Saturation detection in floating point to integer conversions

Details Saturation detection in floating point to integer conversions Saturation detection in floating point to integer conversions

1998-08-31

2001-02-27

Donaghue, Larry D. (Department: 2154)

Electrical computers: arithmetic processing and calculating

Electrical digital calculating computer

Particular function performed

C708S495000, C708S209000, C708S551000, C708S552000

Reexamination Certificate

active

06195672

ABSTRACT:

FIELD OF THE INVENTION
The present invention pertains to the field of digital data processing. More particularly, this invention relates to a method and apparatus for performing saturation detection for floating point to integer conversions.
BACKGROUND OF THE INVENTION
Digital data is frequently represented in either integer notation or floating point notation. One advantage of floating point notation is that a larger range of values can be represented in a given number of bit positions using floating notation then can be represented using integer notation. On the other hand, integer notation operations, such as integer addition, subtraction, etc., are often faster and more accurate than floating point operations. As a result of the various advantages for each notation, a number represented in one notation is often converted to the other notation.
Converting from floating point to integer notation, however, may not always be possible because the magnitude of a floating point number may be outside the range of an integer number. For instance, the magnitude of a floating point number may be too large to be represented in the number of bit positions available in the integer field. In which case, the floating point number “saturates” the integer field.
Generally, saturation detection takes place after a floating point number is converted to integer notation. The conversion process can take a comparatively large amount of processing time. For instance, a floating point number may need to be right shifted a particular number of bit positions, and shifting a data field can take a long time. Then, if saturation detection is performed after the data field has been right shifted, additional processing time is expended.
In order to improve data processing performance, a need exists for an improved method and apparatus for saturation detection in floating point to integer conversions.
SUMMARY OF THE INVENTION
An improved method and apparatus for saturation detection in floating point to integer conversions is described. A floating point number is tested for saturation conditions based on an integer field size. From testing the saturation conditions on the floating point number, the present invention predicts whether a floating point number can be converted into an integer value having the given integer field size, or whether the integer field would be saturated. In one embodiment, the saturation conditions are tested in parallel with a floating point to integer conversion.


REFERENCES:
patent: 5257215 (1993-10-01), Poon
patent: 5550768 (1996-08-01), Ogilvie et al.
patent: 5627773 (1997-05-01), Wolrich et al.
patent: 5764548 (1998-06-01), Keith et al.
patent: 5995122 (1999-11-01), Hsieh et al.
patent: 6061782 (2000-05-01), Elliott et al.

Affiliated with

Also associated with

Rating

Saturation detection in floating point to integer conversions does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Saturation detection in floating point to integer conversions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Saturation detection in floating point to integer conversions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2613388