#[repr(C)]pub struct DLTensor {
pub data: *mut c_void,
pub device: DLDevice,
pub ndim: i32,
pub dtype: DLDataType,
pub shape: *mut i64,
pub strides: *mut i64,
pub byte_offset: u64,
}Expand description
\brief Plain C Tensor object, does not manage memory.
Fields§
§data: *mut c_void\brief The data pointer points to the allocated data. This will be CUDA
device pointer or cl_mem handle in OpenCL. It may be opaque on some device
types. This pointer is always aligned to 256 bytes as in CUDA. The
byte_offset field should be used to point to the beginning of the data.
Note that as of Nov 2021, multiply libraries (CuPy, PyTorch, TensorFlow,
TVM, perhaps others) do not adhere to this 256 byte aligment requirement
on CPU/CUDA/ROCm, and always use byte_offset=0. This must be fixed
(after which this note will be updated); at the moment it is recommended
to not rely on the data pointer being correctly aligned.
For given DLTensor, the size of memory required to store the contents of data is calculated as follows:
\code{.c} static inline size_t GetDataSize(const DLTensor* t) { size_t size = 1; for (tvm_index_t i = 0; i < t->ndim; ++i) { size *= t->shape[i]; } size *= (t->dtype.bits * t->dtype.lanes + 7) / 8; return size; } \endcode
Note that if the tensor is of size zero, then the data pointer should be
set to NULL.
device: DLDevice\brief The device of the tensor
ndim: i32\brief Number of dimensions
dtype: DLDataType\brief The data type of the pointer
shape: *mut i64\brief The shape of the tensor
strides: *mut i64\brief strides of the tensor (in number of elements, not bytes) can be NULL, indicating tensor is compact and row-majored.
byte_offset: u64\brief The offset in bytes to the beginning pointer to data