Title :
FPU implementations with denormalized numbers
Author :
Schwarz, Eric M. ; Schmookler, Martin ; Trong, Son Dao
Author_Institution :
IBM Server Div., Poughkeepsie, NY, USA
fDate :
7/1/2005 12:00:00 AM
Abstract :
Denormalized numbers are the most difficult type of numbers to implement in floating-point units. They are so complex that certain designs have elected to handle them in software rather than in hardware. Traps to software can result in long execution times, which renders denormalized numbers useless to programmers. This does not have to happen. With a small amount of additional hardware, denormalized numbers and underflows can be handled close to the speed of normalized numbers. This paper summarizes the little known techniques for handling denormalized numbers. Most of the techniques described here only appear in filed or pending patent applications.
Keywords :
IEEE standards; floating point arithmetic; IEEE 754 standard; denormalized numbers; floating-point hardware; floating-point unit; underflow trap; Arithmetic; Concrete; H infinity control; Hardware; Helium; Java; Performance loss; Programming profession; Tagging; IEEE 754 Standard; Index Terms- Denormalized numbers; floating-point hardware; subnormals; underflow trap.;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.2005.118