ABSTRACT
Scientific applications rely heavily on floating-point arithmetic and, therefore, are affected by the precision and implementation of floating-point operations. Although the computers we use are IEEE compliant, this only assures the same representation of floating-point numbers; it does not guarantee that floating-point operations will be performed in the same way on all computers. As a result the same program run on different computers may yield different results. This paper is a first step in understanding the reason for this, in particular, different results for the execution of the application Charmm on different computers. We report on our use of a well-known test suite, IeeeCC754, to evaluate IEEE 754 compliance across a wide range of heterogeneous computers with different architectures, operating systems, precisions, and compilers.
- Bailey, D. H. High-precision Floating-point Arithmetic in Scientific Computation. Computing in Science and Engineering, May-June 2005, 7(3):54--61. Google ScholarDigital Library
- Braxenthaler, M., Unger, R., Auerbach, D., Given, J. A. and Moult, J. Chaos in Protein Dynamics, December 2005.Google Scholar
- Cuyt, A., Verdonk, B., and Verschaeren, D. A Precision- and Range-independent Tool for Testing Floating-point Arithmetic II: Conversions. ACM Transactions on Mathematical Software, 27(1):119--140, May 2001. Google ScholarDigital Library
- Goldberg, D. What Every Computer Scientist Should Know About Floating-Point Arithmetic. ACM Computing Surveys, March 1991, 23(1):5--48. Google ScholarDigital Library
- IEEE Std 754--1985, "IEEE Standard for Binary Floating-Point Arithmetic."Google Scholar
- Taufer, M., Anderson, D. P., Cicotti, P., and Brooks III, C. L. Homogeneous Redundancy: a Technique to Ensure Integrity of Molecular Simulation Results Using Public Computing. Proceedings of the 14th Heterogeneous Computing Workshop HCW (2005), in conjunction with IPDPS 2005. Denver, Colorado, April 2005. Google ScholarDigital Library
- Verdonk, B., Cuyt, A., and Verschaeren, D. A Precision-and Range-independent Tool for Testing Floating-point Arithmetic I: Basic Operations, Square Root, and Remainder. ACM Transactions on Mathematical Software, 27(1):92--118, March 2001. Google ScholarDigital Library
Index Terms
- Evaluation of IEEE 754 floating-point arithmetic compliance across a wide range of heterogeneous computers
Recommendations
A FPGA IEEE-754-2008 Decimal64 Floating-Point Multiplier
RECONFIG '09: Proceedings of the 2009 International Conference on Reconfigurable Computing and FPGAsThis paper describes the design and implementation of a hardware module to calculate the decimal floating-point DFP) multiplication compliant with the current IEEE-754-2008 standard. The design proposed is made up of independent stages: IEEE-754 coder / ...
Decimal Floating-Point Multiplication
Decimal multiplication is important in many commercial applications including financial analysis, banking, tax calculation, currency conversion, insurance, and accounting. This paper presents the design of two decimal floating-point multipliers: one ...
Comments