Documentation

vtranspose

Function

vtranspose instruction abstraction.

Transposes a 16 × 16 matrix starting from the input address x (32-byte aligned). Each element has 16 bits. The result is output to y. The input and output are continuous 512-byte storage spaces.

Prototype

1
class vtranspose (x, y)

Parameters

Parameter

Input/Output

Data Type

Description

x

Input

Tensor variable

Input x-vector tensor. INT16 is supported.

y

Output

Tensor variable

Output vector tensor. INT16 is supported.

Example

1
2
3
4
5
from mskpp import vtranspose, Tensor
ub_x, ub_y = Tensor("UB"), Tensor("UB")
gm_x = Tensor("GM")
ub_x.load(gm_x)
out = vtranspose(ub_x, ub_y)()