Optimal Co-Scheduling to Minimize Makespan on Chip Multiprocessors

Tian, Kai; Jiang, Yunlian; Shen, Xipeng; Mao, Weizhen

doi:10.1007/978-3-642-35867-8_7

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has been extensively studied for cache-sharing in multi-processor platforms. Theoretical studies show that the problem is NP-Complete and can be solved only for very simple architectures (Tian et al, 2013). Moreover, scheduling policies may be so diverse that the optimization criteria would be different (e.g.…”

Section: Discussionmentioning

confidence: 99%

Composing multiple StarPU applications over heterogeneous machines: A supervised approach

Hugo

Guermouche

Wacrenier

et al. 2014

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

Enabling HPC applications to perform efficiently when invoking multiple parallel libraries simultaneously is a great challenge. Even if a uniform runtime system is used underneath, scheduling tasks or threads coming from different libraries over the same set of hardware resources introduces many issues, such as resource oversubscription, undesirable cache flushes or memory bus contention. This paper presents an extension of StarPU, a runtime system specifically designed for heterogeneous architectures, that allows multiple parallel codes to run concurrently with minimal interference. Such parallel codes run within scheduling contexts that provide confined execution environments which can be used to partition computing resources. Scheduling contexts can be dynamically resized to optimize the allocation of computing resources among concurrently running libraries. We introduce a hypervisor that automatically expands or shrinks contexts using feedback from the runtime system (e.g. resource utilization). We demonstrate the relevance of our approach using benchmarks invoking multiple high performance linear algebra kernels simultaneously on top of heterogeneous multicore machines. We show that our mechanism can dramatically improve the overall application run time (-34%), most notably by reducing the average cache miss ratio (-50%).

show abstract

Section: Discussionmentioning

confidence: 99%

Composing multiple StarPU applications over heterogeneous machines: A supervised approach

Hugo

Guermouche

Wacrenier

et al. 2014

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

show abstract

“…[1], [3], [8], [9], [17], [21], [22], [25], [28], [40]. Tian et al [35] studied the theoretical problem of finding optimal job-to-core assigments for minimizing makespan, assuming a number of jobs equal to the total number of cores (i.e., as shortest jobs complete, some cores are left idle).…”

Section: Heterogeneous Multiprocessorsmentioning

confidence: 99%

Revisiting symbiotic job scheduling

Eyerman¹,

Michaud²,

Rogiest³

2015

2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)

View full text Add to dashboard Cite

Symbiotic job scheduling exploits the fact that in a system with shared resources, the performance of jobs is impacted by the behavior of other co-running jobs. By coscheduling combinations of jobs that have low interference, the performance of a system can be increased. In this paper, we investigate the impact of using symbiotic job scheduling for increasing throughput. We find that even for a theoretically optimal scheduler, this impact is very low, despite the substantial sensitivity of per job performance to which other jobs are coscheduled: for example, our experiments on a 4-thread SMT processor show that, on average, the job IPC varies by 37% depending on coscheduled jobs, the per-coschedule throughput varies by 69%, and yet the average throughput gain brought by optimal symbiotic scheduling is only 3%. This small margin of improvement can be explained by the observation that all the jobs need to be eventually executed, restricting the job combinations a symbiotic job scheduler can select to optimize throughput. We explain why previous work reported a substantial gain from symbiotic job scheduling, and we find that (only) reporting turnaround time can lead to misleading conclusions. Furthermore, we show how the impact of scheduling can be evaluated in microarchitectural studies, without having to implement a scheduler.

show abstract

“…The execution time of a thread varies depending on which threads are running on other cores of the same chip, because different thread combinations result in different levels of cache contention. In [16], the cache on each of m chips is shared by u cores on the each chip. The execution speed of a job running on a chip depends on what jobs are placed on the same chip.…”

Section: Introductionmentioning

confidence: 99%

Multi-Core Processor Scheduling with Respect to Data Bus Bandwidth

Eremeev¹,

Malakhov²,

Sakhno³

et al. 2020

Preprint

View full text Add to dashboard Cite

The paper considers the problem of scheduling software modules on a multi-core processor, taking into account the limited bandwidth of the data bus and the precedence constraints. Two problem formulations with different levels of problem-specific detail are suggested and both shown to be NP-hard. A mixed integer linear programming (MILP) model is proposed for the first problem formulation, and a greedy algorithm is developed for the second one. An experimental comparison of the results of the greedy algorithm and the MILP solutions found by CPLEX solver is carried out.

show abstract

Optimal Co-Scheduling to Minimize Makespan on Chip Multiprocessors

Cited by 4 publications

References 21 publications

Composing multiple StarPU applications over heterogeneous machines: A supervised approach

Composing multiple StarPU applications over heterogeneous machines: A supervised approach

Revisiting symbiotic job scheduling

Multi-Core Processor Scheduling with Respect to Data Bus Bandwidth

Contact Info

Product

Resources

About