Enhancing L2 organization for CMPs with a center cell
Chun Liu, Anand Sivasubramaniam, Mahmut Kandemir, M.J. Irwin · 2006
Chip multiprocessors (CMPs) are becoming a popular way of exploiting ever-increasing number of on-chip tran-sistors. At the same time, the location of data on the chip can play a critical role in the performance of these CMPs because of the growing on-chip storage capacities and the relative cost of wire delays. It is important to locate the data at the right place at the right time in the on-chip cache hi-erarchy. This paper presents a novel L2 cache organization for CMPs with these goals in mind. We first study the data sharing characteristics of a wide spectrum of multi-threaded applications and show that, while there are a considerable number of L2 accesses to shared data, the volume of this data is relatively low. Con-sequently, it is important to keep this shared data fairly close to all processor cores for both performance and power rea-sons. Motivated by this observation, we propose a small Center Cell cache residing in the middle of the processor cores which provides fast access to its contents. We demon-strate that this cache organization can considerably lower the number of block migrations between the L2 portions that are closer to each core, thus providing better performance and power. 1