Header file declaring utility classes for CUDA memory management, CIDA streams and events.
Definition in file infer_cuda_utils.h.
Go to the source code of this file.
Data Structures | |
class | nvdsinferserver::CudaStream |
Wrapper class for CUDA streams. More... | |
class | nvdsinferserver::CudaEvent |
Wrapper class for CUDA events. More... | |
class | nvdsinferserver::SysMem |
Base class for managing memory allocation. More... | |
class | nvdsinferserver::CudaDeviceMem |
Allocates and manages CUDA device memory. More... | |
class | nvdsinferserver::CudaHostMem |
Allocates and manages CUDA pinned memory. More... | |
class | nvdsinferserver::CpuMem |
Allocates and manages host memory. More... | |
class | nvdsinferserver::CudaTensorBuf |
A batch buffer with CUDA memory allocation. More... | |
Namespaces | |
nvdsinferserver | |
This is a header file for pre-processing cuda kernels with normalization and mean subtraction required by nvdsinfer. | |
Functions | |
UniqCudaTensorBuf | nvdsinferserver::createTensorBuf (const InferDims &dims, InferDataType dt, int batchSize, const std::string &name, InferMemType mt, int devId, bool initCuEvent) |
Create a tensor buffer of the specified memory type, dimensions on the given device. More... | |
UniqCudaTensorBuf | nvdsinferserver::createGpuTensorBuf (const InferDims &dims, InferDataType dt, int batchSize, const std::string &name="", int devId=0, bool initCuEvent=false) |
Create a CUDA device memory tensor buffer of specified dimensions on the given device. More... | |
UniqCudaTensorBuf | nvdsinferserver::createCpuTensorBuf (const InferDims &dims, InferDataType dt, int batchSize, const std::string &name="", int devId=0, bool initCuEvent=false) |
Create a CUDA pinned memory tensor buffer of specified dimensions on the given device. More... | |
NvDsInferStatus | nvdsinferserver::syncAllCudaEvents (const SharedBatchArray &bufList) |
Synchronize on all events associated with the batch buffer array. More... | |