Response Time Bounds for Typed DAG Parallel Tasks on Heterogeneous Multi-Cores

Abstract

Heterogenerous multi-cores utilize the strength of different architectures for executing particular types of workload, and usually offer higher performance and energy efficiency. In this paper, we study the worst-case response time (WCRT) analysis of typed scheduling of parallel DAG tasks on heterogeneous multi-cores, where the workload of each vertex in the DAG is only allowed to execute on a particular type of cores. The only known WCRT bound for this problem is grossly pessimistic and suffers the non-self-sustainability problem. In this paper, we propose two new WCRT bounds. The first new bound has the same time complexity as the existing bound, but is more precise and solves its non-self-sustainability problem. The second new bound explores more detailed task graph structure information to greatly improve the precision, but is computationally more expensive. We prove that the problem of computing the second bound is strongly NP-hard if the number of types in the system is a variable, and develop an efficient algorithm which has polynomial time complexity if the number of types is a constant. Experiments with randomly generated workload show that our proposed new methods are significantly more precise than the existing bound while having good scalability.

Comparative Study of Heterogeneous Multicore Scheduling Algorithms on Media Codecs

“…In Han et al [2], the authors have improved upon the WCRT bounds set by [1]. Instead of considering the entire task graph at each stage, the entire task graph is broken into paths from the source to the sink and the response time for each path is calculated.…”

“…Finally, in Chang et al [3], the authors have taken into account the arguments made regarding [2] and improved the scheduling bounds for heterogeneous multi core systems. It is our wish now to use these three.…”

Improved Multi-Core Real-Time Task Scheduling of Reconfigurable Systems With Energy Constraints

“…In the case where task T s i is executed before T s j , (14) keeps (12) valid. In fact, in this case, we have α ij = 1 and subsequently t sjkp − t sikp ≤ 0.…”

Bounding the execution time of parallel applications on unrelated multiprocessors

“…Related works on scheduling real-time systems that consider the unrelated multiprocessor model have mainly focused on independent tasks (Andersson and Raravi 2014;Chwa et al 2015;Andersson and Raravi 2016;Baruah et al 2019) with no dependencies and typed DAGs (Yang et al 2016;Han et al 2019). Earlier works that consider a DAG as the application model have focused mainly on the related multiprocessor model (Bender and Rabin 2000;Jiang et al 2017).…”

“…To evaluate the proposed approaches, Fast, and Comb, we use real-world parallel applications from the BOTS benchmark suite (Duran et al 2002) as well as randomly generated synthetic DAGs. We also compare the proposed approaches to similar work in the literature for homogeneous (Graham 1969), related (Jiang et al 2017) multiprocessors, and typed DAGs (Han et al 2019) to demonstrate how much we pay for using more generalized models of the application, hardware, and the scheduler with respect to that of state-of-the-art. One of the major findings we have from this empirical study is that the makespan computed using the efficient Fast approach is very close to that computed using the Comb, i.e., our analysis using the polynomial-time approach does not significantly compromise the tightness of the computed makespan.…”