==================================================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_005/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 4 items test_matmul.py [WARNING] ME(167124:281473183252272,MainProcess):2026-01-29-17:37:57.933.228 [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 = 0.307567, [21] [bootstrap]: 0.00073471 [type_inference]: 0.231383 [event_method]: 1.427e-05 [auto_monad]: 0.00024445 [graph_reusing]: 5.99999e-06 [inline]: 2.91999e-06 [add_attr]: 0.0679555, [1] [add_attr_with_inline]: 0.0679267, [1] [Cycle 1]: 0.00093991, [2] [tag_attr]: 2.039e-05 [meta_addattr_fg_expand]: 7.75e-06 [parallel-infer-symbol]: 4.1e-06 [pre_auto_parallel]: 5.388e-05 [insert-virtual-dataset]: 2.60002e-06 [parallel-infer-symbol-second]: 7.99977e-07 [dataset_repeat_opt]: 2.53e-06 [pipeline_split]: 1.59998e-06 [optimize]: 0.00622255, [53] [py_interpret_to_execute]: 2.116e-05 [rewriter_before_opt_a]: 8.878e-05 [opt_a]: 0.00328478, [2] [Cycle 1]: 0.0023061, [45] [expand_dump_flag]: 3.25e-06 [switch_simplify]: 2.879e-05 [loop_unroll]: 1.361e-05 [a_1]: 0.0003933 [with_stream_mark]: 1.849e-05 [recompute_prepare]: 1.243e-05 [updatestate_depend_eliminate]: 6.58e-06 [updatestate_assign_eliminate]: 9.26002e-06 [updatestate_loads_eliminate]: 8.95999e-06 [parameter_eliminate]: 1.98002e-06 [a_2]: 0.00015737 [accelerated_algorithm]: 3.324e-05 [shard]: 2.27001e-06 [meta_shard_fg_expand]: 2.59999e-06 [shard_inline]: 9.69999e-06 [merge_send_recv]: 3.126e-05 [auto_parallel]: 1.192e-05 [parallel]: 8.283e-05 [flash_sp]: 2.12e-05 [merge_comm]: 7.01999e-06 [allreduce_fusion]: 5.43002e-06 [matmul_add_comm_reduction]: 1.387e-05 [allreduce_slice_to_reducescatter]: 7.40023e-07 [virtual_shard_identity]: 1.52e-05 [virtual_dataset]: 9.53002e-06 [get_grad_eliminate_]: 1.443e-05 [virtual_output]: 9.31e-06 [merge_forward]: 6.22001e-06 [cell_reuse_recompute_pass]: 1.62001e-06 [offload_activation]: 1.321e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.112e-05 [merge_recompute_call_nodes]: 1.66998e-06 [before_grad]: 1.581e-05 [set_forward_comm_id_for_comm_node_pass]: 6.74999e-06 [meta_fg_expand]: 4.65001e-06 [flash_sp_send_recv_attached]: 6.09999e-06 [receive_attached]: 1.266e-05 [after_resolve]: 1.699e-05 [a_after_grad]: 1.473e-05 [renormalize]: 0.00078762 [add_forward_monad_depend]: 6.44001e-06 [auto_monad_grad]: 2.14999e-06 [auto_monad_eliminator]: 3.975e-05 [cse]: 7.436e-05 [a_3]: 7.42e-05 [Cycle 2]: 0.0009635, [45] [expand_dump_flag]: 1.91e-06 [switch_simplify]: 1.135e-05 [loop_unroll]: 9.29998e-06 [a_1]: 0.00022632 [with_stream_mark]: 1.415e-05 [recompute_prepare]: 2.458e-05 [updatestate_depend_eliminate]: 6.29999e-06 [updatestate_assign_eliminate]: 5.50001e-06 [updatestate_loads_eliminate]: 7.8e-06 [parameter_eliminate]: 1.54e-06 [a_2]: 0.00012462 [accelerated_algorithm]: 1.254e-05 [shard]: 1.69e-06 [meta_shard_fg_expand]: 1.87999e-06 [shard_inline]: 8.90999e-06 [merge_send_recv]: 8.92e-06 [auto_parallel]: 9.68002e-06 [parallel]: 6.55002e-06 [flash_sp]: 3.25e-06 [merge_comm]: 5.34e-06 [allreduce_fusion]: 6.51e-06 [matmul_add_comm_reduction]: 1.095e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 1.038e-05 [virtual_dataset]: 8.75001e-06 [get_grad_eliminate_]: 8.91997e-06 [virtual_output]: 8.34002e-06 [merge_forward]: 5.72999e-06 [cell_reuse_recompute_pass]: 2.21e-06 [offload_activation]: 1.096e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.708e-05 [merge_recompute_call_nodes]: 8.70001e-07 [before_grad]: 1.454e-05 [set_forward_comm_id_for_comm_node_pass]: 5.98998e-06 [meta_fg_expand]: 3.4e-06 [flash_sp_send_recv_attached]: 1.26002e-06 [receive_attached]: 1.66e-06 [after_resolve]: 1.493e-05 [a_after_grad]: 1.317e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 1.86998e-06 [auto_monad_grad]: 1.98002e-06 [auto_monad_eliminator]: 2.755e-05 [cse]: 3.145e-05 [a_3]: 5.9e-05 [py_interpret_to_execute_after_opt_a]: 1.746e-05 [slice_cell_reuse_recomputed_activation]: 2.11003e-06 [rewriter_after_opt_a]: 0.00022198 [convert_after_rewriter]: 4.332e-05 [order_py_execute_after_rewriter]: 8.50999e-06 [mutable_eliminate]: 0.00069988 [opt_b]: 0.00032958, [1] [Cycle 1]: 0.00032071, [7] [b_1]: 0.00021125 [b_2]: 1.104e-05 [updatestate_depend_eliminate]: 1.043e-05 [updatestate_assign_eliminate]: 5.56e-06 [updatestate_loads_eliminate]: 7.37002e-06 [renormalize]: 4.30009e-07 [cse]: 4.005e-05 [optimize_parallel_all_gather_comm]: 2.412e-05 [overlap_param_gather]: 6.88e-06 [cconv]: 3.31e-05 [loop_unroll]: 0.00046815 [opt_after_cconv]: 0.00015936, [1] [Cycle 1]: 0.00015176, [7] [c_1]: 5.907e-05 [parameter_eliminate]: 4.42e-06 [updatestate_depend_eliminate]: 8.84e-06 [updatestate_assign_eliminate]: 5.37999e-06 [updatestate_loads_eliminate]: 7.22002e-06 [cse]: 3.282e-05 [renormalize]: 3.10014e-07 [remove_dup_value]: 4.735e-05 [tuple_transform]: 9.634e-05, [1] [Cycle 1]: 9.073e-05, [4] [d_1]: 6.082e-05 [none_parameter_eliminate]: 2.01e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 9.42999e-06 [partial_unused_args_eliminate]: 1.79998e-06 [add_recomputation]: 7.534e-05 [cse_after_recomputation]: 3.305e-05, [1] [Cycle 1]: 2.803e-05, [1] [cse]: 2.179e-05 [environ_conv]: 1.738e-05 [swap_dp_allreduce_reducescatter]: 7.68001e-06 [bias_add_comm_swap]: 3.11999e-06 [label_micro_interleaved_index]: 4.72998e-06 [label_fine_grained_interleaved_index]: 3.14999e-06 [merge_cast_opt]: 1.42e-06 [slice_recompute_activation]: 2.01e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.34e-06 [ForceFp32Comm]: 7.7e-07 [remove_cast_before_assign_add]: 1.08001e-06 [full_micro_interleaved_order_control]: 2.58003e-06 [reorder_send_recv_between_fp_bp]: 2.71e-06 [comm_op_add_attrs]: 1.05001e-06 [add_comm_op_reuse_tag]: 9.5999e-07 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 4.464e-05 [overlap_opt_shard_grad_in_pipeline]: 2.09e-06 [control_data_broadcast_order]: 1.999e-05 [grouped_pairwise_exchange_alltoall]: 1.49e-06 [offloading_packed_experts]: 5.77999e-06 [overlap_recompute_and_grad_model_parallel]: 6.53003e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37e-06 [overlap_recompute_comm]: 2.37001e-06 [overlap_grad_ring_attention]: 5.95002e-06 [overlap_grad_flash_sp]: 4.109e-05 [begin_end_overlap_inline]: 7.7e-07 [split_matmul_comm_elemetwise]: 2.48e-06 [split_layernorm_comm]: 1.60001e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 9.888e-05, [1] [Cycle 1]: 9.282e-05, [6] [build]: 4.66002e-06 [elim_shapecalc]: 1.513e-05 [elim_not_effective]: 1.85e-05 [opt_reshape]: 9.90002e-06 [fold_const_symbol]: 1.537e-05 [renormalize]: 1.90019e-07 [detach_backward]: 2.86e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 4.481e-05 [get_jit_bprop_graph]: 2.17999e-06 [rewriter_after_jit_bprop_graph]: 5.61e-06 [opt_after_jit_grad]: 0.00062128 [validate]: 7.506e-05 Sums bootstrap : 0.000735s : 0.31% type_inference : 0.231383s : 97.00% event_method : 0.000014s : 0.01% auto_monad : 0.000244s : 0.10% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000054s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000021s : 0.01% optimize.rewriter_before_opt_a : 0.000089s : 0.04% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000040s : 0.02% optimize.opt_a.loop_unroll : 0.000023s : 0.01% optimize.opt_a.a_1 : 0.000620s : 0.26% optimize.opt_a.with_stream_mark : 0.000033s : 0.01% optimize.opt_a.recompute_prepare : 0.000037s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000015s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000282s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000046s : 0.02% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000019s : 0.01% optimize.opt_a.merge_send_recv : 0.000040s : 0.02% optimize.opt_a.auto_parallel : 0.000022s : 0.01% optimize.opt_a.parallel : 0.000089s : 0.04% optimize.opt_a.flash_sp : 0.000024s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000012s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000025s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.01% optimize.opt_a.virtual_dataset : 0.000018s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.01% optimize.opt_a.virtual_output : 0.000018s : 0.01% optimize.opt_a.merge_forward : 0.000012s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000024s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000038s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000030s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000014s : 0.01% optimize.opt_a.after_resolve : 0.000032s : 0.01% optimize.opt_a.a_after_grad : 0.000028s : 0.01% optimize.opt_a.renormalize : 0.000788s : 0.33% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000067s : 0.03% optimize.opt_a.cse : 0.000106s : 0.04% optimize.opt_a.a_3 : 0.000133s : 0.06% optimize.py_interpret_to_execute_after_opt_a : 0.000017s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000222s : 0.09% optimize.convert_after_rewriter : 0.000043s : 0.02% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000700s : 0.29% optimize.opt_b.b_1 : 0.000211s : 0.09% optimize.opt_b.b_2 : 0.000011s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000040s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.01% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000033s : 0.01% optimize.loop_unroll : 0.000468s : 0.20% optimize.opt_after_cconv.c_1 : 0.000059s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000033s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000047s : 0.02% optimize.tuple_transform.d_1 : 0.000061s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000009s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000075s : 0.03% optimize.cse_after_recomputation.cse : 0.000022s : 0.01% optimize.environ_conv : 0.000017s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000045s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000020s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000006s : 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 : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000041s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000018s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 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 : 0.000045s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000621s : 0.26% validate : 0.000075s : 0.03% Time group info: ------[substitution.] 0.000187 66 4.64% : 0.000009s : 2: substitution.depend_value_elim 1.42% : 0.000003s : 5: substitution.elim_not_effective 1.36% : 0.000003s : 5: substitution.fold_const_symbol 3.85% : 0.000007s : 7: substitution.graph_param_transform 47.30% : 0.000088s : 1: substitution.inline 2.95% : 0.000006s : 10: substitution.j_node_and_user_rematch 10.54% : 0.000020s : 2: substitution.less_batch_normalization 2.98% : 0.000006s : 6: substitution.load_eliminater 4.55% : 0.000008s : 10: substitution.remove_not_recompute_node 3.44% : 0.000006s : 4: substitution.replace_old_param 8.88% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 8.10% : 0.000015s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.231270 2 99.77% : 0.230730s : 1: type_inference.infer 0.23% : 0.000541s : 1: type_inference.specialize ------[replace.] 0.000015 1 100.00% : 0.000015s : 1: replace.inline ------[match.] 0.000087 1 100.00% : 0.000087s : 1: match.inline ------[predicate.] 0.000246 1645 0.84% : 0.000002s : 15: predicate.accumulaten_eliminater 1.04% : 0.000003s : 7: predicate.ad_related_special_op_eliminate 0.79% : 0.000002s : 14: predicate.addn_check_dump 0.83% : 0.000002s : 15: predicate.addn_zero_filter 0.76% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.15% : 0.000005s : 29: predicate.arithmetic_simplify 0.86% : 0.000002s : 15: predicate.cast_eliminate 0.79% : 0.000002s : 14: predicate.check_bprop_eliminate 0.72% : 0.000002s : 14: predicate.compare_switch_simplify 0.23% : 0.000001s : 7: predicate.const_output_eliminate 1.04% : 0.000003s : 14: predicate.depend_value_elim 0.85% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.91% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.76% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.26% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.34% : 0.000001s : 7: predicate.elim_not_effective 0.51% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.09% : 0.000003s : 22: predicate.environ_get_depend_swap 1.98% : 0.000005s : 36: predicate.environ_get_eliminate 1.12% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.85% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.61% : 0.000004s : 16: predicate.float_depend_g_call 0.72% : 0.000002s : 14: predicate.float_environ_get_switch 1.11% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 7: predicate.fold_const_symbol 0.81% : 0.000002s : 14: predicate.get_grad_eliminate 0.26% : 0.000001s : 7: predicate.graph_param_transform 0.85% : 0.000002s : 14: predicate.incorporate_call 0.70% : 0.000002s : 14: predicate.incorporate_call_switch 5.64% : 0.000014s : 73: predicate.inline 1.03% : 0.000003s : 14: predicate.inline_without_move 0.43% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.28% : 0.000003s : 14: predicate.less_batch_normalization 1.60% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.38% : 0.000006s : 44: predicate.load_eliminater 1.00% : 0.000002s : 7: predicate.loop_unroll_after_grad 1.12% : 0.000003s : 19: predicate.loop_unroll_before_grad 1.70% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.79% : 0.000002s : 14: predicate.merge_addn 0.80% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.79% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.75% : 0.000002s : 15: predicate.minmaximum_grad 1.73% : 0.000004s : 7: predicate.mutable_eliminate 0.50% : 0.000001s : 7: predicate.opt_reshape 0.44% : 0.000001s : 7: predicate.parallel_virtual_node 1.04% : 0.000003s : 16: predicate.partial_defer_inline 1.30% : 0.000003s : 22: predicate.partial_eliminate 0.78% : 0.000002s : 15: predicate.print_const_string_wrapper 0.82% : 0.000002s : 14: predicate.reduce_all_const_elim 1.20% : 0.000003s : 15: predicate.reduce_eliminate 2.34% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.70% : 0.000002s : 14: predicate.remove_not_recompute_node 1.09% : 0.000003s : 29: predicate.replace_applicator 0.81% : 0.000002s : 14: predicate.replace_old_param 0.48% : 0.000001s : 7: predicate.reset_defer_inline 0.82% : 0.000002s : 15: predicate.reshape_eliminate 0.86% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.53% : 0.000001s : 7: predicate.row_tensor_eliminate 1.14% : 0.000003s : 14: predicate.same_eliminate 0.52% : 0.000001s : 14: predicate.set_cell_output_no_recompute 1.06% : 0.000003s : 14: predicate.shard_identity_eliminate 0.90% : 0.000002s : 14: predicate.special_op_eliminate 0.90% : 0.000002s : 14: predicate.specialize_transform 1.05% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 0.92% : 0.000002s : 14: predicate.stack_unstack_eliminate 0.48% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.89% : 0.000002s : 16: predicate.switch_defer_inline 1.63% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.52% : 0.000009s : 56: predicate.switch_simplify 0.78% : 0.000002s : 15: predicate.tile_eliminate 0.81% : 0.000002s : 15: predicate.transpose_eliminate 1.58% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.67% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.48% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 3.20% : 0.000008s : 43: predicate.tuple_list_get_item_eliminator 1.54% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.63% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.59% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.29% : 0.000006s : 44: predicate.updatestate_pure_node_eliminater 3.37% : 0.000008s : 58: predicate.updatestate_useless_node_eliminater 0.44% : 0.000001s : 7: predicate.value_based_eliminate 0.87% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.81% : 0.000002s : 14: predicate.virtual_output_eliminate 0.41% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.52% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000252 4 8.14% : 0.000021s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.86% : 0.000232s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.384083 192 0.00% : 0.000003s : 1: ForceFp32Comm 17.69% : 0.067963s : 1: add_attr 17.69% : 0.067932s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.02% : 0.000080s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.07% : 0.000253s : 1: auto_monad 0.01% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.20% : 0.000771s : 1: bootstrap 0.01% : 0.000036s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000023s : 1: control_data_broadcast_order 0.01% : 0.000048s : 1: convert_after_rewriter 0.01% : 0.000036s : 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% : 0.000021s : 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% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.12% : 0.000479s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.18% : 0.000710s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000025s : 1: opt.transform.mutable_eliminate 0.34% : 0.001310s : 78: opt.transform.opt_a 0.02% : 0.000058s : 1: opt.transform.opt_after_cconv 0.01% : 0.000038s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000195s : 28: opt.transform.opt_b 0.02% : 0.000068s : 2: opt.transform.opt_trans_graph 0.01% : 0.000055s : 4: opt.transform.symbol_engine_opt 0.86% : 0.003288s : 1: opt_a 0.04% : 0.000163s : 1: opt_after_cconv 0.17% : 0.000635s : 1: opt_after_jit_grad 0.09% : 0.000333s : 1: opt_b 1.62% : 0.006228s : 1: optimize 0.01% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000050s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 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% : 0.000004s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.02% : 0.000059s : 1: pre_auto_parallel 0.01% : 0.000026s : 1: py_interpret_to_execute 0.01% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000052s : 1: remove_dup_value 0.13% : 0.000486s : 1: renormalize.infer 0.08% : 0.000292s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000230s : 1: rewriter_after_opt_a 0.02% : 0.000094s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000102s : 1: symbol_engine_optimizer 0.03% : 0.000099s : 1: tuple_transform 60.25% : 0.231408s : 1: type_inference [WARNING] INTERNAL_KERNEL(167124,ffff9519ff30,python3.9):2026-01-29-17:38:25.741.342 [/home/jenkins/agent-working-dir/workspace/executor0/ms_kernels_internal/src/ops/common/internal_op.cc:93] Tiling] op_name: MatMul batch = 1 batch_b = 1 m = 1024 k = 1024 n = 1024 m0 = 128 k0 = 256 n0 = 256 mLoop = 8 kLoop = 4 nLoop = 4 coreLoop = 32 blockDim = 20 swizzleCount = 3 swizzleDirect = 0 enShuffleK = 1 syncAddr = 0 tilingId = 0b0000000000000000 tilingKey = 0b000000 cacheL1ANum = 0 tilingK = 0 tilingN = 0 compressOverlapN = 0 splitK = 0 inputs_[0].GetDtype() = Float16 inputs_[1].GetDtype() = Float16 outputs_[0].GetDtype() = Float16 inputs_[0].GetFormat() = 1 inputs_[1].GetFormat() = 1 outputs_[0].GetFormat() = 1 . [hook] pytest_runtest_teardown:test_matmul_1024_1024_1024[mstype0-False] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024[mstype0-False],max_mem:110.0M [WARNING] ME(167124:281473183252272,MainProcess):2026-01-29-17:38:29.111.080 [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 = 0.303514, [21] [bootstrap]: 0.00094192 [type_inference]: 0.00597102 [event_method]: 1.41e-05 [auto_monad]: 0.00024821 [graph_reusing]: 9.29998e-06 [inline]: 2.46998e-06 [add_attr]: 0.120912, [1] [add_attr_with_inline]: 0.120843, [1] [Cycle 1]: 7.626e-05, [2] [tag_attr]: 2.041e-05 [meta_addattr_fg_expand]: 4.51002e-06 [parallel-infer-symbol]: 4e-06 [pre_auto_parallel]: 7.361e-05 [insert-virtual-dataset]: 2.56e-06 [parallel-infer-symbol-second]: 9.99979e-07 [dataset_repeat_opt]: 1.93002e-06 [pipeline_split]: 1.53002e-06 [optimize]: 0.173279, [53] [py_interpret_to_execute]: 5.205e-05 [rewriter_before_opt_a]: 0.00011201 [opt_a]: 0.011602, [2] [Cycle 1]: 0.00709075, [45] [expand_dump_flag]: 3.04999e-06 [switch_simplify]: 2.725e-05 [loop_unroll]: 4.119e-05 [a_1]: 0.00154979 [with_stream_mark]: 2.505e-05 [recompute_prepare]: 4.276e-05 [updatestate_depend_eliminate]: 9.76e-06 [updatestate_assign_eliminate]: 3.119e-05 [updatestate_loads_eliminate]: 8.38001e-06 [parameter_eliminate]: 3.18e-06 [a_2]: 0.00028196 [accelerated_algorithm]: 0.00010135 [shard]: 3.01999e-06 [meta_shard_fg_expand]: 2.98e-06 [shard_inline]: 3.248e-05 [merge_send_recv]: 1.226e-05 [auto_parallel]: 1.144e-05 [parallel]: 6.347e-05 [flash_sp]: 1.165e-05 [merge_comm]: 8.93002e-06 [allreduce_fusion]: 7.03e-06 [matmul_add_comm_reduction]: 1.468e-05 [allreduce_slice_to_reducescatter]: 8.50006e-07 [virtual_shard_identity]: 3.631e-05 [virtual_dataset]: 3.417e-05 [get_grad_eliminate_]: 3.06e-05 [virtual_output]: 3.204e-05 [merge_forward]: 6.56e-06 [cell_reuse_recompute_pass]: 1.89e-06 [offload_activation]: 5.757e-05 [cell_reuse_handle_not_recompute_node_pass]: 8.743e-05 [merge_recompute_call_nodes]: 1.66e-06 [before_grad]: 0.00012166 [set_forward_comm_id_for_comm_node_pass]: 8.25e-06 [meta_fg_expand]: 5.24e-06 [flash_sp_send_recv_attached]: 7.26999e-06 [receive_attached]: 2.74999e-06 [after_resolve]: 8.056e-05 [a_after_grad]: 0.00010108 [renormalize]: 0.00239743 [add_forward_monad_depend]: 8.07e-06 [auto_monad_grad]: 2.51e-06 [auto_monad_eliminator]: 4.459e-05 [cse]: 9.694e-05 [a_3]: 0.00015063 [Cycle 2]: 0.00442322, [45] [expand_dump_flag]: 3.01999e-06 [switch_simplify]: 3.799e-05 [loop_unroll]: 3.405e-05 [a_1]: 0.00085394 [with_stream_mark]: 4.386e-05 [recompute_prepare]: 3.215e-05 [updatestate_depend_eliminate]: 7.48999e-06 [updatestate_assign_eliminate]: 6.25002e-06 [updatestate_loads_eliminate]: 9.44e-06 [parameter_eliminate]: 2.76e-06 [a_2]: 0.00036206 [accelerated_algorithm]: 6.706e-05 [shard]: 2.12001e-06 [meta_shard_fg_expand]: 4.02998e-06 [shard_inline]: 1.141e-05 [merge_send_recv]: 3.755e-05 [auto_parallel]: 1.311e-05 [parallel]: 5.429e-05 [flash_sp]: 6.04999e-06 [merge_comm]: 7.60998e-06 [allreduce_fusion]: 6.17999e-06 [matmul_add_comm_reduction]: 3.719e-05 [allreduce_slice_to_reducescatter]: 7.89994e-07 [virtual_shard_identity]: 3.829e-05 [virtual_dataset]: 6.247e-05 [get_grad_eliminate_]: 7.197e-05 [virtual_output]: 5.167e-05 [merge_forward]: 3.086e-05 [cell_reuse_recompute_pass]: 3.35e-06 [offload_activation]: 3.556e-05 [cell_reuse_handle_not_recompute_node_pass]: 7.805e-05 [merge_recompute_call_nodes]: 1.37999e-06 [before_grad]: 0.00010392 [set_forward_comm_id_for_comm_node_pass]: 8.28999e-06 [meta_fg_expand]: 5.34e-06 [flash_sp_send_recv_attached]: 2.14e-06 [receive_attached]: 2.88998e-06 [after_resolve]: 8.146e-05 [a_after_grad]: 0.00018688 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 5.96998e-06 [auto_monad_grad]: 2.97002e-06 [auto_monad_eliminator]: 0.00012315 [cse]: 0.00016096 [a_3]: 0.00031673 [py_interpret_to_execute_after_opt_a]: 9.483e-05 [slice_cell_reuse_recomputed_activation]: 3.73999e-06 [rewriter_after_opt_a]: 0.00026636 [convert_after_rewriter]: 1.552e-05 [order_py_execute_after_rewriter]: 8.27998e-06 [mutable_eliminate]: 0.00143777 [opt_b]: 0.00340693, [1] [Cycle 1]: 0.00339512, [7] [b_1]: 0.00285643 [b_2]: 5.124e-05 [updatestate_depend_eliminate]: 1.813e-05 [updatestate_assign_eliminate]: 7.05e-06 [updatestate_loads_eliminate]: 1.025e-05 [renormalize]: 9.89996e-07 [cse]: 0.0001658 [optimize_parallel_all_gather_comm]: 6.437e-05 [overlap_param_gather]: 2.47001e-06 [cconv]: 4.422e-05 [loop_unroll]: 0.152477 [opt_after_cconv]: 0.00085767, [1] [Cycle 1]: 0.00084412, [7] [c_1]: 0.0003318 [parameter_eliminate]: 7.87e-06 [updatestate_depend_eliminate]: 1.831e-05 [updatestate_assign_eliminate]: 7.06001e-06 [updatestate_loads_eliminate]: 1.016e-05 [cse]: 0.00026345 [renormalize]: 8.00006e-07 [remove_dup_value]: 8.673e-05 [tuple_transform]: 0.00052122, [1] [Cycle 1]: 0.00048997, [4] [d_1]: 0.00037189 [none_parameter_eliminate]: 3.26001e-06 [renormalize]: 1.79978e-07 [switch_simplify]: 3.463e-05 [partial_unused_args_eliminate]: 2.66999e-06 [add_recomputation]: 0.00020573 [cse_after_recomputation]: 0.00033486, [1] [Cycle 1]: 0.00032816, [1] [cse]: 0.00029491 [environ_conv]: 1.099e-05 [swap_dp_allreduce_reducescatter]: 3.428e-05 [bias_add_comm_swap]: 4.03001e-06 [label_micro_interleaved_index]: 9.39998e-06 [label_fine_grained_interleaved_index]: 3.34001e-06 [merge_cast_opt]: 1.57999e-06 [slice_recompute_activation]: 2.49999e-06 [micro_interleaved_order_control]: 2.90002e-06 [assign_add_opt]: 1.69998e-06 [ForceFp32Comm]: 1.00001e-06 [remove_cast_before_assign_add]: 1.00001e-06 [full_micro_interleaved_order_control]: 2.43e-06 [reorder_send_recv_between_fp_bp]: 3.5e-06 [comm_op_add_attrs]: 1.03001e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.74e-06 [interleave_parallel_branches]: 1.39998e-06 [overlap_opt_shard_in_pipeline]: 2.83e-06 [overlap_opt_shard_grad_in_pipeline]: 1.75001e-06 [control_data_broadcast_order]: 2.392e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 7.01001e-06 [overlap_recompute_and_grad_model_parallel]: 6.61e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57999e-06 [overlap_recompute_comm]: 3.18e-06 [overlap_grad_ring_attention]: 6.34999e-06 [overlap_grad_flash_sp]: 5.535e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.44001e-06 [split_layernorm_comm]: 1.72001e-06 [handle_group_info]: 1.04e-06 [symbol_engine_optimizer]: 0.00049996, [1] [Cycle 1]: 0.00049235, [6] [build]: 8.25999e-06 [elim_shapecalc]: 9.791e-05 [elim_not_effective]: 4.662e-05 [opt_reshape]: 8.447e-05 [fold_const_symbol]: 4.132e-05 [renormalize]: 2.19996e-07 [detach_backward]: 2.66e-06 [pipeline_parallel_scheduler]: 1.86e-06 [auto_monad_reorder]: 4.956e-05 [get_jit_bprop_graph]: 2.38998e-06 [rewriter_after_jit_bprop_graph]: 3.441e-05 [opt_after_jit_grad]: 0.0015444 [validate]: 0.00014083 Sums bootstrap : 0.000942s : 0.53% type_inference : 0.005971s : 3.36% event_method : 0.000014s : 0.01% auto_monad : 0.000248s : 0.14% graph_reusing : 0.000009s : 0.01% inline : 0.000002s : 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 : 0.000004s : 0.00% pre_auto_parallel : 0.000074s : 0.04% 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 : 0.000052s : 0.03% optimize.rewriter_before_opt_a : 0.000112s : 0.06% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000065s : 0.04% optimize.opt_a.loop_unroll : 0.000075s : 0.04% optimize.opt_a.a_1 : 0.002404s : 1.35% optimize.opt_a.with_stream_mark : 0.000069s : 0.04% optimize.opt_a.recompute_prepare : 0.000075s : 0.04% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000037s : 0.02% optimize.opt_a.updatestate_loads_eliminate : 0.000018s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000644s : 0.36% optimize.opt_a.accelerated_algorithm : 0.000168s : 0.09% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.02% optimize.opt_a.merge_send_recv : 0.000050s : 0.03% optimize.opt_a.auto_parallel : 0.000025s : 0.01% optimize.opt_a.parallel : 0.000118s : 0.07% optimize.opt_a.flash_sp : 0.000018s : 0.01% optimize.opt_a.merge_comm : 0.000017s : 0.01% optimize.opt_a.allreduce_fusion : 0.000013s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000052s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000075s : 0.04% optimize.opt_a.virtual_dataset : 0.000097s : 0.05% optimize.opt_a.get_grad_eliminate_ : 0.000103s : 0.06% optimize.opt_a.virtual_output : 0.000084s : 0.05% optimize.opt_a.merge_forward : 0.000037s : 0.02% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000093s : 0.05% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000165s : 0.09% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000226s : 0.13% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000017s : 0.01% optimize.opt_a.meta_fg_expand : 0.000011s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.01% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000162s : 0.09% optimize.opt_a.a_after_grad : 0.000288s : 0.16% optimize.opt_a.renormalize : 0.002398s : 1.35% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000168s : 0.09% optimize.opt_a.cse : 0.000258s : 0.15% optimize.opt_a.a_3 : 0.000467s : 0.26% optimize.py_interpret_to_execute_after_opt_a : 0.000095s : 0.05% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000266s : 0.15% optimize.convert_after_rewriter : 0.000016s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.001438s : 0.81% optimize.opt_b.b_1 : 0.002856s : 1.61% optimize.opt_b.b_2 : 0.000051s : 0.03% optimize.opt_b.updatestate_depend_eliminate : 0.000018s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000166s : 0.09% optimize.optimize_parallel_all_gather_comm : 0.000064s : 0.04% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.02% optimize.loop_unroll : 0.152477s : 85.90% optimize.opt_after_cconv.c_1 : 0.000332s : 0.19% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_after_cconv.cse : 0.000263s : 0.15% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000087s : 0.05% optimize.tuple_transform.d_1 : 0.000372s : 0.21% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000035s : 0.02% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000206s : 0.12% optimize.cse_after_recomputation.cse : 0.000295s : 0.17% optimize.environ_conv : 0.000011s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000034s : 0.02% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 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 : 0.000024s : 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 : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000055s : 0.03% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000008s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000098s : 0.06% optimize.symbol_engine_optimizer.elim_not_effective : 0.000047s : 0.03% optimize.symbol_engine_optimizer.opt_reshape : 0.000084s : 0.05% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000041s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000050s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000034s : 0.02% opt_after_jit_grad : 0.001544s : 0.87% validate : 0.000141s : 0.08% Time group info: ------[substitution.] 0.000466 66 2.16% : 0.000010s : 2: substitution.depend_value_elim 0.63% : 0.000003s : 5: substitution.elim_not_effective 0.49% : 0.000002s : 5: substitution.fold_const_symbol 1.95% : 0.000009s : 7: substitution.graph_param_transform 62.94% : 0.000293s : 1: substitution.inline 1.80% : 0.000008s : 10: substitution.j_node_and_user_rematch 9.60% : 0.000045s : 2: substitution.less_batch_normalization 1.35% : 0.000006s : 6: substitution.load_eliminater 2.03% : 0.000009s : 10: substitution.remove_not_recompute_node 2.02% : 0.000009s : 4: substitution.replace_old_param 6.37% : 0.000030s : 6: substitution.updatestate_pure_node_eliminater 8.64% : 0.000040s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.005895 2 88.38% : 0.005210s : 1: type_inference.infer 11.62% : 0.000685s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000292 1 100.00% : 0.000292s : 1: match.inline ------[predicate.] 0.000321 1645 0.80% : 0.000003s : 15: predicate.accumulaten_eliminater 1.19% : 0.000004s : 7: predicate.ad_related_special_op_eliminate 0.68% : 0.000002s : 14: predicate.addn_check_dump 0.76% : 0.000002s : 15: predicate.addn_zero_filter 0.65% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.41% : 0.000008s : 29: predicate.arithmetic_simplify 0.76% : 0.000002s : 15: predicate.cast_eliminate 0.71% : 0.000002s : 14: predicate.check_bprop_eliminate 0.61% : 0.000002s : 14: predicate.compare_switch_simplify 0.25% : 0.000001s : 7: predicate.const_output_eliminate 0.86% : 0.000003s : 14: predicate.depend_value_elim 0.69% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.97% : 0.000003s : 15: predicate.dict_get_item_eliminator 0.77% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.35% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.37% : 0.000001s : 7: predicate.elim_not_effective 0.72% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000004s : 22: predicate.environ_add_const_eliminate 1.00% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.07% : 0.000003s : 22: predicate.environ_get_depend_swap 1.72% : 0.000006s : 36: predicate.environ_get_eliminate 1.03% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.69% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.28% : 0.000004s : 16: predicate.float_depend_g_call 0.64% : 0.000002s : 14: predicate.float_environ_get_switch 1.06% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 7: predicate.fold_const_symbol 0.75% : 0.000002s : 14: predicate.get_grad_eliminate 0.29% : 0.000001s : 7: predicate.graph_param_transform 0.63% : 0.000002s : 14: predicate.incorporate_call 0.56% : 0.000002s : 14: predicate.incorporate_call_switch 5.33% : 0.000017s : 73: predicate.inline 1.35% : 0.000004s : 14: predicate.inline_without_move 0.46% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.25% : 0.000004s : 14: predicate.less_batch_normalization 2.23% : 0.000007s : 29: predicate.list_to_tuple_eliminator_ 2.19% : 0.000007s : 44: predicate.load_eliminater 2.96% : 0.000009s : 7: predicate.loop_unroll_after_grad 1.15% : 0.000004s : 19: predicate.loop_unroll_before_grad 1.91% : 0.000006s : 29: predicate.make_slice_get_slice_eliminator 0.65% : 0.000002s : 14: predicate.merge_addn 0.82% : 0.000003s : 14: predicate.micro_step_allgather_replace 1.20% : 0.000004s : 14: predicate.mini_step_allgather_replace 0.60% : 0.000002s : 15: predicate.minmaximum_grad 1.14% : 0.000004s : 7: predicate.mutable_eliminate 0.41% : 0.000001s : 7: predicate.opt_reshape 0.72% : 0.000002s : 7: predicate.parallel_virtual_node 1.21% : 0.000004s : 16: predicate.partial_defer_inline 1.03% : 0.000003s : 22: predicate.partial_eliminate 0.71% : 0.000002s : 15: predicate.print_const_string_wrapper 0.65% : 0.000002s : 14: predicate.reduce_all_const_elim 0.97% : 0.000003s : 15: predicate.reduce_eliminate 2.75% : 0.000009s : 44: predicate.redundant_stop_gradient_eliminater 0.53% : 0.000002s : 14: predicate.remove_not_recompute_node 0.97% : 0.000003s : 29: predicate.replace_applicator 0.51% : 0.000002s : 14: predicate.replace_old_param 0.40% : 0.000001s : 7: predicate.reset_defer_inline 0.71% : 0.000002s : 15: predicate.reshape_eliminate 0.92% : 0.000003s : 14: predicate.row_tensor_add_zeros_like 0.60% : 0.000002s : 7: predicate.row_tensor_eliminate 0.98% : 0.000003s : 14: predicate.same_eliminate 0.45% : 0.000001s : 14: predicate.set_cell_output_no_recompute 1.14% : 0.000004s : 14: predicate.shard_identity_eliminate 0.91% : 0.000003s : 14: predicate.special_op_eliminate 0.70% : 0.000002s : 14: predicate.specialize_transform 1.31% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 1.32% : 0.000004s : 14: predicate.stack_unstack_eliminate 0.47% : 0.000002s : 7: predicate.switch_call_monad_eliminater 0.75% : 0.000002s : 16: predicate.switch_defer_inline 1.69% : 0.000005s : 30: predicate.switch_layer_defer_inline 3.24% : 0.000010s : 56: predicate.switch_simplify 0.70% : 0.000002s : 15: predicate.tile_eliminate 0.67% : 0.000002s : 15: predicate.transpose_eliminate 1.51% : 0.000005s : 29: predicate.tuple_list_convert_item_index_to_positive 1.78% : 0.000006s : 29: predicate.tuple_list_get_item_const_eliminator 1.47% : 0.000005s : 29: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000010s : 43: predicate.tuple_list_get_item_eliminator 1.67% : 0.000005s : 29: predicate.tuple_list_get_set_item_eliminator 2.49% : 0.000008s : 43: predicate.tuple_list_set_item_eliminator 1.53% : 0.000005s : 29: predicate.tuple_to_list_eliminator_ 2.34% : 0.000008s : 44: predicate.updatestate_pure_node_eliminater 3.66% : 0.000012s : 58: predicate.updatestate_useless_node_eliminater 0.64% : 0.000002s : 7: predicate.value_based_eliminate 0.83% : 0.000003s : 14: predicate.virtual_dataset_eliminate 0.91% : 0.000003s : 14: predicate.virtual_output_eliminate 0.29% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.47% : 0.000002s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000742 4 3.71% : 0.000028s : 1: func_graph_cloner_run.FuncGraphClonerGraph 96.29% : 0.000714s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.607920 192 0.00% : 0.000004s : 1: ForceFp32Comm 19.89% : 0.120921s : 1: add_attr 19.88% : 0.120848s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000235s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.04% : 0.000257s : 1: auto_monad 0.01% : 0.000055s : 1: auto_monad_reorder 0.02% : 0.000101s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.16% : 0.000982s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000073s : 1: control_data_broadcast_order 0.01% : 0.000042s : 1: convert_after_rewriter 0.06% : 0.000338s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000014s : 1: environ_conv 0.00% : 0.000020s : 1: event_method 0.00% : 0.000027s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.01% : 0.000050s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000029s : 1: interleave_split_concat_branches 0.01% : 0.000052s : 1: label_fine_grained_interleaved_index 0.00% : 0.000012s : 1: label_micro_interleaved_index 25.09% : 0.152534s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000028s : 1: micro_interleaved_order_control 0.24% : 0.001453s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000070s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000083s : 1: opt.transform.mutable_eliminate 0.81% : 0.004917s : 78: opt.transform.opt_a 0.05% : 0.000329s : 1: opt.transform.opt_after_cconv 0.03% : 0.000185s : 1: opt.transform.opt_after_jit_grad 0.31% : 0.001887s : 28: opt.transform.opt_b 0.07% : 0.000402s : 2: opt.transform.opt_trans_graph 0.04% : 0.000265s : 4: opt.transform.symbol_engine_opt 1.91% : 0.011606s : 1: opt_a 0.14% : 0.000863s : 1: opt_after_cconv 0.26% : 0.001585s : 1: opt_after_jit_grad 0.57% : 0.003442s : 1: opt_b 28.50% : 0.173286s : 1: optimize 0.02% : 0.000100s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000035s : 1: order_py_execute_after_rewriter 0.01% : 0.000060s : 1: overlap_grad_flash_sp 0.00% : 0.000030s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000028s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000079s : 1: pre_auto_parallel 0.01% : 0.000077s : 1: py_interpret_to_execute 0.02% : 0.000101s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000123s : 1: remove_dup_value 0.16% : 0.000943s : 1: renormalize.infer 0.24% : 0.001442s : 1: renormalize.specialize 0.01% : 0.000081s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000090s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000273s : 1: rewriter_after_opt_a 0.02% : 0.000118s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000030s : 1: split_matmul_comm_elemetwise 0.01% : 0.000062s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000504s : 1: symbol_engine_optimizer 0.09% : 0.000525s : 1: tuple_transform 0.99% : 0.005995s : 1: type_inference [WARNING] INTERNAL_KERNEL(167124,ffff9519ff30,python3.9):2026-01-29-17:38:34.559.624 [/home/jenkins/agent-working-dir/workspace/executor0/ms_kernels_internal/src/ops/common/internal_op.cc:93] Tiling] op_name: MatMul batch = 1 batch_b = 1 m = 1024 k = 1024 n = 1024 m0 = 128 k0 = 256 n0 = 256 mLoop = 8 kLoop = 4 nLoop = 4 coreLoop = 32 blockDim = 20 swizzleCount = 3 swizzleDirect = 0 enShuffleK = 1 syncAddr = 0 tilingId = 0b0000000000000000 tilingKey = 0b001000 cacheL1ANum = 0 tilingK = 0 tilingN = 0 compressOverlapN = 0 splitK = 0 inputs_[0].GetDtype() = Float16 inputs_[1].GetDtype() = Float16 outputs_[0].GetDtype() = Float16 inputs_[0].GetFormat() = 1 inputs_[1].GetFormat() = 1 outputs_[0].GetFormat() = 1 . [hook] pytest_runtest_teardown:test_matmul_1024_1024_1024[mstype0-True] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024[mstype0-True],max_mem:110.0M [WARNING] ME(167124:281473183252272,MainProcess):2026-01-29-17:38:36.857.996 [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 = 0.240341, [21] [bootstrap]: 0.0151783 [type_inference]: 0.111159 [event_method]: 1.4e-05 [auto_monad]: 0.00026665 [graph_reusing]: 5.94999e-06 [inline]: 2.06e-06 [add_attr]: 0.00641529, [1] [add_attr_with_inline]: 0.00639645, [1] [Cycle 1]: 7.777e-05, [2] [tag_attr]: 2.281e-05 [meta_addattr_fg_expand]: 3.61999e-06 [parallel-infer-symbol]: 3.61001e-06 [pre_auto_parallel]: 4.018e-05 [insert-virtual-dataset]: 2.27001e-06 [parallel-infer-symbol-second]: 8.09989e-07 [dataset_repeat_opt]: 1.88002e-06 [pipeline_split]: 4.08999e-06 [optimize]: 0.105795, [53] [py_interpret_to_execute]: 3.308e-05 [rewriter_before_opt_a]: 9.793e-05 [opt_a]: 0.101877, [2] [Cycle 1]: 0.00652461, [45] [expand_dump_flag]: 3.61999e-06 [switch_simplify]: 3.612e-05 [loop_unroll]: 2.848e-05 [a_1]: 0.00222161 [with_stream_mark]: 5.441e-05 [recompute_prepare]: 4.208e-05 [updatestate_depend_eliminate]: 7.78001e-06 [updatestate_assign_eliminate]: 6.39001e-06 [updatestate_loads_eliminate]: 9.22999e-06 [parameter_eliminate]: 3.33998e-06 [a_2]: 0.00031744 [accelerated_algorithm]: 5.542e-05 [shard]: 3.17002e-06 [meta_shard_fg_expand]: 5.17e-06 [shard_inline]: 3.994e-05 [merge_send_recv]: 1.383e-05 [auto_parallel]: 1.69e-05 [parallel]: 4.073e-05 [flash_sp]: 1.229e-05 [merge_comm]: 6.86001e-06 [allreduce_fusion]: 8.45999e-06 [matmul_add_comm_reduction]: 1.486e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 3.6e-05 [virtual_dataset]: 3.125e-05 [get_grad_eliminate_]: 1.545e-05 [virtual_output]: 3.343e-05 [merge_forward]: 7.13e-06 [cell_reuse_recompute_pass]: 2.54001e-06 [offload_activation]: 1.839e-05 [cell_reuse_handle_not_recompute_node_pass]: 7.029e-05 [merge_recompute_call_nodes]: 1.81e-06 [before_grad]: 6.291e-05 [set_forward_comm_id_for_comm_node_pass]: 8.15e-06 [meta_fg_expand]: 6.39001e-06 [flash_sp_send_recv_attached]: 5.67001e-06 [receive_attached]: 2.93e-06 [after_resolve]: 4.693e-05 [a_after_grad]: 6.418e-05 [renormalize]: 0.0021188 [add_forward_monad_depend]: 1.028e-05 [auto_monad_grad]: 2.58e-06 [auto_monad_eliminator]: 5.362e-05 [cse]: 0.00012208 [a_3]: 0.00016812 [Cycle 2]: 0.0953278, [45] [expand_dump_flag]: 3.45998e-06 [switch_simplify]: 4.576e-05 [loop_unroll]: 3.433e-05 [a_1]: 0.0934757 [with_stream_mark]: 4.866e-05 [recompute_prepare]: 3.536e-05 [updatestate_depend_eliminate]: 9.69e-06 [updatestate_assign_eliminate]: 6.61999e-06 [updatestate_loads_eliminate]: 1.233e-05 [parameter_eliminate]: 2.63e-06 [a_2]: 0.00021977 [accelerated_algorithm]: 3.328e-05 [shard]: 2.94001e-06 [meta_shard_fg_expand]: 7.18e-06 [shard_inline]: 1.38e-05 [merge_send_recv]: 1.268e-05 [auto_parallel]: 1.592e-05 [parallel]: 2.063e-05 [flash_sp]: 4.43001e-06 [merge_comm]: 9.78002e-06 [allreduce_fusion]: 1.299e-05 [matmul_add_comm_reduction]: 2.116e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 1.586e-05 [virtual_dataset]: 1.924e-05 [get_grad_eliminate_]: 1.422e-05 [virtual_output]: 1.18e-05 [merge_forward]: 7.67998e-06 [cell_reuse_recompute_pass]: 3.04999e-06 [offload_activation]: 2.66e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.001e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 2.517e-05 [set_forward_comm_id_for_comm_node_pass]: 6.89001e-06 [meta_fg_expand]: 5.78002e-06 [flash_sp_send_recv_attached]: 1.76e-06 [receive_attached]: 3.31001e-06 [after_resolve]: 2.457e-05 [a_after_grad]: 2.641e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 4.32e-06 [auto_monad_grad]: 3.21001e-06 [auto_monad_eliminator]: 7.001e-05 [cse]: 0.00012761 [a_3]: 0.00010826 [py_interpret_to_execute_after_opt_a]: 3.68e-05 [slice_cell_reuse_recomputed_activation]: 2.14999e-06 [rewriter_after_opt_a]: 0.00019802 [convert_after_rewriter]: 1.644e-05 [order_py_execute_after_rewriter]: 8.22e-06 [mutable_eliminate]: 0.00091618 [opt_b]: 0.00054609, [1] [Cycle 1]: 0.00053633, [7] [b_1]: 0.00036403 [b_2]: 1.277e-05 [updatestate_depend_eliminate]: 1.168e-05 [updatestate_assign_eliminate]: 1.21e-05 [updatestate_loads_eliminate]: 8.75999e-06 [renormalize]: 4.59986e-07 [cse]: 6.902e-05 [optimize_parallel_all_gather_comm]: 3.29e-05 [overlap_param_gather]: 8.19002e-06 [cconv]: 4.045e-05 [loop_unroll]: 0.00060892 [opt_after_cconv]: 0.00022197, [1] [Cycle 1]: 0.00021407, [7] [c_1]: 8.331e-05 [parameter_eliminate]: 4.92e-06 [updatestate_depend_eliminate]: 8.42998e-06 [updatestate_assign_eliminate]: 5.32001e-06 [updatestate_loads_eliminate]: 7.13e-06 [cse]: 5.041e-05 [renormalize]: 3.60014e-07 [remove_dup_value]: 6.448e-05 [tuple_transform]: 0.00018073, [1] [Cycle 1]: 0.00017094, [4] [d_1]: 0.00012491 [none_parameter_eliminate]: 2.24999e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 1.171e-05 [partial_unused_args_eliminate]: 1.84998e-06 [add_recomputation]: 0.00010741 [cse_after_recomputation]: 5.946e-05, [1] [Cycle 1]: 5.392e-05, [1] [cse]: 4.339e-05 [environ_conv]: 9.51998e-06 [swap_dp_allreduce_reducescatter]: 8.60999e-06 [bias_add_comm_swap]: 3.57002e-06 [label_micro_interleaved_index]: 6.10002e-06 [label_fine_grained_interleaved_index]: 3.09999e-06 [merge_cast_opt]: 1.29998e-06 [slice_recompute_activation]: 1.97999e-06 [micro_interleaved_order_control]: 3.09999e-06 [assign_add_opt]: 1.28002e-06 [ForceFp32Comm]: 1.19998e-06 [remove_cast_before_assign_add]: 1.04e-06 [full_micro_interleaved_order_control]: 2.44001e-06 [reorder_send_recv_between_fp_bp]: 3.10998e-06 [comm_op_add_attrs]: 1.03001e-06 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.47001e-06 [interleave_parallel_branches]: 1.37e-06 [overlap_opt_shard_in_pipeline]: 3.33998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.69998e-06 [control_data_broadcast_order]: 2.241e-05 [grouped_pairwise_exchange_alltoall]: 1.60001e-06 [offloading_packed_experts]: 8.48001e-06 [overlap_recompute_and_grad_model_parallel]: 6.60002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.32999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.55999e-06 [overlap_recompute_comm]: 3.01001e-06 [overlap_grad_ring_attention]: 5.67999e-06 [overlap_grad_flash_sp]: 2.866e-05 [begin_end_overlap_inline]: 6.39993e-07 [split_matmul_comm_elemetwise]: 2.20002e-06 [split_layernorm_comm]: 1.62001e-06 [handle_group_info]: 9.79984e-07 [symbol_engine_optimizer]: 0.00016764, [1] [Cycle 1]: 0.0001599, [6] [build]: 6.73e-06 [elim_shapecalc]: 2.383e-05 [elim_not_effective]: 2.569e-05 [opt_reshape]: 1.706e-05 [fold_const_symbol]: 2.227e-05 [renormalize]: 1.60013e-07 [detach_backward]: 2.34999e-06 [pipeline_parallel_scheduler]: 1.58002e-06 [auto_monad_reorder]: 5.107e-05 [get_jit_bprop_graph]: 1.66e-06 [rewriter_after_jit_bprop_graph]: 5.86998e-06 [opt_after_jit_grad]: 0.00066401 [validate]: 7.26e-05 Sums bootstrap : 0.015178s : 6.57% type_inference : 0.111159s : 48.09% event_method : 0.000014s : 0.01% auto_monad : 0.000267s : 0.12% graph_reusing : 0.000006s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000040s : 0.02% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000004s : 0.00% optimize.py_interpret_to_execute : 0.000033s : 0.01% optimize.rewriter_before_opt_a : 0.000098s : 0.04% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000082s : 0.04% optimize.opt_a.loop_unroll : 0.000063s : 0.03% optimize.opt_a.a_1 : 0.095697s : 41.40% optimize.opt_a.with_stream_mark : 0.000103s : 0.04% optimize.opt_a.recompute_prepare : 0.000077s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000022s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000537s : 0.23% optimize.opt_a.accelerated_algorithm : 0.000089s : 0.04% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.01% optimize.opt_a.shard_inline : 0.000054s : 0.02% optimize.opt_a.merge_send_recv : 0.000027s : 0.01% optimize.opt_a.auto_parallel : 0.000033s : 0.01% optimize.opt_a.parallel : 0.000061s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000017s : 0.01% optimize.opt_a.allreduce_fusion : 0.000021s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.02% optimize.opt_a.virtual_dataset : 0.000050s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000030s : 0.01% optimize.opt_a.virtual_output : 0.000045s : 0.02% optimize.opt_a.merge_forward : 0.000015s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000045s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000110s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000088s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.01% optimize.opt_a.meta_fg_expand : 0.000012s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000071s : 0.03% optimize.opt_a.a_after_grad : 0.000091s : 0.04% optimize.opt_a.renormalize : 0.002119s : 0.92% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000124s : 0.05% optimize.opt_a.cse : 0.000250s : 0.11% optimize.opt_a.a_3 : 0.000276s : 0.12% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000198s : 0.09% optimize.convert_after_rewriter : 0.000016s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000916s : 0.40% optimize.opt_b.b_1 : 0.000364s : 0.16% optimize.opt_b.b_2 : 0.000013s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000069s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.01% optimize.overlap_param_gather : 0.000008s : 0.00% optimize.cconv : 0.000040s : 0.02% optimize.loop_unroll : 0.000609s : 0.26% optimize.opt_after_cconv.c_1 : 0.000083s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000050s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000064s : 0.03% optimize.tuple_transform.d_1 : 0.000125s : 0.05% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000107s : 0.05% optimize.cse_after_recomputation.cse : 0.000043s : 0.02% optimize.environ_conv : 0.000010s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000029s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.01% 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 : 0.000051s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000664s : 0.29% validate : 0.000073s : 0.03% Time group info: ------[substitution.] 0.000353 66 2.95% : 0.000010s : 2: substitution.depend_value_elim 1.11% : 0.000004s : 5: substitution.elim_not_effective 0.68% : 0.000002s : 5: substitution.fold_const_symbol 2.41% : 0.000009s : 7: substitution.graph_param_transform 56.77% : 0.000200s : 1: substitution.inline 1.96% : 0.000007s : 10: substitution.j_node_and_user_rematch 5.26% : 0.000019s : 2: substitution.less_batch_normalization 2.90% : 0.000010s : 6: substitution.load_eliminater 2.94% : 0.000010s : 10: substitution.remove_not_recompute_node 2.80% : 0.000010s : 4: substitution.replace_old_param 13.50% : 0.000048s : 6: substitution.updatestate_pure_node_eliminater 6.72% : 0.000024s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.111066 2 99.21% : 0.110187s : 1: type_inference.infer 0.79% : 0.000879s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000198 1 100.00% : 0.000198s : 1: match.inline ------[predicate.] 0.000328 1645 0.84% : 0.000003s : 15: predicate.accumulaten_eliminater 0.94% : 0.000003s : 7: predicate.ad_related_special_op_eliminate 0.57% : 0.000002s : 14: predicate.addn_check_dump 0.84% : 0.000003s : 15: predicate.addn_zero_filter 0.85% : 0.000003s : 15: predicate.adjust_all_reduce_mul_add 2.77% : 0.000009s : 29: predicate.arithmetic_simplify 1.05% : 0.000003s : 15: predicate.cast_eliminate 0.76% : 0.000002s : 14: predicate.check_bprop_eliminate 0.69% : 0.000002s : 14: predicate.compare_switch_simplify 0.18% : 0.000001s : 7: predicate.const_output_eliminate 0.87% : 0.000003s : 14: predicate.depend_value_elim 0.70% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.09% : 0.000004s : 15: predicate.dict_get_item_eliminator 0.69% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.16% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 7: predicate.elim_not_effective 0.49% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000004s : 22: predicate.environ_add_const_eliminate 1.05% : 0.000003s : 22: predicate.environ_get_add_eliminate 2.92% : 0.000010s : 22: predicate.environ_get_depend_swap 1.82% : 0.000006s : 36: predicate.environ_get_eliminate 1.63% : 0.000005s : 22: predicate.environ_get_set_eliminate 0.72% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.40% : 0.000005s : 16: predicate.float_depend_g_call 0.62% : 0.000002s : 14: predicate.float_environ_get_switch 0.93% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 7: predicate.fold_const_symbol 0.82% : 0.000003s : 14: predicate.get_grad_eliminate 0.22% : 0.000001s : 7: predicate.graph_param_transform 0.79% : 0.000003s : 14: predicate.incorporate_call 0.58% : 0.000002s : 14: predicate.incorporate_call_switch 5.96% : 0.000020s : 73: predicate.inline 0.98% : 0.000003s : 14: predicate.inline_without_move 0.36% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.56% : 0.000005s : 14: predicate.less_batch_normalization 1.67% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.31% : 0.000008s : 44: predicate.load_eliminater 1.01% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.03% : 0.000003s : 19: predicate.loop_unroll_before_grad 2.02% : 0.000007s : 29: predicate.make_slice_get_slice_eliminator 0.76% : 0.000003s : 14: predicate.merge_addn 0.79% : 0.000003s : 14: predicate.micro_step_allgather_replace 0.87% : 0.000003s : 14: predicate.mini_step_allgather_replace 0.76% : 0.000002s : 15: predicate.minmaximum_grad 1.01% : 0.000003s : 7: predicate.mutable_eliminate 0.39% : 0.000001s : 7: predicate.opt_reshape 0.43% : 0.000001s : 7: predicate.parallel_virtual_node 1.24% : 0.000004s : 16: predicate.partial_defer_inline 1.04% : 0.000003s : 22: predicate.partial_eliminate 0.74% : 0.000002s : 15: predicate.print_const_string_wrapper 0.79% : 0.000003s : 14: predicate.reduce_all_const_elim 1.86% : 0.000006s : 15: predicate.reduce_eliminate 2.31% : 0.000008s : 44: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 14: predicate.remove_not_recompute_node 1.00% : 0.000003s : 29: predicate.replace_applicator 0.55% : 0.000002s : 14: predicate.replace_old_param 0.24% : 0.000001s : 7: predicate.reset_defer_inline 1.17% : 0.000004s : 15: predicate.reshape_eliminate 0.73% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.40% : 0.000001s : 7: predicate.row_tensor_eliminate 0.96% : 0.000003s : 14: predicate.same_eliminate 0.52% : 0.000002s : 14: predicate.set_cell_output_no_recompute 0.95% : 0.000003s : 14: predicate.shard_identity_eliminate 0.81% : 0.000003s : 14: predicate.special_op_eliminate 0.90% : 0.000003s : 14: predicate.specialize_transform 1.20% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 0.93% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.72% : 0.000002s : 16: predicate.switch_defer_inline 1.33% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.23% : 0.000011s : 56: predicate.switch_simplify 0.99% : 0.000003s : 15: predicate.tile_eliminate 0.76% : 0.000002s : 15: predicate.transpose_eliminate 1.64% : 0.000005s : 29: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000006s : 29: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000005s : 29: predicate.tuple_list_get_item_depend_reorder 3.19% : 0.000010s : 43: predicate.tuple_list_get_item_eliminator 1.42% : 0.000005s : 29: predicate.tuple_list_get_set_item_eliminator 2.71% : 0.000009s : 43: predicate.tuple_list_set_item_eliminator 1.41% : 0.000005s : 29: predicate.tuple_to_list_eliminator_ 2.20% : 0.000007s : 44: predicate.updatestate_pure_node_eliminater 3.25% : 0.000011s : 58: predicate.updatestate_useless_node_eliminater 0.56% : 0.000002s : 7: predicate.value_based_eliminate 0.83% : 0.000003s : 14: predicate.virtual_dataset_eliminate 0.84% : 0.000003s : 14: predicate.virtual_output_eliminate 0.29% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.43% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000949 4 2.73% : 0.000026s : 1: func_graph_cloner_run.FuncGraphClonerGraph 97.27% : 0.000923s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.452441 192 0.00% : 0.000006s : 1: ForceFp32Comm 1.42% : 0.006423s : 1: add_attr 1.41% : 0.006402s : 1: add_attr_with_inline 0.00% : 0.000006s : 1: add_comm_op_reuse_tag 0.03% : 0.000116s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.06% : 0.000277s : 1: auto_monad 0.01% : 0.000057s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 3.37% : 0.015239s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000007s : 1: comm_op_add_attrs 0.01% : 0.000030s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.01% : 0.000063s : 1: cse_after_recomputation 0.08% : 0.000361s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000013s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000007s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000008s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.14% : 0.000619s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000009s : 1: micro_interleaved_order_control 0.21% : 0.000928s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000029s : 1: opt.transform.mutable_eliminate 21.50% : 0.097271s : 78: opt.transform.opt_a 0.02% : 0.000082s : 1: opt.transform.opt_after_cconv 0.01% : 0.000056s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000325s : 28: opt.transform.opt_b 0.03% : 0.000134s : 2: opt.transform.opt_trans_graph 0.02% : 0.000085s : 4: opt.transform.symbol_engine_opt 22.52% : 0.101886s : 1: opt_a 0.05% : 0.000228s : 1: opt_after_cconv 0.15% : 0.000677s : 1: opt_after_jit_grad 0.12% : 0.000555s : 1: opt_b 23.39% : 0.105806s : 1: optimize 0.01% : 0.000038s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.01% : 0.000037s : 1: overlap_grad_flash_sp 0.00% : 0.000007s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000008s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000054s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000013s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000008s : 1: partial_unused_args_eliminate 0.00% : 0.000008s : 1: pipeline_parallel_scheduler 0.00% : 0.000015s : 1: pipeline_split 0.01% : 0.000044s : 1: pre_auto_parallel 0.01% : 0.000038s : 1: py_interpret_to_execute 0.01% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000009s : 1: remove_cast_before_assign_add 0.02% : 0.000069s : 1: remove_dup_value 0.21% : 0.000929s : 1: renormalize.infer 0.26% : 0.001177s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000205s : 1: rewriter_after_opt_a 0.02% : 0.000106s : 1: rewriter_before_opt_a 0.00% : 0.000013s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000008s : 1: slice_recompute_activation 0.00% : 0.000009s : 1: split_layernorm_comm 0.00% : 0.000008s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000174s : 1: symbol_engine_optimizer 0.04% : 0.000186s : 1: tuple_transform 24.58% : 0.111218s : 1: type_inference [WARNING] INTERNAL_KERNEL(167124,ffff9519ff30,python3.9):2026-01-29-17:38:42.828.810 [/home/jenkins/agent-working-dir/workspace/executor0/ms_kernels_internal/src/ops/common/internal_op.cc:93] Tiling] op_name: MatMul batch = 1 batch_b = 1 m = 1024 k = 1024 n = 1024 m0 = 128 k0 = 256 n0 = 256 mLoop = 8 kLoop = 4 nLoop = 4 coreLoop = 32 blockDim = 20 swizzleCount = 3 swizzleDirect = 0 enShuffleK = 1 syncAddr = 0 tilingId = 0b0000000000010001 tilingKey = 0b000000 cacheL1ANum = 0 tilingK = 0 tilingN = 0 compressOverlapN = 0 splitK = 0 inputs_[0].GetDtype() = BF16 inputs_[1].GetDtype() = BF16 outputs_[0].GetDtype() = BF16 inputs_[0].GetFormat() = 1 inputs_[1].GetFormat() = 1 outputs_[0].GetFormat() = 1 . [hook] pytest_runtest_teardown:test_matmul_1024_1024_1024[mstype1-False] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024[mstype1-False],max_mem:110.0M [WARNING] ME(167124:281473183252272,MainProcess):2026-01-29-17:38:44.348.576 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 0.241923, [21] [bootstrap]: 0.00069038 [type_inference]: 0.00476054 [event_method]: 1.312e-05 [auto_monad]: 0.00020956 [graph_reusing]: 5.12e-06 [inline]: 1.96e-06 [add_attr]: 0.00574207, [1] [add_attr_with_inline]: 0.00572628, [1] [Cycle 1]: 7.187e-05, [2] [tag_attr]: 1.979e-05 [meta_addattr_fg_expand]: 4.37998e-06 [parallel-infer-symbol]: 4.47e-06 [pre_auto_parallel]: 4.055e-05 [insert-virtual-dataset]: 2.34001e-06 [parallel-infer-symbol-second]: 1.00001e-06 [dataset_repeat_opt]: 2.53e-06 [pipeline_split]: 1.50001e-06 [optimize]: 0.229114, [53] [py_interpret_to_execute]: 2.493e-05 [rewriter_before_opt_a]: 6.687e-05 [opt_a]: 0.00497442, [2] [Cycle 1]: 0.0032304, [45] [expand_dump_flag]: 3.60998e-06 [switch_simplify]: 2.747e-05 [loop_unroll]: 2.459e-05 [a_1]: 0.00086415 [with_stream_mark]: 2.912e-05 [recompute_prepare]: 1.689e-05 [updatestate_depend_eliminate]: 9.91e-06 [updatestate_assign_eliminate]: 6.02001e-06 [updatestate_loads_eliminate]: 8.98002e-06 [parameter_eliminate]: 2.42001e-06 [a_2]: 0.00018229 [accelerated_algorithm]: 3.948e-05 [shard]: 2.91999e-06 [meta_shard_fg_expand]: 2.91e-06 [shard_inline]: 1.048e-05 [merge_send_recv]: 1.3e-05 [auto_parallel]: 1.077e-05 [parallel]: 3.624e-05 [flash_sp]: 1.075e-05 [merge_comm]: 6.44999e-06 [allreduce_fusion]: 8.12e-06 [matmul_add_comm_reduction]: 1.414e-05 [allreduce_slice_to_reducescatter]: 1.08001e-06 [virtual_shard_identity]: 1.626e-05 [virtual_dataset]: 1.148e-05 [get_grad_eliminate_]: 1.149e-05 [virtual_output]: 1.688e-05 [merge_forward]: 7.1e-06 [cell_reuse_recompute_pass]: 1.79e-06 [offload_activation]: 1.668e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.411e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 2.228e-05 [set_forward_comm_id_for_comm_node_pass]: 6.64001e-06 [meta_fg_expand]: 4.68999e-06 [flash_sp_send_recv_attached]: 5.94999e-06 [receive_attached]: 5.76e-06 [after_resolve]: 2.328e-05 [a_after_grad]: 3.138e-05 [renormalize]: 0.0010793 [add_forward_monad_depend]: 7.51999e-06 [auto_monad_grad]: 2.64999e-06 [auto_monad_eliminator]: 4.395e-05 [cse]: 6.618e-05 [a_3]: 9.647e-05 [Cycle 2]: 0.00172663, [45] [expand_dump_flag]: 2.02001e-06 [switch_simplify]: 1.68e-05 [loop_unroll]: 1.42e-05 [a_1]: 0.00042378 [with_stream_mark]: 2.016e-05 [recompute_prepare]: 1.784e-05 [updatestate_depend_eliminate]: 1.026e-05 [updatestate_assign_eliminate]: 5.61e-06 [updatestate_loads_eliminate]: 7.76001e-06 [parameter_eliminate]: 1.77999e-06 [a_2]: 0.00017183 [accelerated_algorithm]: 1.708e-05 [shard]: 4.95001e-06 [meta_shard_fg_expand]: 3.31001e-06 [shard_inline]: 1.052e-05 [merge_send_recv]: 1.043e-05 [auto_parallel]: 1.17e-05 [parallel]: 1.112e-05 [flash_sp]: 4.19997e-06 [merge_comm]: 6.75998e-06 [allreduce_fusion]: 5.84e-06 [matmul_add_comm_reduction]: 1.242e-05 [allreduce_slice_to_reducescatter]: 1.19e-06 [virtual_shard_identity]: 2.455e-05 [virtual_dataset]: 2.116e-05 [get_grad_eliminate_]: 2.115e-05 [virtual_output]: 1.402e-05 [merge_forward]: 1.163e-05 [cell_reuse_recompute_pass]: 2.31998e-06 [offload_activation]: 2.325e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.472e-05 [merge_recompute_call_nodes]: 1.79e-06 [before_grad]: 3.998e-05 [set_forward_comm_id_for_comm_node_pass]: 1.409e-05 [meta_fg_expand]: 4.70999e-06 [flash_sp_send_recv_attached]: 1.50001e-06 [receive_attached]: 2.69999e-06 [after_resolve]: 2.679e-05 [a_after_grad]: 2.485e-05 [renormalize]: 5.9983e-08 [add_forward_monad_depend]: 4.04002e-06 [auto_monad_grad]: 1.92001e-06 [auto_monad_eliminator]: 4.517e-05 [cse]: 9.27e-05 [a_3]: 9.31e-05 [py_interpret_to_execute_after_opt_a]: 2.905e-05 [slice_cell_reuse_recomputed_activation]: 2.35002e-06 [rewriter_after_opt_a]: 0.000193 [convert_after_rewriter]: 1.396e-05 [order_py_execute_after_rewriter]: 7.77998e-06 [mutable_eliminate]: 0.00083751 [opt_b]: 0.0005025, [1] [Cycle 1]: 0.00049333, [7] [b_1]: 0.00032594 [b_2]: 1.798e-05 [updatestate_depend_eliminate]: 1.183e-05 [updatestate_assign_eliminate]: 8.13001e-06 [updatestate_loads_eliminate]: 7.2e-06 [renormalize]: 4.39992e-07 [cse]: 7.179e-05 [optimize_parallel_all_gather_comm]: 2.671e-05 [overlap_param_gather]: 2.79001e-06 [cconv]: 3.601e-05 [loop_unroll]: 0.220765 [opt_after_cconv]: 0.00036737, [1] [Cycle 1]: 0.00034808, [7] [c_1]: 0.00012718 [parameter_eliminate]: 7.78001e-06 [updatestate_depend_eliminate]: 1.879e-05 [updatestate_assign_eliminate]: 6.32001e-06 [updatestate_loads_eliminate]: 1.228e-05 [cse]: 0.00010551 [renormalize]: 1.24e-06 [remove_dup_value]: 3.161e-05 [tuple_transform]: 0.00021773, [1] [Cycle 1]: 0.00021172, [4] [d_1]: 0.00015961 [none_parameter_eliminate]: 2.53e-06 [renormalize]: 3.69997e-07 [switch_simplify]: 1.37e-05 [partial_unused_args_eliminate]: 2.34001e-06 [add_recomputation]: 0.00020129 [cse_after_recomputation]: 5.901e-05, [1] [Cycle 1]: 5.273e-05, [1] [cse]: 3.465e-05 [environ_conv]: 1.16e-05 [swap_dp_allreduce_reducescatter]: 8.50999e-06 [bias_add_comm_swap]: 3.47002e-06 [label_micro_interleaved_index]: 1.827e-05 [label_fine_grained_interleaved_index]: 3.55e-06 [merge_cast_opt]: 1.76e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 3.01999e-06 [assign_add_opt]: 1.55001e-06 [ForceFp32Comm]: 1.12e-06 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.63998e-06 [reorder_send_recv_between_fp_bp]: 3.03e-06 [comm_op_add_attrs]: 1.08001e-06 [add_comm_op_reuse_tag]: 8.79983e-07 [interleave_split_concat_branches]: 1.38002e-06 [interleave_parallel_branches]: 1.47001e-06 [overlap_opt_shard_in_pipeline]: 1.37e-06 [overlap_opt_shard_grad_in_pipeline]: 2.32001e-06 [control_data_broadcast_order]: 2.732e-05 [grouped_pairwise_exchange_alltoall]: 1.64e-06 [offloading_packed_experts]: 9.76e-06 [overlap_recompute_and_grad_model_parallel]: 8.12003e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.37999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.52001e-06 [overlap_grad_ring_attention]: 6.14001e-06 [overlap_grad_flash_sp]: 3.463e-05 [begin_end_overlap_inline]: 1.10999e-06 [split_matmul_comm_elemetwise]: 2.32999e-06 [split_layernorm_comm]: 1.82001e-06 [handle_group_info]: 1.10001e-06 [symbol_engine_optimizer]: 0.00014256, [1] [Cycle 1]: 0.00013581, [6] [build]: 7.21001e-06 [elim_shapecalc]: 2.215e-05 [elim_not_effective]: 2.552e-05 [opt_reshape]: 1.33e-05 [fold_const_symbol]: 1.768e-05 [renormalize]: 1.39989e-07 [detach_backward]: 2.26998e-06 [pipeline_parallel_scheduler]: 1.42e-06 [auto_monad_reorder]: 6.19e-05 [get_jit_bprop_graph]: 2.71e-06 [rewriter_after_jit_bprop_graph]: 7.92e-06 [opt_after_jit_grad]: 0.00096997 [validate]: 7.776e-05 Sums bootstrap : 0.000690s : 0.29% type_inference : 0.004761s : 2.03% event_method : 0.000013s : 0.01% auto_monad : 0.000210s : 0.09% graph_reusing : 0.000005s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000041s : 0.02% insert-virtual-dataset : 0.000002s : 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 : 0.000025s : 0.01% optimize.rewriter_before_opt_a : 0.000067s : 0.03% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000044s : 0.02% optimize.opt_a.loop_unroll : 0.000039s : 0.02% optimize.opt_a.a_1 : 0.001288s : 0.55% optimize.opt_a.with_stream_mark : 0.000049s : 0.02% optimize.opt_a.recompute_prepare : 0.000035s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000354s : 0.15% optimize.opt_a.accelerated_algorithm : 0.000057s : 0.02% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000021s : 0.01% optimize.opt_a.merge_send_recv : 0.000023s : 0.01% optimize.opt_a.auto_parallel : 0.000022s : 0.01% optimize.opt_a.parallel : 0.000047s : 0.02% optimize.opt_a.flash_sp : 0.000015s : 0.01% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000014s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000027s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000041s : 0.02% optimize.opt_a.virtual_dataset : 0.000033s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.01% optimize.opt_a.virtual_output : 0.000031s : 0.01% optimize.opt_a.merge_forward : 0.000019s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000079s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000062s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.01% optimize.opt_a.meta_fg_expand : 0.000009s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.00% optimize.opt_a.after_resolve : 0.000050s : 0.02% optimize.opt_a.a_after_grad : 0.000056s : 0.02% optimize.opt_a.renormalize : 0.001079s : 0.46% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000089s : 0.04% optimize.opt_a.cse : 0.000159s : 0.07% optimize.opt_a.a_3 : 0.000190s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000193s : 0.08% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000838s : 0.36% optimize.opt_b.b_1 : 0.000326s : 0.14% optimize.opt_b.b_2 : 0.000018s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000072s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.01% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000036s : 0.02% optimize.loop_unroll : 0.220765s : 94.16% optimize.opt_after_cconv.c_1 : 0.000127s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.cse : 0.000106s : 0.05% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000032s : 0.01% optimize.tuple_transform.d_1 : 0.000160s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000201s : 0.09% optimize.cse_after_recomputation.cse : 0.000035s : 0.01% optimize.environ_conv : 0.000012s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000018s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000004s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 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 : 0.000027s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000035s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000018s : 0.01% 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 : 0.000062s : 0.03% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000970s : 0.41% validate : 0.000078s : 0.03% Time group info: ------[substitution.] 0.000244 66 4.14% : 0.000010s : 2: substitution.depend_value_elim 1.18% : 0.000003s : 5: substitution.elim_not_effective 1.05% : 0.000003s : 5: substitution.fold_const_symbol 3.65% : 0.000009s : 7: substitution.graph_param_transform 48.29% : 0.000118s : 1: substitution.inline 2.45% : 0.000006s : 10: substitution.j_node_and_user_rematch 9.06% : 0.000022s : 2: substitution.less_batch_normalization 2.24% : 0.000005s : 6: substitution.load_eliminater 3.51% : 0.000009s : 10: substitution.remove_not_recompute_node 2.70% : 0.000007s : 4: substitution.replace_old_param 12.47% : 0.000030s : 6: substitution.updatestate_pure_node_eliminater 9.27% : 0.000023s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.004697 2 87.17% : 0.004094s : 1: type_inference.infer 12.83% : 0.000603s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000117 1 100.00% : 0.000117s : 1: match.inline ------[predicate.] 0.000302 1645 0.70% : 0.000002s : 15: predicate.accumulaten_eliminater 1.53% : 0.000005s : 7: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 14: predicate.addn_check_dump 0.88% : 0.000003s : 15: predicate.addn_zero_filter 0.63% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.00% : 0.000006s : 29: predicate.arithmetic_simplify 0.86% : 0.000003s : 15: predicate.cast_eliminate 0.78% : 0.000002s : 14: predicate.check_bprop_eliminate 0.74% : 0.000002s : 14: predicate.compare_switch_simplify 0.19% : 0.000001s : 7: predicate.const_output_eliminate 0.76% : 0.000002s : 14: predicate.depend_value_elim 0.78% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.84% : 0.000003s : 15: predicate.dict_get_item_eliminator 0.64% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.28% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 7: predicate.elim_not_effective 0.68% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.15% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.11% : 0.000003s : 22: predicate.environ_get_depend_swap 1.63% : 0.000005s : 36: predicate.environ_get_eliminate 0.96% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.76% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.36% : 0.000004s : 16: predicate.float_depend_g_call 0.61% : 0.000002s : 14: predicate.float_environ_get_switch 1.32% : 0.000004s : 21: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 7: predicate.fold_const_symbol 0.75% : 0.000002s : 14: predicate.get_grad_eliminate 0.45% : 0.000001s : 7: predicate.graph_param_transform 0.70% : 0.000002s : 14: predicate.incorporate_call 0.71% : 0.000002s : 14: predicate.incorporate_call_switch 5.24% : 0.000016s : 73: predicate.inline 0.95% : 0.000003s : 14: predicate.inline_without_move 0.37% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.52% : 0.000005s : 14: predicate.less_batch_normalization 1.67% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.19% : 0.000007s : 44: predicate.load_eliminater 3.26% : 0.000010s : 7: predicate.loop_unroll_after_grad 1.04% : 0.000003s : 19: predicate.loop_unroll_before_grad 2.14% : 0.000006s : 29: predicate.make_slice_get_slice_eliminator 0.69% : 0.000002s : 14: predicate.merge_addn 0.89% : 0.000003s : 14: predicate.micro_step_allgather_replace 0.89% : 0.000003s : 14: predicate.mini_step_allgather_replace 0.69% : 0.000002s : 15: predicate.minmaximum_grad 1.51% : 0.000005s : 7: predicate.mutable_eliminate 0.55% : 0.000002s : 7: predicate.opt_reshape 0.53% : 0.000002s : 7: predicate.parallel_virtual_node 1.30% : 0.000004s : 16: predicate.partial_defer_inline 1.05% : 0.000003s : 22: predicate.partial_eliminate 0.73% : 0.000002s : 15: predicate.print_const_string_wrapper 0.73% : 0.000002s : 14: predicate.reduce_all_const_elim 1.08% : 0.000003s : 15: predicate.reduce_eliminate 2.20% : 0.000007s : 44: predicate.redundant_stop_gradient_eliminater 0.71% : 0.000002s : 14: predicate.remove_not_recompute_node 1.01% : 0.000003s : 29: predicate.replace_applicator 0.51% : 0.000002s : 14: predicate.replace_old_param 0.32% : 0.000001s : 7: predicate.reset_defer_inline 0.84% : 0.000003s : 15: predicate.reshape_eliminate 0.73% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.44% : 0.000001s : 7: predicate.row_tensor_eliminate 1.17% : 0.000004s : 14: predicate.same_eliminate 0.50% : 0.000002s : 14: predicate.set_cell_output_no_recompute 1.08% : 0.000003s : 14: predicate.shard_identity_eliminate 0.95% : 0.000003s : 14: predicate.special_op_eliminate 0.75% : 0.000002s : 14: predicate.specialize_transform 1.37% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 1.12% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.43% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.75% : 0.000002s : 16: predicate.switch_defer_inline 1.47% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.39% : 0.000010s : 56: predicate.switch_simplify 0.63% : 0.000002s : 15: predicate.tile_eliminate 0.79% : 0.000002s : 15: predicate.transpose_eliminate 1.52% : 0.000005s : 29: predicate.tuple_list_convert_item_index_to_positive 1.81% : 0.000005s : 29: predicate.tuple_list_get_item_const_eliminator 1.75% : 0.000005s : 29: predicate.tuple_list_get_item_depend_reorder 3.49% : 0.000011s : 43: predicate.tuple_list_get_item_eliminator 1.56% : 0.000005s : 29: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.48% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.20% : 0.000007s : 44: predicate.updatestate_pure_node_eliminater 3.40% : 0.000010s : 58: predicate.updatestate_useless_node_eliminater 0.44% : 0.000001s : 7: predicate.value_based_eliminate 0.94% : 0.000003s : 14: predicate.virtual_dataset_eliminate 0.71% : 0.000002s : 14: predicate.virtual_output_eliminate 0.35% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.48% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000440 4 5.26% : 0.000023s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.74% : 0.000416s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.480745 192 0.00% : 0.000005s : 1: ForceFp32Comm 1.20% : 0.005750s : 1: add_attr 1.19% : 0.005731s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000212s : 1: add_recomputation 0.00% : 0.000014s : 1: assign_add_opt 0.05% : 0.000217s : 1: auto_monad 0.01% : 0.000072s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.15% : 0.000729s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000007s : 1: comm_op_add_attrs 0.01% : 0.000033s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.01% : 0.000063s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.00% : 0.000019s : 1: event_method 0.00% : 0.000009s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000009s : 1: interleave_split_concat_branches 0.00% : 0.000016s : 1: label_fine_grained_interleaved_index 0.01% : 0.000025s : 1: label_micro_interleaved_index 45.93% : 0.220798s : 1: loop_unroll 0.00% : 0.000013s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.18% : 0.000853s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.01% : 0.000067s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000025s : 1: opt.transform.mutable_eliminate 0.48% : 0.002290s : 78: opt.transform.opt_a 0.03% : 0.000124s : 1: opt.transform.opt_after_cconv 0.01% : 0.000068s : 1: opt.transform.opt_after_jit_grad 0.06% : 0.000293s : 28: opt.transform.opt_b 0.04% : 0.000170s : 2: opt.transform.opt_trans_graph 0.02% : 0.000074s : 4: opt.transform.symbol_engine_opt 1.04% : 0.004979s : 1: opt_a 0.08% : 0.000372s : 1: opt_after_cconv 0.21% : 0.000986s : 1: opt_after_jit_grad 0.11% : 0.000506s : 1: opt_b 47.66% : 0.229121s : 1: optimize 0.01% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000044s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000011s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000011s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000045s : 1: pre_auto_parallel 0.01% : 0.000029s : 1: py_interpret_to_execute 0.01% : 0.000043s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000011s : 1: remove_cast_before_assign_add 0.01% : 0.000038s : 1: remove_dup_value 0.11% : 0.000545s : 1: renormalize.infer 0.11% : 0.000524s : 1: renormalize.specialize 0.00% : 0.000013s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000200s : 1: rewriter_after_opt_a 0.02% : 0.000072s : 1: rewriter_before_opt_a 0.00% : 0.000008s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000012s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000146s : 1: symbol_engine_optimizer 0.05% : 0.000221s : 1: tuple_transform 1.00% : 0.004786s : 1: type_inference [WARNING] INTERNAL_KERNEL(167124,ffff9519ff30,python3.9):2026-01-29-17:38:50.141.107 [/home/jenkins/agent-working-dir/workspace/executor0/ms_kernels_internal/src/ops/common/internal_op.cc:93] Tiling] op_name: MatMul batch = 1 batch_b = 1 m = 1024 k = 1024 n = 1024 m0 = 128 k0 = 256 n0 = 256 mLoop = 8 kLoop = 4 nLoop = 4 coreLoop = 32 blockDim = 20 swizzleCount = 3 swizzleDirect = 0 enShuffleK = 1 syncAddr = 0 tilingId = 0b0000000000010001 tilingKey = 0b001000 cacheL1ANum = 0 tilingK = 0 tilingN = 0 compressOverlapN = 0 splitK = 0 inputs_[0].GetDtype() = BF16 inputs_[1].GetDtype() = BF16 outputs_[0].GetDtype() = BF16 inputs_[0].GetFormat() = 1 inputs_[1].GetFormat() = 1 outputs_[0].GetFormat() = 1 . [hook] pytest_runtest_teardown:test_matmul_1024_1024_1024[mstype1-True] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024[mstype1-True],max_mem:110.0M =============================== 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 ================== 4 passed, 25 warnings in 124.60s (0:02:04) ==================