[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]
  • API function: Implements quant+reduceScatter fusion computation.
  • Formula:output=Reduce(AllToAllScalesAllToAllData)output=Reduce(AllToAllScales * AllToAllData) AllToAllData=AllToAll(x)AllToAllData=AllToAll(x) AllToAllScales=AllToAll(scales)AllToAllScales=AllToAll(scales) The Reduce computation is performed on data from different ranks.
[object Object]

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

[object Object]
[object Object]
[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]
  • When the data type of x is FLOAT8_E4M3FN, FLOAT8_E5M2 and that of scales is FLOAT8_E8M0, the quantization mode of the input data is mx quantization.
  • When the data type of x is INT8, HIFLOAT8, or FLOAT8_E4M3FN, FLOAT8_E5M2 and that of scales is FLOAT, the quantization mode of the input data is pertoken-pergroup quantization (groupSize = 128).
  • This feature is enabled only on the Ascend 950 series platforms.
  • Empty tensor input is not supported.
  • The size of the communicator can be 2, 4, or 8.
  • Restrictions on the use of the communicator: The aclnnQuantAllReduce and aclnnQuantReduceScatter operators can be executed only in sequence in the same communicator, and no other communication operators are allowed in the communicator.
  • HCCL_BUFFSIZE: Before calling this operator, check whether the value of the HCCL_BUFFSIZE environment variable is proper. This environment variable indicates the buffer size occupied by a single communication domain, in MB. If this environment variable is not set, the default value 200 MB is used. The following condition must be met: HCCL_BUFFSIZE >= 2 (xDataSize + scalesDataSize + 1). xDataSize indicates the size of the input x data, which is calculated as follows: xDataSize = BS H 1 (byte). scalesDataSize indicates the size of the scales data. When the quantization mode is pertoken-pergroup quantization, the calculation formula is as follows: scalesDataSize = BS H / 128 4 (byte). When the quantization mode is mx quantization, the calculation formula is as follows: scalesDataSize = BS H / 32 * 1 (byte).
  • The value of H must be 128-aligned and within the range of [1024, 8192].
[object Object]

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

  • Ascend 950PR/Ascend 950DT:

    [object Object]