CSAR Bulletin issued in September 2005

LAPACK and ScaLAPACK Survey

The authors of the LAPACK and ScaLAPACK dense and banded linear algebra libraries are seeking opinions on the software. A new release of both libraries is planned for 2007. The survey will help the developers to prioritise improvements to LAPACK and ScaLAPACK, and suggest possible additions.

Have your say at:

http://icl.cs.utk.edu/lapack-forum/survey/

Floating Point Performance Issues on Itanium 2 Processors

The Itanium 2 processor is capable of delivering 2 floating point multiply-adds per clock cycle, delivering a peak performance of 6 GFlops (on the 1.5GHz processors). In many codes this figure is not achievable as getting data to the processor cannot be done quickly enough. A further complication can also slow the performance down by a more significant amount (several orders of magnitude) if left untreated and that is operations on denormal numbers.

Denormal numbers, also called subnormal or underflow numbers, are defined in the IEEE standard for floating point as those below the normal range (below the figure returned by the Fortran intrinsic TINY). Operations involving these numbers cannot be performed on the processor and need to be performed by the operating system and there is a huge penalty in doing this.

Further information on denormal numbers, their effects, and how to find and reduce the impact of them are available at the following web page:

http://www.csar.cfs.ac.uk/services/hardware/local_newton_config/floating_point.shtml