Developer Reference for Intel® oneAPI Math Kernel Library for C

ID 766684
Date 11/07/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

vslConvSetInternalPrecision/vslCorrSetInternalPrecision

Changes the value of the parameter internal_precision in the convolution or correlation task descriptor.

Syntax

status = vslConvSetInternalPrecision(task, precision);

status = vslCorrSetInternalPrecision(task, precision);

Include Files

  • mkl.h

Input Parameters

Name

Type

Description

task

VSLConvTaskPtr for vslConvSetInternalPrecision

VSLCorrTaskPtr for vslCorrSetInternalPrecision

Pointer to the task descriptor.

precision

const MKL_INT

New value of the parameter internal_precision.

Output Parameters

Name

Type

Description

status

int

Current status of the task.

Description

The vslConvSetInternalPrecision/vslCorrSetInternalPrecision routine changes the value of the parameter internal_precision for the operation of convolution or correlation. This parameter defines whether the internal computations of the convolution or correlation result should be done in single or double precision. Initial value for internal_precision is assigned by a task constructor and set to either "single" or "double" according to the particular flavor of the constructor used.

Changing the internal_precision can be useful if the default setting of this parameter was "single" but you want to calculate the result with double precision even if input and output data are represented in single precision.

Predefined values for the internal_precision input parameter are as follows:

Values of internal_precision Parameter

Value

Purpose

VSL_CONV_PRECISION_SINGLE

Compute convolution with single precision.

VSL_CORR_PRECISION_SINGLE

Compute correlation with single precision.

VSL_CONV_PRECISION_DOUBLE

Compute convolution with double precision.

VSL_CORR_PRECISION_DOUBLE

Compute correlation with double precision.