[object Object]

[object Object][object Object]undefined

Note: When using this API, ensure that the driver firmware package and CANN package are in the 8.0.RC2 version or later. Otherwise, an error, such as BUS ERROR, will be reported.

[object Object]

• Description: Integrates the MatMul computation and AllReduce communication.
• Formula:$$output = AllReduce(x1 @ x2 + bias)$$

[object Object]

Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation flow. Then, [object Object] is called to perform computation.

[object Object]

• Parameters

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter verification. The following errors may be thrown.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• Deterministic computation:
  • [object Object]Atlas A2 training products/Atlas A2 inference products[object Object]: By default, aclnnMatmulAllReduce uses non-deterministic implementation. You can set the HCCL_DETERMINISTIC environment variable to true to enable deterministic computation.
  • Ascend 950PR/Ascend 950DT: [object Object] defaults to a deterministic implementation.
• MC2 is disabled in incremental scenarios but enabled in full scenarios.
• The input [object Object] can be 2D or 3D with shape (m, k) or (b, s, k). [object Object] must be 2D with shape (k, n). The axes meet the input parameter requirements of the MatMul operator, and the k axes of [object Object] and [object Object] must be equal. If [object Object] is not empty, its shape is (n).
• The values of b*s, [object Object], [object Object], and [object Object] cannot exceed [object Object] (INT32_MAX).
• When the shape of the input [object Object] is (b, s, k), the shape of [object Object] is (b, s, n). When the shape of the input [object Object] is (m, k), the shape of [object Object] is (m, n).
• The data types of the inputs [object Object], [object Object], and [object Object] must be the same as the data type of [object Object].
• Only the all-mesh networking of the HCCS link is supported.
  • [object Object]Atlas A2 training products/Atlas A2 inference products[object Object]: 1, 2, 4, and 8 ranks are supported.
  • Ascend 950PR/Ascend 950DT: 1, 2, 4, 8, 16, 32, and 64 cards are supported.
• [object Object]Atlas A2 training products/Atlas A2 inference products[object Object]: Only one communication domain for MC2 operators within a model is supported.
• Empty tensor support:
  • The scenario where k is 0 is supported. In this case, the output is bias.
  • When bs/m/n is 0, the input output should also be an empty tensor. In this case, the kernel is not executed and the result is directly returned.

[object Object]

The following example is for reference only. For details, see .

Note: This sample code calls some HCCL collective communication library APIs: HcclGetCommName, HcclCommInitAll, and HcclCommDestroy. For details, see .

• [object Object]Atlas A2 training products/Atlas A2 inference products[object Object] and Ascend 950PR/Ascend 950DT:

  [object Object]