Hardware implementations of denormalized numbers

Denormalized numbers are the most difficult type of numbers to implement in floating-point units. They are so complex that some designs have elected to handle them in software rather than hardware. This has resulted in execution times in the tens of thousands of cycles, which has made 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. We will summarize the little known techniques for handling denormalized numbers. Most of the techniques discussed have only been discussed in filed or pending patent applications.

[1]  Stamatis Vassiliadis,et al.  A General Proof for Overlapped Multiple-Bit Scanning Multiplications , 1989, IEEE Trans. Computers.

[2]  Cathy May,et al.  The PowerPC Architecture: A Specification for a New Family of RISC Processors , 1994 .

[3]  Eric M. Schwarz,et al.  High performance floating-point unit with 116 bit wide divider , 2003, Proceedings 2003 16th IEEE Symposium on Computer Arithmetic.

[4]  Christopher A. Krygowski,et al.  The S/390 G5 floating-point unit , 1999, IBM J. Res. Dev..

[5]  Gregory B. Zyner,et al.  167 MHz radix-4 floating point multiplier , 1995, Proceedings of the 12th Symposium on Computer Arithmetic.