Emerging data-intensive applications are creating non-uniform CPU and I/O workloads which impose the requirement to consider both CPU and I/O effects in the power management strategies. Current approaches focus on scaling down the CPU frequency based on CPU busy/idle ratio without taking I/O into consideration. Therefore, they do not fully exploit the opportunities in power conservation. In this paper, we propose a novel power management scheme called model-free, adaptive, rule-based (MAR) in multiprocessor systems to minimize the CPU power consumption subject to performance constraints. By introducing new I/O wait status, MAR is able to accurately describe the relationship between core frequencies, performance and power consumption. Moreover, we adopt a model-free control method to filter out the I/O wait status from the traditional CPU busy/idle model in order to achieve fast responsiveness to burst situations and take full advantage of power saving. Our extensive experiments on a physical testbed demonstrate that, for SPEC benchmarks and data-intensive (TPC-C) benchmarks, an MAR prototype system achieves 95.8-97.8 percent accuracy of the ideal power saving strategy calculated offline. Compared with baseline solutions, MAR is able to save 12.3-16.1 percent more power while maintain a comparable performance loss of about 0.78-1.08 percent. In addition, more simulation results indicate that our design achieved 3.35-14.2 percent more power saving efficiency and 4.2-10.7 percent less performance loss under various CMP configurations as compared with various baseline approaches such as LAST, Relax, PID and MPC.

Providing accurate branch prediction is critical to exploit instruction level parallelism effectively. This paper shows that applying evolutionary programming in the hybrid branch prediction method using Switch-Counter can improve branch classification, thus increase branch prediction accuracy. In our study, various EP strategies and algorithms are applied to search the optimum branch classification. Using trace-driven simulation on SPEC2000, SPEC95, and MediaBench benchmarks, we measured the branch prediction accuracy of the hybrid prediction method using Switch-Counter both applying EP and without applying EP. The empirical results show that EP could gain impressive improvements of the branch classification so that the hybrid method achieved higher prediction accuracy comparing with that without EP. The contributions for the improvements by various genetic operators are evaluated as well. The empirical results also show that the EP algorithm applied in branch classification converges fairly fast. This limits the increase of compilation time. The attempt at applying EP to improve branch classification is an innovation in branch prediction. The results are quite encouraging.