Social Applications
Networks
Knowledge Base
Support
|
C-Level Executives
Other Roles
|
Support
Education
Partner
Other Tasks
|
The floating-point environment on Oracle Sun SPARC and x86/x64 platforms enables you to develop robust, high-performance, portable numerical applications. The floating-point environment can also help investigate unusual behavior of numerical programs written by others. These systems implement the arithmetic model specified by IEEE Standard 754 for Binary Floating Point Arithmetic.
Sun Performance Library is a set of optimized, high-speed mathematical subroutines for solving linear algebra and other numerically intensive problems. Sun Performance Library is based on a collection of public domain library functions available from Netlib ( http://www.netlib.org ) that have been enchanced and optimized for high-performance platforms.
Sun Performance Library contains enhanced versions of the following standard libraries:
Sun Performance Library includes the following additional routines:
Reference Manuals
Using the Tuned Libraries for Peak Application Performance
This technical white paper discusses the Sun Performance Library (Perflib) component of Oracle Solaris Studio, and demonstrates how it can be used in applications to boost performance significantly via its highly optimized mathematical subroutines for SPARC® and x86 processor-based systems. (January 2011)
Interval Angles and the Fortran ATAN2 Function (pdf)
Issues that come up when working with interval angles or any periodic numbers, specifically how to rationalize the containment set (or cset) is for the ATAN2 Fortran intrinsic function for all possible interval arguments. (November 8, 2002)
Fast Fourier Transform (FFT) Routines
New FFT interfaces with Sun Performance Library. (November 8, 2002)
LIBMCR
Eight correctly-rounded double-precision transcendental functions from libm. LIBMCR is supplied as source code along with makefiles to build the library and tests to check basic functionality. Envisioned is its use as a reference base for Java Numerics projects or research into, and validation of correctly rounded transcendental functions.
You can download it now. (November 12, 2004)
What Every Computer Scientist Should Know About Floating-Point Arithmetic by David Goldberg
Originally published in the March, 1991 issue of Computing Surveys, Copyright 1991, Association for Computing Machinery, Inc., reprinted by permission.
Performance Analyzer and Tools Forum
Discuss the use and features of the Solaris Studio Performance Analyzer with other users.