Browse Prior Art Database

Handling Leading Zeros in a Data Processing Unit

IP.com Disclosure Number: IPCOM000082934D
Original Publication Date: 1975-Mar-01
Included in the Prior Art Database: 2005-Feb-28
Document File: 2 page(s) / 35K

Publishing Venue

IBM

Related People

Gooding, DN: AUTHOR [+2]

Abstract

This method enables more rapid processing of numerical data, for those cases where the presence of leading zeros affects the required execution time in a data processing unit. This is accomplished by simultaneously examining all the digits in a data number and developing an indication of the rotal leading zero count. This leading zero count is then used to directly manipulate the data number, to reduce the number of steps in the data processing operation in which the data number is involved.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 56% of the total text.

Page 1 of 2

Handling Leading Zeros in a Data Processing Unit

This method enables more rapid processing of numerical data, for those cases where the presence of leading zeros affects the required execution time in a data processing unit. This is accomplished by simultaneously examining all the digits in a data number and developing an indication of the rotal leading zero count. This leading zero count is then used to directly manipulate the data number, to reduce the number of steps in the data processing operation in which the data number is involved.

This method is, for example, useful in normalizing floating-point numbers. This application is illustrated in the drawing. The exponent portion of the floating- point number is located in a register 10, while the fraction portion of the floating- point number is located in a register 11.

A leading zero digit detector 12 simultaneously examines all the digits in the fraction portion in register 11 and develops an indication of the total leading zero digit count in this fraction portion. This leading zero digit count appears in register 13 and is supplied to the shifter controls of a shifter unit 14, to automatically shift the fraction portion the correct amount to normalize the same. The normalized fraction portion is placed in register 15.

At the same time, the leading zero digit count in register 13 is also used to update the exponent portion of the number. In particular, the exponent portion in register 10 is supplied to one...