Asin
English | 简体中文
Product Support Status
| Product | Supported |
|---|---|
| Ascend 950PR&950DT products | √ |
| Atlas A3 products | √ |
| Atlas A2 products | √ |
| Atlas 200I/500 A2 inference products | × |
| Atlas inference products | √ |
| Atlas training products | √ |
Function Description
-
Operator function: computes the arcsine of each element in the input tensor and outputs a tensor whose shape is the same as that of the input.
-
Computation formula:
yi=arcsin(xi)y_{i} = \arcsin(x_{i})
Parameter Description
| Parameter Name | Input/Output/Attribute | Description | Data Type | Data Format |
|---|---|---|---|---|
| x | Input | The input tensor for the arcsine computation, which is x in the formula. | BFLOAT16, FLOAT16, FLOAT | ND |
| y | Output | The arcsine computation result. The shape is the same as that of x, and it is y in the formula. | BFLOAT16, FLOAT16, FLOAT | ND |
- For the data types, type conversion rules, and dimension constraints supported by the aclnn API, see aclnnAsin&aclnnInplaceAsin.
Constraint Description
- The shapes of x and y are the same.
- In graph-mode (GEIR) invocation, the data types of x and y must be the same. The Tiling check returns a failure when the data types of the input and output are different. For the type conversions supported by the aclnn API, see aclnnAsin&aclnnInplaceAsin.
- For the dtype, type conversion, empty tensor, and dimension constraints at the aclnn API layer, see aclnnAsin&aclnnInplaceAsin.
Invocation Description
| Invocation Method | Sample Code | Description |
|---|---|---|
| aclnn invocation | test_aclnn_asin, test_aclnn_asin_fp16 | Invokes the Asin operator through the aclnnAsin API. |
| aclnn in-place invocation | - | Invokes the Asin operator through the aclnnInplaceAsin API. |
| Graph-mode invocation | test_geir_asin, test_geir_asin_const_folding | Invokes the Asin operator by building a graph through the operator IR. |