OON: Matrix Template Library Version 2.1

From: Andrew Lumsdaine (lums@lsc.nd.edu)
Date: Sat Mar 13 1999 - 23:34:53 EST


The Lab for Scientific Computing (LSC) at the University of Notre Dame
announces the initial public release of the Matrix Template
Library (MTL), a library of generic components for high performance
numerical linear algebra.

The Matrix Template Library is:

Generic:
  MTL uses the generic programming paradigm to allow algorithms to be
  expressed in a data-format-independent manner. Generic programming
  techniques are also used to characterize and express MTL's
  performance optimizations.

Orthogonal and Comprehensive:
  MTL includes a large number of data formats and algorithms,
  including most popular sparse and dense matrix formats and
  functionality equivalent to BLAS level 3.

Flexible and Extensible:
  The MTL generic programming interface is designed to allow new
  functionality to be easily incorporated.

High Performance:
  MTL provides performance equal to (and in many cases better than)
  vendor-tuned math libraries.

Portable:
  MTL is written entirely in ANSI C++ and can be compiled and used on
  any target platform with an ANSI C++ compiler. No external
  libraries are required.

Reliable:
  MTL is extensively tested on a nightly basis. Over 350,000
  separate tests are conducted for each supported configuration.
  A scoreboard of test results is mainrained on the MTL web site.

MTL source code and documentation is available from

  http://www.lsc.nd.edu/research/mtl/



This archive was generated by hypermail 2b29 : Wed Feb 20 2002 - 03:20:08 EST