Synchronizing redundant cores in a dynamic DMR multicore architecture

Authors:
Amit Golander;Shlomo Weiss;Ronny Ronen
Affiliations:
Department of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel;Department of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel;Intel Israel, Haifa, Israel
Venue:
IEEE Transactions on Circuits and Systems II: Express Briefs
Year:
2009

Citing 9
Cited 0

Transient fault detection via simultaneous multithreading

Proceedings of the 27th annual international symposium on Computer architecture
Transient-fault recovery for chip multiprocessors

Proceedings of the 30th annual international symposium on Computer architecture
Fingerprinting: bounding soft-error detection latency and bandwidth

ASPLOS XI Proceedings of the 11th international conference on Architectural support for programming languages and operating systems
Interconnections in Multi-Core Architectures: Understanding Mechanisms, Overheads and Scaling

Proceedings of the 32nd annual international symposium on Computer Architecture
Utilizing Dynamically Coupled Cores to Form a Resilient Chip Multiprocessor

DSN '07 Proceedings of the 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
Perturbation-based Fault Screening

HPCA '07 Proceedings of the 2007 IEEE 13th International Symposium on High Performance Computer Architecture
Development of a Testbench for Validation of DMT and DT2 Fault-Tolerant Architectures on SOI PowerPC7448

IOLTS '08 Proceedings of the 2008 14th IEEE International On-Line Testing Symposium
DDMR: Dynamic and Scalable Dual Modular Redundancy with Short Validation Intervals

IEEE Computer Architecture Letters
Using Underutilized CPU Resources to Enhance Its Reliability

IEEE Transactions on Dependable and Secure Computing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We introduce the difficulties in processing context switches, exceptions, and interrupts in DMR architectures. We propose ways to address these problems in a dynamic DMR (DDMR) architecture, providing methods that assure both cores detect the event, synchronize it to the same instruction, perform a secure context switch, run correct interrupt service routines, and avoid process termination. DDMR uses a time-division multiplexing (TDM) ring architecture to dynamically connect pairs of cores. We enhance this protocol to include the different message types required to handle interrupts and exceptions. We also propose a more efficient address-based, rather than TDM-based, ring architecture.