单测全量列表修改 (#32641)

* 单测全量列表修改

* 单测全量列表修改

* 去除挂掉的windows单测

* 去除挂掉的windows单测

tools/parallel_UT_rule.py

@@ -436,6 +436,170 @@ CPU_PARALLEL_JOB = [
     'assign_op_test',
     'allocator_facade_frac_flags_test',
     'aes_cipher_test',
+    'test_dist_sparse_tensor_load_adagrad',
+    'test_dist_mnist_fp16_allreduce',
+    'test_dist_mnist_gradient_merge',
+    'test_dist_allreduce_op',
+    'test_hdfs3',
+    'test_parallel_dygraph_se_resnext',
+    'test_dist_fleet_ps9',
+    'test_dist_fleet_infer',
+    'test_dist_se_resnext_sync',
+    'test_dist_oneps',
+    'test_dist_sparse_load_ps1',
+    'test_dist_mnist_batch_merge',
+    'test_dist_fleet_ctr',
+    'test_dist_fleet_ps10',
+    'test_parallel_dygraph_transformer',
+    'test_dist_mnist_fleetapi',
+    'test_dist_sparse_tensor_load_adam',
+    'test_dist_fleet_ps4',
+    'test_dist_fleet_heter_program',
+    'test_parallel_dygraph_sparse_embedding_over_height',
+    'test_hdfs2',
+    'test_dist_sharding_save',
+    'test_dist_fleet_ps_gpu_ctr',
+    'test_dist_mnist_backward_deps',
+    'test_dist_fleet_heter_base',
+    'test_dist_sparse_tensor_load_sgd',
+    'test_new_group',
+    'test_dist_mnist_with_program',
+    'test_dist_mnist_pg',
+    'test_dist_sparse_tensor_load_rmsprop',
+    'test_auto_checkpoint2',
+    'test_dist_sparse_tensor_load_ftrl',
+    'test_dist_fleet_ps6',
+    'test_dist_mnist_fleet_save',
+    'test_auto_checkpoint1',
+    'test_dist_fleet_a_sync_optimizer_sync',
+    'test_dist_fleet_ps3',
+    'test_dist_se_resnext_nccl',
+    'test_parallel_dygraph_mnist',
+    'test_auto_checkpoint_multiple',
+    'test_dist_fleet_a_sync_optimizer_auto_async',
+    'test_pipeline',
+    'test_dist_fleet_ps8',
+    'test_dist_fleet_sparse_embedding_ctr',
+    'test_dist_se_resnext_dgc',
+    'test_dist_fleet_ps7',
+    'test_dist_fleet_decay',
+    'test_dist_fleet_a_sync_optimizer_auto_geo',
+    'test_dist_fleet_geo',
+    'test_parallel_dygraph_dataparallel',
+    'test_hdfs1',
+    'test_dist_mnist_dgc_nccl',
+    'test_dist_fleet_ctr2',
+    'test_parallel_dygraph_unused_variables',
+    'test_dist_mnist_multi_comm',
+    'test_dist_sparse_tensor_load_momentum',
+    'test_gen_nccl_id_op',
+    'test_parallel_dygraph_sparse_embedding',
+    'test_dist_mnist_ring_allreduce',
+    'test_fleet_launch_async',
+    'test_dist_fleet_a_sync_optimizer_geo',
+    'test_parallel_dygraph_control_flow',
+    'test_auto_checkpoint',
+    'test_fleet_pipeline_meta_optimizer',
+    'test_dist_fleet_heter_ctr',
+    'test_fleet_graph_execution_meta_optimizer',
+    'test_fleet_run_random_port',
+    'test_dist_fleet_ps5',
+    'test_dist_fleet_a_sync_optimizer_auto',
+    'test_dist_lookup_sparse_table_fuse_ops',
+    'test_dist_fleet_a_sync_optimizer_async',
+    'test_c_comm_init_op',
+    'test_fleet_launch_nproc',
+    'test_dist_fleet_simnet',
+    'test_auto_checkpoint_dist_basic',
+    'test_fleet_launch_cloud',
+    'test_dist_fleet_ps',
+    'test_dist_op',
+    'test_dist_sparse_load_ps0',
+    'test_auto_checkpoint3',
+    'test_dist_fleet_ps2',
+    'test_dist_fleet_grad_clip',
+    'test_custom_concat',
+    'test_analyzer_transformer_fuse',
+    'test_analyzer_seq_pool1_fuse_statis',
+    'test_fc_lstm_fuse_pass_cc',
+    'test_layer_norm_fuse_pass',
+    'test_fc_gru_fuse_pass_cc',
+    'test_analyzer_save_model',
+    'test_fleet_ps',
+    'test_analyzer_multi_model_prediction',
+    'test_fleet_base_3',
+    'test_fleet_base_2',
+    'test_ascend_trigger',
+    'test_fleet_amp_meta_optimizer',
+    'test_fleetrun',
+    'test_check_abi',
+    'dense_table_test',
+    'test_custom_relu_op_setup',
+    'test_adaptive_pool2d_convert_global_pass',
+    'test_fleet_recompute_meta_optimizer',
+    'test_fleet_fp16_allreduce_meta_optimizer',
+    'test_post_training_quantization_lstm_model',
+    'test_fleet_metric',
+    'test_fleet_gradient_merge_meta_optimizer',
+    'test_fleet_sharding_meta_optimizer',
+    'test_listen_and_serv_op',
+    'test_analyzer_zerocopytensor_tensor',
+    'test_conv_bn_fuse_pass_cc',
+    'test_collective_optimizer',
+    'test_bf16_utils',
+    'test_analyzer_seq_pool1_compare_determine',
+    'test_avoid_twice_initialization',
+    'test_callback_early_stop',
+    'test_fleet_distributed_strategy',
+    'test_launch_coverage',
+    'test_sgd_op_bf16',
+    'test_model_cast_to_bf16',
+    'test_hybrid_parallel_topology',
+    'barrier_table_test',
+    'test_check_error',
+    'test_fleet_lamb_meta_optimizer',
+    'test_fleet_rolemaker_2',
+    'test_distributed_strategy',
+    'test_rnn_cudnn_params_packing',
+    'test_communicator_async',
+    'brpc_utils_test',
+    'test_analyzer_capi_pd_tensor',
+    'test_recv_save_op',
+    'heter_listen_and_server_test',
+    'test_analyzer_capi_ner',
+    'test_unsqueeze2_eltwise_fuse_pass',
+    'test_dgc_optimizer',
+    'test_fleet_cc',
+    'test_repeated_fc_relu_fuse_pass_cc',
+    'heter_server_test',
+    'test_static_save_load_large',
+    'graph_node_test',
+    'test_custom_conj',
+    'test_fleet_private_function',
+    'test_fake_init_op',
+    'brpc_service_sparse_sgd_test',
+    'test_tf32_cudnn',
+    'test_communicator_geo',
+    'test_dispatch_jit',
+    'test_layer_norm_fuse_pass_cc',
+    'test_fleet_dgc_meta_optimizer',
+    'test_fc_fuse_pass_cc',
+    'test_communicator_sync',
+    'test_analyzer_capi',
+    'test_fleet_lars_meta_optimizer',
+    'test_communicator_half_async',
+    'test_fleet_localsgd_meta_optimizer',
+    'test_fleet_amp_init',
+    'test_fleet_checkpoint',
+    'test_analyzer_seq_pool1_fuse_compare_zero_copy',
+    'test_lookup_table_bf16_op',
+    'test_fleet_meta_optimizer_base',
+    'table_test',
+    'test_fleet_rolemaker_new',
+    'test_fleet_graph_executor',
+    'test_multi_out_jit',
+    'test_fleet_utils',
+    'brpc_service_dense_sgd_test',
 ]
 
 # It run 4 job each time, If it failed due to Insufficient GPU memory or CUBLAS_STATUS_ALLOC_FAILED,
@@ -477,6 +641,53 @@ TETRAD_PARALLEL_JOB = [
     'tensor_test',
     'test_repeated_fc_relu_fuse_pass_cc',
     'test_mkldnn_caching',
+    'test_analyzer_seq_pool1',
+    'test_analyzer_ocr',
+    'test_analyzer_seq_conv1',
+    'test_analyzer_small_dam',
+    'test_analyzer_mobilenet_depthwise_conv',
+    'test_analyzer_pyramid_dnn',
+    'test_analyzer_text_classification',
+    'test_analyzer_rnn2',
+    'test_analyzer_transformer',
+    'test_analyzer_resnet50',
+    'test_analyzer_ner',
+    'test_analyzer_lac',
+    'test_analyzer_transformer_profile',
+    'test_analyzer_mobilenet_transpose',
+    'test_analyzer_rnn1',
+    'test_analyzer_seq_pool1_profile',
+    'test_analyzer_paddletensor_tensor',
+    'test_analyzer_bert',
+    'test_analyzer_googlenet',
+    'zero_copy_tensor_test',
+    'custom_tensor_test',
+    'test_fleet_base',
+    'test_imperative_container_layerdict',
+    'test_complex_simplenet',
+    'test_tensor_register_hook',
+    'test_set_value_op',
+    'test_tensor_type_promotion',
+    'test_view_op_reuse_allocation',
+    'test_complex_grad_accumulated',
+    'test_tensor_methods',
+    'test_sequential',
+    'test_tensor_methods',
+    'test_sequential',
+    'test_imperative_layers',
+    'test_dgc_momentum_op',
+    'test_memcpy_op',
+    'test_dgc_op',
+    'test_modelaverage',
+    'test_lookahead',
+    'test_word2vec_book',
+    'test_callback_visualdl',
+    'test_new_group_api',
+    'test_collective_split_embedding_none_divisible',
+    'test_collective_wait',
+    'test_collective_split_row_linear',
+    'test_collective_split_col_linear',
+    'test_collective_split_embedding',
 ]
 
 # It run 2 job each time, If it failed due to Insufficient GPU memory or CUBLAS_STATUS_ALLOC_FAILED,
@@ -611,7 +822,6 @@ TWO_PARALLEL_JOB = [
     'test_adam_op_multi_thread',
     'test_adamax_op',
     'test_while_loop_op',
-    'test_affine_grid_function',
     'test_transpose_flatten_concat_fuse_pass',
     'test_trace_op',
     'test_backward',
@@ -663,7 +873,6 @@ TWO_PARALLEL_JOB = [
     'test_gather_op',
     'test_partial_concat_op',
     'test_gaussian_random_op',
-    'test_paddle_imperative_double_grad',
     'test_generate_proposals_v2_op',
     'test_pad_constant_like',
     'test_grid_sample_function',
@@ -879,6 +1088,11 @@ TWO_PARALLEL_JOB = [
     'test_imperative_load_static_param',
     'test_fuse_bn_add_act_pass',
     'test_buffer_shared_memory_reuse_pass_and_fuse_optimization_op_pass',
+    'test_quantize_transpiler_v2',
+    'paddle_infer_api_test',
+    'test_analyzer_ernie',
+    'lite_resnet50_test',
+    'lite_mul_model_test',
 ]