Dan Wallin Henrik Löf Erik Hagersten Sverker Holmgren Multigrid and Gauss-Seidel smoothers revisited: parallelization on chip multiprocessors. 145-155 2006 conf/ics/2006 ICS http://doi.acm.org/10.1145/1183401.1183423 db/conf/ics/ics2006.html#WallinLHH06