Reevaluating Amdahl’s law in the multicore era

Sun, Xian-He; Chen, Yong

doi:10.1016/j.jpdc.2009.05.002

Cited by 148 publications

(69 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed approximation dependence of scheduled tasks and time of the runtime scheduling algorithm t scd see (6), describes this dependence well. Approximation proposal does not address the limitations resulting from Amdahl's law [4]. Segmentation into three separate objects priority precedence and optimization has led to simplify the design of the scheduler.…”

Section: Resultsmentioning

confidence: 99%

An Optimization Scheduler in the Intranet Grid

Lukasik

Sysel

2016

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. Scheduling of processes is the basic task for a grid computing. This role is responsible for the allocation of time for computational agents. The calculation agent can include a wide range of devices, based on various types of computer systems. Is it possible to efficiently build a grid infrastructure in the company environment. The grid can be used in scientific and technical computing, as well as better load distribution of the individual computing systems and services. The scheduler is a major component of grid computing. The main task is to effectively distribute the load of the system and allocate tasks to places that are not sufficiently utilized at a given moment. The article also focuses on the relation between conflicting parameters, which relate to the quality of the planning process. Time calculation of the optimization algorithm affects the quality of the draft plan. It has a direct impact on the total period of the job processing. In the strategy of the scheduling there is a point where extensions of time have no effect on quality of the draft of the plan but getting worse the overall runtime of the job. The aim was to compare the common metaheuristic algorithms. From the measured values to propose a methodology for determining the optimum time for planning process

show abstract

Section: Resultsmentioning

confidence: 99%

An Optimization Scheduler in the Intranet Grid

Lukasik

Sysel

2016

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…In the job estimation step, the execution time of a job can be estimated based on a predefined function, according to Amdahl's Law [SC10], by analyzing the historical statistical parameters of previous execution of jobs or using machine learning algorithms [JCM + 16]. A machine learning algorithm learns from experience E with respect to some class of tasks T and performance measure P while its performance at tasks in T , as measured by P , improves with experience E [Mit97].…”

Section: Job Executionmentioning

confidence: 99%

A survey of scheduling frameworks in big data systems

Liu

Pacitti

Valduriez

2018

IJCC

View full text Add to dashboard Cite

Cloud and big data technologies are now converging to enable organizations to outsource data in the cloud and get value from data through big data analytics. Big data systems typically exploit computer clusters to gain scalability and obtain a good cost-performance ratio. However, scheduling a workload in a computer cluster remains a well-known open problem. Scheduling methods are typically implemented in a scheduling framework and may have different objectives. In this paper, we survey scheduling methods and frameworks for big data systems, propose a taxonomy and analyze the features of the different categories of scheduling frameworks. These frameworks have been designed initially for the cloud (MapReduce) to process Web data. We examine sixteen popular scheduling frameworks and discuss their features. Our study shows that different frameworks are proposed for different big data systems, different scales of computer clusters and different objectives. We propose the main dimensions for workloads and metrics for benchmarks to evaluate these scheduling frameworks. Finally, we analyze their limitations and propose new research directions.

show abstract

“…Sun and Chen [13] showed that multicore architectures are not limited properly by Amdahl's predictions, but a real drawback would be the disparity of technology improvements between CPU speed and memory latency. Thus, they conclude that there are not significant limitations in scalability in number of cores, but more research is needed to overcome memory limitations.…”

Section: Related Workmentioning

confidence: 99%

Energy consumption model over parallel programs implemented on multicore architectures

Isidro-Ramirez¹,

Viveros²,

Hernández-Rubio³

2015

ijacsa

View full text Add to dashboard Cite

Abstract-In High Performance Computing, energy consumption is becoming an important aspect to consider. Due to the high costs that represent energy production in all countries it holds an important role and it seek to find ways to save energy. It is reflected in some efforts to reduce the energy requirements of hardware components and applications. Some options have been appearing in order to scale down energy use and, consequently, scale up energy efficiency. One of these strategies is the multithread programming paradigm, whose purpose is to produce parallel programs able to use the full amount of computing resources available in a microprocessor. That energy saving strategy focuses on efficient use of multicore processors that are found in various computing devices, like mobile devices. Actually, as a growing trend, multicore processors are found as part of various specific purpose computers since 2003, from High Performance Computing servers to mobile devices. However, it is not clear how multiprogramming affects energy efficiency. This paper presents an analysis of different types of multicorebased architectures used in computing, and then a valid model is presented. Based on Amdahl's Law, a model that considers different scenarios of energy use in multicore architectures it is proposed. Some interesting results were found from experiments with the developed algorithm, that it was execute of a parallel and sequential way. A lower limit of energy consumption was found in a type of multicore architecture and this behavior was observed experimentally.

show abstract

Reevaluating Amdahl’s law in the multicore era

Cited by 148 publications

References 8 publications

An Optimization Scheduler in the Intranet Grid

An Optimization Scheduler in the Intranet Grid

A survey of scheduling frameworks in big data systems

Energy consumption model over parallel programs implemented on multicore architectures

Contact Info

Product

Resources

About