Increasing multiprocessor lifetime by Youngest-First Round-Robin core gating patterns

Long-mission multiprocessor systems in which direct human intervention is impossible, like satellites in space, require special attention of their lifetime reliability. Relying on the well established power reduction techniques which are frequently used in multiprocessors - power and clock gating, as well as dynamic voltage and frequency scaling, we devise the Youngest-First Round-Robin (YFRR) core gating pattern to be used for reduction of aging effects i.e., lifetime extension of the system. The YFRR technique uses the information supplied by on-chip aging monitors placed in each multiprocessor core, in order to determine their relative age and construct the gating pattern. Furthermore, we introduce a simple analytical method based on theWeibul distribution in order to evaluate and estimate the lifetime reliability of multiprocessors that use core gating patterns. The analyses show an improvement of up to 32% when using the YFRR compared to a simple Round-Robin.

[1]  Bharadwaj Veeravalli,et al.  Aging-aware hardware-software task partitioning for reliable reconfigurable multiprocessor systems , 2013, 2013 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (CASES).

[2]  Luca Benini,et al.  Adaptive idleness distribution for non-uniform aging tolerance in MultiProcessor Systems-on-Chip , 2009, 2009 Design, Automation & Test in Europe Conference & Exhibition.

[3]  Qiang Xu,et al.  On Task Allocation and Scheduling for Lifetime Extension of Platform-Based MPSoC Designs , 2011, IEEE Transactions on Parallel and Distributed Systems.

[4]  Georges Gielen,et al.  Analog IC Reliability in Nanometer CMOS , 2013 .

[5]  Bharadwaj Veeravalli,et al.  Reliability-driven task mapping for lifetime extension of networks-on-chip based multiprocessor systems , 2013, 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[6]  Bharadwaj Veeravalli,et al.  Run-time mapping for reliable many-cores based on energy/performance trade-offs , 2013, 2013 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFTS).

[7]  Donald E. Thomas,et al.  A case for lifetime-aware task mapping in embedded chip multiprocessors , 2010, 2010 IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS).

[8]  Pradip Bose,et al.  The case for lifetime reliability-aware microprocessors , 2004, Proceedings. 31st Annual International Symposium on Computer Architecture, 2004..

[9]  Radu Marculescu,et al.  FARM: Fault-aware resource management in NoC-based multiprocessor platforms , 2011, 2011 Design, Automation & Test in Europe.

[10]  Amin Ansari,et al.  Maestro: Orchestrating Lifetime Reliability in Chip Multiprocessors , 2010, HiPEAC.

[11]  Rolf Kraemer,et al.  Low-complexity integrated circuit aging monitor , 2011, 14th IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems.