NVIDIA DriveWorks API: Tensor Streamer
Description: This file defines the tensor streamer function.
Definition in file TensorStreamer.h.
|
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_consumerReceive (dwDNNTensorHandle_t *tensor, dwTime_t timeout_us, dwDNNTensorStreamerHandle_t streamer) |
| | Receive a pointer to a dwDNNTensorHandle_t from the streamer, acting as a consumer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_consumerReturn (dwDNNTensorHandle_t *tensor, dwDNNTensorStreamerHandle_t streamer) |
| | Return the received tensor back to the producer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_getCUDAStream (cudaStream_t *stream, dwDNNTensorStreamerHandle_t streamer) |
| | Get CUDA stream used by the tensor streamer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_getOutputProperties (dwDNNTensorProperties *props, dwDNNTensorStreamerHandle_t streamer) |
| | Get tensor properties of the tensor received from the streamer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_initialize (dwDNNTensorStreamerHandle_t *streamer, const dwDNNTensorProperties *from, dwDNNTensorType to, dwContextHandle_t ctx) |
| | Creates and initializes the tensor streamer capable of moving tensors between different API types. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_producerReturn (dwDNNTensorHandle_t *tensor, dwTime_t timeout_us, dwDNNTensorStreamerHandle_t streamer) |
| | The producer streamer waits for the tensor sent to be returned by the consumer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_producerSend (dwDNNTensorHandle_t tensor, dwDNNTensorStreamerHandle_t streamer) |
| | Sends an tensor through the streamer acting as the producer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_release (dwDNNTensorStreamerHandle_t streamer) |
| | Releases the tensor streamer. More...
|
| |
| DW_API_PUBLIC dwStatus | dwDNNTensorStreamer_setCUDAStream (cudaStream_t stream, dwDNNTensorStreamerHandle_t streamer) |
| | Sets the CUDA stream for CUDA related streaming operations such as post and receive. More...
|
| |