Optimal queuing-based memory refreshing algorithm for energy efficient processors

The embedded memories of ultra-low power processors require periodic refreshing, which blocks the CPU-memory access and degrades performance. In addition, refreshing queues cause a drop in system performance not only when they are saturated but also when they are empty. We present an optimal queuing...

Full description

Saved in:
Bibliographic Details
Published inComputers & electrical engineering Vol. 71; pp. 505 - 514
Main Authors Herman, Roi, Frankel, Binyamin, Wimer, Shmuel
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier Ltd 01.10.2018
Elsevier BV
Subjects
Algorithms
Central processing units
CPUs
Dependence
Embedded memories
Embedded systems
Energy efficiency
Energy management
Finite capacity queue
Memory
Memory management
Microprocessors
Performance degradation
Power management
Processors
Queues
Queuing
Refreshing
Embedded memories
Queuing
Refreshing
Finite capacity queue
Online AccessGet full text

Cover

More Information
Summary:The embedded memories of ultra-low power processors require periodic refreshing, which blocks the CPU-memory access and degrades performance. In addition, refreshing queues cause a drop in system performance not only when they are saturated but also when they are empty. We present an optimal queuing-based opportunistic refreshing algorithm that eliminates performance loss. We analyze system performance dependence on queue capacity and memory size to derive a closed-form performance expression that provides clear guidelines for memory design implementation. Comparison of a hardware implementation in a RISC-V ultra-low power processor to ordinary periodic refreshing demonstrates the algorithm can provide a considerable performance speedup in a wide variety of real applications.
ISSN:0045-7906
1879-0755
DOI:10.1016/j.compeleceng.2018.07.057