Jeffrey R. Diamond Behnam Robatmili Stephen W. Keckler Robert A. van de Geijn Kazushige Goto Doug Burger High performance dense linear algebra on a spatially distributed processor. 63-72 2008 PPOPP http://doi.acm.org/10.1145/1345206.1345218 conf/ppopp/2008 db/conf/ppopp/ppopp2008.html#DiamondRKGGB08