sector mapping

   In this scheme the memory and cache are divided into blocks
   of 2^m bytes (the cache line size).  A sector consists of
   2^n consecutive blocks.

   When a block is cached, it is read into the correct position
   in any sector of the cache, given by discarding the bottom m
   address bits and taking the next n as the block number within
   the sector.

   That whole sector is then tagged with the remaining upper
   address bits and the other blocks in the sector are marked as
   invalid.  This scheme takes advantage of locality of reference
   to consecutive blocks and needs fewer tags thus reducing the
   cost of associative access to the tags.