Rename template config and move transformations to code snippets (ope…

…nvinotoolkit#16133)

* Rename template config and move transformations to code snippets

* Fixed documentation

* Rename template config

docs/Extensibility_UG/graph_rewrite_pass.md

@@ -3,7 +3,7 @@
 `ov::pass::GraphRewrite` serves for running multiple matcher passes on `ov::Model` in a single graph traversal.
 Example:
 
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:graph_rewrite
+@snippet template_pattern_transformation.cpp matcher_pass:graph_rewrite
 
 In addition, GraphRewrite handles nodes that were registered by MatcherPasses during their execution. This nodes will be added to the beginning of the sequence with nodes for pattern matching.
 

docs/Extensibility_UG/matcher_pass.md

@@ -3,9 +3,9 @@
 `ov::pass::MatcherPass` is used for pattern-based transformations.
 
 Template for MatcherPass transformation class
-@snippet src/transformations/template_pattern_transformation.hpp graph_rewrite:template_transformation_hpp
+@snippet template_pattern_transformation.hpp graph_rewrite:template_transformation_hpp
 
-@snippet src/transformations/template_pattern_transformation.cpp graph_rewrite:template_transformation_cpp
+@snippet template_pattern_transformation.cpp graph_rewrite:template_transformation_cpp
 
 To use `ov::pass::MatcherPass`, you need to complete these steps:
 1. Create a pattern
@@ -43,7 +43,7 @@ That means that matcher passes registered in `ov::pass::GraphRewrite` will be ap
 
 The example below shows how single MatcherPass can fuse sequence of operations using the `register_new_node` method.
 
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:relu_fusion
+@snippet template_pattern_transformation.cpp matcher_pass:relu_fusion
 
 > **NOTE**: If you register multiple nodes, please add them in topological order. We do not topologically sort these nodes as it is a time-consuming operation.
 
@@ -60,11 +60,11 @@ register_matcher(m, callback);
 
 MatcherPass has multiple ways to be executed:
 * Run on a single node - it can be useful if you want to run MatcherPass inside another transformation.
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:run_on_node
+@snippet template_pattern_transformation.cpp matcher_pass:run_on_node
 * Run on `ov::Model` using GraphRewrite - this approach gives ability to run MatcherPass on whole `ov::Model`. Moreover, multiple MatcherPass transformation can be registered in a single GraphRewite to be executed in a single graph traversal.
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:graph_rewrite
+@snippet template_pattern_transformation.cpp matcher_pass:graph_rewrite
 * Run on `ov::Model` using `ov::pass::Manager` - this approach helps you to register MatcherPass for execution on `ov::Model` as another transformation types.
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:manager
+@snippet template_pattern_transformation.cpp matcher_pass:manager
 
 ## Pattern Matching <a name="pattern_matching"></a>
 

docs/Extensibility_UG/model_pass.md

@@ -4,9 +4,9 @@
 
 Template for ModelPass transformation class
 
-@snippet src/transformations/template_model_transformation.hpp model_pass:template_transformation_hpp
+@snippet template_model_transformation.hpp model_pass:template_transformation_hpp
 
-@snippet src/transformations/template_model_transformation.cpp model_pass:template_transformation_cpp
+@snippet template_model_transformation.cpp model_pass:template_transformation_cpp
 
 Using `ov::pass::ModelPass`, you need to override the `run_on_model` method where you will write the transformation code.
 Return value is `true` if the original model has changed during transformation (new operation was added, or operations replacement was made, or node attributes were changed); otherwise, it is `false`.

docs/Extensibility_UG/ov_transformations.md

@@ -124,7 +124,7 @@ Manual constant folding is more preferable than `ov::pass::ConstantFolding()` be
 
 Below you can find an example of manual constant folding:
 
-@snippet src/transformations/template_pattern_transformation.cpp manual_constant_folding
+@snippet template_pattern_transformation.cpp manual_constant_folding
 
 ## Common mistakes in transformations <a name="common_mistakes"></a>
 
@@ -145,11 +145,11 @@ In addition, `ov::pass::Manager` has extended debug capabilities (find more info
 
 The example below shows basic usage of `ov::pass::Manager`
 
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:manager3
+@snippet template_pattern_transformation.cpp matcher_pass:manager3
 
 Another example shows how multiple matcher passes can be united into single GraphRewrite.
 
-@snippet src/transformations/template_pattern_transformation.cpp matcher_pass:manager2
+@snippet template_pattern_transformation.cpp matcher_pass:manager2
 
 ## How to debug transformations <a name="how-to-debug-transformations"></a>
 

docs/IE_PLUGIN_DG/Plugin.md

@@ -34,7 +34,7 @@ The provided plugin class also has several fields:
 * `_waitExecutor` - a task executor that waits for a response from a device about device tasks completion.
 * `_cfg` of type `Configuration`:
 
-@snippet template/src/template_config.hpp configuration:header
+@snippet template/src/config.hpp configuration:header
 
 As an example, a plugin configuration has three value parameters:
 

docs/snippets/CMakeLists.txt

@@ -61,6 +61,7 @@ target_include_directories(${TARGET_NAME} PRIVATE "${OpenVINO_SOURCE_DIR}/src/in
                                                   "${OpenVINO_SOURCE_DIR}/src/common/low_precision_transformations/include"
                                                   "${OpenVINO_SOURCE_DIR}/src/frontends/common/include"
                                                   "${OpenVINO_SOURCE_DIR}/src/core/template_extension/new/")
+ov_mark_target_as_cc(${TARGET_NAME})
 
 if(TARGET OpenCL::OpenCL)
     target_link_libraries(${TARGET_NAME} PRIVATE OpenCL::OpenCL)

src/plugins/template/src/transformations/template_pattern_transformation.cpp → docs/snippets/template_pattern_transformation.cpp

@@ -2,14 +2,14 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-#include "transformations/template_pattern_transformation.hpp"
+#include "template_pattern_transformation.hpp"
 
 #include "openvino/cc/pass/itt.hpp"
 #include "openvino/core/rt_info.hpp"
 #include "openvino/opsets/opset3.hpp"
 #include "openvino/pass/manager.hpp"
 #include "openvino/pass/pattern/op/wrap_type.hpp"
-#include "transformations/template_model_transformation.hpp"
+#include "template_model_transformation.hpp"
 
 // ! [graph_rewrite:template_transformation_cpp]
 // template_pattern_transformation.cpp

src/plugins/template/src/async_infer_request.cpp

@@ -4,9 +4,9 @@
 
 #include "async_infer_request.hpp"
 
+#include "itt.hpp"
 #include "openvino/runtime/iinfer_request.hpp"
 #include "sync_infer_request.hpp"
-#include "template_itt.hpp"
 
 // ! [async_infer_request:ctor]
 ov::template_plugin::AsyncInferRequest::AsyncInferRequest(

src/plugins/template/src/compiled_model.cpp

@@ -9,10 +9,10 @@
 #include "async_infer_request.hpp"
 #include "ie_ngraph_utils.hpp"
 #include "ie_plugin_config.hpp"
+#include "itt.hpp"
 #include "openvino/runtime/properties.hpp"
 #include "plugin.hpp"
 #include "template/config.hpp"
-#include "template_itt.hpp"
 #include "transformations/utils/utils.hpp"
 
 // ! [executable_network:ctor_cnnnetwork]

src/plugins/template/src/compiled_model.hpp

@@ -4,11 +4,11 @@
 
 #pragma once
 
+#include "config.hpp"
 #include "openvino/runtime/icompiled_model.hpp"
 #include "openvino/runtime/iinfer_request.hpp"
 #include "openvino/runtime/isync_infer_request.hpp"
 #include "openvino/runtime/tensor.hpp"
-#include "template_config.hpp"
 
 namespace ov {
 namespace template_plugin {

src/plugins/template/src/template_config.cpp → src/plugins/template/src/config.cpp

@@ -2,7 +2,7 @@
 // SPDX-License-Identifier: Apache-2.0
 //
 
-#include "template_config.hpp"
+#include "config.hpp"
 
 #include <cpp_interfaces/interface/ie_internal_plugin_config.hpp>
 #include <ie_plugin_config.hpp>
@@ -13,7 +13,7 @@ using namespace ov::template_plugin;
 
 Configuration::Configuration() {}
 
-Configuration::Configuration(const ConfigMap& config, const Configuration& defaultCfg, bool throwOnUnsupported) {
+Configuration::Configuration(const ov::AnyMap& config, const Configuration& defaultCfg, bool throwOnUnsupported) {
     *this = defaultCfg;
     // If plugin needs to use ov::threading::StreamsExecutor it should be able to process its configuration
     auto streamExecutorConfigKeys =

src/plugins/template/src/template_config.hpp → src/plugins/template/src/config.hpp

@@ -14,7 +14,6 @@ namespace ov {
 namespace template_plugin {
 
 // ! [configuration:header]
-using ConfigMap = std::map<std::string, ov::Any>;
 
 struct Configuration {
     Configuration();
@@ -23,7 +22,7 @@ struct Configuration {
     Configuration& operator=(const Configuration&) = default;
     Configuration& operator=(Configuration&&) = default;
 
-    explicit Configuration(const ConfigMap& config,
+    explicit Configuration(const ov::AnyMap& config,
                            const Configuration& defaultCfg = {},
                            const bool throwOnUnsupported = true);
 

src/plugins/template/src/template_itt.hpp → src/plugins/template/src/itt.hpp

@@ -4,7 +4,7 @@
 
 /**
  * @brief Defines openvino domains for tracing
- * @file template_itt.hpp
+ * @file itt.hpp
  */
 
 #pragma once

src/plugins/template/src/plugin.cpp

@@ -8,16 +8,15 @@
 
 #include "cpp_interfaces/interface/ie_iplugin_internal.hpp"
 #include "ie_plugin_config.hpp"
+#include "itt.hpp"
 #include "openvino/pass/manager.hpp"
 #include "openvino/runtime/properties.hpp"
 #include "template/config.hpp"
-#include "template_itt.hpp"
 #include "transformations/common_optimizations/common_optimizations.hpp"
 #include "transformations/common_optimizations/convert_compression_only_to_legacy.hpp"
 #include "transformations/control_flow/unroll_if.hpp"
 #include "transformations/disable_decompression_convert_constant_folding.hpp"
 #include "transformations/op_conversions/convert_reduce_to_pooling.hpp"
-#include "transformations/template_pattern_transformation.hpp"
 
 namespace {
 static constexpr const char* wait_executor_name = "TemplateWaitExecutor";
@@ -61,12 +60,10 @@ void transform_model(const std::shared_ptr<ov::Model>& model) {
     ov::pass::Manager passManager;
     // Example: register CommonOptimizations transformation from transformations library
     passManager.register_pass<ov::pass::CommonOptimizations>();
+    // Disable some transformations
     passManager.get_pass_config()->disable<ov::pass::UnrollIf>();
     // This transformation changes output name
     passManager.get_pass_config()->disable<ov::pass::ConvertReduceSumToPooling>();
-    // Example: register plugin specific transformation
-    passManager.register_pass<ov::pass::DecomposeDivideMatcher>();
-    passManager.register_pass<ov::pass::ReluReluFusionMatcher>();
     // Register any other transformations
     // ..
 

src/plugins/template/src/plugin.hpp

@@ -6,10 +6,10 @@
 
 #include "backend.hpp"
 #include "compiled_model.hpp"
+#include "config.hpp"
 #include "openvino/runtime/icompiled_model.hpp"
 #include "openvino/runtime/iplugin.hpp"
 #include "openvino/runtime/threading/itask_executor.hpp"
-#include "template_config.hpp"
 
 //! [plugin:header]
 namespace ov {

src/plugins/template/src/sync_infer_request.cpp

@@ -10,11 +10,11 @@
 #include <string>
 #include <utility>
 
+#include "itt.hpp"
 #include "ngraph/runtime/host_tensor.hpp"
 #include "openvino/core/except.hpp"
 #include "openvino/runtime/profiling_info.hpp"
 #include "plugin.hpp"
-#include "template_itt.hpp"
 
 using Time = std::chrono::high_resolution_clock;