Replacement policies for shared caches on symmetric multicores : a programmer-centric point of view

The presence of shared caches in current multicore processors may generate a lot of performance variability when several applications execute simultaneously. For the programmer of an application with quality-of-service goals, this performance variability may lead to a very pessimistic tuning. To solve this problem, there must be a way for the programmer to define a reasonable performance target and make sure that the actual performance is greater than or close to the target. We propose that the performance target be defined as the performancemeasured when each core runs a copy of the application, which we call self-performance. This study characterizes self-performance and explains how the shared-cache replacement policy can be modified for self-performance to be meaningful