[object Object]

[object Object][object Object]undefined[object Object]

Description: Zeros input elements or scales them by [object Object] based on [object Object] bits during training. If a bit in [object Object] is [object Object], the corresponding [object Object] element is scaled; if a bit in [object Object] is [object Object], the corresponding [object Object] element is zeroed. Specially, if [object Object] is [object Object], all elements are zeroed; if [object Object] is [object Object], the [object Object] elements remain unchanged. You are advised to use it together with [object Object] or [object Object].

[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 process. Then, [object Object] is called to perform computation.

• [object Object]
• [object Object]

[object Object]

• Parameters

  • [object Object] (aclTensor*, computation input): tensor to be processed, [object Object] on the device. Empty tensors are not supported. are supported. The can be ND.
    • [object Object]Atlas training products[object Object]: The data type can be FLOAT16 or FLOAT32.
    • [object Object]Atlas A2 training products/Atlas A2 inference products[object Object] and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: The data type can be BFLOAT16, FLOAT16, or FLOAT32.
  • [object Object] (aclTensor*, computation input): bitmask data stored as UINT8, [object Object] on the device. Empty tensors are not supported. The data type can be UINT8. The shape must be ([object Object](number of elements in [object Object], 128)/8), indicating that the number of bits must be aligned with 128. [object Object] indicates that the number of elements in the input is rounded up to a multiple of 128. For example, the result of align (1111, 128) is 1152. are supported. The can be ND.
  • [object Object] (double, computation input): DOUBLE type on the host. The input is [object Object], and the output is the data scaling ratio. The data type can be DOUBLE.
  • [object Object] (aclTensor*, computation output): output tensor, [object Object] on the device. The data type must be convertible from that of [object Object]. The shape must be identical to that of [object Object]. are supported. The can be ND.
    • [object Object]Atlas training products[object Object]: The data type can be FLOAT16 or FLOAT32.
    • [object Object]Atlas A2 training products/Atlas A2 inference products[object Object] and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: The data type can be BFLOAT16, FLOAT16, or FLOAT32.
  • [object Object] (uint64_t*, output): size of the workspace to be allocated on the device.
  • [object Object] (aclOpExecutor**, output): operator executor, containing the operator computation process.

• Returns

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

[object Object]

• Parameters

  • [object Object] (void*, input): address of the workspace to be allocated on the device.
  • [object Object] (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling the first-phase API [object Object].
  • [object Object] (aclOpExecutor*, input): operator executor, containing the operator computation process.
  • [object Object] (aclrtStream, input): stream for executing the task.

• Returns

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

[object Object]

• Deterministic computation:
  • [object Object] defaults to a deterministic implementation.

[object Object]

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