AllocTensor
Applicability
Product |
Supported |
|---|---|
√ |
|
√ |
|
x |
|
x |
|
x |
Function Description
FlowBufferFactory is used to build shared memory to reduce input and output copying time.
Allocates tensors based on the shape, data type, and alignment size. By default, the tensor is 64-byte aligned. You can specify the alignment size to optimize performance.
Prototype
1 | std::shared_ptr<Tensor> AllocTensor(const std::vector<int64_t> &shape, TensorDataType dataType, uint32_t align = 512U) |
Command-Line Options
Parameter |
Input/Output |
Description |
|---|---|---|
shape |
Input |
Shape of a tensor. |
dataType |
Input |
Data type of a tensor. |
align |
Input |
Alignment size for the allocated memory address. The value range is [32, 64, 128, 256, 512, 1024]. |
Returns
Allocated tensor pointer.
Troubleshooting
If no tensor pointer can be allocated, NULL is returned.
Constraints
None