DNNPlugin.h

Go to the documentation of this file.

// This code contains NVIDIA Confidential Information and is disclosed
// under the Mutual Non-Disclosure Agreement.
//
// Notice
// ALL NVIDIA DESIGN SPECIFICATIONS AND CODE ("MATERIALS") ARE PROVIDED "AS IS" NVIDIA MAKES
// NO REPRESENTATIONS, WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO
// THE MATERIALS, AND EXPRESSLY DISCLAIMS ANY IMPLIED WARRANTIES OF NONINFRINGEMENT,
// MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
//
// NVIDIA Corporation assumes no responsibility for the consequences of use of such
// information or for any infringement of patents or other rights of third parties that may
// result from its use. No license is granted by implication or otherwise under any patent
// or patent rights of NVIDIA Corporation. No third party distribution is allowed unless
// expressly authorized by NVIDIA.  Details are subject to change without notice.
// This code supersedes and replaces all information previously supplied.
// NVIDIA Corporation products are not authorized for use as critical
// components in life support devices or systems without express written approval of
// NVIDIA Corporation.
//
// Copyright (c) 2018 NVIDIA Corporation. All rights reserved.
//
// NVIDIA Corporation and its licensors retain all intellectual property and proprietary
// rights in and to this software and related documentation and any modifications thereto.
// Any use, reproduction, disclosure or distribution of this software and related
// documentation without an express license agreement from NVIDIA Corporation is
// strictly prohibited.
//

#ifndef DW_DNN_PLUGIN_H_
#define DW_DNN_PLUGIN_H_

#include <dw/core/Types.h>
#include <dw/dnn/DNN.h>

#ifdef __cplusplus
extern "C" {
#endif

typedef enum dwDNNPluginLayout {
    DW_DNN_PLUGIN_LAYOUT_LINEAR = 0,                           
    DW_DNN_PLUGIN_LAYOUT_NCHW   = DW_DNN_PLUGIN_LAYOUT_LINEAR, 
    DW_DNN_PLUGIN_LAYOUT_NC2HW2 = 1,                           
    DW_DNN_PLUGIN_LAYOUT_CHW2   = DW_DNN_PLUGIN_LAYOUT_NC2HW2, 
    DW_DNN_PLUGIN_LAYOUT_NHWC8  = 2,                           
    DW_DNN_PLUGIN_LAYOUT_HWC8   = DW_DNN_PLUGIN_LAYOUT_NHWC8,  
    DW_DNN_PLUGIN_LAYOUT_CHW4   = 3,                           
    DW_DNN_PLUGIN_LAYOUT_CHW16  = 4,                           
    DW_DNN_PLUGIN_LAYOUT_CHW32  = 5,                           
} dwDNNPluginLayout;

typedef struct dwDNNPluginWeights
{
    dwPrecision precision; 
    const void* values;    
    int64_t count;         
} dwDNNPluginWeights;

typedef void* _dwDNNPluginHandle_t;

dwStatus _dwDNNPlugin_initializeFromWeights(_dwDNNPluginHandle_t* handle, const char8_t* layerName,
                                            const dwDNNPluginWeights* weights, int32_t numWeights);

dwStatus _dwDNNPlugin_initialize(_dwDNNPluginHandle_t* handle, const char8_t* layerName,
                                 const void* data, size_t length);

dwStatus _dwDNNPlugin_release(_dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_getNumOutputs(int32_t* numOutputs, _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_getOutputDimensions(dwBlobSize* outputDimensions,
                                          int32_t outputIndex, const dwBlobSize* inputDimensions,
                                          int32_t numInputs, _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_getWorkspaceSize(size_t* workspaceSize, int32_t maxBatchSize,
                                       _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_supportsFormat(bool* res, dwPrecision precision,
                                     dwDNNPluginLayout pluginLayout, _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_configureWithFormat(const dwBlobSize* inputDimensions,
                                          int32_t numInputs, const dwBlobSize* outputDimensions,
                                          int32_t numOutputs, dwPrecision precision,
                                          dwDNNPluginLayout layout, int32_t maxBatchSize,
                                          _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_enqueue(int32_t batchSize, const void* const* inputs, void** outputs,
                              void* workspace, cudaStream_t stream, _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_getSerializationSize(size_t* serializationSize, _dwDNNPluginHandle_t handle);

dwStatus _dwDNNPlugin_serialize(void* buffer, _dwDNNPluginHandle_t handle);

#ifdef __cplusplus
}
#endif

#endif // DW_DNN_PLUGIN_H_