Runtime management of adaptive MPSoCs for graceful degradation

• DOI: 10.1145/2968455.2968517
• Publication Date: 2016-10-13T19:25:51Z
• Authors: Stavros Tzilis; Ioannis Sourdis; Vasileios Vasilikos; Dimitrios Rodopoulos; Dimitrios Soudris
• Keywords: Control reconfiguration; Heuristics; Adaptability; Response time

In this paper we propose optimization algorithms for the runtime management of gracefully degradable adaptive MP-SoCs. Assuring reliability all hardware components in a system becomes increasingly difficult. On top growing defect densities and rising complexity conventional testing, wear-out effects may reduce availability on-chip resources during lifetime. However, adaptability modern MPSoCs can provide means permanent fault tolerance graceful degradation via management. We have developed custom heuristics as well tailored existing techniques (simulated annealing genetic algorithm), to deliver fast efficient response unpredictable loss resources. emulated resulting manager on Intel Single-Chip Cloud Computer (SCC), an experimental chip multiprocessor by Labs. Comparison different terms solution quality time, scaling their time with size problem input, indicate that our are faster at least one order magnitude, but simulated algorithm more consistent dealing constraints allowed solutions, e.g. limited reconfiguration time. All scale well, since almost every case, grows sub-linearly respect input size.