Understanding and Analyzing the Impact of Memory Controller's Scheduling Policies on DRAM's Energy and Performance

Abstract In current scenario while designing a computing system it is necessary that detailed emphasis should be laid on two common goals, i.e ., increasing performance and decreasing power consumption. As we needto achieve either more performance at same power level or minimum power consumption for same performance level. Main memory of a system is one of the key resources that a program needs to run hence it acts as a major contributor towards both system's performance and power consumption. Main memory's performance depends on the way it accesses its contents. It is memory controller's access scheduler that decides which command to issue in every DRAM clock cycle on the basis of employed memory access scheduling policy. Based on underlying access strategy DRAM operations are scheduled in a way that it reduces DRAM's latency and power consumption by utilizing low power modes. In this paper, we have compared and analysedvarious memory access scheduling algorithms on the basis ofpage hit rate, energy-delay product, total execution time and maximum slowdown time. This analysis contributes to better understand how the performance and energy consumption of DRAM memory system is affected by the underlying memory controller's scheduling policies.

[1]  Tao Li,et al.  Informed Microarchitecture Design Space Exploration Using Workload Dynamics , 2007, 40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007).

[2]  William J. Dally,et al.  Memory access scheduling , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[3]  Goran Narancic,et al.  A Preliminary Exploration of Memory Controller Policies on Smartphone Workloads , 2012 .

[4]  Mor Harchol-Balter,et al.  Thread Cluster Memory Scheduling: Exploiting Differences in Memory Access Behavior , 2010, 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture.

[5]  M. Horowitz,et al.  Energy dissipation in general purpose processors , 1995, 1995 IEEE Symposium on Low Power Electronics. Digest of Technical Papers.

[6]  Carla Schlatter Ellis,et al.  Memory controller policies for DRAM power management , 2001, ISLPED '01.

[7]  Onur Mutlu,et al.  Stall-Time Fair Memory Access Scheduling for Chip Multiprocessors , 2007, 40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007).

[8]  Engin Ipek,et al.  PARDIS: a programmable memory controller for the DDRx interfacing standards , 2012, ISCA '12.

[9]  Thomas Vogelsang,et al.  Understanding the Energy Consumption of Dynamic Random Access Memories , 2010, 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture.

[10]  Michael A. Bender,et al.  Flow and stretch metrics for scheduling continuous job streams , 1998, SODA '98.

[11]  Onur Mutlu,et al.  Parallelism-Aware Batch Scheduling: Enhancing both Performance and Fairness of Shared DRAM Systems , 2008, 2008 International Symposium on Computer Architecture.

[12]  Karthick Rajamani,et al.  Energy Management for Commercial Servers , 2003, Computer.

[13]  Kai Li,et al.  The PARSEC benchmark suite: Characterization and architectural implications , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[14]  Calvin Lin,et al.  A comprehensive approach to DRAM power management , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.