AllocTensorListMsg

Applicability

Product	Supported
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	x
Atlas inference products	x
Atlas training products	x

Function Description

Allocates a continuous memory block based on the input dtype shapes array to carry the tensor array.

Prototype

virtual std::shared_ptr<FlowMsg> AllocTensorListMsg(const std::vector<std::vector<int64_t>> &shapes, const std::vector<TensorDataType> &dataTypes, uint32_t align = 512U)

Command-Line Options

Parameter	Input/Output	Description
shapes	Input	Shape list of the tensor list.
dataTypes	Input	DataType list of the tensor list.
align	Input	Alignment size for the allocated memory address. Values: [32, 64, 128, 256, 512, 1024].

Returns

Allocated FlowMsg pointer.

Troubleshooting

If no tensor pointer can be allocated, NULL is returned.

Constraints

None

Parent topic: GetOutputNum