LeftShift
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: performs the bitwise left shift operation on the input tensors x and y element-wise.
-
Computation formula:
zi=xi<<yiz_i = x_i << y_i
Parameter Description
| Parameter Name | Input/Output/Attribute | Description | Data Type | Data Format |
|---|---|---|---|---|
| x | Input | The input x is a k-dimensional tensor and is the input parameter for the left_shift computation, which is x_i in the formula. | INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64 | ND |
| y | Input | Input parameter for the left_shift computation, which is y_i in the formula. | INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64 | ND |
| z | Output | Output parameter for the left_shift computation, which is z_i in the formula. | INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64 | ND |
Constraint Description
If shiftBits is negative or is not less than the bit width of the x data type, the output is 0, which is consistent with torch.bitwise_left_shift of PyTorch.
Invocation Description
| Invocation Method | Invocation Sample | Description |
|---|---|---|
| aclnn invocation | test_aclnn_left_shift | Invokes the left_shift operator through the aclnnLeftShift API. |
| aclnn invocation | test_aclnn_left_shifts | Invokes the left_shift operator through the aclnnLeftShifts API (shiftBits is a scalar). |
| Graph-mode invocation | test_geir_left_shift | Invokes the LeftShift operator by building a graph through the operator IR. |