Qing Yi Ken Kennedy Haihang You Keith Seymour Jack Dongarra Automatic blocking of QR and LU factorizations for locality. 12-22 2004 conf/ACMmsp/2004 Memory System Performance http://doi.acm.org/10.1145/1065895.1065898 db/conf/ACMmsp/msp2004.html#YiKYSD04