Data Structures | Namespaces | Functions
gpu_context_api_va.hpp File Reference

a header that defines wrappers for internal GPU plugin-specific shared Video Acceleration device contexts and shared memory blobs which contain Video Acceleration surfaces More...

#include <memory>
#include <string>
#include "gpu/gpu_context_api_ocl.hpp"
#include <va/va.h>

Go to the source code of this file.

Data Structures

class  InferenceEngine::gpu::VAContext
 This class represents an abstraction for GPU plugin remote context which is shared with VA display object. The plugin object derived from this class can be obtained either with GetContext() method of Executable network or using CreateContext() Core call. More...
 
class  InferenceEngine::gpu::VASurfaceBlob
 This class represents an abstraction for GPU plugin remote blob which is shared with VA output surface. The plugin object derived from this class can be obtained with CreateBlob() call. More...
 

Namespaces

 InferenceEngine
 Inference Engine C++ API.
 

Functions

static Blob::Ptr InferenceEngine::gpu::make_shared_blob_nv12 (size_t height, size_t width, RemoteContext::Ptr ctx, VASurfaceID nv12_surf)
 This function is used to obtain a NV12 compound blob object from NV12 VA decoder output. The resulting compound contains two remote blobs for Y and UV planes of the surface.
 
static VAContext::Ptr InferenceEngine::gpu::make_shared_context (Core &core, std::string deviceName, VADisplay device)
 This function is used to obtain remote context object from VA display handle.
 
static VASurfaceBlob::Ptr InferenceEngine::gpu::make_shared_blob (const TensorDesc &desc, RemoteContext::Ptr ctx, VASurfaceID surface, uint32_t plane=0)
 This function is used to obtain remote blob object from VA surface handle.
 

Detailed Description

a header that defines wrappers for internal GPU plugin-specific shared Video Acceleration device contexts and shared memory blobs which contain Video Acceleration surfaces