Issue No.07 - July (2005 vol.54)
Eric M. Schwarz , IEEE
Martin Schmookler , IEEE
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TC.2005.118
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 will summarize the little known techniques for handling denormalized numbers. Most of the techniques described here only appear in filed or pending patent applications.
Index Terms- Denormalized numbers, subnormals, IEEE 754 Standard, floating-point hardware, underflow trap.
Eric M. Schwarz, Martin Schmookler, Son Dao Trong, "FPU Implementations with Denormalized Numbers", IEEE Transactions on Computers, vol.54, no. 7, pp. 825-836, July 2005, doi:10.1109/TC.2005.118