A new paper from IIT Hyderabad in India surveys cache partitioning techniques for multicore processors. Now accepted in ACM Computing Surveys 2017, the survey by Sparsh Mittal reviews 90 papers.
As the number of on-chip cores and memory demands of applications increase, judicious management of cache resources has become imperative. Cache partitioning is a promising approach to provide capacity benefits of shared cache with performance isolation of private caches. This paper reviews various cache partitioning techniques, e.g., strict/psuedo, static/dynamic, hardware/software-based, block/set/way-based, for improving performance/fairness/load-balancing/QoS, etc. Also, the paper reviews integration of cache partitioning with other management techniques, e.g., processor/DRAM/bandwidth partitioning, DVFS, etc.