4 October 2018 in IEEE Access
Energy saving and system reliability are two crucial issues for designing modern multiprocessor systems. There has been reliability-aware power management with dynamic voltage–frequency scaling (DVFS) schemes in recent studies. However, they are limited to optimization under the impact of DVFS on energy and reliability and have not considered reducing the non-negligible leakage energy consumption. In this paper, we focus on co-management of system reliability and total energy for applications with precedence constrained tasks on heterogeneous multiprocessor real-time systems. We first investigate the impact of energy management techniques on both reliability and energy of the systems using task recovery for fault tolerance and then propose an Energy-efficient Fault-tolerant Scheduling (EFS) scheme integrated with power mode management, which can mitigate the negative impact of DVFS on system reliability. To obtain the optimal energy-efficient reliability-guaranteed scheduling for pre-mapped applications on systems considering various realistic issues, we build mixed integer linear programing formulations with the proposed EFS scheme. To address mapping and scheduling for energy-efficiency and fault-tolerance, we finally develop a framework implemented by a List-based Binary Particle Swarm Optimization algorithm. The extensive comparative evaluations for synthetic and realistic benchmarks show that our approaches outperform several related studies in terms of energy consumption and system reliability.
25 July 2018 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Task mapping has been a hot topic in MPSoC software design for decades. During the mapping process, load balance and communication optimization have been two important performance optimization factors. This paper studies the relations between load balance, inter-processor communications and communication pipeline technique during the mapping process, and proposes an Integer Linear Programming (ILP)-based static task mapping approach, which considers both load balance and communication optimization. The approach consists of an optimized ILP model for task mapping with fewer variables compared to previous ILP mapping works. Moreover, to enhance the scalability of the ILP task mapping, the Task-Processor-Cluster (TP-CLUSTER) algorithm is proposed to reduce the scale of the task graph and the number of processors and then solve the coarse-grained input by the ILP mapping. To increase the adaptability of the ILP task mapping, the improved augmented ε-constraint (AUGMECON2) method is further integrated with the ILP formulations to select the best mapping for different applications. Experimental results on a 2/4/8/16/24-CPU platform of both synthetic and real-life benchmarks demonstrate the efficiency of the proposed approach.
6 July 2018 in IEEE Transactions on Sustainable Computing
Energy optimization plays an increasingly critical role in designing an embedded real-time multiprocessor System on Chip (MPSoC). Dynamic Voltage Frequency Scaling (DVFS) and Dynamic Power Management (DPM) are preferable techniques to optimize energy consumption. However, previous DVFS and DPM algorithms were mostly designed for inter-task scheduling, without sufficient exploration on intra-task scheduling for further energy reduction. This paper presents a new intra-task scheduling approach considering the probabilistic distribution of task execution time, and it optimizes the mathematical expectation of power consumption (expected power consumption) for periodic dependent tasks with uncertain execution time running on MPSoCs using DVFS and DPM. The energy-efficient scheduling problem can be formulated by means of mixed integer linear programming (MILP) with the proposed technique. Moreover, we also propose a technique to compress the exploration space by reorganizing the probabilistic profiling information of all tasks. Our experimental results on synthetic and realistic benchmarks show that the proposed approach achieves up to 30% energy savings compared with other existing methods.
7 March 2018 in IEEE Access
Fine-grained multithreaded models can provide more opportunities for system performance improvements, but they face large amount of communication overhead. To reduce the communication overhead to improve performance, message aggregation and communication pipeline have been proposed and their advantages have been discussed in previous works. However, when exploiting them in reallife applications, it is challenging to maximize their advantages due to their unrevealed problems. This paper investigates the two communication optimization techniques from the view of their problems to fulfill the studies. We have found that when applying the techniques, message aggregation may have the deadlock problem and latency problem, and communication pipeline may face the ineffective problem and prolog and epilog problem. Based on the basic requirement of allocating the two techniques on an initial schedule, we then present general solutions to avoid or handle the problems. To obtain a minimum schedule length for an initial schedule, we further develop a Binary Particle Swarm Optimization (BPSO)- based fine-grained communication optimization method (BFCO) to allocate message aggregation and communication pipeline for best performance. The method is also integrated into Light and Efficient Simulink Compiler for Embedded Application (LESCEA) multithreaded code generator to generate high quality codes. Experimental results on both synthetic and real-life applications demonstrate the efficiency of the proposed method.
16 April 2019 in IEEE Access