Dani , Aparna Mandke and Amrutur, Bharadwaj and Srikant, YN (2010) Applying Genetic Algorithms to Optimize Power in Tiled SNUCA Chip Multicore Architectures. UNSPECIFIED.
TR_CSA_2010-7.pdf - ["content_typename_completed" not defined]
Download (374Kb) | Preview
We propose a novel technique for reducing the power consumed by the on-chip cache in SNUCA chip multicore platform. This is achieved by what we call a "remap table", which maps accesses to the cache banks that are as close as possible to the cores, on which the processes are scheduled. With this technique, instead of using all the available cache, we use a portion of the cache and allocate lesser cache to the application. We formulate the problem as an energy-delay (ED) minimization problem and solve it offline using a scalable genetic algorithm approach. Our experiments show up to 40% of savings in the memory sub-system power consumption and 47% savings in energy-delay product (ED).
|Item Type:||Departmental Technical Report|
|Additional Information:||Copyright for this article belongs to the Authors|
|Department/Centre:||Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)|
|Date Deposited:||30 Jul 2012 05:03|
|Last Modified:||30 Jul 2012 05:03|
Actions (login required)