A novel implementation of tile-based address mapping

Tile-based data layout has been applied to achieve various objectives such as minimizing cache conflicts and memory row switching activity. In some applications of tile-based mapping, the size of the tile can be assumed to be a power of two. In this paper, this ´power of two´ assumption has been used to drastically simplify the tile-based address mapping functions. Once optimized, the implementation of the non-linear tile-based mapping consumes 60% less power than the implementation of the linear row-major mapping. This result is very interesting because one would normally expect a power penalty in the address generation stage of the more sophisticated tile-based mapping. Moreover, on average tile-based mapping implementation takes 10% less area and incurs virtually no additional delay over row-major mapping implementation.