PandA-2024.02
|
Plain C Tensor object, does not manage memory. More...
#include <dlpack.h>
Data Fields | |
void * | data |
The opaque data pointer points to the allocated data. This will be CUDA device pointer or cl_mem handle in OpenCL. This pointer is always aligns to 256 bytes as in CUDA. More... | |
DLContext | ctx |
The device context of the tensor. More... | |
int | ndim |
Number of dimensions. More... | |
DLDataType | dtype |
The data type of the pointer. More... | |
int64_t * | shape |
The shape of the tensor. More... | |
int64_t * | strides |
strides of the tensor, can be NULL, indicating tensor is compact. More... | |
uint64_t | byte_offset |
The offset in bytes to the beginning pointer to data. More... | |
uint64_t DLTensor::byte_offset |
void* DLTensor::data |
The opaque data pointer points to the allocated data. This will be CUDA device pointer or cl_mem handle in OpenCL. This pointer is always aligns to 256 bytes as in CUDA.
For given DLTensor, the size of memory required to store the contents of data is calculated as follows:
Definition at line 131 of file dlpack.h.
Referenced by fused_activations_wrapper(), fused_conv2d_wrapper(), fused_multiply_wrapper(), fused_nn_dense_add_wrapper(), fused_nn_max_pool2d_wrapper(), fused_nn_softmax_wrapper(), and mlp_wrapper().
DLDataType DLTensor::dtype |
int64_t* DLTensor::strides |