Loading...
Search for:
multitasking
0.004 seconds
Total 34 records
NURA: A framework for supporting non-uniform resource accesses in GPUs
, Article Performance Evaluation Review ; Volume 50, Issue 1 , 2022 , Pages 39-40 ; 01635999 (ISSN) ; Mahani, N ; Baxishi, H ; Yousefzadeh, E ; Sadrosadati, M ; Sarbazi Azad, H ; Sharif University of Technology
Association for Computing Machinery
2022
Abstract
Multi-application execution in Graphics Processing Units (GPUs), a promising way to utilize GPU resources, is still challenging. Some pieces of prior work (e.g. spatial multitasking) have limited opportunity to improve resource utilization, while others, e.g. simultaneous multi-kernel, provide fine-grained resource sharing at the price of unfair execution. This paper proposes a new multi-application paradigm for GPUs, called NURA, that provides high potential to improve resource utilization and ensure fairness and Quality-of-Service(QoS). The key idea is that each streaming multiprocessor (SM) executes the Cooperative Thread Arrays (CTAs) that belong to only one application (similar to...
Modeling of HV Substation Automation Systems and Evaluating of Operation Failure
, M.Sc. Thesis Sharif University of Technology ; Vakilian, Mehdi (Supervisor)
Abstract
In two past decades, a revolution has occurred by emerging of substation automation system in field of substation control and protection system. The traditional control system has changed to the modern automation systems which are based on computer networks. The development of this project become possible by having experience in and being familiar with automation systems, studying equipment specifications, tasks, and criteria and analyzing operation of various systems. The main target of this thesis is evaluating the automation system precisely and exhaustively and developing a model based on mathematical relations. This model is founded based on the application and analysis of the networks....
What we know and do not know about connected and autonomous vehicles
, Article Transportmetrica A: Transport Science ; Volume 16, Issue 3 , 2020 , Pages 987-1029 ; Najmi, A ; Haider, A ; Wang, C ; Hosseinzadeh, F ; Sharif University of Technology
Taylor and Francis Ltd
2020
Abstract
Connected and autonomous vehicles (CAVs) have the potential to drastically change the structure of future cities and regions. Researchers predict different outcomes to result from the emergence of CAV technology. While some see their potential as amounting to a complete overhaul of the transport system, others predict the technology will be slow to be adopted and may face competition from other mobility options such as drones. Therefore, the future can be viewed along a spectrum, ranging from no CAVs to a fully driverless transport system. This paper presents an overview of the past attempts on studying CAVs and their impacts to provide a comprehensive view about possible futures with CAVs....
Reduced communications fault tolerant task scheduling algorithm for multiprocessor systems
, Article Procedia Engineering ; Volume 29 , 2012 , Pages 3820-3825 ; 18777058 (ISSN) ; Entezari Maleki, R ; Movaghar, A ; Sharif University of Technology
Abstract
Multiprocessor systems have been widely used for the execution of parallel applications. Task scheduling is crucial for the right operation of multiprocessor systems, where the aim is shortening the length of schedules. Fault tolerance is becoming a necessary attribute in multiprocessor systems as the number of processing elements is getting larger. This paper presents a fault tolerant scheduling algorithm for task graph applications in multiprocessor systems. The algorithm is an extension of a previously proposed algorithm with a reduced communications scheme. Simulation results show the efficiency of the proposed algorithm despite its simplicity
Simultaneous variation-aware architecture exploration and task scheduling for MPSoC energy minimization
, Article Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI ; 2011 , Pages 271-276 ; 9781450306676 (ISBN) ; Ghorbani, M ; Goudarzi, M ; Sanaei, E
Abstract
In nanometer-scale process technologies, the effects of process variations are observed in Multiprocessor System-on-Chips (MPSoC) in terms of variations in frequencies and leakage powers among the processors on the same chip as well as across different chips of the same design. Traditionally, worst-case values are assumed for these parameters and then a deterministic optimization technique is applied to the MPSoC application under design. We show that such worst-case-based approaches are not optimal with the increasing variation observed at system-level, and instead, statistical approaches should be employed. We consider the problem of simultaneously choosing MPSoC architecture and task...
NURA: A framework for supporting non-uniform resource accesses in gpus
, Article Proceedings of the ACM on Measurement and Analysis of Computing Systems ; Volume 6, Issue 1 , 2022 ; 24761249 (ISSN) ; Mahani, N ; Baxishi, H ; Yousefzadeh Asl Miandoab, E ; Sadrosadati, M ; Sarbazi Azad, H ; Sharif University of Technology
Association for Computing Machinery
2022
Abstract
Multi-application execution in Graphics Processing Units (GPUs), a promising way to utilize GPU resources, is still challenging. Some pieces of prior work (e.g., spatial multitasking) have limited opportunity to improve resource utilization, while other works, e.g., simultaneous multi-kernel, provide fine-grained resource sharing at the price of unfair execution. This paper proposes a new multi-application paradigm for GPUs, called NURA, that provides high potential to improve resource utilization and ensures fairness and Quality-of-Service (QoS). The key idea is that each streaming multiprocessor (SM) executes Cooperative Thread Arrays (CTAs) belong to only one application (similar to the...
Chaos control in single mode approximation of T-AFM systems using nonlinear delayed feedback based on sliding mode control
, Article 2007 Proceedings of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference ; Volume 3 PART B , 2008 , Pages 725-730 ; ISBN: 9780791848043 ; Salarieh, H ; Arjmand, M. T ; Alasty, A ; Sharif University of Technology
Abstract
The taping mode Atomic Force Microscopic (T-AFM) can be properly described by a sinusoidal excitation of its base and nonlinear potential interaction with sample. Thus the cantilever may cause chaotic behavior which decreases the performance of the sample topography. In this paper a nonlinear delayed feedback control.is proposed to control.chaos in a single mode approximation of a T-AFM system. Assuming model parameters uncertainties, the first order Unstable Periodic Orbits (UPOs) of the system is stabilized using the sliding nonlinear delayed feedback control. The effectiveness of the presented methods is numerically verified and the results show the high performance of the control.er
Throughput-memory footprint trade-off in synthesis of streaming software on embedded multiprocessors
, Article Transactions on Embedded Computing Systems ; Volume 13, Issue 3 , December , 2013 ; 15399087 (ISSN) ; Foroozannejad, M. H ; Ghiasi, S ; Sharif University of Technology
2013
Abstract
We study the trade-off between throughput and memory footprint of embedded software that is synthesized from acyclic static dataflow (task graph) specifications targeting distributed memory multiprocessors. We identify iteration overlapping as a knob in the synthesis process by which one can trade application throughput for its memory requirement. Given an initial processor assignment and non-overlapped task schedule, we formally present underlying properties of the problem, such as constraints on a valid iteration overlapping, maximum possible throughput, and minimum memory footprint. Moreover, we develop an effective algorithm for generation of a rich set of design points that provide a...
Static statistical MPSoC power optimization by variation-aware task and communication scheduling
, Article Microprocessors and Microsystems ; Volume 37, Issue 8 PART B , 2013 , Pages 953-963 ; 01419331 (ISSN) ; Goudarzi, M ; Sanaei, E ; Sharif University of Technology
2013
Abstract
Corner-case analysis is a well-known technique to cope with occasional deviations occurring during the manufacturing process of semiconductors. However, the increasing amount of process variation in nanometer technologies has made it inevitable to move toward statistical analysis methods, instead of deterministic worst-case-based techniques, at all design levels. We show that by statically considering statistical effects of random and systematic process variation on performance and power consumption of a Multiprocessor System-on-Chip (MPSoC), significant power improvement can be achieved by static software-level optimizations such as task and communication scheduling. Moreover, we analyze...
Yield-driven design-time task scheduling techniques for multi-processor system on chips under process variation: A comparative study
, Article IET Computers and Digital Techniques ; Volume 9, Issue 4 , 2015 , Pages 221-229 ; 17518601 (ISSN) ; Assare, O ; Rahmati, N ; Boroumand, A ; Barati, S ; Goudarzi, M ; Sharif University of Technology
Institution of Engineering and Technology
2015
Abstract
Process variation has already emerged as a major concern in design of multi-processor system on chips (MPSoC). In recent years, there have been several attempts to bring variability awareness into the task scheduling process of embedded MPSoCs to improve performance yield. This study attempts to provide a comparative study of the current variation-aware design-time task and communication scheduling techniques that target embedded MPSoCs. To this end, the authors first use a sign-off variability modelling framework to accurately estimate the frequency distribution of MPSoC components. The task scheduling methods are then compared in terms of both the quality of the final solution and the...
A genetic-based scheduling algorithm to minimize the makespan of the grid applications
, Article Communications in Computer and Information Science, 13 December 2010 through 15 December 2010 ; Volume 121 CCIS , December , 2010 , Pages 22-31 ; 18650929 (ISSN) ; 9783642176241 (ISBN) ; Movaghar, A ; Sharif University of Technology
2010
Abstract
Task scheduling algorithms in grid environments strive to maximize the overall throughput of the grid. In order to maximize the throughput of the grid environments, the makespan of the grid tasks should be minimized. In this paper, a new task scheduling algorithm is proposed to assign tasks to the grid resources with goal of minimizing the total makespan of the tasks. The algorithm uses the genetic approach to find the suitable assignment within grid resources. The experimental results obtained from applying the proposed algorithm to schedule independent tasks within grid environments demonstrate the applicability of the algorithm in achieving schedules with comparatively lower makespan in...
New approach for reducing energy consumption and load balancing in data centers of cloud computing
, Article Journal of Intelligent and Fuzzy Systems ; Volume 37, Issue 5 , 2019 , Pages 6443-6455 ; 10641246 (ISSN) ; Izadi, M ; Sharif University of Technology
IOS Press
2019
Abstract
Cloud computing is a new framework, which is facing a numerous type of challenges including resource management and energy consumption of data centers. One of the most important duties of cloud service providers is to manage resources and schedule tasks for reducing energy consumption in data centers. In this paper, fuzzy logic is used for finding most adequate DC, improved DVFS algorithm is used for selecting ideal host and developed version of EDF-VD algorithm is utilized for Task scheduling and load balance in cloud computing. Our approach improvement to the current methods including EEVS, DVFS, Homogeneous, MBFD and EEVS-N. © 2019-IOS Press and the authors. All rights reserved
A budget constrained scheduling algorithm for executing workflow application in infrastructure as a service clouds
, Article Peer-to-Peer Networking and Applications ; Volume 12, Issue 1 , 2019 , Pages 241-268 ; 19366442 (ISSN) ; Movaghar, A ; Mohsenzadeh, M ; Sharif University of Technology
Springer New York LLC
2019
Abstract
Cloud computing technology, which is a new model of service provisioning in distributed systems, has been raised as a way to execute workflow applications. To profit from this technology for executing workflow applications, it is necessary to develop workflow scheduling algorithms that consider different QoS parameters such as execution time and cost. Therefore, in this paper, we focus on two criteria: makespan (completion time) and execution cost of workflow application and propose a scheduling algorithm named CB-DT (Constrained Budget-Decreased Time) which aims to create a schedule that decreases the makespan while satisfying the budget constraint of the workflow application. In the...
New approach for reducing energy consumption and load balancing in data centers of cloud computing
, Article Journal of Intelligent and Fuzzy Systems ; Volume 37, Issue 5 , 2019 , Pages 6443-6455 ; 10641246 (ISSN) ; Izadi, M ; Sharif University of Technology
IOS Press
2019
Abstract
Cloud computing is a new framework, which is facing a numerous type of challenges including resource management and energy consumption of data centers. One of the most important duties of cloud service providers is to manage resources and schedule tasks for reducing energy consumption in data centers. In this paper, fuzzy logic is used for finding most adequate DC, improved DVFS algorithm is used for selecting ideal host and developed version of EDF-VD algorithm is utilized for Task scheduling and load balance in cloud computing. Our approach improvement to the current methods including EEVS, DVFS, Homogeneous, MBFD and EEVS-N. © 2019-IOS Press and the authors. All rights reserved
Task scheduling mechanisms in cloud computing: A systematic review
, Article International Journal of Communication Systems ; Volume 33, Issue 6 , 2020 ; Movaghar, A ; Rahmani, A. M ; Sharif University of Technology
John Wiley and Sons Ltd
2020
Abstract
Today, cloud computing has developed as one of the important emergent technologies in communication and Internet. It offers on demand, pay per use access to infrastructure, platforms, and applications. Due to the increase in its popularity, the huge number of requests need to be handled in an efficient manner. Task scheduling as one of the challenges in the cloud computing supports the requests for assigning a particular resource so as to perform effectively. In the resource management, task scheduling is performed where there is the dependency between tasks. Many approaches and case studies have been developed for the scheduling of these tasks. Up to now, a systematic literature review...
A new reliability-based task scheduling algorithm in cloud computing
, Article International Journal of Communication Systems ; 2021 ; 10745351 (ISSN) ; Movaghar, A ; Rahmani, A. M ; Sharif University of Technology
John Wiley and Sons Ltd
2021
Abstract
In the last decade, the scale of heterogeneous computing (HC) systems such as heterogeneous cloud computing environments was growing like never before. So network failures are unavoidable in such systems, which affect system reliability. Since the task scheduling algorithm in HC is challenging, we investigate a new reliability-aware task scheduling algorithm (RATSA) in this paper. RATSA is designed to schedule tasks on directed acyclic graphs (DAGs) by using the shuffled frog-leaping algorithm (SFLA) and genetic algorithm (GA) as evolutionary algorithms. The population-based SFLA-GA is applied to optimize makespan in the RATSA as an NP-complete problem. Moreover, the proposed algorithm...
NURA: A framework for supporting non-uniform resource accesses in GPUs
, Article 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS/PERFORMANCE 2022, 6 June 2022 through 10 June 2022 ; 2022 , Pages 39-40 ; 9781450391412 (ISBN) ; Mahani, N ; Baxishi, H ; Yousefzadeh, E ; Sadrosadati, M ; Sarbazi Azad, H ; ACM SIGMETRICS ; Sharif University of Technology
Association for Computing Machinery, Inc
2022
Abstract
Multi-application execution in Graphics Processing Units (GPUs), a promising way to utilize GPU resources, is still challenging. Some pieces of prior work (e.g. spatial multitasking) have limited opportunity to improve resource utilization, while others, e.g. simultaneous multi-kernel, provide fine-grained resource sharing at the price of unfair execution. This paper proposes a new multi-application paradigm for GPUs, called NURA, that provides high potential to improve resource utilization and ensure fairness and Quality-of-Service(QoS). The key idea is that each streaming multiprocessor (SM) executes the Cooperative Thread Arrays (CTAs) that belong to only one application (similar to...
A new reliability-based task scheduling algorithm in cloud computing
, Article International Journal of Communication Systems ; Volume 35, Issue 3 , 2022 ; 10745351 (ISSN) ; Movaghar, A ; Rahmani, A. M ; Sharif University of Technology
John Wiley and Sons Ltd
2022
Abstract
In the last decade, the scale of heterogeneous computing (HC) systems such as heterogeneous cloud computing environments was growing like never before. So network failures are unavoidable in such systems, which affect system reliability. Since the task scheduling algorithm in HC is challenging, we investigate a new reliability-aware task scheduling algorithm (RATSA) in this paper. RATSA is designed to schedule tasks on directed acyclic graphs (DAGs) by using the shuffled frog-leaping algorithm (SFLA) and genetic algorithm (GA) as evolutionary algorithms. The population-based SFLA-GA is applied to optimize makespan in the RATSA as an NP-complete problem. Moreover, the proposed algorithm...
A hybrid genetic algorithm and variable neighborhood search for task scheduling problem in grid environment
, Article Procedia Engineering ; Volume 29 , 2012 , Pages 3808-3814 ; 18777058 (ISSN) ; Khodadadi, F ; Entezari Maleki, R ; Movaghar, A ; Sharif University of Technology
2012
Abstract
This paper addresses scheduling problem of independent tasks in the market-based grid environment. In market-based grids, resource providers can charge users based on the amount of resource requested by them. In this case, scheduling algorithms should consider users' willingness to execute their applications in most economical manner. As a solution to this problem, a hybrid genetic algorithm and variable neighborhood search is presented to reduce overall cost of task executions without noticeable increment in system makespan. Simulation results show that our algorithm performs much better than other algorithms in terms of cost of task executions. Considering the negative correlation between...
A probabilistic task scheduling method for grid environments
, Article Future Generation Computer Systems ; Volume 28, Issue 3 , 2012 , Pages 513-524 ; 0167739X (ISSN) ; Movaghar, A ; Sharif University of Technology
Abstract
This paper presents a probabilistic task scheduling method to minimize the overall mean response time of the tasks submitted to the grid computing environments. Minimum mean response time of a given task can be obtained by finding a subset of appropriate computational resources to service the task. To achieve this, a discrete time Markov chain (DTMC) representing the task scheduling process within the grid environment is constructed. The connection probabilities between the nodes representing the grid managers and resources can be considered as transition probabilities of the obtained DTMC. Knowing the mean response times of the managers and resources, and finding fundamental matrix of the...