Proceedings of the 24th annual international symposium on Computer architecture
Dual use of superscalar datapath for transient-fault detection and recovery
Proceedings of the 34th annual ACM/IEEE international symposium on Microarchitecture
Increasing Instruction-Level Parallelism with Instruction Precomputation (Research Note)
Euro-Par '02 Proceedings of the 8th International Euro-Par Conference on Parallel Processing
A study of time redundant fault tolerance techniques for superscalar processors
DFT '95 Proceedings of the IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems
Proceedings of the 31st annual international symposium on Computer architecture
Instruction Precomputation for Fault Detection
DSD '09 Proceedings of the 2009 12th Euromicro Conference on Digital System Design, Architectures, Methods and Tools
Dynamic code duplication with vulnerability awareness for soft error detection on VLIW architectures
ACM Transactions on Architecture and Code Optimization (TACO) - Special Issue on High-Performance Embedded Architectures and Compilers
| Hi-index | 0.00 |
Fault tolerance (FT) has become a major concern in computing systems. Instruction duplication has been proposed to verify application execution at run time. Two techniques, instruction memoization and precomputation, have been shown to improve the performance and fault coverage of duplication. This work shows that the combination of these two techniques is much more powerful than either one in isolation. In addition to performance, it improves the long-lasting transient and permanent fault coverage upon the memoization scheme. Compared to the precomputation scheme, it reduces the long-lasting transient and permanent fault coverage of 10.6% of the instructions, but covers 2.6 times as many instructions against shorter transient faults. On a system with 2 integer ALUs, the combined scheme reduces the performance degradation due to duplication by on average 27.3% and 22.2% compared to the precomputation and memoization-based techniques, respectively, with similar hardware requirements.