Static statistical MPSoC power optimization by variation-aware task and communication scheduling

Yield‐driven design‐time task scheduling techniques for multi‐processor system on chips under process variation: a comparative study

“…This section tries to provide a brief overview of VAREX for being self-contained, yet the readers can refer to [13,14] for more details. Gaussian frequency distribution Singhal [3] performance yield SPDAG 2 NA, timing yields of cores are given Mirzoyan [4] performance yield SDFG 3 Discretised Gaussian frequency distribution Metaheuristic-based Algorithms Chon [5] performance yield DAG Discretised Gaussian frequency distribution Huang [6] performance yield DAG VARIUS [12], An approximative model to propagate variability in L eff and V th to the frequency of cores Momtazpour [7] power yield, performance yield wDAG Gaussian frequency distribution Momtazpour [8] power yield, performance yield wDAG an approximative model to propagate variability in L eff , V th and T ox to the frequency of cores ILP-based Algorithms Singhal [9] throughput, performance yield DAG NA, timing yields of cores are given Bhardwaj [10] power-performance yield DAG Gaussian frequency distribution Ghorbani [11] power yield, performance yield wDAG Gaussian frequency distribution 1 Weighted directed acyclic graph.…”

“…For our comparative study, we use five different approaches to solve the variation-aware MPSoC task and communication scheduling problem: (i) An ILP-based task scheduling method, previously proposed in [11] to find the optimal solution, (ii) a fast heuristic task scheduling technique, previously used in [2] to find a reasonable local solution efficiently, (iii) another heuristic method that is proposed in this work and is inspired from the work in [2], (iv) a GA-based task scheduling technique [7] and (v) an SA-based task scheduling technique [8]. This section provides a brief overview of the mentioned approaches, as well as minor modifications applied to them to provide fair comparison.…”

“…In this paper, we use previously proposed GA-based [7] and SA-based [8] techniques to solve variation-aware task and communication scheduling problem. This section briefly reviews the mentioned methods for being self-contained.…”

“…Recently, Huang et al [6] presented a quasi‐static SA‐based task scheduling method that is followed by a clustering‐based performance yield enhancement procedure. In our previous work [7, 8], we presented GA‐based and SA‐based variation‐aware task and communication scheduling algorithms for power yield maximisation under performance yield constraint.…”

Variation-aware Server Placement and Task Assignment for Data Center Power Minimization

“…Such variation effects are visible in today processors and are expected to further rise with technology scaling when further approaching atomic scales. Process variation effects are already studied in highperformance multiprocessor and embedded systems [11], [12], [13], but to the best of our knowledge such effects have not been previously considered at data center scales.…”