Mark Silberstein Assaf Schuster Dan Geiger Anjul Patney John D. Owens Efficient computation of sum-products on GPUs through software-managed cache. 309-318 2008 ICS http://doi.acm.org/10.1145/1375527.1375572 conf/ics/2008 db/conf/ics/ics2008.html#SilbersteinSGPO08