 58: predicate.specialize_transform 0.39% : 0.000008s : 34: predicate.split_environ_get_set_with_tuple_value 0.35% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.16% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.89% : 0.000037s : 209: predicate.switch_defer_inline 2.06% : 0.000040s : 243: predicate.switch_layer_defer_inline 6.18% : 0.000121s : 646: predicate.switch_simplify 1.05% : 0.000021s : 123: predicate.tile_eliminate 0.98% : 0.000019s : 123: predicate.transpose_eliminate 1.52% : 0.000030s : 157: predicate.tuple_list_convert_item_index_to_positive 1.59% : 0.000031s : 157: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000032s : 157: predicate.tuple_list_get_item_depend_reorder 6.26% : 0.000122s : 228: predicate.tuple_list_get_item_eliminator 1.64% : 0.000032s : 157: predicate.tuple_list_get_set_item_eliminator 2.06% : 0.000040s : 215: predicate.tuple_list_set_item_eliminator 1.42% : 0.000028s : 170: predicate.tuple_to_list_eliminator_ 4.15% : 0.000081s : 295: predicate.updatestate_pure_node_eliminater 2.90% : 0.000057s : 353: predicate.updatestate_useless_node_eliminater 0.16% : 0.000003s : 17: predicate.value_based_eliminate 0.31% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.30% : 0.000006s : 35: predicate.virtual_output_eliminate 0.14% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.18% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.016056 133 60.13% : 0.009654s : 53: func_graph_cloner_run.FuncGraphClonerGraph 39.87% : 0.006402s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.280615 209 0.00% : 0.000004s : 1: ForceFp32Comm 2.94% : 0.125996s : 1: add_attr 2.94% : 0.125971s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.00% : 0.000169s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000827s : 1: auto_monad 0.00% : 0.000075s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000884s : 1: bootstrap 0.00% : 0.000051s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000046s : 1: control_data_broadcast_order 0.00% : 0.000035s : 1: convert_after_rewriter 0.00% : 0.000078s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.01% : 0.000223s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000055s : 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 0.01% : 0.000639s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000877s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000041s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000051s : 1: opt.transform.mutable_eliminate 0.36% : 0.015338s : 95: opt.transform.opt_a 0.00% : 0.000134s : 1: opt.transform.opt_after_cconv 0.00% : 0.000086s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000600s : 28: opt.transform.opt_b 0.01% : 0.000243s : 2: opt.transform.opt_trans_graph 0.00% : 0.000193s : 4: opt.transform.symbol_engine_opt 5.29% : 0.226526s : 1: opt_a 0.01% : 0.000325s : 1: opt_after_cconv 0.02% : 0.000834s : 1: opt_after_jit_grad 0.02% : 0.000867s : 1: opt_b 5.45% : 0.233215s : 1: optimize 0.00% : 0.000048s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000059s : 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% : 0.000009s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000013s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000281s : 1: pre_auto_parallel 0.01% : 0.000287s : 1: py_interpret_to_execute 0.00% : 0.000053s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000114s : 1: remove_dup_value 4.72% : 0.201956s : 1: renormalize.infer 0.13% : 0.005691s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000925s : 1: rewriter_after_opt_a 0.02% : 0.000897s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000569s : 1: symbol_engine_optimizer 0.01% : 0.000282s : 1: tuple_transform 77.90% : 3.334725s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape1-256] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape1-256],max_mem:408.0M [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:41:50.810.758 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.40292, [21] [bootstrap]: 0.00136532 [type_inference]: 2.08465 [event_method]: 0.00021712 [auto_monad]: 0.00080229 [graph_reusing]: 8.673e-05 [inline]: 4.73001e-06 [add_attr]: 0.00540574, [1] [add_attr_with_inline]: 0.00537688, [1] [Cycle 1]: 0.00032935, [2] [tag_attr]: 0.000218 [meta_addattr_fg_expand]: 6.192e-05 [parallel-infer-symbol]: 3.75e-06 [pre_auto_parallel]: 0.00026287 [insert-virtual-dataset]: 2.82002e-06 [parallel-infer-symbol-second]: 1.27e-06 [dataset_repeat_opt]: 1.97999e-06 [pipeline_split]: 1.65001e-06 [optimize]: 0.308704, [53] [py_interpret_to_execute]: 0.00026373 [rewriter_before_opt_a]: 0.00090773 [opt_a]: 0.301687, [2] [Cycle 1]: 0.299401, [45] [expand_dump_flag]: 2.151e-05 [switch_simplify]: 0.00084269 [loop_unroll]: 0.00037492 [a_1]: 0.110924 [with_stream_mark]: 6.255e-05 [recompute_prepare]: 4.426e-05 [updatestate_depend_eliminate]: 2.147e-05 [updatestate_assign_eliminate]: 1.957e-05 [updatestate_loads_eliminate]: 2.091e-05 [parameter_eliminate]: 2.68003e-06 [a_2]: 0.00087641 [accelerated_algorithm]: 6.507e-05 [shard]: 2.16e-06 [meta_shard_fg_expand]: 2.968e-05 [shard_inline]: 2.454e-05 [merge_send_recv]: 2.074e-05 [auto_parallel]: 2.265e-05 [parallel]: 3.492e-05 [flash_sp]: 1.512e-05 [merge_comm]: 1.432e-05 [allreduce_fusion]: 1.324e-05 [matmul_add_comm_reduction]: 2.344e-05 [allreduce_slice_to_reducescatter]: 8.40024e-07 [virtual_shard_identity]: 3.139e-05 [virtual_dataset]: 2.783e-05 [get_grad_eliminate_]: 2.467e-05 [virtual_output]: 2.434e-05 [merge_forward]: 1.306e-05 [cell_reuse_recompute_pass]: 1.96998e-06 [offload_activation]: 2.363e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.039e-05 [merge_recompute_call_nodes]: 1.51998e-06 [before_grad]: 4.54e-05 [set_forward_comm_id_for_comm_node_pass]: 1.51e-05 [meta_fg_expand]: 2.292e-05 [flash_sp_send_recv_attached]: 5.20999e-06 [receive_attached]: 2.71999e-06 [after_resolve]: 3.208e-05 [a_after_grad]: 3.915e-05 [renormalize]: 0.0461619 [add_forward_monad_depend]: 1.37e-05 [auto_monad_grad]: 4.32e-06 [auto_monad_eliminator]: 9.18e-05 [cse]: 0.138614 [a_3]: 0.00019527 [Cycle 2]: 0.00226884, [45] [expand_dump_flag]: 3.91001e-06 [switch_simplify]: 2.798e-05 [loop_unroll]: 2.418e-05 [a_1]: 0.0007018 [with_stream_mark]: 4.048e-05 [recompute_prepare]: 2.358e-05 [updatestate_depend_eliminate]: 1.594e-05 [updatestate_assign_eliminate]: 1.153e-05 [updatestate_loads_eliminate]: 1.439e-05 [parameter_eliminate]: 2.74001e-06 [a_2]: 0.00033577 [accelerated_algorithm]: 3.07e-05 [shard]: 2.59001e-06 [meta_shard_fg_expand]: 8.89998e-06 [shard_inline]: 2.25e-05 [merge_send_recv]: 1.921e-05 [auto_parallel]: 2.009e-05 [parallel]: 9.48002e-06 [flash_sp]: 4.52e-06 [merge_comm]: 1.345e-05 [allreduce_fusion]: 1.257e-05 [matmul_add_comm_reduction]: 2.31e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 2.424e-05 [virtual_dataset]: 2.194e-05 [get_grad_eliminate_]: 2.181e-05 [virtual_output]: 3.83e-05 [merge_forward]: 1.315e-05 [cell_reuse_recompute_pass]: 2.93e-06 [offload_activation]: 2.528e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.637e-05 [merge_recompute_call_nodes]: 1.77001e-06 [before_grad]: 4.35e-05 [set_forward_comm_id_for_comm_node_pass]: 1.406e-05 [meta_fg_expand]: 1.188e-05 [flash_sp_send_recv_attached]: 2.51e-06 [receive_attached]: 2.71999e-06 [after_resolve]: 2.901e-05 [a_after_grad]: 3.498e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.71001e-06 [auto_monad_grad]: 2.94999e-06 [auto_monad_eliminator]: 7.128e-05 [cse]: 7.837e-05 [a_3]: 0.00016431 [py_interpret_to_execute_after_opt_a]: 3.544e-05 [slice_cell_reuse_recomputed_activation]: 2.49999e-06 [rewriter_after_opt_a]: 0.00087833 [convert_after_rewriter]: 2.733e-05 [order_py_execute_after_rewriter]: 1.524e-05 [mutable_eliminate]: 0.00085846 [opt_b]: 0.00087473, [1] [Cycle 1]: 0.0008644, [7] [b_1]: 0.00063343 [b_2]: 3.09e-05 [updatestate_depend_eliminate]: 2.097e-05 [updatestate_assign_eliminate]: 1.257e-05 [updatestate_loads_eliminate]: 1.4e-05 [renormalize]: 1.42999e-06 [cse]: 9.953e-05 [optimize_parallel_all_gather_comm]: 4.914e-05 [overlap_param_gather]: 2.72001e-06 [cconv]: 4.547e-05 [loop_unroll]: 0.00072542 [opt_after_cconv]: 0.00035028, [1] [Cycle 1]: 0.00034116, [7] [c_1]: 0.00014617 [parameter_eliminate]: 5.89999e-06 [updatestate_depend_eliminate]: 2.158e-05 [updatestate_assign_eliminate]: 1.208e-05 [updatestate_loads_eliminate]: 1.376e-05 [cse]: 9.027e-05 [renormalize]: 9.5999e-07 [remove_dup_value]: 0.00012367 [tuple_transform]: 0.00032717, [1] [Cycle 1]: 0.00031911, [4] [d_1]: 0.00025212 [none_parameter_eliminate]: 3.35e-06 [renormalize]: 5.19998e-07 [switch_simplify]: 3.038e-05 [partial_unused_args_eliminate]: 3.68999e-06 [add_recomputation]: 0.000188 [cse_after_recomputation]: 9.498e-05, [1] [Cycle 1]: 8.674e-05, [1] [cse]: 7.521e-05 [environ_conv]: 3.02e-05 [swap_dp_allreduce_reducescatter]: 2.452e-05 [bias_add_comm_swap]: 3.25e-06 [label_micro_interleaved_index]: 7.45998e-06 [label_fine_grained_interleaved_index]: 3.13e-06 [merge_cast_opt]: 1.69e-06 [slice_recompute_activation]: 2.57001e-06 [micro_interleaved_order_control]: 2.83e-06 [assign_add_opt]: 1.67001e-06 [ForceFp32Comm]: 1.19e-06 [remove_cast_before_assign_add]: 1.46998e-06 [full_micro_interleaved_order_control]: 2.53e-06 [reorder_send_recv_between_fp_bp]: 3.11999e-06 [comm_op_add_attrs]: 1.30999e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.25999e-06 [interleave_parallel_branches]: 1.16002e-06 [overlap_opt_shard_in_pipeline]: 1.54e-06 [overlap_opt_shard_grad_in_pipeline]: 2.49001e-06 [control_data_broadcast_order]: 4.522e-05 [grouped_pairwise_exchange_alltoall]: 1.64e-06 [offloading_packed_experts]: 1.35e-05 [overlap_recompute_and_grad_model_parallel]: 1.181e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.27999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.75001e-06 [overlap_recompute_comm]: 2.59001e-06 [overlap_grad_ring_attention]: 1.023e-05 [overlap_grad_flash_sp]: 6.239e-05 [begin_end_overlap_inline]: 6.39993e-07 [split_matmul_comm_elemetwise]: 2.41e-06 [split_layernorm_comm]: 1.74e-06 [handle_group_info]: 1.09003e-06 [symbol_engine_optimizer]: 0.00064334, [1] [Cycle 1]: 0.00063472, [6] [build]: 0.00033749 [elim_shapecalc]: 4.883e-05 [elim_not_effective]: 6.302e-05 [opt_reshape]: 4.206e-05 [fold_const_symbol]: 7.133e-05 [renormalize]: 1.00001e-06 [detach_backward]: 3.18e-06 [pipeline_parallel_scheduler]: 2.07999e-06 [auto_monad_reorder]: 7.641e-05 [get_jit_bprop_graph]: 2.33002e-06 [rewriter_after_jit_bprop_graph]: 8.85001e-06 [opt_after_jit_grad]: 0.00093687 [validate]: 0.0001434 Sums bootstrap : 0.001365s : 0.06% type_inference : 2.084646s : 87.00% event_method : 0.000217s : 0.01% auto_monad : 0.000802s : 0.03% graph_reusing : 0.000087s : 0.00% inline : 0.000005s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000218s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000062s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000263s : 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 : 0.000264s : 0.01% optimize.rewriter_before_opt_a : 0.000908s : 0.04% optimize.opt_a.expand_dump_flag : 0.000025s : 0.00% optimize.opt_a.switch_simplify : 0.000871s : 0.04% optimize.opt_a.loop_unroll : 0.000399s : 0.02% optimize.opt_a.a_1 : 0.111626s : 4.66% optimize.opt_a.with_stream_mark : 0.000103s : 0.00% optimize.opt_a.recompute_prepare : 0.000068s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000031s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000035s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001212s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000096s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000039s : 0.00% optimize.opt_a.shard_inline : 0.000047s : 0.00% optimize.opt_a.merge_send_recv : 0.000040s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000044s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000028s : 0.00% optimize.opt_a.allreduce_fusion : 0.000026s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000047s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000056s : 0.00% optimize.opt_a.virtual_dataset : 0.000050s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000063s : 0.00% optimize.opt_a.merge_forward : 0.000026s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000049s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000097s : 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 : 0.000029s : 0.00% optimize.opt_a.meta_fg_expand : 0.000035s : 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 : 0.000061s : 0.00% optimize.opt_a.a_after_grad : 0.000074s : 0.00% optimize.opt_a.renormalize : 0.046162s : 1.93% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000163s : 0.01% optimize.opt_a.cse : 0.138693s : 5.79% optimize.opt_a.a_3 : 0.000360s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000035s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000878s : 0.04% optimize.convert_after_rewriter : 0.000027s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000858s : 0.04% optimize.opt_b.b_1 : 0.000633s : 0.03% optimize.opt_b.b_2 : 0.000031s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000100s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000049s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000725s : 0.03% optimize.opt_after_cconv.c_1 : 0.000146s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000090s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000124s : 0.01% optimize.tuple_transform.d_1 : 0.000252s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000030s : 0.00% optimize.partial_unused_args_eliminate : 0.000004s : 0.00% optimize.add_recomputation : 0.000188s : 0.01% optimize.cse_after_recomputation.cse : 0.000075s : 0.00% optimize.environ_conv : 0.000030s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000025s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 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 : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000062s : 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 : 0.000337s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000049s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000063s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000042s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000071s : 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 : 0.000076s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000937s : 0.04% validate : 0.000143s : 0.01% Time group info: ------[substitution.] 0.004147 569 0.43% : 0.000018s : 8: substitution.depend_value_elim 0.42% : 0.000017s : 14: substitution.elim_not_effective 0.43% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.77% : 0.000032s : 14: substitution.fold_const_symbol 0.44% : 0.000018s : 17: substitution.graph_param_transform 69.95% : 0.002901s : 71: substitution.inline 0.38% : 0.000016s : 29: substitution.j_node_and_user_rematch 0.83% : 0.000035s : 6: substitution.less_batch_normalization 1.57% : 0.000065s : 2: substitution.list_to_tuple_eliminator_ 0.17% : 0.000007s : 6: substitution.load_eliminater 0.94% : 0.000039s : 21: substitution.minmaximum_grad 0.25% : 0.000010s : 2: substitution.opt_reshape 0.53% : 0.000022s : 29: substitution.remove_not_recompute_node 0.20% : 0.000008s : 4: substitution.replace_old_param 1.77% : 0.000073s : 18: substitution.reshape_eliminate 1.30% : 0.000054s : 24: substitution.switch_simplify 4.25% : 0.000176s : 51: substitution.tuple_list_convert_item_index_to_positive 2.37% : 0.000098s : 51: substitution.tuple_list_get_item_const_eliminator 3.04% : 0.000126s : 51: substitution.tuple_list_get_item_depend_reorder 5.75% : 0.000238s : 73: substitution.tuple_list_get_item_eliminator 3.01% : 0.000125s : 51: substitution.tuple_list_get_set_item_eliminator 0.68% : 0.000028s : 6: substitution.updatestate_pure_node_eliminater 0.53% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 2.084181 2 91.42% : 1.905279s : 1: type_inference.infer 8.58% : 0.178901s : 1: type_inference.specialize ------[replace.] 0.001228 115 3.90% : 0.000048s : 5: replace.depend_value_elim 58.13% : 0.000714s : 71: replace.inline 3.82% : 0.000047s : 2: replace.list_to_tuple_eliminator_ 24.22% : 0.000298s : 24: replace.switch_simplify 9.93% : 0.000122s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002998 115 0.08% : 0.000002s : 5: match.depend_value_elim 95.17% : 0.002854s : 71: match.inline 2.09% : 0.000063s : 2: match.list_to_tuple_eliminator_ 1.30% : 0.000039s : 24: match.switch_simplify 1.36% : 0.000041s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001782 9701 1.19% : 0.000021s : 123: predicate.accumulaten_eliminater 0.54% : 0.000010s : 17: predicate.ad_related_special_op_eliminate 0.47% : 0.000008s : 58: predicate.addn_check_dump 1.12% : 0.000020s : 123: predicate.addn_zero_filter 1.06% : 0.000019s : 123: predicate.adjust_all_reduce_mul_add 2.34% : 0.000042s : 181: predicate.arithmetic_simplify 1.17% : 0.000021s : 123: predicate.cast_eliminate 0.33% : 0.000006s : 34: predicate.check_bprop_eliminate 0.47% : 0.000008s : 58: predicate.compare_switch_simplify 0.09% : 0.000002s : 17: predicate.const_output_eliminate 0.57% : 0.000010s : 61: predicate.depend_value_elim 1.17% : 0.000021s : 123: predicate.dict_get_item_const_eliminator 1.26% : 0.000022s : 123: predicate.dict_get_item_eliminator 1.31% : 0.000023s : 123: predicate.dict_set_item_eliminator 0.46% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.21% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.26% : 0.000022s : 140: predicate.environ_add_const_eliminate 1.20% : 0.000021s : 140: predicate.environ_get_add_eliminate 1.22% : 0.000022s : 140: predicate.environ_get_depend_swap 1.70% : 0.000030s : 198: predicate.environ_get_eliminate 1.21% : 0.000022s : 140: predicate.environ_get_set_eliminate 2.29% : 0.000041s : 209: predicate.exchange_switch_depend_value 2.87% : 0.000051s : 209: predicate.float_depend_g_call 0.47% : 0.000008s : 58: predicate.float_environ_get_switch 0.68% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.36% : 0.000006s : 35: predicate.get_grad_eliminate 0.11% : 0.000002s : 17: predicate.graph_param_transform 0.51% : 0.000009s : 58: predicate.incorporate_call 0.47% : 0.000008s : 58: predicate.incorporate_call_switch 6.32% : 0.000113s : 459: predicate.inline 0.43% : 0.000008s : 35: predicate.inline_without_move 0.15% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.40% : 0.000007s : 36: predicate.less_batch_normalization 1.65% : 0.000029s : 172: predicate.list_to_tuple_eliminator_ 2.58% : 0.000046s : 295: predicate.load_eliminater 0.39% : 0.000007s : 17: predicate.loop_unroll_after_grad 3.38% : 0.000060s : 314: predicate.loop_unroll_before_grad 1.45% : 0.000026s : 157: predicate.make_slice_get_slice_eliminator 0.48% : 0.000008s : 58: predicate.merge_addn 0.30% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.33% : 0.000006s : 34: predicate.mini_step_allgather_replace 1.08% : 0.000019s : 123: predicate.minmaximum_grad 0.43% : 0.000008s : 17: predicate.mutable_eliminate 0.20% : 0.000004s : 17: predicate.opt_reshape 0.19% : 0.000003s : 17: predicate.parallel_virtual_node 3.30% : 0.000059s : 209: predicate.partial_defer_inline 1.56% : 0.000028s : 155: predicate.partial_eliminate 1.10% : 0.000020s : 123: predicate.print_const_string_wrapper 0.45% : 0.000008s : 53: predicate.reduce_all_const_elim 1.50% : 0.000027s : 123: predicate.reduce_eliminate 2.68% : 0.000048s : 295: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 35: predicate.remove_not_recompute_node 1.06% : 0.000019s : 172: predicate.replace_applicator 0.18% : 0.000003s : 35: predicate.replace_old_param 0.10% : 0.000002s : 17: predicate.reset_defer_inline 1.24% : 0.000022s : 123: predicate.reshape_eliminate 0.30% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.23% : 0.000004s : 17: predicate.row_tensor_eliminate 0.48% : 0.000009s : 34: predicate.same_eliminate 0.23% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.36% : 0.000006s : 35: predicate.shard_identity_eliminate 0.42% : 0.000007s : 34: predicate.special_op_eliminate 0.63% : 0.000011s : 58: predicate.specialize_transform 0.40% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.37% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.05% : 0.000036s : 209: predicate.switch_defer_inline 2.30% : 0.000041s : 243: predicate.switch_layer_defer_inline 6.58% : 0.000117s : 646: predicate.switch_simplify 1.15% : 0.000021s : 123: predicate.tile_eliminate 1.11% : 0.000020s : 123: predicate.transpose_eliminate 1.74% : 0.000031s : 157: predicate.tuple_list_convert_item_index_to_positive 1.98% : 0.000035s : 157: predicate.tuple_list_get_item_const_eliminator 1.70% : 0.000030s : 157: predicate.tuple_list_get_item_depend_reorder 3.12% : 0.000056s : 228: predicate.tuple_list_get_item_eliminator 1.79% : 0.000032s : 157: predicate.tuple_list_get_set_item_eliminator 2.28% : 0.000041s : 215: predicate.tuple_list_set_item_eliminator 1.61% : 0.000029s : 170: predicate.tuple_to_list_eliminator_ 2.48% : 0.000044s : 295: predicate.updatestate_pure_node_eliminater 3.02% : 0.000054s : 353: predicate.updatestate_useless_node_eliminater 0.18% : 0.000003s : 17: predicate.value_based_eliminate 0.35% : 0.000006s : 35: predicate.virtual_dataset_eliminate 1.22% : 0.000022s : 35: predicate.virtual_output_eliminate 0.15% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.21% : 0.000004s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.026492 133 71.90% : 0.019048s : 53: func_graph_cloner_run.FuncGraphClonerGraph 28.10% : 0.007444s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.879366 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.19% : 0.005413s : 1: add_attr 0.19% : 0.005383s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.01% : 0.000196s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.03% : 0.000819s : 1: auto_monad 0.00% : 0.000085s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.001405s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000052s : 1: control_data_broadcast_order 0.00% : 0.000033s : 1: convert_after_rewriter 0.00% : 0.000099s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000035s : 1: environ_conv 0.01% : 0.000228s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000095s : 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% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.03% : 0.000737s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000871s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000043s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000050s : 1: opt.transform.mutable_eliminate 4.00% : 0.115046s : 95: opt.transform.opt_a 0.01% : 0.000144s : 1: opt.transform.opt_after_cconv 0.00% : 0.000103s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000621s : 28: opt.transform.opt_b 0.01% : 0.000278s : 2: opt.transform.opt_trans_graph 0.01% : 0.000216s : 4: opt.transform.symbol_engine_opt 10.48% : 0.301692s : 1: opt_a 0.01% : 0.000355s : 1: opt_after_cconv 0.03% : 0.000952s : 1: opt_after_jit_grad 0.03% : 0.000879s : 1: opt_b 10.72% : 0.308712s : 1: optimize 0.00% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000068s : 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% : 0.000008s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000008s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000271s : 1: pre_auto_parallel 0.01% : 0.000271s : 1: py_interpret_to_execute 0.00% : 0.000040s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000131s : 1: remove_dup_value 1.36% : 0.039071s : 1: renormalize.infer 0.25% : 0.007067s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000891s : 1: rewriter_after_opt_a 0.03% : 0.000920s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000029s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000649s : 1: symbol_engine_optimizer 0.01% : 0.000333s : 1: tuple_transform 72.40% : 2.084676s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape1-1024] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape1-1024],max_mem:280.0M [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:42:41.215.750 [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 = 1.70723, [21] [bootstrap]: 0.00095596 [type_inference]: 1.41959 [event_method]: 0.00022233 [auto_monad]: 0.00081941 [graph_reusing]: 5.33e-05 [inline]: 3.61999e-06 [add_attr]: 0.0483542, [1] [add_attr_with_inline]: 0.0483368, [1] [Cycle 1]: 0.00033931, [2] [tag_attr]: 0.00021975 [meta_addattr_fg_expand]: 6.277e-05 [parallel-infer-symbol]: 4.42e-06 [pre_auto_parallel]: 0.00027091 [insert-virtual-dataset]: 2.76999e-06 [parallel-infer-symbol-second]: 1.20999e-06 [dataset_repeat_opt]: 2.48e-06 [pipeline_split]: 2.01003e-06 [optimize]: 0.197354, [53] [py_interpret_to_execute]: 0.00027179 [rewriter_before_opt_a]: 0.00090733 [opt_a]: 0.136283, [2] [Cycle 1]: 0.133565, [45] [expand_dump_flag]: 2.337e-05 [switch_simplify]: 0.00093697 [loop_unroll]: 0.00034315 [a_1]: 0.0460306 [with_stream_mark]: 5.529e-05 [recompute_prepare]: 4.028e-05 [updatestate_depend_eliminate]: 2.051e-05 [updatestate_assign_eliminate]: 1.573e-05 [updatestate_loads_eliminate]: 1.989e-05 [parameter_eliminate]: 2.41998e-06 [a_2]: 0.00086986 [accelerated_algorithm]: 6.646e-05 [shard]: 3.19001e-06 [meta_shard_fg_expand]: 2.594e-05 [shard_inline]: 2.597e-05 [merge_send_recv]: 2.075e-05 [auto_parallel]: 2.149e-05 [parallel]: 3.091e-05 [flash_sp]: 1.496e-05 [merge_comm]: 1.697e-05 [allreduce_fusion]: 1.35e-05 [matmul_add_comm_reduction]: 2.152e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 3.013e-05 [virtual_dataset]: 2.374e-05 [get_grad_eliminate_]: 2.267e-05 [virtual_output]: 2.282e-05 [merge_forward]: 1.304e-05 [cell_reuse_recompute_pass]: 2.17999e-06 [offload_activation]: 2.491e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.275e-05 [merge_recompute_call_nodes]: 1.54998e-06 [before_grad]: 4.296e-05 [set_forward_comm_id_for_comm_node_pass]: 1.502e-05 [meta_fg_expand]: 2.098e-05 [flash_sp_send_recv_attached]: 4.92e-06 [receive_attached]: 1.96e-06 [after_resolve]: 3.182e-05 [a_after_grad]: 4.041e-05 [renormalize]: 0.0818139 [add_forward_monad_depend]: 1.374e-05 [auto_monad_grad]: 3.58999e-06 [auto_monad_eliminator]: 8.904e-05 [cse]: 0.00199653 [a_3]: 0.00019602 [Cycle 2]: 0.00269923, [45] [expand_dump_flag]: 3.76001e-06 [switch_simplify]: 3.04e-05 [loop_unroll]: 2.311e-05 [a_1]: 0.00070214 [with_stream_mark]: 4.321e-05 [recompute_prepare]: 2.982e-05 [updatestate_depend_eliminate]: 1.74e-05 [updatestate_assign_eliminate]: 1.194e-05 [updatestate_loads_eliminate]: 1.396e-05 [parameter_eliminate]: 2.53998e-06 [a_2]: 0.00035302 [accelerated_algorithm]: 3.555e-05 [shard]: 2.41998e-06 [meta_shard_fg_expand]: 1.017e-05 [shard_inline]: 2.295e-05 [merge_send_recv]: 2.206e-05 [auto_parallel]: 2.166e-05 [parallel]: 1.143e-05 [flash_sp]: 5.02e-06 [merge_comm]: 1.467e-05 [allreduce_fusion]: 1.301e-05 [matmul_add_comm_reduction]: 2.456e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 2.875e-05 [virtual_dataset]: 2.242e-05 [get_grad_eliminate_]: 2.299e-05 [virtual_output]: 2.17e-05 [merge_forward]: 1.331e-05 [cell_reuse_recompute_pass]: 3.38e-06 [offload_activation]: 2.579e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.982e-05 [merge_recompute_call_nodes]: 1.62999e-06 [before_grad]: 3.969e-05 [set_forward_comm_id_for_comm_node_pass]: 1.479e-05 [meta_fg_expand]: 1.082e-05 [flash_sp_send_recv_attached]: 1.55999e-06 [receive_attached]: 2.37999e-06 [after_resolve]: 3.05e-05 [a_after_grad]: 3.492e-05 [renormalize]: 5.9983e-08 [add_forward_monad_depend]: 3.95e-06 [auto_monad_grad]: 3.35003e-06 [auto_monad_eliminator]: 7.7e-05 [cse]: 0.00041979 [a_3]: 0.00016254 [py_interpret_to_execute_after_opt_a]: 4.089e-05 [slice_cell_reuse_recomputed_activation]: 2.27999e-06 [rewriter_after_opt_a]: 0.0534799 [convert_after_rewriter]: 3.917e-05 [order_py_execute_after_rewriter]: 1.638e-05 [mutable_eliminate]: 0.00115832 [opt_b]: 0.00087391, [1] [Cycle 1]: 0.00086399, [7] [b_1]: 0.00061063 [b_2]: 2.834e-05 [updatestate_depend_eliminate]: 2.084e-05 [updatestate_assign_eliminate]: 1.146e-05 [updatestate_loads_eliminate]: 1.527e-05 [renormalize]: 4.50003e-07 [cse]: 0.00012146 [optimize_parallel_all_gather_comm]: 4.464e-05 [overlap_param_gather]: 2.45002e-06 [cconv]: 4.548e-05 [loop_unroll]: 0.00205109 [opt_after_cconv]: 0.0003517, [1] [Cycle 1]: 0.0003415, [7] [c_1]: 0.0001401 [parameter_eliminate]: 6.66e-06 [updatestate_depend_eliminate]: 2.213e-05 [updatestate_assign_eliminate]: 1.181e-05 [updatestate_loads_eliminate]: 1.409e-05 [cse]: 9.953e-05 [renormalize]: 1.15001e-06 [remove_dup_value]: 0.00011011 [tuple_transform]: 0.00028718, [1] [Cycle 1]: 0.00027923, [4] [d_1]: 0.00022266 [none_parameter_eliminate]: 3.38999e-06 [renormalize]: 5.29981e-07 [switch_simplify]: 2.541e-05 [partial_unused_args_eliminate]: 3.35998e-06 [add_recomputation]: 0.00016477 [cse_after_recomputation]: 8.129e-05, [1] [Cycle 1]: 7.286e-05, [1] [cse]: 6.403e-05 [environ_conv]: 2.568e-05 [swap_dp_allreduce_reducescatter]: 1.984e-05 [bias_add_comm_swap]: 3.41999e-06 [label_micro_interleaved_index]: 6.66999e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.38002e-06 [slice_recompute_activation]: 2.19999e-06 [micro_interleaved_order_control]: 2.76e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 9.89996e-07 [remove_cast_before_assign_add]: 1.34e-06 [full_micro_interleaved_order_control]: 2.37999e-06 [reorder_send_recv_between_fp_bp]: 3.38e-06 [comm_op_add_attrs]: 1.04e-06 [add_comm_op_reuse_tag]: 9.80013e-07 [interleave_split_concat_branches]: 1.34e-06 [interleave_parallel_branches]: 1.02e-06 [overlap_opt_shard_in_pipeline]: 1.22e-06 [overlap_opt_shard_grad_in_pipeline]: 1.74e-06 [control_data_broadcast_order]: 4.17e-05 [grouped_pairwise_exchange_alltoall]: 1.60999e-06 [offloading_packed_experts]: 1.261e-05 [overlap_recompute_and_grad_model_parallel]: 1.081e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.19003e-06 [overlap_recompute_allgather_and_fa_grad]: 1.58002e-06 [overlap_recompute_comm]: 2.12999e-06 [overlap_grad_ring_attention]: 1.034e-05 [overlap_grad_flash_sp]: 5.18e-05 [begin_end_overlap_inline]: 1.04e-06 [split_matmul_comm_elemetwise]: 2.63003e-06 [split_layernorm_comm]: 1.59e-06 [handle_group_info]: 1.21002e-06 [symbol_engine_optimizer]: 0.00057563, [1] [Cycle 1]: 0.00056823, [6] [build]: 0.00029712 [elim_shapecalc]: 4.299e-05 [elim_not_effective]: 6.056e-05 [opt_reshape]: 3.823e-05 [fold_const_symbol]: 6.8e-05 [renormalize]: 4.10015e-07 [detach_backward]: 2.96999e-06 [pipeline_parallel_scheduler]: 1.72999e-06 [auto_monad_reorder]: 6.638e-05 [get_jit_bprop_graph]: 2.37001e-06 [rewriter_after_jit_bprop_graph]: 8.37e-06 [opt_after_jit_grad]: 0.0391203 [validate]: 0.0001416 Sums bootstrap : 0.000956s : 0.06% type_inference : 1.419588s : 85.64% event_method : 0.000222s : 0.01% auto_monad : 0.000819s : 0.05% graph_reusing : 0.000053s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000220s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000063s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000271s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000272s : 0.02% optimize.rewriter_before_opt_a : 0.000907s : 0.05% optimize.opt_a.expand_dump_flag : 0.000027s : 0.00% optimize.opt_a.switch_simplify : 0.000967s : 0.06% optimize.opt_a.loop_unroll : 0.000366s : 0.02% optimize.opt_a.a_1 : 0.046733s : 2.82% optimize.opt_a.with_stream_mark : 0.000099s : 0.01% optimize.opt_a.recompute_prepare : 0.000070s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000038s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000034s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001223s : 0.07% optimize.opt_a.accelerated_algorithm : 0.000102s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000036s : 0.00% optimize.opt_a.shard_inline : 0.000049s : 0.00% optimize.opt_a.merge_send_recv : 0.000043s : 0.00% optimize.opt_a.auto_parallel : 0.000043s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000032s : 0.00% optimize.opt_a.allreduce_fusion : 0.000027s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000046s : 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 : 0.000046s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000046s : 0.00% optimize.opt_a.virtual_output : 0.000045s : 0.00% optimize.opt_a.merge_forward : 0.000026s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000051s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000103s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000083s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000030s : 0.00% optimize.opt_a.meta_fg_expand : 0.000032s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000062s : 0.00% optimize.opt_a.a_after_grad : 0.000075s : 0.00% optimize.opt_a.renormalize : 0.081814s : 4.94% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000166s : 0.01% optimize.opt_a.cse : 0.002416s : 0.15% optimize.opt_a.a_3 : 0.000359s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000041s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.053480s : 3.23% optimize.convert_after_rewriter : 0.000039s : 0.00% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.001158s : 0.07% optimize.opt_b.b_1 : 0.000611s : 0.04% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000121s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000045s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.002051s : 0.12% optimize.opt_after_cconv.c_1 : 0.000140s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.cse : 0.000100s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000110s : 0.01% optimize.tuple_transform.d_1 : 0.000223s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000165s : 0.01% optimize.cse_after_recomputation.cse : 0.000064s : 0.00% optimize.environ_conv : 0.000026s : 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 : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 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 : 0.000042s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000011s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000010s : 0.00% optimize.overlap_grad_flash_sp : 0.000052s : 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 : 0.000297s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000043s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000061s : 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 : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000066s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.039120s : 2.36% validate : 0.000142s : 0.01% Time group info: ------[substitution.] 0.004157 569 0.43% : 0.000018s : 8: substitution.depend_value_elim 0.41% : 0.000017s : 14: substitution.elim_not_effective 0.48% : 0.000020s : 12: substitution.float_tuple_getitem_switch 0.70% : 0.000029s : 14: substitution.fold_const_symbol 0.38% : 0.000016s : 17: substitution.graph_param_transform 71.87% : 0.002988s : 71: substitution.inline 0.34% : 0.000014s : 29: substitution.j_node_and_user_rematch 0.83% : 0.000035s : 6: substitution.less_batch_normalization 1.40% : 0.000058s : 2: substitution.list_to_tuple_eliminator_ 0.17% : 0.000007s : 6: substitution.load_eliminater 0.78% : 0.000033s : 21: substitution.minmaximum_grad 0.22% : 0.000009s : 2: substitution.opt_reshape 0.56% : 0.000023s : 29: substitution.remove_not_recompute_node 0.21% : 0.000009s : 4: substitution.replace_old_param 1.98% : 0.000082s : 18: substitution.reshape_eliminate 1.41% : 0.000059s : 24: substitution.switch_simplify 3.82% : 0.000159s : 51: substitution.tuple_list_convert_item_index_to_positive 2.00% : 0.000083s : 51: substitution.tuple_list_get_item_const_eliminator 2.75% : 0.000114s : 51: substitution.tuple_list_get_item_depend_reorder 5.36% : 0.000223s : 73: substitution.tuple_list_get_item_eliminator 2.66% : 0.000111s : 51: substitution.tuple_list_get_set_item_eliminator 0.71% : 0.000030s : 6: substitution.updatestate_pure_node_eliminater 0.54% : 0.000022s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.419130 2 94.34% : 1.338783s : 1: type_inference.infer 5.66% : 0.080347s : 1: type_inference.specialize ------[replace.] 0.036630 115 0.14% : 0.000050s : 5: replace.depend_value_elim 98.48% : 0.036073s : 71: replace.inline 0.12% : 0.000043s : 2: replace.list_to_tuple_eliminator_ 0.98% : 0.000359s : 24: replace.switch_simplify 0.29% : 0.000106s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003075 115 0.10% : 0.000003s : 5: match.depend_value_elim 95.55% : 0.002938s : 71: match.inline 1.80% : 0.000055s : 2: match.list_to_tuple_eliminator_ 1.39% : 0.000043s : 24: match.switch_simplify 1.17% : 0.000036s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001782 9701 1.20% : 0.000021s : 123: predicate.accumulaten_eliminater 0.73% : 0.000013s : 17: predicate.ad_related_special_op_eliminate 0.52% : 0.000009s : 58: predicate.addn_check_dump 1.15% : 0.000020s : 123: predicate.addn_zero_filter 1.06% : 0.000019s : 123: predicate.adjust_all_reduce_mul_add 2.52% : 0.000045s : 181: predicate.arithmetic_simplify 1.16% : 0.000021s : 123: predicate.cast_eliminate 0.29% : 0.000005s : 34: predicate.check_bprop_eliminate 0.49% : 0.000009s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.56% : 0.000010s : 61: predicate.depend_value_elim 1.15% : 0.000021s : 123: predicate.dict_get_item_const_eliminator 1.24% : 0.000022s : 123: predicate.dict_get_item_eliminator 1.08% : 0.000019s : 123: predicate.dict_set_item_eliminator 0.46% : 0.000008s : 34: predicate.dumpgradient_eliminate 0.10% : 0.000002s : 17: predicate.elim_not_effective 0.19% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000022s : 140: predicate.environ_add_const_eliminate 1.22% : 0.000022s : 140: predicate.environ_get_add_eliminate 1.22% : 0.000022s : 140: predicate.environ_get_depend_swap 1.77% : 0.000032s : 198: predicate.environ_get_eliminate 1.24% : 0.000022s : 140: predicate.environ_get_set_eliminate 1.90% : 0.000034s : 209: predicate.exchange_switch_depend_value 3.04% : 0.000054s : 209: predicate.float_depend_g_call 0.49% : 0.000009s : 58: predicate.float_environ_get_switch 0.70% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.34% : 0.000006s : 35: predicate.get_grad_eliminate 0.10% : 0.000002s : 17: predicate.graph_param_transform 0.50% : 0.000009s : 58: predicate.incorporate_call 0.47% : 0.000008s : 58: predicate.incorporate_call_switch 6.33% : 0.000113s : 459: predicate.inline 0.48% : 0.000009s : 35: predicate.inline_without_move 0.15% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.46% : 0.000008s : 36: predicate.less_batch_normalization 1.59% : 0.000028s : 172: predicate.list_to_tuple_eliminator_ 2.68% : 0.000048s : 295: predicate.load_eliminater 0.50% : 0.000009s : 17: predicate.loop_unroll_after_grad 3.26% : 0.000058s : 314: predicate.loop_unroll_before_grad 1.56% : 0.000028s : 157: predicate.make_slice_get_slice_eliminator 0.51% : 0.000009s : 58: predicate.merge_addn 0.27% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.28% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.20% : 0.000021s : 123: predicate.minmaximum_grad 0.44% : 0.000008s : 17: predicate.mutable_eliminate 0.19% : 0.000003s : 17: predicate.opt_reshape 0.17% : 0.000003s : 17: predicate.parallel_virtual_node 3.71% : 0.000066s : 209: predicate.partial_defer_inline 1.60% : 0.000028s : 155: predicate.partial_eliminate 1.13% : 0.000020s : 123: predicate.print_const_string_wrapper 0.44% : 0.000008s : 53: predicate.reduce_all_const_elim 1.48% : 0.000026s : 123: predicate.reduce_eliminate 2.59% : 0.000046s : 295: predicate.redundant_stop_gradient_eliminater 0.18% : 0.000003s : 35: predicate.remove_not_recompute_node 1.06% : 0.000019s : 172: predicate.replace_applicator 0.17% : 0.000003s : 35: predicate.replace_old_param 0.11% : 0.000002s : 17: predicate.reset_defer_inline 1.23% : 0.000022s : 123: predicate.reshape_eliminate 0.29% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.17% : 0.000003s : 17: predicate.row_tensor_eliminate 0.55% : 0.000010s : 34: predicate.same_eliminate 0.21% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.36% : 0.000006s : 35: predicate.shard_identity_eliminate 0.35% : 0.000006s : 34: predicate.special_op_eliminate 0.66% : 0.000012s : 58: predicate.specialize_transform 0.43% : 0.000008s : 34: predicate.split_environ_get_set_with_tuple_value 0.41% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.09% : 0.000037s : 209: predicate.switch_defer_inline 2.24% : 0.000040s : 243: predicate.switch_layer_defer_inline 6.68% : 0.000119s : 646: predicate.switch_simplify 1.15% : 0.000021s : 123: predicate.tile_eliminate 1.10% : 0.000020s : 123: predicate.transpose_eliminate 1.94% : 0.000035s : 157: predicate.tuple_list_convert_item_index_to_positive 1.80% : 0.000032s : 157: predicate.tuple_list_get_item_const_eliminator 1.78% : 0.000032s : 157: predicate.tuple_list_get_item_depend_reorder 3.16% : 0.000056s : 228: predicate.tuple_list_get_item_eliminator 1.71% : 0.000031s : 157: predicate.tuple_list_get_set_item_eliminator 2.24% : 0.000040s : 215: predicate.tuple_list_set_item_eliminator 1.61% : 0.000029s : 170: predicate.tuple_to_list_eliminator_ 2.57% : 0.000046s : 295: predicate.updatestate_pure_node_eliminater 3.10% : 0.000055s : 353: predicate.updatestate_useless_node_eliminater 0.16% : 0.000003s : 17: predicate.value_based_eliminate 0.34% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.34% : 0.000006s : 35: predicate.virtual_output_eliminate 0.16% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.19% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.054393 133 85.62% : 0.046571s : 53: func_graph_cloner_run.FuncGraphClonerGraph 14.38% : 0.007822s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.086067 209 0.00% : 0.000004s : 1: ForceFp32Comm 2.32% : 0.048362s : 1: add_attr 2.32% : 0.048343s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000172s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.04% : 0.000836s : 1: auto_monad 0.00% : 0.000072s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.05% : 0.000998s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000046s : 1: control_data_broadcast_order 0.00% : 0.000049s : 1: convert_after_rewriter 0.00% : 0.000085s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000029s : 1: environ_conv 0.01% : 0.000235s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000061s : 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% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000003s : 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 0.10% : 0.002067s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.06% : 0.001171s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000054s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000054s : 1: opt.transform.mutable_eliminate 2.41% : 0.050216s : 95: opt.transform.opt_a 0.01% : 0.000138s : 1: opt.transform.opt_after_cconv 0.01% : 0.000123s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000593s : 28: opt.transform.opt_b 0.01% : 0.000243s : 2: opt.transform.opt_trans_graph 0.01% : 0.000202s : 4: opt.transform.symbol_engine_opt 6.53% : 0.136288s : 1: opt_a 0.02% : 0.000356s : 1: opt_after_cconv 1.88% : 0.039147s : 1: opt_after_jit_grad 0.04% : 0.000878s : 1: opt_b 9.46% : 0.197361s : 1: optimize 0.00% : 0.000050s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000021s : 1: order_py_execute_after_rewriter 0.00% : 0.000056s : 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% : 0.000007s : 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% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000279s : 1: pre_auto_parallel 0.01% : 0.000282s : 1: py_interpret_to_execute 0.00% : 0.000047s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000117s : 1: remove_dup_value 3.57% : 0.074493s : 1: renormalize.infer 0.35% : 0.007295s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 2.56% : 0.053504s : 1: rewriter_after_opt_a 0.04% : 0.000920s : 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% : 0.000023s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000580s : 1: symbol_engine_optimizer 0.01% : 0.000291s : 1: tuple_transform 68.05% : 1.419621s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape2-256] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape2-256],max_mem:372.0M [WARNING] ME(164330:281473304026928,MainProcess):2026-01-29-17:43:37.151.250 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 0.344648, [21] [bootstrap]: 0.00107554 [type_inference]: 0.28582 [event_method]: 0.00021571 [auto_monad]: 0.00078764 [graph_reusing]: 5.068e-05 [inline]: 3.28e-06 [add_attr]: 0.00566245, [1] [add_attr_with_inline]: 0.00564644, [1] [Cycle 1]: 0.00032059, [2] [tag_attr]: 0.00021077 [meta_addattr_fg_expand]: 6.191e-05 [parallel-infer-symbol]: 3.75e-06 [pre_auto_parallel]: 0.00025247 [insert-virtual-dataset]: 2.63e-06 [parallel-infer-symbol-second]: 1.00999e-06 [dataset_repeat_opt]: 2.51e-06 [pipeline_split]: 1.79e-06 [optimize]: 0.0497966, [53] [py_interpret_to_execute]: 0.00025009 [rewriter_before_opt_a]: 0.00089234 [opt_a]: 0.0434807, [2] [Cycle 1]: 0.0411721, [45] [expand_dump_flag]: 2.177e-05 [switch_simplify]: 0.00083947 [loop_unroll]: 0.00034383 [a_1]: 0.0229525 [with_stream_mark]: 5.075e-05 [recompute_prepare]: 4.241e-05 [updatestate_depend_eliminate]: 1.992e-05 [updatestate_assign_eliminate]: 1.496e-05 [updatestate_loads_eliminate]: 1.833e-05 [parameter_eliminate]: 2.37999e-06 [a_2]: 0.00085747 [accelerated_algorithm]: 6.679e-05 [shard]: 2.31e-06 [meta_shard_fg_expand]: 2.25e-05 [shard_inline]: 2.62e-05 [merge_send_recv]: 3.578e-05 [auto_parallel]: 2.308e-05 [parallel]: 3.632e-05 [flash_sp]: 1.501e-05 [merge_comm]: 1.488e-05 [allreduce_fusion]: 1.371e-05 [matmul_add_comm_reduction]: 2.066e-05 [allreduce_slice_to_reducescatter]: 1.30001e-06 [virtual_shard_identity]: 3.175e-05 [virtual_dataset]: 2.491e-05 [get_grad_eliminate_]: 2.259e-05 [virtual_output]: 2.179e-05 [merge_forward]: 1.349e-05 [cell_reuse_recompute_pass]: 2.41998e-06 [offload_activation]: 2.295e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.35e-05 [merge_recompute_call_nodes]: 1.50999e-06 [before_grad]: 4.305e-05 [set_forward_comm_id_for_comm_node_pass]: 1.486e-05 [meta_fg_expand]: 2.069e-05 [flash_sp_send_recv_attached]: 6.22001e-06 [receive_attached]: 2.14999e-06 [after_resolve]: 3.219e-05 [a_after_grad]: 4.008e-05 [renormalize]: 0.0129809 [add_forward_monad_depend]: 1.503e-05 [auto_monad_grad]: 2.78e-06 [auto_monad_eliminator]: 9.148e-05 [cse]: 0.0016611 [a_3]: 0.0001955 [Cycle 2]: 0.00229224, [45] [expand_dump_flag]: 4.38001e-06 [switch_simplify]: 2.817e-05 [loop_unroll]: 2.338e-05 [a_1]: 0.00073385 [with_stream_mark]: 3.753e-05 [recompute_prepare]: 2.715e-05 [updatestate_depend_eliminate]: 1.676e-05 [updatestate_assign_eliminate]: 1.219e-05 [updatestate_loads_eliminate]: 1.431e-05 [parameter_eliminate]: 2.68e-06 [a_2]: 0.00034234 [accelerated_algorithm]: 3.42e-05 [shard]: 3.01999e-06 [meta_shard_fg_expand]: 7.63001e-06 [shard_inline]: 2.351e-05 [merge_send_recv]: 2.001e-05 [auto_parallel]: 2.288e-05 [parallel]: 1.093e-05 [flash_sp]: 4.67e-06 [merge_comm]: 1.338e-05 [allreduce_fusion]: 1.249e-05 [matmul_add_comm_reduction]: 2.294e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 2.547e-05 [virtual_dataset]: 2.191e-05 [get_grad_eliminate_]: 2.191e-05 [virtual_output]: 2.101e-05 [merge_forward]: 1.221e-05 [cell_reuse_recompute_pass]: 3.26999e-06 [offload_activation]: 2.531e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.537e-05 [merge_recompute_call_nodes]: 1.50999e-06 [before_grad]: 3.942e-05 [set_forward_comm_id_for_comm_node_pass]: 1.414e-05 [meta_fg_expand]: 1.137e-05 [flash_sp_send_recv_attached]: 2.41e-06 [receive_attached]: 2.77002e-06 [after_resolve]: 2.914e-05 [a_after_grad]: 3.457e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 4.03001e-06 [auto_monad_grad]: 2.79999e-06 [auto_monad_eliminator]: 6.037e-05 [cse]: 8.626e-05 [a_3]: 0.00015297 [py_interpret_to_execute_after_opt_a]: 3.468e-05 [slice_cell_reuse_recomputed_activation]: 1.99e-06 [rewriter_after_opt_a]: 0.00087116 [convert_after_rewriter]: 2.574e-05 [order_py_execute_after_rewriter]: 1.556e-05 [mutable_eliminate]: 0.00082024 [opt_b]: 0.0008814, [1] [Cycle 1]: 0.00087278, [7] [b_1]: 0.00066834 [b_2]: 2.567e-05 [updatestate_depend_eliminate]: 1.879e-05 [updatestate_assign_eliminate]: 1.125e-05 [updatestate_loads_eliminate]: 1.293e-05 [renormalize]: 5.89993e-07 [cse]: 8.722e-05 [optimize_parallel_all_gather_comm]: 3.96e-05 [overlap_param_gather]: 7.46999e-06 [cconv]: 4.095e-05 [loop_unroll]: 0.00052584 [opt_after_cconv]: 0.00029332, [1] [Cycle 1]: 0.00028494, [7] [c_1]: 0.00012871 [parameter_eliminate]: 5.47001e-06 [updatestate_depend_eliminate]: 1.782e-05 [updatestate_assign_eliminate]: 1.084e-05 [updatestate_loads_eliminate]: 1.218e-05 [cse]: 7.08e-05 [renormalize]: 6.60017e-07 [remove_dup_value]: 0.00010045 [tuple_transform]: 0.00027677, [1] [Cycle 1]: 0.00027072, [4] [d_1]: 0.00022013 [none_parameter_eliminate]: 2.59001e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 2.49e-05 [partial_unused_args_eliminate]: 2.28998e-06 [add_recomputation]: 0.00014917 [cse_after_recomputation]: 7.135e-05, [1] [Cycle 1]: 6.444e-05, [1] [cse]: 5.737e-05 [environ_conv]: 2.043e-05 [swap_dp_allreduce_reducescatter]: 1.876e-05 [bias_add_comm_swap]: 2.78e-06 [label_micro_interleaved_index]: 5.12e-06 [label_fine_grained_interleaved_index]: 2.71e-06 [merge_cast_opt]: 1.49998e-06 [slice_recompute_activation]: 1.99999e-06 [micro_interleaved_order_control]: 2.76999e-06 [assign_add_opt]: 1.75001e-06 [ForceFp32Comm]: 1.10001e-06 [remove_cast_before_assign_add]: 1.06002e-06 [full_micro_interleaved_order_control]: 2.64999e-06 [reorder_send_recv_between_fp_bp]: 2.64999e-06 [comm_op_add_attrs]: 1.32999e-06 [add_comm_op_reuse_tag]: 9.50007e-07 [interleave_split_concat_branches]: 1.30999e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 4.90999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.16e-06 [control_data_broadcast_order]: 3.947e-05 [grouped_pairwise_exchange_alltoall]: 1.74e-06 [offloading_packed_experts]: 1.135e-05 [overlap_recompute_and_grad_model_parallel]: 1.162e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.42999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.31002e-06 [overlap_recompute_comm]: 2.61e-06 [overlap_grad_ring_attention]: 9.84001e-06 [overlap_grad_flash_sp]: 5.211e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.51e-06 [split_layernorm_comm]: 1.62001e-06 [handle_group_info]: 9.49978e-07 [symbol_engine_optimizer]: 0.00050539, [1] [Cycle 1]: 0.00049981, [6] [build]: 0.00027915 [elim_shapecalc]: 3.27e-05 [elim_not_effective]: 5.333e-05 [opt_reshape]: 3.422e-05 [fold_const_symbol]: 5.793e-05 [renormalize]: 5.00004e-07 [detach_backward]: 2.51998e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 5.995e-05 [get_jit_bprop_graph]: 1.97001e-06 [rewriter_after_jit_bprop_graph]: 6.51e-06 [opt_after_jit_grad]: 0.00057541 [validate]: 0.00010036 Sums bootstrap : 0.001076s : 0.32% type_inference : 0.285820s : 84.60% event_method : 0.000216s : 0.06% auto_monad : 0.000788s : 0.23% graph_reusing : 0.000051s : 0.02% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000211s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000062s : 0.02% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000252s : 0.07% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000250s : 0.07% optimize.rewriter_before_opt_a : 0.000892s : 0.26% optimize.opt_a.expand_dump_flag : 0.000026s : 0.01% optimize.opt_a.switch_simplify : 0.000868s : 0.26% optimize.opt_a.loop_unroll : 0.000367s : 0.11% optimize.opt_a.a_1 : 0.023686s : 7.01% optimize.opt_a.with_stream_mark : 0.000088s : 0.03% optimize.opt_a.recompute_prepare : 0.000070s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000037s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000027s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000033s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001200s : 0.36% optimize.opt_a.accelerated_algorithm : 0.000101s : 0.03% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000030s : 0.01% optimize.opt_a.shard_inline : 0.000050s : 0.01% optimize.opt_a.merge_send_recv : 0.000056s : 0.02% optimize.opt_a.auto_parallel : 0.000046s : 0.01% optimize.opt_a.parallel : 0.000047s : 0.01% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000028s : 0.01% optimize.opt_a.allreduce_fusion : 0.000026s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000044s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000057s : 0.02% optimize.opt_a.virtual_dataset : 0.000047s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000045s : 0.01% optimize.opt_a.virtual_output : 0.000043s : 0.01% optimize.opt_a.merge_forward : 0.000026s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000048s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000099s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000082s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000029s : 0.01% optimize.opt_a.meta_fg_expand : 0.000032s : 0.01% 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 : 0.000061s : 0.02% optimize.opt_a.a_after_grad : 0.000075s : 0.02% optimize.opt_a.renormalize : 0.012981s : 3.84% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000152s : 0.04% optimize.opt_a.cse : 0.001747s : 0.52% optimize.opt_a.a_3 : 0.000348s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000035s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000871s : 0.26% optimize.convert_after_rewriter : 0.000026s : 0.01% optimize.order_py_execute_after_rewriter : 0.000016s : 0.00% optimize.mutable_eliminate : 0.000820s : 0.24% optimize.opt_b.b_1 : 0.000668s : 0.20% optimize.opt_b.b_2 : 0.000026s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000087s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000040s : 0.01% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000526s : 0.16% optimize.opt_after_cconv.c_1 : 0.000129s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000071s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000100s : 0.03% optimize.tuple_transform.d_1 : 0.000220s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000149s : 0.04% optimize.cse_after_recomputation.cse : 0.000057s : 0.02% optimize.environ_conv : 0.000020s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000019s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000005s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000039s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 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 : 0.000052s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000279s : 0.08% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000033s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000053s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000058s : 0.02% 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 : 0.000060s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000575s : 0.17% validate : 0.000100s : 0.03% Time group info: ------[substitution.] 0.003732 569 0.45% : 0.000017s : 8: substitution.depend_value_elim 0.42% : 0.000016s : 14: substitution.elim_not_effective 0.49% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.66% : 0.000025s : 14: substitution.fold_const_symbol 0.44% : 0.000016s : 17: substitution.graph_param_transform 68.65% : 0.002562s : 71: substitution.inline 0.37% : 0.000014s : 29: substitution.j_node_and_user_rematch 0.91% : 0.000034s : 6: substitution.less_batch_normalization 1.45% : 0.000054s : 2: substitution.list_to_tuple_eliminator_ 0.18% : 0.000007s : 6: substitution.load_eliminater 0.83% : 0.000031s : 21: substitution.minmaximum_grad 0.22% : 0.000008s : 2: substitution.opt_reshape 0.58% : 0.000022s : 29: substitution.remove_not_recompute_node 0.20% : 0.000008s : 4: substitution.replace_old_param 1.78% : 0.000067s : 18: substitution.reshape_eliminate 1.40% : 0.000052s : 24: substitution.switch_simplify 5.21% : 0.000194s : 51: substitution.tuple_list_convert_item_index_to_positive 2.44% : 0.000091s : 51: substitution.tuple_list_get_item_const_eliminator 3.11% : 0.000116s : 51: substitution.tuple_list_get_item_depend_reorder 5.90% : 0.000220s : 73: substitution.tuple_list_get_item_eliminator 3.15% : 0.000118s : 51: substitution.tuple_list_get_set_item_eliminator 0.59% : 0.000022s : 6: substitution.updatestate_pure_node_eliminater 0.55% : 0.000021s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.285384 2 92.69% : 0.264536s : 1: type_inference.infer 7.31% : 0.020847s : 1: type_inference.specialize ------[replace.] 0.001166 115 4.10% : 0.000048s : 5: replace.depend_value_elim 57.08% : 0.000666s : 71: replace.inline 3.91% : 0.000046s : 2: replace.list_to_tuple_eliminator_ 25.79% : 0.000301s : 24: replace.switch_simplify 9.12% : 0.000106s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002641 115 0.10% : 0.000003s : 5: match.depend_value_elim 95.11% : 0.002512s : 71: match.inline 1.96% : 0.000052s : 2: match.list_to_tuple_eliminator_ 1.41% : 0.000037s : 24: match.switch_simplify 1.42% : 0.000037s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001719 9701 1.21% : 0.000021s : 123: predicate.accumulaten_eliminater 0.32% : 0.000005s : 17: predicate.ad_related_special_op_eliminate 0.49% : 0.000008s : 58: predicate.addn_check_dump 1.20% : 0.000021s : 123: predicate.addn_zero_filter 1.14% : 0.000020s : 123: predicate.adjust_all_reduce_mul_add 2.32% : 0.000040s : 181: predicate.arithmetic_simplify 1.12% : 0.000019s : 123: predicate.cast_eliminate 0.30% : 0.000005s : 34: predicate.check_bprop_eliminate 0.48% : 0.000008s : 58: predicate.compare_switch_simplify 0.08% : 0.000001s : 17: predicate.const_output_eliminate 0.56% : 0.000010s : 61: predicate.depend_value_elim 1.33% : 0.000023s : 123: predicate.dict_get_item_const_eliminator 1.31% : 0.000023s : 123: predicate.dict_get_item_eliminator 1.30% : 0.000022s : 123: predicate.dict_set_item_eliminator 0.36% : 0.000006s : 34: predicate.dumpgradient_eliminate 0.09% : 0.000001s : 17: predicate.elim_not_effective 0.19% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.29% : 0.000022s : 140: predicate.environ_add_const_eliminate 1.25% : 0.000021s : 140: predicate.environ_get_add_eliminate 1.28% : 0.000022s : 140: predicate.environ_get_depend_swap 1.79% : 0.000031s : 198: predicate.environ_get_eliminate 1.24% : 0.000021s : 140: predicate.environ_get_set_eliminate 1.94% : 0.000033s : 209: predicate.exchange_switch_depend_value 2.86% : 0.000049s : 209: predicate.float_depend_g_call 0.52% : 0.000009s : 58: predicate.float_environ_get_switch 0.67% : 0.000012s : 75: predicate.float_tuple_getitem_switch 0.08% : 0.000001s : 17: predicate.fold_const_symbol 0.33% : 0.000006s : 35: predicate.get_grad_eliminate 0.10% : 0.000002s : 17: predicate.graph_param_transform 0.57% : 0.000010s : 58: predicate.incorporate_call 0.48% : 0.000008s : 58: predicate.incorporate_call_switch 6.51% : 0.000112s : 459: predicate.inline 0.46% : 0.000008s : 35: predicate.inline_without_move 0.15% : 0.000003s : 35: predicate.j_node_and_user_rematch 0.51% : 0.000009s : 36: predicate.less_batch_normalization 1.63% : 0.000028s : 172: predicate.list_to_tuple_eliminator_ 2.68% : 0.000046s : 295: predicate.load_eliminater 0.30% : 0.000005s : 17: predicate.loop_unroll_after_grad 3.36% : 0.000058s : 314: predicate.loop_unroll_before_grad 1.55% : 0.000027s : 157: predicate.make_slice_get_slice_eliminator 0.53% : 0.000009s : 58: predicate.merge_addn 0.29% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.29% : 0.000005s : 34: predicate.mini_step_allgather_replace 1.15% : 0.000020s : 123: predicate.minmaximum_grad 0.38% : 0.000007s : 17: predicate.mutable_eliminate 0.17% : 0.000003s : 17: predicate.opt_reshape 0.17% : 0.000003s : 17: predicate.parallel_virtual_node 3.14% : 0.000054s : 209: predicate.partial_defer_inline 1.59% : 0.000027s : 155: predicate.partial_eliminate 1.18% : 0.000020s : 123: predicate.print_const_string_wrapper 0.47% : 0.000008s : 53: predicate.reduce_all_const_elim 1.59% : 0.000027s : 123: predicate.reduce_eliminate 2.60% : 0.000045s : 295: predicate.redundant_stop_gradient_eliminater 0.16% : 0.000003s : 35: predicate.remove_not_recompute_node 1.17% : 0.000020s : 172: predicate.replace_applicator 0.20% : 0.000003s : 35: predicate.replace_old_param 0.12% : 0.000002s : 17: predicate.reset_defer_inline 1.33% : 0.000023s : 123: predicate.reshape_eliminate 0.33% : 0.000006s : 34: predicate.row_tensor_add_zeros_like 0.18% : 0.000003s : 17: predicate.row_tensor_eliminate 0.52% : 0.000009s : 34: predicate.same_eliminate 0.24% : 0.000004s : 40: predicate.set_cell_output_no_recompute 0.38% : 0.000007s : 35: predicate.shard_identity_eliminate 0.33% : 0.000006s : 34: predicate.special_op_eliminate 0.70% : 0.000012s : 58: predicate.specialize_transform 0.41% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.40% : 0.000007s : 35: predicate.stack_unstack_eliminate 0.18% : 0.000003s : 17: predicate.switch_call_monad_eliminater 2.09% : 0.000036s : 209: predicate.switch_defer_inline 2.35% : 0.000040s : 243: predicate.switch_layer_defer_inline 6.63% : 0.000114s : 646: predicate.switch_simplify 1.18% : 0.000020s : 123: predicate.tile_eliminate 1.10% : 0.000019s : 123: predicate.transpose_eliminate 1.84% : 0.000032s : 157: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000032s : 157: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000028s : 157: predicate.tuple_list_get_item_depend_reorder 3.11% : 0.000054s : 228: predicate.tuple_list_get_item_eliminator 1.70% : 0.000029s : 157: predicate.tuple_list_get_set_item_eliminator 2.35% : 0.000040s : 215: predicate.tuple_list_set_item_eliminator 1.59% : 0.000027s : 170: predicate.tuple_to_list_eliminator_ 2.62% : 0.000045s : 295: predicate.updatestate_pure_node_eliminater 3.17% : 0.000054s : 353: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 17: predicate.value_based_eliminate 0.37% : 0.000006s : 35: predicate.virtual_dataset_eliminate 0.33% : 0.000006s : 35: predicate.virtual_output_eliminate 0.15% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.20% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.016512 133 57.31% : 0.009463s : 53: func_graph_cloner_run.FuncGraphClonerGraph 42.69% : 0.007049s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.441226 209 0.00% : 0.000004s : 1: ForceFp32Comm 1.28% : 0.005669s : 1: add_attr 1.28% : 0.005652s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.04% : 0.000155s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.18% : 0.000802s : 1: auto_monad 0.01% : 0.000065s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.25% : 0.001113s : 1: bootstrap 0.01% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000043s : 1: control_data_broadcast_order 0.01% : 0.000032s : 1: convert_after_rewriter 0.02% : 0.000075s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000024s : 1: environ_conv 0.05% : 0.000229s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000057s : 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% : 0.000006s : 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 0.12% : 0.000535s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.19% : 0.000830s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.01% : 0.000036s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000044s : 1: opt.transform.mutable_eliminate 6.13% : 0.027041s : 95: opt.transform.opt_a 0.03% : 0.000127s : 1: opt.transform.opt_after_cconv 0.02% : 0.000076s : 1: opt.transform.opt_after_jit_grad 0.15% : 0.000651s : 28: opt.transform.opt_b 0.05% : 0.000242s : 2: opt.transform.opt_trans_graph 0.04% : 0.000173s : 4: opt.transform.symbol_engine_opt 9.86% : 0.043485s : 1: opt_a 0.07% : 0.000298s : 1: opt_after_cconv 0.13% : 0.000584s : 1: opt_after_jit_grad 0.20% : 0.000886s : 1: opt_b 11.29% : 0.049802s : 1: optimize 0.01% : 0.000043s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.01% : 0.000056s : 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% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000012s : 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% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.06% : 0.000261s : 1: pre_auto_parallel 0.06% : 0.000258s : 1: py_interpret_to_execute 0.01% : 0.000039s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000106s : 1: remove_dup_value 1.47% : 0.006477s : 1: renormalize.infer 1.47% : 0.006484s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.20% : 0.000883s : 1: rewriter_after_opt_a 0.20% : 0.000902s : 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 0.01% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.12% : 0.000510s : 1: symbol_engine_optimizer 0.06% : 0.000281s : 1: tuple_transform 64.79% : 0.285857s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_0[True-mstype0-k_n_shape2-1024] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_0[True-mstype0-k_n_shape2-1024],max_mem:438.0M =============================== 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 466.43s (0:07:46) ==================