The Computation of Transcendental Functions on the IA-64 Architecture

John Harrison, Ted Kubaska, Shane Story and Peter Tang.

Intel Technology Journal, Q4 1999.

Abstract:

The fast and accurate evaluation of transcendental functions (e.g. exp, log, sin, and atan) is vitally important in many fields of scientific computing. Intel provides a software library of these functions that can be called from both the C and FORTRAN programming languages. By exploiting some of the key features of the IA-64 floating-point architecture, we have been able to provide double-precision transcendental functions that are highly accurate yet can typically be evaluated in between 50 and 70 clock cycles. In this paper, we discuss some of the design principles and implementation details of these functions.

PDF or HTML

Bibtex entry:

@INPROCEEDINGS{harrison-itj,
        author          = "John Harrison and Ted Kubaska and
                           Shane Story and Peter Tang",
        title           = "The Computation of Transcendental Functions on the
                           {IA-64} Architecture",
        journal         = "Intel Technology Journal",
        volume          = "1999 Q4",
        year            = 1999,
        note            = "Available on the Web from
                           {\tt http://developer.intel.com/technology/itj/}"}