#include <cstddef>
#include <memory>
|
template<class T > |
void | RooBatchCompute::CudaInterface::copyDeviceToDevice (const T *src, T *dest, std::size_t n, CudaStream *=nullptr) |
| Copies data from the CUDA device to the CUDA device.
|
|
template<class T > |
void | RooBatchCompute::CudaInterface::copyDeviceToHost (const T *src, T *dest, std::size_t n, CudaStream *=nullptr) |
| Copies data from the CUDA device to the host.
|
|
template<class T > |
void | RooBatchCompute::CudaInterface::copyHostToDevice (const T *src, T *dest, std::size_t n, CudaStream *=nullptr) |
| Copies data from the host to the CUDA device.
|
|
float | RooBatchCompute::CudaInterface::cudaEventElapsedTime (CudaEvent &begin, CudaEvent &end) |
| Calculates the elapsed time between two CUDA events.
|
|
void | RooBatchCompute::CudaInterface::cudaEventRecord (CudaEvent &event, CudaStream &stream) |
| Records a CUDA event.
|
|