Hybrid Hexagonal/Classical Tiling for GPUs
Tobias Grosser, Albert Cohen, Justin Holewinski, Ponnuswamy Sadayappan, Sven Verdoolaege · 2014
Time-tiling is necessary for the efficient execution of iterative stencil computations. Classical hyper-rectangular tiles cannot be used due to the combination of backward and forward dependences along space dimensions. Existing techniques trade temporal data reuse for inefficiencies in other areas, such as load imbalance, redundant computations, or increased control flow overhead, therefore making it challenging for use with GPUs.