Documentation

vconv_deq

Function

vconv_deq instruction abstraction.

y = vconv_deq(x, dtype), where vconv_deq indicates vector calculation for quantization on input data.

Currently, the conversion from FP16 to INT8 and from INT32 to FP16 are supported.

Prototype

1
class vconv_deq(x, y, dtype)

Parameters

Parameter

Input/Output

Data Type

Description

x

Input

Tensor variable

Input x-vector tensor.

y

Output

Tensor variable

Output y-vector tensor.

dtype

Input

String

Data type of the target tensor.

Example

1
2
3
4
5
from mskpp import vconv_deq, Tensor
ub_x, ub_y = Tensor("UB", "FP16"), Tensor("UB")
gm_x = Tensor("GM")
ub_x.load(gm_x)
out = vconv_deq(ub_x, ub_y, "FP32")()