Floating-Point IP Cores User Guide

ID 683750
Date 10/27/2021
Public

A newer version of this document is available.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

Document Table of Contents

15.7. ALTFP_CONVERT Parameters

Table 90.  ALTFP_CONVERT Parameters
Port Name Type Required Description
WIDTH_EXP_INPUT Integer Yes Specifies the precision of the exponent. If this parameter is not specified, the default is 8. The bias of the exponent is always set to 2 (WIDTH_EXP - 1) - 1, that is, 127 for the single-precision format and 1023 for the double-precision format. The value of WIDTH_EXP_INPUT must be 8 for the single-precision format, 11 for the double-precision format, and a minimum of 11 for the single-extended precision format. The value of WIDTH_EXP_INPUT must be less than the value of WIDTH_MAN_INPUT, and the sum of WIDTH_EXP_INPUT and WIDTH_MAN_INPUT must be less than 64. These settings apply only to the FLOAT2FIXED, FLOAT2INT, and FLOAT2FLOAT operation modes.
WIDTH_MAN_INPUT Integer Yes Specifies the precision of the mantissa. If this parameter is not specified, the default is 23. When WIDTH_EXP_INPUT is 8 and the floating-point format is single-precision, the WIDTH_MAN_INPUT value must be 23. Otherwise, the value of WIDTH_MAN_INPUT must be a minimum of 31. The value of WIDTH_MAN_INPUT must be greater than the value of WIDTH_EXP_INPUT, and the sum of WIDTH_EXP_INPUT and WIDTH_MAN_INPUT must be less than 64. These settings apply only to the FLOAT2FIXED, FLOAT2INT, and FLOAT2FLOAT operation modes.
WIDTH_INT Integer Yes Specifies the integer width.

If the operation is FIXED2FLOAT or INT2FLOAT, this parameter defines the integer width on the input side.

If the operation is FLOAT2INT or FLOAT2FIXED, this parameter defines the result width on the output side.

The available settings are 32 bits, 64 bits or n bits. For n bits settings, the range is from 4 bits to 64 bits.

If unspecified, the default setting for WIDTH_INT is 32 bits.

WIDTH_DATA Integer Yes Specifies the input data width.

If the operation is INT2FLOAT, the WIDTH_DATA is also WIDTH_INT.

If the operation is FIXED2FLOAT, the data width value is WIDTH_INT + fractional width.

If the operation is FLOAT2FIXED, FLOAT2INT or FLOAT2FLOAT, the data width value is WIDTH_EXP_INPUT + WIDTH_MAN_INPUT + 1.

The available settings are 32 bits, 64 bits or n bits. For n bits settings, the range is from 4 bits to 64 bits.

If unspecified, the default setting for WIDTH_DATA is 32 bits.

WIDTH_EXP_OUTPUT Integer Yes Specifies the precision of the exponent. If this parameter is not specified, the default is 8. The bias of the exponent is always set to 2 (WIDTH_EXP - 1) - 1, that is, 127 for the single-precision format and 1023 for the double-precision format. The value of WIDTH_EXP_OUTPUT must be 8 for the single-precision format, 11 for the double-precision format, and a minimum of 11 for the single-extended precision format. The value of WIDTH_EXP_OUTPUT must be less than the value of WIDTH_MAN_OUTPUT, and the sum of WIDTH_EXP_OUTPUT and WIDTH_MAN_OUTPUT must be less than 64. These settings apply only to the FLOAT2FIXED, FLOAT2INT, and FLOAT2FLOAT operation modes.
WIDTH_MAN_OUTPUT Integer Yes Specifies the precision of the mantissa. If this parameter is not specified, the default is 23. When WIDTH_EXP_OUTPUT is 8 and the floating point format is single-precision, the WIDTH_MAN_OUTPUT value must be 23. Otherwise, the value of WIDTH_MAN_OUTPUT must be a minimum of 31. The value of WIDTH_MAN_OUTPUT must be greater than the value of WIDTH_EXP_OUTPUT, and the sum of WIDTH_EXP_OUTPUT and WIDTH_MAN_OUTPUT must be less than 64. These settings apply only to the FLOAT2FIXED, FLOAT2INT, and FLOAT2FLOAT operation modes.
WIDTH_RESULT Integer Yes Specifies the width of the output result. In an INT2FLOAT, FLOAT2FLOAT, or FIXED2FLOAT operation, the result width is WIDTH_EXP_OUTPUT + WIDTH_MAN_OUTPUT + 1. In a FLOAT2INT operation, the result width is the value of the WIDTH_INT parameter.

In a FLOAT2FIXED operation, this parameter is the result width.

The available settings are 32 bits, 64 bits or n bits. For n bits settings, the range is from 4 bits to 64 bits.

ROUNDING Integer Yes Specifies the rounding mode. The default value is TO_NEAREST. Other modes are not supported.
OPERATION Integer Yes Specifies the operating mode. Values are INT2FLOAT, FLOAT2INT, FLOAT2FLOAT, FLOAT2FIXED, and FIXED2FLOAT. If this parameter is not specified, the default value is INT2FLOAT.

When set to INT2FLOAT, the conversion of an integer input to an IEEE floating-point representation output takes place.

When set to FLOAT2INT, the conversion of an IEEE floating-point representation input to an integer output takes place.

When set to FLOAT2FLOAT, the conversion between IEEE floating-point representations input and output takes place.

When set to FIXED2FLOAT, the conversion of a fixed point input to an IEEE floating-point representation output takes place.

When set to FLOAT2FIXED, the IEEE floating-point input conversion to fixed point representation output takes place.