==================================================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/mint, configfile: ../../../../../../sault/virtual_test/virtualenv_002/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 6 items test_repeat_interleave.py . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[0-pynative] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[0-pynative],max_mem:2.0M TotalTime = 1.20958, [21] [bootstrap]: 0.00073794 [type_inference]: 1.0149 [event_method]: 0.00038583 [auto_monad]: 0.00015338 [graph_reusing]: 9.12001e-06 [inline]: 2.56998e-06 [add_attr]: 0.184307, [1] [add_attr_with_inline]: 0.184287, [1] [Cycle 1]: 0.00014931, [2] [tag_attr]: 4.904e-05 [meta_addattr_fg_expand]: 9.61e-06 [parallel-infer-symbol]: 4.37e-06 [pre_auto_parallel]: 7.735e-05 [insert-virtual-dataset]: 3.28998e-06 [parallel-infer-symbol-second]: 8.99978e-07 [dataset_repeat_opt]: 2.24999e-06 [pipeline_split]: 1.81e-06 [optimize]: 0.00797955, [53] [py_interpret_to_execute]: 1.058e-05 [rewriter_before_opt_a]: 0.00039222 [opt_a]: 0.00441794, [2] [Cycle 1]: 0.00375433, [45] [expand_dump_flag]: 4.15e-06 [switch_simplify]: 6.359e-05 [loop_unroll]: 4.488e-05 [a_1]: 0.00093209 [with_stream_mark]: 2.087e-05 [recompute_prepare]: 9.08002e-06 [updatestate_depend_eliminate]: 4.89e-06 [updatestate_assign_eliminate]: 4.38001e-06 [updatestate_loads_eliminate]: 3.77002e-06 [parameter_eliminate]: 2.68e-06 [a_2]: 8.832e-05 [accelerated_algorithm]: 7.4e-06 [shard]: 2.23002e-06 [meta_shard_fg_expand]: 2.98998e-06 [shard_inline]: 6.21e-06 [merge_send_recv]: 1.01e-05 [auto_parallel]: 8.29002e-06 [parallel]: 5.337e-05 [flash_sp]: 1.03e-05 [merge_comm]: 5.05999e-06 [allreduce_fusion]: 3.87002e-06 [matmul_add_comm_reduction]: 9.84999e-06 [allreduce_slice_to_reducescatter]: 7.2e-07 [virtual_shard_identity]: 1.015e-05 [virtual_dataset]: 7.24001e-06 [get_grad_eliminate_]: 6.58998e-06 [virtual_output]: 6.96001e-06 [merge_forward]: 4.44002e-06 [cell_reuse_recompute_pass]: 1.24998e-06 [offload_activation]: 1.139e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.359e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 1.26e-05 [set_forward_comm_id_for_comm_node_pass]: 3.78001e-06 [meta_fg_expand]: 4.22e-06 [flash_sp_send_recv_attached]: 2.89999e-06 [receive_attached]: 1.227e-05 [after_resolve]: 1.239e-05 [a_after_grad]: 1.015e-05 [renormalize]: 0.00191604 [add_forward_monad_depend]: 8.69998e-06 [auto_monad_grad]: 3.19001e-06 [auto_monad_eliminator]: 2.018e-05 [cse]: 5.372e-05 [a_3]: 5.782e-05 [Cycle 2]: 0.00064968, [45] [expand_dump_flag]: 2.63e-06 [switch_simplify]: 8.28999e-06 [loop_unroll]: 6.02001e-06 [a_1]: 0.00010372 [with_stream_mark]: 1.842e-05 [recompute_prepare]: 6.28998e-06 [updatestate_depend_eliminate]: 4.56002e-06 [updatestate_assign_eliminate]: 3.3e-06 [updatestate_loads_eliminate]: 3.25998e-06 [parameter_eliminate]: 1.97001e-06 [a_2]: 6.941e-05 [accelerated_algorithm]: 5.91998e-06 [shard]: 2.27999e-06 [meta_shard_fg_expand]: 2.46998e-06 [shard_inline]: 5.74e-06 [merge_send_recv]: 7.71999e-06 [auto_parallel]: 8.79e-06 [parallel]: 8.07e-06 [flash_sp]: 3.60998e-06 [merge_comm]: 3.58999e-06 [allreduce_fusion]: 3.48e-06 [matmul_add_comm_reduction]: 8.07e-06 [allreduce_slice_to_reducescatter]: 5.50004e-07 [virtual_shard_identity]: 6.86001e-06 [virtual_dataset]: 5.72999e-06 [get_grad_eliminate_]: 6.34999e-06 [virtual_output]: 5.76e-06 [merge_forward]: 3.98999e-06 [cell_reuse_recompute_pass]: 2.62001e-06 [offload_activation]: 1.005e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.497e-05 [merge_recompute_call_nodes]: 1.09e-06 [before_grad]: 9.99001e-06 [set_forward_comm_id_for_comm_node_pass]: 3.95e-06 [meta_fg_expand]: 2.81e-06 [flash_sp_send_recv_attached]: 1.40999e-06 [receive_attached]: 1.84998e-06 [after_resolve]: 1.014e-05 [a_after_grad]: 8.02998e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.90001e-06 [auto_monad_grad]: 1.94e-06 [auto_monad_eliminator]: 7.7e-06 [cse]: 1.968e-05 [a_3]: 3.536e-05 [py_interpret_to_execute_after_opt_a]: 6.23998e-06 [slice_cell_reuse_recomputed_activation]: 1.96e-06 [rewriter_after_opt_a]: 3.856e-05 [convert_after_rewriter]: 1.34e-06 [order_py_execute_after_rewriter]: 1.15001e-06 [mutable_eliminate]: 0.00077952 [opt_b]: 0.00027089, [1] [Cycle 1]: 0.00026139, [7] [b_1]: 0.00016354 [b_2]: 1.02e-05 [updatestate_depend_eliminate]: 9.43002e-06 [updatestate_assign_eliminate]: 2.79001e-06 [updatestate_loads_eliminate]: 2.99999e-06 [renormalize]: 6.19999e-07 [cse]: 3.046e-05 [optimize_parallel_all_gather_comm]: 2.113e-05 [overlap_param_gather]: 5.12e-06 [cconv]: 3.67e-05 [loop_unroll]: 0.00049672 [opt_after_cconv]: 0.00011162, [1] [Cycle 1]: 0.00010496, [7] [c_1]: 2.685e-05 [parameter_eliminate]: 3.83999e-06 [updatestate_depend_eliminate]: 6.49999e-06 [updatestate_assign_eliminate]: 2.89999e-06 [updatestate_loads_eliminate]: 2.63e-06 [cse]: 2.533e-05 [renormalize]: 4.70027e-07 [remove_dup_value]: 2.049e-05 [tuple_transform]: 7.817e-05, [1] [Cycle 1]: 7.292e-05, [4] [d_1]: 4.514e-05 [none_parameter_eliminate]: 2.12001e-06 [renormalize]: 2.09984e-07 [switch_simplify]: 6.39001e-06 [partial_unused_args_eliminate]: 2.30002e-06 [add_recomputation]: 6.165e-05 [cse_after_recomputation]: 2.772e-05, [1] [Cycle 1]: 2.195e-05, [1] [cse]: 1.562e-05 [environ_conv]: 1.857e-05 [swap_dp_allreduce_reducescatter]: 6.06998e-06 [bias_add_comm_swap]: 2.94999e-06 [label_micro_interleaved_index]: 5.19998e-06 [label_fine_grained_interleaved_index]: 3.18e-06 [merge_cast_opt]: 1.47001e-06 [slice_recompute_activation]: 3.08998e-06 [micro_interleaved_order_control]: 0.00045511 [assign_add_opt]: 2.48e-06 [ForceFp32Comm]: 1.30999e-06 [remove_cast_before_assign_add]: 1.32999e-06 [full_micro_interleaved_order_control]: 4.77e-06 [reorder_send_recv_between_fp_bp]: 4.565e-05 [comm_op_add_attrs]: 1.57001e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 2.34001e-06 [interleave_parallel_branches]: 1.25999e-06 [overlap_opt_shard_in_pipeline]: 4.241e-05 [overlap_opt_shard_grad_in_pipeline]: 2.61e-06 [control_data_broadcast_order]: 2.349e-05 [grouped_pairwise_exchange_alltoall]: 1.72001e-06 [offloading_packed_experts]: 5.38002e-06 [overlap_recompute_and_grad_model_parallel]: 5.28002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.45999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.60999e-06 [overlap_recompute_comm]: 2.63998e-06 [overlap_grad_ring_attention]: 4.88001e-06 [overlap_grad_flash_sp]: 4.216e-05 [begin_end_overlap_inline]: 5.89993e-07 [split_matmul_comm_elemetwise]: 2.86e-06 [split_layernorm_comm]: 2.51e-06 [handle_group_info]: 1.19e-06 [symbol_engine_optimizer]: 0.00010622, [1] [Cycle 1]: 9.898e-05, [6] [build]: 5.59e-06 [elim_shapecalc]: 1.984e-05 [elim_not_effective]: 1.723e-05 [opt_reshape]: 8.08001e-06 [fold_const_symbol]: 1.071e-05 [renormalize]: 4.69998e-07 [detach_backward]: 2.63e-06 [pipeline_parallel_scheduler]: 1.60999e-06 [auto_monad_reorder]: 3.097e-05 [get_jit_bprop_graph]: 1.72001e-06 [rewriter_after_jit_bprop_graph]: 6.44999e-06 [opt_after_jit_grad]: 0.0006753 [validate]: 7.214e-05 Sums bootstrap : 0.000738s : 0.07% type_inference : 1.014896s : 99.11% event_method : 0.000386s : 0.04% auto_monad : 0.000153s : 0.01% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000049s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000010s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000077s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000011s : 0.00% optimize.rewriter_before_opt_a : 0.000392s : 0.04% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000072s : 0.01% optimize.opt_a.loop_unroll : 0.000051s : 0.00% optimize.opt_a.a_1 : 0.001036s : 0.10% optimize.opt_a.with_stream_mark : 0.000039s : 0.00% optimize.opt_a.recompute_prepare : 0.000015s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000158s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000013s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.00% optimize.opt_a.merge_send_recv : 0.000018s : 0.00% optimize.opt_a.auto_parallel : 0.000017s : 0.00% optimize.opt_a.parallel : 0.000061s : 0.01% optimize.opt_a.flash_sp : 0.000014s : 0.00% optimize.opt_a.merge_comm : 0.000009s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000018s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000017s : 0.00% optimize.opt_a.virtual_dataset : 0.000013s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000013s : 0.00% optimize.opt_a.virtual_output : 0.000013s : 0.00% optimize.opt_a.merge_forward : 0.000008s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000021s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000029s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000023s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 0.00% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000014s : 0.00% optimize.opt_a.after_resolve : 0.000023s : 0.00% optimize.opt_a.a_after_grad : 0.000018s : 0.00% optimize.opt_a.renormalize : 0.001916s : 0.19% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000028s : 0.00% optimize.opt_a.cse : 0.000073s : 0.01% optimize.opt_a.a_3 : 0.000093s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000006s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000039s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000780s : 0.08% optimize.opt_b.b_1 : 0.000164s : 0.02% optimize.opt_b.b_2 : 0.000010s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000030s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000021s : 0.00% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000497s : 0.05% optimize.opt_after_cconv.c_1 : 0.000027s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000025s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000020s : 0.00% optimize.tuple_transform.d_1 : 0.000045s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000062s : 0.01% optimize.cse_after_recomputation.cse : 0.000016s : 0.00% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 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 : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000455s : 0.04% 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 : 0.000005s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000046s : 0.00% optimize.comm_op_add_attrs : 0.000002s : 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 : 0.000042s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000003s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000017s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000011s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000031s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000675s : 0.07% validate : 0.000072s : 0.01% Time group info: ------[substitution.] 0.000304 28 0.68% : 0.000002s : 2: substitution.elim_not_effective 0.51% : 0.000002s : 2: substitution.fold_const_symbol 2.15% : 0.000007s : 3: substitution.graph_param_transform 86.11% : 0.000262s : 7: substitution.inline 1.51% : 0.000005s : 4: substitution.j_node_and_user_rematch 1.81% : 0.000006s : 4: substitution.remove_not_recompute_node 1.44% : 0.000004s : 2: substitution.replace_old_param 5.79% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 1.014781 2 99.68% : 1.011499s : 1: type_inference.infer 0.32% : 0.003282s : 1: type_inference.specialize ------[replace.] 0.000123 11 69.30% : 0.000085s : 7: replace.inline 30.70% : 0.000038s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000274 11 94.24% : 0.000258s : 7: match.inline 5.76% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000241 1291 1.18% : 0.000003s : 15: predicate.accumulaten_eliminater 1.16% : 0.000003s : 3: predicate.ad_related_special_op_eliminate 0.36% : 0.000001s : 6: predicate.addn_check_dump 1.17% : 0.000003s : 15: predicate.addn_zero_filter 1.01% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.28% : 0.000006s : 21: predicate.arithmetic_simplify 1.18% : 0.000003s : 15: predicate.cast_eliminate 0.51% : 0.000001s : 6: predicate.check_bprop_eliminate 0.43% : 0.000001s : 6: predicate.compare_switch_simplify 0.12% : 0.000000s : 3: predicate.const_output_eliminate 0.43% : 0.000001s : 6: predicate.depend_value_elim 0.99% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.01% : 0.000002s : 15: predicate.dict_get_item_eliminator 1.15% : 0.000003s : 15: predicate.dict_set_item_eliminator 0.92% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.22% : 0.000001s : 3: predicate.elim_not_effective 0.51% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.06% : 0.000003s : 18: predicate.environ_get_add_eliminate 1.27% : 0.000003s : 18: predicate.environ_get_depend_swap 1.65% : 0.000004s : 24: predicate.environ_get_eliminate 1.18% : 0.000003s : 18: predicate.environ_get_set_eliminate 1.57% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.51% : 0.000006s : 26: predicate.float_depend_g_call 0.41% : 0.000001s : 6: predicate.float_environ_get_switch 0.51% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.12% : 0.000000s : 3: predicate.fold_const_symbol 0.86% : 0.000002s : 6: predicate.get_grad_eliminate 0.20% : 0.000000s : 3: predicate.graph_param_transform 0.39% : 0.000001s : 6: predicate.incorporate_call 0.34% : 0.000001s : 6: predicate.incorporate_call_switch 5.87% : 0.000014s : 59: predicate.inline 0.51% : 0.000001s : 6: predicate.inline_without_move 0.21% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.78% : 0.000002s : 6: predicate.less_batch_normalization 1.95% : 0.000005s : 25: predicate.list_to_tuple_eliminator_ 2.44% : 0.000006s : 40: predicate.load_eliminater 0.94% : 0.000002s : 3: predicate.loop_unroll_after_grad 2.72% : 0.000007s : 49: predicate.loop_unroll_before_grad 1.82% : 0.000004s : 21: predicate.make_slice_get_slice_eliminator 0.66% : 0.000002s : 6: predicate.merge_addn 0.60% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.46% : 0.000001s : 6: predicate.mini_step_allgather_replace 1.05% : 0.000003s : 15: predicate.minmaximum_grad 1.04% : 0.000003s : 3: predicate.mutable_eliminate 0.36% : 0.000001s : 3: predicate.opt_reshape 0.56% : 0.000001s : 3: predicate.parallel_virtual_node 2.14% : 0.000005s : 26: predicate.partial_defer_inline 1.39% : 0.000003s : 22: predicate.partial_eliminate 1.00% : 0.000002s : 15: predicate.print_const_string_wrapper 0.55% : 0.000001s : 6: predicate.reduce_all_const_elim 1.32% : 0.000003s : 15: predicate.reduce_eliminate 2.41% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.36% : 0.000001s : 6: predicate.remove_not_recompute_node 1.11% : 0.000003s : 25: predicate.replace_applicator 0.39% : 0.000001s : 6: predicate.replace_old_param 0.19% : 0.000000s : 3: predicate.reset_defer_inline 1.13% : 0.000003s : 15: predicate.reshape_eliminate 0.39% : 0.000001s : 6: predicate.row_tensor_add_zeros_like 0.42% : 0.000001s : 3: predicate.row_tensor_eliminate 0.75% : 0.000002s : 6: predicate.same_eliminate 0.29% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.78% : 0.000002s : 6: predicate.shard_identity_eliminate 0.64% : 0.000002s : 6: predicate.special_op_eliminate 0.48% : 0.000001s : 6: predicate.specialize_transform 0.94% : 0.000002s : 6: predicate.split_environ_get_set_with_tuple_value 0.60% : 0.000001s : 6: predicate.stack_unstack_eliminate 0.34% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.68% : 0.000004s : 26: predicate.switch_defer_inline 2.12% : 0.000005s : 32: predicate.switch_layer_defer_inline 5.40% : 0.000013s : 84: predicate.switch_simplify 1.00% : 0.000002s : 15: predicate.tile_eliminate 1.02% : 0.000002s : 15: predicate.transpose_eliminate 1.78% : 0.000004s : 21: predicate.tuple_list_convert_item_index_to_positive 1.58% : 0.000004s : 21: predicate.tuple_list_get_item_const_eliminator 1.68% : 0.000004s : 21: predicate.tuple_list_get_item_depend_reorder 3.34% : 0.000008s : 31: predicate.tuple_list_get_item_eliminator 1.54% : 0.000004s : 21: predicate.tuple_list_get_set_item_eliminator 2.42% : 0.000006s : 27: predicate.tuple_list_set_item_eliminator 1.62% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.47% : 0.000006s : 40: predicate.updatestate_pure_node_eliminater 2.91% : 0.000007s : 46: predicate.updatestate_useless_node_eliminater 0.31% : 0.000001s : 3: predicate.value_based_eliminate 0.54% : 0.000001s : 6: predicate.virtual_dataset_eliminate 0.51% : 0.000001s : 6: predicate.virtual_output_eliminate 0.18% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.46% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.096089 18 99.05% : 0.095179s : 9: func_graph_cloner_run.FuncGraphClonerGraph 0.95% : 0.000910s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.405327 192 0.00% : 0.000006s : 1: ForceFp32Comm 13.12% : 0.184315s : 1: add_attr 13.11% : 0.184292s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000067s : 1: add_recomputation 0.00% : 0.000013s : 1: assign_add_opt 0.01% : 0.000164s : 1: auto_monad 0.00% : 0.000037s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.06% : 0.000781s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000024s : 1: environ_conv 0.03% : 0.000404s : 1: event_method 0.00% : 0.000008s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.04% : 0.000509s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.03% : 0.000470s : 1: micro_interleaved_order_control 0.06% : 0.000793s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000020s : 1: opt.transform.mutable_eliminate 0.11% : 0.001500s : 78: opt.transform.opt_a 0.00% : 0.000025s : 1: opt.transform.opt_after_cconv 0.00% : 0.000031s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000144s : 28: opt.transform.opt_b 0.00% : 0.000048s : 2: opt.transform.opt_trans_graph 0.00% : 0.000049s : 4: opt.transform.symbol_engine_opt 0.31% : 0.004422s : 1: opt_a 0.01% : 0.000116s : 1: opt_after_cconv 0.05% : 0.000691s : 1: opt_after_jit_grad 0.02% : 0.000275s : 1: opt_b 0.57% : 0.007987s : 1: optimize 0.00% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000050s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 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% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000082s : 1: pre_auto_parallel 0.00% : 0.000015s : 1: py_interpret_to_execute 0.00% : 0.000010s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.00% : 0.000024s : 1: remove_dup_value 0.07% : 0.001011s : 1: renormalize.infer 0.06% : 0.000892s : 1: renormalize.specialize 0.00% : 0.000056s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000043s : 1: rewriter_after_opt_a 0.03% : 0.000398s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000109s : 1: symbol_engine_optimizer 0.01% : 0.000081s : 1: tuple_transform 72.22% : 1.014932s : 1: type_inference TotalTime = 0.765047, [21] [bootstrap]: 0.00056939 [type_inference]: 0.451414 [event_method]: 0.0002786 [auto_monad]: 0.00022487 [graph_reusing]: 1.159e-05 [inline]: 3.38999e-06 [add_attr]: 0.00514719, [1] [add_attr_with_inline]: 0.00513344, [1] [Cycle 1]: 0.00014544, [2] [tag_attr]: 8.007e-05 [meta_addattr_fg_expand]: 1.393e-05 [parallel-infer-symbol]: 4.70999e-06 [pre_auto_parallel]: 9.144e-05 [insert-virtual-dataset]: 3.42002e-06 [parallel-infer-symbol-second]: 9.20001e-07 [dataset_repeat_opt]: 2.94001e-06 [pipeline_split]: 2.01e-06 [optimize]: 0.306356, [53] [py_interpret_to_execute]: 8.53001e-06 [rewriter_before_opt_a]: 0.00058014 [opt_a]: 0.303283, [3] [Cycle 1]: 0.284897, [45] [expand_dump_flag]: 6.26e-06 [switch_simplify]: 0.00019928 [loop_unroll]: 8.598e-05 [a_1]: 0.00197223 [with_stream_mark]: 4.628e-05 [recompute_prepare]: 3.226e-05 [updatestate_depend_eliminate]: 1.23e-05 [updatestate_assign_eliminate]: 8.13001e-06 [updatestate_loads_eliminate]: 7.63999e-06 [parameter_eliminate]: 5.12999e-06 [a_2]: 0.00023386 [accelerated_algorithm]: 1.807e-05 [shard]: 2.26e-06 [meta_shard_fg_expand]: 5.91e-06 [shard_inline]: 1.58e-05 [merge_send_recv]: 2.14e-05 [auto_parallel]: 1.795e-05 [parallel]: 3.603e-05 [flash_sp]: 5.968e-05 [merge_comm]: 4.477e-05 [allreduce_fusion]: 1.016e-05 [matmul_add_comm_reduction]: 5.141e-05 [allreduce_slice_to_reducescatter]: 1.17e-06 [virtual_shard_identity]: 5.387e-05 [virtual_dataset]: 1.717e-05 [get_grad_eliminate_]: 1.547e-05 [virtual_output]: 1.447e-05 [merge_forward]: 1.365e-05 [cell_reuse_recompute_pass]: 4.38999e-06 [offload_activation]: 2.113e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.552e-05 [merge_recompute_call_nodes]: 1.66e-06 [before_grad]: 4.569e-05 [set_forward_comm_id_for_comm_node_pass]: 1.21e-05 [meta_fg_expand]: 0.00245145 [flash_sp_send_recv_attached]: 5.33002e-06 [receive_attached]: 2.46e-06 [after_resolve]: 8.573e-05 [a_after_grad]: 0.00010221 [renormalize]: 0.149115 [add_forward_monad_depend]: 2.062e-05 [auto_monad_grad]: 8.43001e-06 [auto_monad_eliminator]: 7.146e-05 [cse]: 0.00039297 [a_3]: 0.0003634 [Cycle 2]: 0.0177057, [45] [expand_dump_flag]: 3.83999e-06 [switch_simplify]: 4.755e-05 [loop_unroll]: 4.114e-05 [a_1]: 0.00135979 [with_stream_mark]: 3.028e-05 [recompute_prepare]: 1.309e-05 [updatestate_depend_eliminate]: 5.56e-06 [updatestate_assign_eliminate]: 4.13999e-06 [updatestate_loads_eliminate]: 3.93001e-06 [parameter_eliminate]: 2.71e-06 [a_2]: 0.00010257 [accelerated_algorithm]: 9.15999e-06 [shard]: 2.21e-06 [meta_shard_fg_expand]: 2.74001e-06 [shard_inline]: 7.80998e-06 [merge_send_recv]: 1.041e-05 [auto_parallel]: 1.171e-05 [parallel]: 9.56998e-06 [flash_sp]: 8.59e-06 [merge_comm]: 4.97e-06 [allreduce_fusion]: 4.60001e-06 [matmul_add_comm_reduction]: 1.16e-05 [allreduce_slice_to_reducescatter]: 9.70002e-07 [virtual_shard_identity]: 9.94001e-06 [virtual_dataset]: 8.07e-06 [get_grad_eliminate_]: 8.42e-06 [virtual_output]: 7.42002e-06 [merge_forward]: 5.29e-06 [cell_reuse_recompute_pass]: 1.48002e-06 [offload_activation]: 1.324e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.915e-05 [merge_recompute_call_nodes]: 1.66e-06 [before_grad]: 1.228e-05 [set_forward_comm_id_for_comm_node_pass]: 4.99998e-06 [meta_fg_expand]: 0.0125693 [flash_sp_send_recv_attached]: 4.94e-06 [receive_attached]: 4.17e-06 [after_resolve]: 4.116e-05 [a_after_grad]: 1.611e-05 [renormalize]: 0.00282698 [add_forward_monad_depend]: 1.134e-05 [auto_monad_grad]: 2.43e-06 [auto_monad_eliminator]: 2.273e-05 [cse]: 3.371e-05 [a_3]: 4.798e-05 [Cycle 3]: 0.00065323, [45] [expand_dump_flag]: 2.31e-06 [switch_simplify]: 7.21999e-06 [loop_unroll]: 4.12e-06 [a_1]: 5.887e-05 [with_stream_mark]: 1.735e-05 [recompute_prepare]: 4.95999e-06 [updatestate_depend_eliminate]: 3.46999e-06 [updatestate_assign_eliminate]: 2.93e-06 [updatestate_loads_eliminate]: 2.43002e-06 [parameter_eliminate]: 2.48e-06 [a_2]: 4.248e-05 [accelerated_algorithm]: 4.16001e-06 [shard]: 3.16999e-06 [meta_shard_fg_expand]: 2.27001e-06 [shard_inline]: 3.98999e-06 [merge_send_recv]: 8.72998e-06 [auto_parallel]: 9.14998e-06 [parallel]: 8.498e-05 [flash_sp]: 1.99e-06 [merge_comm]: 2.98e-06 [allreduce_fusion]: 2.58e-06 [matmul_add_comm_reduction]: 1.061e-05 [allreduce_slice_to_reducescatter]: 9.5999e-07 [virtual_shard_identity]: 7.95e-06 [virtual_dataset]: 4.08001e-06 [get_grad_eliminate_]: 3.73001e-06 [virtual_output]: 4e-06 [merge_forward]: 3.61001e-06 [cell_reuse_recompute_pass]: 3.05998e-06 [offload_activation]: 9.83002e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.668e-05 [merge_recompute_call_nodes]: 1.99999e-06 [before_grad]: 8.65999e-06 [set_forward_comm_id_for_comm_node_pass]: 2.81e-06 [meta_fg_expand]: 2.16998e-06 [flash_sp_send_recv_attached]: 2.06e-06 [receive_attached]: 2.00002e-06 [after_resolve]: 4.94e-06 [a_after_grad]: 5.74e-06 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.69999e-06 [auto_monad_grad]: 1.72001e-06 [auto_monad_eliminator]: 7.01999e-06 [cse]: 1.802e-05 [a_3]: 4.616e-05 [py_interpret_to_execute_after_opt_a]: 8.48999e-06 [slice_cell_reuse_recomputed_activation]: 3.68e-06 [rewriter_after_opt_a]: 2.164e-05 [convert_after_rewriter]: 1.49e-06 [order_py_execute_after_rewriter]: 1.32e-06 [mutable_eliminate]: 0.00086422 [opt_b]: 0.00023232, [1] [Cycle 1]: 0.00022257, [7] [b_1]: 0.0001299 [b_2]: 6.47001e-06 [updatestate_depend_eliminate]: 9.66e-06 [updatestate_assign_eliminate]: 2.51998e-06 [updatestate_loads_eliminate]: 2.41e-06 [renormalize]: 9.50007e-07 [cse]: 2.885e-05 [optimize_parallel_all_gather_comm]: 2.064e-05 [overlap_param_gather]: 1.92001e-06 [cconv]: 4.051e-05 [loop_unroll]: 0.00056745 [opt_after_cconv]: 9.801e-05, [1] [Cycle 1]: 8.943e-05, [7] [c_1]: 1.715e-05 [parameter_eliminate]: 5.05999e-06 [updatestate_depend_eliminate]: 7.16999e-06 [updatestate_assign_eliminate]: 2.03002e-06 [updatestate_loads_eliminate]: 1.87999e-06 [cse]: 2.024e-05 [renormalize]: 9.09989e-07 [remove_dup_value]: 1.65e-05 [tuple_transform]: 6.376e-05, [1] [Cycle 1]: 5.692e-05, [4] [d_1]: 3.038e-05 [none_parameter_eliminate]: 1.57001e-06 [renormalize]: 2.09984e-07 [switch_simplify]: 5.81e-06 [partial_unused_args_eliminate]: 2.94999e-06 [add_recomputation]: 6.64e-05 [cse_after_recomputation]: 2.536e-05, [1] [Cycle 1]: 1.956e-05, [1] [cse]: 1.284e-05 [environ_conv]: 6.23e-06 [swap_dp_allreduce_reducescatter]: 6.05002e-06 [bias_add_comm_swap]: 2.99999e-06 [label_micro_interleaved_index]: 5.18002e-06 [label_fine_grained_interleaved_index]: 2.92002e-06 [merge_cast_opt]: 1.54e-06 [slice_recompute_activation]: 2.83e-06 [micro_interleaved_order_control]: 2.45002e-06 [assign_add_opt]: 1.42e-06 [ForceFp32Comm]: 1.05999e-06 [remove_cast_before_assign_add]: 1.12999e-06 [full_micro_interleaved_order_control]: 2.17001e-06 [reorder_send_recv_between_fp_bp]: 2.72001e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.59e-06 [interleave_split_concat_branches]: 1.45999e-06 [interleave_parallel_branches]: 1.11002e-06 [overlap_opt_shard_in_pipeline]: 1.25999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.17999e-06 [control_data_broadcast_order]: 1.327e-05 [grouped_pairwise_exchange_alltoall]: 1.84998e-06 [offloading_packed_experts]: 4.05998e-06 [overlap_recompute_and_grad_model_parallel]: 4.41002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57001e-06 [overlap_recompute_comm]: 2.76999e-06 [overlap_grad_ring_attention]: 3.42997e-06 [overlap_grad_flash_sp]: 2.122e-05 [begin_end_overlap_inline]: 6.30011e-07 [split_matmul_comm_elemetwise]: 2.49001e-06 [split_layernorm_comm]: 2.11003e-06 [handle_group_info]: 1.40999e-06 [symbol_engine_optimizer]: 7.32e-05, [1] [Cycle 1]: 6.818e-05, [6] [build]: 3.33e-06 [elim_shapecalc]: 1.039e-05 [elim_not_effective]: 1.104e-05 [opt_reshape]: 5.49998e-06 [fold_const_symbol]: 6.84999e-06 [renormalize]: 2.09984e-07 [detach_backward]: 2.76999e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 1.897e-05 [get_jit_bprop_graph]: 2.17001e-06 [rewriter_after_jit_bprop_graph]: 6.59001e-06 [opt_after_jit_grad]: 0.00059698 [validate]: 7.745e-05 Sums bootstrap : 0.000569s : 0.09% type_inference : 0.451414s : 71.70% event_method : 0.000279s : 0.04% auto_monad : 0.000225s : 0.04% graph_reusing : 0.000012s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000080s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000014s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000091s : 0.01% 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 : 0.000009s : 0.00% optimize.rewriter_before_opt_a : 0.000580s : 0.09% optimize.opt_a.expand_dump_flag : 0.000012s : 0.00% optimize.opt_a.switch_simplify : 0.000254s : 0.04% optimize.opt_a.loop_unroll : 0.000131s : 0.02% optimize.opt_a.a_1 : 0.003391s : 0.54% optimize.opt_a.with_stream_mark : 0.000094s : 0.01% optimize.opt_a.recompute_prepare : 0.000050s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000379s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000031s : 0.00% optimize.opt_a.shard : 0.000008s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.00% optimize.opt_a.shard_inline : 0.000028s : 0.00% optimize.opt_a.merge_send_recv : 0.000041s : 0.01% optimize.opt_a.auto_parallel : 0.000039s : 0.01% optimize.opt_a.parallel : 0.000131s : 0.02% optimize.opt_a.flash_sp : 0.000070s : 0.01% optimize.opt_a.merge_comm : 0.000053s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000074s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000072s : 0.01% optimize.opt_a.virtual_dataset : 0.000029s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.00% optimize.opt_a.virtual_output : 0.000026s : 0.00% optimize.opt_a.merge_forward : 0.000023s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000009s : 0.00% optimize.opt_a.offload_activation : 0.000044s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000091s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000067s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.00% optimize.opt_a.meta_fg_expand : 0.015023s : 2.39% optimize.opt_a.flash_sp_send_recv_attached : 0.000012s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000132s : 0.02% optimize.opt_a.a_after_grad : 0.000124s : 0.02% optimize.opt_a.renormalize : 0.151942s : 24.13% optimize.opt_a.add_forward_monad_depend : 0.000035s : 0.01% optimize.opt_a.auto_monad_grad : 0.000013s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000101s : 0.02% optimize.opt_a.cse : 0.000445s : 0.07% optimize.opt_a.a_3 : 0.000458s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000008s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.00% optimize.rewriter_after_opt_a : 0.000022s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000864s : 0.14% optimize.opt_b.b_1 : 0.000130s : 0.02% optimize.opt_b.b_2 : 0.000006s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000029s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000021s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000567s : 0.09% optimize.opt_after_cconv.c_1 : 0.000017s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000020s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000030s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000066s : 0.01% optimize.cse_after_recomputation.cse : 0.000013s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 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 : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000002s : 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 : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000004s : 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 : 0.000003s : 0.00% optimize.overlap_grad_flash_sp : 0.000021s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000010s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000011s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000005s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000007s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000019s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000597s : 0.09% validate : 0.000077s : 0.01% Time group info: ------[substitution.] 0.001080 161 0.18% : 0.000002s : 1: substitution.elim_not_effective 1.08% : 0.000012s : 12: substitution.float_depend_g_call 0.53% : 0.000006s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000001s : 1: substitution.fold_const_symbol 0.49% : 0.000005s : 1: substitution.graph_param_transform 0.39% : 0.000004s : 2: substitution.incorporate_call 0.21% : 0.000002s : 2: substitution.incorporate_call_switch 67.09% : 0.000724s : 23: substitution.inline 2.56% : 0.000028s : 2: substitution.inline_without_move 2.62% : 0.000028s : 12: substitution.j_node_and_user_rematch 1.12% : 0.000012s : 7: substitution.minmaximum_grad 3.35% : 0.000036s : 12: substitution.partial_eliminate 1.17% : 0.000013s : 12: substitution.remove_not_recompute_node 2.77% : 0.000030s : 9: substitution.replace_applicator 0.77% : 0.000008s : 11: substitution.replace_old_param 0.84% : 0.000009s : 1: substitution.reshape_eliminate 0.36% : 0.000004s : 1: substitution.set_cell_output_no_recompute 1.41% : 0.000015s : 3: substitution.switch_simplify 2.49% : 0.000027s : 7: substitution.tuple_list_convert_item_index_to_positive 0.99% : 0.000011s : 7: substitution.tuple_list_get_item_const_eliminator 1.48% : 0.000016s : 7: substitution.tuple_list_get_item_depend_reorder 6.53% : 0.000070s : 19: substitution.tuple_list_get_item_eliminator 1.48% : 0.000016s : 7: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.451238 2 74.15% : 0.334589s : 1: type_inference.infer 25.85% : 0.116649s : 1: type_inference.specialize ------[replace.] 0.000393 36 60.54% : 0.000238s : 23: replace.inline 13.76% : 0.000054s : 3: replace.switch_simplify 25.70% : 0.000101s : 10: replace.tuple_list_get_item_eliminator ------[match.] 0.000759 36 93.68% : 0.000711s : 23: match.inline 1.68% : 0.000013s : 3: match.switch_simplify 4.64% : 0.000035s : 10: match.tuple_list_get_item_eliminator ------[predicate.] 0.000686 4012 1.16% : 0.000008s : 53: predicate.accumulaten_eliminater 0.26% : 0.000002s : 1: predicate.ad_related_special_op_eliminate 0.45% : 0.000003s : 17: predicate.addn_check_dump 1.28% : 0.000009s : 53: predicate.addn_zero_filter 1.07% : 0.000007s : 53: predicate.adjust_all_reduce_mul_add 1.91% : 0.000013s : 70: predicate.arithmetic_simplify 1.03% : 0.000007s : 53: predicate.cast_eliminate 0.98% : 0.000007s : 42: predicate.check_bprop_eliminate 0.39% : 0.000003s : 17: predicate.compare_switch_simplify 0.02% : 0.000000s : 1: predicate.const_output_eliminate 0.45% : 0.000003s : 17: predicate.depend_value_elim 1.16% : 0.000008s : 53: predicate.dict_get_item_const_eliminator 1.11% : 0.000008s : 53: predicate.dict_get_item_eliminator 1.06% : 0.000007s : 53: predicate.dict_set_item_eliminator 0.26% : 0.000002s : 2: predicate.dumpgradient_eliminate 0.03% : 0.000000s : 1: predicate.elim_not_effective 0.11% : 0.000001s : 1: predicate.elim_shapecalc_of_broadcastargs 1.29% : 0.000009s : 54: predicate.environ_add_const_eliminate 1.21% : 0.000008s : 54: predicate.environ_get_add_eliminate 1.11% : 0.000008s : 54: predicate.environ_get_depend_swap 1.42% : 0.000010s : 71: predicate.environ_get_eliminate 1.04% : 0.000007s : 54: predicate.environ_get_set_eliminate 1.77% : 0.000012s : 86: predicate.exchange_switch_depend_value 2.79% : 0.000019s : 86: predicate.float_depend_g_call 0.43% : 0.000003s : 17: predicate.float_environ_get_switch 0.47% : 0.000003s : 18: predicate.float_tuple_getitem_switch 0.01% : 0.000000s : 1: predicate.fold_const_symbol 0.57% : 0.000004s : 17: predicate.get_grad_eliminate 0.08% : 0.000001s : 1: predicate.graph_param_transform 0.39% : 0.000003s : 17: predicate.incorporate_call 0.32% : 0.000002s : 17: predicate.incorporate_call_switch 5.19% : 0.000036s : 175: predicate.inline 1.59% : 0.000011s : 47: predicate.inline_without_move 0.18% : 0.000001s : 17: predicate.j_node_and_user_rematch 0.66% : 0.000004s : 17: predicate.less_batch_normalization 1.41% : 0.000010s : 65: predicate.list_to_tuple_eliminator_ 2.58% : 0.000018s : 118: predicate.load_eliminater 0.31% : 0.000002s : 1: predicate.loop_unroll_after_grad 2.96% : 0.000020s : 136: predicate.loop_unroll_before_grad 1.51% : 0.000010s : 55: predicate.make_slice_get_slice_eliminator 0.46% : 0.000003s : 17: predicate.merge_addn 0.91% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.96% : 0.000007s : 42: predicate.mini_step_allgather_replace 1.05% : 0.000007s : 53: predicate.minmaximum_grad 0.33% : 0.000002s : 1: predicate.mutable_eliminate 0.09% : 0.000001s : 1: predicate.opt_reshape 0.06% : 0.000000s : 1: predicate.parallel_virtual_node 2.53% : 0.000017s : 86: predicate.partial_defer_inline 1.45% : 0.000010s : 64: predicate.partial_eliminate 1.01% : 0.000007s : 53: predicate.print_const_string_wrapper 0.46% : 0.000003s : 17: predicate.reduce_all_const_elim 1.41% : 0.000010s : 53: predicate.reduce_eliminate 2.27% : 0.000016s : 118: predicate.redundant_stop_gradient_eliminater 0.37% : 0.000003s : 17: predicate.remove_not_recompute_node 1.63% : 0.000011s : 105: predicate.replace_applicator 0.89% : 0.000006s : 47: predicate.replace_old_param 0.12% : 0.000001s : 1: predicate.reset_defer_inline 1.12% : 0.000008s : 53: predicate.reshape_eliminate 0.88% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.07% : 0.000000s : 1: predicate.row_tensor_eliminate 4.01% : 0.000028s : 42: predicate.same_eliminate 0.29% : 0.000002s : 17: predicate.set_cell_output_no_recompute 0.96% : 0.000007s : 17: predicate.shard_identity_eliminate 0.13% : 0.000001s : 2: predicate.special_op_eliminate 0.42% : 0.000003s : 17: predicate.specialize_transform 1.20% : 0.000008s : 42: predicate.split_environ_get_set_with_tuple_value 1.47% : 0.000010s : 47: predicate.stack_unstack_eliminate 0.03% : 0.000000s : 1: predicate.switch_call_monad_eliminater 2.03% : 0.000014s : 86: predicate.switch_defer_inline 2.74% : 0.000019s : 128: predicate.switch_layer_defer_inline 5.73% : 0.000039s : 246: predicate.switch_simplify 1.07% : 0.000007s : 53: predicate.tile_eliminate 1.10% : 0.000008s : 53: predicate.transpose_eliminate 2.57% : 0.000018s : 55: predicate.tuple_list_convert_item_index_to_positive 1.32% : 0.000009s : 55: predicate.tuple_list_get_item_const_eliminator 1.59% : 0.000011s : 55: predicate.tuple_list_get_item_depend_reorder 2.50% : 0.000017s : 82: predicate.tuple_list_get_item_eliminator 1.42% : 0.000010s : 55: predicate.tuple_list_get_set_item_eliminator 1.78% : 0.000012s : 72: predicate.tuple_list_set_item_eliminator 1.35% : 0.000009s : 65: predicate.tuple_to_list_eliminator_ 2.33% : 0.000016s : 118: predicate.updatestate_pure_node_eliminater 2.72% : 0.000019s : 135: predicate.updatestate_useless_node_eliminater 0.04% : 0.000000s : 1: predicate.value_based_eliminate 0.49% : 0.000003s : 17: predicate.virtual_dataset_eliminate 0.44% : 0.000003s : 17: predicate.virtual_output_eliminate 0.03% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.12% : 0.000001s : 1: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.185652 54 35.97% : 0.066786s : 27: func_graph_cloner_run.FuncGraphClonerGraph 64.03% : 0.118866s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.233557 233 0.00% : 0.000004s : 1: ForceFp32Comm 0.42% : 0.005155s : 1: add_attr 0.42% : 0.005139s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000073s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000242s : 1: auto_monad 0.00% : 0.000026s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.05% : 0.000607s : 1: bootstrap 0.00% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.00% : 0.000029s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000009s : 1: environ_conv 0.02% : 0.000295s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 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 0.05% : 0.000580s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.07% : 0.000882s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000016s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000021s : 1: opt.transform.mutable_eliminate 0.41% : 0.005088s : 117: opt.transform.opt_a 0.00% : 0.000016s : 1: opt.transform.opt_after_cconv 0.00% : 0.000024s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000056s : 28: opt.transform.opt_b 0.00% : 0.000034s : 2: opt.transform.opt_trans_graph 0.00% : 0.000029s : 4: opt.transform.symbol_engine_opt 24.59% : 0.303288s : 1: opt_a 0.01% : 0.000102s : 1: opt_after_cconv 0.05% : 0.000612s : 1: opt_after_jit_grad 0.02% : 0.000236s : 1: opt_b 24.84% : 0.306363s : 1: optimize 0.00% : 0.000024s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000024s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000007s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000098s : 1: pre_auto_parallel 0.00% : 0.000012s : 1: py_interpret_to_execute 0.00% : 0.000013s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000006s : 1: remove_cast_before_assign_add 0.00% : 0.000020s : 1: remove_dup_value 2.54% : 0.031290s : 2: renormalize.infer 9.78% : 0.120620s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000026s : 1: rewriter_after_opt_a 0.05% : 0.000594s : 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% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000076s : 1: symbol_engine_optimizer 0.01% : 0.000067s : 1: tuple_transform 36.60% : 0.451446s : 1: type_inference TotalTime = 0.429845, [21] [bootstrap]: 0.00045164 [type_inference]: 0.415839 [event_method]: 0.00022255 [auto_monad]: 0.00011723 [graph_reusing]: 8.35999e-06 [inline]: 3.53e-06 [add_attr]: 0.00449341, [1] [add_attr_with_inline]: 0.0044798, [1] [Cycle 1]: 0.00010395, [2] [tag_attr]: 4.301e-05 [meta_addattr_fg_expand]: 8.11002e-06 [parallel-infer-symbol]: 3.95e-06 [pre_auto_parallel]: 6.196e-05 [insert-virtual-dataset]: 2.94999e-06 [parallel-infer-symbol-second]: 1.07e-06 [dataset_repeat_opt]: 2.15002e-06 [pipeline_split]: 1.97001e-06 [optimize]: 0.00765319, [53] [py_interpret_to_execute]: 9.74999e-06 [rewriter_before_opt_a]: 0.0003938 [opt_a]: 0.00448265, [2] [Cycle 1]: 0.00374344, [45] [expand_dump_flag]: 4.69998e-06 [switch_simplify]: 6.418e-05 [loop_unroll]: 4.368e-05 [a_1]: 0.00089443 [with_stream_mark]: 3.001e-05 [recompute_prepare]: 1.143e-05 [updatestate_depend_eliminate]: 5.47001e-06 [updatestate_assign_eliminate]: 4.38999e-06 [updatestate_loads_eliminate]: 3.56001e-06 [parameter_eliminate]: 3.54002e-06 [a_2]: 8.218e-05 [accelerated_algorithm]: 8.03999e-06 [shard]: 2.61e-06 [meta_shard_fg_expand]: 3.38999e-06 [shard_inline]: 6.69001e-06 [merge_send_recv]: 1.159e-05 [auto_parallel]: 8.57998e-06 [parallel]: 2.312e-05 [flash_sp]: 1.416e-05 [merge_comm]: 4e-06 [allreduce_fusion]: 3.53e-06 [matmul_add_comm_reduction]: 1.237e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 1.01e-05 [virtual_dataset]: 6.98998e-06 [get_grad_eliminate_]: 6.59999e-06 [virtual_output]: 6.23e-06 [merge_forward]: 4.19002e-06 [cell_reuse_recompute_pass]: 2.15002e-06 [offload_activation]: 1.232e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.769e-05 [merge_recompute_call_nodes]: 2.48998e-06 [before_grad]: 1.196e-05 [set_forward_comm_id_for_comm_node_pass]: 4.67998e-06 [meta_fg_expand]: 3.56001e-06 [flash_sp_send_recv_attached]: 3.4e-06 [receive_attached]: 3.25e-06 [after_resolve]: 1.132e-05 [a_after_grad]: 9.79e-06 [renormalize]: 0.0019296 [add_forward_monad_depend]: 1.137e-05 [auto_monad_grad]: 3.01001e-06 [auto_monad_eliminator]: 2.311e-05 [cse]: 5.344e-05 [a_3]: 5.957e-05 [Cycle 2]: 0.00072356, [45] [expand_dump_flag]: 2.01e-06 [switch_simplify]: 8.38001e-06 [loop_unroll]: 6.26e-06 [a_1]: 0.00012033 [with_stream_mark]: 2.117e-05 [recompute_prepare]: 6.82002e-06 [updatestate_depend_eliminate]: 4.75001e-06 [updatestate_assign_eliminate]: 3.34001e-06 [updatestate_loads_eliminate]: 3.35e-06 [parameter_eliminate]: 2.72001e-06 [a_2]: 6.935e-05 [accelerated_algorithm]: 7.05e-06 [shard]: 2.49001e-06 [meta_shard_fg_expand]: 2.81e-06 [shard_inline]: 2.621e-05 [merge_send_recv]: 8.54e-06 [auto_parallel]: 9.71e-06 [parallel]: 9.76e-06 [flash_sp]: 4.58999e-06 [merge_comm]: 3.81001e-06 [allreduce_fusion]: 3.7e-06 [matmul_add_comm_reduction]: 9.49999e-06 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 7.52002e-06 [virtual_dataset]: 5.86e-06 [get_grad_eliminate_]: 6.11e-06 [virtual_output]: 6.04001e-06 [merge_forward]: 4.63999e-06 [cell_reuse_recompute_pass]: 3.03e-06 [offload_activation]: 1.104e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.846e-05 [merge_recompute_call_nodes]: 1.55999e-06 [before_grad]: 1.052e-05 [set_forward_comm_id_for_comm_node_pass]: 3.95e-06 [meta_fg_expand]: 3.31001e-06 [flash_sp_send_recv_attached]: 2.04e-06 [receive_attached]: 2.92002e-06 [after_resolve]: 1.091e-05 [a_after_grad]: 8.54e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.94e-06 [auto_monad_grad]: 1.64e-06 [auto_monad_eliminator]: 9.61998e-06 [cse]: 2.496e-05 [a_3]: 3.627e-05 [py_interpret_to_execute_after_opt_a]: 7.71999e-06 [slice_cell_reuse_recomputed_activation]: 2.56998e-06 [rewriter_after_opt_a]: 2.628e-05 [convert_after_rewriter]: 1.91e-06 [order_py_execute_after_rewriter]: 1.25999e-06 [mutable_eliminate]: 0.00095437 [opt_b]: 0.000289, [1] [Cycle 1]: 0.00027943, [7] [b_1]: 0.00017437 [b_2]: 9.70002e-06 [updatestate_depend_eliminate]: 1.088e-05 [updatestate_assign_eliminate]: 3.71999e-06 [updatestate_loads_eliminate]: 3.03e-06 [renormalize]: 7.09988e-07 [cse]: 3.643e-05 [optimize_parallel_all_gather_comm]: 2.174e-05 [overlap_param_gather]: 2.05002e-06 [cconv]: 4.19e-05 [loop_unroll]: 0.00062122 [opt_after_cconv]: 0.00011664, [1] [Cycle 1]: 0.00010774, [7] [c_1]: 2.676e-05 [parameter_eliminate]: 5.37001e-06 [updatestate_depend_eliminate]: 6.57002e-06 [updatestate_assign_eliminate]: 3.16999e-06 [updatestate_loads_eliminate]: 2.49999e-06 [cse]: 2.749e-05 [renormalize]: 6.80011e-07 [remove_dup_value]: 5.734e-05 [tuple_transform]: 7.877e-05, [1] [Cycle 1]: 7.252e-05, [4] [d_1]: 4.362e-05 [none_parameter_eliminate]: 1.77999e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 7.07002e-06 [partial_unused_args_eliminate]: 2.27001e-06 [add_recomputation]: 6.156e-05 [cse_after_recomputation]: 2.759e-05, [1] [Cycle 1]: 2.221e-05, [1] [cse]: 1.562e-05 [environ_conv]: 7.4e-06 [swap_dp_allreduce_reducescatter]: 5.91e-06 [bias_add_comm_swap]: 2.95002e-06 [label_micro_interleaved_index]: 5.66e-06 [label_fine_grained_interleaved_index]: 3.26001e-06 [merge_cast_opt]: 1.79e-06 [slice_recompute_activation]: 2.61e-06 [micro_interleaved_order_control]: 2.53e-06 [assign_add_opt]: 1.78002e-06 [ForceFp32Comm]: 8.99978e-07 [remove_cast_before_assign_add]: 1.08001e-06 [full_micro_interleaved_order_control]: 2.76e-06 [reorder_send_recv_between_fp_bp]: 3.12002e-06 [comm_op_add_attrs]: 1.84e-06 [add_comm_op_reuse_tag]: 1.25001e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.14003e-06 [overlap_opt_shard_in_pipeline]: 1.30001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06e-06 [control_data_broadcast_order]: 1.581e-05 [grouped_pairwise_exchange_alltoall]: 1.82999e-06 [offloading_packed_experts]: 4.77998e-06 [overlap_recompute_and_grad_model_parallel]: 5.89e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.30001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.55999e-06 [overlap_recompute_comm]: 3.04999e-06 [overlap_grad_ring_attention]: 5.19e-06 [overlap_grad_flash_sp]: 2.477e-05 [begin_end_overlap_inline]: 6.39993e-07 [split_matmul_comm_elemetwise]: 3.33998e-06 [split_layernorm_comm]: 1.95001e-06 [handle_group_info]: 1.58002e-06 [symbol_engine_optimizer]: 8.08e-05, [1] [Cycle 1]: 7.616e-05, [6] [build]: 3.78999e-06 [elim_shapecalc]: 1.087e-05 [elim_not_effective]: 1.353e-05 [opt_reshape]: 6.55002e-06 [fold_const_symbol]: 1.005e-05 [renormalize]: 2.00002e-07 [detach_backward]: 3.13e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 2.194e-05 [get_jit_bprop_graph]: 1.94e-06 [rewriter_after_jit_bprop_graph]: 3.019e-05 [opt_after_jit_grad]: 0.00065792 [validate]: 5.538e-05 Sums bootstrap : 0.000452s : 0.11% type_inference : 0.415839s : 98.02% event_method : 0.000223s : 0.05% auto_monad : 0.000117s : 0.03% graph_reusing : 0.000008s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000043s : 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 : 0.000062s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000010s : 0.00% optimize.rewriter_before_opt_a : 0.000394s : 0.09% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000073s : 0.02% optimize.opt_a.loop_unroll : 0.000050s : 0.01% optimize.opt_a.a_1 : 0.001015s : 0.24% optimize.opt_a.with_stream_mark : 0.000051s : 0.01% optimize.opt_a.recompute_prepare : 0.000018s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000152s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000015s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.01% optimize.opt_a.merge_send_recv : 0.000020s : 0.00% optimize.opt_a.auto_parallel : 0.000018s : 0.00% optimize.opt_a.parallel : 0.000033s : 0.01% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000008s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000022s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000018s : 0.00% optimize.opt_a.virtual_dataset : 0.000013s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000013s : 0.00% optimize.opt_a.virtual_output : 0.000012s : 0.00% optimize.opt_a.merge_forward : 0.000009s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000023s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000036s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000022s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.00% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000022s : 0.01% optimize.opt_a.a_after_grad : 0.000018s : 0.00% optimize.opt_a.renormalize : 0.001930s : 0.45% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000033s : 0.01% optimize.opt_a.cse : 0.000078s : 0.02% optimize.opt_a.a_3 : 0.000096s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000008s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000026s : 0.01% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000954s : 0.22% optimize.opt_b.b_1 : 0.000174s : 0.04% optimize.opt_b.b_2 : 0.000010s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000036s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.01% optimize.loop_unroll : 0.000621s : 0.15% optimize.opt_after_cconv.c_1 : 0.000027s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000027s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000057s : 0.01% optimize.tuple_transform.d_1 : 0.000044s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000007s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000062s : 0.01% optimize.cse_after_recomputation.cse : 0.000016s : 0.00% optimize.environ_conv : 0.000007s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000002s : 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 : 0.000016s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000025s : 0.01% 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000011s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000014s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000022s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000030s : 0.01% opt_after_jit_grad : 0.000658s : 0.16% validate : 0.000055s : 0.01% Time group info: ------[substitution.] 0.000299 28 0.88% : 0.000003s : 2: substitution.elim_not_effective 0.47% : 0.000001s : 2: substitution.fold_const_symbol 2.44% : 0.000007s : 3: substitution.graph_param_transform 84.35% : 0.000252s : 7: substitution.inline 1.67% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.17% : 0.000006s : 4: substitution.remove_not_recompute_node 1.84% : 0.000006s : 2: substitution.replace_old_param 6.17% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.415703 2 53.95% : 0.224256s : 1: type_inference.infer 46.05% : 0.191448s : 1: type_inference.specialize ------[replace.] 0.000124 11 66.54% : 0.000082s : 7: replace.inline 33.46% : 0.000041s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000264 11 93.90% : 0.000248s : 7: match.inline 6.10% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000234 1291 1.10% : 0.000003s : 15: predicate.accumulaten_eliminater 1.00% : 0.000002s : 3: predicate.ad_related_special_op_eliminate 0.44% : 0.000001s : 6: predicate.addn_check_dump 1.05% : 0.000002s : 15: predicate.addn_zero_filter 0.95% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.15% : 0.000005s : 21: predicate.arithmetic_simplify 1.16% : 0.000003s : 15: predicate.cast_eliminate 0.54% : 0.000001s : 6: predicate.check_bprop_eliminate 0.50% : 0.000001s : 6: predicate.compare_switch_simplify 0.13% : 0.000000s : 3: predicate.const_output_eliminate 0.52% : 0.000001s : 6: predicate.depend_value_elim 0.94% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.10% : 0.000003s : 15: predicate.dict_get_item_eliminator 1.23% : 0.000003s : 15: predicate.dict_set_item_eliminator 0.96% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.15% : 0.000000s : 3: predicate.elim_not_effective 0.35% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 1.45% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.06% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.11% : 0.000003s : 18: predicate.environ_get_depend_swap 1.44% : 0.000003s : 24: predicate.environ_get_eliminate 1.25% : 0.000003s : 18: predicate.environ_get_set_eliminate 1.86% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.43% : 0.000006s : 26: predicate.float_depend_g_call 0.34% : 0.000001s : 6: predicate.float_environ_get_switch 0.75% : 0.000002s : 9: predicate.float_tuple_getitem_switch 0.12% : 0.000000s : 3: predicate.fold_const_symbol 0.49% : 0.000001s : 6: predicate.get_grad_eliminate 0.23% : 0.000001s : 3: predicate.graph_param_transform 0.52% : 0.000001s : 6: predicate.incorporate_call 0.32% : 0.000001s : 6: predicate.incorporate_call_switch 6.21% : 0.000015s : 59: predicate.inline 0.73% : 0.000002s : 6: predicate.inline_without_move 0.23% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.88% : 0.000002s : 6: predicate.less_batch_normalization 1.59% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.46% : 0.000006s : 40: predicate.load_eliminater 1.07% : 0.000003s : 3: predicate.loop_unroll_after_grad 2.81% : 0.000007s : 49: predicate.loop_unroll_before_grad 1.52% : 0.000004s : 21: predicate.make_slice_get_slice_eliminator 0.47% : 0.000001s : 6: predicate.merge_addn 0.44% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.69% : 0.000002s : 6: predicate.mini_step_allgather_replace 0.86% : 0.000002s : 15: predicate.minmaximum_grad 1.38% : 0.000003s : 3: predicate.mutable_eliminate 0.29% : 0.000001s : 3: predicate.opt_reshape 0.28% : 0.000001s : 3: predicate.parallel_virtual_node 1.93% : 0.000005s : 26: predicate.partial_defer_inline 1.38% : 0.000003s : 22: predicate.partial_eliminate 0.91% : 0.000002s : 15: predicate.print_const_string_wrapper 0.46% : 0.000001s : 6: predicate.reduce_all_const_elim 1.13% : 0.000003s : 15: predicate.reduce_eliminate 2.76% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.38% : 0.000001s : 6: predicate.remove_not_recompute_node 1.34% : 0.000003s : 25: predicate.replace_applicator 0.41% : 0.000001s : 6: predicate.replace_old_param 0.27% : 0.000001s : 3: predicate.reset_defer_inline 1.10% : 0.000003s : 15: predicate.reshape_eliminate 0.67% : 0.000002s : 6: predicate.row_tensor_add_zeros_like 0.32% : 0.000001s : 3: predicate.row_tensor_eliminate 0.80% : 0.000002s : 6: predicate.same_eliminate 0.32% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.59% : 0.000001s : 6: predicate.shard_identity_eliminate 0.73% : 0.000002s : 6: predicate.special_op_eliminate 0.64% : 0.000001s : 6: predicate.specialize_transform 0.91% : 0.000002s : 6: predicate.split_environ_get_set_with_tuple_value 0.73% : 0.000002s : 6: predicate.stack_unstack_eliminate 0.30% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.94% : 0.000005s : 26: predicate.switch_defer_inline 1.98% : 0.000005s : 32: predicate.switch_layer_defer_inline 5.60% : 0.000013s : 84: predicate.switch_simplify 0.96% : 0.000002s : 15: predicate.tile_eliminate 1.19% : 0.000003s : 15: predicate.transpose_eliminate 1.76% : 0.000004s : 21: predicate.tuple_list_convert_item_index_to_positive 1.46% : 0.000003s : 21: predicate.tuple_list_get_item_const_eliminator 1.30% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 3.63% : 0.000008s : 31: predicate.tuple_list_get_item_eliminator 1.21% : 0.000003s : 21: predicate.tuple_list_get_set_item_eliminator 2.09% : 0.000005s : 27: predicate.tuple_list_set_item_eliminator 1.82% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.42% : 0.000006s : 40: predicate.updatestate_pure_node_eliminater 2.97% : 0.000007s : 46: predicate.updatestate_useless_node_eliminater 0.31% : 0.000001s : 3: predicate.value_based_eliminate 0.50% : 0.000001s : 6: predicate.virtual_dataset_eliminate 0.66% : 0.000002s : 6: predicate.virtual_output_eliminate 0.19% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.40% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001582 18 54.76% : 0.000866s : 9: func_graph_cloner_run.FuncGraphClonerGraph 45.24% : 0.000716s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.445588 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.01% : 0.004501s : 1: add_attr 1.01% : 0.004484s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000066s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000127s : 1: auto_monad 0.01% : 0.000026s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.11% : 0.000481s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000019s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.01% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.05% : 0.000239s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.14% : 0.000633s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.22% : 0.000971s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000018s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000022s : 1: opt.transform.mutable_eliminate 0.34% : 0.001508s : 78: opt.transform.opt_a 0.01% : 0.000025s : 1: opt.transform.opt_after_cconv 0.01% : 0.000029s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000154s : 28: opt.transform.opt_b 0.01% : 0.000048s : 2: opt.transform.opt_trans_graph 0.01% : 0.000037s : 4: opt.transform.symbol_engine_opt 1.01% : 0.004487s : 1: opt_a 0.03% : 0.000121s : 1: opt_after_cconv 0.15% : 0.000672s : 1: opt_after_jit_grad 0.07% : 0.000294s : 1: opt_b 1.72% : 0.007660s : 1: optimize 0.01% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.01% : 0.000028s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 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% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000067s : 1: pre_auto_parallel 0.00% : 0.000013s : 1: py_interpret_to_execute 0.00% : 0.000011s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000062s : 1: remove_dup_value 0.23% : 0.001020s : 1: renormalize.infer 0.20% : 0.000895s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000038s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000030s : 1: rewriter_after_opt_a 0.09% : 0.000401s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000084s : 1: symbol_engine_optimizer 0.02% : 0.000083s : 1: tuple_transform 93.33% : 0.415875s : 1: type_inference TotalTime = 0.707152, [21] [bootstrap]: 0.00046072 [type_inference]: 0.513945 [event_method]: 0.0003774 [auto_monad]: 0.00022311 [graph_reusing]: 1.314e-05 [inline]: 7.26999e-06 [add_attr]: 0.0046283, [1] [add_attr_with_inline]: 0.00461328, [1] [Cycle 1]: 0.00016734, [2] [tag_attr]: 9.41e-05 [meta_addattr_fg_expand]: 1.592e-05 [parallel-infer-symbol]: 5.15999e-06 [pre_auto_parallel]: 0.00010249 [insert-virtual-dataset]: 3.37002e-06 [parallel-infer-symbol-second]: 1.09e-06 [dataset_repeat_opt]: 2.69999e-06 [pipeline_split]: 1.79998e-06 [optimize]: 0.186479, [53] [py_interpret_to_execute]: 1.096e-05 [rewriter_before_opt_a]: 0.00059134 [opt_a]: 0.182884, [3] [Cycle 1]: 0.0918123, [45] [expand_dump_flag]: 8.97e-06 [switch_simplify]: 0.0002085 [loop_unroll]: 9.099e-05 [a_1]: 0.00186441 [with_stream_mark]: 4.327e-05 [recompute_prepare]: 2.713e-05 [updatestate_depend_eliminate]: 1.023e-05 [updatestate_assign_eliminate]: 7.55998e-06 [updatestate_loads_eliminate]: 7.71999e-06 [parameter_eliminate]: 4.24002e-06 [a_2]: 0.0002259 [accelerated_algorithm]: 1.542e-05 [shard]: 2.57001e-06 [meta_shard_fg_expand]: 7.21999e-06 [shard_inline]: 1.433e-05 [merge_send_recv]: 2.119e-05 [auto_parallel]: 1.786e-05 [parallel]: 3.399e-05 [flash_sp]: 1.523e-05 [merge_comm]: 1.08e-05 [allreduce_fusion]: 8.82e-06 [matmul_add_comm_reduction]: 3.888e-05 [allreduce_slice_to_reducescatter]: 9.80013e-07 [virtual_shard_identity]: 1.802e-05 [virtual_dataset]: 1.428e-05 [get_grad_eliminate_]: 1.547e-05 [virtual_output]: 1.393e-05 [merge_forward]: 1.061e-05 [cell_reuse_recompute_pass]: 1.14e-06 [offload_activation]: 1.994e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.022e-05 [merge_recompute_call_nodes]: 2.27999e-06 [before_grad]: 2.819e-05 [set_forward_comm_id_for_comm_node_pass]: 9.79999e-06 [meta_fg_expand]: 0.0745146 [flash_sp_send_recv_attached]: 5.09e-06 [receive_attached]: 2.93e-06 [after_resolve]: 8.715e-05 [a_after_grad]: 9.551e-05 [renormalize]: 0.0129599 [add_forward_monad_depend]: 1.539e-05 [auto_monad_grad]: 7.92e-06 [auto_monad_eliminator]: 8.955e-05 [cse]: 0.00042656 [a_3]: 0.00032589 [Cycle 2]: 0.0903774, [45] [expand_dump_flag]: 3.52997e-06 [switch_simplify]: 4.302e-05 [loop_unroll]: 3.842e-05 [a_1]: 0.0875039 [with_stream_mark]: 5.063e-05 [recompute_prepare]: 1.641e-05 [updatestate_depend_eliminate]: 5.09e-06 [updatestate_assign_eliminate]: 3.45e-06 [updatestate_loads_eliminate]: 3.36001e-06 [parameter_eliminate]: 3.34001e-06 [a_2]: 7.089e-05 [accelerated_algorithm]: 6.59001e-06 [shard]: 4.77e-06 [meta_shard_fg_expand]: 5.39e-06 [shard_inline]: 5.76e-06 [merge_send_recv]: 1.12e-05 [auto_parallel]: 1.207e-05 [parallel]: 1.261e-05 [flash_sp]: 5.14e-06 [merge_comm]: 3.30998e-06 [allreduce_fusion]: 3.88001e-06 [matmul_add_comm_reduction]: 1.38e-05 [allreduce_slice_to_reducescatter]: 1.17999e-06 [virtual_shard_identity]: 1.02e-05 [virtual_dataset]: 6.11998e-06 [get_grad_eliminate_]: 5.96e-06 [virtual_output]: 7.43999e-06 [merge_forward]: 4.91997e-06 [cell_reuse_recompute_pass]: 4.33001e-06 [offload_activation]: 1.145e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.378e-05 [merge_recompute_call_nodes]: 1.71e-06 [before_grad]: 1.523e-05 [set_forward_comm_id_for_comm_node_pass]: 4.10998e-06 [meta_fg_expand]: 0.00046156 [flash_sp_send_recv_attached]: 3.22002e-06 [receive_attached]: 3.31001e-06 [after_resolve]: 2.602e-05 [a_after_grad]: 1.1e-05 [renormalize]: 0.00146471 [add_forward_monad_depend]: 1.1e-05 [auto_monad_grad]: 3.02002e-06 [auto_monad_eliminator]: 2.247e-05 [cse]: 3.648e-05 [a_3]: 5.782e-05 [Cycle 3]: 0.00066874, [45] [expand_dump_flag]: 2.64001e-06 [switch_simplify]: 8.39998e-06 [loop_unroll]: 5.89e-06 [a_1]: 0.00010783 [with_stream_mark]: 2.139e-05 [recompute_prepare]: 6.44999e-06 [updatestate_depend_eliminate]: 3.58e-06 [updatestate_assign_eliminate]: 3.00002e-06 [updatestate_loads_eliminate]: 2.99999e-06 [parameter_eliminate]: 2.58e-06 [a_2]: 6.146e-05 [accelerated_algorithm]: 6.54999e-06 [shard]: 2.90002e-06 [meta_shard_fg_expand]: 2.46e-06 [shard_inline]: 5.24e-06 [merge_send_recv]: 1.033e-05 [auto_parallel]: 1.168e-05 [parallel]: 1.09e-05 [flash_sp]: 1.59998e-06 [merge_comm]: 3.61999e-06 [allreduce_fusion]: 3.43e-06 [matmul_add_comm_reduction]: 1.137e-05 [allreduce_slice_to_reducescatter]: 4.19997e-07 [virtual_shard_identity]: 8.39998e-06 [virtual_dataset]: 5.14e-06 [get_grad_eliminate_]: 4.82e-06 [virtual_output]: 5.42999e-06 [merge_forward]: 4.89998e-06 [cell_reuse_recompute_pass]: 3.24001e-06 [offload_activation]: 1.102e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.683e-05 [merge_recompute_call_nodes]: 1.40999e-06 [before_grad]: 1.144e-05 [set_forward_comm_id_for_comm_node_pass]: 4.35e-06 [meta_fg_expand]: 3.28e-06 [flash_sp_send_recv_attached]: 2.13002e-06 [receive_attached]: 2.58003e-06 [after_resolve]: 1.059e-05 [a_after_grad]: 7.15e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.66999e-06 [auto_monad_grad]: 1.57001e-06 [auto_monad_eliminator]: 6.91001e-06 [cse]: 1.777e-05 [a_3]: 3.015e-05 [py_interpret_to_execute_after_opt_a]: 8.90999e-06 [slice_cell_reuse_recomputed_activation]: 2.53e-06 [rewriter_after_opt_a]: 2.243e-05 [convert_after_rewriter]: 1.39e-06 [order_py_execute_after_rewriter]: 1.69e-06 [mutable_eliminate]: 0.00096621 [opt_b]: 0.00056499, [2] [Cycle 1]: 0.00041398, [7] [b_1]: 0.00031095 [b_2]: 7.00002e-06 [updatestate_depend_eliminate]: 1.271e-05 [updatestate_assign_eliminate]: 2.74001e-06 [updatestate_loads_eliminate]: 2.37001e-06 [renormalize]: 7.00005e-07 [cse]: 3.102e-05 [Cycle 2]: 0.00013571, [7] [b_1]: 8.222e-05 [b_2]: 5.12999e-06 [updatestate_depend_eliminate]: 2.19001e-06 [updatestate_assign_eliminate]: 1.58002e-06 [updatestate_loads_eliminate]: 1.52999e-06 [renormalize]: 1.00001e-07 [cse]: 1.004e-05 [optimize_parallel_all_gather_comm]: 1.996e-05 [overlap_param_gather]: 9.77001e-06 [cconv]: 3.789e-05 [loop_unroll]: 0.00065032 [opt_after_cconv]: 9.832e-05, [1] [Cycle 1]: 9.064e-05, [7] [c_1]: 1.801e-05 [parameter_eliminate]: 6.33002e-06 [updatestate_depend_eliminate]: 6.68e-06 [updatestate_assign_eliminate]: 2.21998e-06 [updatestate_loads_eliminate]: 1.57999e-06 [cse]: 2.093e-05 [renormalize]: 5.50004e-07 [remove_dup_value]: 1.72e-05 [tuple_transform]: 5.988e-05, [1] [Cycle 1]: 5.362e-05, [4] [d_1]: 2.458e-05 [none_parameter_eliminate]: 1.80001e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 5.71e-06 [partial_unused_args_eliminate]: 2.02001e-06 [add_recomputation]: 4.525e-05 [cse_after_recomputation]: 2.068e-05, [1] [Cycle 1]: 1.613e-05, [1] [cse]: 9.89001e-06 [environ_conv]: 6.02999e-06 [swap_dp_allreduce_reducescatter]: 4.99e-06 [bias_add_comm_swap]: 3.48999e-06 [label_micro_interleaved_index]: 6.51e-06 [label_fine_grained_interleaved_index]: 3.16999e-06 [merge_cast_opt]: 1.49998e-06 [slice_recompute_activation]: 2.66e-06 [micro_interleaved_order_control]: 2.79001e-06 [assign_add_opt]: 2.02999e-06 [ForceFp32Comm]: 9.79984e-07 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.78e-06 [reorder_send_recv_between_fp_bp]: 3.6e-06 [comm_op_add_attrs]: 1.18001e-06 [add_comm_op_reuse_tag]: 1.19e-06 [interleave_split_concat_branches]: 1.60999e-06 [interleave_parallel_branches]: 1.21002e-06 [overlap_opt_shard_in_pipeline]: 6.01998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.28998e-06 [control_data_broadcast_order]: 1.432e-05 [grouped_pairwise_exchange_alltoall]: 1.87999e-06 [offloading_packed_experts]: 4.08999e-06 [overlap_recompute_and_grad_model_parallel]: 4.85999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.59001e-06 [overlap_grad_ring_attention]: 4.1e-06 [overlap_grad_flash_sp]: 2.029e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.27001e-06 [split_layernorm_comm]: 2.36e-06 [handle_group_info]: 1.17999e-06 [symbol_engine_optimizer]: 7.261e-05, [1] [Cycle 1]: 6.647e-05, [6] [build]: 3.58e-06 [elim_shapecalc]: 8.74998e-06 [elim_not_effective]: 1.163e-05 [opt_reshape]: 5.69e-06 [fold_const_symbol]: 7.06001e-06 [renormalize]: 1.70025e-07 [detach_backward]: 2.84001e-06 [pipeline_parallel_scheduler]: 2.15002e-06 [auto_monad_reorder]: 1.734e-05 [get_jit_bprop_graph]: 1.91e-06 [rewriter_after_jit_bprop_graph]: 3.87002e-06 [opt_after_jit_grad]: 0.00060244 [validate]: 4.41e-05 Sums bootstrap : 0.000461s : 0.07% type_inference : 0.513945s : 73.33% event_method : 0.000377s : 0.05% auto_monad : 0.000223s : 0.03% graph_reusing : 0.000013s : 0.00% inline : 0.000007s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000094s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000016s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000102s : 0.01% 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 : 0.000011s : 0.00% optimize.rewriter_before_opt_a : 0.000591s : 0.08% optimize.opt_a.expand_dump_flag : 0.000015s : 0.00% optimize.opt_a.switch_simplify : 0.000260s : 0.04% optimize.opt_a.loop_unroll : 0.000135s : 0.02% optimize.opt_a.a_1 : 0.089476s : 12.77% optimize.opt_a.with_stream_mark : 0.000115s : 0.02% optimize.opt_a.recompute_prepare : 0.000050s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000358s : 0.05% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.00% optimize.opt_a.shard : 0.000010s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000015s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.00% optimize.opt_a.merge_send_recv : 0.000043s : 0.01% optimize.opt_a.auto_parallel : 0.000042s : 0.01% optimize.opt_a.parallel : 0.000057s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000018s : 0.00% optimize.opt_a.allreduce_fusion : 0.000016s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000064s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.01% optimize.opt_a.virtual_dataset : 0.000026s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.00% optimize.opt_a.virtual_output : 0.000027s : 0.00% optimize.opt_a.merge_forward : 0.000020s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000009s : 0.00% optimize.opt_a.offload_activation : 0.000042s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000071s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000055s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.00% optimize.opt_a.meta_fg_expand : 0.074979s : 10.70% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000124s : 0.02% optimize.opt_a.a_after_grad : 0.000114s : 0.02% optimize.opt_a.renormalize : 0.014425s : 2.06% optimize.opt_a.add_forward_monad_depend : 0.000029s : 0.00% optimize.opt_a.auto_monad_grad : 0.000013s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000119s : 0.02% optimize.opt_a.cse : 0.000481s : 0.07% optimize.opt_a.a_3 : 0.000414s : 0.06% optimize.py_interpret_to_execute_after_opt_a : 0.000009s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000022s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000002s : 0.00% optimize.mutable_eliminate : 0.000966s : 0.14% optimize.opt_b.b_1 : 0.000393s : 0.06% optimize.opt_b.b_2 : 0.000012s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000041s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000020s : 0.00% optimize.overlap_param_gather : 0.000010s : 0.00% optimize.cconv : 0.000038s : 0.01% optimize.loop_unroll : 0.000650s : 0.09% optimize.opt_after_cconv.c_1 : 0.000018s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000021s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000025s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000045s : 0.01% optimize.cse_after_recomputation.cse : 0.000010s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000005s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 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 : 0.000006s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000014s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000020s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000009s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000012s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000006s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000007s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000017s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000602s : 0.09% validate : 0.000044s : 0.01% Time group info: ------[substitution.] 0.001082 163 0.23% : 0.000003s : 1: substitution.elim_not_effective 0.95% : 0.000010s : 12: substitution.float_depend_g_call 0.43% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.15% : 0.000002s : 1: substitution.fold_const_symbol 0.43% : 0.000005s : 1: substitution.graph_param_transform 0.34% : 0.000004s : 2: substitution.incorporate_call 0.20% : 0.000002s : 2: substitution.incorporate_call_switch 62.82% : 0.000680s : 23: substitution.inline 1.94% : 0.000021s : 2: substitution.inline_without_move 1.29% : 0.000014s : 12: substitution.j_node_and_user_rematch 0.99% : 0.000011s : 7: substitution.minmaximum_grad 1.07% : 0.000012s : 12: substitution.partial_eliminate 1.19% : 0.000013s : 12: substitution.remove_not_recompute_node 2.68% : 0.000029s : 9: substitution.replace_applicator 1.52% : 0.000016s : 13: substitution.replace_old_param 0.29% : 0.000003s : 1: substitution.set_cell_output_no_recompute 1.37% : 0.000015s : 3: substitution.switch_simplify 2.38% : 0.000026s : 7: substitution.tuple_list_convert_item_index_to_positive 0.92% : 0.000010s : 7: substitution.tuple_list_get_item_const_eliminator 1.52% : 0.000016s : 7: substitution.tuple_list_get_item_depend_reorder 5.75% : 0.000062s : 19: substitution.tuple_list_get_item_eliminator 1.31% : 0.000014s : 7: substitution.tuple_list_get_set_item_eliminator 10.24% : 0.000111s : 1: substitution.zero_like_fill_zero ------[type_inference.] 0.513760 2 78.01% : 0.400783s : 1: type_inference.infer 21.99% : 0.112977s : 1: type_inference.specialize ------[replace.] 0.000436 37 50.65% : 0.000221s : 23: replace.inline 13.00% : 0.000057s : 3: replace.switch_simplify 25.93% : 0.000113s : 10: replace.tuple_list_get_item_eliminator 10.42% : 0.000045s : 1: replace.zero_like_fill_zero ------[match.] 0.000819 37 81.50% : 0.000667s : 23: match.inline 1.55% : 0.000013s : 3: match.switch_simplify 3.57% : 0.000029s : 10: match.tuple_list_get_item_eliminator 13.37% : 0.000109s : 1: match.zero_like_fill_zero ------[predicate.] 0.000684 4087 1.29% : 0.000009s : 53: predicate.accumulaten_eliminater 0.12% : 0.000001s : 1: predicate.ad_related_special_op_eliminate 0.37% : 0.000003s : 17: predicate.addn_check_dump 1.40% : 0.000010s : 53: predicate.addn_zero_filter 1.21% : 0.000008s : 53: predicate.adjust_all_reduce_mul_add 2.22% : 0.000015s : 70: predicate.arithmetic_simplify 1.34% : 0.000009s : 53: predicate.cast_eliminate 0.89% : 0.000006s : 44: predicate.check_bprop_eliminate 0.39% : 0.000003s : 17: predicate.compare_switch_simplify 0.04% : 0.000000s : 3: predicate.const_output_eliminate 0.44% : 0.000003s : 17: predicate.depend_value_elim 1.40% : 0.000010s : 53: predicate.dict_get_item_const_eliminator 2.20% : 0.000015s : 53: predicate.dict_get_item_eliminator 1.14% : 0.000008s : 53: predicate.dict_set_item_eliminator 0.23% : 0.000002s : 4: predicate.dumpgradient_eliminate 0.02% : 0.000000s : 1: predicate.elim_not_effective 0.09% : 0.000001s : 1: predicate.elim_shapecalc_of_broadcastargs 1.30% : 0.000009s : 56: predicate.environ_add_const_eliminate 1.22% : 0.000008s : 56: predicate.environ_get_add_eliminate 1.19% : 0.000008s : 56: predicate.environ_get_depend_swap 1.65% : 0.000011s : 73: predicate.environ_get_eliminate 1.03% : 0.000007s : 56: predicate.environ_get_set_eliminate 1.82% : 0.000012s : 86: predicate.exchange_switch_depend_value 2.39% : 0.000016s : 86: predicate.float_depend_g_call 0.42% : 0.000003s : 17: predicate.float_environ_get_switch 0.57% : 0.000004s : 20: predicate.float_tuple_getitem_switch 0.01% : 0.000000s : 1: predicate.fold_const_symbol 0.50% : 0.000003s : 17: predicate.get_grad_eliminate 0.01% : 0.000000s : 1: predicate.graph_param_transform 0.36% : 0.000002s : 17: predicate.incorporate_call 0.31% : 0.000002s : 17: predicate.incorporate_call_switch 5.67% : 0.000039s : 177: predicate.inline 1.34% : 0.000009s : 47: predicate.inline_without_move 0.21% : 0.000001s : 17: predicate.j_node_and_user_rematch 0.60% : 0.000004s : 17: predicate.less_batch_normalization 1.57% : 0.000011s : 67: predicate.list_to_tuple_eliminator_ 2.29% : 0.000016s : 120: predicate.load_eliminater 0.31% : 0.000002s : 1: predicate.loop_unroll_after_grad 3.33% : 0.000023s : 136: predicate.loop_unroll_before_grad 1.24% : 0.000008s : 57: predicate.make_slice_get_slice_eliminator 0.38% : 0.000003s : 17: predicate.merge_addn 0.96% : 0.000007s : 44: predicate.micro_step_allgather_replace 0.88% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.21% : 0.000008s : 53: predicate.minmaximum_grad 0.68% : 0.000005s : 3: predicate.mutable_eliminate 0.09% : 0.000001s : 1: predicate.opt_reshape 0.13% : 0.000001s : 3: predicate.parallel_virtual_node 2.56% : 0.000018s : 86: predicate.partial_defer_inline 1.38% : 0.000009s : 64: predicate.partial_eliminate 1.06% : 0.000007s : 53: predicate.print_const_string_wrapper 0.44% : 0.000003s : 17: predicate.reduce_all_const_elim 1.54% : 0.000011s : 53: predicate.reduce_eliminate 2.37% : 0.000016s : 120: predicate.redundant_stop_gradient_eliminater 0.29% : 0.000002s : 17: predicate.remove_not_recompute_node 1.58% : 0.000011s : 107: predicate.replace_applicator 0.65% : 0.000004s : 47: predicate.replace_old_param 0.12% : 0.000001s : 3: predicate.reset_defer_inline 1.32% : 0.000009s : 53: predicate.reshape_eliminate 0.99% : 0.000007s : 44: predicate.row_tensor_add_zeros_like 0.18% : 0.000001s : 2: predicate.row_tensor_eliminate 1.32% : 0.000009s : 44: predicate.same_eliminate 0.29% : 0.000002s : 17: predicate.set_cell_output_no_recompute 0.58% : 0.000004s : 17: predicate.shard_identity_eliminate 0.22% : 0.000002s : 4: predicate.special_op_eliminate 0.47% : 0.000003s : 17: predicate.specialize_transform 1.23% : 0.000008s : 44: predicate.split_environ_get_set_with_tuple_value 1.45% : 0.000010s : 47: predicate.stack_unstack_eliminate 0.06% : 0.000000s : 1: predicate.switch_call_monad_eliminater 2.20% : 0.000015s : 86: predicate.switch_defer_inline 2.73% : 0.000019s : 130: predicate.switch_layer_defer_inline 6.42% : 0.000044s : 246: predicate.switch_simplify 1.21% : 0.000008s : 53: predicate.tile_eliminate 1.37% : 0.000009s : 53: predicate.transpose_eliminate 1.22% : 0.000008s : 57: predicate.tuple_list_convert_item_index_to_positive 1.47% : 0.000010s : 57: predicate.tuple_list_get_item_const_eliminator 1.41% : 0.000010s : 57: predicate.tuple_list_get_item_depend_reorder 2.58% : 0.000018s : 84: predicate.tuple_list_get_item_eliminator 1.30% : 0.000009s : 57: predicate.tuple_list_get_set_item_eliminator 1.76% : 0.000012s : 74: predicate.tuple_list_set_item_eliminator 1.34% : 0.000009s : 67: predicate.tuple_to_list_eliminator_ 2.27% : 0.000016s : 120: predicate.updatestate_pure_node_eliminater 2.66% : 0.000018s : 137: predicate.updatestate_useless_node_eliminater 0.13% : 0.000001s : 3: predicate.value_based_eliminate 0.50% : 0.000003s : 17: predicate.virtual_dataset_eliminate 0.41% : 0.000003s : 17: predicate.virtual_output_eliminate 0.07% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.34% : 0.000002s : 5: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004822 54 59.84% : 0.002885s : 27: func_graph_cloner_run.FuncGraphClonerGraph 40.16% : 0.001936s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.004053 288 0.00% : 0.000004s : 1: ForceFp32Comm 0.46% : 0.004636s : 1: add_attr 0.46% : 0.004619s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000050s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000236s : 1: auto_monad 0.00% : 0.000021s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.000497s : 1: bootstrap 0.00% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000018s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000024s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.04% : 0.000396s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000018s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000011s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.07% : 0.000665s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.10% : 0.000986s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000016s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000081s : 1: opt.transform.mutable_eliminate 9.07% : 0.091047s : 117: opt.transform.opt_a 0.00% : 0.000016s : 1: opt.transform.opt_after_cconv 0.00% : 0.000019s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000320s : 83: opt.transform.opt_b 0.00% : 0.000028s : 2: opt.transform.opt_trans_graph 0.00% : 0.000029s : 4: opt.transform.symbol_engine_opt 18.22% : 0.182888s : 1: opt_a 0.01% : 0.000103s : 1: opt_after_cconv 0.06% : 0.000614s : 1: opt_after_jit_grad 0.06% : 0.000569s : 1: opt_b 18.57% : 0.186486s : 1: optimize 0.00% : 0.000024s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000024s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000007s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000009s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000014s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000109s : 1: pre_auto_parallel 0.00% : 0.000015s : 1: py_interpret_to_execute 0.00% : 0.000012s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000021s : 1: remove_dup_value 1.11% : 0.011115s : 2: renormalize.infer 0.33% : 0.003280s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000026s : 1: rewriter_after_opt_a 0.06% : 0.000602s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000008s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000075s : 1: symbol_engine_optimizer 0.01% : 0.000063s : 1: tuple_transform 51.19% : 0.513987s : 1: type_inference . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[0-KBK] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[0-KBK],max_mem:4.0M . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[-1-pynative] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[-1-pynative],max_mem:4.0M TotalTime = 0.275145, [21] [bootstrap]: 0.00068518 [type_inference]: 0.26158 [event_method]: 0.00014363 [auto_monad]: 9.457e-05 [graph_reusing]: 7.24001e-06 [inline]: 2.84001e-06 [add_attr]: 0.00476584, [1] [add_attr_with_inline]: 0.00475012, [1] [Cycle 1]: 9.137e-05, [2] [tag_attr]: 4.047e-05 [meta_addattr_fg_expand]: 7.16001e-06 [parallel-infer-symbol]: 3.76001e-06 [pre_auto_parallel]: 5.515e-05 [insert-virtual-dataset]: 2.84001e-06 [parallel-infer-symbol-second]: 1.00001e-06 [dataset_repeat_opt]: 1.89999e-06 [pipeline_split]: 1.86e-06 [optimize]: 0.00698494, [53] [py_interpret_to_execute]: 7.20998e-06 [rewriter_before_opt_a]: 0.0003478 [opt_a]: 0.0041027, [2] [Cycle 1]: 0.00344575, [45] [expand_dump_flag]: 4.38001e-06 [switch_simplify]: 6.107e-05 [loop_unroll]: 4.307e-05 [a_1]: 0.00087817 [with_stream_mark]: 2.367e-05 [recompute_prepare]: 9.54e-06 [updatestate_depend_eliminate]: 4.64998e-06 [updatestate_assign_eliminate]: 3.97e-06 [updatestate_loads_eliminate]: 3.21001e-06 [parameter_eliminate]: 3.09001e-06 [a_2]: 7.981e-05 [accelerated_algorithm]: 6.61e-06 [shard]: 2.37001e-06 [meta_shard_fg_expand]: 2.41e-06 [shard_inline]: 6.10002e-06 [merge_send_recv]: 9.27001e-06 [auto_parallel]: 8.43999e-06 [parallel]: 4.404e-05 [flash_sp]: 1.182e-05 [merge_comm]: 5.42999e-06 [allreduce_fusion]: 3.76999e-06 [matmul_add_comm_reduction]: 1.088e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 9.57999e-06 [virtual_dataset]: 6.83e-06 [get_grad_eliminate_]: 5.97999e-06 [virtual_output]: 6.24001e-06 [merge_forward]: 4.80999e-06 [cell_reuse_recompute_pass]: 1.32999e-06 [offload_activation]: 1.073e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.455e-05 [merge_recompute_call_nodes]: 1.92999e-06 [before_grad]: 1.116e-05 [set_forward_comm_id_for_comm_node_pass]: 4.06001e-06 [meta_fg_expand]: 3.88999e-06 [flash_sp_send_recv_attached]: 3.08e-06 [receive_attached]: 2.84999e-06 [after_resolve]: 1.212e-05 [a_after_grad]: 9.89001e-06 [renormalize]: 0.00167051 [add_forward_monad_depend]: 9.81e-06 [auto_monad_grad]: 2.91e-06 [auto_monad_eliminator]: 2.129e-05 [cse]: 4.283e-05 [a_3]: 8.517e-05 [Cycle 2]: 0.00064149, [45] [expand_dump_flag]: 2.61e-06 [switch_simplify]: 8.75999e-06 [loop_unroll]: 5.67001e-06 [a_1]: 0.00010153 [with_stream_mark]: 2.022e-05 [recompute_prepare]: 6.22001e-06 [updatestate_depend_eliminate]: 4.55999e-06 [updatestate_assign_eliminate]: 3.45e-06 [updatestate_loads_eliminate]: 3.51999e-06 [parameter_eliminate]: 2.26e-06 [a_2]: 6.901e-05 [accelerated_algorithm]: 5.87001e-06 [shard]: 2.31998e-06 [meta_shard_fg_expand]: 2.09e-06 [shard_inline]: 5.46e-06 [merge_send_recv]: 7.41999e-06 [auto_parallel]: 8.57e-06 [parallel]: 7.92e-06 [flash_sp]: 3.8e-06 [merge_comm]: 3.76999e-06 [allreduce_fusion]: 3.41001e-06 [matmul_add_comm_reduction]: 8.84e-06 [allreduce_slice_to_reducescatter]: 3.69997e-07 [virtual_shard_identity]: 6.42001e-06 [virtual_dataset]: 5.67001e-06 [get_grad_eliminate_]: 5.39e-06 [virtual_output]: 5.22e-06 [merge_forward]: 4.50001e-06 [cell_reuse_recompute_pass]: 2.44001e-06 [offload_activation]: 1.024e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.486e-05 [merge_recompute_call_nodes]: 1.25999e-06 [before_grad]: 9.76e-06 [set_forward_comm_id_for_comm_node_pass]: 3.63999e-06 [meta_fg_expand]: 2.44001e-06 [flash_sp_send_recv_attached]: 1.25999e-06 [receive_attached]: 1.82999e-06 [after_resolve]: 9.29998e-06 [a_after_grad]: 8.22e-06 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.41998e-06 [auto_monad_grad]: 1.15999e-06 [auto_monad_eliminator]: 8.52e-06 [cse]: 2.166e-05 [a_3]: 3.396e-05 [py_interpret_to_execute_after_opt_a]: 8.70999e-06 [slice_cell_reuse_recomputed_activation]: 2.24999e-06 [rewriter_after_opt_a]: 2.433e-05 [convert_after_rewriter]: 1.83997e-06 [order_py_execute_after_rewriter]: 1.31998e-06 [mutable_eliminate]: 0.00090791 [opt_b]: 0.00021419, [1] [Cycle 1]: 0.00020408, [7] [b_1]: 0.00011814 [b_2]: 7.68999e-06 [updatestate_depend_eliminate]: 8.62e-06 [updatestate_assign_eliminate]: 2.86e-06 [updatestate_loads_eliminate]: 2.66e-06 [renormalize]: 7.50006e-07 [cse]: 2.839e-05 [optimize_parallel_all_gather_comm]: 1.894e-05 [overlap_param_gather]: 2.44001e-06 [cconv]: 3.848e-05 [loop_unroll]: 0.00053113 [opt_after_cconv]: 0.0001045, [1] [Cycle 1]: 9.796e-05, [7] [c_1]: 2.471e-05 [parameter_eliminate]: 4.82e-06 [updatestate_depend_eliminate]: 6.02001e-06 [updatestate_assign_eliminate]: 2.53e-06 [updatestate_loads_eliminate]: 2.46998e-06 [cse]: 2.329e-05 [renormalize]: 7.50006e-07 [remove_dup_value]: 2.109e-05 [tuple_transform]: 7.574e-05, [1] [Cycle 1]: 7.017e-05, [4] [d_1]: 4.032e-05 [none_parameter_eliminate]: 1.89999e-06 [renormalize]: 3.39991e-07 [switch_simplify]: 8.13001e-06 [partial_unused_args_eliminate]: 2.29001e-06 [add_recomputation]: 6.546e-05 [cse_after_recomputation]: 2.635e-05, [1] [Cycle 1]: 2.158e-05, [1] [cse]: 1.579e-05 [environ_conv]: 7.95998e-06 [swap_dp_allreduce_reducescatter]: 5.34e-06 [bias_add_comm_swap]: 3.31001e-06 [label_micro_interleaved_index]: 5.14e-06 [label_fine_grained_interleaved_index]: 2.74999e-06 [merge_cast_opt]: 1.72001e-06 [slice_recompute_activation]: 2.38002e-06 [micro_interleaved_order_control]: 2.52001e-06 [assign_add_opt]: 1.34998e-06 [ForceFp32Comm]: 9.09989e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 2.56998e-06 [reorder_send_recv_between_fp_bp]: 3.04001e-06 [comm_op_add_attrs]: 1.67001e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 1.26002e-06 [interleave_parallel_branches]: 1.10999e-06 [overlap_opt_shard_in_pipeline]: 1.32e-06 [overlap_opt_shard_grad_in_pipeline]: 1.80001e-06 [control_data_broadcast_order]: 1.381e-05 [grouped_pairwise_exchange_alltoall]: 1.72001e-06 [offloading_packed_experts]: 4.41002e-06 [overlap_recompute_and_grad_model_parallel]: 5.34998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.18001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.74998e-06 [overlap_recompute_comm]: 2.18998e-06 [overlap_grad_ring_attention]: 4.67998e-06 [overlap_grad_flash_sp]: 2.342e-05 [begin_end_overlap_inline]: 5.40022e-07 [split_matmul_comm_elemetwise]: 2.30002e-06 [split_layernorm_comm]: 2.06e-06 [handle_group_info]: 1.29e-06 [symbol_engine_optimizer]: 7.592e-05, [1] [Cycle 1]: 7.07e-05, [6] [build]: 3.84002e-06 [elim_shapecalc]: 9.64e-06 [elim_not_effective]: 1.372e-05 [opt_reshape]: 6.33e-06 [fold_const_symbol]: 9.65002e-06 [renormalize]: 3.00002e-07 [detach_backward]: 2.54999e-06 [pipeline_parallel_scheduler]: 2.17001e-06 [auto_monad_reorder]: 2.175e-05 [get_jit_bprop_graph]: 2.06998e-06 [rewriter_after_jit_bprop_graph]: 5.93002e-06 [opt_after_jit_grad]: 0.00050586 [validate]: 5.278e-05 Sums bootstrap : 0.000685s : 0.25% type_inference : 0.261580s : 97.14% event_method : 0.000144s : 0.05% auto_monad : 0.000095s : 0.04% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000040s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000055s : 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 : 0.000007s : 0.00% optimize.rewriter_before_opt_a : 0.000348s : 0.13% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000070s : 0.03% optimize.opt_a.loop_unroll : 0.000049s : 0.02% optimize.opt_a.a_1 : 0.000980s : 0.36% optimize.opt_a.with_stream_mark : 0.000044s : 0.02% optimize.opt_a.recompute_prepare : 0.000016s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000149s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000012s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.00% optimize.opt_a.merge_send_recv : 0.000017s : 0.01% optimize.opt_a.auto_parallel : 0.000017s : 0.01% optimize.opt_a.parallel : 0.000052s : 0.02% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000009s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000020s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000016s : 0.01% optimize.opt_a.virtual_dataset : 0.000013s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000011s : 0.00% optimize.opt_a.virtual_output : 0.000011s : 0.00% optimize.opt_a.merge_forward : 0.000009s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000021s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000029s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000021s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 0.00% optimize.opt_a.meta_fg_expand : 0.000006s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000021s : 0.01% optimize.opt_a.a_after_grad : 0.000018s : 0.01% optimize.opt_a.renormalize : 0.001671s : 0.62% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000030s : 0.01% optimize.opt_a.cse : 0.000064s : 0.02% optimize.opt_a.a_3 : 0.000119s : 0.04% optimize.py_interpret_to_execute_after_opt_a : 0.000009s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000024s : 0.01% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000908s : 0.34% optimize.opt_b.b_1 : 0.000118s : 0.04% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000028s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000019s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.01% optimize.loop_unroll : 0.000531s : 0.20% optimize.opt_after_cconv.c_1 : 0.000025s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000023s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000021s : 0.01% optimize.tuple_transform.d_1 : 0.000040s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000008s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000065s : 0.02% optimize.cse_after_recomputation.cse : 0.000016s : 0.01% optimize.environ_conv : 0.000008s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000005s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 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 : 0.000002s : 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 : 0.000014s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 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 : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000010s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000014s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000006s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000022s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000506s : 0.19% validate : 0.000053s : 0.02% Time group info: ------[substitution.] 0.000283 28 0.97% : 0.000003s : 2: substitution.elim_not_effective 0.48% : 0.000001s : 2: substitution.fold_const_symbol 2.27% : 0.000006s : 3: substitution.graph_param_transform 85.11% : 0.000241s : 7: substitution.inline 1.59% : 0.000004s : 4: substitution.j_node_and_user_rematch 1.86% : 0.000005s : 4: substitution.remove_not_recompute_node 1.51% : 0.000004s : 2: substitution.replace_old_param 6.21% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.261483 2 99.11% : 0.259151s : 1: type_inference.infer 0.89% : 0.002332s : 1: type_inference.specialize ------[replace.] 0.000124 11 68.70% : 0.000085s : 7: replace.inline 31.30% : 0.000039s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000252 11 93.78% : 0.000237s : 7: match.inline 6.22% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000217 1291 1.08% : 0.000002s : 15: predicate.accumulaten_eliminater 0.64% : 0.000001s : 3: predicate.ad_related_special_op_eliminate 0.62% : 0.000001s : 6: predicate.addn_check_dump 1.13% : 0.000002s : 15: predicate.addn_zero_filter 0.96% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 2.03% : 0.000004s : 21: predicate.arithmetic_simplify 1.01% : 0.000002s : 15: predicate.cast_eliminate 0.57% : 0.000001s : 6: predicate.check_bprop_eliminate 0.58% : 0.000001s : 6: predicate.compare_switch_simplify 0.13% : 0.000000s : 3: predicate.const_output_eliminate 0.38% : 0.000001s : 6: predicate.depend_value_elim 1.06% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.24% : 0.000003s : 15: predicate.dict_get_item_eliminator 1.11% : 0.000002s : 15: predicate.dict_set_item_eliminator 0.93% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.17% : 0.000000s : 3: predicate.elim_not_effective 0.36% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000002s : 18: predicate.environ_add_const_eliminate 1.05% : 0.000002s : 18: predicate.environ_get_add_eliminate 1.58% : 0.000003s : 18: predicate.environ_get_depend_swap 1.48% : 0.000003s : 24: predicate.environ_get_eliminate 1.04% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.69% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.84% : 0.000006s : 26: predicate.float_depend_g_call 0.39% : 0.000001s : 6: predicate.float_environ_get_switch 0.55% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.13% : 0.000000s : 3: predicate.fold_const_symbol 0.51% : 0.000001s : 6: predicate.get_grad_eliminate 0.26% : 0.000001s : 3: predicate.graph_param_transform 0.43% : 0.000001s : 6: predicate.incorporate_call 0.37% : 0.000001s : 6: predicate.incorporate_call_switch 6.11% : 0.000013s : 59: predicate.inline 1.12% : 0.000002s : 6: predicate.inline_without_move 0.23% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.69% : 0.000001s : 6: predicate.less_batch_normalization 1.96% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.41% : 0.000005s : 40: predicate.load_eliminater 0.89% : 0.000002s : 3: predicate.loop_unroll_after_grad 2.95% : 0.000006s : 49: predicate.loop_unroll_before_grad 1.71% : 0.000004s : 21: predicate.make_slice_get_slice_eliminator 0.39% : 0.000001s : 6: predicate.merge_addn 0.50% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.45% : 0.000001s : 6: predicate.mini_step_allgather_replace 1.02% : 0.000002s : 15: predicate.minmaximum_grad 1.20% : 0.000003s : 3: predicate.mutable_eliminate 0.32% : 0.000001s : 3: predicate.opt_reshape 0.78% : 0.000002s : 3: predicate.parallel_virtual_node 2.26% : 0.000005s : 26: predicate.partial_defer_inline 1.49% : 0.000003s : 22: predicate.partial_eliminate 0.91% : 0.000002s : 15: predicate.print_const_string_wrapper 0.57% : 0.000001s : 6: predicate.reduce_all_const_elim 1.38% : 0.000003s : 15: predicate.reduce_eliminate 2.54% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000001s : 6: predicate.remove_not_recompute_node 1.30% : 0.000003s : 25: predicate.replace_applicator 0.48% : 0.000001s : 6: predicate.replace_old_param 0.23% : 0.000001s : 3: predicate.reset_defer_inline 1.00% : 0.000002s : 15: predicate.reshape_eliminate 0.42% : 0.000001s : 6: predicate.row_tensor_add_zeros_like 0.36% : 0.000001s : 3: predicate.row_tensor_eliminate 0.57% : 0.000001s : 6: predicate.same_eliminate 0.29% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.57% : 0.000001s : 6: predicate.shard_identity_eliminate 0.61% : 0.000001s : 6: predicate.special_op_eliminate 0.51% : 0.000001s : 6: predicate.specialize_transform 1.14% : 0.000002s : 6: predicate.split_environ_get_set_with_tuple_value 0.51% : 0.000001s : 6: predicate.stack_unstack_eliminate 0.21% : 0.000000s : 3: predicate.switch_call_monad_eliminater 1.75% : 0.000004s : 26: predicate.switch_defer_inline 2.26% : 0.000005s : 32: predicate.switch_layer_defer_inline 6.06% : 0.000013s : 84: predicate.switch_simplify 1.02% : 0.000002s : 15: predicate.tile_eliminate 0.97% : 0.000002s : 15: predicate.transpose_eliminate 1.49% : 0.000003s : 21: predicate.tuple_list_convert_item_index_to_positive 1.45% : 0.000003s : 21: predicate.tuple_list_get_item_const_eliminator 1.25% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 3.23% : 0.000007s : 31: predicate.tuple_list_get_item_eliminator 1.30% : 0.000003s : 21: predicate.tuple_list_get_set_item_eliminator 2.10% : 0.000005s : 27: predicate.tuple_list_set_item_eliminator 1.64% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.54% : 0.000006s : 40: predicate.updatestate_pure_node_eliminater 2.95% : 0.000006s : 46: predicate.updatestate_useless_node_eliminater 0.23% : 0.000001s : 3: predicate.value_based_eliminate 0.66% : 0.000001s : 6: predicate.virtual_dataset_eliminate 0.56% : 0.000001s : 6: predicate.virtual_output_eliminate 0.18% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.41% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001752 18 59.98% : 0.001051s : 9: func_graph_cloner_run.FuncGraphClonerGraph 40.02% : 0.000701s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.290116 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.65% : 0.004772s : 1: add_attr 1.64% : 0.004755s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000071s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000104s : 1: auto_monad 0.01% : 0.000026s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.25% : 0.000725s : 1: bootstrap 0.01% : 0.000042s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.01% : 0.000029s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000028s : 1: detach_backward 0.00% : 0.000011s : 1: environ_conv 0.05% : 0.000156s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 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% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.19% : 0.000542s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.32% : 0.000921s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.01% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000019s : 1: opt.transform.mutable_eliminate 0.50% : 0.001456s : 78: opt.transform.opt_a 0.01% : 0.000023s : 1: opt.transform.opt_after_cconv 0.01% : 0.000024s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000098s : 28: opt.transform.opt_b 0.02% : 0.000046s : 2: opt.transform.opt_trans_graph 0.01% : 0.000036s : 4: opt.transform.symbol_engine_opt 1.42% : 0.004106s : 1: opt_a 0.05% : 0.000155s : 1: opt_after_cconv 0.18% : 0.000517s : 1: opt_after_jit_grad 0.08% : 0.000218s : 1: opt_b 2.41% : 0.006991s : 1: optimize 0.01% : 0.000023s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.01% : 0.000027s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000008s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000060s : 1: pre_auto_parallel 0.00% : 0.000011s : 1: py_interpret_to_execute 0.00% : 0.000012s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000025s : 1: remove_dup_value 0.31% : 0.000886s : 1: renormalize.infer 0.27% : 0.000773s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000028s : 1: rewriter_after_opt_a 0.12% : 0.000356s : 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% : 0.000008s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000079s : 1: symbol_engine_optimizer 0.03% : 0.000078s : 1: tuple_transform 90.17% : 0.261606s : 1: type_inference TotalTime = 0.480561, [21] [bootstrap]: 0.00047425 [type_inference]: 0.274057 [event_method]: 0.00029591 [auto_monad]: 0.00021003 [graph_reusing]: 1.239e-05 [inline]: 3.78999e-06 [add_attr]: 0.0172815, [1] [add_attr_with_inline]: 0.0172581, [1] [Cycle 1]: 0.0129334, [2] [tag_attr]: 9.35e-05 [meta_addattr_fg_expand]: 0.0127222 [parallel-infer-symbol]: 7.16001e-06 [pre_auto_parallel]: 0.00028298 [insert-virtual-dataset]: 3.2e-06 [parallel-infer-symbol-second]: 1.22e-06 [dataset_repeat_opt]: 3.23e-06 [pipeline_split]: 2.49999e-06 [optimize]: 0.186951, [53] [py_interpret_to_execute]: 1.553e-05 [rewriter_before_opt_a]: 0.00072391 [opt_a]: 0.183862, [3] [Cycle 1]: 0.0681449, [45] [expand_dump_flag]: 1.004e-05 [switch_simplify]: 0.00022451 [loop_unroll]: 8.79e-05 [a_1]: 0.00225315 [with_stream_mark]: 4.334e-05 [recompute_prepare]: 3.297e-05 [updatestate_depend_eliminate]: 1.178e-05 [updatestate_assign_eliminate]: 8.17e-06 [updatestate_loads_eliminate]: 7.43e-06 [parameter_eliminate]: 4.72e-06 [a_2]: 0.00026457 [accelerated_algorithm]: 1.782e-05 [shard]: 2.67001e-06 [meta_shard_fg_expand]: 8.57e-06 [shard_inline]: 1.59e-05 [merge_send_recv]: 2.265e-05 [auto_parallel]: 1.587e-05 [parallel]: 2.421e-05 [flash_sp]: 1.389e-05 [merge_comm]: 1.086e-05 [allreduce_fusion]: 9.00001e-06 [matmul_add_comm_reduction]: 3.66e-05 [allreduce_slice_to_reducescatter]: 1.19003e-06 [virtual_shard_identity]: 1.933e-05 [virtual_dataset]: 1.584e-05 [get_grad_eliminate_]: 1.363e-05 [virtual_output]: 1.439e-05 [merge_forward]: 1.189e-05 [cell_reuse_recompute_pass]: 2.11998e-06 [offload_activation]: 2.004e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.482e-05 [merge_recompute_call_nodes]: 1.94e-06 [before_grad]: 2.828e-05 [set_forward_comm_id_for_comm_node_pass]: 1.204e-05 [meta_fg_expand]: 0.0496296 [flash_sp_send_recv_attached]: 5.80002e-06 [receive_attached]: 3.20998e-06 [after_resolve]: 0.00010128 [a_after_grad]: 9.951e-05 [renormalize]: 0.0136505 [add_forward_monad_depend]: 1.728e-05 [auto_monad_grad]: 8.23001e-06 [auto_monad_eliminator]: 7.015e-05 [cse]: 0.00042634 [a_3]: 0.00038398 [Cycle 2]: 0.115127, [45] [expand_dump_flag]: 3.07002e-06 [switch_simplify]: 4.776e-05 [loop_unroll]: 4.069e-05 [a_1]: 0.026823 [with_stream_mark]: 4.585e-05 [recompute_prepare]: 1.886e-05 [updatestate_depend_eliminate]: 7.48e-06 [updatestate_assign_eliminate]: 5.00001e-06 [updatestate_loads_eliminate]: 4.17e-06 [parameter_eliminate]: 2.93e-06 [a_2]: 0.00010832 [accelerated_algorithm]: 1.024e-05 [shard]: 3.3e-06 [meta_shard_fg_expand]: 6.63e-06 [shard_inline]: 8.17e-06 [merge_send_recv]: 1.249e-05 [auto_parallel]: 1.227e-05 [parallel]: 1.16e-05 [flash_sp]: 6.17001e-06 [merge_comm]: 6.18002e-06 [allreduce_fusion]: 4.35e-06 [matmul_add_comm_reduction]: 1.406e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 1.237e-05 [virtual_dataset]: 8.1e-06 [get_grad_eliminate_]: 7.5e-06 [virtual_output]: 7.78001e-06 [merge_forward]: 5.45001e-06 [cell_reuse_recompute_pass]: 3.59002e-06 [offload_activation]: 1.621e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.127e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 1.7e-05 [set_forward_comm_id_for_comm_node_pass]: 6.32001e-06 [meta_fg_expand]: 0.0004698 [flash_sp_send_recv_attached]: 3.19001e-06 [receive_attached]: 3.53e-06 [after_resolve]: 2.467e-05 [a_after_grad]: 1.401e-05 [renormalize]: 0.0867666 [add_forward_monad_depend]: 1.464e-05 [auto_monad_grad]: 4.08999e-06 [auto_monad_eliminator]: 2.866e-05 [cse]: 4.3e-05 [a_3]: 5.548e-05 [Cycle 3]: 0.00055875, [45] [expand_dump_flag]: 3.53e-06 [switch_simplify]: 7.36001e-06 [loop_unroll]: 4.68001e-06 [a_1]: 5.864e-05 [with_stream_mark]: 1.964e-05 [recompute_prepare]: 5.10001e-06 [updatestate_depend_eliminate]: 3.85e-06 [updatestate_assign_eliminate]: 2.53e-06 [updatestate_loads_eliminate]: 2.35002e-06 [parameter_eliminate]: 3.00002e-06 [a_2]: 3.93e-05 [accelerated_algorithm]: 4.62998e-06 [shard]: 3.02002e-06 [meta_shard_fg_expand]: 2.49001e-06 [shard_inline]: 4.10998e-06 [merge_send_recv]: 9.51e-06 [auto_parallel]: 1.13e-05 [parallel]: 1.048e-05 [flash_sp]: 1.69e-06 [merge_comm]: 2.41e-06 [allreduce_fusion]: 2.63e-06 [matmul_add_comm_reduction]: 9.69999e-06 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 5.69999e-06 [virtual_dataset]: 4.22e-06 [get_grad_eliminate_]: 3.8e-06 [virtual_output]: 4.68999e-06 [merge_forward]: 4.22e-06 [cell_reuse_recompute_pass]: 4.2e-06 [offload_activation]: 9.79e-06 [cell_reuse_handle_not_recompute_node_pass]: 2.675e-05 [merge_recompute_call_nodes]: 1.69e-06 [before_grad]: 8.53001e-06 [set_forward_comm_id_for_comm_node_pass]: 2.85002e-06 [meta_fg_expand]: 2.51998e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 2.67001e-06 [after_resolve]: 4.42e-06 [a_after_grad]: 4.92e-06 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 1.70001e-06 [auto_monad_grad]: 2.12999e-06 [auto_monad_eliminator]: 5.89999e-06 [cse]: 1.631e-05 [a_3]: 2.01e-05 [py_interpret_to_execute_after_opt_a]: 1.108e-05 [slice_cell_reuse_recomputed_activation]: 2.59001e-06 [rewriter_after_opt_a]: 2.204e-05 [convert_after_rewriter]: 1.27999e-06 [order_py_execute_after_rewriter]: 1.21002e-06 [mutable_eliminate]: 0.00085333 [opt_b]: 0.00016792, [1] [Cycle 1]: 0.00015749, [7] [b_1]: 7.735e-05 [b_2]: 6.74999e-06 [updatestate_depend_eliminate]: 8.74e-06 [updatestate_assign_eliminate]: 2.32999e-06 [updatestate_loads_eliminate]: 2.41e-06 [renormalize]: 6.89994e-07 [cse]: 2.359e-05 [optimize_parallel_all_gather_comm]: 1.97e-05 [overlap_param_gather]: 2.09e-06 [cconv]: 4.178e-05 [loop_unroll]: 0.00050966 [opt_after_cconv]: 8.989e-05, [1] [Cycle 1]: 8.301e-05, [7] [c_1]: 1.452e-05 [parameter_eliminate]: 5.52999e-06 [updatestate_depend_eliminate]: 6.33e-06 [updatestate_assign_eliminate]: 1.87999e-06 [updatestate_loads_eliminate]: 1.64e-06 [cse]: 1.832e-05 [renormalize]: 8.60018e-07 [remove_dup_value]: 1.669e-05 [tuple_transform]: 6.321e-05, [1] [Cycle 1]: 5.659e-05, [4] [d_1]: 2.936e-05 [none_parameter_eliminate]: 2.39001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 5.32999e-06 [partial_unused_args_eliminate]: 2.22001e-06 [add_recomputation]: 4.336e-05 [cse_after_recomputation]: 2.148e-05, [1] [Cycle 1]: 1.621e-05, [1] [cse]: 1.024e-05 [environ_conv]: 6.43998e-06 [swap_dp_allreduce_reducescatter]: 5.61998e-06 [bias_add_comm_swap]: 3.45e-06 [label_micro_interleaved_index]: 5.61e-06 [label_fine_grained_interleaved_index]: 2.76e-06 [merge_cast_opt]: 1.71e-06 [slice_recompute_activation]: 2.49001e-06 [micro_interleaved_order_control]: 3.29001e-06 [assign_add_opt]: 1.29998e-06 [ForceFp32Comm]: 1.27999e-06 [remove_cast_before_assign_add]: 1.45001e-06 [full_micro_interleaved_order_control]: 2.39999e-06 [reorder_send_recv_between_fp_bp]: 3.51999e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.15001e-06 [interleave_split_concat_branches]: 1.32e-06 [interleave_parallel_branches]: 1.13001e-06 [overlap_opt_shard_in_pipeline]: 1.44e-06 [overlap_opt_shard_grad_in_pipeline]: 1.87999e-06 [control_data_broadcast_order]: 1.285e-05 [grouped_pairwise_exchange_alltoall]: 1.75001e-06 [offloading_packed_experts]: 3.61001e-06 [overlap_recompute_and_grad_model_parallel]: 4.62e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.89e-06 [overlap_recompute_comm]: 2.66e-06 [overlap_grad_ring_attention]: 3.61999e-06 [overlap_grad_flash_sp]: 2.074e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.76999e-06 [split_layernorm_comm]: 2.09999e-06 [handle_group_info]: 1.20999e-06 [symbol_engine_optimizer]: 6.952e-05, [1] [Cycle 1]: 6.376e-05, [6] [build]: 3.78001e-06 [elim_shapecalc]: 9.15999e-06 [elim_not_effective]: 9.46e-06 [opt_reshape]: 5.15001e-06 [fold_const_symbol]: 6.87002e-06 [renormalize]: 1.8999e-07 [detach_backward]: 2.59001e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 1.605e-05 [get_jit_bprop_graph]: 1.86998e-06 [rewriter_after_jit_bprop_graph]: 6.09999e-06 [opt_after_jit_grad]: 0.00067266 [validate]: 4.836e-05 Sums bootstrap : 0.000474s : 0.10% type_inference : 0.274057s : 57.78% event_method : 0.000296s : 0.06% auto_monad : 0.000210s : 0.04% graph_reusing : 0.000012s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000093s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.012722s : 2.68% parallel-infer-symbol : 0.000007s : 0.00% pre_auto_parallel : 0.000283s : 0.06% 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 : 0.000016s : 0.00% optimize.rewriter_before_opt_a : 0.000724s : 0.15% optimize.opt_a.expand_dump_flag : 0.000017s : 0.00% optimize.opt_a.switch_simplify : 0.000280s : 0.06% optimize.opt_a.loop_unroll : 0.000133s : 0.03% optimize.opt_a.a_1 : 0.029135s : 6.14% optimize.opt_a.with_stream_mark : 0.000109s : 0.02% optimize.opt_a.recompute_prepare : 0.000057s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_a.parameter_eliminate : 0.000011s : 0.00% optimize.opt_a.a_2 : 0.000412s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000033s : 0.01% optimize.opt_a.shard : 0.000009s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000018s : 0.00% optimize.opt_a.shard_inline : 0.000028s : 0.01% optimize.opt_a.merge_send_recv : 0.000045s : 0.01% optimize.opt_a.auto_parallel : 0.000039s : 0.01% optimize.opt_a.parallel : 0.000046s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000019s : 0.00% optimize.opt_a.allreduce_fusion : 0.000016s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000060s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.01% optimize.opt_a.virtual_dataset : 0.000028s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000025s : 0.01% optimize.opt_a.virtual_output : 0.000027s : 0.01% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000010s : 0.00% optimize.opt_a.offload_activation : 0.000046s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000083s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000054s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.050102s : 10.56% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000130s : 0.03% optimize.opt_a.a_after_grad : 0.000118s : 0.02% optimize.opt_a.renormalize : 0.100417s : 21.17% optimize.opt_a.add_forward_monad_depend : 0.000034s : 0.01% optimize.opt_a.auto_monad_grad : 0.000014s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000105s : 0.02% optimize.opt_a.cse : 0.000486s : 0.10% optimize.opt_a.a_3 : 0.000460s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000011s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000022s : 0.00% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000853s : 0.18% optimize.opt_b.b_1 : 0.000077s : 0.02% optimize.opt_b.b_2 : 0.000007s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000024s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000020s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.01% optimize.loop_unroll : 0.000510s : 0.11% optimize.opt_after_cconv.c_1 : 0.000015s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000018s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000017s : 0.00% optimize.tuple_transform.d_1 : 0.000029s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000005s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000043s : 0.01% optimize.cse_after_recomputation.cse : 0.000010s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 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 : 0.000004s : 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 : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000021s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000009s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000009s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000005s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000007s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000016s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000673s : 0.14% validate : 0.000048s : 0.01% Time group info: ------[substitution.] 0.026443 161 0.01% : 0.000002s : 1: substitution.elim_not_effective 0.05% : 0.000012s : 12: substitution.float_depend_g_call 0.02% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.01% : 0.000002s : 1: substitution.fold_const_symbol 0.02% : 0.000005s : 1: substitution.graph_param_transform 0.01% : 0.000004s : 2: substitution.incorporate_call 0.01% : 0.000003s : 2: substitution.incorporate_call_switch 98.70% : 0.026099s : 23: substitution.inline 0.09% : 0.000025s : 2: substitution.inline_without_move 0.05% : 0.000014s : 12: substitution.j_node_and_user_rematch 0.05% : 0.000014s : 7: substitution.minmaximum_grad 0.04% : 0.000012s : 12: substitution.partial_eliminate 0.05% : 0.000014s : 12: substitution.remove_not_recompute_node 0.12% : 0.000033s : 9: substitution.replace_applicator 0.03% : 0.000008s : 11: substitution.replace_old_param 0.04% : 0.000011s : 1: substitution.reshape_eliminate 0.01% : 0.000003s : 1: substitution.set_cell_output_no_recompute 0.07% : 0.000019s : 3: substitution.switch_simplify 0.10% : 0.000025s : 7: substitution.tuple_list_convert_item_index_to_positive 0.04% : 0.000011s : 7: substitution.tuple_list_get_item_const_eliminator 0.07% : 0.000019s : 7: substitution.tuple_list_get_item_depend_reorder 0.33% : 0.000087s : 19: substitution.tuple_list_get_item_eliminator 0.06% : 0.000017s : 7: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.273879 2 93.21% : 0.255295s : 1: type_inference.infer 6.79% : 0.018584s : 1: type_inference.specialize ------[replace.] 0.000524 36 64.25% : 0.000337s : 23: replace.inline 11.33% : 0.000059s : 3: replace.switch_simplify 24.42% : 0.000128s : 10: replace.tuple_list_get_item_eliminator ------[match.] 0.026147 36 99.75% : 0.026081s : 23: match.inline 0.06% : 0.000016s : 3: match.switch_simplify 0.19% : 0.000050s : 10: match.tuple_list_get_item_eliminator ------[predicate.] 0.000766 4012 1.17% : 0.000009s : 53: predicate.accumulaten_eliminater 0.22% : 0.000002s : 1: predicate.ad_related_special_op_eliminate 0.42% : 0.000003s : 17: predicate.addn_check_dump 1.04% : 0.000008s : 53: predicate.addn_zero_filter 1.00% : 0.000008s : 53: predicate.adjust_all_reduce_mul_add 1.80% : 0.000014s : 70: predicate.arithmetic_simplify 1.00% : 0.000008s : 53: predicate.cast_eliminate 0.88% : 0.000007s : 42: predicate.check_bprop_eliminate 0.38% : 0.000003s : 17: predicate.compare_switch_simplify 0.02% : 0.000000s : 1: predicate.const_output_eliminate 0.36% : 0.000003s : 17: predicate.depend_value_elim 1.26% : 0.000010s : 53: predicate.dict_get_item_const_eliminator 1.25% : 0.000010s : 53: predicate.dict_get_item_eliminator 1.23% : 0.000009s : 53: predicate.dict_set_item_eliminator 0.29% : 0.000002s : 2: predicate.dumpgradient_eliminate 0.02% : 0.000000s : 1: predicate.elim_not_effective 0.06% : 0.000000s : 1: predicate.elim_shapecalc_of_broadcastargs 1.04% : 0.000008s : 54: predicate.environ_add_const_eliminate 0.91% : 0.000007s : 54: predicate.environ_get_add_eliminate 0.90% : 0.000007s : 54: predicate.environ_get_depend_swap 1.28% : 0.000010s : 71: predicate.environ_get_eliminate 0.91% : 0.000007s : 54: predicate.environ_get_set_eliminate 9.10% : 0.000070s : 86: predicate.exchange_switch_depend_value 2.71% : 0.000021s : 86: predicate.float_depend_g_call 0.48% : 0.000004s : 17: predicate.float_environ_get_switch 0.70% : 0.000005s : 18: predicate.float_tuple_getitem_switch 0.01% : 0.000000s : 1: predicate.fold_const_symbol 0.36% : 0.000003s : 17: predicate.get_grad_eliminate 0.02% : 0.000000s : 1: predicate.graph_param_transform 0.34% : 0.000003s : 17: predicate.incorporate_call 0.28% : 0.000002s : 17: predicate.incorporate_call_switch 6.94% : 0.000053s : 175: predicate.inline 1.33% : 0.000010s : 47: predicate.inline_without_move 0.17% : 0.000001s : 17: predicate.j_node_and_user_rematch 0.59% : 0.000004s : 17: predicate.less_batch_normalization 1.20% : 0.000009s : 65: predicate.list_to_tuple_eliminator_ 2.09% : 0.000016s : 118: predicate.load_eliminater 0.21% : 0.000002s : 1: predicate.loop_unroll_after_grad 2.58% : 0.000020s : 136: predicate.loop_unroll_before_grad 1.18% : 0.000009s : 55: predicate.make_slice_get_slice_eliminator 0.36% : 0.000003s : 17: predicate.merge_addn 0.74% : 0.000006s : 42: predicate.micro_step_allgather_replace 0.81% : 0.000006s : 42: predicate.mini_step_allgather_replace 1.12% : 0.000009s : 53: predicate.minmaximum_grad 0.34% : 0.000003s : 1: predicate.mutable_eliminate 0.07% : 0.000001s : 1: predicate.opt_reshape 0.06% : 0.000000s : 1: predicate.parallel_virtual_node 2.83% : 0.000022s : 86: predicate.partial_defer_inline 1.32% : 0.000010s : 64: predicate.partial_eliminate 0.97% : 0.000007s : 53: predicate.print_const_string_wrapper 0.43% : 0.000003s : 17: predicate.reduce_all_const_elim 1.20% : 0.000009s : 53: predicate.reduce_eliminate 2.18% : 0.000017s : 118: predicate.redundant_stop_gradient_eliminater 0.25% : 0.000002s : 17: predicate.remove_not_recompute_node 1.60% : 0.000012s : 105: predicate.replace_applicator 0.69% : 0.000005s : 47: predicate.replace_old_param 0.03% : 0.000000s : 1: predicate.reset_defer_inline 0.94% : 0.000007s : 53: predicate.reshape_eliminate 0.81% : 0.000006s : 42: predicate.row_tensor_add_zeros_like 0.10% : 0.000001s : 1: predicate.row_tensor_eliminate 3.15% : 0.000024s : 42: predicate.same_eliminate 0.27% : 0.000002s : 17: predicate.set_cell_output_no_recompute 0.54% : 0.000004s : 17: predicate.shard_identity_eliminate 0.14% : 0.000001s : 2: predicate.special_op_eliminate 0.37% : 0.000003s : 17: predicate.specialize_transform 1.12% : 0.000009s : 42: predicate.split_environ_get_set_with_tuple_value 1.13% : 0.000009s : 47: predicate.stack_unstack_eliminate 0.03% : 0.000000s : 1: predicate.switch_call_monad_eliminater 1.87% : 0.000014s : 86: predicate.switch_defer_inline 2.42% : 0.000019s : 128: predicate.switch_layer_defer_inline 5.82% : 0.000045s : 246: predicate.switch_simplify 1.00% : 0.000008s : 53: predicate.tile_eliminate 0.99% : 0.000008s : 53: predicate.transpose_eliminate 1.58% : 0.000012s : 55: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000012s : 55: predicate.tuple_list_get_item_const_eliminator 1.39% : 0.000011s : 55: predicate.tuple_list_get_item_depend_reorder 2.65% : 0.000020s : 82: predicate.tuple_list_get_item_eliminator 1.11% : 0.000008s : 55: predicate.tuple_list_get_set_item_eliminator 1.59% : 0.000012s : 72: predicate.tuple_list_set_item_eliminator 1.17% : 0.000009s : 65: predicate.tuple_to_list_eliminator_ 1.98% : 0.000015s : 118: predicate.updatestate_pure_node_eliminater 2.54% : 0.000019s : 135: predicate.updatestate_useless_node_eliminater 0.05% : 0.000000s : 1: predicate.value_based_eliminate 0.45% : 0.000003s : 17: predicate.virtual_dataset_eliminate 0.41% : 0.000003s : 17: predicate.virtual_output_eliminate 0.02% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.06% : 0.000000s : 1: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005613 54 59.75% : 0.003354s : 27: func_graph_cloner_run.FuncGraphClonerGraph 40.25% : 0.002259s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.816034 233 0.00% : 0.000004s : 1: ForceFp32Comm 2.12% : 0.017293s : 1: add_attr 2.12% : 0.017266s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000048s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000222s : 1: auto_monad 0.00% : 0.000021s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.06% : 0.000506s : 1: bootstrap 0.01% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000016s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000024s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000009s : 1: environ_conv 0.04% : 0.000311s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000018s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.06% : 0.000519s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.11% : 0.000868s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000013s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000019s : 1: opt.transform.mutable_eliminate 3.78% : 0.030850s : 117: opt.transform.opt_a 0.00% : 0.000013s : 1: opt.transform.opt_after_cconv 0.00% : 0.000025s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000048s : 28: opt.transform.opt_b 0.00% : 0.000032s : 2: opt.transform.opt_trans_graph 0.00% : 0.000026s : 4: opt.transform.symbol_engine_opt 22.53% : 0.183868s : 1: opt_a 0.01% : 0.000093s : 1: opt_after_cconv 0.08% : 0.000690s : 1: opt_after_jit_grad 0.02% : 0.000172s : 1: opt_b 22.91% : 0.186958s : 1: optimize 0.00% : 0.000023s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000024s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000015s : 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% : 0.000007s : 1: pipeline_split 0.04% : 0.000291s : 1: pre_auto_parallel 0.00% : 0.000021s : 1: py_interpret_to_execute 0.00% : 0.000014s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.01% : 0.000056s : 1: remove_dup_value 1.57% : 0.012799s : 2: renormalize.infer 10.73% : 0.087583s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000025s : 1: rewriter_after_opt_a 0.09% : 0.000743s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000072s : 1: symbol_engine_optimizer 0.01% : 0.000067s : 1: tuple_transform 33.59% : 0.274088s : 1: type_inference TotalTime = 0.204837, [21] [bootstrap]: 0.00057759 [type_inference]: 0.111505 [event_method]: 0.00016329 [auto_monad]: 0.0001047 [graph_reusing]: 8.32e-06 [inline]: 3.36001e-06 [add_attr]: 0.0839777, [1] [add_attr_with_inline]: 0.0839637, [1] [Cycle 1]: 9.997e-05, [2] [tag_attr]: 4.224e-05 [meta_addattr_fg_expand]: 7.33e-06 [parallel-infer-symbol]: 4.35e-06 [pre_auto_parallel]: 5.9e-05 [insert-virtual-dataset]: 3.25e-06 [parallel-infer-symbol-second]: 1.15999e-06 [dataset_repeat_opt]: 2.16e-06 [pipeline_split]: 1.81003e-06 [optimize]: 0.00747699, [53] [py_interpret_to_execute]: 1.113e-05 [rewriter_before_opt_a]: 0.00038137 [opt_a]: 0.00435522, [2] [Cycle 1]: 0.0035688, [45] [expand_dump_flag]: 4.07e-06 [switch_simplify]: 6.205e-05 [loop_unroll]: 4.339e-05 [a_1]: 0.00086854 [with_stream_mark]: 2.968e-05 [recompute_prepare]: 9.71e-06 [updatestate_depend_eliminate]: 5.09998e-06 [updatestate_assign_eliminate]: 3.81001e-06 [updatestate_loads_eliminate]: 3.58999e-06 [parameter_eliminate]: 2.56e-06 [a_2]: 8.05e-05 [accelerated_algorithm]: 7.51001e-06 [shard]: 2.63998e-06 [meta_shard_fg_expand]: 3.05002e-06 [shard_inline]: 6.88e-06 [merge_send_recv]: 1.059e-05 [auto_parallel]: 1.017e-05 [parallel]: 2.178e-05 [flash_sp]: 1.179e-05 [merge_comm]: 3.8e-06 [allreduce_fusion]: 3.65e-06 [matmul_add_comm_reduction]: 1.067e-05 [allreduce_slice_to_reducescatter]: 6.40022e-07 [virtual_shard_identity]: 8.17e-06 [virtual_dataset]: 6.88e-06 [get_grad_eliminate_]: 6.42001e-06 [virtual_output]: 6.84001e-06 [merge_forward]: 4.3e-06 [cell_reuse_recompute_pass]: 1.30999e-06 [offload_activation]: 1.235e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.524e-05 [merge_recompute_call_nodes]: 2.00002e-06 [before_grad]: 1.167e-05 [set_forward_comm_id_for_comm_node_pass]: 4.15e-06 [meta_fg_expand]: 3.23998e-06 [flash_sp_send_recv_attached]: 2.87002e-06 [receive_attached]: 3.38e-06 [after_resolve]: 1.123e-05 [a_after_grad]: 9.59e-06 [renormalize]: 0.00181011 [add_forward_monad_depend]: 9.27001e-06 [auto_monad_grad]: 2.99001e-06 [auto_monad_eliminator]: 2.122e-05 [cse]: 4.467e-05 [a_3]: 8.007e-05 [Cycle 2]: 0.00076989, [45] [expand_dump_flag]: 2.64001e-06 [switch_simplify]: 8.99e-06 [loop_unroll]: 5.75001e-06 [a_1]: 0.00011404 [with_stream_mark]: 2.032e-05 [recompute_prepare]: 6.42001e-06 [updatestate_depend_eliminate]: 4.60999e-06 [updatestate_assign_eliminate]: 3.62998e-06 [updatestate_loads_eliminate]: 3.55e-06 [parameter_eliminate]: 2.04e-06 [a_2]: 6.83e-05 [accelerated_algorithm]: 6.59999e-06 [shard]: 2.31e-06 [meta_shard_fg_expand]: 2.22001e-06 [shard_inline]: 4.993e-05 [merge_send_recv]: 1.045e-05 [auto_parallel]: 1.131e-05 [parallel]: 9.76e-06 [flash_sp]: 4.75001e-06 [merge_comm]: 4.33001e-06 [allreduce_fusion]: 3.63999e-06 [matmul_add_comm_reduction]: 1.054e-05 [allreduce_slice_to_reducescatter]: 7.00005e-07 [virtual_shard_identity]: 8.64e-06 [virtual_dataset]: 6.24999e-06 [get_grad_eliminate_]: 5.82001e-06 [virtual_output]: 5.95002e-06 [merge_forward]: 5.94999e-06 [cell_reuse_recompute_pass]: 2.99999e-06 [offload_activation]: 1.141e-05 [cell_reuse_handle_not_recompute_node_pass]: 2e-05 [merge_recompute_call_nodes]: 2.36e-06 [before_grad]: 1.092e-05 [set_forward_comm_id_for_comm_node_pass]: 4.90001e-06 [meta_fg_expand]: 3.13e-06 [flash_sp_send_recv_attached]: 1.57001e-06 [receive_attached]: 2.54001e-06 [after_resolve]: 1.324e-05 [a_after_grad]: 8.40999e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.24001e-06 [auto_monad_grad]: 2.04999e-06 [auto_monad_eliminator]: 1.137e-05 [cse]: 2.518e-05 [a_3]: 3.81e-05 [py_interpret_to_execute_after_opt_a]: 1.128e-05 [slice_cell_reuse_recomputed_activation]: 3.06999e-06 [rewriter_after_opt_a]: 3.37e-05 [convert_after_rewriter]: 1.53002e-06 [order_py_execute_after_rewriter]: 1.29e-06 [mutable_eliminate]: 0.00090333 [opt_b]: 0.00024148, [1] [Cycle 1]: 0.00023088, [7] [b_1]: 0.00012634 [b_2]: 7.26999e-06 [updatestate_depend_eliminate]: 1.303e-05 [updatestate_assign_eliminate]: 3.9e-06 [updatestate_loads_eliminate]: 3.6e-06 [renormalize]: 1.10001e-06 [cse]: 3.718e-05 [optimize_parallel_all_gather_comm]: 4.704e-05 [overlap_param_gather]: 2.94001e-06 [cconv]: 3.98e-05 [loop_unroll]: 0.00054768 [opt_after_cconv]: 0.00017997, [1] [Cycle 1]: 0.00010828, [7] [c_1]: 2.622e-05 [parameter_eliminate]: 6.55002e-06 [updatestate_depend_eliminate]: 8.97e-06 [updatestate_assign_eliminate]: 2.57001e-06 [updatestate_loads_eliminate]: 2.37999e-06 [cse]: 2.7e-05 [renormalize]: 5.8001e-07 [remove_dup_value]: 2.222e-05 [tuple_transform]: 8.537e-05, [1] [Cycle 1]: 7.953e-05, [4] [d_1]: 4.62e-05 [none_parameter_eliminate]: 1.95001e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 9.12001e-06 [partial_unused_args_eliminate]: 2.56e-06 [add_recomputation]: 6.692e-05 [cse_after_recomputation]: 3.02e-05, [1] [Cycle 1]: 2.521e-05, [1] [cse]: 1.879e-05 [environ_conv]: 2.895e-05 [swap_dp_allreduce_reducescatter]: 7.59002e-06 [bias_add_comm_swap]: 3.45e-06 [label_micro_interleaved_index]: 6.21e-06 [label_fine_grained_interleaved_index]: 2.86e-06 [merge_cast_opt]: 1.57001e-06 [slice_recompute_activation]: 2.33002e-06 [micro_interleaved_order_control]: 2.76e-06 [assign_add_opt]: 1.39e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 9.5999e-07 [full_micro_interleaved_order_control]: 3.01001e-06 [reorder_send_recv_between_fp_bp]: 3.36001e-06 [comm_op_add_attrs]: 1.14e-06 [add_comm_op_reuse_tag]: 1.10001e-06 [interleave_split_concat_branches]: 1.49998e-06 [interleave_parallel_branches]: 1.51998e-06 [overlap_opt_shard_in_pipeline]: 1.34e-06 [overlap_opt_shard_grad_in_pipeline]: 1.93002e-06 [control_data_broadcast_order]: 1.787e-05 [grouped_pairwise_exchange_alltoall]: 1.75001e-06 [offloading_packed_experts]: 4.89003e-06 [overlap_recompute_and_grad_model_parallel]: 6.63e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.79e-06 [overlap_recompute_allgather_and_fa_grad]: 1.61002e-06 [overlap_recompute_comm]: 2.46e-06 [overlap_grad_ring_attention]: 4.86002e-06 [overlap_grad_flash_sp]: 2.644e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.71e-06 [split_layernorm_comm]: 2.12999e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 8.895e-05, [1] [Cycle 1]: 8.255e-05, [6] [build]: 3.48e-06 [elim_shapecalc]: 1.28e-05 [elim_not_effective]: 1.563e-05 [opt_reshape]: 7.55e-06 [fold_const_symbol]: 1.175e-05 [renormalize]: 2.69996e-07 [detach_backward]: 2.88998e-06 [pipeline_parallel_scheduler]: 1.99e-06 [auto_monad_reorder]: 2.286e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 7.61001e-06 [opt_after_jit_grad]: 0.00060449 [validate]: 6.929e-05 Sums bootstrap : 0.000578s : 0.48% type_inference : 0.111505s : 93.19% event_method : 0.000163s : 0.14% auto_monad : 0.000105s : 0.09% graph_reusing : 0.000008s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000042s : 0.04% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000059s : 0.05% 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 : 0.000011s : 0.01% optimize.rewriter_before_opt_a : 0.000381s : 0.32% optimize.opt_a.expand_dump_flag : 0.000007s : 0.01% optimize.opt_a.switch_simplify : 0.000071s : 0.06% optimize.opt_a.loop_unroll : 0.000049s : 0.04% optimize.opt_a.a_1 : 0.000983s : 0.82% optimize.opt_a.with_stream_mark : 0.000050s : 0.04% optimize.opt_a.recompute_prepare : 0.000016s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000149s : 0.12% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000057s : 0.05% optimize.opt_a.merge_send_recv : 0.000021s : 0.02% optimize.opt_a.auto_parallel : 0.000021s : 0.02% optimize.opt_a.parallel : 0.000032s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000008s : 0.01% optimize.opt_a.allreduce_fusion : 0.000007s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000017s : 0.01% optimize.opt_a.virtual_dataset : 0.000013s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000012s : 0.01% optimize.opt_a.virtual_output : 0.000013s : 0.01% optimize.opt_a.merge_forward : 0.000010s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000024s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000035s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000023s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.01% optimize.opt_a.meta_fg_expand : 0.000006s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000024s : 0.02% optimize.opt_a.a_after_grad : 0.000018s : 0.02% optimize.opt_a.renormalize : 0.001810s : 1.51% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000033s : 0.03% optimize.opt_a.cse : 0.000070s : 0.06% optimize.opt_a.a_3 : 0.000118s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000011s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000034s : 0.03% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000903s : 0.75% optimize.opt_b.b_1 : 0.000126s : 0.11% optimize.opt_b.b_2 : 0.000007s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000037s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000047s : 0.04% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000040s : 0.03% optimize.loop_unroll : 0.000548s : 0.46% optimize.opt_after_cconv.c_1 : 0.000026s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000027s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.02% optimize.tuple_transform.d_1 : 0.000046s : 0.04% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000067s : 0.06% optimize.cse_after_recomputation.cse : 0.000019s : 0.02% optimize.environ_conv : 0.000029s : 0.02% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 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 : 0.000001s : 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 : 0.000002s : 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 : 0.000018s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000026s : 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 : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000016s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000008s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000012s : 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 : 0.000023s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.01% opt_after_jit_grad : 0.000604s : 0.51% validate : 0.000069s : 0.06% Time group info: ------[substitution.] 0.000281 28 0.94% : 0.000003s : 2: substitution.elim_not_effective 0.63% : 0.000002s : 2: substitution.fold_const_symbol 2.48% : 0.000007s : 3: substitution.graph_param_transform 83.61% : 0.000235s : 7: substitution.inline 1.84% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.16% : 0.000006s : 4: substitution.remove_not_recompute_node 2.06% : 0.000006s : 2: substitution.replace_old_param 6.28% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.111398 2 97.58% : 0.108705s : 1: type_inference.infer 2.42% : 0.002693s : 1: type_inference.specialize ------[replace.] 0.000113 11 66.94% : 0.000076s : 7: replace.inline 33.06% : 0.000037s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000247 11 93.65% : 0.000231s : 7: match.inline 6.35% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000272 1291 0.81% : 0.000002s : 15: predicate.accumulaten_eliminater 1.11% : 0.000003s : 3: predicate.ad_related_special_op_eliminate 0.30% : 0.000001s : 6: predicate.addn_check_dump 0.87% : 0.000002s : 15: predicate.addn_zero_filter 0.79% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 1.84% : 0.000005s : 21: predicate.arithmetic_simplify 0.82% : 0.000002s : 15: predicate.cast_eliminate 0.37% : 0.000001s : 6: predicate.check_bprop_eliminate 0.34% : 0.000001s : 6: predicate.compare_switch_simplify 0.11% : 0.000000s : 3: predicate.const_output_eliminate 0.65% : 0.000002s : 6: predicate.depend_value_elim 1.06% : 0.000003s : 15: predicate.dict_get_item_const_eliminator 0.95% : 0.000003s : 15: predicate.dict_get_item_eliminator 0.90% : 0.000002s : 15: predicate.dict_set_item_eliminator 0.85% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.12% : 0.000000s : 3: predicate.elim_not_effective 0.37% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 0.98% : 0.000003s : 18: predicate.environ_add_const_eliminate 0.84% : 0.000002s : 18: predicate.environ_get_add_eliminate 0.95% : 0.000003s : 18: predicate.environ_get_depend_swap 1.20% : 0.000003s : 24: predicate.environ_get_eliminate 0.89% : 0.000002s : 18: predicate.environ_get_set_eliminate 1.34% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.21% : 0.000006s : 26: predicate.float_depend_g_call 0.29% : 0.000001s : 6: predicate.float_environ_get_switch 0.46% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.10% : 0.000000s : 3: predicate.fold_const_symbol 0.45% : 0.000001s : 6: predicate.get_grad_eliminate 0.26% : 0.000001s : 3: predicate.graph_param_transform 0.33% : 0.000001s : 6: predicate.incorporate_call 0.29% : 0.000001s : 6: predicate.incorporate_call_switch 20.25% : 0.000055s : 59: predicate.inline 0.54% : 0.000001s : 6: predicate.inline_without_move 0.19% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.68% : 0.000002s : 6: predicate.less_batch_normalization 1.64% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.36% : 0.000006s : 40: predicate.load_eliminater 1.14% : 0.000003s : 3: predicate.loop_unroll_after_grad 2.57% : 0.000007s : 49: predicate.loop_unroll_before_grad 1.60% : 0.000004s : 21: predicate.make_slice_get_slice_eliminator 0.30% : 0.000001s : 6: predicate.merge_addn 0.33% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.43% : 0.000001s : 6: predicate.mini_step_allgather_replace 0.72% : 0.000002s : 15: predicate.minmaximum_grad 1.58% : 0.000004s : 3: predicate.mutable_eliminate 0.45% : 0.000001s : 3: predicate.opt_reshape 0.47% : 0.000001s : 3: predicate.parallel_virtual_node 1.83% : 0.000005s : 26: predicate.partial_defer_inline 1.22% : 0.000003s : 22: predicate.partial_eliminate 0.72% : 0.000002s : 15: predicate.print_const_string_wrapper 0.39% : 0.000001s : 6: predicate.reduce_all_const_elim 0.98% : 0.000003s : 15: predicate.reduce_eliminate 2.14% : 0.000006s : 40: predicate.redundant_stop_gradient_eliminater 0.42% : 0.000001s : 6: predicate.remove_not_recompute_node 1.13% : 0.000003s : 25: predicate.replace_applicator 0.44% : 0.000001s : 6: predicate.replace_old_param 0.18% : 0.000000s : 3: predicate.reset_defer_inline 0.79% : 0.000002s : 15: predicate.reshape_eliminate 0.44% : 0.000001s : 6: predicate.row_tensor_add_zeros_like 0.26% : 0.000001s : 3: predicate.row_tensor_eliminate 0.65% : 0.000002s : 6: predicate.same_eliminate 0.25% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.80% : 0.000002s : 6: predicate.shard_identity_eliminate 0.51% : 0.000001s : 6: predicate.special_op_eliminate 0.42% : 0.000001s : 6: predicate.specialize_transform 0.97% : 0.000003s : 6: predicate.split_environ_get_set_with_tuple_value 0.47% : 0.000001s : 6: predicate.stack_unstack_eliminate 0.20% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.39% : 0.000004s : 26: predicate.switch_defer_inline 1.74% : 0.000005s : 32: predicate.switch_layer_defer_inline 4.70% : 0.000013s : 84: predicate.switch_simplify 0.80% : 0.000002s : 15: predicate.tile_eliminate 0.83% : 0.000002s : 15: predicate.transpose_eliminate 1.20% : 0.000003s : 21: predicate.tuple_list_convert_item_index_to_positive 1.25% : 0.000003s : 21: predicate.tuple_list_get_item_const_eliminator 1.11% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 2.88% : 0.000008s : 31: predicate.tuple_list_get_item_eliminator 1.17% : 0.000003s : 21: predicate.tuple_list_get_set_item_eliminator 1.86% : 0.000005s : 27: predicate.tuple_list_set_item_eliminator 1.37% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.15% : 0.000006s : 40: predicate.updatestate_pure_node_eliminater 2.52% : 0.000007s : 46: predicate.updatestate_useless_node_eliminater 0.21% : 0.000001s : 3: predicate.value_based_eliminate 0.55% : 0.000002s : 6: predicate.virtual_dataset_eliminate 0.45% : 0.000001s : 6: predicate.virtual_output_eliminate 0.15% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.30% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001666 18 49.59% : 0.000826s : 9: func_graph_cloner_run.FuncGraphClonerGraph 50.41% : 0.000840s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.299703 192 0.00% : 0.000004s : 1: ForceFp32Comm 28.02% : 0.083985s : 1: add_attr 28.02% : 0.083968s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000072s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000115s : 1: auto_monad 0.01% : 0.000027s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000619s : 1: bootstrap 0.01% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000022s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.01% : 0.000034s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000035s : 1: environ_conv 0.07% : 0.000202s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000008s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.19% : 0.000558s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.31% : 0.000922s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000026s : 1: opt.transform.mutable_eliminate 0.50% : 0.001494s : 78: opt.transform.opt_a 0.01% : 0.000025s : 1: opt.transform.opt_after_cconv 0.01% : 0.000029s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000102s : 28: opt.transform.opt_b 0.02% : 0.000053s : 2: opt.transform.opt_trans_graph 0.01% : 0.000044s : 4: opt.transform.symbol_engine_opt 1.45% : 0.004359s : 1: opt_a 0.06% : 0.000184s : 1: opt_after_cconv 0.21% : 0.000617s : 1: opt_after_jit_grad 0.08% : 0.000246s : 1: opt_b 2.50% : 0.007484s : 1: optimize 0.02% : 0.000054s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.01% : 0.000030s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 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% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000064s : 1: pre_auto_parallel 0.00% : 0.000015s : 1: py_interpret_to_execute 0.01% : 0.000016s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000026s : 1: remove_dup_value 0.31% : 0.000922s : 1: renormalize.infer 0.29% : 0.000875s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000038s : 1: rewriter_after_opt_a 0.13% : 0.000390s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000092s : 1: symbol_engine_optimizer 0.03% : 0.000089s : 1: tuple_transform 37.22% : 0.111535s : 1: type_inference TotalTime = 0.42437, [21] [bootstrap]: 0.072916 [type_inference]: 0.184276 [event_method]: 0.00028473 [auto_monad]: 0.0454727 [graph_reusing]: 2.17e-05 [inline]: 4.23001e-06 [add_attr]: 0.00442402, [1] [add_attr_with_inline]: 0.0044092, [1] [Cycle 1]: 0.00016267, [2] [tag_attr]: 9.555e-05 [meta_addattr_fg_expand]: 1.797e-05 [parallel-infer-symbol]: 3.71001e-06 [pre_auto_parallel]: 0.00015254 [insert-virtual-dataset]: 2.91999e-06 [parallel-infer-symbol-second]: 1.60999e-06 [dataset_repeat_opt]: 3.11999e-06 [pipeline_split]: 2.30002e-06 [optimize]: 0.115838, [53] [py_interpret_to_execute]: 9.91e-06 [rewriter_before_opt_a]: 0.00062633 [opt_a]: 0.112571, [3] [Cycle 1]: 0.108114, [45] [expand_dump_flag]: 8.18999e-06 [switch_simplify]: 0.00021768 [loop_unroll]: 9.862e-05 [a_1]: 0.00200434 [with_stream_mark]: 4.685e-05 [recompute_prepare]: 3.461e-05 [updatestate_depend_eliminate]: 1.226e-05 [updatestate_assign_eliminate]: 7.41001e-06 [updatestate_loads_eliminate]: 7.97e-06 [parameter_eliminate]: 3.95998e-06 [a_2]: 0.00023416 [accelerated_algorithm]: 1.687e-05 [shard]: 2.27999e-06 [meta_shard_fg_expand]: 1.023e-05 [shard_inline]: 1.478e-05 [merge_send_recv]: 2.204e-05 [auto_parallel]: 1.864e-05 [parallel]: 2.339e-05 [flash_sp]: 1.583e-05 [merge_comm]: 1.026e-05 [allreduce_fusion]: 8.99998e-06 [matmul_add_comm_reduction]: 3.787e-05 [allreduce_slice_to_reducescatter]: 1.03001e-06 [virtual_shard_identity]: 2.373e-05 [virtual_dataset]: 1.538e-05 [get_grad_eliminate_]: 1.494e-05 [virtual_output]: 1.601e-05 [merge_forward]: 1.148e-05 [cell_reuse_recompute_pass]: 1.81998e-06 [offload_activation]: 2.021e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.127e-05 [merge_recompute_call_nodes]: 2.16e-06 [before_grad]: 2.721e-05 [set_forward_comm_id_for_comm_node_pass]: 1.169e-05 [meta_fg_expand]: 0.00256436 [flash_sp_send_recv_attached]: 5.14e-06 [receive_attached]: 2.34001e-06 [after_resolve]: 0.00010087 [a_after_grad]: 0.00010259 [renormalize]: 0.101036 [add_forward_monad_depend]: 1.825e-05 [auto_monad_grad]: 7.99002e-06 [auto_monad_eliminator]: 6.698e-05 [cse]: 0.00040855 [a_3]: 0.00034244 [Cycle 2]: 0.00382028, [45] [expand_dump_flag]: 3.64002e-06 [switch_simplify]: 4.603e-05 [loop_unroll]: 3.853e-05 [a_1]: 0.00131059 [with_stream_mark]: 2.491e-05 [recompute_prepare]: 9.20999e-06 [updatestate_depend_eliminate]: 5.34e-06 [updatestate_assign_eliminate]: 3.04001e-06 [updatestate_loads_eliminate]: 2.54999e-06 [parameter_eliminate]: 2.66e-06 [a_2]: 6.412e-05 [accelerated_algorithm]: 6.37001e-06 [shard]: 2.21998e-06 [meta_shard_fg_expand]: 3.04001e-06 [shard_inline]: 5.27001e-06 [merge_send_recv]: 9.00999e-06 [auto_parallel]: 1.041e-05 [parallel]: 1.026e-05 [flash_sp]: 4.87e-06 [merge_comm]: 3.16999e-06 [allreduce_fusion]: 3.08e-06 [matmul_add_comm_reduction]: 1.065e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 8.47e-06 [virtual_dataset]: 5.44e-06 [get_grad_eliminate_]: 5.34e-06 [virtual_output]: 5.28002e-06 [merge_forward]: 3.97002e-06 [cell_reuse_recompute_pass]: 1.11997e-06 [offload_activation]: 1.034e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.391e-05 [merge_recompute_call_nodes]: 1.77999e-06 [before_grad]: 9.92999e-06 [set_forward_comm_id_for_comm_node_pass]: 3.98999e-06 [meta_fg_expand]: 0.00040553 [flash_sp_send_recv_attached]: 2.78e-06 [receive_attached]: 2.93e-06 [after_resolve]: 2.01e-05 [a_after_grad]: 8.85001e-06 [renormalize]: 0.00130117 [add_forward_monad_depend]: 5.89e-06 [auto_monad_grad]: 3.04999e-06 [auto_monad_eliminator]: 1.591e-05 [cse]: 8.798e-05 [a_3]: 4.491e-05 [Cycle 3]: 0.0006107, [45] [expand_dump_flag]: 1.44998e-06 [switch_simplify]: 7.34002e-06 [loop_unroll]: 5.10999e-06 [a_1]: 9.84e-05 [with_stream_mark]: 1.289e-05 [recompute_prepare]: 5.96998e-06 [updatestate_depend_eliminate]: 3.41999e-06 [updatestate_assign_eliminate]: 2.29001e-06 [updatestate_loads_eliminate]: 2.69999e-06 [parameter_eliminate]: 2.773e-05 [a_2]: 6.235e-05 [accelerated_algorithm]: 5.80002e-06 [shard]: 1.44e-06 [meta_shard_fg_expand]: 2.14e-06 [shard_inline]: 5.39998e-06 [merge_send_recv]: 5.89999e-06 [auto_parallel]: 7.58999e-06 [parallel]: 6.54999e-06 [flash_sp]: 1.27e-06 [merge_comm]: 3.16999e-06 [allreduce_fusion]: 2.93998e-06 [matmul_add_comm_reduction]: 6.28e-06 [allreduce_slice_to_reducescatter]: 7.10017e-07 [virtual_shard_identity]: 6.66e-06 [virtual_dataset]: 5.19998e-06 [get_grad_eliminate_]: 4.64998e-06 [virtual_output]: 4.90001e-06 [merge_forward]: 3.4e-06 [cell_reuse_recompute_pass]: 2.29001e-06 [offload_activation]: 7.53e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.305e-05 [merge_recompute_call_nodes]: 9.00007e-07 [before_grad]: 8.80001e-06 [set_forward_comm_id_for_comm_node_pass]: 3.28998e-06 [meta_fg_expand]: 1.87999e-06 [flash_sp_send_recv_attached]: 1.22999e-06 [receive_attached]: 1.15001e-06 [after_resolve]: 8.54998e-06 [a_after_grad]: 7.48999e-06 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 1.49e-06 [auto_monad_grad]: 1.67999e-06 [auto_monad_eliminator]: 6.01e-06 [cse]: 1.466e-05 [a_3]: 2.903e-05 [py_interpret_to_execute_after_opt_a]: 6.70998e-06 [slice_cell_reuse_recomputed_activation]: 2.02001e-06 [rewriter_after_opt_a]: 2.099e-05 [convert_after_rewriter]: 1.29e-06 [order_py_execute_after_rewriter]: 1.21997e-06 [mutable_eliminate]: 0.00080247 [opt_b]: 0.00042479, [2] [Cycle 1]: 0.00030903, [7] [b_1]: 0.00022743 [b_2]: 6.86999e-06 [updatestate_depend_eliminate]: 6.81001e-06 [updatestate_assign_eliminate]: 1.88002e-06 [updatestate_loads_eliminate]: 2.25002e-06 [renormalize]: 6.69999e-07 [cse]: 2.009e-05 [Cycle 2]: 0.00010268, [7] [b_1]: 5.754e-05 [b_2]: 3.74002e-06 [updatestate_depend_eliminate]: 1.87999e-06 [updatestate_assign_eliminate]: 1.40001e-06 [updatestate_loads_eliminate]: 1.27e-06 [renormalize]: 7.00238e-08 [cse]: 7.51999e-06 [optimize_parallel_all_gather_comm]: 1.808e-05 [overlap_param_gather]: 1.89e-06 [cconv]: 3.454e-05 [loop_unroll]: 0.0006578 [opt_after_cconv]: 9.386e-05, [1] [Cycle 1]: 8.593e-05, [7] [c_1]: 1.729e-05 [parameter_eliminate]: 5.15001e-06 [updatestate_depend_eliminate]: 5.79999e-06 [updatestate_assign_eliminate]: 2.29999e-06 [updatestate_loads_eliminate]: 1.59e-06 [cse]: 1.955e-05 [renormalize]: 2.50002e-07 [remove_dup_value]: 1.595e-05 [tuple_transform]: 5.634e-05, [1] [Cycle 1]: 5.151e-05, [4] [d_1]: 2.448e-05 [none_parameter_eliminate]: 1.54e-06 [renormalize]: 1.30007e-07 [switch_simplify]: 5.42999e-06 [partial_unused_args_eliminate]: 2.04e-06 [add_recomputation]: 4.312e-05 [cse_after_recomputation]: 2.011e-05, [1] [Cycle 1]: 1.565e-05, [1] [cse]: 1.002e-05 [environ_conv]: 5.54998e-06 [swap_dp_allreduce_reducescatter]: 4.33999e-06 [bias_add_comm_swap]: 3.04999e-06 [label_micro_interleaved_index]: 4.57e-06 [label_fine_grained_interleaved_index]: 3.28e-06 [merge_cast_opt]: 1.56002e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.88998e-06 [assign_add_opt]: 1.50001e-06 [ForceFp32Comm]: 1.30001e-06 [remove_cast_before_assign_add]: 1.15001e-06 [full_micro_interleaved_order_control]: 2.58e-06 [reorder_send_recv_between_fp_bp]: 2.87002e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.27e-06 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.14e-06 [overlap_opt_shard_in_pipeline]: 1.67001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.81998e-06 [control_data_broadcast_order]: 1.275e-05 [grouped_pairwise_exchange_alltoall]: 1.89999e-06 [offloading_packed_experts]: 3.2e-06 [overlap_recompute_and_grad_model_parallel]: 4.28001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.16002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.45999e-06 [overlap_recompute_comm]: 2.48e-06 [overlap_grad_ring_attention]: 4.72e-06 [overlap_grad_flash_sp]: 2.175e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.68e-06 [split_layernorm_comm]: 2.02001e-06 [handle_group_info]: 1.42e-06 [symbol_engine_optimizer]: 6.84e-05, [1] [Cycle 1]: 6.102e-05, [6] [build]: 3.49001e-06 [elim_shapecalc]: 6.73998e-06 [elim_not_effective]: 1.015e-05 [opt_reshape]: 5.24e-06 [fold_const_symbol]: 6.48e-06 [renormalize]: 1.90019e-07 [detach_backward]: 2.87002e-06 [pipeline_parallel_scheduler]: 1.86e-06 [auto_monad_reorder]: 1.615e-05 [get_jit_bprop_graph]: 2.58e-06 [rewriter_after_jit_bprop_graph]: 6.71e-06 [opt_after_jit_grad]: 0.00055335 [validate]: 4.362e-05 Sums bootstrap : 0.072916s : 17.43% type_inference : 0.184276s : 44.05% event_method : 0.000285s : 0.07% auto_monad : 0.045473s : 10.87% graph_reusing : 0.000022s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000096s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000018s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000153s : 0.04% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000010s : 0.00% optimize.rewriter_before_opt_a : 0.000626s : 0.15% optimize.opt_a.expand_dump_flag : 0.000013s : 0.00% optimize.opt_a.switch_simplify : 0.000271s : 0.06% optimize.opt_a.loop_unroll : 0.000142s : 0.03% optimize.opt_a.a_1 : 0.003413s : 0.82% optimize.opt_a.with_stream_mark : 0.000085s : 0.02% optimize.opt_a.recompute_prepare : 0.000050s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_a.parameter_eliminate : 0.000034s : 0.01% optimize.opt_a.a_2 : 0.000361s : 0.09% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000015s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.01% optimize.opt_a.merge_send_recv : 0.000037s : 0.01% optimize.opt_a.auto_parallel : 0.000037s : 0.01% optimize.opt_a.parallel : 0.000040s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.01% optimize.opt_a.merge_comm : 0.000017s : 0.00% optimize.opt_a.allreduce_fusion : 0.000015s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000055s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.01% optimize.opt_a.virtual_dataset : 0.000026s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000025s : 0.01% optimize.opt_a.virtual_output : 0.000026s : 0.01% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000058s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000046s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.00% optimize.opt_a.meta_fg_expand : 0.002972s : 0.71% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000130s : 0.03% optimize.opt_a.a_after_grad : 0.000119s : 0.03% optimize.opt_a.renormalize : 0.102337s : 24.46% optimize.opt_a.add_forward_monad_depend : 0.000026s : 0.01% optimize.opt_a.auto_monad_grad : 0.000013s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000089s : 0.02% optimize.opt_a.cse : 0.000511s : 0.12% optimize.opt_a.a_3 : 0.000416s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000007s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000021s : 0.01% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000802s : 0.19% optimize.opt_b.b_1 : 0.000285s : 0.07% 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 : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000028s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000018s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.01% optimize.loop_unroll : 0.000658s : 0.16% optimize.opt_after_cconv.c_1 : 0.000017s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000020s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000016s : 0.00% optimize.tuple_transform.d_1 : 0.000024s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000005s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000043s : 0.01% optimize.cse_after_recomputation.cse : 0.000010s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000004s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000003s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000004s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000022s : 0.01% 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 : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000007s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000010s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000005s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000006s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000016s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000553s : 0.13% validate : 0.000044s : 0.01% Time group info: ------[substitution.] 0.001101 163 0.19% : 0.000002s : 1: substitution.elim_not_effective 0.89% : 0.000010s : 12: substitution.float_depend_g_call 0.52% : 0.000006s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000001s : 1: substitution.fold_const_symbol 0.45% : 0.000005s : 1: substitution.graph_param_transform 0.32% : 0.000004s : 2: substitution.incorporate_call 0.26% : 0.000003s : 2: substitution.incorporate_call_switch 67.51% : 0.000744s : 23: substitution.inline 2.47% : 0.000027s : 2: substitution.inline_without_move 0.99% : 0.000011s : 12: substitution.j_node_and_user_rematch 1.08% : 0.000012s : 7: substitution.minmaximum_grad 1.00% : 0.000011s : 12: substitution.partial_eliminate 1.02% : 0.000011s : 12: substitution.remove_not_recompute_node 2.67% : 0.000029s : 9: substitution.replace_applicator 1.32% : 0.000015s : 13: substitution.replace_old_param 0.46% : 0.000005s : 1: substitution.set_cell_output_no_recompute 1.35% : 0.000015s : 3: substitution.switch_simplify 2.35% : 0.000026s : 7: substitution.tuple_list_convert_item_index_to_positive 1.04% : 0.000011s : 7: substitution.tuple_list_get_item_const_eliminator 1.46% : 0.000016s : 7: substitution.tuple_list_get_item_depend_reorder 6.43% : 0.000071s : 19: substitution.tuple_list_get_item_eliminator 1.37% : 0.000015s : 7: substitution.tuple_list_get_set_item_eliminator 4.74% : 0.000052s : 1: substitution.zero_like_fill_zero ------[type_inference.] 0.184120 2 96.97% : 0.178537s : 1: type_inference.infer 3.03% : 0.005583s : 1: type_inference.specialize ------[replace.] 0.000462 37 52.54% : 0.000243s : 23: replace.inline 13.63% : 0.000063s : 3: replace.switch_simplify 25.88% : 0.000120s : 10: replace.tuple_list_get_item_eliminator 7.95% : 0.000037s : 1: replace.zero_like_fill_zero ------[match.] 0.000829 37 88.08% : 0.000730s : 23: match.inline 1.46% : 0.000012s : 3: match.switch_simplify 4.29% : 0.000036s : 10: match.tuple_list_get_item_eliminator 6.17% : 0.000051s : 1: match.zero_like_fill_zero ------[predicate.] 0.000640 4087 1.08% : 0.000007s : 53: predicate.accumulaten_eliminater 0.18% : 0.000001s : 1: predicate.ad_related_special_op_eliminate 0.41% : 0.000003s : 17: predicate.addn_check_dump 1.27% : 0.000008s : 53: predicate.addn_zero_filter 1.05% : 0.000007s : 53: predicate.adjust_all_reduce_mul_add 2.04% : 0.000013s : 70: predicate.arithmetic_simplify 1.18% : 0.000008s : 53: predicate.cast_eliminate 1.01% : 0.000006s : 44: predicate.check_bprop_eliminate 0.38% : 0.000002s : 17: predicate.compare_switch_simplify 0.05% : 0.000000s : 3: predicate.const_output_eliminate 0.35% : 0.000002s : 17: predicate.depend_value_elim 1.17% : 0.000007s : 53: predicate.dict_get_item_const_eliminator 1.34% : 0.000009s : 53: predicate.dict_get_item_eliminator 1.11% : 0.000007s : 53: predicate.dict_set_item_eliminator 0.28% : 0.000002s : 4: predicate.dumpgradient_eliminate 0.03% : 0.000000s : 1: predicate.elim_not_effective 0.09% : 0.000001s : 1: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000007s : 56: predicate.environ_add_const_eliminate 1.11% : 0.000007s : 56: predicate.environ_get_add_eliminate 1.15% : 0.000007s : 56: predicate.environ_get_depend_swap 1.53% : 0.000010s : 73: predicate.environ_get_eliminate 1.08% : 0.000007s : 56: predicate.environ_get_set_eliminate 1.95% : 0.000012s : 86: predicate.exchange_switch_depend_value 2.71% : 0.000017s : 86: predicate.float_depend_g_call 0.37% : 0.000002s : 17: predicate.float_environ_get_switch 0.46% : 0.000003s : 20: predicate.float_tuple_getitem_switch 0.02% : 0.000000s : 1: predicate.fold_const_symbol 0.43% : 0.000003s : 17: predicate.get_grad_eliminate 0.03% : 0.000000s : 1: predicate.graph_param_transform 0.43% : 0.000003s : 17: predicate.incorporate_call 0.34% : 0.000002s : 17: predicate.incorporate_call_switch 5.70% : 0.000036s : 177: predicate.inline 1.44% : 0.000009s : 47: predicate.inline_without_move 0.19% : 0.000001s : 17: predicate.j_node_and_user_rematch 0.55% : 0.000003s : 17: predicate.less_batch_normalization 1.54% : 0.000010s : 67: predicate.list_to_tuple_eliminator_ 2.56% : 0.000016s : 120: predicate.load_eliminater 0.21% : 0.000001s : 1: predicate.loop_unroll_after_grad 3.51% : 0.000022s : 136: predicate.loop_unroll_before_grad 1.30% : 0.000008s : 57: predicate.make_slice_get_slice_eliminator 0.54% : 0.000003s : 17: predicate.merge_addn 0.91% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.93% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.08% : 0.000007s : 53: predicate.minmaximum_grad 0.38% : 0.000002s : 3: predicate.mutable_eliminate 0.06% : 0.000000s : 1: predicate.opt_reshape 0.14% : 0.000001s : 3: predicate.parallel_virtual_node 2.80% : 0.000018s : 86: predicate.partial_defer_inline 1.51% : 0.000010s : 64: predicate.partial_eliminate 1.08% : 0.000007s : 53: predicate.print_const_string_wrapper 0.39% : 0.000002s : 17: predicate.reduce_all_const_elim 1.43% : 0.000009s : 53: predicate.reduce_eliminate 2.62% : 0.000017s : 120: predicate.redundant_stop_gradient_eliminater 0.24% : 0.000002s : 17: predicate.remove_not_recompute_node 1.75% : 0.000011s : 107: predicate.replace_applicator 0.77% : 0.000005s : 47: predicate.replace_old_param 0.11% : 0.000001s : 3: predicate.reset_defer_inline 1.29% : 0.000008s : 53: predicate.reshape_eliminate 0.92% : 0.000006s : 44: predicate.row_tensor_add_zeros_like 0.17% : 0.000001s : 2: predicate.row_tensor_eliminate 1.30% : 0.000008s : 44: predicate.same_eliminate 0.27% : 0.000002s : 17: predicate.set_cell_output_no_recompute 0.62% : 0.000004s : 17: predicate.shard_identity_eliminate 0.22% : 0.000001s : 4: predicate.special_op_eliminate 0.49% : 0.000003s : 17: predicate.specialize_transform 1.34% : 0.000009s : 44: predicate.split_environ_get_set_with_tuple_value 1.39% : 0.000009s : 47: predicate.stack_unstack_eliminate 0.04% : 0.000000s : 1: predicate.switch_call_monad_eliminater 2.02% : 0.000013s : 86: predicate.switch_defer_inline 2.93% : 0.000019s : 130: predicate.switch_layer_defer_inline 7.30% : 0.000047s : 246: predicate.switch_simplify 1.23% : 0.000008s : 53: predicate.tile_eliminate 1.06% : 0.000007s : 53: predicate.transpose_eliminate 1.23% : 0.000008s : 57: predicate.tuple_list_convert_item_index_to_positive 1.35% : 0.000009s : 57: predicate.tuple_list_get_item_const_eliminator 1.15% : 0.000007s : 57: predicate.tuple_list_get_item_depend_reorder 2.79% : 0.000018s : 84: predicate.tuple_list_get_item_eliminator 1.27% : 0.000008s : 57: predicate.tuple_list_get_set_item_eliminator 2.12% : 0.000014s : 74: predicate.tuple_list_set_item_eliminator 1.39% : 0.000009s : 67: predicate.tuple_to_list_eliminator_ 2.35% : 0.000015s : 120: predicate.updatestate_pure_node_eliminater 2.88% : 0.000018s : 137: predicate.updatestate_useless_node_eliminater 0.12% : 0.000001s : 3: predicate.value_based_eliminate 0.46% : 0.000003s : 17: predicate.virtual_dataset_eliminate 0.43% : 0.000003s : 17: predicate.virtual_output_eliminate 0.03% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.37% : 0.000002s : 5: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005626 54 62.34% : 0.003507s : 27: func_graph_cloner_run.FuncGraphClonerGraph 37.66% : 0.002119s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.652129 288 0.00% : 0.000005s : 1: ForceFp32Comm 0.68% : 0.004431s : 1: add_attr 0.68% : 0.004414s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000048s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 6.98% : 0.045521s : 1: auto_monad 0.00% : 0.000020s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 11.19% : 0.072966s : 1: bootstrap 0.01% : 0.000038s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000016s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000023s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.06% : 0.000362s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000030s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000008s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.10% : 0.000669s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.12% : 0.000814s : 1: mutable_eliminate 0.00% : 0.000006s : 1: offloading_packed_experts 0.00% : 0.000014s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000016s : 1: opt.transform.mutable_eliminate 0.77% : 0.005015s : 117: opt.transform.opt_a 0.00% : 0.000016s : 1: opt.transform.opt_after_cconv 0.00% : 0.000018s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000218s : 83: opt.transform.opt_b 0.00% : 0.000027s : 2: opt.transform.opt_trans_graph 0.00% : 0.000025s : 4: opt.transform.symbol_engine_opt 17.26% : 0.112575s : 1: opt_a 0.01% : 0.000097s : 1: opt_after_cconv 0.09% : 0.000564s : 1: opt_after_jit_grad 0.07% : 0.000429s : 1: opt_b 17.76% : 0.115845s : 1: optimize 0.00% : 0.000022s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000025s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000007s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000005s : 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% : 0.000162s : 1: pre_auto_parallel 0.00% : 0.000014s : 1: py_interpret_to_execute 0.00% : 0.000010s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000019s : 1: remove_dup_value 1.91% : 0.012481s : 2: renormalize.infer 13.77% : 0.089828s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000024s : 1: rewriter_after_opt_a 0.10% : 0.000637s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000007s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000071s : 1: symbol_engine_optimizer 0.01% : 0.000059s : 1: tuple_transform 28.26% : 0.184307s : 1: type_inference . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[-1-KBK] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[-1-KBK],max_mem:4.0M . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[None-pynative] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[None-pynative],max_mem:4.0M TotalTime = 0.963899, [21] [bootstrap]: 0.00063255 [type_inference]: 0.545627 [event_method]: 0.00021494 [auto_monad]: 9.61e-05 [graph_reusing]: 7.61999e-06 [inline]: 1.2e-05 [add_attr]: 0.404936, [1] [add_attr_with_inline]: 0.404858, [1] [Cycle 1]: 0.00029331, [2] [tag_attr]: 0.00023629 [meta_addattr_fg_expand]: 8.37e-06 [parallel-infer-symbol]: 4.03001e-06 [pre_auto_parallel]: 6.106e-05 [insert-virtual-dataset]: 2.71e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 2.39999e-06 [pipeline_split]: 2.24999e-06 [optimize]: 0.0113176, [53] [py_interpret_to_execute]: 1.077e-05 [rewriter_before_opt_a]: 0.00037457 [opt_a]: 0.00716689, [2] [Cycle 1]: 0.00650581, [45] [expand_dump_flag]: 3.55e-06 [switch_simplify]: 5.927e-05 [loop_unroll]: 4.301e-05 [a_1]: 0.00103537 [with_stream_mark]: 1.633e-05 [recompute_prepare]: 8.27e-06 [updatestate_depend_eliminate]: 4.17e-06 [updatestate_assign_eliminate]: 3.44001e-06 [updatestate_loads_eliminate]: 3.14999e-06 [parameter_eliminate]: 1.89e-06 [a_2]: 7.839e-05 [accelerated_algorithm]: 6.28e-06 [shard]: 1.85001e-06 [meta_shard_fg_expand]: 2.16e-06 [shard_inline]: 5.69e-06 [merge_send_recv]: 8.48999e-06 [auto_parallel]: 6.09001e-06 [parallel]: 0.00102093 [flash_sp]: 1.033e-05 [merge_comm]: 5.61e-06 [allreduce_fusion]: 3.83001e-06 [matmul_add_comm_reduction]: 1.007e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.058e-05 [virtual_dataset]: 7.01001e-06 [get_grad_eliminate_]: 6.07999e-06 [virtual_output]: 7.06001e-06 [merge_forward]: 6.33e-06 [cell_reuse_recompute_pass]: 1.54e-06 [offload_activation]: 1.18e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.57e-05 [merge_recompute_call_nodes]: 1.79998e-06 [before_grad]: 1.491e-05 [set_forward_comm_id_for_comm_node_pass]: 5.45001e-06 [meta_fg_expand]: 3.36001e-06 [flash_sp_send_recv_attached]: 3.76999e-06 [receive_attached]: 2.48998e-06 [after_resolve]: 1.387e-05 [a_after_grad]: 1.025e-05 [renormalize]: 0.00258365 [add_forward_monad_depend]: 5.60001e-06 [auto_monad_grad]: 3.27002e-06 [auto_monad_eliminator]: 1.656e-05 [cse]: 4.329e-05 [a_3]: 4.67e-05 [Cycle 2]: 0.00064967, [45] [expand_dump_flag]: 1.44998e-06 [switch_simplify]: 6.78998e-06 [loop_unroll]: 5.51e-06 [a_1]: 0.00015894 [with_stream_mark]: 1.331e-05 [recompute_prepare]: 6.34001e-06 [updatestate_depend_eliminate]: 4e-06 [updatestate_assign_eliminate]: 2.95998e-06 [updatestate_loads_eliminate]: 2.58e-06 [parameter_eliminate]: 1.12e-06 [a_2]: 6.601e-05 [accelerated_algorithm]: 5.79e-06 [shard]: 1.65001e-06 [meta_shard_fg_expand]: 1.33002e-06 [shard_inline]: 5.29e-06 [merge_send_recv]: 5.19e-06 [auto_parallel]: 6.78e-06 [parallel]: 5.17e-06 [flash_sp]: 3.49001e-06 [merge_comm]: 3.69002e-06 [allreduce_fusion]: 3.36999e-06 [matmul_add_comm_reduction]: 5.57001e-06 [allreduce_slice_to_reducescatter]: 3.19997e-07 [virtual_shard_identity]: 6.26998e-06 [virtual_dataset]: 5.32999e-06 [get_grad_eliminate_]: 4.84998e-06 [virtual_output]: 5.12e-06 [merge_forward]: 3.49001e-06 [cell_reuse_recompute_pass]: 1.62999e-06 [offload_activation]: 1.026e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.32e-05 [merge_recompute_call_nodes]: 1.07998e-06 [before_grad]: 9.03002e-06 [set_forward_comm_id_for_comm_node_pass]: 3.39001e-06 [meta_fg_expand]: 2.11003e-06 [flash_sp_send_recv_attached]: 8.39995e-07 [receive_attached]: 1.14e-06 [after_resolve]: 8.32e-06 [a_after_grad]: 7.6e-06 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.33002e-06 [auto_monad_grad]: 1.35999e-06 [auto_monad_eliminator]: 6.66e-06 [cse]: 1.742e-05 [a_3]: 3.22e-05 [py_interpret_to_execute_after_opt_a]: 3.8e-06 [slice_cell_reuse_recomputed_activation]: 2.03997e-06 [rewriter_after_opt_a]: 0.0002894 [convert_after_rewriter]: 1.39e-06 [order_py_execute_after_rewriter]: 1.15999e-06 [mutable_eliminate]: 0.00060066 [opt_b]: 0.00019063, [1] [Cycle 1]: 0.00018387, [7] [b_1]: 0.00011031 [b_2]: 7.53e-06 [updatestate_depend_eliminate]: 6.14001e-06 [updatestate_assign_eliminate]: 2.54999e-06 [updatestate_loads_eliminate]: 2.44999e-06 [renormalize]: 2.40019e-07 [cse]: 2.181e-05 [optimize_parallel_all_gather_comm]: 1.636e-05 [overlap_param_gather]: 2.17999e-06 [cconv]: 2.646e-05 [loop_unroll]: 0.00070291 [opt_after_cconv]: 9.899e-05, [1] [Cycle 1]: 9.327e-05, [7] [c_1]: 2.473e-05 [parameter_eliminate]: 2.84999e-06 [updatestate_depend_eliminate]: 5.69e-06 [updatestate_assign_eliminate]: 2.81999e-06 [updatestate_loads_eliminate]: 2.42001e-06 [cse]: 2.184e-05 [renormalize]: 4.00003e-07 [remove_dup_value]: 3.468e-05 [tuple_transform]: 6.537e-05, [1] [Cycle 1]: 6.075e-05, [4] [d_1]: 3.58e-05 [none_parameter_eliminate]: 1.70001e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 6.18998e-06 [partial_unused_args_eliminate]: 2.21e-06 [add_recomputation]: 0.00077837 [cse_after_recomputation]: 2.77e-05, [1] [Cycle 1]: 2.254e-05, [1] [cse]: 1.652e-05 [environ_conv]: 5.99e-06 [swap_dp_allreduce_reducescatter]: 5.64998e-06 [bias_add_comm_swap]: 2.36e-06 [label_micro_interleaved_index]: 3.95998e-06 [label_fine_grained_interleaved_index]: 2.69999e-06 [merge_cast_opt]: 1.37e-06 [slice_recompute_activation]: 2.12999e-06 [micro_interleaved_order_control]: 2.80002e-06 [assign_add_opt]: 1.60999e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.18001e-06 [full_micro_interleaved_order_control]: 2.27001e-06 [reorder_send_recv_between_fp_bp]: 3.08e-06 [comm_op_add_attrs]: 1.32e-06 [add_comm_op_reuse_tag]: 1.06002e-06 [interleave_split_concat_branches]: 1.29e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 1.21002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.19001e-06 [control_data_broadcast_order]: 1.375e-05 [grouped_pairwise_exchange_alltoall]: 1.66002e-06 [offloading_packed_experts]: 3.88001e-06 [overlap_recompute_and_grad_model_parallel]: 5.04e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42999e-06 [overlap_recompute_comm]: 2.57001e-06 [overlap_grad_ring_attention]: 4.35e-06 [overlap_grad_flash_sp]: 2.008e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 2.19001e-06 [split_layernorm_comm]: 2.09999e-06 [handle_group_info]: 1.87999e-06 [symbol_engine_optimizer]: 0.00018529, [1] [Cycle 1]: 0.00018094, [6] [build]: 3.03e-06 [elim_shapecalc]: 1.079e-05 [elim_not_effective]: 1.247e-05 [opt_reshape]: 7.34002e-06 [fold_const_symbol]: 1.002e-05 [renormalize]: 2.3999e-07 [detach_backward]: 2.14999e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 2.079e-05 [get_jit_bprop_graph]: 1.97999e-06 [rewriter_after_jit_bprop_graph]: 3.79002e-06 [opt_after_jit_grad]: 0.00069615 [validate]: 4.324e-05 Sums bootstrap : 0.000633s : 0.11% type_inference : 0.545627s : 98.03% event_method : 0.000215s : 0.04% auto_monad : 0.000096s : 0.02% graph_reusing : 0.000008s : 0.00% inline : 0.000012s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000236s : 0.04% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000061s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000011s : 0.00% optimize.rewriter_before_opt_a : 0.000375s : 0.07% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000066s : 0.01% optimize.opt_a.loop_unroll : 0.000049s : 0.01% optimize.opt_a.a_1 : 0.001194s : 0.21% optimize.opt_a.with_stream_mark : 0.000030s : 0.01% optimize.opt_a.recompute_prepare : 0.000015s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000144s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000012s : 0.00% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000003s : 0.00% optimize.opt_a.shard_inline : 0.000011s : 0.00% optimize.opt_a.merge_send_recv : 0.000014s : 0.00% optimize.opt_a.auto_parallel : 0.000013s : 0.00% optimize.opt_a.parallel : 0.001026s : 0.18% optimize.opt_a.flash_sp : 0.000014s : 0.00% optimize.opt_a.merge_comm : 0.000009s : 0.00% optimize.opt_a.allreduce_fusion : 0.000007s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000016s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000017s : 0.00% optimize.opt_a.virtual_dataset : 0.000012s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000011s : 0.00% optimize.opt_a.virtual_output : 0.000012s : 0.00% optimize.opt_a.merge_forward : 0.000010s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000022s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000029s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000024s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000009s : 0.00% optimize.opt_a.meta_fg_expand : 0.000005s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000022s : 0.00% optimize.opt_a.a_after_grad : 0.000018s : 0.00% optimize.opt_a.renormalize : 0.002584s : 0.46% optimize.opt_a.add_forward_monad_depend : 0.000007s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000023s : 0.00% optimize.opt_a.cse : 0.000061s : 0.01% optimize.opt_a.a_3 : 0.000079s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000004s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000289s : 0.05% optimize.convert_after_rewriter : 0.000001s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000601s : 0.11% optimize.opt_b.b_1 : 0.000110s : 0.02% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000022s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000016s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000026s : 0.00% optimize.loop_unroll : 0.000703s : 0.13% optimize.opt_after_cconv.c_1 : 0.000025s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000022s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000035s : 0.01% optimize.tuple_transform.d_1 : 0.000036s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000778s : 0.14% optimize.cse_after_recomputation.cse : 0.000017s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000002s : 0.00% optimize.label_micro_interleaved_index : 0.000004s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000014s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000004s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000020s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000011s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000012s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000007s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000010s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000021s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000696s : 0.13% validate : 0.000043s : 0.01% Time group info: ------[substitution.] 0.000268 28 0.83% : 0.000002s : 2: substitution.elim_not_effective 0.70% : 0.000002s : 2: substitution.fold_const_symbol 2.03% : 0.000005s : 3: substitution.graph_param_transform 85.08% : 0.000228s : 7: substitution.inline 1.75% : 0.000005s : 4: substitution.j_node_and_user_rematch 1.82% : 0.000005s : 4: substitution.remove_not_recompute_node 1.51% : 0.000004s : 2: substitution.replace_old_param 6.28% : 0.000017s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.545351 2 99.33% : 0.541690s : 1: type_inference.infer 0.67% : 0.003661s : 1: type_inference.specialize ------[replace.] 0.000105 11 67.31% : 0.000071s : 7: replace.inline 32.69% : 0.000034s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000239 11 93.75% : 0.000224s : 7: match.inline 6.25% : 0.000015s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000271 1291 0.83% : 0.000002s : 15: predicate.accumulaten_eliminater 0.60% : 0.000002s : 3: predicate.ad_related_special_op_eliminate 0.31% : 0.000001s : 6: predicate.addn_check_dump 0.84% : 0.000002s : 15: predicate.addn_zero_filter 0.87% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 1.68% : 0.000005s : 21: predicate.arithmetic_simplify 0.87% : 0.000002s : 15: predicate.cast_eliminate 0.46% : 0.000001s : 6: predicate.check_bprop_eliminate 0.30% : 0.000001s : 6: predicate.compare_switch_simplify 0.11% : 0.000000s : 3: predicate.const_output_eliminate 0.33% : 0.000001s : 6: predicate.depend_value_elim 0.85% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.88% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 15: predicate.dict_set_item_eliminator 0.61% : 0.000002s : 6: predicate.dumpgradient_eliminate 0.12% : 0.000000s : 3: predicate.elim_not_effective 0.30% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 0.89% : 0.000002s : 18: predicate.environ_add_const_eliminate 0.85% : 0.000002s : 18: predicate.environ_get_add_eliminate 0.85% : 0.000002s : 18: predicate.environ_get_depend_swap 1.19% : 0.000003s : 24: predicate.environ_get_eliminate 23.80% : 0.000065s : 18: predicate.environ_get_set_eliminate 1.41% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.02% : 0.000005s : 26: predicate.float_depend_g_call 0.42% : 0.000001s : 6: predicate.float_environ_get_switch 0.49% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.09% : 0.000000s : 3: predicate.fold_const_symbol 0.36% : 0.000001s : 6: predicate.get_grad_eliminate 0.19% : 0.000001s : 3: predicate.graph_param_transform 0.33% : 0.000001s : 6: predicate.incorporate_call 0.31% : 0.000001s : 6: predicate.incorporate_call_switch 4.73% : 0.000013s : 59: predicate.inline 0.68% : 0.000002s : 6: predicate.inline_without_move 0.21% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.48% : 0.000001s : 6: predicate.less_batch_normalization 1.44% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 1.90% : 0.000005s : 40: predicate.load_eliminater 0.66% : 0.000002s : 3: predicate.loop_unroll_after_grad 2.40% : 0.000007s : 49: predicate.loop_unroll_before_grad 1.26% : 0.000003s : 21: predicate.make_slice_get_slice_eliminator 0.52% : 0.000001s : 6: predicate.merge_addn 0.38% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.47% : 0.000001s : 6: predicate.mini_step_allgather_replace 0.70% : 0.000002s : 15: predicate.minmaximum_grad 0.55% : 0.000001s : 3: predicate.mutable_eliminate 0.34% : 0.000001s : 3: predicate.opt_reshape 0.28% : 0.000001s : 3: predicate.parallel_virtual_node 1.67% : 0.000005s : 26: predicate.partial_defer_inline 1.21% : 0.000003s : 22: predicate.partial_eliminate 0.76% : 0.000002s : 15: predicate.print_const_string_wrapper 0.37% : 0.000001s : 6: predicate.reduce_all_const_elim 1.05% : 0.000003s : 15: predicate.reduce_eliminate 1.92% : 0.000005s : 40: predicate.redundant_stop_gradient_eliminater 0.25% : 0.000001s : 6: predicate.remove_not_recompute_node 1.03% : 0.000003s : 25: predicate.replace_applicator 0.28% : 0.000001s : 6: predicate.replace_old_param 0.18% : 0.000000s : 3: predicate.reset_defer_inline 0.87% : 0.000002s : 15: predicate.reshape_eliminate 0.32% : 0.000001s : 6: predicate.row_tensor_add_zeros_like 0.24% : 0.000001s : 3: predicate.row_tensor_eliminate 0.55% : 0.000001s : 6: predicate.same_eliminate 0.22% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.52% : 0.000001s : 6: predicate.shard_identity_eliminate 0.64% : 0.000002s : 6: predicate.special_op_eliminate 0.42% : 0.000001s : 6: predicate.specialize_transform 0.54% : 0.000001s : 6: predicate.split_environ_get_set_with_tuple_value 0.49% : 0.000001s : 6: predicate.stack_unstack_eliminate 0.19% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.53% : 0.000004s : 26: predicate.switch_defer_inline 1.70% : 0.000005s : 32: predicate.switch_layer_defer_inline 4.62% : 0.000013s : 84: predicate.switch_simplify 0.74% : 0.000002s : 15: predicate.tile_eliminate 0.76% : 0.000002s : 15: predicate.transpose_eliminate 1.35% : 0.000004s : 21: predicate.tuple_list_convert_item_index_to_positive 1.22% : 0.000003s : 21: predicate.tuple_list_get_item_const_eliminator 1.06% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 2.46% : 0.000007s : 31: predicate.tuple_list_get_item_eliminator 1.13% : 0.000003s : 21: predicate.tuple_list_get_set_item_eliminator 1.65% : 0.000004s : 27: predicate.tuple_list_set_item_eliminator 1.40% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 1.88% : 0.000005s : 40: predicate.updatestate_pure_node_eliminater 2.39% : 0.000006s : 46: predicate.updatestate_useless_node_eliminater 0.21% : 0.000001s : 3: predicate.value_based_eliminate 0.45% : 0.000001s : 6: predicate.virtual_dataset_eliminate 0.39% : 0.000001s : 6: predicate.virtual_output_eliminate 0.15% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.23% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.003020 18 48.42% : 0.001462s : 9: func_graph_cloner_run.FuncGraphClonerGraph 51.58% : 0.001558s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.384007 192 0.00% : 0.000004s : 1: ForceFp32Comm 29.26% : 0.404944s : 1: add_attr 29.25% : 0.404863s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.06% : 0.000785s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000105s : 1: auto_monad 0.00% : 0.000024s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.05% : 0.000674s : 1: bootstrap 0.00% : 0.000030s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.00% : 0.000031s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000009s : 1: environ_conv 0.02% : 0.000227s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000015s : 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 0.05% : 0.000713s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000610s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000014s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000014s : 1: opt.transform.mutable_eliminate 0.12% : 0.001631s : 78: opt.transform.opt_a 0.00% : 0.000024s : 1: opt.transform.opt_after_cconv 0.00% : 0.000024s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000091s : 28: opt.transform.opt_b 0.00% : 0.000040s : 2: opt.transform.opt_trans_graph 0.00% : 0.000037s : 4: opt.transform.symbol_engine_opt 0.52% : 0.007172s : 1: opt_a 0.01% : 0.000102s : 1: opt_after_cconv 0.05% : 0.000707s : 1: opt_after_jit_grad 0.01% : 0.000194s : 1: opt_b 0.82% : 0.011323s : 1: optimize 0.00% : 0.000020s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000023s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000007s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 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% : 0.000004s : 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 0.00% : 0.000066s : 1: pre_auto_parallel 0.00% : 0.000014s : 1: py_interpret_to_execute 0.00% : 0.000008s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000039s : 1: remove_dup_value 0.10% : 0.001393s : 1: renormalize.infer 0.09% : 0.001180s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000295s : 1: rewriter_after_opt_a 0.03% : 0.000381s : 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% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000196s : 1: symbol_engine_optimizer 0.00% : 0.000068s : 1: tuple_transform 39.43% : 0.545668s : 1: type_inference TotalTime = 0.719423, [21] [bootstrap]: 0.00048312 [type_inference]: 0.457103 [event_method]: 0.00046348 [auto_monad]: 0.00021558 [graph_reusing]: 1.164e-05 [inline]: 3.33998e-06 [add_attr]: 0.00443311, [1] [add_attr_with_inline]: 0.00441906, [1] [Cycle 1]: 0.00016566, [2] [tag_attr]: 9.984e-05 [meta_addattr_fg_expand]: 1.66e-05 [parallel-infer-symbol]: 4.41002e-06 [pre_auto_parallel]: 9.732e-05 [insert-virtual-dataset]: 3.70998e-06 [parallel-infer-symbol-second]: 1.07e-06 [dataset_repeat_opt]: 2.63e-06 [pipeline_split]: 2.42001e-06 [optimize]: 0.25578, [53] [py_interpret_to_execute]: 9.15001e-06 [rewriter_before_opt_a]: 0.00067107 [opt_a]: 0.252836, [3] [Cycle 1]: 0.144417, [45] [expand_dump_flag]: 8.45001e-06 [switch_simplify]: 0.00024698 [loop_unroll]: 9.535e-05 [a_1]: 0.00231365 [with_stream_mark]: 6.561e-05 [recompute_prepare]: 3.489e-05 [updatestate_depend_eliminate]: 1.383e-05 [updatestate_assign_eliminate]: 7.73001e-06 [updatestate_loads_eliminate]: 7.79997e-06 [parameter_eliminate]: 4.43001e-06 [a_2]: 0.00023748 [accelerated_algorithm]: 1.874e-05 [shard]: 3.45998e-06 [meta_shard_fg_expand]: 1.294e-05 [shard_inline]: 1.865e-05 [merge_send_recv]: 2.321e-05 [auto_parallel]: 1.753e-05 [parallel]: 2.424e-05 [flash_sp]: 1.522e-05 [merge_comm]: 1.22e-05 [allreduce_fusion]: 1.001e-05 [matmul_add_comm_reduction]: 4.137e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 2.301e-05 [virtual_dataset]: 1.554e-05 [get_grad_eliminate_]: 1.617e-05 [virtual_output]: 1.523e-05 [merge_forward]: 1.175e-05 [cell_reuse_recompute_pass]: 1.67999e-06 [offload_activation]: 2.08e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.76e-05 [merge_recompute_call_nodes]: 2.43e-06 [before_grad]: 2.986e-05 [set_forward_comm_id_for_comm_node_pass]: 1.324e-05 [meta_fg_expand]: 0.12567 [flash_sp_send_recv_attached]: 5.15001e-06 [receive_attached]: 2.84999e-06 [after_resolve]: 0.00010381 [a_after_grad]: 0.00010474 [renormalize]: 0.0134996 [add_forward_monad_depend]: 2.101e-05 [auto_monad_grad]: 1.132e-05 [auto_monad_eliminator]: 7.486e-05 [cse]: 0.00051204 [a_3]: 0.00050047 [Cycle 2]: 0.107867, [45] [expand_dump_flag]: 3.71999e-06 [switch_simplify]: 5.147e-05 [loop_unroll]: 4.43e-05 [a_1]: 0.103092 [with_stream_mark]: 4.068e-05 [recompute_prepare]: 1.96e-05 [updatestate_depend_eliminate]: 6.73e-06 [updatestate_assign_eliminate]: 5.77001e-06 [updatestate_loads_eliminate]: 5.18002e-06 [parameter_eliminate]: 2.93e-06 [a_2]: 0.00013401 [accelerated_algorithm]: 1.259e-05 [shard]: 2.47001e-06 [meta_shard_fg_expand]: 5.58002e-06 [shard_inline]: 1.085e-05 [merge_send_recv]: 1.301e-05 [auto_parallel]: 1.343e-05 [parallel]: 1.061e-05 [flash_sp]: 4.89998e-06 [merge_comm]: 5.79e-06 [allreduce_fusion]: 4.99003e-06 [matmul_add_comm_reduction]: 1.263e-05 [allreduce_slice_to_reducescatter]: 1.14e-06 [virtual_shard_identity]: 1.558e-05 [virtual_dataset]: 1.041e-05 [get_grad_eliminate_]: 9.89001e-06 [virtual_output]: 9.87999e-06 [merge_forward]: 7.18998e-06 [cell_reuse_recompute_pass]: 1.83002e-06 [offload_activation]: 1.352e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.177e-05 [merge_recompute_call_nodes]: 2.24999e-06 [before_grad]: 1.751e-05 [set_forward_comm_id_for_comm_node_pass]: 5.01002e-06 [meta_fg_expand]: 0.00046839 [flash_sp_send_recv_attached]: 2.87002e-06 [receive_attached]: 3.14001e-06 [after_resolve]: 2.294e-05 [a_after_grad]: 1.843e-05 [renormalize]: 0.00324185 [add_forward_monad_depend]: 1.195e-05 [auto_monad_grad]: 3.35998e-06 [auto_monad_eliminator]: 1.578e-05 [cse]: 3.373e-05 [a_3]: 4.869e-05 [Cycle 3]: 0.00052797, [45] [expand_dump_flag]: 2.54999e-06 [switch_simplify]: 7.65e-06 [loop_unroll]: 4.24002e-06 [a_1]: 5.459e-05 [with_stream_mark]: 1.706e-05 [recompute_prepare]: 4.27e-06 [updatestate_depend_eliminate]: 3.76001e-06 [updatestate_assign_eliminate]: 3.38e-06 [updatestate_loads_eliminate]: 2.27999e-06 [parameter_eliminate]: 2.76e-06 [a_2]: 4.118e-05 [accelerated_algorithm]: 4.70001e-06 [shard]: 2.59001e-06 [meta_shard_fg_expand]: 1.99e-06 [shard_inline]: 3.79002e-06 [merge_send_recv]: 7.71999e-06 [auto_parallel]: 9.66e-06 [parallel]: 1.028e-05 [flash_sp]: 2.31e-06 [merge_comm]: 3.41001e-06 [allreduce_fusion]: 2.61999e-06 [matmul_add_comm_reduction]: 8.57e-06 [allreduce_slice_to_reducescatter]: 6.09987e-07 [virtual_shard_identity]: 5.89e-06 [virtual_dataset]: 4.50001e-06 [get_grad_eliminate_]: 3.98999e-06 [virtual_output]: 3.94002e-06 [merge_forward]: 4.18999e-06 [cell_reuse_recompute_pass]: 2.84001e-06 [offload_activation]: 9.15001e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.496e-05 [merge_recompute_call_nodes]: 2.02999e-06 [before_grad]: 9.49e-06 [set_forward_comm_id_for_comm_node_pass]: 2.48998e-06 [meta_fg_expand]: 2.83998e-06 [flash_sp_send_recv_attached]: 1.77001e-06 [receive_attached]: 2.92002e-06 [after_resolve]: 4.18999e-06 [a_after_grad]: 5.57999e-06 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.54001e-06 [auto_monad_grad]: 1.19e-06 [auto_monad_eliminator]: 5.19e-06 [cse]: 1.378e-05 [a_3]: 2.105e-05 [py_interpret_to_execute_after_opt_a]: 7.19001e-06 [slice_cell_reuse_recomputed_activation]: 2.99999e-06 [rewriter_after_opt_a]: 2.122e-05 [convert_after_rewriter]: 1.72001e-06 [order_py_execute_after_rewriter]: 1.29003e-06 [mutable_eliminate]: 0.00079079 [opt_b]: 0.00015957, [1] [Cycle 1]: 0.00015173, [7] [b_1]: 7.79e-05 [b_2]: 5.74999e-06 [updatestate_depend_eliminate]: 8.05999e-06 [updatestate_assign_eliminate]: 1.87999e-06 [updatestate_loads_eliminate]: 2.00002e-06 [renormalize]: 8.89995e-07 [cse]: 1.938e-05 [optimize_parallel_all_gather_comm]: 1.715e-05 [overlap_param_gather]: 2.27999e-06 [cconv]: 3.583e-05 [loop_unroll]: 0.00048584 [opt_after_cconv]: 9.038e-05, [1] [Cycle 1]: 8.415e-05, [7] [c_1]: 1.731e-05 [parameter_eliminate]: 4.73001e-06 [updatestate_depend_eliminate]: 6.33e-06 [updatestate_assign_eliminate]: 1.82999e-06 [updatestate_loads_eliminate]: 1.62999e-06 [cse]: 1.811e-05 [renormalize]: 5.29981e-07 [remove_dup_value]: 1.587e-05 [tuple_transform]: 5.285e-05, [1] [Cycle 1]: 4.829e-05, [4] [d_1]: 2.478e-05 [none_parameter_eliminate]: 1.50999e-06 [renormalize]: 1.40019e-07 [switch_simplify]: 4.3e-06 [partial_unused_args_eliminate]: 2.59999e-06 [add_recomputation]: 4.13e-05 [cse_after_recomputation]: 2.241e-05, [1] [Cycle 1]: 1.682e-05, [1] [cse]: 1.01e-05 [environ_conv]: 5.78997e-06 [swap_dp_allreduce_reducescatter]: 4.82e-06 [bias_add_comm_swap]: 3.91001e-06 [label_micro_interleaved_index]: 4.92e-06 [label_fine_grained_interleaved_index]: 3.17002e-06 [merge_cast_opt]: 1.70001e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.73998e-06 [assign_add_opt]: 1.40999e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 1.14998e-06 [full_micro_interleaved_order_control]: 2.16e-06 [reorder_send_recv_between_fp_bp]: 2.99001e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.20001e-06 [interleave_split_concat_branches]: 1.27999e-06 [interleave_parallel_branches]: 1.12999e-06 [overlap_opt_shard_in_pipeline]: 1.66e-06 [overlap_opt_shard_grad_in_pipeline]: 2.40002e-06 [control_data_broadcast_order]: 1.275e-05 [grouped_pairwise_exchange_alltoall]: 1.90001e-06 [offloading_packed_experts]: 3.27002e-06 [overlap_recompute_and_grad_model_parallel]: 4.74002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.77001e-06 [overlap_recompute_comm]: 2.50002e-06 [overlap_grad_ring_attention]: 3.88999e-06 [overlap_grad_flash_sp]: 2.255e-05 [begin_end_overlap_inline]: 5.8001e-07 [split_matmul_comm_elemetwise]: 2.76999e-06 [split_layernorm_comm]: 1.92999e-06 [handle_group_info]: 1.13001e-06 [symbol_engine_optimizer]: 7.236e-05, [1] [Cycle 1]: 6.627e-05, [6] [build]: 3.23998e-06 [elim_shapecalc]: 8.73001e-06 [elim_not_effective]: 1.131e-05 [opt_reshape]: 5.42001e-06 [fold_const_symbol]: 7.67002e-06 [renormalize]: 2.09984e-07 [detach_backward]: 2.56e-06 [pipeline_parallel_scheduler]: 1.95001e-06 [auto_monad_reorder]: 1.816e-05 [get_jit_bprop_graph]: 2.22999e-06 [rewriter_after_jit_bprop_graph]: 5.74e-06 [opt_after_jit_grad]: 0.00053255 [validate]: 3.777e-05 Sums bootstrap : 0.000483s : 0.07% type_inference : 0.457103s : 64.08% event_method : 0.000463s : 0.06% auto_monad : 0.000216s : 0.03% graph_reusing : 0.000012s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000100s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000017s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000097s : 0.01% insert-virtual-dataset : 0.000004s : 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 : 0.000009s : 0.00% optimize.rewriter_before_opt_a : 0.000671s : 0.09% optimize.opt_a.expand_dump_flag : 0.000015s : 0.00% optimize.opt_a.switch_simplify : 0.000306s : 0.04% optimize.opt_a.loop_unroll : 0.000144s : 0.02% optimize.opt_a.a_1 : 0.105460s : 14.78% optimize.opt_a.with_stream_mark : 0.000123s : 0.02% optimize.opt_a.recompute_prepare : 0.000059s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000413s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000036s : 0.01% optimize.opt_a.shard : 0.000009s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000021s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.00% optimize.opt_a.merge_send_recv : 0.000044s : 0.01% optimize.opt_a.auto_parallel : 0.000041s : 0.01% optimize.opt_a.parallel : 0.000045s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000018s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000063s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000044s : 0.01% optimize.opt_a.virtual_dataset : 0.000030s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000030s : 0.00% optimize.opt_a.virtual_output : 0.000029s : 0.00% optimize.opt_a.merge_forward : 0.000023s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000043s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000074s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000007s : 0.00% optimize.opt_a.before_grad : 0.000057s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.126141s : 17.68% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000009s : 0.00% optimize.opt_a.after_resolve : 0.000131s : 0.02% optimize.opt_a.a_after_grad : 0.000129s : 0.02% optimize.opt_a.renormalize : 0.016742s : 2.35% optimize.opt_a.add_forward_monad_depend : 0.000036s : 0.00% optimize.opt_a.auto_monad_grad : 0.000016s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000096s : 0.01% optimize.opt_a.cse : 0.000560s : 0.08% optimize.opt_a.a_3 : 0.000570s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000007s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000021s : 0.00% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000791s : 0.11% optimize.opt_b.b_1 : 0.000078s : 0.01% optimize.opt_b.b_2 : 0.000006s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000019s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000017s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000036s : 0.01% optimize.loop_unroll : 0.000486s : 0.07% optimize.opt_after_cconv.c_1 : 0.000017s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000018s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000016s : 0.00% optimize.tuple_transform.d_1 : 0.000025s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000004s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000041s : 0.01% optimize.cse_after_recomputation.cse : 0.000010s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000005s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000003s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000003s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000009s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000011s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000005s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000008s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000018s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000533s : 0.07% validate : 0.000038s : 0.01% Time group info: ------[substitution.] 0.102682 164 0.00% : 0.000002s : 1: substitution.elim_not_effective 0.01% : 0.000014s : 12: substitution.float_depend_g_call 0.00% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.00% : 0.000001s : 1: substitution.fold_const_symbol 0.00% : 0.000004s : 1: substitution.graph_param_transform 0.00% : 0.000004s : 2: substitution.incorporate_call 0.00% : 0.000003s : 2: substitution.incorporate_call_switch 1.02% : 0.001046s : 23: substitution.inline 0.03% : 0.000028s : 2: substitution.inline_without_move 0.01% : 0.000013s : 13: substitution.j_node_and_user_rematch 98.64% : 0.101282s : 7: substitution.minmaximum_grad 0.01% : 0.000012s : 12: substitution.partial_eliminate 0.01% : 0.000012s : 13: substitution.remove_not_recompute_node 0.04% : 0.000040s : 9: substitution.replace_applicator 0.01% : 0.000009s : 11: substitution.replace_old_param 0.01% : 0.000011s : 2: substitution.reshape_eliminate 0.00% : 0.000004s : 1: substitution.set_cell_output_no_recompute 0.02% : 0.000018s : 3: substitution.switch_simplify 0.03% : 0.000033s : 7: substitution.tuple_list_convert_item_index_to_positive 0.01% : 0.000012s : 7: substitution.tuple_list_get_item_const_eliminator 0.02% : 0.000020s : 7: substitution.tuple_list_get_item_depend_reorder 0.09% : 0.000089s : 19: substitution.tuple_list_get_item_eliminator 0.02% : 0.000020s : 7: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.456943 2 98.74% : 0.451207s : 1: type_inference.infer 1.26% : 0.005736s : 1: type_inference.specialize ------[replace.] 0.000605 36 61.64% : 0.000373s : 23: replace.inline 12.66% : 0.000077s : 3: replace.switch_simplify 25.69% : 0.000155s : 10: replace.tuple_list_get_item_eliminator ------[match.] 0.001084 36 94.89% : 0.001028s : 23: match.inline 1.41% : 0.000015s : 3: match.switch_simplify 3.70% : 0.000040s : 10: match.tuple_list_get_item_eliminator ------[predicate.] 0.000705 4182 1.13% : 0.000008s : 55: predicate.accumulaten_eliminater 0.16% : 0.000001s : 1: predicate.ad_related_special_op_eliminate 0.38% : 0.000003s : 19: predicate.addn_check_dump 1.34% : 0.000009s : 55: predicate.addn_zero_filter 1.34% : 0.000009s : 55: predicate.adjust_all_reduce_mul_add 2.60% : 0.000018s : 74: predicate.arithmetic_simplify 1.11% : 0.000008s : 55: predicate.cast_eliminate 0.94% : 0.000007s : 44: predicate.check_bprop_eliminate 0.46% : 0.000003s : 19: predicate.compare_switch_simplify 0.02% : 0.000000s : 1: predicate.const_output_eliminate 0.44% : 0.000003s : 19: predicate.depend_value_elim 1.15% : 0.000008s : 55: predicate.dict_get_item_const_eliminator 1.30% : 0.000009s : 55: predicate.dict_get_item_eliminator 1.28% : 0.000009s : 55: predicate.dict_set_item_eliminator 0.21% : 0.000001s : 2: predicate.dumpgradient_eliminate 0.05% : 0.000000s : 1: predicate.elim_not_effective 0.07% : 0.000000s : 1: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000008s : 56: predicate.environ_add_const_eliminate 0.99% : 0.000007s : 56: predicate.environ_get_add_eliminate 1.01% : 0.000007s : 56: predicate.environ_get_depend_swap 1.49% : 0.000011s : 75: predicate.environ_get_eliminate 1.04% : 0.000007s : 56: predicate.environ_get_set_eliminate 1.87% : 0.000013s : 88: predicate.exchange_switch_depend_value 2.77% : 0.000020s : 88: predicate.float_depend_g_call 0.37% : 0.000003s : 19: predicate.float_environ_get_switch 0.44% : 0.000003s : 20: predicate.float_tuple_getitem_switch 0.01% : 0.000000s : 1: predicate.fold_const_symbol 0.57% : 0.000004s : 19: predicate.get_grad_eliminate 0.02% : 0.000000s : 1: predicate.graph_param_transform 0.39% : 0.000003s : 19: predicate.incorporate_call 0.34% : 0.000002s : 19: predicate.incorporate_call_switch 5.56% : 0.000039s : 183: predicate.inline 1.55% : 0.000011s : 49: predicate.inline_without_move 0.21% : 0.000001s : 19: predicate.j_node_and_user_rematch 0.69% : 0.000005s : 19: predicate.less_batch_normalization 1.36% : 0.000010s : 67: predicate.list_to_tuple_eliminator_ 2.60% : 0.000018s : 122: predicate.load_eliminater 0.18% : 0.000001s : 1: predicate.loop_unroll_after_grad 3.28% : 0.000023s : 138: predicate.loop_unroll_before_grad 1.24% : 0.000009s : 57: predicate.make_slice_get_slice_eliminator 0.42% : 0.000003s : 19: predicate.merge_addn 0.88% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.90% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.02% : 0.000007s : 55: predicate.minmaximum_grad 0.27% : 0.000002s : 1: predicate.mutable_eliminate 0.07% : 0.000000s : 1: predicate.opt_reshape 0.10% : 0.000001s : 1: predicate.parallel_virtual_node 3.42% : 0.000024s : 88: predicate.partial_defer_inline 1.44% : 0.000010s : 66: predicate.partial_eliminate 1.04% : 0.000007s : 55: predicate.print_const_string_wrapper 0.42% : 0.000003s : 19: predicate.reduce_all_const_elim 1.45% : 0.000010s : 55: predicate.reduce_eliminate 2.41% : 0.000017s : 122: predicate.redundant_stop_gradient_eliminater 0.26% : 0.000002s : 19: predicate.remove_not_recompute_node 1.82% : 0.000013s : 109: predicate.replace_applicator 0.72% : 0.000005s : 49: predicate.replace_old_param 0.03% : 0.000000s : 1: predicate.reset_defer_inline 1.11% : 0.000008s : 55: predicate.reshape_eliminate 0.89% : 0.000006s : 44: predicate.row_tensor_add_zeros_like 0.10% : 0.000001s : 1: predicate.row_tensor_eliminate 1.58% : 0.000011s : 44: predicate.same_eliminate 0.32% : 0.000002s : 19: predicate.set_cell_output_no_recompute 0.56% : 0.000004s : 19: predicate.shard_identity_eliminate 0.13% : 0.000001s : 2: predicate.special_op_eliminate 0.54% : 0.000004s : 19: predicate.specialize_transform 1.26% : 0.000009s : 44: predicate.split_environ_get_set_with_tuple_value 1.36% : 0.000010s : 49: predicate.stack_unstack_eliminate 0.03% : 0.000000s : 1: predicate.switch_call_monad_eliminater 2.01% : 0.000014s : 88: predicate.switch_defer_inline 2.82% : 0.000020s : 132: predicate.switch_layer_defer_inline 6.84% : 0.000048s : 252: predicate.switch_simplify 1.24% : 0.000009s : 55: predicate.tile_eliminate 1.19% : 0.000008s : 55: predicate.transpose_eliminate 1.29% : 0.000009s : 57: predicate.tuple_list_convert_item_index_to_positive 1.34% : 0.000009s : 57: predicate.tuple_list_get_item_const_eliminator 1.29% : 0.000009s : 57: predicate.tuple_list_get_item_depend_reorder 2.79% : 0.000020s : 86: predicate.tuple_list_get_item_eliminator 1.58% : 0.000011s : 57: predicate.tuple_list_get_set_item_eliminator 2.06% : 0.000014s : 76: predicate.tuple_list_set_item_eliminator 1.44% : 0.000010s : 67: predicate.tuple_to_list_eliminator_ 2.21% : 0.000016s : 122: predicate.updatestate_pure_node_eliminater 3.01% : 0.000021s : 141: predicate.updatestate_useless_node_eliminater 0.13% : 0.000001s : 1: predicate.value_based_eliminate 0.51% : 0.000004s : 19: predicate.virtual_dataset_eliminate 0.57% : 0.000004s : 19: predicate.virtual_output_eliminate 0.03% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.07% : 0.000001s : 1: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005553 54 59.47% : 0.003302s : 27: func_graph_cloner_run.FuncGraphClonerGraph 40.53% : 0.002251s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.103687 233 0.00% : 0.000004s : 1: ForceFp32Comm 0.40% : 0.004439s : 1: add_attr 0.40% : 0.004424s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000046s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000227s : 1: auto_monad 0.00% : 0.000022s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.000522s : 1: bootstrap 0.00% : 0.000040s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000016s : 1: control_data_broadcast_order 0.00% : 0.000004s : 1: convert_after_rewriter 0.00% : 0.000026s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000009s : 1: environ_conv 0.04% : 0.000484s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.04% : 0.000496s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.07% : 0.000805s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000011s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000015s : 1: opt.transform.mutable_eliminate 9.73% : 0.107352s : 117: opt.transform.opt_a 0.00% : 0.000016s : 1: opt.transform.opt_after_cconv 0.00% : 0.000017s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000054s : 28: opt.transform.opt_b 0.00% : 0.000027s : 2: opt.transform.opt_trans_graph 0.00% : 0.000029s : 4: opt.transform.symbol_engine_opt 22.91% : 0.252841s : 1: opt_a 0.01% : 0.000094s : 1: opt_after_cconv 0.05% : 0.000543s : 1: opt_after_jit_grad 0.01% : 0.000163s : 1: opt_b 23.18% : 0.255788s : 1: optimize 0.00% : 0.000021s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000027s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000007s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000103s : 1: pre_auto_parallel 0.00% : 0.000013s : 1: py_interpret_to_execute 0.00% : 0.000010s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000019s : 1: remove_dup_value 1.13% : 0.012454s : 2: renormalize.infer 0.39% : 0.004253s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000025s : 1: rewriter_after_opt_a 0.07% : 0.000725s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000008s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000075s : 1: symbol_engine_optimizer 0.01% : 0.000056s : 1: tuple_transform 41.42% : 0.457134s : 1: type_inference TotalTime = 0.591751, [21] [bootstrap]: 0.00051608 [type_inference]: 0.321456 [event_method]: 0.00022061 [auto_monad]: 0.00010274 [graph_reusing]: 8e-06 [inline]: 3.54002e-06 [add_attr]: 0.0045625, [1] [add_attr_with_inline]: 0.00454781, [1] [Cycle 1]: 0.00010876, [2] [tag_attr]: 4.989e-05 [meta_addattr_fg_expand]: 8.22e-06 [parallel-infer-symbol]: 3.92002e-06 [pre_auto_parallel]: 6.197e-05 [insert-virtual-dataset]: 3.48e-06 [parallel-infer-symbol-second]: 9.00007e-07 [dataset_repeat_opt]: 2.20002e-06 [pipeline_split]: 1.74998e-06 [optimize]: 0.263627, [53] [py_interpret_to_execute]: 9.74999e-06 [rewriter_before_opt_a]: 0.00037458 [opt_a]: 0.260003, [2] [Cycle 1]: 0.259189, [45] [expand_dump_flag]: 4.77e-06 [switch_simplify]: 6.679e-05 [loop_unroll]: 4.684e-05 [a_1]: 0.000924 [with_stream_mark]: 2.53e-05 [recompute_prepare]: 9.51998e-06 [updatestate_depend_eliminate]: 5.25999e-06 [updatestate_assign_eliminate]: 3.9e-06 [updatestate_loads_eliminate]: 3.20998e-06 [parameter_eliminate]: 2.94001e-06 [a_2]: 8.051e-05 [accelerated_algorithm]: 7.4e-06 [shard]: 1.94e-06 [meta_shard_fg_expand]: 2.59999e-06 [shard_inline]: 6.39001e-06 [merge_send_recv]: 9.39e-06 [auto_parallel]: 9.44998e-06 [parallel]: 2.211e-05 [flash_sp]: 1.039e-05 [merge_comm]: 4.18001e-06 [allreduce_fusion]: 4.02998e-06 [matmul_add_comm_reduction]: 1.081e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 1.003e-05 [virtual_dataset]: 7.4e-06 [get_grad_eliminate_]: 6.23e-06 [virtual_output]: 7.58999e-06 [merge_forward]: 5.21998e-06 [cell_reuse_recompute_pass]: 2.09e-06 [offload_activation]: 1.169e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.845e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 1.255e-05 [set_forward_comm_id_for_comm_node_pass]: 4.42e-06 [meta_fg_expand]: 3.43e-06 [flash_sp_send_recv_attached]: 3.63999e-06 [receive_attached]: 2.56e-06 [after_resolve]: 1.28e-05 [a_after_grad]: 1.083e-05 [renormalize]: 0.25724 [add_forward_monad_depend]: 1.753e-05 [auto_monad_grad]: 3.35e-06 [auto_monad_eliminator]: 3.297e-05 [cse]: 5.075e-05 [a_3]: 0.00013155 [Cycle 2]: 0.00077296, [45] [expand_dump_flag]: 3.65e-06 [switch_simplify]: 9.07999e-06 [loop_unroll]: 7.31001e-06 [a_1]: 0.00011888 [with_stream_mark]: 2.774e-05 [recompute_prepare]: 8.18001e-06 [updatestate_depend_eliminate]: 5.20001e-06 [updatestate_assign_eliminate]: 3.48e-06 [updatestate_loads_eliminate]: 3.9e-06 [parameter_eliminate]: 3.23e-06 [a_2]: 7.286e-05 [accelerated_algorithm]: 7.06999e-06 [shard]: 3.23998e-06 [meta_shard_fg_expand]: 2.48e-06 [shard_inline]: 5.46e-06 [merge_send_recv]: 1.054e-05 [auto_parallel]: 1.158e-05 [parallel]: 1.2e-05 [flash_sp]: 5.22e-06 [merge_comm]: 3.78999e-06 [allreduce_fusion]: 3.48e-06 [matmul_add_comm_reduction]: 1.094e-05 [allreduce_slice_to_reducescatter]: 1.19e-06 [virtual_shard_identity]: 9.06002e-06 [virtual_dataset]: 6.22001e-06 [get_grad_eliminate_]: 6.06e-06 [virtual_output]: 5.96e-06 [merge_forward]: 4.74e-06 [cell_reuse_recompute_pass]: 3.48e-06 [offload_activation]: 1.249e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.398e-05 [merge_recompute_call_nodes]: 2.43e-06 [before_grad]: 1.217e-05 [set_forward_comm_id_for_comm_node_pass]: 3.81001e-06 [meta_fg_expand]: 3.2e-06 [flash_sp_send_recv_attached]: 2.16998e-06 [receive_attached]: 3.31001e-06 [after_resolve]: 1.259e-05 [a_after_grad]: 9.99001e-06 [renormalize]: 1.10012e-07 [add_forward_monad_depend]: 2.73003e-06 [auto_monad_grad]: 2.34999e-06 [auto_monad_eliminator]: 1.121e-05 [cse]: 3.231e-05 [a_3]: 3.816e-05 [py_interpret_to_execute_after_opt_a]: 1.356e-05 [slice_cell_reuse_recomputed_activation]: 2.11e-06 [rewriter_after_opt_a]: 2.945e-05 [convert_after_rewriter]: 2.26e-06 [order_py_execute_after_rewriter]: 1.28002e-06 [mutable_eliminate]: 0.00094164 [opt_b]: 0.00027171, [1] [Cycle 1]: 0.0002609, [7] [b_1]: 0.00013691 [b_2]: 7.92e-06 [updatestate_depend_eliminate]: 1.513e-05 [updatestate_assign_eliminate]: 3.3e-06 [updatestate_loads_eliminate]: 3.56999e-06 [renormalize]: 1.11002e-06 [cse]: 4.758e-05 [optimize_parallel_all_gather_comm]: 2.598e-05 [overlap_param_gather]: 1.92999e-06 [cconv]: 4.317e-05 [loop_unroll]: 0.00075248 [opt_after_cconv]: 0.00015148, [1] [Cycle 1]: 0.00014195, [7] [c_1]: 3.167e-05 [parameter_eliminate]: 7.55e-06 [updatestate_depend_eliminate]: 1.156e-05 [updatestate_assign_eliminate]: 3.60998e-06 [updatestate_loads_eliminate]: 2.94999e-06 [cse]: 4.325e-05 [renormalize]: 7.30011e-07 [remove_dup_value]: 5.912e-05 [tuple_transform]: 9.337e-05, [1] [Cycle 1]: 8.795e-05, [4] [d_1]: 5.445e-05 [none_parameter_eliminate]: 2.97002e-06 [renormalize]: 2.29978e-07 [switch_simplify]: 7.65e-06 [partial_unused_args_eliminate]: 2.49001e-06 [add_recomputation]: 6.5e-05 [cse_after_recomputation]: 3.176e-05, [1] [Cycle 1]: 2.668e-05, [1] [cse]: 1.931e-05 [environ_conv]: 9.09e-06 [swap_dp_allreduce_reducescatter]: 7.42002e-06 [bias_add_comm_swap]: 3.38e-06 [label_micro_interleaved_index]: 7.80998e-06 [label_fine_grained_interleaved_index]: 3.06001e-06 [merge_cast_opt]: 2.42001e-06 [slice_recompute_activation]: 2.58e-06 [micro_interleaved_order_control]: 2.73e-06 [assign_add_opt]: 2.19999e-06 [ForceFp32Comm]: 1.34e-06 [remove_cast_before_assign_add]: 1.40999e-06 [full_micro_interleaved_order_control]: 2.82002e-06 [reorder_send_recv_between_fp_bp]: 2.89999e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.64e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 1.60999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.17001e-06 [control_data_broadcast_order]: 2.072e-05 [grouped_pairwise_exchange_alltoall]: 2.06e-06 [offloading_packed_experts]: 5.22999e-06 [overlap_recompute_and_grad_model_parallel]: 5.77001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.72999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.48002e-06 [overlap_recompute_comm]: 2.53998e-06 [overlap_grad_ring_attention]: 4.87e-06 [overlap_grad_flash_sp]: 2.629e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.29999e-06 [split_layernorm_comm]: 2.09999e-06 [handle_group_info]: 1.24e-06 [symbol_engine_optimizer]: 0.00019513, [1] [Cycle 1]: 0.00018745, [6] [build]: 4.72998e-06 [elim_shapecalc]: 1.819e-05 [elim_not_effective]: 1.756e-05 [opt_reshape]: 1.087e-05 [fold_const_symbol]: 1.27e-05 [renormalize]: 6.50005e-07 [detach_backward]: 2.97002e-06 [pipeline_parallel_scheduler]: 2.43e-06 [auto_monad_reorder]: 2.96e-05 [get_jit_bprop_graph]: 1.84998e-06 [rewriter_after_jit_bprop_graph]: 5.31002e-06 [opt_after_jit_grad]: 0.00085008 [validate]: 5.895e-05 Sums bootstrap : 0.000516s : 0.09% type_inference : 0.321456s : 54.88% event_method : 0.000221s : 0.04% auto_monad : 0.000103s : 0.02% graph_reusing : 0.000008s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000050s : 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 : 0.000062s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000010s : 0.00% optimize.rewriter_before_opt_a : 0.000375s : 0.06% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000076s : 0.01% optimize.opt_a.loop_unroll : 0.000054s : 0.01% optimize.opt_a.a_1 : 0.001043s : 0.18% optimize.opt_a.with_stream_mark : 0.000053s : 0.01% optimize.opt_a.recompute_prepare : 0.000018s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000153s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000014s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000012s : 0.00% optimize.opt_a.merge_send_recv : 0.000020s : 0.00% optimize.opt_a.auto_parallel : 0.000021s : 0.00% optimize.opt_a.parallel : 0.000034s : 0.01% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000008s : 0.00% optimize.opt_a.allreduce_fusion : 0.000008s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000022s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000019s : 0.00% optimize.opt_a.virtual_dataset : 0.000014s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000012s : 0.00% optimize.opt_a.virtual_output : 0.000014s : 0.00% optimize.opt_a.merge_forward : 0.000010s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000024s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000042s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000025s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000008s : 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 : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000025s : 0.00% optimize.opt_a.a_after_grad : 0.000021s : 0.00% optimize.opt_a.renormalize : 0.257240s : 43.92% optimize.opt_a.add_forward_monad_depend : 0.000020s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000044s : 0.01% optimize.opt_a.cse : 0.000083s : 0.01% optimize.opt_a.a_3 : 0.000170s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000014s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000029s : 0.01% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000942s : 0.16% optimize.opt_b.b_1 : 0.000137s : 0.02% optimize.opt_b.b_2 : 0.000008s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000003s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000048s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.01% optimize.loop_unroll : 0.000752s : 0.13% optimize.opt_after_cconv.c_1 : 0.000032s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.cse : 0.000043s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000059s : 0.01% optimize.tuple_transform.d_1 : 0.000054s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000008s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000065s : 0.01% optimize.cse_after_recomputation.cse : 0.000019s : 0.00% optimize.environ_conv : 0.000009s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000026s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000005s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000018s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000013s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000030s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000850s : 0.15% validate : 0.000059s : 0.01% Time group info: ------[substitution.] 0.000302 28 0.76% : 0.000002s : 2: substitution.elim_not_effective 0.66% : 0.000002s : 2: substitution.fold_const_symbol 2.19% : 0.000007s : 3: substitution.graph_param_transform 84.34% : 0.000255s : 7: substitution.inline 1.74% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.23% : 0.000007s : 4: substitution.remove_not_recompute_node 2.01% : 0.000006s : 2: substitution.replace_old_param 6.07% : 0.000018s : 4: substitution.tuple_list_get_item_eliminator ------[type_inference.] 0.321344 2 99.12% : 0.318505s : 1: type_inference.infer 0.88% : 0.002840s : 1: type_inference.specialize ------[replace.] 0.000122 11 66.27% : 0.000081s : 7: replace.inline 33.73% : 0.000041s : 4: replace.tuple_list_get_item_eliminator ------[match.] 0.000267 11 93.86% : 0.000251s : 7: match.inline 6.14% : 0.000016s : 4: match.tuple_list_get_item_eliminator ------[predicate.] 0.000247 1291 1.03% : 0.000003s : 15: predicate.accumulaten_eliminater 1.22% : 0.000003s : 3: predicate.ad_related_special_op_eliminate 0.51% : 0.000001s : 6: predicate.addn_check_dump 1.15% : 0.000003s : 15: predicate.addn_zero_filter 0.93% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 1.96% : 0.000005s : 21: predicate.arithmetic_simplify 1.00% : 0.000002s : 15: predicate.cast_eliminate 0.45% : 0.000001s : 6: predicate.check_bprop_eliminate 0.36% : 0.000001s : 6: predicate.compare_switch_simplify 0.12% : 0.000000s : 3: predicate.const_output_eliminate 0.38% : 0.000001s : 6: predicate.depend_value_elim 0.99% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.99% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.93% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.22% : 0.000003s : 6: predicate.dumpgradient_eliminate 0.22% : 0.000001s : 3: predicate.elim_not_effective 0.36% : 0.000001s : 3: predicate.elim_shapecalc_of_broadcastargs 1.32% : 0.000003s : 18: predicate.environ_add_const_eliminate 1.02% : 0.000003s : 18: predicate.environ_get_add_eliminate 1.43% : 0.000004s : 18: predicate.environ_get_depend_swap 1.52% : 0.000004s : 24: predicate.environ_get_eliminate 1.18% : 0.000003s : 18: predicate.environ_get_set_eliminate 1.49% : 0.000004s : 26: predicate.exchange_switch_depend_value 2.37% : 0.000006s : 26: predicate.float_depend_g_call 0.36% : 0.000001s : 6: predicate.float_environ_get_switch 0.57% : 0.000001s : 9: predicate.float_tuple_getitem_switch 0.10% : 0.000000s : 3: predicate.fold_const_symbol 0.51% : 0.000001s : 6: predicate.get_grad_eliminate 0.22% : 0.000001s : 3: predicate.graph_param_transform 0.36% : 0.000001s : 6: predicate.incorporate_call 0.33% : 0.000001s : 6: predicate.incorporate_call_switch 5.72% : 0.000014s : 59: predicate.inline 0.62% : 0.000002s : 6: predicate.inline_without_move 0.24% : 0.000001s : 6: predicate.j_node_and_user_rematch 0.94% : 0.000002s : 6: predicate.less_batch_normalization 1.74% : 0.000004s : 25: predicate.list_to_tuple_eliminator_ 2.34% : 0.000006s : 40: predicate.load_eliminater 2.12% : 0.000005s : 3: predicate.loop_unroll_after_grad 2.85% : 0.000007s : 49: predicate.loop_unroll_before_grad 1.76% : 0.000004s : 21: predicate.make_slice_get_slice_eliminator 0.49% : 0.000001s : 6: predicate.merge_addn 0.47% : 0.000001s : 6: predicate.micro_step_allgather_replace 0.44% : 0.000001s : 6: predicate.mini_step_allgather_replace 0.84% : 0.000002s : 15: predicate.minmaximum_grad 1.76% : 0.000004s : 3: predicate.mutable_eliminate 0.39% : 0.000001s : 3: predicate.opt_reshape 0.43% : 0.000001s : 3: predicate.parallel_virtual_node 1.81% : 0.000004s : 26: predicate.partial_defer_inline 1.30% : 0.000003s : 22: predicate.partial_eliminate 0.90% : 0.000002s : 15: predicate.print_const_string_wrapper 0.42% : 0.000001s : 6: predicate.reduce_all_const_elim 1.40% : 0.000003s : 15: predicate.reduce_eliminate 2.88% : 0.000007s : 40: predicate.redundant_stop_gradient_eliminater 0.43% : 0.000001s : 6: predicate.remove_not_recompute_node 1.48% : 0.000004s : 25: predicate.replace_applicator 0.41% : 0.000001s : 6: predicate.replace_old_param 0.34% : 0.000001s : 3: predicate.reset_defer_inline 1.05% : 0.000003s : 15: predicate.reshape_eliminate 0.36% : 0.000001s : 6: predicate.row_tensor_add_zeros_like 0.47% : 0.000001s : 3: predicate.row_tensor_eliminate 0.90% : 0.000002s : 6: predicate.same_eliminate 0.30% : 0.000001s : 6: predicate.set_cell_output_no_recompute 0.88% : 0.000002s : 6: predicate.shard_identity_eliminate 0.58% : 0.000001s : 6: predicate.special_op_eliminate 0.47% : 0.000001s : 6: predicate.specialize_transform 0.81% : 0.000002s : 6: predicate.split_environ_get_set_with_tuple_value 0.61% : 0.000002s : 6: predicate.stack_unstack_eliminate 0.39% : 0.000001s : 3: predicate.switch_call_monad_eliminater 1.56% : 0.000004s : 26: predicate.switch_defer_inline 2.00% : 0.000005s : 32: predicate.switch_layer_defer_inline 5.64% : 0.000014s : 84: predicate.switch_simplify 0.97% : 0.000002s : 15: predicate.tile_eliminate 1.12% : 0.000003s : 15: predicate.transpose_eliminate 1.91% : 0.000005s : 21: predicate.tuple_list_convert_item_index_to_positive 1.47% : 0.000004s : 21: predicate.tuple_list_get_item_const_eliminator 1.26% : 0.000003s : 21: predicate.tuple_list_get_item_depend_reorder 3.60% : 0.000009s : 31: predicate.tuple_list_get_item_eliminator 1.59% : 0.000004s : 21: predicate.tuple_list_get_set_item_eliminator 2.13% : 0.000005s : 27: predicate.tuple_list_set_item_eliminator 1.57% : 0.000004s : 25: predicate.tuple_to_list_eliminator_ 2.28% : 0.000006s : 40: predicate.updatestate_pure_node_eliminater 2.88% : 0.000007s : 46: predicate.updatestate_useless_node_eliminater 0.40% : 0.000001s : 3: predicate.value_based_eliminate 0.66% : 0.000002s : 6: predicate.virtual_dataset_eliminate 0.58% : 0.000001s : 6: predicate.virtual_output_eliminate 0.17% : 0.000000s : 3: predicate.virtual_view_grad_eliminate 0.30% : 0.000001s : 3: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001621 18 49.15% : 0.000797s : 9: func_graph_cloner_run.FuncGraphClonerGraph 50.85% : 0.000824s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.118765 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.41% : 0.004570s : 1: add_attr 0.41% : 0.004553s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000071s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000112s : 1: auto_monad 0.00% : 0.000036s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.000548s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000026s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.00% : 0.000035s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000015s : 1: environ_conv 0.02% : 0.000240s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 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% : 0.000012s : 1: label_micro_interleaved_index 0.07% : 0.000774s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.09% : 0.000967s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000032s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000034s : 1: opt.transform.mutable_eliminate 0.14% : 0.001542s : 78: opt.transform.opt_a 0.00% : 0.000030s : 1: opt.transform.opt_after_cconv 0.00% : 0.000037s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000107s : 28: opt.transform.opt_b 0.01% : 0.000059s : 2: opt.transform.opt_trans_graph 0.00% : 0.000054s : 4: opt.transform.symbol_engine_opt 23.24% : 0.260008s : 1: opt_a 0.01% : 0.000158s : 1: opt_after_cconv 0.08% : 0.000874s : 1: opt_after_jit_grad 0.02% : 0.000276s : 1: opt_b 23.56% : 0.263635s : 1: optimize 0.00% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000031s : 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 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 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% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000067s : 1: pre_auto_parallel 0.00% : 0.000013s : 1: py_interpret_to_execute 0.00% : 0.000018s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000006s : 1: remove_cast_before_assign_add 0.01% : 0.000065s : 1: remove_dup_value 0.09% : 0.001025s : 1: renormalize.infer 22.90% : 0.256196s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000034s : 1: rewriter_after_opt_a 0.03% : 0.000383s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000198s : 1: symbol_engine_optimizer 0.01% : 0.000096s : 1: tuple_transform 28.74% : 0.321492s : 1: type_inference TotalTime = 0.598783, [21] [bootstrap]: 0.00050031 [type_inference]: 0.367108 [event_method]: 0.00044832 [auto_monad]: 0.00021045 [graph_reusing]: 1.246e-05 [inline]: 2.98e-06 [add_attr]: 0.00436944, [1] [add_attr_with_inline]: 0.00435496, [1] [Cycle 1]: 0.00015807, [2] [tag_attr]: 9.304e-05 [meta_addattr_fg_expand]: 1.739e-05 [parallel-infer-symbol]: 4.54002e-06 [pre_auto_parallel]: 8.858e-05 [insert-virtual-dataset]: 3.31999e-06 [parallel-infer-symbol-second]: 7.99977e-07 [dataset_repeat_opt]: 2.55002e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.225113, [53] [py_interpret_to_execute]: 5.54e-06 [rewriter_before_opt_a]: 0.00063539 [opt_a]: 0.221685, [3] [Cycle 1]: 0.216601, [45] [expand_dump_flag]: 6.04001e-06 [switch_simplify]: 0.00021305 [loop_unroll]: 8.974e-05 [a_1]: 0.0908292 [with_stream_mark]: 5.064e-05 [recompute_prepare]: 3.91e-05 [updatestate_depend_eliminate]: 1.233e-05 [updatestate_assign_eliminate]: 8.34002e-06 [updatestate_loads_eliminate]: 7.12997e-06 [parameter_eliminate]: 4.28001e-06 [a_2]: 0.00023349 [accelerated_algorithm]: 1.828e-05 [shard]: 2.78e-06 [meta_shard_fg_expand]: 1.26e-05 [shard_inline]: 1.602e-05 [merge_send_recv]: 2.419e-05 [auto_parallel]: 1.872e-05 [parallel]: 2.437e-05 [flash_sp]: 1.51e-05 [merge_comm]: 9.93002e-06 [allreduce_fusion]: 9.06002e-06 [matmul_add_comm_reduction]: 3.892e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 2.238e-05 [virtual_dataset]: 1.62e-05 [get_grad_eliminate_]: 1.501e-05 [virtual_output]: 1.44e-05 [merge_forward]: 1.175e-05 [cell_reuse_recompute_pass]: 1.36998e-06 [offload_activation]: 2.079e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.679e-05 [merge_recompute_call_nodes]: 1.94999e-06 [before_grad]: 3.073e-05 [set_forward_comm_id_for_comm_node_pass]: 1.282e-05 [meta_fg_expand]: 0.00266361 [flash_sp_send_recv_attached]: 6.01e-06 [receive_attached]: 3.19001e-06 [after_resolve]: 9.996e-05 [a_after_grad]: 0.00010603 [renormalize]: 0.120391 [add_forward_monad_depend]: 2.243e-05 [auto_monad_grad]: 1.082e-05 [auto_monad_eliminator]: 7.692e-05 [cse]: 0.00050384 [a_3]: 0.00036309 [Cycle 2]: 0.00436475, [45] [expand_dump_flag]: 4.35e-06 [switch_simplify]: 5.15e-05 [loop_unroll]: 4.277e-05 [a_1]: 0.0015612 [with_stream_mark]: 3.446e-05 [recompute_prepare]: 1.248e-05 [updatestate_depend_eliminate]: 4.50001e-06 [updatestate_assign_eliminate]: 2.98e-06 [updatestate_loads_eliminate]: 2.91e-06 [parameter_eliminate]: 2.91e-06 [a_2]: 6.577e-05 [accelerated_algorithm]: 5.81e-06 [shard]: 2.13002e-06 [meta_shard_fg_expand]: 3.22002e-06 [shard_inline]: 6.26e-06 [merge_send_recv]: 1.09e-05 [auto_parallel]: 1.091e-05 [parallel]: 1.078e-05 [flash_sp]: 5.46e-06 [merge_comm]: 3.28e-06 [allreduce_fusion]: 2.99001e-06 [matmul_add_comm_reduction]: 1.111e-05 [allreduce_slice_to_reducescatter]: 1.12999e-06 [virtual_shard_identity]: 9.05001e-06 [virtual_dataset]: 5.82999e-06 [get_grad_eliminate_]: 5.52999e-06 [virtual_output]: 6.63e-06 [merge_forward]: 3.95e-06 [cell_reuse_recompute_pass]: 1.81e-06 [offload_activation]: 1.103e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.665e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 9.91e-06 [set_forward_comm_id_for_comm_node_pass]: 3.38e-06 [meta_fg_expand]: 0.0004223 [flash_sp_send_recv_attached]: 2.59999e-06 [receive_attached]: 2.53e-06 [after_resolve]: 2.465e-05 [a_after_grad]: 1.01e-05 [renormalize]: 0.00154026 [add_forward_monad_depend]: 8.62998e-06 [auto_monad_grad]: 2.82002e-06 [auto_monad_eliminator]: 1.868e-05 [cse]: 3.399e-05 [a_3]: 5.06e-05 [Cycle 3]: 0.0006942, [45] [expand_dump_flag]: 3.01001e-06 [switch_simplify]: 8.55001e-06 [loop_unroll]: 5.23002e-06 [a_1]: 0.00010817 [with_stream_mark]: 1.583e-05 [recompute_prepare]: 5.30001e-06 [updatestate_depend_eliminate]: 3.34001e-06 [updatestate_assign_eliminate]: 2.88e-06 [updatestate_loads_eliminate]: 3.04999e-06 [parameter_eliminate]: 2.49001e-06 [a_2]: 5.866e-05 [accelerated_algorithm]: 5.09998e-06 [shard]: 2.31e-06 [meta_shard_fg_expand]: 2.74001e-06 [shard_inline]: 8.50999e-06 [merge_send_recv]: 1.088e-05 [auto_parallel]: 9.59e-06 [parallel]: 9.54e-06 [flash_sp]: 1.74e-06 [merge_comm]: 2.89999e-06 [allreduce_fusion]: 2.97002e-06 [matmul_add_comm_reduction]: 8.82e-06 [allreduce_slice_to_reducescatter]: 6.09987e-07 [virtual_shard_identity]: 7.91001e-06 [virtual_dataset]: 5.77999e-06 [get_grad_eliminate_]: 5.64998e-06 [virtual_output]: 5.14e-06 [merge_forward]: 4.09997e-06 [cell_reuse_recompute_pass]: 2.47001e-06 [offload_activation]: 1.038e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.646e-05 [merge_recompute_call_nodes]: 1.35001e-06 [before_grad]: 1.032e-05 [set_forward_comm_id_for_comm_node_pass]: 3.15998e-06 [meta_fg_expand]: 2.84999e-06 [flash_sp_send_recv_attached]: 1.76003e-06 [receive_attached]: 1.82001e-06 [after_resolve]: 1.001e-05 [a_after_grad]: 8.40999e-06 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.36e-06 [auto_monad_grad]: 1.18001e-06 [auto_monad_eliminator]: 7.36999e-06 [cse]: 1.942e-05 [a_3]: 3.159e-05 [py_interpret_to_execute_after_opt_a]: 7.63999e-06 [slice_cell_reuse_recomputed_activation]: 2.85002e-06 [rewriter_after_opt_a]: 2.228e-05 [convert_after_rewriter]: 1.92001e-06 [order_py_execute_after_rewriter]: 1.18001e-06 [mutable_eliminate]: 0.00091439 [opt_b]: 0.00044968, [2] [Cycle 1]: 0.00033086, [7] [b_1]: 0.00024449 [b_2]: 6.93e-06 [updatestate_depend_eliminate]: 8.08001e-06 [updatestate_assign_eliminate]: 2.71999e-06 [updatestate_loads_eliminate]: 2.02999e-06 [renormalize]: 8.39995e-07 [cse]: 2.421e-05 [Cycle 2]: 0.00010525, [7] [b_1]: 5.704e-05 [b_2]: 3.91001e-06 [updatestate_depend_eliminate]: 2.16e-06 [updatestate_assign_eliminate]: 1.51998e-06 [updatestate_loads_eliminate]: 1.34e-06 [renormalize]: 8.9989e-08 [cse]: 8.07e-06 [optimize_parallel_all_gather_comm]: 1.657e-05 [overlap_param_gather]: 2.32999e-06 [cconv]: 3.523e-05 [loop_unroll]: 0.00059266 [opt_after_cconv]: 9.622e-05, [1] [Cycle 1]: 8.768e-05, [7] [c_1]: 1.816e-05 [parameter_eliminate]: 6.16e-06 [updatestate_depend_eliminate]: 6.33e-06 [updatestate_assign_eliminate]: 1.88002e-06 [updatestate_loads_eliminate]: 1.67999e-06 [cse]: 1.931e-05 [renormalize]: 6.90023e-07 [remove_dup_value]: 1.599e-05 [tuple_transform]: 6.482e-05, [1] [Cycle 1]: 5.83e-05, [4] [d_1]: 2.782e-05 [none_parameter_eliminate]: 2.22001e-06 [renormalize]: 3.80009e-07 [switch_simplify]: 5.82001e-06 [partial_unused_args_eliminate]: 2.37999e-06 [add_recomputation]: 4.716e-05 [cse_after_recomputation]: 2.27e-05, [1] [Cycle 1]: 1.743e-05, [1] [cse]: 1.148e-05 [environ_conv]: 6.28e-06 [swap_dp_allreduce_reducescatter]: 5.57001e-06 [bias_add_comm_swap]: 3.73001e-06 [label_micro_interleaved_index]: 5.42999e-06 [label_fine_grained_interleaved_index]: 3.19001e-06 [merge_cast_opt]: 1.46998e-06 [slice_recompute_activation]: 2.32999e-06 [micro_interleaved_order_control]: 2.81999e-06 [assign_add_opt]: 1.55999e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.38002e-06 [full_micro_interleaved_order_control]: 2.89001e-06 [reorder_send_recv_between_fp_bp]: 3.35e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.32e-06 [interleave_split_concat_branches]: 1.52001e-06 [interleave_parallel_branches]: 1.25999e-06 [overlap_opt_shard_in_pipeline]: 1.77999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.36998e-06 [control_data_broadcast_order]: 1.314e-05 [grouped_pairwise_exchange_alltoall]: 1.71e-06 [offloading_packed_experts]: 3.21999e-06 [overlap_recompute_and_grad_model_parallel]: 4.26001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49e-06 [overlap_recompute_comm]: 2.31998e-06 [overlap_grad_ring_attention]: 3.78001e-06 [overlap_grad_flash_sp]: 2.072e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.37999e-06 [split_layernorm_comm]: 2.25002e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 7.696e-05, [1] [Cycle 1]: 7.014e-05, [6] [build]: 3.83001e-06 [elim_shapecalc]: 8.75001e-06 [elim_not_effective]: 1.212e-05 [opt_reshape]: 5.77999e-06 [fold_const_symbol]: 8.59002e-06 [renormalize]: 2.20025e-07 [detach_backward]: 3.33e-06 [pipeline_parallel_scheduler]: 2.612e-05 [auto_monad_reorder]: 1.846e-05 [get_jit_bprop_graph]: 2.34999e-06 [rewriter_after_jit_bprop_graph]: 6.13998e-06 [opt_after_jit_grad]: 0.00060417 [validate]: 4.505e-05 Sums bootstrap : 0.000500s : 0.08% type_inference : 0.367108s : 61.94% event_method : 0.000448s : 0.08% auto_monad : 0.000210s : 0.04% graph_reusing : 0.000012s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000093s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000017s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000089s : 0.01% 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 : 0.000006s : 0.00% optimize.rewriter_before_opt_a : 0.000635s : 0.11% optimize.opt_a.expand_dump_flag : 0.000013s : 0.00% optimize.opt_a.switch_simplify : 0.000273s : 0.05% optimize.opt_a.loop_unroll : 0.000138s : 0.02% optimize.opt_a.a_1 : 0.092499s : 15.61% optimize.opt_a.with_stream_mark : 0.000101s : 0.02% optimize.opt_a.recompute_prepare : 0.000057s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_a.parameter_eliminate : 0.000010s : 0.00% optimize.opt_a.a_2 : 0.000358s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.00% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000019s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.01% optimize.opt_a.merge_send_recv : 0.000046s : 0.01% optimize.opt_a.auto_parallel : 0.000039s : 0.01% optimize.opt_a.parallel : 0.000045s : 0.01% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000016s : 0.00% optimize.opt_a.allreduce_fusion : 0.000015s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000059s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.01% optimize.opt_a.virtual_dataset : 0.000028s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.00% optimize.opt_a.virtual_output : 0.000026s : 0.00% optimize.opt_a.merge_forward : 0.000020s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000042s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000070s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000051s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.00% optimize.opt_a.meta_fg_expand : 0.003089s : 0.52% optimize.opt_a.flash_sp_send_recv_attached : 0.000010s : 0.00% optimize.opt_a.receive_attached : 0.000008s : 0.00% optimize.opt_a.after_resolve : 0.000135s : 0.02% optimize.opt_a.a_after_grad : 0.000125s : 0.02% optimize.opt_a.renormalize : 0.121932s : 20.57% optimize.opt_a.add_forward_monad_depend : 0.000033s : 0.01% optimize.opt_a.auto_monad_grad : 0.000015s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000103s : 0.02% optimize.opt_a.cse : 0.000557s : 0.09% optimize.opt_a.a_3 : 0.000445s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000008s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000022s : 0.00% optimize.convert_after_rewriter : 0.000002s : 0.00% optimize.order_py_execute_after_rewriter : 0.000001s : 0.00% optimize.mutable_eliminate : 0.000914s : 0.15% optimize.opt_b.b_1 : 0.000302s : 0.05% 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 : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000003s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000032s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000017s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.01% optimize.loop_unroll : 0.000593s : 0.10% optimize.opt_after_cconv.c_1 : 0.000018s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000002s : 0.00% optimize.opt_after_cconv.cse : 0.000019s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000016s : 0.00% optimize.tuple_transform.d_1 : 0.000028s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000006s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000047s : 0.01% optimize.cse_after_recomputation.cse : 0.000011s : 0.00% optimize.environ_conv : 0.000006s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000006s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000013s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000003s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000004s : 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 : 0.000004s : 0.00% optimize.overlap_grad_flash_sp : 0.000021s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000004s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000009s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000012s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000006s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000009s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000026s : 0.00% auto_monad_reorder : 0.000018s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000604s : 0.10% validate : 0.000045s : 0.01% Time group info: ------[substitution.] 0.001526 163 0.15% : 0.000002s : 1: substitution.elim_not_effective 0.78% : 0.000012s : 12: substitution.float_depend_g_call 0.32% : 0.000005s : 2: substitution.float_tuple_getitem_switch 0.10% : 0.000002s : 1: substitution.fold_const_symbol 0.37% : 0.000006s : 1: substitution.graph_param_transform 0.25% : 0.000004s : 2: substitution.incorporate_call 0.15% : 0.000002s : 2: substitution.incorporate_call_switch 73.37% : 0.001120s : 23: substitution.inline 1.84% : 0.000028s : 2: substitution.inline_without_move 0.71% : 0.000011s : 12: substitution.j_node_and_user_rematch 0.80% : 0.000012s : 7: substitution.minmaximum_grad 0.79% : 0.000012s : 12: substitution.partial_eliminate 0.85% : 0.000013s : 12: substitution.remove_not_recompute_node 2.47% : 0.000038s : 9: substitution.replace_applicator 1.01% : 0.000015s : 13: substitution.replace_old_param 0.31% : 0.000005s : 1: substitution.set_cell_output_no_recompute 0.99% : 0.000015s : 3: substitution.switch_simplify 1.88% : 0.000029s : 7: substitution.tuple_list_convert_item_index_to_positive 0.78% : 0.000012s : 7: substitution.tuple_list_get_item_const_eliminator 1.15% : 0.000018s : 7: substitution.tuple_list_get_item_depend_reorder 5.80% : 0.000089s : 19: substitution.tuple_list_get_item_eliminator 1.11% : 0.000017s : 7: substitution.tuple_list_get_set_item_eliminator 4.00% : 0.000061s : 1: substitution.zero_like_fill_zero ------[type_inference.] 0.366949 2 98.33% : 0.360825s : 1: type_inference.infer 1.67% : 0.006124s : 1: type_inference.specialize ------[replace.] 0.000597 37 54.12% : 0.000323s : 23: replace.inline 10.79% : 0.000064s : 3: replace.switch_simplify 28.18% : 0.000168s : 10: replace.tuple_list_get_item_eliminator 6.90% : 0.000041s : 1: replace.zero_like_fill_zero ------[match.] 0.001221 37 90.20% : 0.001101s : 23: match.inline 0.94% : 0.000011s : 3: match.switch_simplify 3.94% : 0.000048s : 10: match.tuple_list_get_item_eliminator 4.92% : 0.000060s : 1: match.zero_like_fill_zero ------[predicate.] 0.000701 4087 1.19% : 0.000008s : 53: predicate.accumulaten_eliminater 0.24% : 0.000002s : 1: predicate.ad_related_special_op_eliminate 0.43% : 0.000003s : 17: predicate.addn_check_dump 1.08% : 0.000008s : 53: predicate.addn_zero_filter 1.30% : 0.000009s : 53: predicate.adjust_all_reduce_mul_add 2.08% : 0.000015s : 70: predicate.arithmetic_simplify 1.31% : 0.000009s : 53: predicate.cast_eliminate 0.95% : 0.000007s : 44: predicate.check_bprop_eliminate 0.34% : 0.000002s : 17: predicate.compare_switch_simplify 0.04% : 0.000000s : 3: predicate.const_output_eliminate 0.37% : 0.000003s : 17: predicate.depend_value_elim 1.11% : 0.000008s : 53: predicate.dict_get_item_const_eliminator 1.12% : 0.000008s : 53: predicate.dict_get_item_eliminator 1.53% : 0.000011s : 53: predicate.dict_set_item_eliminator 0.30% : 0.000002s : 4: predicate.dumpgradient_eliminate 0.03% : 0.000000s : 1: predicate.elim_not_effective 0.08% : 0.000001s : 1: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000008s : 56: predicate.environ_add_const_eliminate 1.18% : 0.000008s : 56: predicate.environ_get_add_eliminate 1.06% : 0.000007s : 56: predicate.environ_get_depend_swap 1.42% : 0.000010s : 73: predicate.environ_get_eliminate 1.01% : 0.000007s : 56: predicate.environ_get_set_eliminate 1.71% : 0.000012s : 86: predicate.exchange_switch_depend_value 3.18% : 0.000022s : 86: predicate.float_depend_g_call 0.36% : 0.000003s : 17: predicate.float_environ_get_switch 0.43% : 0.000003s : 20: predicate.float_tuple_getitem_switch 0.01% : 0.000000s : 1: predicate.fold_const_symbol 0.46% : 0.000003s : 17: predicate.get_grad_eliminate 0.06% : 0.000000s : 1: predicate.graph_param_transform 0.36% : 0.000003s : 17: predicate.incorporate_call 0.32% : 0.000002s : 17: predicate.incorporate_call_switch 5.45% : 0.000038s : 177: predicate.inline 1.35% : 0.000009s : 47: predicate.inline_without_move 0.21% : 0.000001s : 17: predicate.j_node_and_user_rematch 0.58% : 0.000004s : 17: predicate.less_batch_normalization 1.55% : 0.000011s : 67: predicate.list_to_tuple_eliminator_ 2.30% : 0.000016s : 120: predicate.load_eliminater 0.25% : 0.000002s : 1: predicate.loop_unroll_after_grad 2.92% : 0.000020s : 136: predicate.loop_unroll_before_grad 1.26% : 0.000009s : 57: predicate.make_slice_get_slice_eliminator 0.36% : 0.000003s : 17: predicate.merge_addn 0.87% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.94% : 0.000007s : 44: predicate.mini_step_allgather_replace 0.97% : 0.000007s : 53: predicate.minmaximum_grad 0.39% : 0.000003s : 3: predicate.mutable_eliminate 0.09% : 0.000001s : 1: predicate.opt_reshape 0.12% : 0.000001s : 3: predicate.parallel_virtual_node 3.49% : 0.000024s : 86: predicate.partial_defer_inline 1.41% : 0.000010s : 64: predicate.partial_eliminate 0.98% : 0.000007s : 53: predicate.print_const_string_wrapper 0.37% : 0.000003s : 17: predicate.reduce_all_const_elim 1.20% : 0.000008s : 53: predicate.reduce_eliminate 2.26% : 0.000016s : 120: predicate.redundant_stop_gradient_eliminater 0.30% : 0.000002s : 17: predicate.remove_not_recompute_node 1.60% : 0.000011s : 107: predicate.replace_applicator 0.78% : 0.000005s : 47: predicate.replace_old_param 0.09% : 0.000001s : 3: predicate.reset_defer_inline 1.10% : 0.000008s : 53: predicate.reshape_eliminate 0.97% : 0.000007s : 44: predicate.row_tensor_add_zeros_like 0.18% : 0.000001s : 2: predicate.row_tensor_eliminate 1.37% : 0.000010s : 44: predicate.same_eliminate 0.30% : 0.000002s : 17: predicate.set_cell_output_no_recompute 0.55% : 0.000004s : 17: predicate.shard_identity_eliminate 0.22% : 0.000002s : 4: predicate.special_op_eliminate 0.43% : 0.000003s : 17: predicate.specialize_transform 1.33% : 0.000009s : 44: predicate.split_environ_get_set_with_tuple_value 1.24% : 0.000009s : 47: predicate.stack_unstack_eliminate 0.03% : 0.000000s : 1: predicate.switch_call_monad_eliminater 1.91% : 0.000013s : 86: predicate.switch_defer_inline 2.98% : 0.000021s : 130: predicate.switch_layer_defer_inline 7.58% : 0.000053s : 246: predicate.switch_simplify 1.17% : 0.000008s : 53: predicate.tile_eliminate 1.45% : 0.000010s : 53: predicate.transpose_eliminate 1.64% : 0.000011s : 57: predicate.tuple_list_convert_item_index_to_positive 1.83% : 0.000013s : 57: predicate.tuple_list_get_item_const_eliminator 1.08% : 0.000008s : 57: predicate.tuple_list_get_item_depend_reorder 3.50% : 0.000025s : 84: predicate.tuple_list_get_item_eliminator 1.41% : 0.000010s : 57: predicate.tuple_list_get_set_item_eliminator 1.91% : 0.000013s : 74: predicate.tuple_list_set_item_eliminator 1.47% : 0.000010s : 67: predicate.tuple_to_list_eliminator_ 2.12% : 0.000015s : 120: predicate.updatestate_pure_node_eliminater 2.62% : 0.000018s : 137: predicate.updatestate_useless_node_eliminater 0.17% : 0.000001s : 3: predicate.value_based_eliminate 0.43% : 0.000003s : 17: predicate.virtual_dataset_eliminate 0.40% : 0.000003s : 17: predicate.virtual_output_eliminate 0.03% : 0.000000s : 1: predicate.virtual_view_grad_eliminate 0.28% : 0.000002s : 5: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005761 54 62.83% : 0.003620s : 27: func_graph_cloner_run.FuncGraphClonerGraph 37.17% : 0.002141s : 27: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.044492 288 0.00% : 0.000004s : 1: ForceFp32Comm 0.42% : 0.004376s : 1: add_attr 0.42% : 0.004361s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000052s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000221s : 1: auto_monad 0.00% : 0.000024s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.000530s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000017s : 1: control_data_broadcast_order 0.00% : 0.000005s : 1: convert_after_rewriter 0.00% : 0.000026s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000010s : 1: environ_conv 0.05% : 0.000470s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000017s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 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 0.06% : 0.000604s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.09% : 0.000930s : 1: mutable_eliminate 0.00% : 0.000007s : 1: offloading_packed_experts 0.00% : 0.000014s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000021s : 1: opt.transform.mutable_eliminate 9.01% : 0.094150s : 117: opt.transform.opt_a 0.00% : 0.000017s : 1: opt.transform.opt_after_cconv 0.00% : 0.000021s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000237s : 83: opt.transform.opt_b 0.00% : 0.000030s : 2: opt.transform.opt_trans_graph 0.00% : 0.000031s : 4: opt.transform.symbol_engine_opt 21.22% : 0.221690s : 1: opt_a 0.01% : 0.000100s : 1: opt_after_cconv 0.06% : 0.000617s : 1: opt_after_jit_grad 0.04% : 0.000454s : 1: opt_b 21.55% : 0.225120s : 1: optimize 0.00% : 0.000021s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000004s : 1: order_py_execute_after_rewriter 0.00% : 0.000024s : 1: overlap_grad_flash_sp 0.00% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000007s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000007s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000033s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000094s : 1: pre_auto_parallel 0.00% : 0.000010s : 1: py_interpret_to_execute 0.00% : 0.000011s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000019s : 1: remove_dup_value 1.23% : 0.012869s : 2: renormalize.infer 10.44% : 0.109031s : 2: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000025s : 1: rewriter_after_opt_a 0.06% : 0.000647s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000009s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000080s : 1: symbol_engine_optimizer 0.01% : 0.000068s : 1: tuple_transform 35.15% : 0.367137s : 1: type_inference . [hook] pytest_runtest_teardown:test_repeat_interleave_forward_backward_int[None-KBK] tests/st/mint/test_repeat_interleave.py::test_repeat_interleave_forward_backward_int[None-KBK],max_mem:4.0M =============================== warnings summary =============================== ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 6 passed, 25 warnings in 124.60s (0:02:04) ==================