Efficient FP32 -> FP16 conversion for convert_precision, save_model, ovc and mo (#18988)

* WIP Postpone fp16 in CompressFloatConstantsImpl

* Apply suggestions from code review

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

* WIP: Compression to FP16 in Serialize

* Prepared for efficient fp32 to fp16 conversion

* Update src/core/reference/src/runtime/reference/convert.cpp

* Called real slow reference implementations in the place where the optimized versions are supposed to be implemented

* Code style

* Fixed 0 values in the fast f64 to f16 compression

* Optimized convert_from_f32_to_f16_with_clamp

* Added optimized f32->f16 instance of change_constant_precision

* compression transformation Python test

* use tmp dir, minor corrections

* Update src/bindings/python/tests/test_transformations/test_compression.py

* Update src/bindings/python/tests/test_transformations/test_compression.py

* style fix

* define rt_info for postponed_fp16_compression

* remove redundant class

* fix temp dir for Win in test_compression.py

* update definitions in convert.hpp

* Update implementation in convert.cpp

* Update serialize.cpp

* Update compress_float_constants.cpp

* added macros for ARM/non_x86 in convert.cpp

* fix macros in convert.cpp

* change fixme placement in serialize.cpp

* style_fix

* Update src/core/reference/src/runtime/reference/convert.cpp

* style_fix

* Optimized count_out_of_f16_range

* Code style

* Revert unused

* Update src/core/src/pass/serialize.cpp

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

* Update src/core/reference/src/runtime/reference/convert.cpp

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

* use optimized convert_from_f32_to_f16_with_clamp for non postponed

* minor corrections

* Update src/common/transformations/src/transformations/common_optimizations/compress_float_constants.cpp

* Update compress_float_constants.cpp

* Switched mo and ovc to save_model instead of serialize to leverage performance improvements in fp32->fp16

* Applied minor code imporvements to address review feedback

* Minor changes in code

* Update tools/ovc/openvino/tools/ovc/main.py

* Apply suggestions from code review

* Fixed failed test in case when both usual xml compression and fp16 compression are applied simultaneously (disabled for now)

* Added description for CompressFloatConstantImpl postponed parameter

* Description of postponed parameter for CompressFloatConstants

* Reverted switching to save_model in mo as the compression can be applied not only via CLI and old code should be kept for Python path (not applicable for ovc)

* Removed remining committed test artefacts and reverted remaining changes in mo

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: dmitrygo <dmitry.gorokhov@intel.com>
Co-authored-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Co-authored-by: Pavel Esir <pavel.esir@intel.com>
Co-authored-by: Pavel Esir <pavel.esir@gmail.com>

tools/ovc/openvino/tools/ovc/main.py

@@ -13,7 +13,7 @@ from openvino.tools.ovc.convert_impl import _convert
 from openvino.tools.ovc.cli_parser import get_model_name_from_args
 
 # pylint: disable=no-name-in-module,import-error
-from openvino.runtime import serialize
+from openvino.runtime import save_model
 
 
 def main():
@@ -24,12 +24,8 @@ def main():
 
     model_path = get_model_name_from_args(argv)
 
-    # TODO: replace compress_model + serialize with save_model
-    if argv.compress_to_fp16:
-        from openvino.tools.ovc.moc_frontend.offline_transformations import compress_model
-        compress_model(ngraph_function)
-
-    serialize(ngraph_function, model_path.encode('utf-8'), model_path.replace('.xml', '.bin').encode('utf-8'))
+    compress_to_fp16 = 'compress_to_fp16' in argv and argv.compress_to_fp16
+    save_model(ngraph_function, model_path.encode('utf-8'), compress_to_fp16)
 
     print('[ SUCCESS ] XML file: {}'.format(model_path))
     print('[ SUCCESS ] BIN file: {}'.format(model_path.replace('.xml', '.bin')))