Merge branch 'update-docs' into 'master'

Update the document with latest APIs.

See merge request !791

docs/user_guide/advanced_usage.rst

@@ -180,7 +180,6 @@ There are two common advanced use cases:
 
             // Include the headers
             #include "mace/public/mace.h"
-            #include "mace/public/mace_runtime.h"
             // If the model_graph_format is code
             #include "mace/public/${model_name}.h"
             #include "mace/public/mace_engine_factory.h"
@@ -199,7 +198,7 @@ There are two common advanced use cases:
                                          device_type,
                                          &engine);
             if (create_engine_status != MaceStatus::MACE_SUCCESS) {
-              // Report error
+              // Report error or fallback
             }
 
             // ... Same with the code in basic usage
@@ -271,13 +270,24 @@ There are two common advanced use cases:
 
             // Include the headers
             #include "mace/public/mace.h"
-            #include "mace/public/mace_runtime.h"
-
-            // 0. Set pre-compiled OpenCL binary program file paths and OpenCL parameters file path when available
-            if (device_type == DeviceType::GPU) {
-              mace::SetOpenCLBinaryPaths(path/to/opencl_binary_paths);
-              mace::SetOpenCLParameterPath(path/to/opencl_parameter_file);
-            }
+            // 0. Declare the device type (must be same with ``runtime`` in configuration file)
+            DeviceType device_type = DeviceType::GPU;
+
+            // 1. configuration
+            MaceStatus status;
+            MaceEngineConfig config(device_type);
+            std::shared_ptr<GPUContext> gpu_context;
+
+            const std::string storage_path ="path/to/storage";
+            gpu_context = GPUContextBuilder()
+                .SetStoragePath(storage_path)
+                .SetOpenCLBinaryPaths(path/to/opencl_binary_paths)
+                .SetOpenCLParameterPath(path/to/opencl_parameter_file)
+                .Finalize();
+            config.SetGPUContext(gpu_context);
+            config.SetGPUHints(
+                static_cast<GPUPerfHint>(GPUPerfHint::PERF_NORMAL),
+                static_cast<GPUPriorityHint>(GPUPriorityHint::PRIORITY_LOW));
 
             // ... Same with the code in basic usage.
 

docs/user_guide/basic_usage.rst

@@ -332,21 +332,28 @@ Please refer to \ ``mace/examples/example.cc``\ for full usage. The following li
 
     // Include the headers
     #include "mace/public/mace.h"
-    #include "mace/public/mace_runtime.h"
-
-    // 0. Set compiled OpenCL kernel cache, this is used to reduce the
-    // initialization time since the compiling is too slow. It's suggested
-    // to set this even when pre-compiled OpenCL program file is provided
-    // because the OpenCL version upgrade may also leads to kernel
-    // recompilations.
-    const std::string file_path ="path/to/opencl_cache_file";
-    std::shared_ptr<KVStorageFactory> storage_factory(
-        new FileStorageFactory(file_path));
-    ConfigKVStorageFactory(storage_factory);
-
-    // 1. Declare the device type (must be same with ``runtime`` in configuration file)
+
+    // 0. Declare the device type (must be same with ``runtime`` in configuration file)
     DeviceType device_type = DeviceType::GPU;
 
+    // 1. configuration
+    MaceStatus status;
+    MaceEngineConfig config(device_type);
+    std::shared_ptr<GPUContext> gpu_context;
+    // Set the path to store compiled OpenCL kernel binaries.
+    // please make sure your application have read/write rights of the directory.
+    // this is used to reduce the initialization time since the compiling is too slow.
+    // It's suggested to set this even when pre-compiled OpenCL program file is provided
+    // because the OpenCL version upgrade may also leads to kernel recompilations.
+    const std::string storage_path ="path/to/storage";
+    gpu_context = GPUContextBuilder()
+        .SetStoragePath(storage_path)
+        .Finalize();
+    config.SetGPUContext(gpu_context);
+    config.SetGPUHints(
+        static_cast<GPUPerfHint>(GPUPerfHint::PERF_NORMAL),
+        static_cast<GPUPriorityHint>(GPUPriorityHint::PRIORITY_LOW));
+
     // 2. Define the input and output tensor names.
     std::vector<std::string> input_names = {...};
     std::vector<std::string> output_names = {...};

mace/core/net.cc

@@ -87,9 +87,6 @@ MaceStatus SerialNet::Run(RunMetadata *run_metadata) {
       } else {
         future.wait_fn(nullptr);
       }
-#ifdef MACE_ENABLE_OPENCL
-      device_->opencl_runtime()->command_queue().finish();
-#endif
     } else if (run_metadata != nullptr) {
       call_stats.start_micros = NowMicros();
       MACE_RETURN_IF_ERROR(op->Run(nullptr));

mace/core/runtime/opencl/opencl_runtime.cc

@@ -441,6 +441,7 @@ OpenCLRuntime::OpenCLRuntime(
 }
 
 OpenCLRuntime::~OpenCLRuntime() {
+  command_queue_->finish();
   built_program_map_.clear();
   // We need to control the destruction order, which has dependencies
   command_queue_.reset();

mace/examples/cli/example.cc

@@ -120,8 +120,8 @@ DEFINE_string(device, "GPU", "CPU/GPU/HEXAGON");
 DEFINE_int32(round, 1, "round");
 DEFINE_int32(restart_round, 1, "restart round");
 DEFINE_int32(malloc_check_cycle, -1, "malloc debug check cycle, -1 to disable");
-DEFINE_int32(gpu_perf_hint, 3, "0:DEFAULT/1:LOW/2:NORMAL/3:HIGH");
-DEFINE_int32(gpu_priority_hint, 3, "0:DEFAULT/1:LOW/2:NORMAL/3:HIGH");
+DEFINE_int32(gpu_perf_hint, 2, "0:DEFAULT/1:LOW/2:NORMAL/3:HIGH");
+DEFINE_int32(gpu_priority_hint, 1, "0:DEFAULT/1:LOW/2:NORMAL/3:HIGH");
 DEFINE_int32(omp_num_threads, -1, "num of openmp threads");
 DEFINE_int32(cpu_affinity_policy, 1,
              "0:AFFINITY_NONE/1:AFFINITY_BIG_ONLY/2:AFFINITY_LITTLE_ONLY");

mace/ops/ops_test_util.h

@@ -131,10 +131,6 @@ class OpsTestNet {
     op_registry_(new OperatorRegistry()) {
   }
 
-  ~OpsTestNet() {
-    Sync();
-  }
-
   template <DeviceType D, typename T>
   void AddInputFromArray(const std::string &name,
                          const std::vector<index_t> &shape,