add strategy and parallelExe doc (#13862)

test=release/1.0.0

paddle/fluid/pybind/pybind.cc

@@ -596,26 +596,58 @@ All parameter, weight, gradient are variables in Paddle.
 
   // -- python binds for parallel executor.
   py::class_<ParallelExecutor> pe(m, "ParallelExecutor");
-  py::class_<ExecutionStrategy> exec_strategy(pe, "ExecutionStrategy");
+  py::class_<ExecutionStrategy> exec_strategy(pe, "ExecutionStrategy", R"DOC(
+    ExecutionStrategy allows the user to more preciously control how to run
+    the program in ParallelExecutor by setting the property.
+
+    Examples:
+        .. code-block:: python
+
+          exec_strategy = fluid.ExecutionStrategy()
+          exec_strategy.num_threads = 4
+
+          train_exe = fluid.ParallelExecutor(use_cuda=True,
+                                             loss_name=loss.name,
+                                             exec_strategy=exec_strategy)
+
+          train_loss, = train_exe.run([loss.name], feed=feed_dict)
+
+        )DOC");
+
   exec_strategy.def(py::init())
       .def_property(
           "num_threads",
           [](const ExecutionStrategy &self) { return self.num_threads_; },
           [](ExecutionStrategy &self, size_t num_threads) {
             self.num_threads_ = num_threads;
-          })
+          },
+          R"DOC(The type is INT, num_threads represents the size of thread pool that
+            used to run the operators of the current program in ParallelExecutor.
+            If :math:`num\_threads=1`, all the operators will execute one by one,
+            but the order maybe difference between iterations.
+            If it is not set, it will be set in ParallelExecutor according to the
+            device type and device count, for GPU, :math:`num\_threads=device\_count*4`, for CPU,
+            :math:`num\_threads=CPU\_NUM*4`, the explanation of:math:`CPU\_NUM` is in ParallelExecutor.
+            if it is not set, ParallelExecutor will get the cpu count by calling
+            `multiprocessing.cpu_count()`. Default 0.)DOC")
       .def_property(
           "use_cuda",
           [](const ExecutionStrategy &self) { return self.use_cuda_; },
           [](ExecutionStrategy &self, bool use_cuda) {
             self.use_cuda_ = use_cuda;
-          })
+          })  // FIXME(chengduo): Doesn't add doc for 'use_cuda', use_cuda may
+      // make user confuse, because ParallelExecutor has a parameter named
+      // 'use_cuda' too, in current implementation, ParallelExecutor's
+      // 'use_cuda' will rewrite ExecutionStrategy's 'use_cuda'.
       .def_property(
           "allow_op_delay",
           [](const ExecutionStrategy &self) { return self.allow_op_delay_; },
           [](ExecutionStrategy &self, bool allow_op_delay) {
             self.allow_op_delay_ = allow_op_delay;
-          })
+          },
+          R"DOC(The type is BOOL, allow_op_delay represents whether to delay the
+                communication operators to run, it may make the execution faster.
+                Note that in some models, allow_op_delay may cause program hang. Default False.)DOC")
       .def_property(
           "num_iteration_per_drop_scope",
           [](const ExecutionStrategy &self) {
@@ -623,7 +655,19 @@ All parameter, weight, gradient are variables in Paddle.
           },
           [](ExecutionStrategy &self, size_t num_iteration_per_drop_scope) {
             self.num_iteration_per_drop_scope_ = num_iteration_per_drop_scope;
-          });
+          },
+          R"DOC(The type is INT, num_iteration_per_drop_scope indicates how
+                many iterations to clean up the temp variables which
+                is generated during execution. It may make the execution faster,
+                because the temp variable's shape maybe the same between two iterations. Default 100.
+
+                NOTES:
+                    1. If you fetch data when calling the 'run', the ParallelExecutor
+                       will clean up the temp variables at the end of the current iteration.
+                    2. In some NLP model, it may cause the GPU memory is insufficient,
+                       in this case, you should reduce `num_iteration_per_drop_scope`.
+              )DOC");
+
   exec_strategy.def_property(
       "use_experimental_executor",
       [](const ExecutionStrategy &self) {
@@ -634,7 +678,22 @@ All parameter, weight, gradient are variables in Paddle.
                                   : ExecutionStrategy::kDefault;
       });
 
-  py::class_<BuildStrategy> build_strategy(pe, "BuildStrategy");
+  py::class_<BuildStrategy> build_strategy(pe, "BuildStrategy", R"DOC(
+    BuildStrategy allows the user to more preciously control how to
+    build the SSA Graph in ParallelExecutor by setting the property.
+
+    Examples:
+        .. code-block:: python
+
+          build_strategy = fluid.BuildStrategy()
+          build_strategy.reduce_strategy = fluid.BuildStrategy.ReduceStrategy.Reduce
+
+          train_exe = fluid.ParallelExecutor(use_cuda=True,
+                                             loss_name=loss.name,
+                                             build_strategy=build_strategy)
+
+          train_loss, = train_exe.run([loss.name], feed=feed_dict)
+)DOC");
 
   py::enum_<BuildStrategy::ReduceStrategy>(build_strategy, "ReduceStrategy")
       .value("Reduce", BuildStrategy::ReduceStrategy::kReduce)
@@ -652,31 +711,51 @@ All parameter, weight, gradient are variables in Paddle.
           [](const BuildStrategy &self) { return self.reduce_; },
           [](BuildStrategy &self, BuildStrategy::ReduceStrategy strategy) {
             self.reduce_ = strategy;
-          })
+          },
+          R"DOC(The type is STR, there are two reduce strategies in ParallelExecutor,
+                  'AllReduce' and 'Reduce'. If you want that all the parameters'
+                  optimization are done on all devices independently, you should choose 'AllReduce';
+                  if you choose 'Reduce', all the parameters' optimization will be evenly distributed
+                  to different devices, and then broadcast the optimized parameter to other devices.
+                  In some models, `Reduce` is faster. Default 'AllReduce'. )DOC")
       .def_property(
           "gradient_scale_strategy",
           [](const BuildStrategy &self) { return self.gradient_scale_; },
           [](BuildStrategy &self,
              BuildStrategy::GradientScaleStrategy strategy) {
             self.gradient_scale_ = strategy;
-          })
+          },
+          R"DOC(The type is STR, there are three ways of defining :math:`loss@grad` in
+                   ParallelExecutor, 'CoeffNumDevice', 'One' and 'Customized'. By default,
+                   ParallelExecutor sets the :math:`loss@grad` according to the number of devices.
+                   If you want to customize :math:`loss@grad`, you can choose 'Customized'.
+                   Default 'CoeffNumDevice'.)DOC")
       .def_property(
           "debug_graphviz_path",
           [](const BuildStrategy &self) { return self.debug_graphviz_path_; },
           [](BuildStrategy &self, const std::string &path) {
             self.debug_graphviz_path_ = path;
-          })
+          },
+          R"DOC(The type is STR, debug_graphviz_path indicate the path that
+                    writing the SSA Graph to file in the form of graphviz, you.
+                    It is useful for debugging. Default "")DOC")
       .def_property(
           "enable_data_balance",
           [](const BuildStrategy &self) { return self.enable_data_balance_; },
-          [](BuildStrategy &self, bool b) { self.enable_data_balance_ = b; })
-      .def_property("fuse_elewise_add_act_ops",
+          [](BuildStrategy &self, bool b) {
+            self.enable_data_balance_ = b;
+          })  // FIXME(chengudo): enable_data_balance seems not important
+      .def_property(
+          "fuse_elewise_add_act_ops",
           [](const BuildStrategy &self) {
             return self.fuse_elewise_add_act_ops_;
           },
           [](BuildStrategy &self, bool b) {
             self.fuse_elewise_add_act_ops_ = b;
-                    });
+          },
+          R"DOC(The type is BOOL, fuse_elewise_add_act_ops indicate whether
+                     to fuse elementwise_add_op and activation_op,
+                     it may make the execution faster. Default False)DOC");
 
   pe.def(py::init<const std::vector<platform::Place> &,
                   const std::unordered_set<std::string> &,

python/paddle/fluid/parallel_executor.py

@@ -31,15 +31,32 @@ BuildStrategy = core.ParallelExecutor.BuildStrategy
 
 class ParallelExecutor(object):
     """
-    ParallelExecutor can run program in parallel.
+    ParallelExecutor is designed for data parallelism, which focuses on distributing
+    the data across different nodes and every node operates on the data in parallel.
+    If you use ParallelExecutor to run the current program on GPU, the node means GPU
+    device, and ParallelExecutor will get the available GPU device automatically on
+    the current machine. If you use ParallelExecutor to run the current program on CPU,
+    the node means the CPU device, and you can specify the CPU device number by adding
+    'CPU_NUM' environment variable, for example 'CPU_NUM=4', if the environment variable
+    is not found, ParallelExecutor will call `multiprocessing.cpu_count` to get the number
+    of CPUs in the system.
 
     Args:
         use_cuda (bool): Whether to use CUDA or not.
         loss_name (str): The loss name must set in training. Default None.
         main_program (Program): The program that need to run, if not provided,
             then default_main_program will be used. Default None.
-        share_vars_from(ParallelExecutor): If provied, it will share variables
+        share_vars_from(ParallelExecutor): If provide, it will share variables
             from the specified ParallelExecutor. Default None.
+        exec_strategy(ExecutionStrategy): exec_strategy is used to control how to run
+            the program in ParallelExecutor, for example how many threads are used to
+            execute the program, how many iterations to clean up the temp variables
+            which is generated during execution. For more information, please refer
+            to fluid.ExecutionStrategy. Default None.
+        build_strategy(BuildStrategy): build_strategy is used to control how to
+            build the SSA Graph in ParallelExecutor by setting the property,
+            for example reduce_strategy, gradient_scale_strategy. For more information,
+            please refer to fluid.BuildStrategy. Default None.
         num_trainers(int): If greater than 1, NCCL will be initialized with
             multiple rank of nodes, each node should have same number of GPUs.
             Distributed training will be enabled then. Default 1.