ConnectAsync

Applicable Products

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

Function Description

Establishes a link asynchronously with the remote HIXL instance.

Prototype

1

Status ConnectAsync(const AscendString &remote_engine, int32_t timeout_in_millis = 1000)

Parameters

Example

Click GitCode, select the matching version, and obtain the sample from the examples/cpp directory.

Returns

• SUCCESS: Success.
• RESOURCE_EXHAUSTED: The task queue is full.
• Other values: Failure.

Constraints

• This API must be called after the Initialize API is called on the client and server to complete initialization.
• The maximum number of communication links that can be created is 512; creating too many links may lead to OOM errors and performance degradation during KV cache transmission. This restriction applies to the following products:
  • Atlas A2 training products / Atlas A2 inference products
  • Atlas A3 training products / Atlas A3 inference products
• You are advised to set the timeout interval longer than 200 ms. If TLS is enabled, it is recommended that the timeout period be set to a value greater than 2000 ms. Run the following command to query the TLS status:

  hccn_tool [-i %d] -tls -g [host]

• Before calling this API, register all local and remote memories. Otherwise, memories registered after link establishment will not support remote access.
• In container scenarios, you must map the /etc/hccn.conf file into the container or ensure that hccn_tool exists in the default path /usr/local/Ascend/driver/tools. If neither condition is met, you need to add the directory containing hccn_tool to the PATH environment variable. A configuration example is provided below, where hccn_tool_install_path indicates the directory containing hccn_tool.

  export PATH=$PATH:${hccn_tool_install_path}

  This restriction applies to the following products:

  • Atlas A2 training products / Atlas A2 inference products
  • Atlas A3 training products / Atlas A3 inference products
• This API and Initialize must run in the same thread. If you need to switch threads to call this API, first call aclrtGetCurrentContext in the thread where Initialize is running to obtain the context. Then, in the new thread, call aclrtSetCurrentContext to set the context.

• The number of threads in the thread pool and the length of the task queue are configured through the Initialize API of HIXL. The following is an example:

   "GlobalResourceConfig": "{"connect_pool.thread_num":"2","connect_pool.task_queue_capacity":"256"}"

• The ConnectAsync and DisconnectAsync APIs cannot be used together with the Connect and Disconnect APIs.
• Tasks delivered by users are executed in sequence. If multiple tasks are delivered to the same remote_engine, the remote_engine executes these tasks in sequence and obtains the status of the latest delivered task.