Documentation

vlrelu

Function

vlrelu instruction abstraction.

If x is greater than or equal to 0, z = x. If x is less than 0, z = x × y, where x is multiplied by scalar y by element.

Prototype

1
class vlrelu(x, y, z)

Parameters

Parameter

Input/Output

Data Type

Description

x

Input

Tensor variable

Input x-vector tensor. float16 and float32 are supported.

y

Input

Tensor variable

Input y scalar. float16 and float32 are supported.

z

Output

Tensor variable

Output vector tensor. float16 and float32 are supported.

Example

1
2
3
4
5
6
from mskpp import vlrelu, Tensor
ub_x, ub_z = Tensor("UB"), Tensor("UB")
gm_x = Tensor("GM")
scalar_y = 5  // 5 is the value of scalar y.
ub_x.load(gm_x)
out = vlrelu(ub_x, scalar_y, ub_z)()