Energy Aware Proportionate Slack Management Scheduling for Multiprocessor Systems

Ramesh, Pasupuleti; Ramachandraiah, Uppu

doi:10.1016/j.procs.2018.07.109

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resource allocation and scheduling techniques can be applied as a part of MM in order to choose a specific memory unit for the task. Recent studies on the shared resource-aware scheduling and task allocation methods for HPC systems have focused on locality- [47], energy- [48], performance- [49], resilience- [50] aware usage planning of the processors and accelerators. The power-aware threads co-scheduling approach for the multicore processor presented in [51] takes into account an effect of the shared last-level cache on the performance degradation.…”

Section: H Allocationmentioning

confidence: 99%

Survey of Memory Management Techniques for HPC and Cloud Computing

Pupykina

Agosta

2019

IEEE Access

View full text Add to dashboard Cite

The emergence of new classes of HPC applications and usage models, such as real-time HPC and cloud HPC, coupled with the increasingly heterogeneous nature of HPC architectures, requires a renewed investigation of memory management solutions. Traditionally, memory is shared by an operating system using segmentation and paging techniques. At the same time, new classes of applications require Quality of Service (QoS) guarantees. As such, the typical practice of reserving a subset of the supercomputer to a single application becomes less attractive, leading to the exploration of cloud technologies. In this context, a viable scenario is that of multiple applications, with different QoS levels, coexisting on the same deeply heterogeneous HPC infrastructure and sharing resources. However, for this scenario to succeed in practice, resources, including memory, need to be allocated with a vision that includes both the application requirements and the current and future state of the overall system. In this survey, challenges of memory management in HPC and Cloud Computing, different memory management systems and optimisation techniques to increase memory utilisation are discussed in detail. INDEX TERMS Clouds, high performance computing, memory management, resource management. ANNA PUPYKINA received the higher education degree in data processing and control systems engineering from Samara State Aerospace University, Russia, in 2009. She is currently pursuing the Ph.D. degree with the Politecnico di Milano, under the supervision of Prof. G. Agosta. She was with Russian State Humanitarian University (RSUH), Togliatti, and also with the Department of Applied Mathematics and Informatics, Togliatti State University (TSU). Her main research interests include runtime management algorithms and programming model extensions for deeply heterogeneous systems. GIOVANNI AGOSTA received the Laurea degree in computer engineering and the Ph.D. degree in information technology from the Politecnico di Milano, Italy, in 2000 and 2004, respectively. He is currently a tenured Researcher. He has authored more than 80 articles in international journals, conferences, and workshops. His main research interest includes compiler technology. He was a recipient of four HiPEAC Awards and three Best Paper Awards. He has been involved in eight European funded projects, since 2010, holding workpackage and task leader responsibilities. He is a Full Member of the HiPEAC Network and the Organizer of two workshops colocated with the HiPEAC Conference.

show abstract

Section: H Allocationmentioning

confidence: 99%

Survey of Memory Management Techniques for HPC and Cloud Computing

Pupykina

Agosta

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Consider the task set with three tasks: (15,15,3), (30, 30, 4), and (45, 45, 3). The hyper period (lcm( ∑ n i=0 T i )) is 90 and the total utilization is 0.4.…”

Section: Motivational Examplementioning

confidence: 99%

“…In [15], the dynamic slack reclamation method was applied to a multimedia application based on SoCLib. The authors in [16] proposed a dynamic slow-down factor computation algorithm called energy-aware proportionate slack management (EAPSM) for multiprocessors.…”

Section: Slack Reclamation Techniquesmentioning

confidence: 99%

Energy-efficient scheduling for real-time tasks using dynamic slack reclamation

Kannaian¹,

Palanisamy²

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

The application domains of portable embedded real-time systems range from safety-critical applications like electronic control units in the automotive sector to entertainment applications like digital cameras and setup boxes in the consumer electronics sector. These systems attract users with multiple and sophisticated functionalities in a single system. The developments in VLSI technology have enabled IC manufacturers to incorporate more features in a single die, which facilitates these multipurpose systems. The increase in features and functionalities has a direct impact on power consumption and has to be strictly accounted for in the design of these embedded systems. The possibility of achieving low power consumption is obtained by using only effective software techniques along with the hardware powersaving methods. The dynamic power management techniques with the support of real-time operating systems (RTOSs) provided in recent microcontrollers enable better power management using software control. The scheduling of tasks in real-time systems is based on the worst-case execution time (WCET), whereas tasks based on their environmental conditions may complete their execution before the WCET. This leads to increased laxity (slack time) and reduced utilization of the CPU. This paper proposes Fixed Window DynaClam, a dynamic reclamation algorithm, to effectively utilize slack time. The clock frequency of the processor is slowed down by reclaiming the available slack time to reduce the energy consumption. The Fixed Window DynaClam algorithm is implemented for nonpreemptive periodic tasks in the controllers with dynamic voltage and frequency scaling power management features. The novelty of the algorithm is that the clock frequency is not only adjusted based on the real-time demands of the tasks but also does not overload the kernel of the RTOS as the complexity is on the lower side.

show abstract