More GPU Routines Now Available from Numerical Algorithms Group

(www.nag.com, www.nag.co.uk, www.nag-gc.com, www.nag-j.co.jp) Computer scientists, IT Managers, and other application developers who need speed, accuracy and portability for their Fortran code can now obtain the newest release of what is widely regarded as one of the best checking compilers — Fortran Builder 5.2 (www.nag.com/market/np/fortranbuilder) from the Numerical Algorithms Group (NAG). This release features a virtually complete implementation of the latest Fortran 2003 standard and an integrated development environment.

Malcolm Cohen, a NAG principal technical consultant and Editor of the ISO/IEC Fortran Standard comments, “Fortran users do not always consider that they ought not to depend on a single compiler, which may be set to sacrifice accuracy, standards-conformance and portability in exchange for speed. NAG’s Fortran Builder is probably the best checking compiler available. It is very exact in the interpretation of Fortran standards and incorporates cutting-edge run-time checking features including: procedure interface checking across multiple files; undefined variable trapping; memory leak detection; and more. Many report that their use of NAG Fortran Builder for maintaining standards, debugging and verification of their Fortran programs is invaluable, even if they also use another compiler”.

NAG Fortran Builder is for the Microsoft Windows® environment and provides a Fortran-aware editor, build system, GUI debugger and help system for Fortran. The NAG Fortran Compiler is also available for other platforms.

Key new NAG Fortran Compiler features include:

-More information, including line number, displayed in runtime messages

-More Fortran 2003 Features

-Quad precision real and complex

-I/O library multi-threaded for performance

-Improved RANDOM_NUMBER generator

A complete listing of NAG Fortran Builder features can be found at (www.nag.com/market/np/fortranbuilder )

Trials are available at (www.nag.com/market/trialrequest/NPW)

With origins in several UK universities, the Numerical Algorithms Group (NAG, www.nag.com) has its headquarters in Oxford, and is a not-for-profit organization that collaborates with world-leading researchers and practitioners in academia and industry. NAG serves its customers from offices in Oxford, Manchester, Chicago, Tokyo and Taipei, through field sales staff in France and Germany, as well as via a global network of distributors.