A compiler-microarchitecture hybrid approach to soft error reduction for register files

Authors:
Jongeun Lee;Aviral Shrivastava
Affiliations:
School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology, Ulsan, Korea;Department of Computer Science and Engineering, Arizona State University, Tempe, AZ
Venue:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Year:
2010

Citing 19
Cited 3

Improvements to graph coloring register allocation

ACM Transactions on Programming Languages and Systems (TOPLAS)
The SimpleScalar tool set, version 2.0

ACM SIGARCH Computer Architecture News
The MIPS R10000 Superscalar Microprocessor

IEEE Micro
IBM's S/390 G5 Microprocessor Design

IEEE Micro
Temperature-aware microarchitecture

Proceedings of the 30th annual international symposium on Computer architecture
A Systematic Methodology to Compute the Architectural Vulnerability Factors for a High-Performance Microprocessor

Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture
Robust System Design with Built-In Soft-Error Resilience

Computer
SWIFT: Software Implemented Fault Tolerance

Proceedings of the international symposium on Code generation and optimization
Engineering Over-Clocking: Reliability-Performance Trade-Offs for High-Performance Register Files

DSN '05 Proceedings of the 2005 International Conference on Dependable Systems and Networks
Compiler-guided register reliability improvement against soft errors

Proceedings of the 5th ACM international conference on Embedded software
MiBench: A free, commercially representative embedded benchmark suite

WWC '01 Proceedings of the Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop
Bypass aware instruction scheduling for register file power reduction

Proceedings of the 2006 ACM SIGPLAN/SIGBED conference on Language, compilers, and tool support for embedded systems
Cost-efficient soft error protection for embedded microprocessors

CASES '06 Proceedings of the 2006 international conference on Compilers, architecture and synthesis for embedded systems
Fault-Tolerant Systems

Fault-Tolerant Systems
An Area-Efficient Approach to Improving Register File Reliability against Transient Errors

AINAW '07 Proceedings of the 21st International Conference on Advanced Information Networking and Applications Workshops - Volume 01
Using Register Lifetime Predictions to Protect Register Files against Soft Errors

DSN '07 Proceedings of the 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
Compiler-managed register file protection for energy-efficient soft error reduction

Proceedings of the 2009 Asia and South Pacific Design Automation Conference
A compiler optimization to reduce soft errors in register files

Proceedings of the 2009 ACM SIGPLAN/SIGBED conference on Languages, compilers, and tools for embedded systems
Static analysis to mitigate soft errors in register files

Proceedings of the Conference on Design, Automation and Test in Europe

Detailed Analysis of Compilation Options for Robust Software-based Embedded Systems

Journal of Electronic Testing: Theory and Applications
Software-based register file vulnerability reduction for embedded processors

ACM Transactions on Embedded Computing Systems (TECS) - Special Section on ESTIMedia'10
Selective SWIFT-R

Journal of Electronic Testing: Theory and Applications

Quantified Score

Hi-index	0.03

Visualization

Abstract

For embedded systems, where neither energy nor reliability can be easily sacrificed, this paper presents an energy efficient soft error protection scheme for register files (RFs). Unlike previous approaches, the proposed method explicitly optimizes for energy efficiency and can exploit the fundamental tradeoff between reliability and energy. While even simple compiler-managed RF protection scheme can be more energy efficient than hardware schemes, this paper formulates and solves further compiler optimization problems to significantly enhance the energy efficiency of RF protection schemes by an additional 30 % on average, as demonstrated in our experiments on a number of embedded application benchmarks.