Abstract:
Decimal data and decimal arithmetic operations are ubiquitous in daily life. Although microprocessors normally use binary arithmetic for computations, decimal arithmetic...Show MoreMetadata
Abstract:
Decimal data and decimal arithmetic operations are ubiquitous in daily life. Although microprocessors normally use binary arithmetic for computations, decimal arithmetic is often required in financial and commercial applications. Due to the increasing importance of and demand for decimal arithmetic, decimal floating-point (DFP) formats and operations are specified in the revised IEEE Standard for Floating-Point Arithmetic (IEEE 754-2008). This paper provides a survey of hardware designs for decimal arithmetic. It gives an overview of DFP arithmetic in IEEE 754-2008, describes processors that provide hardware and instruction set support for decimal arithmetic, and provides a survey of hardware designs for decimal addition, subtraction, multiplication, and division. Finally, it describes potential areas for future research.
Published in: IBM Journal of Research and Development ( Volume: 54, Issue: 2, March-April 2010)