Move unittest test_optimizer_in_control_flow from CI multi_cards. (#27185)

python/paddle/fluid/tests/unittests/CMakeLists.txt

@@ -562,7 +562,7 @@ set_tests_properties(test_parallel_executor_test_while_train test_parallel_execu
         test_parallel_executor_feed_persistable_var
         test_buffer_shared_memory_reuse_pass_and_fuse_optimization_op_pass
         test_data_norm_op test_imperative_using_non_zero_gpu test_fuse_bn_act_pass
-        test_optimizer_in_control_flow test_dataloader_keep_order
+        test_dataloader_keep_order
         test_dataloader_unkeep_order
         test_parallel_executor_fetch_isolated_var
         test_parallel_executor_inference_feed_partial_data

python/paddle/fluid/tests/unittests/test_optimizer_in_control_flow.py

@@ -261,7 +261,13 @@ class TestMultiOptimizersMultiCardsError(unittest.TestCase):
             exe.run(startup_program)
 
             np.random.seed(SEED)
+
+            # NOTE(liym27):
+            # This test needs to run in multi cards to test NotImplementedError.
+            # Here, move this test from RUN_TYPE=DIST in tests/unittests/CMakeList.txt,
+            # to use multi cards ** only on CPU ** not GPU to reduce CI time.
             os.environ['CPU_NUM'] = str(2)
+
             pe_exe = fluid.ParallelExecutor(
                 use_cuda=use_cuda,
                 main_program=main_program,