TransferAsync

Applicability

Product	Supported (√/x)
Atlas 350 Accelerator Card	x
Atlas A3 training product / Atlas A3 inference product	√
Atlas A2 training product / Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	x
Atlas inference product	x
Atlas training product	x

Note: For Atlas A2 training product / Atlas A2 inference product , only the Atlas 800I A2 inference server and A200I A2 Box heterogeneous subrack are supported.

Function Description

Transmits memory in batches with the remote HIXL instance asynchronously.

Prototype

      
           Status TransferAsync(const AscendString &remote_engine,
                     TransferOp operation,
                     const std::vector<TransferOpDesc> &op_descs,
                     const TransferArgs &optional_args,
                     TransferReq &req)

Parameters

Parameter	Input/Output	Description
remote_engine	Input	Unique identifier of the remote HIXL instance.
operation	Input	Reading the remote memory to the local side or writing the local memory to the remote side.
op_descs	Input	Local and remote addresses for batch operations.
optional_args	Input	Optional parameter (reserved).
req	Output	Request handle, which is used to query the transmission request status.

Example

// Initialize the engines on the client and server and establish a link.
client_engine.TransferAsync(remote_engine, operation, op_descs, optional_args, req);

Returns

SUCCESS: Success.
NOT_CONNECTED: No link is established with the peer end.
RESOURCE_EXHAUSTED: Resources are used up.
Other values: Failure.

Restrictions

Before calling this API, note the following constraints:
- Call the Connect API to establish a link with the peer end.
- Alternatively, enable the link pool mechanism during HIXL initialization. Specifically, set the OPTION_GLOBAL_RESOURCE_CONFIG parameter in options. This restriction applies to the following products:
  - Atlas A2 training product / Atlas A2 inference product
  - Atlas A3 training product / Atlas A3 inference product
This API and Initialize must run in the same thread. If you need to switch threads to call this API, first call aclrtGetCurrentContext in Application Development (C&C++) in the thread where Initialize is running to obtain the context. Then, in the new thread, call aclrtSetCurrentContext in Application Development (C&C++) to set the context.
Currently, asynchronous transmission supports only direct transmission (used by default). Relay transmission is not supported at this time.
In Fabric Mem transfer mode, the transfer types of all op_descs must be the same. The system determines the transfer direction based on the memory type of the first op_desc. This restriction applies to the following products:
- Atlas A3 training product / Atlas A3 inference product

Parent topic: HIXL APIs