Resource Sharing Centric Dynamic Voltage and Frequency Scaling for CMP Cores, Uncore, and Memory Academic Article uri icon

abstract

  • With the breakdown of Dennards scaling over the past decade, performance growth of modern microprocessor design has largely relied on scaling core count in chip multiprocessors (CMPs). The challenge of chip power density, however, remains and demands new power management solutions. This work investigates a coordinated CMP systemwide Dynamic Voltage and Frequency Scaling (DVFS) policy centered around shared resource utilization. This approach represents a new angle on the problem, differing from the conventional core-workload-driven approaches. The key component of our work is per-core DVFS leveraging a technique similar to TCP Vegas congestion control from networking. This TCP Vegasbased DVFS can potentially identify the synergy between power reduction and performance improvement. Further, this work includes uncore (on-chip interconnect and shared last level cache) and main memory DVFS policies coordinated with the per-core DVFS policy. Full system simulations on PARSEC benchmarks show that our technique reduces total energy dissipation by over 47% across all benchmarks with less than 2.3% performance degradation. Our work also leads to 12% more energy savings compared to a prior work CMP DVFS policy.

published proceedings

  • ACM Transactions on Design Automation of Electronic Systems

author list (cited authors)

  • Won, J., Gratz, P. V., Shakkottai, S., & Hu, J.

citation count

  • 2

complete list of authors

  • Won, Jae-Yeon||Gratz, Paul V||Shakkottai, Srinivas||Hu, Jiang

publication date

  • September 2016