==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_002/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 6 items test_matmul_split.py [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:37:54.741.441 [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 = 4.83844, [21] [bootstrap]: 0.00063718 [type_inference]: 4.60649 [event_method]: 1.972e-05 [auto_monad]: 0.00191597 [graph_reusing]: 7.37002e-06 [inline]: 3.59002e-06 [add_attr]: 0.199096, [1] [add_attr_with_inline]: 0.199079, [1] [Cycle 1]: 0.00010907, [2] [tag_attr]: 2.456e-05 [meta_addattr_fg_expand]: 6.05002e-06 [parallel-infer-symbol]: 4.39998e-06 [pre_auto_parallel]: 5.771e-05 [insert-virtual-dataset]: 3.18998e-06 [parallel-infer-symbol-second]: 1.10001e-06 [dataset_repeat_opt]: 2.61e-06 [pipeline_split]: 2.16998e-06 [optimize]: 0.0291431, [53] [py_interpret_to_execute]: 3.73e-05 [rewriter_before_opt_a]: 9.365e-05 [opt_a]: 0.025095, [2] [Cycle 1]: 0.0121269, [45] [expand_dump_flag]: 3.18e-06 [switch_simplify]: 3.818e-05 [loop_unroll]: 2.376e-05 [a_1]: 0.00073948 [with_stream_mark]: 3.329e-05 [recompute_prepare]: 2.26e-05 [updatestate_depend_eliminate]: 1.011e-05 [updatestate_assign_eliminate]: 8.57e-06 [updatestate_loads_eliminate]: 1.185e-05 [parameter_eliminate]: 3.04001e-06 [a_2]: 0.00024429 [accelerated_algorithm]: 5.385e-05 [shard]: 2.11003e-06 [meta_shard_fg_expand]: 4.94e-06 [shard_inline]: 1.733e-05 [merge_send_recv]: 1.516e-05 [auto_parallel]: 1.486e-05 [parallel]: 5.399e-05 [flash_sp]: 1.423e-05 [merge_comm]: 9.76e-06 [allreduce_fusion]: 8.13999e-06 [matmul_add_comm_reduction]: 1.806e-05 [allreduce_slice_to_reducescatter]: 1.30001e-06 [virtual_shard_identity]: 2.205e-05 [virtual_dataset]: 1.782e-05 [get_grad_eliminate_]: 1.61e-05 [virtual_output]: 1.754e-05 [merge_forward]: 9.70002e-06 [cell_reuse_recompute_pass]: 2.32999e-06 [offload_activation]: 1.815e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.314e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 2.788e-05 [set_forward_comm_id_for_comm_node_pass]: 9.32999e-06 [meta_fg_expand]: 6.51e-06 [flash_sp_send_recv_attached]: 6.59001e-06 [receive_attached]: 1.155e-05 [after_resolve]: 2.552e-05 [a_after_grad]: 2.639e-05 [renormalize]: 0.00965717 [add_forward_monad_depend]: 1.307e-05 [auto_monad_grad]: 3.47997e-06 [auto_monad_eliminator]: 6.232e-05 [cse]: 0.00030178 [a_3]: 0.00014 [Cycle 2]: 0.0129505, [45] [expand_dump_flag]: 3.09001e-06 [switch_simplify]: 1.985e-05 [loop_unroll]: 1.671e-05 [a_1]: 0.0115281 [with_stream_mark]: 4.828e-05 [recompute_prepare]: 3.068e-05 [updatestate_depend_eliminate]: 1.091e-05 [updatestate_assign_eliminate]: 8.43999e-06 [updatestate_loads_eliminate]: 1.155e-05 [parameter_eliminate]: 2.78e-06 [a_2]: 0.00026912 [accelerated_algorithm]: 2.355e-05 [shard]: 3.31999e-06 [meta_shard_fg_expand]: 7.81001e-06 [shard_inline]: 1.504e-05 [merge_send_recv]: 1.717e-05 [auto_parallel]: 1.606e-05 [parallel]: 1.09e-05 [flash_sp]: 5.10001e-06 [merge_comm]: 8.85001e-06 [allreduce_fusion]: 9.61e-06 [matmul_add_comm_reduction]: 1.866e-05 [allreduce_slice_to_reducescatter]: 8.40024e-07 [virtual_shard_identity]: 1.744e-05 [virtual_dataset]: 1.594e-05 [get_grad_eliminate_]: 1.569e-05 [virtual_output]: 1.513e-05 [merge_forward]: 8.64e-06 [cell_reuse_recompute_pass]: 4.29997e-06 [offload_activation]: 1.8e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.794e-05 [merge_recompute_call_nodes]: 1.59998e-06 [before_grad]: 2.622e-05 [set_forward_comm_id_for_comm_node_pass]: 9.56e-06 [meta_fg_expand]: 7.56001e-06 [flash_sp_send_recv_attached]: 2.02001e-06 [receive_attached]: 2.64999e-06 [after_resolve]: 2.297e-05 [a_after_grad]: 2.841e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 4.17003e-06 [auto_monad_grad]: 3.37002e-06 [auto_monad_eliminator]: 6.493e-05 [cse]: 0.00015951 [a_3]: 0.00010846 [py_interpret_to_execute_after_opt_a]: 3.115e-05 [slice_cell_reuse_recomputed_activation]: 2.86e-06 [rewriter_after_opt_a]: 0.00050542 [convert_after_rewriter]: 2.28e-05 [order_py_execute_after_rewriter]: 1.091e-05 [mutable_eliminate]: 0.00082879 [opt_b]: 0.00057786, [1] [Cycle 1]: 0.00056815, [7] [b_1]: 0.00038305 [b_2]: 1.895e-05 [updatestate_depend_eliminate]: 1.404e-05 [updatestate_assign_eliminate]: 7.73001e-06 [updatestate_loads_eliminate]: 1.103e-05 [renormalize]: 8.00006e-07 [cse]: 9.095e-05 [optimize_parallel_all_gather_comm]: 3.221e-05 [overlap_param_gather]: 2.32001e-06 [cconv]: 3.808e-05 [loop_unroll]: 0.0005672 [opt_after_cconv]: 0.00024425, [1] [Cycle 1]: 0.00023641, [7] [c_1]: 0.00010529 [parameter_eliminate]: 4.79998e-06 [updatestate_depend_eliminate]: 1.23e-05 [updatestate_assign_eliminate]: 8.47e-06 [updatestate_loads_eliminate]: 9.27999e-06 [cse]: 5.74e-05 [renormalize]: 5.8001e-07 [remove_dup_value]: 6.912e-05 [tuple_transform]: 0.00017789, [1] [Cycle 1]: 0.00017161, [4] [d_1]: 0.00012994 [none_parameter_eliminate]: 1.87001e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 1.763e-05 [partial_unused_args_eliminate]: 2.02999e-06 [add_recomputation]: 0.00011564 [cse_after_recomputation]: 5.286e-05, [1] [Cycle 1]: 4.717e-05, [1] [cse]: 4.08e-05 [environ_conv]: 3.307e-05 [swap_dp_allreduce_reducescatter]: 1.205e-05 [bias_add_comm_swap]: 3.46001e-06 [label_micro_interleaved_index]: 4.55001e-06 [label_fine_grained_interleaved_index]: 2.79001e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.14999e-06 [micro_interleaved_order_control]: 2.24001e-06 [assign_add_opt]: 1.65001e-06 [ForceFp32Comm]: 1.10999e-06 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.22001e-06 [reorder_send_recv_between_fp_bp]: 2.64001e-06 [comm_op_add_attrs]: 1.02e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.14998e-06 [interleave_parallel_branches]: 1.11002e-06 [overlap_opt_shard_in_pipeline]: 2.53e-05 [overlap_opt_shard_grad_in_pipeline]: 1.85001e-06 [control_data_broadcast_order]: 2.708e-05 [grouped_pairwise_exchange_alltoall]: 1.67001e-06 [offloading_packed_experts]: 7.79002e-06 [overlap_recompute_and_grad_model_parallel]: 8.07998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.30999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.45001e-06 [overlap_recompute_comm]: 2.21998e-06 [overlap_grad_ring_attention]: 7.23e-06 [overlap_grad_flash_sp]: 5.011e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.26e-06 [split_layernorm_comm]: 2.02999e-06 [handle_group_info]: 1.56002e-06 [symbol_engine_optimizer]: 0.0001528, [1] [Cycle 1]: 0.00014681, [6] [build]: 1.633e-05 [elim_shapecalc]: 2.277e-05 [elim_not_effective]: 2.912e-05 [opt_reshape]: 2.143e-05 [fold_const_symbol]: 2.405e-05 [renormalize]: 3.50003e-07 [detach_backward]: 2.51e-06 [pipeline_parallel_scheduler]: 1.60999e-06 [auto_monad_reorder]: 5.027e-05 [get_jit_bprop_graph]: 2.25002e-06 [rewriter_after_jit_bprop_graph]: 4.2e-06 [opt_after_jit_grad]: 0.00064183 [validate]: 0.000105 Sums bootstrap : 0.000637s : 0.01% type_inference : 4.606493s : 99.32% event_method : 0.000020s : 0.00% auto_monad : 0.001916s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000058s : 0.00% 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 : 0.000037s : 0.00% optimize.rewriter_before_opt_a : 0.000094s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000058s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.012268s : 0.26% optimize.opt_a.with_stream_mark : 0.000082s : 0.00% optimize.opt_a.recompute_prepare : 0.000053s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000023s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000513s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000077s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000013s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000032s : 0.00% optimize.opt_a.auto_parallel : 0.000031s : 0.00% optimize.opt_a.parallel : 0.000065s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000019s : 0.00% optimize.opt_a.allreduce_fusion : 0.000018s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.00% optimize.opt_a.virtual_dataset : 0.000034s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.00% optimize.opt_a.virtual_output : 0.000033s : 0.00% optimize.opt_a.merge_forward : 0.000018s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000061s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000054s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.00% optimize.opt_a.meta_fg_expand : 0.000014s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000014s : 0.00% optimize.opt_a.after_resolve : 0.000048s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.009657s : 0.21% 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 : 0.000127s : 0.00% optimize.opt_a.cse : 0.000461s : 0.01% optimize.opt_a.a_3 : 0.000248s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000505s : 0.01% optimize.convert_after_rewriter : 0.000023s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000829s : 0.02% optimize.opt_b.b_1 : 0.000383s : 0.01% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000091s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.00% optimize.loop_unroll : 0.000567s : 0.01% optimize.opt_after_cconv.c_1 : 0.000105s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000057s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000069s : 0.00% optimize.tuple_transform.d_1 : 0.000130s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000116s : 0.00% optimize.cse_after_recomputation.cse : 0.000041s : 0.00% optimize.environ_conv : 0.000033s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 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 : 0.000025s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000050s : 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000029s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000021s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 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 : 0.000050s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000642s : 0.01% validate : 0.000105s : 0.00% Time group info: ------[substitution.] 0.000337 96 3.44% : 0.000012s : 2: substitution.depend_value_elim 1.16% : 0.000004s : 8: substitution.elim_not_effective 1.06% : 0.000004s : 8: substitution.fold_const_symbol 7.44% : 0.000025s : 13: substitution.graph_param_transform 41.53% : 0.000140s : 1: substitution.inline 2.93% : 0.000010s : 16: substitution.j_node_and_user_rematch 8.56% : 0.000029s : 2: substitution.less_batch_normalization 1.87% : 0.000006s : 6: substitution.load_eliminater 0.57% : 0.000002s : 2: substitution.opt_reshape 3.86% : 0.000013s : 16: substitution.remove_not_recompute_node 2.39% : 0.000008s : 4: substitution.replace_old_param 13.37% : 0.000045s : 4: substitution.reshape_eliminate 6.10% : 0.000021s : 6: substitution.updatestate_pure_node_eliminater 5.73% : 0.000019s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 4.606374 2 99.87% : 4.600562s : 1: type_inference.infer 0.13% : 0.005811s : 1: type_inference.specialize ------[replace.] 0.000023 1 100.00% : 0.000023s : 1: replace.inline ------[match.] 0.000138 1 100.00% : 0.000138s : 1: match.inline ------[predicate.] 0.000474 3002 0.84% : 0.000004s : 27: predicate.accumulaten_eliminater 0.96% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 0.69% : 0.000003s : 26: predicate.addn_check_dump 0.83% : 0.000004s : 27: predicate.addn_zero_filter 0.72% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.12% : 0.000010s : 53: predicate.arithmetic_simplify 0.94% : 0.000004s : 27: predicate.cast_eliminate 0.73% : 0.000003s : 26: predicate.check_bprop_eliminate 0.69% : 0.000003s : 26: predicate.compare_switch_simplify 0.23% : 0.000001s : 13: predicate.const_output_eliminate 0.86% : 0.000004s : 26: predicate.depend_value_elim 0.80% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 0.95% : 0.000005s : 27: predicate.dict_get_item_eliminator 0.83% : 0.000004s : 27: predicate.dict_set_item_eliminator 0.98% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 13: predicate.elim_not_effective 0.45% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000006s : 40: predicate.environ_add_const_eliminate 1.07% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.04% : 0.000005s : 40: predicate.environ_get_depend_swap 1.87% : 0.000009s : 66: predicate.environ_get_eliminate 1.09% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.77% : 0.000004s : 28: predicate.exchange_switch_depend_value 1.84% : 0.000009s : 28: predicate.float_depend_g_call 0.81% : 0.000004s : 26: predicate.float_environ_get_switch 1.06% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 13: predicate.fold_const_symbol 0.90% : 0.000004s : 26: predicate.get_grad_eliminate 0.28% : 0.000001s : 13: predicate.graph_param_transform 0.73% : 0.000003s : 26: predicate.incorporate_call 0.64% : 0.000003s : 26: predicate.incorporate_call_switch 5.17% : 0.000024s : 133: predicate.inline 0.99% : 0.000005s : 26: predicate.inline_without_move 0.41% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.35% : 0.000006s : 27: predicate.less_batch_normalization 1.57% : 0.000007s : 53: predicate.list_to_tuple_eliminator_ 2.20% : 0.000010s : 80: predicate.load_eliminater 1.02% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.11% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.72% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.75% : 0.000004s : 26: predicate.merge_addn 0.77% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.79% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.75% : 0.000004s : 27: predicate.minmaximum_grad 0.99% : 0.000005s : 13: predicate.mutable_eliminate 0.44% : 0.000002s : 13: predicate.opt_reshape 0.43% : 0.000002s : 13: predicate.parallel_virtual_node 2.26% : 0.000011s : 28: predicate.partial_defer_inline 1.18% : 0.000006s : 40: predicate.partial_eliminate 0.78% : 0.000004s : 27: predicate.print_const_string_wrapper 0.78% : 0.000004s : 26: predicate.reduce_all_const_elim 1.12% : 0.000005s : 27: predicate.reduce_eliminate 2.28% : 0.000011s : 80: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000003s : 26: predicate.remove_not_recompute_node 2.04% : 0.000010s : 53: predicate.replace_applicator 0.44% : 0.000002s : 26: predicate.replace_old_param 0.32% : 0.000002s : 13: predicate.reset_defer_inline 1.11% : 0.000005s : 27: predicate.reshape_eliminate 0.83% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.42% : 0.000002s : 13: predicate.row_tensor_eliminate 1.07% : 0.000005s : 26: predicate.same_eliminate 0.55% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.92% : 0.000004s : 26: predicate.shard_identity_eliminate 0.94% : 0.000004s : 26: predicate.special_op_eliminate 0.94% : 0.000004s : 26: predicate.specialize_transform 1.19% : 0.000006s : 26: predicate.split_environ_get_set_with_tuple_value 1.00% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.44% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.85% : 0.000004s : 28: predicate.switch_defer_inline 2.21% : 0.000010s : 54: predicate.switch_layer_defer_inline 3.54% : 0.000017s : 98: predicate.switch_simplify 0.89% : 0.000004s : 27: predicate.tile_eliminate 0.78% : 0.000004s : 27: predicate.transpose_eliminate 1.59% : 0.000008s : 53: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.55% : 0.000007s : 53: predicate.tuple_list_get_item_depend_reorder 3.45% : 0.000016s : 79: predicate.tuple_list_get_item_eliminator 1.59% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.70% : 0.000013s : 79: predicate.tuple_list_set_item_eliminator 1.66% : 0.000008s : 53: predicate.tuple_to_list_eliminator_ 2.13% : 0.000010s : 80: predicate.updatestate_pure_node_eliminater 3.35% : 0.000016s : 106: predicate.updatestate_useless_node_eliminater 0.47% : 0.000002s : 13: predicate.value_based_eliminate 0.81% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.90% : 0.000004s : 26: predicate.virtual_output_eliminate 0.36% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.49% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.010883 56 77.49% : 0.008433s : 53: func_graph_cloner_run.FuncGraphClonerGraph 22.51% : 0.002450s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 5.090436 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.91% : 0.199103s : 1: add_attr 3.91% : 0.199084s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000120s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.001957s : 1: auto_monad 0.00% : 0.000055s : 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% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000028s : 1: convert_after_rewriter 0.00% : 0.000056s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000037s : 1: environ_conv 0.00% : 0.000029s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.01% : 0.000578s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000841s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.27% : 0.013508s : 78: opt.transform.opt_a 0.00% : 0.000103s : 1: opt.transform.opt_after_cconv 0.00% : 0.000063s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000361s : 28: opt.transform.opt_b 0.00% : 0.000144s : 2: opt.transform.opt_trans_graph 0.00% : 0.000092s : 4: opt.transform.symbol_engine_opt 0.49% : 0.025099s : 1: opt_a 0.00% : 0.000248s : 1: opt_after_cconv 0.01% : 0.000655s : 1: opt_after_jit_grad 0.01% : 0.000582s : 1: opt_b 0.57% : 0.029149s : 1: optimize 0.00% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000054s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000029s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000062s : 1: pre_auto_parallel 0.00% : 0.000044s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000074s : 1: remove_dup_value 0.13% : 0.006721s : 1: renormalize.infer 0.06% : 0.002917s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000515s : 1: rewriter_after_opt_a 0.00% : 0.000099s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000156s : 1: symbol_engine_optimizer 0.00% : 0.000181s : 1: tuple_transform 90.49% : 4.606527s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape0-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape0-1],max_mem:272.0M [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:40:09.541.780 [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 = 3.58382, [21] [bootstrap]: 0.0009235 [type_inference]: 3.40018 [event_method]: 1.964e-05 [auto_monad]: 0.00033781 [graph_reusing]: 6.98e-06 [inline]: 3.16001e-06 [add_attr]: 0.0085824, [1] [add_attr_with_inline]: 0.00856532, [1] [Cycle 1]: 7.043e-05, [2] [tag_attr]: 2.299e-05 [meta_addattr_fg_expand]: 4.68999e-06 [parallel-infer-symbol]: 5.88002e-06 [pre_auto_parallel]: 4.007e-05 [insert-virtual-dataset]: 2.96001e-06 [parallel-infer-symbol-second]: 7.59988e-07 [dataset_repeat_opt]: 2.01e-06 [pipeline_split]: 1.63002e-06 [optimize]: 0.172702, [53] [py_interpret_to_execute]: 3.28e-05 [rewriter_before_opt_a]: 8.773e-05 [opt_a]: 0.169146, [2] [Cycle 1]: 0.167492, [45] [expand_dump_flag]: 2.89999e-06 [switch_simplify]: 3.521e-05 [loop_unroll]: 2.098e-05 [a_1]: 0.00084036 [with_stream_mark]: 2.854e-05 [recompute_prepare]: 2.279e-05 [updatestate_depend_eliminate]: 1.19e-05 [updatestate_assign_eliminate]: 8.57e-06 [updatestate_loads_eliminate]: 1.091e-05 [parameter_eliminate]: 2.12999e-06 [a_2]: 0.00025692 [accelerated_algorithm]: 4.901e-05 [shard]: 2.07001e-06 [meta_shard_fg_expand]: 4.3e-06 [shard_inline]: 1.867e-05 [merge_send_recv]: 1.39e-05 [auto_parallel]: 1.415e-05 [parallel]: 3.881e-05 [flash_sp]: 1.373e-05 [merge_comm]: 9.10999e-06 [allreduce_fusion]: 8.43001e-06 [matmul_add_comm_reduction]: 1.723e-05 [allreduce_slice_to_reducescatter]: 6.99976e-07 [virtual_shard_identity]: 2.111e-05 [virtual_dataset]: 1.776e-05 [get_grad_eliminate_]: 1.672e-05 [virtual_output]: 1.539e-05 [merge_forward]: 8.20999e-06 [cell_reuse_recompute_pass]: 2.17999e-06 [offload_activation]: 1.932e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.49e-05 [merge_recompute_call_nodes]: 1.69e-06 [before_grad]: 2.932e-05 [set_forward_comm_id_for_comm_node_pass]: 9.60001e-06 [meta_fg_expand]: 6.76999e-06 [flash_sp_send_recv_attached]: 6.56999e-06 [receive_attached]: 2.73e-06 [after_resolve]: 2.607e-05 [a_after_grad]: 2.678e-05 [renormalize]: 0.163914 [add_forward_monad_depend]: 1.236e-05 [auto_monad_grad]: 2.90998e-06 [auto_monad_eliminator]: 6.059e-05 [cse]: 0.0013296 [a_3]: 0.00014297 [Cycle 2]: 0.0016356, [45] [expand_dump_flag]: 3.36999e-06 [switch_simplify]: 2.006e-05 [loop_unroll]: 1.785e-05 [a_1]: 0.00047325 [with_stream_mark]: 3.069e-05 [recompute_prepare]: 1.738e-05 [updatestate_depend_eliminate]: 9.43002e-06 [updatestate_assign_eliminate]: 8.07e-06 [updatestate_loads_eliminate]: 1.025e-05 [parameter_eliminate]: 2.69001e-06 [a_2]: 0.00021899 [accelerated_algorithm]: 2.126e-05 [shard]: 2.16998e-06 [meta_shard_fg_expand]: 5.16002e-06 [shard_inline]: 1.527e-05 [merge_send_recv]: 1.467e-05 [auto_parallel]: 1.546e-05 [parallel]: 1.07e-05 [flash_sp]: 5.56e-06 [merge_comm]: 8.63001e-06 [allreduce_fusion]: 9.49e-06 [matmul_add_comm_reduction]: 1.617e-05 [allreduce_slice_to_reducescatter]: 8.00006e-07 [virtual_shard_identity]: 1.765e-05 [virtual_dataset]: 1.52e-05 [get_grad_eliminate_]: 1.54e-05 [virtual_output]: 1.564e-05 [merge_forward]: 8.25e-06 [cell_reuse_recompute_pass]: 3.36001e-06 [offload_activation]: 1.737e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.849e-05 [merge_recompute_call_nodes]: 1.71998e-06 [before_grad]: 2.51e-05 [set_forward_comm_id_for_comm_node_pass]: 8.12003e-06 [meta_fg_expand]: 6.62002e-06 [flash_sp_send_recv_attached]: 2.06e-06 [receive_attached]: 2.58998e-06 [after_resolve]: 2.329e-05 [a_after_grad]: 2.537e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.07002e-06 [auto_monad_grad]: 2.63e-06 [auto_monad_eliminator]: 5.637e-05 [cse]: 8.59e-05 [a_3]: 0.00010151 [py_interpret_to_execute_after_opt_a]: 2.882e-05 [slice_cell_reuse_recomputed_activation]: 2.32999e-06 [rewriter_after_opt_a]: 0.00019964 [convert_after_rewriter]: 1.557e-05 [order_py_execute_after_rewriter]: 1.045e-05 [mutable_eliminate]: 0.00080471 [opt_b]: 0.00054801, [1] [Cycle 1]: 0.00053836, [7] [b_1]: 0.00038032 [b_2]: 1.879e-05 [updatestate_depend_eliminate]: 1.516e-05 [updatestate_assign_eliminate]: 7.76001e-06 [updatestate_loads_eliminate]: 9.84001e-06 [renormalize]: 8.80013e-07 [cse]: 6.17e-05 [optimize_parallel_all_gather_comm]: 3.37e-05 [overlap_param_gather]: 3.85e-06 [cconv]: 4.078e-05 [loop_unroll]: 0.00053176 [opt_after_cconv]: 0.00022185, [1] [Cycle 1]: 0.00021317, [7] [c_1]: 9.728e-05 [parameter_eliminate]: 5.43002e-06 [updatestate_depend_eliminate]: 1.272e-05 [updatestate_assign_eliminate]: 6.70002e-06 [updatestate_loads_eliminate]: 8.43001e-06 [cse]: 4.665e-05 [renormalize]: 3.19997e-07 [remove_dup_value]: 6.979e-05 [tuple_transform]: 0.00015848, [1] [Cycle 1]: 0.00015255, [4] [d_1]: 0.000112 [none_parameter_eliminate]: 1.96e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 1.629e-05 [partial_unused_args_eliminate]: 1.81e-06 [add_recomputation]: 0.00012502 [cse_after_recomputation]: 5.165e-05, [1] [Cycle 1]: 4.653e-05, [1] [cse]: 4.023e-05 [environ_conv]: 1.745e-05 [swap_dp_allreduce_reducescatter]: 1.317e-05 [bias_add_comm_swap]: 3.36999e-06 [label_micro_interleaved_index]: 5.44998e-06 [label_fine_grained_interleaved_index]: 2.81e-06 [merge_cast_opt]: 1.38002e-06 [slice_recompute_activation]: 2.11e-06 [micro_interleaved_order_control]: 2.45997e-06 [assign_add_opt]: 1.67001e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 1.25001e-06 [full_micro_interleaved_order_control]: 2.63e-06 [reorder_send_recv_between_fp_bp]: 2.71e-06 [comm_op_add_attrs]: 9.99979e-07 [add_comm_op_reuse_tag]: 9.39996e-07 [interleave_split_concat_branches]: 1.12999e-06 [interleave_parallel_branches]: 1.03001e-06 [overlap_opt_shard_in_pipeline]: 2.49001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.31e-06 [control_data_broadcast_order]: 2.591e-05 [grouped_pairwise_exchange_alltoall]: 1.54e-06 [offloading_packed_experts]: 6.63e-06 [overlap_recompute_and_grad_model_parallel]: 7.94002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19e-06 [overlap_recompute_allgather_and_fa_grad]: 1.30001e-06 [overlap_recompute_comm]: 2.33998e-06 [overlap_grad_ring_attention]: 7.83001e-06 [overlap_grad_flash_sp]: 4.026e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.77002e-06 [split_layernorm_comm]: 1.81998e-06 [handle_group_info]: 1.10001e-06 [symbol_engine_optimizer]: 0.00015312, [1] [Cycle 1]: 0.00014642, [6] [build]: 1.756e-05 [elim_shapecalc]: 2.219e-05 [elim_not_effective]: 2.925e-05 [opt_reshape]: 2.259e-05 [fold_const_symbol]: 2.377e-05 [renormalize]: 2.09984e-07 [detach_backward]: 2.22999e-06 [pipeline_parallel_scheduler]: 1.78002e-06 [auto_monad_reorder]: 4.396e-05 [get_jit_bprop_graph]: 2.14e-06 [rewriter_after_jit_bprop_graph]: 5.62999e-06 [opt_after_jit_grad]: 0.00058364 [validate]: 0.00014274 Sums bootstrap : 0.000923s : 0.03% type_inference : 3.400178s : 95.14% event_method : 0.000020s : 0.00% auto_monad : 0.000338s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000040s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000033s : 0.00% optimize.rewriter_before_opt_a : 0.000088s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001314s : 0.04% optimize.opt_a.with_stream_mark : 0.000059s : 0.00% optimize.opt_a.recompute_prepare : 0.000040s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000476s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000070s : 0.00% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000034s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000050s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000018s : 0.00% optimize.opt_a.allreduce_fusion : 0.000018s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.00% optimize.opt_a.virtual_dataset : 0.000033s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.00% optimize.opt_a.virtual_output : 0.000031s : 0.00% optimize.opt_a.merge_forward : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000063s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000054s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.00% optimize.opt_a.meta_fg_expand : 0.000013s : 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 : 0.000049s : 0.00% optimize.opt_a.a_after_grad : 0.000052s : 0.00% optimize.opt_a.renormalize : 0.163914s : 4.59% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000117s : 0.00% optimize.opt_a.cse : 0.001416s : 0.04% optimize.opt_a.a_3 : 0.000244s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000200s : 0.01% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000805s : 0.02% optimize.opt_b.b_1 : 0.000380s : 0.01% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000062s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000034s : 0.00% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000532s : 0.01% optimize.opt_after_cconv.c_1 : 0.000097s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.cse : 0.000047s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000070s : 0.00% optimize.tuple_transform.d_1 : 0.000112s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000125s : 0.00% optimize.cse_after_recomputation.cse : 0.000040s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 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 : 0.000003s : 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 : 0.000026s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000040s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000029s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000023s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000044s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000584s : 0.02% validate : 0.000143s : 0.00% Time group info: ------[substitution.] 0.000277 96 3.94% : 0.000011s : 2: substitution.depend_value_elim 1.27% : 0.000004s : 8: substitution.elim_not_effective 1.11% : 0.000003s : 8: substitution.fold_const_symbol 4.20% : 0.000012s : 13: substitution.graph_param_transform 41.29% : 0.000114s : 1: substitution.inline 3.50% : 0.000010s : 16: substitution.j_node_and_user_rematch 8.55% : 0.000024s : 2: substitution.less_batch_normalization 2.03% : 0.000006s : 6: substitution.load_eliminater 1.15% : 0.000003s : 2: substitution.opt_reshape 4.87% : 0.000013s : 16: substitution.remove_not_recompute_node 2.98% : 0.000008s : 4: substitution.replace_old_param 11.02% : 0.000030s : 4: substitution.reshape_eliminate 8.03% : 0.000022s : 6: substitution.updatestate_pure_node_eliminater 6.04% : 0.000017s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.400062 2 99.84% : 3.394546s : 1: type_inference.infer 0.16% : 0.005516s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000113 1 100.00% : 0.000113s : 1: match.inline ------[predicate.] 0.000442 3002 0.91% : 0.000004s : 27: predicate.accumulaten_eliminater 0.97% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.77% : 0.000003s : 26: predicate.addn_check_dump 1.18% : 0.000005s : 27: predicate.addn_zero_filter 0.78% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.30% : 0.000010s : 53: predicate.arithmetic_simplify 0.87% : 0.000004s : 27: predicate.cast_eliminate 0.90% : 0.000004s : 26: predicate.check_bprop_eliminate 0.75% : 0.000003s : 26: predicate.compare_switch_simplify 0.24% : 0.000001s : 13: predicate.const_output_eliminate 0.88% : 0.000004s : 26: predicate.depend_value_elim 0.88% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 0.99% : 0.000004s : 27: predicate.dict_get_item_eliminator 0.82% : 0.000004s : 27: predicate.dict_set_item_eliminator 1.12% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.30% : 0.000001s : 13: predicate.elim_not_effective 0.61% : 0.000003s : 13: predicate.elim_shapecalc_of_broadcastargs 1.23% : 0.000005s : 40: predicate.environ_add_const_eliminate 1.15% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.09% : 0.000005s : 40: predicate.environ_get_depend_swap 1.98% : 0.000009s : 66: predicate.environ_get_eliminate 1.14% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.80% : 0.000004s : 28: predicate.exchange_switch_depend_value 1.31% : 0.000006s : 28: predicate.float_depend_g_call 0.74% : 0.000003s : 26: predicate.float_environ_get_switch 1.12% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 13: predicate.fold_const_symbol 0.83% : 0.000004s : 26: predicate.get_grad_eliminate 0.33% : 0.000001s : 13: predicate.graph_param_transform 0.80% : 0.000004s : 26: predicate.incorporate_call 0.71% : 0.000003s : 26: predicate.incorporate_call_switch 5.25% : 0.000023s : 133: predicate.inline 1.03% : 0.000005s : 26: predicate.inline_without_move 0.44% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.48% : 0.000007s : 27: predicate.less_batch_normalization 1.65% : 0.000007s : 53: predicate.list_to_tuple_eliminator_ 2.25% : 0.000010s : 80: predicate.load_eliminater 0.83% : 0.000004s : 13: predicate.loop_unroll_after_grad 1.02% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.73% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.82% : 0.000004s : 26: predicate.merge_addn 0.73% : 0.000003s : 26: predicate.micro_step_allgather_replace 0.82% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.85% : 0.000004s : 27: predicate.minmaximum_grad 1.04% : 0.000005s : 13: predicate.mutable_eliminate 0.46% : 0.000002s : 13: predicate.opt_reshape 0.47% : 0.000002s : 13: predicate.parallel_virtual_node 1.08% : 0.000005s : 28: predicate.partial_defer_inline 1.33% : 0.000006s : 40: predicate.partial_eliminate 0.84% : 0.000004s : 27: predicate.print_const_string_wrapper 0.85% : 0.000004s : 26: predicate.reduce_all_const_elim 1.07% : 0.000005s : 27: predicate.reduce_eliminate 2.54% : 0.000011s : 80: predicate.redundant_stop_gradient_eliminater 0.49% : 0.000002s : 26: predicate.remove_not_recompute_node 1.34% : 0.000006s : 53: predicate.replace_applicator 0.62% : 0.000003s : 26: predicate.replace_old_param 0.39% : 0.000002s : 13: predicate.reset_defer_inline 0.95% : 0.000004s : 27: predicate.reshape_eliminate 0.85% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 13: predicate.row_tensor_eliminate 1.29% : 0.000006s : 26: predicate.same_eliminate 0.52% : 0.000002s : 26: predicate.set_cell_output_no_recompute 1.00% : 0.000004s : 26: predicate.shard_identity_eliminate 0.90% : 0.000004s : 26: predicate.special_op_eliminate 0.87% : 0.000004s : 26: predicate.specialize_transform 1.01% : 0.000004s : 26: predicate.split_environ_get_set_with_tuple_value 1.00% : 0.000004s : 26: predicate.stack_unstack_eliminate 0.48% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.91% : 0.000004s : 28: predicate.switch_defer_inline 1.61% : 0.000007s : 54: predicate.switch_layer_defer_inline 3.52% : 0.000016s : 98: predicate.switch_simplify 0.86% : 0.000004s : 27: predicate.tile_eliminate 0.85% : 0.000004s : 27: predicate.transpose_eliminate 1.60% : 0.000007s : 53: predicate.tuple_list_convert_item_index_to_positive 1.79% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.58% : 0.000007s : 53: predicate.tuple_list_get_item_depend_reorder 2.87% : 0.000013s : 79: predicate.tuple_list_get_item_eliminator 1.70% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.59% : 0.000011s : 79: predicate.tuple_list_set_item_eliminator 1.89% : 0.000008s : 53: predicate.tuple_to_list_eliminator_ 2.23% : 0.000010s : 80: predicate.updatestate_pure_node_eliminater 3.46% : 0.000015s : 106: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 13: predicate.value_based_eliminate 0.88% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.88% : 0.000004s : 26: predicate.virtual_output_eliminate 0.41% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.259086 56 98.61% : 0.255473s : 53: func_graph_cloner_run.FuncGraphClonerGraph 1.39% : 0.003614s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 3.932039 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.22% : 0.008591s : 1: add_attr 0.22% : 0.008570s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000131s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000350s : 1: auto_monad 0.00% : 0.000048s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000978s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000030s : 1: control_data_broadcast_order 0.00% : 0.000020s : 1: convert_after_rewriter 0.00% : 0.000055s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.00% : 0.000029s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 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% : 0.000008s : 1: label_micro_interleaved_index 0.01% : 0.000543s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000818s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000035s : 1: opt.transform.mutable_eliminate 0.06% : 0.002505s : 78: opt.transform.opt_a 0.00% : 0.000096s : 1: opt.transform.opt_after_cconv 0.00% : 0.000059s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000363s : 28: opt.transform.opt_b 0.00% : 0.000126s : 2: opt.transform.opt_trans_graph 0.00% : 0.000093s : 4: opt.transform.symbol_engine_opt 4.30% : 0.169150s : 1: opt_a 0.01% : 0.000225s : 1: opt_after_cconv 0.02% : 0.000595s : 1: opt_after_jit_grad 0.01% : 0.000552s : 1: opt_b 4.39% : 0.172710s : 1: optimize 0.00% : 0.000038s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000044s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000044s : 1: pre_auto_parallel 0.00% : 0.000038s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000074s : 1: remove_dup_value 4.07% : 0.159867s : 1: renormalize.infer 0.10% : 0.004029s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000207s : 1: rewriter_after_opt_a 0.00% : 0.000093s : 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% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000156s : 1: symbol_engine_optimizer 0.00% : 0.000162s : 1: tuple_transform 86.47% : 3.400211s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape0-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape0-16],max_mem:274.0M [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:41:58.121.850 [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 = 2.14442, [21] [bootstrap]: 0.00077889 [type_inference]: 1.96113 [event_method]: 2.014e-05 [auto_monad]: 0.0003885 [graph_reusing]: 6.29999e-06 [inline]: 3.17002e-06 [add_attr]: 0.00726548, [1] [add_attr_with_inline]: 0.00724636, [1] [Cycle 1]: 7.621e-05, [2] [tag_attr]: 2.304e-05 [meta_addattr_fg_expand]: 4.95001e-06 [parallel-infer-symbol]: 5.54e-06 [pre_auto_parallel]: 4.024e-05 [insert-virtual-dataset]: 2.52001e-06 [parallel-infer-symbol-second]: 7.29982e-07 [dataset_repeat_opt]: 1.66e-06 [pipeline_split]: 1.54e-06 [optimize]: 0.173672, [53] [py_interpret_to_execute]: 3.243e-05 [rewriter_before_opt_a]: 8.245e-05 [opt_a]: 0.169728, [2] [Cycle 1]: 0.167911, [45] [expand_dump_flag]: 2.82002e-06 [switch_simplify]: 3.634e-05 [loop_unroll]: 2.049e-05 [a_1]: 0.00085319 [with_stream_mark]: 2.907e-05 [recompute_prepare]: 2.34e-05 [updatestate_depend_eliminate]: 1.164e-05 [updatestate_assign_eliminate]: 8.1e-06 [updatestate_loads_eliminate]: 1.133e-05 [parameter_eliminate]: 1.97999e-06 [a_2]: 0.00027776 [accelerated_algorithm]: 6.649e-05 [shard]: 2.17999e-06 [meta_shard_fg_expand]: 3.43999e-06 [shard_inline]: 1.683e-05 [merge_send_recv]: 2.445e-05 [auto_parallel]: 1.727e-05 [parallel]: 3.5e-05 [flash_sp]: 1.228e-05 [merge_comm]: 1.911e-05 [allreduce_fusion]: 1.541e-05 [matmul_add_comm_reduction]: 2.225e-05 [allreduce_slice_to_reducescatter]: 6.00005e-07 [virtual_shard_identity]: 3.577e-05 [virtual_dataset]: 4.183e-05 [get_grad_eliminate_]: 3.831e-05 [virtual_output]: 1.985e-05 [merge_forward]: 8.74e-06 [cell_reuse_recompute_pass]: 1.64e-06 [offload_activation]: 1.848e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.426e-05 [merge_recompute_call_nodes]: 1.62001e-06 [before_grad]: 2.823e-05 [set_forward_comm_id_for_comm_node_pass]: 8.90999e-06 [meta_fg_expand]: 6.01e-06 [flash_sp_send_recv_attached]: 7.01999e-06 [receive_attached]: 2.66e-06 [after_resolve]: 2.441e-05 [a_after_grad]: 3.032e-05 [renormalize]: 0.164316 [add_forward_monad_depend]: 1.209e-05 [auto_monad_grad]: 3.09001e-06 [auto_monad_eliminator]: 6.062e-05 [cse]: 0.00119959 [a_3]: 0.00013526 [Cycle 2]: 0.00180187, [45] [expand_dump_flag]: 2.95998e-06 [switch_simplify]: 1.838e-05 [loop_unroll]: 1.652e-05 [a_1]: 0.00047294 [with_stream_mark]: 3.103e-05 [recompute_prepare]: 1.677e-05 [updatestate_depend_eliminate]: 9.62001e-06 [updatestate_assign_eliminate]: 8.11002e-06 [updatestate_loads_eliminate]: 1.051e-05 [parameter_eliminate]: 2.31e-06 [a_2]: 0.00034309 [accelerated_algorithm]: 2.396e-05 [shard]: 2.77002e-06 [meta_shard_fg_expand]: 5.77001e-06 [shard_inline]: 1.616e-05 [merge_send_recv]: 1.618e-05 [auto_parallel]: 1.651e-05 [parallel]: 1.065e-05 [flash_sp]: 4.95001e-06 [merge_comm]: 8.59e-06 [allreduce_fusion]: 1.012e-05 [matmul_add_comm_reduction]: 1.741e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 1.667e-05 [virtual_dataset]: 1.547e-05 [get_grad_eliminate_]: 1.533e-05 [virtual_output]: 1.577e-05 [merge_forward]: 7.88999e-06 [cell_reuse_recompute_pass]: 2.39001e-06 [offload_activation]: 1.785e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.861e-05 [merge_recompute_call_nodes]: 1.83002e-06 [before_grad]: 2.456e-05 [set_forward_comm_id_for_comm_node_pass]: 8.70999e-06 [meta_fg_expand]: 6.29001e-06 [flash_sp_send_recv_attached]: 2.14999e-06 [receive_attached]: 2.16998e-06 [after_resolve]: 2.261e-05 [a_after_grad]: 2.468e-05 [renormalize]: 5.9983e-08 [add_forward_monad_depend]: 3.03e-06 [auto_monad_grad]: 2.59999e-06 [auto_monad_eliminator]: 5.504e-05 [cse]: 0.00011629 [a_3]: 0.00010482 [py_interpret_to_execute_after_opt_a]: 2.763e-05 [slice_cell_reuse_recomputed_activation]: 2.59999e-06 [rewriter_after_opt_a]: 0.00019085 [convert_after_rewriter]: 1.374e-05 [order_py_execute_after_rewriter]: 1.005e-05 [mutable_eliminate]: 0.00084728 [opt_b]: 0.00054116, [1] [Cycle 1]: 0.00053182, [7] [b_1]: 0.00036702 [b_2]: 1.96e-05 [updatestate_depend_eliminate]: 1.583e-05 [updatestate_assign_eliminate]: 8.07e-06 [updatestate_loads_eliminate]: 9.94999e-06 [renormalize]: 5.69999e-07 [cse]: 6.974e-05 [optimize_parallel_all_gather_comm]: 3.073e-05 [overlap_param_gather]: 2.31e-06 [cconv]: 3.794e-05 [loop_unroll]: 0.00056669 [opt_after_cconv]: 0.00050663, [1] [Cycle 1]: 0.00049737, [7] [c_1]: 0.00034321 [parameter_eliminate]: 6.23e-06 [updatestate_depend_eliminate]: 1.755e-05 [updatestate_assign_eliminate]: 7.65e-06 [updatestate_loads_eliminate]: 1.029e-05 [cse]: 6.045e-05 [renormalize]: 3.10014e-07 [remove_dup_value]: 7.72e-05 [tuple_transform]: 0.0001716, [1] [Cycle 1]: 0.00016421, [4] [d_1]: 0.00012006 [none_parameter_eliminate]: 2.13002e-06 [renormalize]: 1.39989e-07 [switch_simplify]: 1.743e-05 [partial_unused_args_eliminate]: 2.28002e-06 [add_recomputation]: 0.00013453 [cse_after_recomputation]: 6.037e-05, [1] [Cycle 1]: 5.469e-05, [1] [cse]: 4.616e-05 [environ_conv]: 2.094e-05 [swap_dp_allreduce_reducescatter]: 1.208e-05 [bias_add_comm_swap]: 3.24001e-06 [label_micro_interleaved_index]: 6.66999e-06 [label_fine_grained_interleaved_index]: 2.74999e-06 [merge_cast_opt]: 1.53002e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.24001e-06 [assign_add_opt]: 1.99999e-06 [ForceFp32Comm]: 1.14e-06 [remove_cast_before_assign_add]: 1.69e-06 [full_micro_interleaved_order_control]: 2.36e-06 [reorder_send_recv_between_fp_bp]: 2.54001e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.08001e-06 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 1.25001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.91998e-06 [control_data_broadcast_order]: 2.833e-05 [grouped_pairwise_exchange_alltoall]: 1.71e-06 [offloading_packed_experts]: 7.4e-06 [overlap_recompute_and_grad_model_parallel]: 7.77002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.64998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.30999e-06 [overlap_recompute_comm]: 2.11e-06 [overlap_grad_ring_attention]: 8.61002e-06 [overlap_grad_flash_sp]: 3.81e-05 [begin_end_overlap_inline]: 7.50006e-07 [split_matmul_comm_elemetwise]: 2.81999e-06 [split_layernorm_comm]: 2.06e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00016107, [1] [Cycle 1]: 0.0001539, [6] [build]: 1.618e-05 [elim_shapecalc]: 2.498e-05 [elim_not_effective]: 2.974e-05 [opt_reshape]: 2.208e-05 [fold_const_symbol]: 2.465e-05 [renormalize]: 1.69995e-07 [detach_backward]: 2.40002e-06 [pipeline_parallel_scheduler]: 1.40999e-06 [auto_monad_reorder]: 4.751e-05 [get_jit_bprop_graph]: 1.81e-06 [rewriter_after_jit_bprop_graph]: 6.84001e-06 [opt_after_jit_grad]: 0.00070898 [validate]: 9.785e-05 Sums bootstrap : 0.000779s : 0.04% type_inference : 1.961127s : 91.82% event_method : 0.000020s : 0.00% auto_monad : 0.000389s : 0.02% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000040s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000032s : 0.00% optimize.rewriter_before_opt_a : 0.000082s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.00% optimize.opt_a.loop_unroll : 0.000037s : 0.00% optimize.opt_a.a_1 : 0.001326s : 0.06% optimize.opt_a.with_stream_mark : 0.000060s : 0.00% optimize.opt_a.recompute_prepare : 0.000040s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000621s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000090s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.00% optimize.opt_a.merge_send_recv : 0.000041s : 0.00% optimize.opt_a.auto_parallel : 0.000034s : 0.00% optimize.opt_a.parallel : 0.000046s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 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 : 0.000040s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.00% optimize.opt_a.virtual_dataset : 0.000057s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000054s : 0.00% optimize.opt_a.virtual_output : 0.000036s : 0.00% optimize.opt_a.merge_forward : 0.000017s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000063s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000053s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.00% optimize.opt_a.meta_fg_expand : 0.000012s : 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 : 0.000047s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.164316s : 7.69% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000116s : 0.01% optimize.opt_a.cse : 0.001316s : 0.06% optimize.opt_a.a_3 : 0.000240s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000191s : 0.01% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000847s : 0.04% optimize.opt_b.b_1 : 0.000367s : 0.02% optimize.opt_b.b_2 : 0.000020s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000070s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.00% optimize.loop_unroll : 0.000567s : 0.03% optimize.opt_after_cconv.c_1 : 0.000343s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000060s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000077s : 0.00% optimize.tuple_transform.d_1 : 0.000120s : 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 : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000135s : 0.01% optimize.cse_after_recomputation.cse : 0.000046s : 0.00% optimize.environ_conv : 0.000021s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 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 : 0.000002s : 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 : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000038s : 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 : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000030s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000022s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000048s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000709s : 0.03% validate : 0.000098s : 0.00% Time group info: ------[substitution.] 0.000295 96 3.65% : 0.000011s : 2: substitution.depend_value_elim 1.30% : 0.000004s : 8: substitution.elim_not_effective 1.19% : 0.000004s : 8: substitution.fold_const_symbol 4.42% : 0.000013s : 13: substitution.graph_param_transform 46.58% : 0.000138s : 1: substitution.inline 2.64% : 0.000008s : 16: substitution.j_node_and_user_rematch 7.89% : 0.000023s : 2: substitution.less_batch_normalization 1.89% : 0.000006s : 6: substitution.load_eliminater 1.03% : 0.000003s : 2: substitution.opt_reshape 4.21% : 0.000012s : 16: substitution.remove_not_recompute_node 2.64% : 0.000008s : 4: substitution.replace_old_param 10.05% : 0.000030s : 4: substitution.reshape_eliminate 6.42% : 0.000019s : 6: substitution.updatestate_pure_node_eliminater 6.08% : 0.000018s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.961019 2 99.69% : 1.954901s : 1: type_inference.infer 0.31% : 0.006118s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000136 1 100.00% : 0.000136s : 1: match.inline ------[predicate.] 0.000442 3002 0.92% : 0.000004s : 27: predicate.accumulaten_eliminater 1.11% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 0.73% : 0.000003s : 26: predicate.addn_check_dump 0.85% : 0.000004s : 27: predicate.addn_zero_filter 0.72% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.18% : 0.000010s : 53: predicate.arithmetic_simplify 0.91% : 0.000004s : 27: predicate.cast_eliminate 0.81% : 0.000004s : 26: predicate.check_bprop_eliminate 0.79% : 0.000004s : 26: predicate.compare_switch_simplify 0.24% : 0.000001s : 13: predicate.const_output_eliminate 0.82% : 0.000004s : 26: predicate.depend_value_elim 0.88% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 0.91% : 0.000004s : 27: predicate.dict_get_item_eliminator 0.80% : 0.000004s : 27: predicate.dict_set_item_eliminator 1.06% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.33% : 0.000001s : 13: predicate.elim_not_effective 0.52% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000005s : 40: predicate.environ_add_const_eliminate 1.09% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.11% : 0.000005s : 40: predicate.environ_get_depend_swap 1.94% : 0.000009s : 66: predicate.environ_get_eliminate 1.12% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.78% : 0.000003s : 28: predicate.exchange_switch_depend_value 1.30% : 0.000006s : 28: predicate.float_depend_g_call 0.77% : 0.000003s : 26: predicate.float_environ_get_switch 1.10% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.25% : 0.000001s : 13: predicate.fold_const_symbol 0.85% : 0.000004s : 26: predicate.get_grad_eliminate 0.29% : 0.000001s : 13: predicate.graph_param_transform 0.80% : 0.000004s : 26: predicate.incorporate_call 0.72% : 0.000003s : 26: predicate.incorporate_call_switch 5.48% : 0.000024s : 133: predicate.inline 1.02% : 0.000004s : 26: predicate.inline_without_move 0.44% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.27% : 0.000006s : 27: predicate.less_batch_normalization 1.73% : 0.000008s : 53: predicate.list_to_tuple_eliminator_ 2.37% : 0.000010s : 80: predicate.load_eliminater 0.95% : 0.000004s : 13: predicate.loop_unroll_after_grad 1.04% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.91% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.80% : 0.000004s : 26: predicate.merge_addn 0.86% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.81% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.79% : 0.000004s : 27: predicate.minmaximum_grad 1.25% : 0.000006s : 13: predicate.mutable_eliminate 0.54% : 0.000002s : 13: predicate.opt_reshape 0.55% : 0.000002s : 13: predicate.parallel_virtual_node 1.18% : 0.000005s : 28: predicate.partial_defer_inline 1.30% : 0.000006s : 40: predicate.partial_eliminate 0.79% : 0.000004s : 27: predicate.print_const_string_wrapper 0.78% : 0.000003s : 26: predicate.reduce_all_const_elim 1.11% : 0.000005s : 27: predicate.reduce_eliminate 2.38% : 0.000011s : 80: predicate.redundant_stop_gradient_eliminater 0.50% : 0.000002s : 26: predicate.remove_not_recompute_node 1.30% : 0.000006s : 53: predicate.replace_applicator 0.55% : 0.000002s : 26: predicate.replace_old_param 0.34% : 0.000001s : 13: predicate.reset_defer_inline 0.93% : 0.000004s : 27: predicate.reshape_eliminate 0.80% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.55% : 0.000002s : 13: predicate.row_tensor_eliminate 1.17% : 0.000005s : 26: predicate.same_eliminate 0.60% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.89% : 0.000004s : 26: predicate.shard_identity_eliminate 0.88% : 0.000004s : 26: predicate.special_op_eliminate 0.97% : 0.000004s : 26: predicate.specialize_transform 1.02% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000004s : 26: predicate.stack_unstack_eliminate 0.53% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.85% : 0.000004s : 28: predicate.switch_defer_inline 1.62% : 0.000007s : 54: predicate.switch_layer_defer_inline 3.54% : 0.000016s : 98: predicate.switch_simplify 0.83% : 0.000004s : 27: predicate.tile_eliminate 0.84% : 0.000004s : 27: predicate.transpose_eliminate 1.84% : 0.000008s : 53: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.58% : 0.000007s : 53: predicate.tuple_list_get_item_depend_reorder 2.85% : 0.000013s : 79: predicate.tuple_list_get_item_eliminator 1.73% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.62% : 0.000012s : 79: predicate.tuple_list_set_item_eliminator 1.77% : 0.000008s : 53: predicate.tuple_to_list_eliminator_ 2.34% : 0.000010s : 80: predicate.updatestate_pure_node_eliminater 3.47% : 0.000015s : 106: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 13: predicate.value_based_eliminate 0.89% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.88% : 0.000004s : 26: predicate.virtual_output_eliminate 0.43% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.59% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.014097 56 74.10% : 0.010446s : 53: func_graph_cloner_run.FuncGraphClonerGraph 25.90% : 0.003651s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.493218 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.29% : 0.007273s : 1: add_attr 0.29% : 0.007251s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000140s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000404s : 1: auto_monad 0.00% : 0.000052s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.03% : 0.000837s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.00% : 0.000063s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000027s : 1: environ_conv 0.00% : 0.000030s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 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% : 0.000010s : 1: label_micro_interleaved_index 0.02% : 0.000578s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.03% : 0.000860s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.11% : 0.002733s : 78: opt.transform.opt_a 0.01% : 0.000340s : 1: opt.transform.opt_after_cconv 0.00% : 0.000063s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000350s : 28: opt.transform.opt_b 0.01% : 0.000134s : 2: opt.transform.opt_trans_graph 0.00% : 0.000097s : 4: opt.transform.symbol_engine_opt 6.81% : 0.169731s : 1: opt_a 0.02% : 0.000511s : 1: opt_after_cconv 0.03% : 0.000721s : 1: opt_after_jit_grad 0.02% : 0.000545s : 1: opt_b 6.97% : 0.173680s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000042s : 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% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000045s : 1: pre_auto_parallel 0.00% : 0.000036s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000083s : 1: remove_dup_value 6.44% : 0.160447s : 1: renormalize.infer 0.15% : 0.003854s : 1: renormalize.specialize 0.00% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000198s : 1: rewriter_after_opt_a 0.00% : 0.000087s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000164s : 1: symbol_engine_optimizer 0.01% : 0.000175s : 1: tuple_transform 78.66% : 1.961163s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape1-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape1-1],max_mem:274.0M [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:42:35.369.410 [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 = 1.86349, [21] [bootstrap]: 0.00081899 [type_inference]: 1.57475 [event_method]: 1.88e-05 [auto_monad]: 0.00034028 [graph_reusing]: 5.61003e-06 [inline]: 3.38999e-06 [add_attr]: 0.147546, [1] [add_attr_with_inline]: 0.147529, [1] [Cycle 1]: 7.244e-05, [2] [tag_attr]: 2.155e-05 [meta_addattr_fg_expand]: 4.42e-06 [parallel-infer-symbol]: 4.74e-06 [pre_auto_parallel]: 3.879e-05 [insert-virtual-dataset]: 2.49999e-06 [parallel-infer-symbol-second]: 8.39995e-07 [dataset_repeat_opt]: 2.15002e-06 [pipeline_split]: 1.62999e-06 [optimize]: 0.138902, [53] [py_interpret_to_execute]: 2.874e-05 [rewriter_before_opt_a]: 8.172e-05 [opt_a]: 0.0153814, [2] [Cycle 1]: 0.0136859, [45] [expand_dump_flag]: 3.26001e-06 [switch_simplify]: 3.576e-05 [loop_unroll]: 2.055e-05 [a_1]: 0.0008602 [with_stream_mark]: 3.092e-05 [recompute_prepare]: 2.423e-05 [updatestate_depend_eliminate]: 1.254e-05 [updatestate_assign_eliminate]: 8.2e-06 [updatestate_loads_eliminate]: 1.082e-05 [parameter_eliminate]: 2.19001e-06 [a_2]: 0.00026315 [accelerated_algorithm]: 4.727e-05 [shard]: 2.21e-06 [meta_shard_fg_expand]: 4.14002e-06 [shard_inline]: 1.691e-05 [merge_send_recv]: 1.382e-05 [auto_parallel]: 1.365e-05 [parallel]: 3.268e-05 [flash_sp]: 1.413e-05 [merge_comm]: 8.35001e-06 [allreduce_fusion]: 8.06001e-06 [matmul_add_comm_reduction]: 1.788e-05 [allreduce_slice_to_reducescatter]: 1.21997e-06 [virtual_shard_identity]: 1.987e-05 [virtual_dataset]: 1.725e-05 [get_grad_eliminate_]: 1.929e-05 [virtual_output]: 1.76e-05 [merge_forward]: 9.05999e-06 [cell_reuse_recompute_pass]: 2.44001e-06 [offload_activation]: 1.842e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.368e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 2.908e-05 [set_forward_comm_id_for_comm_node_pass]: 9.86e-06 [meta_fg_expand]: 5.83002e-06 [flash_sp_send_recv_attached]: 6.53e-06 [receive_attached]: 2.67001e-06 [after_resolve]: 2.691e-05 [a_after_grad]: 2.981e-05 [renormalize]: 0.0108847 [add_forward_monad_depend]: 1.209e-05 [auto_monad_grad]: 2.78e-06 [auto_monad_eliminator]: 6.352e-05 [cse]: 0.00054236 [a_3]: 0.00014956 [Cycle 2]: 0.0016819, [45] [expand_dump_flag]: 2.69001e-06 [switch_simplify]: 2.126e-05 [loop_unroll]: 1.844e-05 [a_1]: 0.00050032 [with_stream_mark]: 2.586e-05 [recompute_prepare]: 1.703e-05 [updatestate_depend_eliminate]: 9.61e-06 [updatestate_assign_eliminate]: 8.54e-06 [updatestate_loads_eliminate]: 1.156e-05 [parameter_eliminate]: 2.66e-06 [a_2]: 0.00024241 [accelerated_algorithm]: 2.331e-05 [shard]: 2.36998e-06 [meta_shard_fg_expand]: 4.80001e-06 [shard_inline]: 1.806e-05 [merge_send_recv]: 1.476e-05 [auto_parallel]: 1.552e-05 [parallel]: 9.84999e-06 [flash_sp]: 4.47e-06 [merge_comm]: 9.44e-06 [allreduce_fusion]: 9.07999e-06 [matmul_add_comm_reduction]: 1.584e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.801e-05 [virtual_dataset]: 1.516e-05 [get_grad_eliminate_]: 1.507e-05 [virtual_output]: 1.512e-05 [merge_forward]: 8.22998e-06 [cell_reuse_recompute_pass]: 3.06001e-06 [offload_activation]: 1.709e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.929e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 2.417e-05 [set_forward_comm_id_for_comm_node_pass]: 8.27e-06 [meta_fg_expand]: 6.24001e-06 [flash_sp_send_recv_attached]: 1.77001e-06 [receive_attached]: 2.54001e-06 [after_resolve]: 2.158e-05 [a_after_grad]: 2.528e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.17001e-06 [auto_monad_grad]: 2.41998e-06 [auto_monad_eliminator]: 3.686e-05 [cse]: 0.00010489 [a_3]: 0.00010178 [py_interpret_to_execute_after_opt_a]: 2.684e-05 [slice_cell_reuse_recomputed_activation]: 2.76e-06 [rewriter_after_opt_a]: 0.00019655 [convert_after_rewriter]: 1.579e-05 [order_py_execute_after_rewriter]: 1.065e-05 [mutable_eliminate]: 0.120461 [opt_b]: 0.00069226, [1] [Cycle 1]: 0.0006812, [7] [b_1]: 0.00047373 [b_2]: 2.023e-05 [updatestate_depend_eliminate]: 2.189e-05 [updatestate_assign_eliminate]: 8.58001e-06 [updatestate_loads_eliminate]: 1.144e-05 [renormalize]: 5.10016e-07 [cse]: 9.5e-05 [optimize_parallel_all_gather_comm]: 4.3e-05 [overlap_param_gather]: 3.40003e-06 [cconv]: 4.247e-05 [loop_unroll]: 0.0006549 [opt_after_cconv]: 0.00024281, [1] [Cycle 1]: 0.00023272, [7] [c_1]: 0.00010702 [parameter_eliminate]: 5.92001e-06 [updatestate_depend_eliminate]: 1.504e-05 [updatestate_assign_eliminate]: 7.45e-06 [updatestate_loads_eliminate]: 9.00001e-06 [cse]: 5.016e-05 [renormalize]: 1.80007e-07 [remove_dup_value]: 7.316e-05 [tuple_transform]: 0.00015978, [1] [Cycle 1]: 0.00015419, [4] [d_1]: 0.00011178 [none_parameter_eliminate]: 2.02999e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.794e-05 [partial_unused_args_eliminate]: 1.85001e-06 [add_recomputation]: 0.00012181 [cse_after_recomputation]: 5.593e-05, [1] [Cycle 1]: 5.045e-05, [1] [cse]: 4.345e-05 [environ_conv]: 1.907e-05 [swap_dp_allreduce_reducescatter]: 1.39e-05 [bias_add_comm_swap]: 3.21001e-06 [label_micro_interleaved_index]: 6.43998e-06 [label_fine_grained_interleaved_index]: 2.53003e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.17999e-06 [micro_interleaved_order_control]: 2.41998e-06 [assign_add_opt]: 1.35001e-06 [ForceFp32Comm]: 8.50006e-07 [remove_cast_before_assign_add]: 9.30013e-07 [full_micro_interleaved_order_control]: 2.37001e-06 [reorder_send_recv_between_fp_bp]: 2.88e-06 [comm_op_add_attrs]: 1.02998e-06 [add_comm_op_reuse_tag]: 1.27e-06 [interleave_split_concat_branches]: 1.17999e-06 [interleave_parallel_branches]: 1.05001e-06 [overlap_opt_shard_in_pipeline]: 2.36e-06 [overlap_opt_shard_grad_in_pipeline]: 1.99e-06 [control_data_broadcast_order]: 2.619e-05 [grouped_pairwise_exchange_alltoall]: 1.75001e-06 [offloading_packed_experts]: 7.41001e-06 [overlap_recompute_and_grad_model_parallel]: 7.51999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.25999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.32e-06 [overlap_recompute_comm]: 1.94e-06 [overlap_grad_ring_attention]: 7.97e-06 [overlap_grad_flash_sp]: 4.063e-05 [begin_end_overlap_inline]: 6.19999e-07 [split_matmul_comm_elemetwise]: 2.58003e-06 [split_layernorm_comm]: 1.85001e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00015626, [1] [Cycle 1]: 0.00014972, [6] [build]: 1.802e-05 [elim_shapecalc]: 2.337e-05 [elim_not_effective]: 2.888e-05 [opt_reshape]: 2.307e-05 [fold_const_symbol]: 2.38e-05 [renormalize]: 1.8999e-07 [detach_backward]: 2.22001e-06 [pipeline_parallel_scheduler]: 1.43002e-06 [auto_monad_reorder]: 4.504e-05 [get_jit_bprop_graph]: 1.86998e-06 [rewriter_after_jit_bprop_graph]: 7.15998e-06 [opt_after_jit_grad]: 0.00064823 [validate]: 0.00010023 Sums bootstrap : 0.000819s : 0.05% type_inference : 1.574748s : 91.84% event_method : 0.000019s : 0.00% auto_monad : 0.000340s : 0.02% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000022s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000039s : 0.00% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000029s : 0.00% optimize.rewriter_before_opt_a : 0.000082s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000057s : 0.00% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001361s : 0.08% optimize.opt_a.with_stream_mark : 0.000057s : 0.00% optimize.opt_a.recompute_prepare : 0.000041s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000506s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000071s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000035s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000029s : 0.00% optimize.opt_a.parallel : 0.000043s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000018s : 0.00% optimize.opt_a.allreduce_fusion : 0.000017s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000034s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000038s : 0.00% optimize.opt_a.virtual_dataset : 0.000032s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000034s : 0.00% optimize.opt_a.virtual_output : 0.000033s : 0.00% optimize.opt_a.merge_forward : 0.000017s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000063s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000053s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.00% optimize.opt_a.meta_fg_expand : 0.000012s : 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 : 0.000048s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.010885s : 0.63% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000100s : 0.01% optimize.opt_a.cse : 0.000647s : 0.04% optimize.opt_a.a_3 : 0.000251s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000197s : 0.01% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.120461s : 7.03% optimize.opt_b.b_1 : 0.000474s : 0.03% optimize.opt_b.b_2 : 0.000020s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000095s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000043s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000655s : 0.04% optimize.opt_after_cconv.c_1 : 0.000107s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.cse : 0.000050s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000073s : 0.00% optimize.tuple_transform.d_1 : 0.000112s : 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 : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000122s : 0.01% optimize.cse_after_recomputation.cse : 0.000043s : 0.00% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000026s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000041s : 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 : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000029s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000023s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000045s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000648s : 0.04% validate : 0.000100s : 0.01% Time group info: ------[substitution.] 0.000290 96 3.84% : 0.000011s : 2: substitution.depend_value_elim 1.17% : 0.000003s : 8: substitution.elim_not_effective 1.08% : 0.000003s : 8: substitution.fold_const_symbol 3.86% : 0.000011s : 13: substitution.graph_param_transform 43.42% : 0.000126s : 1: substitution.inline 3.15% : 0.000009s : 16: substitution.j_node_and_user_rematch 8.12% : 0.000024s : 2: substitution.less_batch_normalization 2.21% : 0.000006s : 6: substitution.load_eliminater 1.10% : 0.000003s : 2: substitution.opt_reshape 3.98% : 0.000012s : 16: substitution.remove_not_recompute_node 2.63% : 0.000008s : 4: substitution.replace_old_param 9.68% : 0.000028s : 4: substitution.reshape_eliminate 9.06% : 0.000026s : 6: substitution.updatestate_pure_node_eliminater 6.68% : 0.000019s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.574636 2 99.68% : 1.569660s : 1: type_inference.infer 0.32% : 0.004976s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000125 1 100.00% : 0.000125s : 1: match.inline ------[predicate.] 0.000474 3002 0.86% : 0.000004s : 27: predicate.accumulaten_eliminater 0.97% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 0.71% : 0.000003s : 26: predicate.addn_check_dump 1.02% : 0.000005s : 27: predicate.addn_zero_filter 0.74% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.05% : 0.000010s : 53: predicate.arithmetic_simplify 0.86% : 0.000004s : 27: predicate.cast_eliminate 0.81% : 0.000004s : 26: predicate.check_bprop_eliminate 0.75% : 0.000004s : 26: predicate.compare_switch_simplify 0.24% : 0.000001s : 13: predicate.const_output_eliminate 3.09% : 0.000015s : 26: predicate.depend_value_elim 0.77% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 0.88% : 0.000004s : 27: predicate.dict_get_item_eliminator 0.74% : 0.000004s : 27: predicate.dict_set_item_eliminator 1.04% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 13: predicate.elim_not_effective 0.50% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.08% : 0.000005s : 40: predicate.environ_add_const_eliminate 1.07% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.05% : 0.000005s : 40: predicate.environ_get_depend_swap 2.02% : 0.000010s : 66: predicate.environ_get_eliminate 1.06% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.78% : 0.000004s : 28: predicate.exchange_switch_depend_value 1.29% : 0.000006s : 28: predicate.float_depend_g_call 0.74% : 0.000004s : 26: predicate.float_environ_get_switch 1.16% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 13: predicate.fold_const_symbol 0.81% : 0.000004s : 26: predicate.get_grad_eliminate 0.27% : 0.000001s : 13: predicate.graph_param_transform 0.77% : 0.000004s : 26: predicate.incorporate_call 0.71% : 0.000003s : 26: predicate.incorporate_call_switch 5.29% : 0.000025s : 133: predicate.inline 0.90% : 0.000004s : 26: predicate.inline_without_move 0.42% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.16% : 0.000006s : 27: predicate.less_batch_normalization 1.82% : 0.000009s : 53: predicate.list_to_tuple_eliminator_ 2.23% : 0.000011s : 80: predicate.load_eliminater 1.26% : 0.000006s : 13: predicate.loop_unroll_after_grad 1.03% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.72% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.79% : 0.000004s : 26: predicate.merge_addn 0.76% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.81% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.73% : 0.000003s : 27: predicate.minmaximum_grad 2.09% : 0.000010s : 13: predicate.mutable_eliminate 0.59% : 0.000003s : 13: predicate.opt_reshape 0.55% : 0.000003s : 13: predicate.parallel_virtual_node 1.12% : 0.000005s : 28: predicate.partial_defer_inline 1.26% : 0.000006s : 40: predicate.partial_eliminate 0.80% : 0.000004s : 27: predicate.print_const_string_wrapper 0.83% : 0.000004s : 26: predicate.reduce_all_const_elim 0.95% : 0.000004s : 27: predicate.reduce_eliminate 2.21% : 0.000010s : 80: predicate.redundant_stop_gradient_eliminater 0.51% : 0.000002s : 26: predicate.remove_not_recompute_node 1.32% : 0.000006s : 53: predicate.replace_applicator 0.50% : 0.000002s : 26: predicate.replace_old_param 0.43% : 0.000002s : 13: predicate.reset_defer_inline 0.99% : 0.000005s : 27: predicate.reshape_eliminate 0.92% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.49% : 0.000002s : 13: predicate.row_tensor_eliminate 1.11% : 0.000005s : 26: predicate.same_eliminate 0.51% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.92% : 0.000004s : 26: predicate.shard_identity_eliminate 0.89% : 0.000004s : 26: predicate.special_op_eliminate 0.87% : 0.000004s : 26: predicate.specialize_transform 1.04% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.87% : 0.000004s : 26: predicate.stack_unstack_eliminate 0.45% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.83% : 0.000004s : 28: predicate.switch_defer_inline 1.60% : 0.000008s : 54: predicate.switch_layer_defer_inline 3.41% : 0.000016s : 98: predicate.switch_simplify 0.81% : 0.000004s : 27: predicate.tile_eliminate 0.83% : 0.000004s : 27: predicate.transpose_eliminate 1.57% : 0.000007s : 53: predicate.tuple_list_convert_item_index_to_positive 1.66% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.51% : 0.000007s : 53: predicate.tuple_list_get_item_depend_reorder 2.96% : 0.000014s : 79: predicate.tuple_list_get_item_eliminator 1.65% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.44% : 0.000012s : 79: predicate.tuple_list_set_item_eliminator 1.52% : 0.000007s : 53: predicate.tuple_to_list_eliminator_ 2.24% : 0.000011s : 80: predicate.updatestate_pure_node_eliminater 3.49% : 0.000017s : 106: predicate.updatestate_useless_node_eliminater 0.44% : 0.000002s : 13: predicate.value_based_eliminate 0.82% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.81% : 0.000004s : 26: predicate.virtual_output_eliminate 0.36% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.58% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.016546 56 78.63% : 0.013010s : 53: func_graph_cloner_run.FuncGraphClonerGraph 21.37% : 0.003536s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.164105 192 0.00% : 0.000003s : 1: ForceFp32Comm 6.82% : 0.147554s : 1: add_attr 6.82% : 0.147534s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000127s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000352s : 1: auto_monad 0.00% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000880s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000029s : 1: control_data_broadcast_order 0.00% : 0.000020s : 1: convert_after_rewriter 0.00% : 0.000059s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000024s : 1: environ_conv 0.00% : 0.000027s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000005s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000665s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 5.57% : 0.120481s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000061s : 1: opt.transform.mutable_eliminate 0.12% : 0.002597s : 78: opt.transform.opt_a 0.00% : 0.000105s : 1: opt.transform.opt_after_cconv 0.00% : 0.000061s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000453s : 28: opt.transform.opt_b 0.01% : 0.000127s : 2: opt.transform.opt_trans_graph 0.00% : 0.000095s : 4: opt.transform.symbol_engine_opt 0.71% : 0.015385s : 1: opt_a 0.01% : 0.000247s : 1: opt_after_cconv 0.03% : 0.000662s : 1: opt_after_jit_grad 0.03% : 0.000698s : 1: opt_b 6.42% : 0.138909s : 1: optimize 0.00% : 0.000048s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.00% : 0.000044s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000043s : 1: pre_auto_parallel 0.00% : 0.000033s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000003s : 1: remove_cast_before_assign_add 0.00% : 0.000078s : 1: remove_dup_value 0.32% : 0.006915s : 1: renormalize.infer 0.18% : 0.003953s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000204s : 1: rewriter_after_opt_a 0.00% : 0.000086s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000159s : 1: symbol_engine_optimizer 0.01% : 0.000163s : 1: tuple_transform 72.77% : 1.574786s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape1-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape1-16],max_mem:272.0M [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:43:08.988.166 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 0.850439, [21] [bootstrap]: 0.00084408 [type_inference]: 0.795958 [event_method]: 1.833e-05 [auto_monad]: 0.00035038 [graph_reusing]: 6.33e-06 [inline]: 3.31001e-06 [add_attr]: 0.019666, [1] [add_attr_with_inline]: 0.0196463, [1] [Cycle 1]: 7.117e-05, [2] [tag_attr]: 2.359e-05 [meta_addattr_fg_expand]: 4.02e-06 [parallel-infer-symbol]: 4.82e-06 [pre_auto_parallel]: 4.172e-05 [insert-virtual-dataset]: 2.50002e-06 [parallel-infer-symbol-second]: 7.2e-07 [dataset_repeat_opt]: 2.07001e-06 [pipeline_split]: 1.54e-06 [optimize]: 0.0323517, [53] [py_interpret_to_execute]: 3.419e-05 [rewriter_before_opt_a]: 8.302e-05 [opt_a]: 0.016216, [2] [Cycle 1]: 0.0145663, [45] [expand_dump_flag]: 2.87002e-06 [switch_simplify]: 3.442e-05 [loop_unroll]: 2.001e-05 [a_1]: 0.00086834 [with_stream_mark]: 2.958e-05 [recompute_prepare]: 2.432e-05 [updatestate_depend_eliminate]: 1.159e-05 [updatestate_assign_eliminate]: 8.23001e-06 [updatestate_loads_eliminate]: 1.138e-05 [parameter_eliminate]: 2.12001e-06 [a_2]: 0.00025569 [accelerated_algorithm]: 4.279e-05 [shard]: 2.32001e-06 [meta_shard_fg_expand]: 3.5e-06 [shard_inline]: 1.727e-05 [merge_send_recv]: 1.476e-05 [auto_parallel]: 1.229e-05 [parallel]: 3.132e-05 [flash_sp]: 1.31e-05 [merge_comm]: 8.67e-06 [allreduce_fusion]: 8.18001e-06 [matmul_add_comm_reduction]: 1.76e-05 [allreduce_slice_to_reducescatter]: 8.29983e-07 [virtual_shard_identity]: 2.066e-05 [virtual_dataset]: 1.905e-05 [get_grad_eliminate_]: 1.887e-05 [virtual_output]: 1.773e-05 [merge_forward]: 9.07001e-06 [cell_reuse_recompute_pass]: 1.82001e-06 [offload_activation]: 1.807e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.646e-05 [merge_recompute_call_nodes]: 1.77001e-06 [before_grad]: 3.361e-05 [set_forward_comm_id_for_comm_node_pass]: 9.52001e-06 [meta_fg_expand]: 6.01998e-06 [flash_sp_send_recv_attached]: 5.88998e-06 [receive_attached]: 2.51e-06 [after_resolve]: 2.908e-05 [a_after_grad]: 3.629e-05 [renormalize]: 0.0115999 [add_forward_monad_depend]: 1.233e-05 [auto_monad_grad]: 2.91e-06 [auto_monad_eliminator]: 6.409e-05 [cse]: 0.00070486 [a_3]: 0.0001411 [Cycle 2]: 0.00163497, [45] [expand_dump_flag]: 3.16999e-06 [switch_simplify]: 1.973e-05 [loop_unroll]: 1.748e-05 [a_1]: 0.00046107 [with_stream_mark]: 2.815e-05 [recompute_prepare]: 1.773e-05 [updatestate_depend_eliminate]: 9.53002e-06 [updatestate_assign_eliminate]: 7.85998e-06 [updatestate_loads_eliminate]: 1.047e-05 [parameter_eliminate]: 2.31e-06 [a_2]: 0.00022114 [accelerated_algorithm]: 2.326e-05 [shard]: 2.99999e-06 [meta_shard_fg_expand]: 5.25999e-06 [shard_inline]: 1.551e-05 [merge_send_recv]: 1.394e-05 [auto_parallel]: 1.515e-05 [parallel]: 1.022e-05 [flash_sp]: 4.13999e-06 [merge_comm]: 8.28001e-06 [allreduce_fusion]: 8.61002e-06 [matmul_add_comm_reduction]: 1.703e-05 [allreduce_slice_to_reducescatter]: 1.28002e-06 [virtual_shard_identity]: 1.82e-05 [virtual_dataset]: 1.503e-05 [get_grad_eliminate_]: 1.535e-05 [virtual_output]: 1.559e-05 [merge_forward]: 8.58001e-06 [cell_reuse_recompute_pass]: 3.07002e-06 [offload_activation]: 1.683e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.79e-05 [merge_recompute_call_nodes]: 1.40001e-06 [before_grad]: 2.45e-05 [set_forward_comm_id_for_comm_node_pass]: 8.85001e-06 [meta_fg_expand]: 6.54999e-06 [flash_sp_send_recv_attached]: 1.63002e-06 [receive_attached]: 2.99999e-06 [after_resolve]: 2.282e-05 [a_after_grad]: 2.518e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.08e-06 [auto_monad_grad]: 3.18e-06 [auto_monad_eliminator]: 4.853e-05 [cse]: 0.00010576 [a_3]: 0.00010419 [py_interpret_to_execute_after_opt_a]: 2.613e-05 [slice_cell_reuse_recomputed_activation]: 2.47001e-06 [rewriter_after_opt_a]: 0.00020175 [convert_after_rewriter]: 1.402e-05 [order_py_execute_after_rewriter]: 1e-05 [mutable_eliminate]: 0.00082998 [opt_b]: 0.00053646, [1] [Cycle 1]: 0.00052784, [7] [b_1]: 0.00036597 [b_2]: 1.864e-05 [updatestate_depend_eliminate]: 1.457e-05 [updatestate_assign_eliminate]: 7.60998e-06 [updatestate_loads_eliminate]: 9.69e-06 [renormalize]: 8.90024e-07 [cse]: 6.919e-05 [optimize_parallel_all_gather_comm]: 3.16e-05 [overlap_param_gather]: 1.96e-06 [cconv]: 3.696e-05 [loop_unroll]: 0.0129795 [opt_after_cconv]: 0.0002934, [1] [Cycle 1]: 0.00028105, [7] [c_1]: 0.00011711 [parameter_eliminate]: 7.55e-06 [updatestate_depend_eliminate]: 2.041e-05 [updatestate_assign_eliminate]: 7.58999e-06 [updatestate_loads_eliminate]: 1.233e-05 [cse]: 7.694e-05 [renormalize]: 7.50006e-07 [remove_dup_value]: 7.838e-05 [tuple_transform]: 0.0001661, [1] [Cycle 1]: 0.00016033, [4] [d_1]: 0.00011783 [none_parameter_eliminate]: 2.33002e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 1.782e-05 [partial_unused_args_eliminate]: 2.22001e-06 [add_recomputation]: 0.00013246 [cse_after_recomputation]: 6.216e-05, [1] [Cycle 1]: 5.612e-05, [1] [cse]: 4.86e-05 [environ_conv]: 1.974e-05 [swap_dp_allreduce_reducescatter]: 1.227e-05 [bias_add_comm_swap]: 3.39001e-06 [label_micro_interleaved_index]: 7.53e-06 [label_fine_grained_interleaved_index]: 2.69001e-06 [merge_cast_opt]: 1.47001e-06 [slice_recompute_activation]: 2.20002e-06 [micro_interleaved_order_control]: 2.58e-06 [assign_add_opt]: 1.79e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.03001e-06 [full_micro_interleaved_order_control]: 2.60997e-06 [reorder_send_recv_between_fp_bp]: 2.64999e-06 [comm_op_add_attrs]: 1.26002e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.39e-06 [overlap_opt_shard_in_pipeline]: 1.48002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.76998e-06 [control_data_broadcast_order]: 2.813e-05 [grouped_pairwise_exchange_alltoall]: 1.55999e-06 [offloading_packed_experts]: 6.80998e-06 [overlap_recompute_and_grad_model_parallel]: 7.04001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.14e-06 [overlap_recompute_allgather_and_fa_grad]: 1.30999e-06 [overlap_recompute_comm]: 2.54001e-06 [overlap_grad_ring_attention]: 7.56999e-06 [overlap_grad_flash_sp]: 3.728e-05 [begin_end_overlap_inline]: 4.99975e-07 [split_matmul_comm_elemetwise]: 2.49999e-06 [split_layernorm_comm]: 1.79e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00016453, [1] [Cycle 1]: 0.00015774, [6] [build]: 1.775e-05 [elim_shapecalc]: 2.601e-05 [elim_not_effective]: 3.112e-05 [opt_reshape]: 2.305e-05 [fold_const_symbol]: 2.486e-05 [renormalize]: 3.69997e-07 [detach_backward]: 2.21e-06 [pipeline_parallel_scheduler]: 1.64e-06 [auto_monad_reorder]: 4.744e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 6.71e-06 [opt_after_jit_grad]: 0.0007949 [validate]: 0.00010076 Sums bootstrap : 0.000844s : 0.10% type_inference : 0.795958s : 95.95% event_method : 0.000018s : 0.00% auto_monad : 0.000350s : 0.04% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000042s : 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 : 0.000034s : 0.00% optimize.rewriter_before_opt_a : 0.000083s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000054s : 0.01% optimize.opt_a.loop_unroll : 0.000037s : 0.00% optimize.opt_a.a_1 : 0.001329s : 0.16% optimize.opt_a.with_stream_mark : 0.000058s : 0.01% optimize.opt_a.recompute_prepare : 0.000042s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000477s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000066s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000027s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.01% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000017s : 0.00% optimize.opt_a.allreduce_fusion : 0.000017s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.00% optimize.opt_a.virtual_dataset : 0.000034s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000034s : 0.00% optimize.opt_a.virtual_output : 0.000033s : 0.00% optimize.opt_a.merge_forward : 0.000018s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000035s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000064s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000058s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.00% optimize.opt_a.meta_fg_expand : 0.000013s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000052s : 0.01% optimize.opt_a.a_after_grad : 0.000061s : 0.01% optimize.opt_a.renormalize : 0.011600s : 1.40% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000113s : 0.01% optimize.opt_a.cse : 0.000811s : 0.10% optimize.opt_a.a_3 : 0.000245s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000202s : 0.02% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000830s : 0.10% optimize.opt_b.b_1 : 0.000366s : 0.04% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000069s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.012979s : 1.56% optimize.opt_after_cconv.c_1 : 0.000117s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.cse : 0.000077s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000078s : 0.01% optimize.tuple_transform.d_1 : 0.000118s : 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 : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000132s : 0.02% optimize.cse_after_recomputation.cse : 0.000049s : 0.01% optimize.environ_conv : 0.000020s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 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 : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000037s : 0.00% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000023s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000047s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000795s : 0.10% validate : 0.000101s : 0.01% Time group info: ------[substitution.] 0.000293 96 4.12% : 0.000012s : 2: substitution.depend_value_elim 1.20% : 0.000004s : 8: substitution.elim_not_effective 1.15% : 0.000003s : 8: substitution.fold_const_symbol 4.11% : 0.000012s : 13: substitution.graph_param_transform 44.64% : 0.000131s : 1: substitution.inline 2.89% : 0.000008s : 16: substitution.j_node_and_user_rematch 7.62% : 0.000022s : 2: substitution.less_batch_normalization 2.12% : 0.000006s : 6: substitution.load_eliminater 1.07% : 0.000003s : 2: substitution.opt_reshape 4.14% : 0.000012s : 16: substitution.remove_not_recompute_node 2.80% : 0.000008s : 4: substitution.replace_old_param 9.68% : 0.000028s : 4: substitution.reshape_eliminate 7.78% : 0.000023s : 6: substitution.updatestate_pure_node_eliminater 6.69% : 0.000020s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.795859 2 99.37% : 0.790876s : 1: type_inference.infer 0.63% : 0.004983s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000129 1 100.00% : 0.000129s : 1: match.inline ------[predicate.] 0.000442 3002 0.90% : 0.000004s : 27: predicate.accumulaten_eliminater 0.89% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.74% : 0.000003s : 26: predicate.addn_check_dump 0.87% : 0.000004s : 27: predicate.addn_zero_filter 0.76% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.10% : 0.000009s : 53: predicate.arithmetic_simplify 0.86% : 0.000004s : 27: predicate.cast_eliminate 0.81% : 0.000004s : 26: predicate.check_bprop_eliminate 0.78% : 0.000003s : 26: predicate.compare_switch_simplify 0.25% : 0.000001s : 13: predicate.const_output_eliminate 0.83% : 0.000004s : 26: predicate.depend_value_elim 0.83% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 0.90% : 0.000004s : 27: predicate.dict_get_item_eliminator 0.81% : 0.000004s : 27: predicate.dict_set_item_eliminator 1.12% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 13: predicate.elim_not_effective 0.48% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000005s : 40: predicate.environ_add_const_eliminate 1.21% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.19% : 0.000005s : 40: predicate.environ_get_depend_swap 1.90% : 0.000008s : 66: predicate.environ_get_eliminate 1.06% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.87% : 0.000004s : 28: predicate.exchange_switch_depend_value 1.36% : 0.000006s : 28: predicate.float_depend_g_call 0.81% : 0.000004s : 26: predicate.float_environ_get_switch 1.18% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 13: predicate.fold_const_symbol 0.83% : 0.000004s : 26: predicate.get_grad_eliminate 0.29% : 0.000001s : 13: predicate.graph_param_transform 0.77% : 0.000003s : 26: predicate.incorporate_call 0.69% : 0.000003s : 26: predicate.incorporate_call_switch 5.63% : 0.000025s : 133: predicate.inline 1.05% : 0.000005s : 26: predicate.inline_without_move 0.43% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.29% : 0.000006s : 27: predicate.less_batch_normalization 1.90% : 0.000008s : 53: predicate.list_to_tuple_eliminator_ 2.29% : 0.000010s : 80: predicate.load_eliminater 1.78% : 0.000008s : 13: predicate.loop_unroll_after_grad 1.03% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.74% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.78% : 0.000003s : 26: predicate.merge_addn 0.74% : 0.000003s : 26: predicate.micro_step_allgather_replace 0.77% : 0.000003s : 26: predicate.mini_step_allgather_replace 0.75% : 0.000003s : 27: predicate.minmaximum_grad 1.05% : 0.000005s : 13: predicate.mutable_eliminate 0.55% : 0.000002s : 13: predicate.opt_reshape 0.48% : 0.000002s : 13: predicate.parallel_virtual_node 1.15% : 0.000005s : 28: predicate.partial_defer_inline 1.28% : 0.000006s : 40: predicate.partial_eliminate 0.78% : 0.000003s : 27: predicate.print_const_string_wrapper 0.84% : 0.000004s : 26: predicate.reduce_all_const_elim 1.08% : 0.000005s : 27: predicate.reduce_eliminate 2.31% : 0.000010s : 80: predicate.redundant_stop_gradient_eliminater 0.48% : 0.000002s : 26: predicate.remove_not_recompute_node 1.32% : 0.000006s : 53: predicate.replace_applicator 0.54% : 0.000002s : 26: predicate.replace_old_param 0.50% : 0.000002s : 13: predicate.reset_defer_inline 0.94% : 0.000004s : 27: predicate.reshape_eliminate 0.83% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.49% : 0.000002s : 13: predicate.row_tensor_eliminate 1.08% : 0.000005s : 26: predicate.same_eliminate 0.63% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.91% : 0.000004s : 26: predicate.shard_identity_eliminate 1.00% : 0.000004s : 26: predicate.special_op_eliminate 0.88% : 0.000004s : 26: predicate.specialize_transform 1.10% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000004s : 26: predicate.stack_unstack_eliminate 0.47% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.88% : 0.000004s : 28: predicate.switch_defer_inline 1.61% : 0.000007s : 54: predicate.switch_layer_defer_inline 3.36% : 0.000015s : 98: predicate.switch_simplify 0.82% : 0.000004s : 27: predicate.tile_eliminate 0.87% : 0.000004s : 27: predicate.transpose_eliminate 1.70% : 0.000008s : 53: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.74% : 0.000008s : 53: predicate.tuple_list_get_item_depend_reorder 2.79% : 0.000012s : 79: predicate.tuple_list_get_item_eliminator 1.72% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.74% : 0.000012s : 79: predicate.tuple_list_set_item_eliminator 1.69% : 0.000007s : 53: predicate.tuple_to_list_eliminator_ 2.28% : 0.000010s : 80: predicate.updatestate_pure_node_eliminater 3.40% : 0.000015s : 106: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 13: predicate.value_based_eliminate 0.86% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.84% : 0.000004s : 26: predicate.virtual_output_eliminate 0.39% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.54% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.012395 56 81.52% : 0.010104s : 53: func_graph_cloner_run.FuncGraphClonerGraph 18.48% : 0.002291s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.917260 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.14% : 0.019673s : 1: add_attr 2.14% : 0.019651s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000138s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000362s : 1: auto_monad 0.01% : 0.000053s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.10% : 0.000906s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000006s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000065s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000025s : 1: environ_conv 0.00% : 0.000028s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 1.42% : 0.012996s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.09% : 0.000843s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000049s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000035s : 1: opt.transform.mutable_eliminate 0.28% : 0.002538s : 78: opt.transform.opt_a 0.01% : 0.000115s : 1: opt.transform.opt_after_cconv 0.01% : 0.000129s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000350s : 28: opt.transform.opt_b 0.01% : 0.000132s : 2: opt.transform.opt_trans_graph 0.01% : 0.000100s : 4: opt.transform.symbol_engine_opt 1.77% : 0.016220s : 1: opt_a 0.03% : 0.000298s : 1: opt_after_cconv 0.09% : 0.000810s : 1: opt_after_jit_grad 0.06% : 0.000541s : 1: opt_b 3.53% : 0.032359s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000041s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000047s : 1: pre_auto_parallel 0.00% : 0.000038s : 1: py_interpret_to_execute 0.00% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000084s : 1: remove_dup_value 0.97% : 0.008884s : 1: renormalize.infer 0.29% : 0.002697s : 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% : 0.000209s : 1: rewriter_after_opt_a 0.01% : 0.000088s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000167s : 1: symbol_engine_optimizer 0.02% : 0.000169s : 1: tuple_transform 86.78% : 0.795987s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape2-1] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape2-1],max_mem:352.0M [WARNING] ME(171825:281473262071600,MainProcess):2026-01-29-17:43:59.728.564 [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 = 0.306262, [21] [bootstrap]: 0.00067116 [type_inference]: 0.278312 [event_method]: 1.808e-05 [auto_monad]: 0.00034506 [graph_reusing]: 6.61e-06 [inline]: 3.9e-06 [add_attr]: 0.00670551, [1] [add_attr_with_inline]: 0.00668811, [1] [Cycle 1]: 7.167e-05, [2] [tag_attr]: 2.036e-05 [meta_addattr_fg_expand]: 4.57e-06 [parallel-infer-symbol]: 5.61e-06 [pre_auto_parallel]: 3.819e-05 [insert-virtual-dataset]: 2.89999e-06 [parallel-infer-symbol-second]: 8.09989e-07 [dataset_repeat_opt]: 1.80001e-06 [pipeline_split]: 1.56002e-06 [optimize]: 0.0190468, [53] [py_interpret_to_execute]: 3.092e-05 [rewriter_before_opt_a]: 8.057e-05 [opt_a]: 0.0150844, [2] [Cycle 1]: 0.0123441, [45] [expand_dump_flag]: 2.98e-06 [switch_simplify]: 3.489e-05 [loop_unroll]: 2.091e-05 [a_1]: 0.00089324 [with_stream_mark]: 2.623e-05 [recompute_prepare]: 2.338e-05 [updatestate_depend_eliminate]: 1.148e-05 [updatestate_assign_eliminate]: 8.59e-06 [updatestate_loads_eliminate]: 1.169e-05 [parameter_eliminate]: 2.19999e-06 [a_2]: 0.00026792 [accelerated_algorithm]: 4.259e-05 [shard]: 2.12999e-06 [meta_shard_fg_expand]: 3.88999e-06 [shard_inline]: 1.759e-05 [merge_send_recv]: 1.44e-05 [auto_parallel]: 1.284e-05 [parallel]: 3.44e-05 [flash_sp]: 1.195e-05 [merge_comm]: 9.59999e-06 [allreduce_fusion]: 8.68001e-06 [matmul_add_comm_reduction]: 1.743e-05 [allreduce_slice_to_reducescatter]: 7.2e-07 [virtual_shard_identity]: 1.928e-05 [virtual_dataset]: 1.878e-05 [get_grad_eliminate_]: 2.09e-05 [virtual_output]: 1.991e-05 [merge_forward]: 8.94e-06 [cell_reuse_recompute_pass]: 2.28002e-06 [offload_activation]: 1.706e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.431e-05 [merge_recompute_call_nodes]: 1.77001e-06 [before_grad]: 3.003e-05 [set_forward_comm_id_for_comm_node_pass]: 9.25999e-06 [meta_fg_expand]: 5.96998e-06 [flash_sp_send_recv_attached]: 6.34001e-06 [receive_attached]: 2.63e-06 [after_resolve]: 2.907e-05 [a_after_grad]: 2.95e-05 [renormalize]: 0.0098862 [add_forward_monad_depend]: 1.106e-05 [auto_monad_grad]: 3.16999e-06 [auto_monad_eliminator]: 6.837e-05 [cse]: 0.00018443 [a_3]: 0.00013178 [Cycle 2]: 0.00272521, [45] [expand_dump_flag]: 2.17001e-06 [switch_simplify]: 1.887e-05 [loop_unroll]: 1.637e-05 [a_1]: 0.00045799 [with_stream_mark]: 2.18e-05 [recompute_prepare]: 2.022e-05 [updatestate_depend_eliminate]: 9.28002e-06 [updatestate_assign_eliminate]: 7.58001e-06 [updatestate_loads_eliminate]: 1.009e-05 [parameter_eliminate]: 1.97999e-06 [a_2]: 0.0002225 [accelerated_algorithm]: 2.478e-05 [shard]: 2.39999e-06 [meta_shard_fg_expand]: 4.03001e-06 [shard_inline]: 1.543e-05 [merge_send_recv]: 1.544e-05 [auto_parallel]: 1.465e-05 [parallel]: 9.25001e-06 [flash_sp]: 4.87e-06 [merge_comm]: 9.36998e-06 [allreduce_fusion]: 9.25001e-06 [matmul_add_comm_reduction]: 1.637e-05 [allreduce_slice_to_reducescatter]: 9.70002e-07 [virtual_shard_identity]: 2.024e-05 [virtual_dataset]: 1.583e-05 [get_grad_eliminate_]: 1.557e-05 [virtual_output]: 1.607e-05 [merge_forward]: 9.25999e-06 [cell_reuse_recompute_pass]: 3.45e-06 [offload_activation]: 1.693e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.251e-05 [merge_recompute_call_nodes]: 1.67999e-06 [before_grad]: 2.719e-05 [set_forward_comm_id_for_comm_node_pass]: 8.87e-06 [meta_fg_expand]: 7.8e-06 [flash_sp_send_recv_attached]: 2.26e-06 [receive_attached]: 2.46998e-06 [after_resolve]: 2.27e-05 [a_after_grad]: 2.598e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.13e-06 [auto_monad_grad]: 2.21998e-06 [auto_monad_eliminator]: 3.796e-05 [cse]: 0.00114493 [a_3]: 0.00011804 [py_interpret_to_execute_after_opt_a]: 2.518e-05 [slice_cell_reuse_recomputed_activation]: 2.39999e-06 [rewriter_after_opt_a]: 0.0002774 [convert_after_rewriter]: 1.794e-05 [order_py_execute_after_rewriter]: 1.059e-05 [mutable_eliminate]: 0.00100388 [opt_b]: 0.00056349, [1] [Cycle 1]: 0.00055389, [7] [b_1]: 0.00037272 [b_2]: 2.024e-05 [updatestate_depend_eliminate]: 1.347e-05 [updatestate_assign_eliminate]: 7.75e-06 [updatestate_loads_eliminate]: 1.153e-05 [renormalize]: 5.3001e-07 [cse]: 7.718e-05 [optimize_parallel_all_gather_comm]: 3.639e-05 [overlap_param_gather]: 3.06999e-06 [cconv]: 3.437e-05 [loop_unroll]: 0.00059448 [opt_after_cconv]: 0.00024059, [1] [Cycle 1]: 0.00022933, [7] [c_1]: 0.00010128 [parameter_eliminate]: 4.63999e-06 [updatestate_depend_eliminate]: 1.347e-05 [updatestate_assign_eliminate]: 7.46001e-06 [updatestate_loads_eliminate]: 9.69e-06 [cse]: 5.355e-05 [renormalize]: 4.7998e-07 [remove_dup_value]: 6.7e-05 [tuple_transform]: 0.000167, [1] [Cycle 1]: 0.00016106, [4] [d_1]: 0.00011553 [none_parameter_eliminate]: 2.04999e-06 [renormalize]: 6.69999e-07 [switch_simplify]: 1.842e-05 [partial_unused_args_eliminate]: 2.06e-06 [add_recomputation]: 0.00012169 [cse_after_recomputation]: 6.029e-05, [1] [Cycle 1]: 5.456e-05, [1] [cse]: 4.588e-05 [environ_conv]: 1.596e-05 [swap_dp_allreduce_reducescatter]: 1.429e-05 [bias_add_comm_swap]: 2.92002e-06 [label_micro_interleaved_index]: 6.19001e-06 [label_fine_grained_interleaved_index]: 2.55002e-06 [merge_cast_opt]: 1.29e-06 [slice_recompute_activation]: 2.07001e-06 [micro_interleaved_order_control]: 2.64001e-06 [assign_add_opt]: 1.29e-06 [ForceFp32Comm]: 7.89994e-07 [remove_cast_before_assign_add]: 1.00999e-06 [full_micro_interleaved_order_control]: 2.52001e-06 [reorder_send_recv_between_fp_bp]: 2.79001e-06 [comm_op_add_attrs]: 1.20001e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.27999e-06 [interleave_parallel_branches]: 1.03001e-06 [overlap_opt_shard_in_pipeline]: 2.51e-06 [overlap_opt_shard_grad_in_pipeline]: 1.94e-06 [control_data_broadcast_order]: 2.713e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 7.16999e-06 [overlap_recompute_and_grad_model_parallel]: 7.60998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.34998e-06 [overlap_recompute_comm]: 2.31998e-06 [overlap_grad_ring_attention]: 8.23999e-06 [overlap_grad_flash_sp]: 4.185e-05 [begin_end_overlap_inline]: 4.89992e-07 [split_matmul_comm_elemetwise]: 2.36998e-06 [split_layernorm_comm]: 2.16e-06 [handle_group_info]: 1.00999e-06 [symbol_engine_optimizer]: 0.0001644, [1] [Cycle 1]: 0.00015754, [6] [build]: 1.741e-05 [elim_shapecalc]: 2.607e-05 [elim_not_effective]: 2.977e-05 [opt_reshape]: 2.257e-05 [fold_const_symbol]: 2.535e-05 [renormalize]: 2.80008e-07 [detach_backward]: 2.67001e-06 [pipeline_parallel_scheduler]: 1.72999e-06 [auto_monad_reorder]: 4.665e-05 [get_jit_bprop_graph]: 1.76e-06 [rewriter_after_jit_bprop_graph]: 4.83001e-06 [opt_after_jit_grad]: 0.00073527 [validate]: 9.107e-05 Sums bootstrap : 0.000671s : 0.23% type_inference : 0.278312s : 93.31% event_method : 0.000018s : 0.01% auto_monad : 0.000345s : 0.12% graph_reusing : 0.000007s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000038s : 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 : 0.000031s : 0.01% optimize.rewriter_before_opt_a : 0.000081s : 0.03% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000054s : 0.02% optimize.opt_a.loop_unroll : 0.000037s : 0.01% optimize.opt_a.a_1 : 0.001351s : 0.45% optimize.opt_a.with_stream_mark : 0.000048s : 0.02% optimize.opt_a.recompute_prepare : 0.000044s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000490s : 0.16% optimize.opt_a.accelerated_algorithm : 0.000067s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.01% optimize.opt_a.merge_send_recv : 0.000030s : 0.01% optimize.opt_a.auto_parallel : 0.000027s : 0.01% optimize.opt_a.parallel : 0.000044s : 0.01% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000019s : 0.01% optimize.opt_a.allreduce_fusion : 0.000018s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000034s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000040s : 0.01% optimize.opt_a.virtual_dataset : 0.000035s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000036s : 0.01% optimize.opt_a.virtual_output : 0.000036s : 0.01% optimize.opt_a.merge_forward : 0.000018s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000067s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000057s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.01% optimize.opt_a.meta_fg_expand : 0.000014s : 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 : 0.000052s : 0.02% optimize.opt_a.a_after_grad : 0.000055s : 0.02% optimize.opt_a.renormalize : 0.009886s : 3.31% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000106s : 0.04% optimize.opt_a.cse : 0.001329s : 0.45% optimize.opt_a.a_3 : 0.000250s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000277s : 0.09% optimize.convert_after_rewriter : 0.000018s : 0.01% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.001004s : 0.34% optimize.opt_b.b_1 : 0.000373s : 0.12% optimize.opt_b.b_2 : 0.000020s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000077s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000034s : 0.01% optimize.loop_unroll : 0.000594s : 0.20% optimize.opt_after_cconv.c_1 : 0.000101s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.cse : 0.000054s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000067s : 0.02% optimize.tuple_transform.d_1 : 0.000116s : 0.04% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000122s : 0.04% optimize.cse_after_recomputation.cse : 0.000046s : 0.02% optimize.environ_conv : 0.000016s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.01% optimize.begin_end_overlap_inline : 0.000000s : 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 : 0.000017s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000030s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000023s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000047s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000735s : 0.25% validate : 0.000091s : 0.03% Time group info: ------[substitution.] 0.000267 96 3.84% : 0.000010s : 2: substitution.depend_value_elim 1.44% : 0.000004s : 8: substitution.elim_not_effective 1.34% : 0.000004s : 8: substitution.fold_const_symbol 4.18% : 0.000011s : 13: substitution.graph_param_transform 42.59% : 0.000114s : 1: substitution.inline 3.20% : 0.000009s : 16: substitution.j_node_and_user_rematch 7.47% : 0.000020s : 2: substitution.less_batch_normalization 2.32% : 0.000006s : 6: substitution.load_eliminater 1.05% : 0.000003s : 2: substitution.opt_reshape 4.48% : 0.000012s : 16: substitution.remove_not_recompute_node 2.79% : 0.000007s : 4: substitution.replace_old_param 10.66% : 0.000028s : 4: substitution.reshape_eliminate 7.99% : 0.000021s : 6: substitution.updatestate_pure_node_eliminater 6.65% : 0.000018s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.278214 2 98.02% : 0.272710s : 1: type_inference.infer 1.98% : 0.005504s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000112 1 100.00% : 0.000112s : 1: match.inline ------[predicate.] 0.000454 3002 0.84% : 0.000004s : 27: predicate.accumulaten_eliminater 0.93% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.73% : 0.000003s : 26: predicate.addn_check_dump 1.19% : 0.000005s : 27: predicate.addn_zero_filter 0.75% : 0.000003s : 27: predicate.adjust_all_reduce_mul_add 2.18% : 0.000010s : 53: predicate.arithmetic_simplify 0.86% : 0.000004s : 27: predicate.cast_eliminate 0.77% : 0.000003s : 26: predicate.check_bprop_eliminate 0.78% : 0.000004s : 26: predicate.compare_switch_simplify 0.24% : 0.000001s : 13: predicate.const_output_eliminate 0.80% : 0.000004s : 26: predicate.depend_value_elim 0.85% : 0.000004s : 27: predicate.dict_get_item_const_eliminator 1.09% : 0.000005s : 27: predicate.dict_get_item_eliminator 0.80% : 0.000004s : 27: predicate.dict_set_item_eliminator 1.06% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 13: predicate.elim_not_effective 0.47% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000005s : 40: predicate.environ_add_const_eliminate 1.20% : 0.000005s : 40: predicate.environ_get_add_eliminate 1.23% : 0.000006s : 40: predicate.environ_get_depend_swap 1.89% : 0.000009s : 66: predicate.environ_get_eliminate 1.20% : 0.000005s : 40: predicate.environ_get_set_eliminate 0.79% : 0.000004s : 28: predicate.exchange_switch_depend_value 1.31% : 0.000006s : 28: predicate.float_depend_g_call 0.83% : 0.000004s : 26: predicate.float_environ_get_switch 1.09% : 0.000005s : 39: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 13: predicate.fold_const_symbol 0.94% : 0.000004s : 26: predicate.get_grad_eliminate 0.35% : 0.000002s : 13: predicate.graph_param_transform 0.76% : 0.000003s : 26: predicate.incorporate_call 0.69% : 0.000003s : 26: predicate.incorporate_call_switch 5.33% : 0.000024s : 133: predicate.inline 0.97% : 0.000004s : 26: predicate.inline_without_move 0.43% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.31% : 0.000006s : 27: predicate.less_batch_normalization 1.65% : 0.000007s : 53: predicate.list_to_tuple_eliminator_ 2.32% : 0.000011s : 80: predicate.load_eliminater 1.02% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.07% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.79% : 0.000008s : 53: predicate.make_slice_get_slice_eliminator 0.84% : 0.000004s : 26: predicate.merge_addn 0.72% : 0.000003s : 26: predicate.micro_step_allgather_replace 0.78% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.74% : 0.000003s : 27: predicate.minmaximum_grad 0.93% : 0.000004s : 13: predicate.mutable_eliminate 0.49% : 0.000002s : 13: predicate.opt_reshape 0.46% : 0.000002s : 13: predicate.parallel_virtual_node 1.10% : 0.000005s : 28: predicate.partial_defer_inline 1.26% : 0.000006s : 40: predicate.partial_eliminate 0.85% : 0.000004s : 27: predicate.print_const_string_wrapper 0.77% : 0.000003s : 26: predicate.reduce_all_const_elim 1.06% : 0.000005s : 27: predicate.reduce_eliminate 2.23% : 0.000010s : 80: predicate.redundant_stop_gradient_eliminater 0.57% : 0.000003s : 26: predicate.remove_not_recompute_node 1.39% : 0.000006s : 53: predicate.replace_applicator 0.54% : 0.000002s : 26: predicate.replace_old_param 0.33% : 0.000002s : 13: predicate.reset_defer_inline 0.96% : 0.000004s : 27: predicate.reshape_eliminate 0.78% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.53% : 0.000002s : 13: predicate.row_tensor_eliminate 1.19% : 0.000005s : 26: predicate.same_eliminate 0.56% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.94% : 0.000004s : 26: predicate.shard_identity_eliminate 0.95% : 0.000004s : 26: predicate.special_op_eliminate 0.89% : 0.000004s : 26: predicate.specialize_transform 1.24% : 0.000006s : 26: predicate.split_environ_get_set_with_tuple_value 0.97% : 0.000004s : 26: predicate.stack_unstack_eliminate 0.44% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.97% : 0.000004s : 28: predicate.switch_defer_inline 1.58% : 0.000007s : 54: predicate.switch_layer_defer_inline 3.45% : 0.000016s : 98: predicate.switch_simplify 0.91% : 0.000004s : 27: predicate.tile_eliminate 1.00% : 0.000005s : 27: predicate.transpose_eliminate 1.77% : 0.000008s : 53: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000008s : 53: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000007s : 53: predicate.tuple_list_get_item_depend_reorder 2.97% : 0.000013s : 79: predicate.tuple_list_get_item_eliminator 1.80% : 0.000008s : 53: predicate.tuple_list_get_set_item_eliminator 2.77% : 0.000013s : 79: predicate.tuple_list_set_item_eliminator 1.63% : 0.000007s : 53: predicate.tuple_to_list_eliminator_ 2.28% : 0.000010s : 80: predicate.updatestate_pure_node_eliminater 3.34% : 0.000015s : 106: predicate.updatestate_useless_node_eliminater 0.56% : 0.000003s : 13: predicate.value_based_eliminate 0.98% : 0.000004s : 26: predicate.virtual_dataset_eliminate 1.03% : 0.000005s : 26: predicate.virtual_output_eliminate 0.35% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.55% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.012488 56 75.16% : 0.009387s : 53: func_graph_cloner_run.FuncGraphClonerGraph 24.84% : 0.003101s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.345063 192 0.00% : 0.000003s : 1: ForceFp32Comm 1.95% : 0.006712s : 1: add_attr 1.94% : 0.006693s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000127s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.10% : 0.000356s : 1: auto_monad 0.02% : 0.000052s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000725s : 1: bootstrap 0.01% : 0.000039s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000031s : 1: control_data_broadcast_order 0.01% : 0.000022s : 1: convert_after_rewriter 0.02% : 0.000064s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000021s : 1: environ_conv 0.01% : 0.000025s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.18% : 0.000606s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.29% : 0.001017s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000036s : 1: opt.transform.mutable_eliminate 0.75% : 0.002578s : 78: opt.transform.opt_a 0.03% : 0.000099s : 1: opt.transform.opt_after_cconv 0.02% : 0.000064s : 1: opt.transform.opt_after_jit_grad 0.10% : 0.000355s : 28: opt.transform.opt_b 0.04% : 0.000130s : 2: opt.transform.opt_trans_graph 0.03% : 0.000099s : 4: opt.transform.symbol_engine_opt 4.37% : 0.015089s : 1: opt_a 0.07% : 0.000245s : 1: opt_after_cconv 0.22% : 0.000751s : 1: opt_after_jit_grad 0.16% : 0.000568s : 1: opt_b 5.52% : 0.019055s : 1: optimize 0.01% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000047s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000043s : 1: pre_auto_parallel 0.01% : 0.000035s : 1: py_interpret_to_execute 0.01% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000073s : 1: remove_dup_value 1.84% : 0.006348s : 1: renormalize.infer 1.02% : 0.003522s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.08% : 0.000287s : 1: rewriter_after_opt_a 0.02% : 0.000085s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000018s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000167s : 1: symbol_engine_optimizer 0.05% : 0.000170s : 1: tuple_transform 80.66% : 0.278337s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_fp16_1[False-mstype0-k_n_shape2-16] tests/st/infer/ops/test_internal_ops/test_matmul_split.py::test_matmul_ffn_fp16_1[False-mstype0-k_n_shape2-16],max_mem:352.0M =============================== 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 457.34s (0:07:37) ==================