==================================================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_001/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 2 items test_matmul.py [WARNING] ME(159110:281473820356400,MainProcess):2026-01-29-17:37:28.234.524 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 0.264257, [21] [bootstrap]: 0.00064259 [type_inference]: 0.248155 [event_method]: 1.2e-05 [auto_monad]: 0.00018026 [graph_reusing]: 5.05001e-06 [inline]: 2.20002e-06 [add_attr]: 0.00852956, [1] [add_attr_with_inline]: 0.0085127, [1] [Cycle 1]: 8.802e-05, [2] [tag_attr]: 1.701e-05 [meta_addattr_fg_expand]: 3.60998e-06 [parallel-infer-symbol]: 3.56999e-06 [pre_auto_parallel]: 4.133e-05 [insert-virtual-dataset]: 2.73e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 1.76e-06 [pipeline_split]: 1.78002e-06 [optimize]: 0.00585019, [53] [py_interpret_to_execute]: 2.042e-05 [rewriter_before_opt_a]: 7.359e-05 [opt_a]: 0.00307348, [2] [Cycle 1]: 0.00213734, [45] [expand_dump_flag]: 2.87002e-06 [switch_simplify]: 3.264e-05 [loop_unroll]: 1.398e-05 [a_1]: 0.00039773 [with_stream_mark]: 2.014e-05 [recompute_prepare]: 1.034e-05 [updatestate_depend_eliminate]: 6.44999e-06 [updatestate_assign_eliminate]: 7.06001e-06 [updatestate_loads_eliminate]: 1.052e-05 [parameter_eliminate]: 2.37999e-06 [a_2]: 0.00014078 [accelerated_algorithm]: 2.656e-05 [shard]: 2.59001e-06 [meta_shard_fg_expand]: 2.05002e-06 [shard_inline]: 9.17999e-06 [merge_send_recv]: 1.076e-05 [auto_parallel]: 8.63001e-06 [parallel]: 5.037e-05 [flash_sp]: 8.69e-06 [merge_comm]: 6.14001e-06 [allreduce_fusion]: 5.38002e-06 [matmul_add_comm_reduction]: 1.234e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 1.181e-05 [virtual_dataset]: 9.23002e-06 [get_grad_eliminate_]: 9.33002e-06 [virtual_output]: 9.39e-06 [merge_forward]: 6.33e-06 [cell_reuse_recompute_pass]: 1.86e-06 [offload_activation]: 1.34e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.809e-05 [merge_recompute_call_nodes]: 1.71998e-06 [before_grad]: 1.522e-05 [set_forward_comm_id_for_comm_node_pass]: 5.99e-06 [meta_fg_expand]: 3.72998e-06 [flash_sp_send_recv_attached]: 4.81002e-06 [receive_attached]: 2.26998e-06 [after_resolve]: 1.577e-05 [a_after_grad]: 1.454e-05 [renormalize]: 0.00073428 [add_forward_monad_depend]: 5.52999e-06 [auto_monad_grad]: 2.62001e-06 [auto_monad_eliminator]: 4.321e-05 [cse]: 7.029e-05 [a_3]: 7.886e-05 [Cycle 2]: 0.0009235, [45] [expand_dump_flag]: 1.77001e-06 [switch_simplify]: 1.162e-05 [loop_unroll]: 8.90001e-06 [a_1]: 0.00022485 [with_stream_mark]: 1.332e-05 [recompute_prepare]: 9.30001e-06 [updatestate_depend_eliminate]: 5.86998e-06 [updatestate_assign_eliminate]: 4.85999e-06 [updatestate_loads_eliminate]: 6.39999e-06 [parameter_eliminate]: 1.17999e-06 [a_2]: 0.00012473 [accelerated_algorithm]: 1.222e-05 [shard]: 1.39998e-06 [meta_shard_fg_expand]: 2.19001e-06 [shard_inline]: 9.27001e-06 [merge_send_recv]: 7.48999e-06 [auto_parallel]: 9.02e-06 [parallel]: 5.32999e-06 [flash_sp]: 3.66001e-06 [merge_comm]: 5.89e-06 [allreduce_fusion]: 5.35001e-06 [matmul_add_comm_reduction]: 8.71002e-06 [allreduce_slice_to_reducescatter]: 3.69997e-07 [virtual_shard_identity]: 1.055e-05 [virtual_dataset]: 9.32999e-06 [get_grad_eliminate_]: 8.91002e-06 [virtual_output]: 8.48001e-06 [merge_forward]: 5.25999e-06 [cell_reuse_recompute_pass]: 1.51998e-06 [offload_activation]: 1.116e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.704e-05 [merge_recompute_call_nodes]: 7.2e-07 [before_grad]: 1.403e-05 [set_forward_comm_id_for_comm_node_pass]: 6.33998e-06 [meta_fg_expand]: 3.26999e-06 [flash_sp_send_recv_attached]: 1.07998e-06 [receive_attached]: 1.67001e-06 [after_resolve]: 1.301e-05 [a_after_grad]: 1.337e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 1.35999e-06 [auto_monad_grad]: 1.45001e-06 [auto_monad_eliminator]: 2.428e-05 [cse]: 2.832e-05 [a_3]: 6.023e-05 [py_interpret_to_execute_after_opt_a]: 1.463e-05 [slice_cell_reuse_recomputed_activation]: 1.82001e-06 [rewriter_after_opt_a]: 0.00017599 [convert_after_rewriter]: 1.341e-05 [order_py_execute_after_rewriter]: 7.37002e-06 [mutable_eliminate]: 0.00069664 [opt_b]: 0.00032485, [1] [Cycle 1]: 0.00031698, [7] [b_1]: 0.00020973 [b_2]: 1.137e-05 [updatestate_depend_eliminate]: 8.97999e-06 [updatestate_assign_eliminate]: 5.24e-06 [updatestate_loads_eliminate]: 7.03998e-06 [renormalize]: 7.80012e-07 [cse]: 3.778e-05 [optimize_parallel_all_gather_comm]: 2.197e-05 [overlap_param_gather]: 1.81998e-06 [cconv]: 3.275e-05 [loop_unroll]: 0.00046192 [opt_after_cconv]: 0.00015756, [1] [Cycle 1]: 0.00015058, [7] [c_1]: 6.118e-05 [parameter_eliminate]: 4.02e-06 [updatestate_depend_eliminate]: 8.48001e-06 [updatestate_assign_eliminate]: 4.70001e-06 [updatestate_loads_eliminate]: 5.97001e-06 [cse]: 3.058e-05 [renormalize]: 4.39992e-07 [remove_dup_value]: 4.798e-05 [tuple_transform]: 9.921e-05, [1] [Cycle 1]: 9.35e-05, [4] [d_1]: 6.276e-05 [none_parameter_eliminate]: 1.87001e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 1.025e-05 [partial_unused_args_eliminate]: 1.99e-06 [add_recomputation]: 7.313e-05 [cse_after_recomputation]: 3.442e-05, [1] [Cycle 1]: 2.943e-05, [1] [cse]: 2.364e-05 [environ_conv]: 1.923e-05 [swap_dp_allreduce_reducescatter]: 7.75998e-06 [bias_add_comm_swap]: 2.80997e-06 [label_micro_interleaved_index]: 4.52998e-06 [label_fine_grained_interleaved_index]: 2.93e-06 [merge_cast_opt]: 1.57999e-06 [slice_recompute_activation]: 2.11998e-06 [micro_interleaved_order_control]: 2.41e-06 [assign_add_opt]: 1.55001e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 9.89996e-07 [full_micro_interleaved_order_control]: 2.17999e-06 [reorder_send_recv_between_fp_bp]: 2.86e-06 [comm_op_add_attrs]: 1.35001e-06 [add_comm_op_reuse_tag]: 1.01002e-06 [interleave_split_concat_branches]: 1.35999e-06 [interleave_parallel_branches]: 1.22999e-06 [overlap_opt_shard_in_pipeline]: 2.112e-05 [overlap_opt_shard_grad_in_pipeline]: 1.71998e-06 [control_data_broadcast_order]: 1.936e-05 [grouped_pairwise_exchange_alltoall]: 1.46002e-06 [offloading_packed_experts]: 5.66e-06 [overlap_recompute_and_grad_model_parallel]: 6.34999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.17999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37999e-06 [overlap_recompute_comm]: 2.02999e-06 [overlap_grad_ring_attention]: 1.568e-05 [overlap_grad_flash_sp]: 4.102e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.56e-06 [split_layernorm_comm]: 1.65001e-06 [handle_group_info]: 1.05001e-06 [symbol_engine_optimizer]: 0.00010431, [1] [Cycle 1]: 9.904e-05, [6] [build]: 5.25999e-06 [elim_shapecalc]: 1.518e-05 [elim_not_effective]: 1.9e-05 [opt_reshape]: 1.041e-05 [fold_const_symbol]: 2.014e-05 [renormalize]: 3.30008e-07 [detach_backward]: 2.64999e-06 [pipeline_parallel_scheduler]: 1.44e-06 [auto_monad_reorder]: 4.094e-05 [get_jit_bprop_graph]: 1.89e-06 [rewriter_after_jit_bprop_graph]: 5.04998e-06 [opt_after_jit_grad]: 0.00053148 [validate]: 6.933e-05 Sums bootstrap : 0.000643s : 0.25% type_inference : 0.248155s : 97.43% event_method : 0.000012s : 0.00% auto_monad : 0.000180s : 0.07% graph_reusing : 0.000005s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 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 : 0.000003s : 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 : 0.000020s : 0.01% optimize.rewriter_before_opt_a : 0.000074s : 0.03% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000044s : 0.02% optimize.opt_a.loop_unroll : 0.000023s : 0.01% optimize.opt_a.a_1 : 0.000623s : 0.24% optimize.opt_a.with_stream_mark : 0.000033s : 0.01% optimize.opt_a.recompute_prepare : 0.000020s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.00% 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 : 0.000266s : 0.10% optimize.opt_a.accelerated_algorithm : 0.000039s : 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 : 0.000018s : 0.01% optimize.opt_a.merge_send_recv : 0.000018s : 0.01% optimize.opt_a.auto_parallel : 0.000018s : 0.01% optimize.opt_a.parallel : 0.000056s : 0.02% optimize.opt_a.flash_sp : 0.000012s : 0.00% optimize.opt_a.merge_comm : 0.000012s : 0.00% optimize.opt_a.allreduce_fusion : 0.000011s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000022s : 0.01% optimize.opt_a.virtual_dataset : 0.000019s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000018s : 0.01% optimize.opt_a.virtual_output : 0.000018s : 0.01% optimize.opt_a.merge_forward : 0.000012s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000035s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.00% optimize.opt_a.before_grad : 0.000029s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.00% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000029s : 0.01% optimize.opt_a.a_after_grad : 0.000028s : 0.01% optimize.opt_a.renormalize : 0.000734s : 0.29% optimize.opt_a.add_forward_monad_depend : 0.000007s : 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 : 0.000099s : 0.04% optimize.opt_a.a_3 : 0.000139s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000015s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000176s : 0.07% optimize.convert_after_rewriter : 0.000013s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000697s : 0.27% optimize.opt_b.b_1 : 0.000210s : 0.08% optimize.opt_b.b_2 : 0.000011s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000038s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000033s : 0.01% optimize.loop_unroll : 0.000462s : 0.18% optimize.opt_after_cconv.c_1 : 0.000061s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 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 : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.000031s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000048s : 0.02% optimize.tuple_transform.d_1 : 0.000063s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000073s : 0.03% optimize.cse_after_recomputation.cse : 0.000024s : 0.01% optimize.environ_conv : 0.000019s : 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 : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 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 : 0.000021s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 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 : 0.000006s : 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 : 0.000016s : 0.01% optimize.overlap_grad_flash_sp : 0.000041s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000041s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000531s : 0.21% validate : 0.000069s : 0.03% Time group info: ------[substitution.] 0.000188 66 5.03% : 0.000009s : 2: substitution.depend_value_elim 1.53% : 0.000003s : 5: substitution.elim_not_effective 1.15% : 0.000002s : 5: substitution.fold_const_symbol 3.93% : 0.000007s : 7: substitution.graph_param_transform 50.44% : 0.000095s : 1: substitution.inline 2.96% : 0.000006s : 10: substitution.j_node_and_user_rematch 8.77% : 0.000016s : 2: substitution.less_batch_normalization 2.42% : 0.000005s : 6: substitution.load_eliminater 4.27% : 0.000008s : 10: substitution.remove_not_recompute_node 3.89% : 0.000007s : 4: substitution.replace_old_param 8.86% : 0.000017s : 6: substitution.updatestate_pure_node_eliminater 6.74% : 0.000013s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.248091 2 99.85% : 0.247719s : 1: type_inference.infer 0.15% : 0.000371s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000094 1 100.00% : 0.000094s : 1: match.inline ------[predicate.] 0.000247 1645 0.85% : 0.000002s : 15: predicate.accumulaten_eliminater 0.98% : 0.000002s : 7: predicate.ad_related_special_op_eliminate 0.71% : 0.000002s : 14: predicate.addn_check_dump 0.81% : 0.000002s : 15: predicate.addn_zero_filter 0.73% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 1.98% : 0.000005s : 29: predicate.arithmetic_simplify 0.86% : 0.000002s : 15: predicate.cast_eliminate 0.83% : 0.000002s : 14: predicate.check_bprop_eliminate 0.74% : 0.000002s : 14: predicate.compare_switch_simplify 0.24% : 0.000001s : 7: predicate.const_output_eliminate 0.74% : 0.000002s : 14: predicate.depend_value_elim 0.83% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.89% : 0.000002s : 15: predicate.dict_get_item_eliminator 1.04% : 0.000003s : 15: predicate.dict_set_item_eliminator 1.18% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 7: predicate.elim_not_effective 0.61% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.32% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.07% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.19% : 0.000003s : 22: predicate.environ_get_depend_swap 1.91% : 0.000005s : 36: predicate.environ_get_eliminate 1.08% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.85% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.51% : 0.000004s : 16: predicate.float_depend_g_call 0.72% : 0.000002s : 14: predicate.float_environ_get_switch 1.08% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 7: predicate.fold_const_symbol 0.89% : 0.000002s : 14: predicate.get_grad_eliminate 0.33% : 0.000001s : 7: predicate.graph_param_transform 0.75% : 0.000002s : 14: predicate.incorporate_call 0.68% : 0.000002s : 14: predicate.incorporate_call_switch 5.66% : 0.000014s : 73: predicate.inline 1.00% : 0.000002s : 14: predicate.inline_without_move 0.42% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.21% : 0.000003s : 14: predicate.less_batch_normalization 1.81% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 2.34% : 0.000006s : 44: predicate.load_eliminater 1.25% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.07% : 0.000003s : 19: predicate.loop_unroll_before_grad 1.87% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.81% : 0.000002s : 14: predicate.merge_addn 0.91% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.84% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.75% : 0.000002s : 15: predicate.minmaximum_grad 1.36% : 0.000003s : 7: predicate.mutable_eliminate 0.54% : 0.000001s : 7: predicate.opt_reshape 0.47% : 0.000001s : 7: predicate.parallel_virtual_node 1.09% : 0.000003s : 16: predicate.partial_defer_inline 1.32% : 0.000003s : 22: predicate.partial_eliminate 0.78% : 0.000002s : 15: predicate.print_const_string_wrapper 0.75% : 0.000002s : 14: predicate.reduce_all_const_elim 1.05% : 0.000003s : 15: predicate.reduce_eliminate 2.24% : 0.000006s : 44: predicate.redundant_stop_gradient_eliminater 0.66% : 0.000002s : 14: predicate.remove_not_recompute_node 1.13% : 0.000003s : 29: predicate.replace_applicator 0.62% : 0.000002s : 14: predicate.replace_old_param 0.43% : 0.000001s : 7: predicate.reset_defer_inline 0.83% : 0.000002s : 15: predicate.reshape_eliminate 0.92% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.49% : 0.000001s : 7: predicate.row_tensor_eliminate 1.07% : 0.000003s : 14: predicate.same_eliminate 0.53% : 0.000001s : 14: predicate.set_cell_output_no_recompute 0.93% : 0.000002s : 14: predicate.shard_identity_eliminate 0.84% : 0.000002s : 14: predicate.special_op_eliminate 0.96% : 0.000002s : 14: predicate.specialize_transform 1.06% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 1.07% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.47% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.88% : 0.000002s : 16: predicate.switch_defer_inline 1.71% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.66% : 0.000009s : 56: predicate.switch_simplify 0.80% : 0.000002s : 15: predicate.tile_eliminate 0.92% : 0.000002s : 15: predicate.transpose_eliminate 1.56% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.71% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000004s : 29: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000007s : 43: predicate.tuple_list_get_item_eliminator 1.63% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.62% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.63% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 2.31% : 0.000006s : 44: predicate.updatestate_pure_node_eliminater 3.37% : 0.000008s : 58: predicate.updatestate_useless_node_eliminater 0.48% : 0.000001s : 7: predicate.value_based_eliminate 0.89% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.82% : 0.000002s : 14: predicate.virtual_output_eliminate 0.40% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.53% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000213 4 9.96% : 0.000021s : 1: func_graph_cloner_run.FuncGraphClonerGraph 90.04% : 0.000192s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.280939 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.04% : 0.008536s : 1: add_attr 3.03% : 0.008519s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000077s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.07% : 0.000188s : 1: auto_monad 0.02% : 0.000046s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.24% : 0.000686s : 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% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000037s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000023s : 1: environ_conv 0.01% : 0.000018s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000005s : 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% : 0.000007s : 1: label_micro_interleaved_index 0.17% : 0.000471s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.25% : 0.000709s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000022s : 1: opt.transform.mutable_eliminate 0.45% : 0.001277s : 78: opt.transform.opt_a 0.02% : 0.000060s : 1: opt.transform.opt_after_cconv 0.01% : 0.000035s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000194s : 28: opt.transform.opt_b 0.03% : 0.000071s : 2: opt.transform.opt_trans_graph 0.02% : 0.000060s : 4: opt.transform.symbol_engine_opt 1.10% : 0.003077s : 1: opt_a 0.06% : 0.000161s : 1: opt_after_cconv 0.19% : 0.000542s : 1: opt_after_jit_grad 0.12% : 0.000328s : 1: opt_b 2.08% : 0.005856s : 1: optimize 0.01% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000019s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000025s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000045s : 1: pre_auto_parallel 0.01% : 0.000024s : 1: py_interpret_to_execute 0.01% : 0.000018s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000052s : 1: remove_dup_value 0.15% : 0.000424s : 1: renormalize.infer 0.11% : 0.000301s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000182s : 1: rewriter_after_opt_a 0.03% : 0.000078s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000107s : 1: symbol_engine_optimizer 0.04% : 0.000102s : 1: tuple_transform 88.34% : 0.248173s : 1: type_inference [WARNING] INTERNAL_KERNEL(159110,ffffbb136f30,python3.9):2026-01-29-17:37:59.331.814 [/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_nz_input_fp16[mstype0-False] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024_nz_input_fp16[mstype0-False],max_mem:110.0M [WARNING] ME(159110:281473820356400,MainProcess):2026-01-29-17:38:03.844.489 [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 = 0.0222038, [21] [bootstrap]: 0.00061382 [type_inference]: 0.00465632 [event_method]: 1.346e-05 [auto_monad]: 0.0002367 [graph_reusing]: 7.75e-06 [inline]: 2.35002e-06 [add_attr]: 0.00555289, [1] [add_attr_with_inline]: 0.00553576, [1] [Cycle 1]: 8.277e-05, [2] [tag_attr]: 2.248e-05 [meta_addattr_fg_expand]: 3.91001e-06 [parallel-infer-symbol]: 4.54002e-06 [pre_auto_parallel]: 7.238e-05 [insert-virtual-dataset]: 2.72001e-06 [parallel-infer-symbol-second]: 9.70002e-07 [dataset_repeat_opt]: 2.46998e-06 [pipeline_split]: 1.71e-06 [optimize]: 0.00983722, [53] [py_interpret_to_execute]: 3.583e-05 [rewriter_before_opt_a]: 7.684e-05 [opt_a]: 0.00568998, [2] [Cycle 1]: 0.00361352, [45] [expand_dump_flag]: 2.88998e-06 [switch_simplify]: 3.987e-05 [loop_unroll]: 1.635e-05 [a_1]: 0.00080144 [with_stream_mark]: 3.25e-05 [recompute_prepare]: 2.466e-05 [updatestate_depend_eliminate]: 8.06001e-06 [updatestate_assign_eliminate]: 9.38002e-06 [updatestate_loads_eliminate]: 1.11e-05 [parameter_eliminate]: 2.79001e-06 [a_2]: 0.00019031 [accelerated_algorithm]: 4.219e-05 [shard]: 4.90999e-06 [meta_shard_fg_expand]: 3.42002e-06 [shard_inline]: 1.433e-05 [merge_send_recv]: 1.349e-05 [auto_parallel]: 1.264e-05 [parallel]: 3.636e-05 [flash_sp]: 1.338e-05 [merge_comm]: 1.527e-05 [allreduce_fusion]: 6.31e-06 [matmul_add_comm_reduction]: 1.541e-05 [allreduce_slice_to_reducescatter]: 8.09989e-07 [virtual_shard_identity]: 2.333e-05 [virtual_dataset]: 1.578e-05 [get_grad_eliminate_]: 1.725e-05 [virtual_output]: 1.442e-05 [merge_forward]: 7.87998e-06 [cell_reuse_recompute_pass]: 2.04999e-06 [offload_activation]: 2.191e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.678e-05 [merge_recompute_call_nodes]: 2.01998e-06 [before_grad]: 2.438e-05 [set_forward_comm_id_for_comm_node_pass]: 7.16001e-06 [meta_fg_expand]: 4.94e-06 [flash_sp_send_recv_attached]: 7.13e-06 [receive_attached]: 2.39001e-06 [after_resolve]: 2.476e-05 [a_after_grad]: 2.579e-05 [renormalize]: 0.00131137 [add_forward_monad_depend]: 9.70002e-06 [auto_monad_grad]: 3.33e-06 [auto_monad_eliminator]: 5.482e-05 [cse]: 7.441e-05 [a_3]: 0.00011573 [Cycle 2]: 0.00205717, [45] [expand_dump_flag]: 2.40002e-06 [switch_simplify]: 1.587e-05 [loop_unroll]: 1.528e-05 [a_1]: 0.00051012 [with_stream_mark]: 2.797e-05 [recompute_prepare]: 2.191e-05 [updatestate_depend_eliminate]: 9.08002e-06 [updatestate_assign_eliminate]: 6.64001e-06 [updatestate_loads_eliminate]: 1.001e-05 [parameter_eliminate]: 2.67001e-06 [a_2]: 0.00023041 [accelerated_algorithm]: 3.117e-05 [shard]: 4.72e-06 [meta_shard_fg_expand]: 3.65e-06 [shard_inline]: 1.268e-05 [merge_send_recv]: 1.339e-05 [auto_parallel]: 1.335e-05 [parallel]: 1.343e-05 [flash_sp]: 5.12999e-06 [merge_comm]: 9.28002e-06 [allreduce_fusion]: 6.20002e-06 [matmul_add_comm_reduction]: 1.789e-05 [allreduce_slice_to_reducescatter]: 7.79983e-07 [virtual_shard_identity]: 2.759e-05 [virtual_dataset]: 1.482e-05 [get_grad_eliminate_]: 1.212e-05 [virtual_output]: 1.454e-05 [merge_forward]: 8.22e-06 [cell_reuse_recompute_pass]: 2.74001e-06 [offload_activation]: 2.546e-05 [cell_reuse_handle_not_recompute_node_pass]: 8.121e-05 [merge_recompute_call_nodes]: 2.36e-06 [before_grad]: 4.089e-05 [set_forward_comm_id_for_comm_node_pass]: 1.029e-05 [meta_fg_expand]: 4.63999e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 2.03997e-06 [after_resolve]: 2.799e-05 [a_after_grad]: 3.498e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 3.96001e-06 [auto_monad_grad]: 2.95002e-06 [auto_monad_eliminator]: 6.002e-05 [cse]: 0.00012542 [a_3]: 0.00010323 [py_interpret_to_execute_after_opt_a]: 2.793e-05 [slice_cell_reuse_recomputed_activation]: 2.39999e-06 [rewriter_after_opt_a]: 0.00020351 [convert_after_rewriter]: 1.286e-05 [order_py_execute_after_rewriter]: 7.82e-06 [mutable_eliminate]: 0.00091362 [opt_b]: 0.00061097, [1] [Cycle 1]: 0.00059651, [7] [b_1]: 0.00039427 [b_2]: 2.014e-05 [updatestate_depend_eliminate]: 1.401e-05 [updatestate_assign_eliminate]: 6.34999e-06 [updatestate_loads_eliminate]: 1.013e-05 [renormalize]: 7.30011e-07 [cse]: 7.787e-05 [optimize_parallel_all_gather_comm]: 2.896e-05 [overlap_param_gather]: 2.41e-06 [cconv]: 4.282e-05 [loop_unroll]: 0.00071379 [opt_after_cconv]: 0.00028919, [1] [Cycle 1]: 0.00027896, [7] [c_1]: 0.00010456 [parameter_eliminate]: 5.16998e-06 [updatestate_depend_eliminate]: 1.167e-05 [updatestate_assign_eliminate]: 8.00999e-06 [updatestate_loads_eliminate]: 8.2e-06 [cse]: 7.371e-05 [renormalize]: 7.30011e-07 [remove_dup_value]: 2.94e-05 [tuple_transform]: 0.00019739, [1] [Cycle 1]: 0.0001885, [4] [d_1]: 0.00014262 [none_parameter_eliminate]: 2.34001e-06 [renormalize]: 2.30008e-07 [switch_simplify]: 1.215e-05 [partial_unused_args_eliminate]: 2.79999e-06 [add_recomputation]: 0.00011652 [cse_after_recomputation]: 7.759e-05, [1] [Cycle 1]: 7.139e-05, [1] [cse]: 5.837e-05 [environ_conv]: 9.41e-06 [swap_dp_allreduce_reducescatter]: 1.475e-05 [bias_add_comm_swap]: 3.81001e-06 [label_micro_interleaved_index]: 6.89001e-06 [label_fine_grained_interleaved_index]: 3.03e-06 [merge_cast_opt]: 1.80001e-06 [slice_recompute_activation]: 2.19001e-06 [micro_interleaved_order_control]: 2.91999e-06 [assign_add_opt]: 1.35999e-06 [ForceFp32Comm]: 1.14e-06 [remove_cast_before_assign_add]: 9.5999e-07 [full_micro_interleaved_order_control]: 2.64001e-06 [reorder_send_recv_between_fp_bp]: 3.37002e-06 [comm_op_add_attrs]: 1.47001e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.82001e-06 [interleave_parallel_branches]: 1.27999e-06 [overlap_opt_shard_in_pipeline]: 3.39001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.86e-06 [control_data_broadcast_order]: 2.379e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 6.67002e-06 [overlap_recompute_and_grad_model_parallel]: 9.71e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.60001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.66002e-06 [overlap_recompute_comm]: 2.58003e-06 [overlap_grad_ring_attention]: 6.84999e-06 [overlap_grad_flash_sp]: 3.299e-05 [begin_end_overlap_inline]: 7.2e-07 [split_matmul_comm_elemetwise]: 2.40002e-06 [split_layernorm_comm]: 2.31e-06 [handle_group_info]: 1.64e-06 [symbol_engine_optimizer]: 0.00017484, [1] [Cycle 1]: 0.00016563, [6] [build]: 5.73002e-06 [elim_shapecalc]: 2.459e-05 [elim_not_effective]: 3.587e-05 [opt_reshape]: 1.571e-05 [fold_const_symbol]: 1.921e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.46998e-06 [pipeline_parallel_scheduler]: 1.76e-06 [auto_monad_reorder]: 4.806e-05 [get_jit_bprop_graph]: 2.36e-06 [rewriter_after_jit_bprop_graph]: 8.15999e-06 [opt_after_jit_grad]: 0.00083949 [validate]: 9.425e-05 Sums bootstrap : 0.000614s : 4.15% type_inference : 0.004656s : 31.49% event_method : 0.000013s : 0.09% auto_monad : 0.000237s : 1.60% graph_reusing : 0.000008s : 0.05% inline : 0.000002s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000022s : 0.15% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000005s : 0.03% pre_auto_parallel : 0.000072s : 0.49% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.02% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000036s : 0.24% optimize.rewriter_before_opt_a : 0.000077s : 0.52% optimize.opt_a.expand_dump_flag : 0.000005s : 0.04% optimize.opt_a.switch_simplify : 0.000056s : 0.38% optimize.opt_a.loop_unroll : 0.000032s : 0.21% optimize.opt_a.a_1 : 0.001312s : 8.87% optimize.opt_a.with_stream_mark : 0.000060s : 0.41% optimize.opt_a.recompute_prepare : 0.000047s : 0.31% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.12% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.11% optimize.opt_a.updatestate_loads_eliminate : 0.000021s : 0.14% optimize.opt_a.parameter_eliminate : 0.000005s : 0.04% optimize.opt_a.a_2 : 0.000421s : 2.85% optimize.opt_a.accelerated_algorithm : 0.000073s : 0.50% optimize.opt_a.shard : 0.000010s : 0.07% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.05% optimize.opt_a.shard_inline : 0.000027s : 0.18% optimize.opt_a.merge_send_recv : 0.000027s : 0.18% optimize.opt_a.auto_parallel : 0.000026s : 0.18% optimize.opt_a.parallel : 0.000050s : 0.34% optimize.opt_a.flash_sp : 0.000019s : 0.13% optimize.opt_a.merge_comm : 0.000025s : 0.17% optimize.opt_a.allreduce_fusion : 0.000013s : 0.08% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.23% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000051s : 0.34% optimize.opt_a.virtual_dataset : 0.000031s : 0.21% optimize.opt_a.get_grad_eliminate_ : 0.000029s : 0.20% optimize.opt_a.virtual_output : 0.000029s : 0.20% optimize.opt_a.merge_forward : 0.000016s : 0.11% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.03% optimize.opt_a.offload_activation : 0.000047s : 0.32% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000118s : 0.80% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.03% optimize.opt_a.before_grad : 0.000065s : 0.44% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000017s : 0.12% optimize.opt_a.meta_fg_expand : 0.000010s : 0.06% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.06% optimize.opt_a.receive_attached : 0.000004s : 0.03% optimize.opt_a.after_resolve : 0.000053s : 0.36% optimize.opt_a.a_after_grad : 0.000061s : 0.41% optimize.opt_a.renormalize : 0.001311s : 8.87% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.09% optimize.opt_a.auto_monad_grad : 0.000006s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000115s : 0.78% optimize.opt_a.cse : 0.000200s : 1.35% optimize.opt_a.a_3 : 0.000219s : 1.48% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.19% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.02% optimize.rewriter_after_opt_a : 0.000204s : 1.38% optimize.convert_after_rewriter : 0.000013s : 0.09% optimize.order_py_execute_after_rewriter : 0.000008s : 0.05% optimize.mutable_eliminate : 0.000914s : 6.18% optimize.opt_b.b_1 : 0.000394s : 2.67% optimize.opt_b.b_2 : 0.000020s : 0.14% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.04% optimize.opt_b.updatestate_loads_eliminate : 0.000010s : 0.07% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000078s : 0.53% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.20% optimize.overlap_param_gather : 0.000002s : 0.02% optimize.cconv : 0.000043s : 0.29% optimize.loop_unroll : 0.000714s : 4.83% optimize.opt_after_cconv.c_1 : 0.000105s : 0.71% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.08% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.05% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.06% optimize.opt_after_cconv.cse : 0.000074s : 0.50% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000029s : 0.20% optimize.tuple_transform.d_1 : 0.000143s : 0.96% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.02% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.08% optimize.partial_unused_args_eliminate : 0.000003s : 0.02% optimize.add_recomputation : 0.000117s : 0.79% optimize.cse_after_recomputation.cse : 0.000058s : 0.39% optimize.environ_conv : 0.000009s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000015s : 0.10% optimize.bias_add_comm_swap : 0.000004s : 0.03% optimize.label_micro_interleaved_index : 0.000007s : 0.05% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000003s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000002s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000024s : 0.16% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000007s : 0.05% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.07% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000007s : 0.05% optimize.overlap_grad_flash_sp : 0.000033s : 0.22% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.02% optimize.handle_group_info : 0.000002s : 0.01% optimize.symbol_engine_optimizer.build : 0.000006s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.17% optimize.symbol_engine_optimizer.elim_not_effective : 0.000036s : 0.24% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.11% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.13% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000048s : 0.33% get_jit_bprop_graph : 0.000002s : 0.02% rewriter_after_jit_bprop_graph : 0.000008s : 0.06% opt_after_jit_grad : 0.000839s : 5.68% validate : 0.000094s : 0.64% Time group info: ------[substitution.] 0.000288 66 3.84% : 0.000011s : 2: substitution.depend_value_elim 1.01% : 0.000003s : 5: substitution.elim_not_effective 0.78% : 0.000002s : 5: substitution.fold_const_symbol 2.95% : 0.000008s : 7: substitution.graph_param_transform 52.97% : 0.000152s : 1: substitution.inline 2.91% : 0.000008s : 10: substitution.j_node_and_user_rematch 8.23% : 0.000024s : 2: substitution.less_batch_normalization 1.99% : 0.000006s : 6: substitution.load_eliminater 3.90% : 0.000011s : 10: substitution.remove_not_recompute_node 2.98% : 0.000009s : 4: substitution.replace_old_param 8.56% : 0.000025s : 6: substitution.updatestate_pure_node_eliminater 9.87% : 0.000028s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.004587 2 87.93% : 0.004034s : 1: type_inference.infer 12.07% : 0.000553s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000151 1 100.00% : 0.000151s : 1: match.inline ------[predicate.] 0.000293 1645 0.84% : 0.000002s : 15: predicate.accumulaten_eliminater 1.25% : 0.000004s : 7: predicate.ad_related_special_op_eliminate 0.69% : 0.000002s : 14: predicate.addn_check_dump 0.72% : 0.000002s : 15: predicate.addn_zero_filter 0.74% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.25% : 0.000007s : 29: predicate.arithmetic_simplify 0.81% : 0.000002s : 15: predicate.cast_eliminate 0.81% : 0.000002s : 14: predicate.check_bprop_eliminate 0.81% : 0.000002s : 14: predicate.compare_switch_simplify 0.23% : 0.000001s : 7: predicate.const_output_eliminate 0.87% : 0.000003s : 14: predicate.depend_value_elim 0.79% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.95% : 0.000003s : 15: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.72% : 0.000005s : 14: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 7: predicate.elim_not_effective 0.52% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 22: predicate.environ_get_add_eliminate 1.07% : 0.000003s : 22: predicate.environ_get_depend_swap 2.06% : 0.000006s : 36: predicate.environ_get_eliminate 1.10% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.36% : 0.000004s : 16: predicate.float_depend_g_call 0.73% : 0.000002s : 14: predicate.float_environ_get_switch 1.13% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 7: predicate.fold_const_symbol 0.92% : 0.000003s : 14: predicate.get_grad_eliminate 0.30% : 0.000001s : 7: predicate.graph_param_transform 0.69% : 0.000002s : 14: predicate.incorporate_call 0.67% : 0.000002s : 14: predicate.incorporate_call_switch 6.12% : 0.000018s : 73: predicate.inline 1.29% : 0.000004s : 14: predicate.inline_without_move 0.37% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.71% : 0.000005s : 14: predicate.less_batch_normalization 1.56% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.18% : 0.000006s : 44: predicate.load_eliminater 0.94% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.19% : 0.000003s : 19: predicate.loop_unroll_before_grad 1.73% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.75% : 0.000002s : 14: predicate.merge_addn 0.70% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.68% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.72% : 0.000002s : 15: predicate.minmaximum_grad 1.12% : 0.000003s : 7: predicate.mutable_eliminate 0.46% : 0.000001s : 7: predicate.opt_reshape 0.45% : 0.000001s : 7: predicate.parallel_virtual_node 1.12% : 0.000003s : 16: predicate.partial_defer_inline 1.28% : 0.000004s : 22: predicate.partial_eliminate 0.74% : 0.000002s : 15: predicate.print_const_string_wrapper 0.73% : 0.000002s : 14: predicate.reduce_all_const_elim 1.01% : 0.000003s : 15: predicate.reduce_eliminate 2.27% : 0.000007s : 44: predicate.redundant_stop_gradient_eliminater 0.68% : 0.000002s : 14: predicate.remove_not_recompute_node 1.12% : 0.000003s : 29: predicate.replace_applicator 0.61% : 0.000002s : 14: predicate.replace_old_param 0.30% : 0.000001s : 7: predicate.reset_defer_inline 0.82% : 0.000002s : 15: predicate.reshape_eliminate 0.86% : 0.000003s : 14: predicate.row_tensor_add_zeros_like 0.56% : 0.000002s : 7: predicate.row_tensor_eliminate 1.26% : 0.000004s : 14: predicate.same_eliminate 0.55% : 0.000002s : 14: predicate.set_cell_output_no_recompute 1.14% : 0.000003s : 14: predicate.shard_identity_eliminate 1.03% : 0.000003s : 14: predicate.special_op_eliminate 0.90% : 0.000003s : 14: predicate.specialize_transform 1.23% : 0.000004s : 14: predicate.split_environ_get_set_with_tuple_value 1.11% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.43% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.92% : 0.000003s : 16: predicate.switch_defer_inline 1.54% : 0.000005s : 30: predicate.switch_layer_defer_inline 3.48% : 0.000010s : 56: predicate.switch_simplify 0.92% : 0.000003s : 15: predicate.tile_eliminate 0.78% : 0.000002s : 15: predicate.transpose_eliminate 1.54% : 0.000005s : 29: predicate.tuple_list_convert_item_index_to_positive 1.50% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.54% : 0.000005s : 29: predicate.tuple_list_get_item_depend_reorder 2.99% : 0.000009s : 43: predicate.tuple_list_get_item_eliminator 1.74% : 0.000005s : 29: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.56% : 0.000005s : 29: predicate.tuple_to_list_eliminator_ 2.16% : 0.000006s : 44: predicate.updatestate_pure_node_eliminater 3.46% : 0.000010s : 58: predicate.updatestate_useless_node_eliminater 0.45% : 0.000001s : 7: predicate.value_based_eliminate 0.98% : 0.000003s : 14: predicate.virtual_dataset_eliminate 1.04% : 0.000003s : 14: predicate.virtual_output_eliminate 0.38% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.57% : 0.000002s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000451 4 5.41% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.59% : 0.000427s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.041983 192 0.01% : 0.000004s : 1: ForceFp32Comm 13.25% : 0.005561s : 1: add_attr 13.20% : 0.005540s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.29% : 0.000122s : 1: add_recomputation 0.02% : 0.000008s : 1: assign_add_opt 0.59% : 0.000246s : 1: auto_monad 0.13% : 0.000053s : 1: auto_monad_reorder 0.03% : 0.000014s : 1: begin_end_overlap_inline 0.02% : 0.000007s : 1: bias_add_comm_swap 1.53% : 0.000644s : 1: bootstrap 0.12% : 0.000052s : 1: cconv 0.01% : 0.000004s : 1: comm_op_add_attrs 0.07% : 0.000029s : 1: control_data_broadcast_order 0.04% : 0.000017s : 1: convert_after_rewriter 0.20% : 0.000084s : 1: cse_after_recomputation 0.01% : 0.000006s : 1: dataset_repeat_opt 0.02% : 0.000006s : 1: detach_backward 0.03% : 0.000013s : 1: environ_conv 0.05% : 0.000021s : 1: event_method 0.02% : 0.000008s : 1: full_micro_interleaved_order_control 0.01% : 0.000006s : 1: get_jit_bprop_graph 0.03% : 0.000012s : 1: graph_reusing 0.03% : 0.000011s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000005s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.02% : 0.000007s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000005s : 1: interleave_split_concat_branches 0.04% : 0.000016s : 1: label_fine_grained_interleaved_index 0.02% : 0.000010s : 1: label_micro_interleaved_index 1.74% : 0.000730s : 1: loop_unroll 0.01% : 0.000005s : 1: merge_cast_opt 0.01% : 0.000006s : 1: micro_interleaved_order_control 2.34% : 0.000984s : 1: mutable_eliminate 0.03% : 0.000011s : 1: offloading_packed_experts 0.07% : 0.000030s : 1: opt.transform.loop_unroll_optimizer 0.08% : 0.000032s : 1: opt.transform.mutable_eliminate 5.87% : 0.002465s : 78: opt.transform.opt_a 0.24% : 0.000103s : 1: opt.transform.opt_after_cconv 0.16% : 0.000065s : 1: opt.transform.opt_after_jit_grad 0.86% : 0.000362s : 28: opt.transform.opt_b 0.36% : 0.000152s : 2: opt.transform.opt_trans_graph 0.22% : 0.000090s : 4: opt.transform.symbol_engine_opt 13.57% : 0.005697s : 1: opt_a 0.70% : 0.000293s : 1: opt_after_cconv 2.04% : 0.000857s : 1: opt_after_jit_grad 1.48% : 0.000619s : 1: opt_b 23.45% : 0.009844s : 1: optimize 0.10% : 0.000040s : 1: optimize_parallel_all_gather_comm 0.03% : 0.000015s : 1: order_py_execute_after_rewriter 0.09% : 0.000039s : 1: overlap_grad_flash_sp 0.01% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.03% : 0.000011s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.03% : 0.000011s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000006s : 1: overlap_param_gather 0.01% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.04% : 0.000017s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000006s : 1: overlap_recompute_comm 0.02% : 0.000009s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.02% : 0.000009s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.19% : 0.000079s : 1: pre_auto_parallel 0.10% : 0.000040s : 1: py_interpret_to_execute 0.08% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.08% : 0.000034s : 1: remove_dup_value 1.55% : 0.000653s : 1: renormalize.infer 1.53% : 0.000644s : 1: renormalize.specialize 0.04% : 0.000016s : 1: reorder_send_recv_between_fp_bp 0.05% : 0.000020s : 1: rewriter_after_jit_bprop_graph 0.50% : 0.000211s : 1: rewriter_after_opt_a 0.20% : 0.000082s : 1: rewriter_before_opt_a 0.02% : 0.000009s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.02% : 0.000009s : 1: split_layernorm_comm 0.01% : 0.000006s : 1: split_matmul_comm_elemetwise 0.04% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.42% : 0.000178s : 1: symbol_engine_optimizer 0.48% : 0.000201s : 1: tuple_transform 11.15% : 0.004680s : 1: type_inference [WARNING] INTERNAL_KERNEL(159110,ffffbb136f30,python3.9):2026-01-29-17:38:07.997.886 [/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_nz_input_fp16[mstype0-True] tests/st/infer/ops/test_internal_ops/test_matmul.py::test_matmul_1024_1024_1024_nz_input_fp16[mstype0-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 ================== 2 passed, 25 warnings in 82.74s (0:01:22) ===================