Title :
New algorithms for improved transcendental functions on IA-64
Author :
Story, Shane ; Tang, Ping Tak Peter
Author_Institution :
Intel Corp., Hillsboro, OR, USA
Abstract :
The IA-64 architecture provides new opportunities and challenges for implementing an improved set of transcendental functions. Using several novel polynomial-based table-driven techniques, we are able to provide new algorithms for the transcendental functions. Major improvements include an accuracy level of about 0.6 ulps (units in the last place) and forward trigonometric functions that have a period of 2π. The accuracy enhancements are achieved at improved speed, yet without an increase in the table size. In this paper, we highlight the key IA-64 architectural features that influenced our designs, and explain the main ideas used in our new algorithms
Keywords :
computer architecture; digital arithmetic; functions; mathematics computing; IA-64 architecture; accuracy; computation speed; forward trigonometric functions; polynomial-based table-driven techniques; table size; transcendental function algorithms; Application software; Approximation algorithms; Computer aided instruction; Computer architecture; Concurrent computing; Hardware; Iterative algorithms; Parallel processing; Parallel programming; Software quality;
Conference_Titel :
Computer Arithmetic, 1999. Proceedings. 14th IEEE Symposium on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7695-0116-8
DOI :
10.1109/ARITH.1999.762822