A low-power I-cache architecture is proposed that is appropriate for embedd
ed low-power processors, Unlike existing schemes, the proposed organisation
places an extra small cache in parallel alongside the L1 cache. Since it a
llows simultaneous accesses to both caches, the proposed scheme introduces
Little performance degradation. Using simple hardware logic (for sequential
accesses) and a compiler transformation (for loop accesses), most L1 cache
requests are served by a small each. so that the amount of energy consumed
by the L1 cache is significantly reduced. Experimental results show that f
or the SPEC95 benchmarks. the proposed organisation reduces the energy-dela
y product on average by 67.2% over a conventional cache design and 16.8% ov
er the filter cache design.