Low-Cost Microarchitectural Support for Improved Floating-Point Accuracy

Abstract—Some processors designed for consumer applications, such as Graphics Processing Units (GPUs) and the CELL processor, promise outstanding floating-point performance for scientific applications at commodity prices. However, IEEE single precision is the most precise floating-point data type these processors directly support in hardware. Pairs of native floatingpoint numbers can be used to represent a base result and a residual term to increase accuracy, but the resulting order of magnitude slowdown dramatically reduces the price/performance advantage of these systems. By adding a few simple microarchitectural features, acceptable accuracy can be obtained with relatively little performance penalty. To reduce the cost of native-pair arithmetic, a residual register is used to hold information that would normally have been discarded after each floating-point computation. The residual register dramatically simplifies the code, providing both lower latency and better instructio...

• Type: Journal
• Year: 2007
• Where: CAL
• Authors: William R. Dieter, A. Kaveti, Henry G. Dietz
• Keywords: CAL 2007, CAL 2008, IEEE Single Precision, Outstanding floating-point Performance, Residual Register