A methodology for task based partitioning and scheduling of dynamically reconfigurable systems

Muñoz‐Merino, Pedro J.; Jacome, Margarida F.; López, Juan Carlos

doi:10.1109/fpga.1998.707937

Cited by 11 publications

(20 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We do not follow any particular scheduling policy. We have restricted our implementation of the service to a 2D pre-partitioned model, where the PR areas are already predefined [3]. Nevertheless the reconfiguration service could also be applied to any other kind of partitioning models.…”

Section: Layer 3: Dynamic Objects Managementmentioning

confidence: 98%

Dynamic Reconfiguration Management Based on a Distributed Object Model

Dondo

Rincón

Barba

et al. 2007

2007 International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

In this paper we propose a contribution to reduce the complexity of management of dynamic reconfiguration. The model for Dynamic Reconfiguration presented here is based on the object-oriented paradigm and a clear separation between the functionality inside the reconfigured cores and the communication infrastructure. This infrastructure will be the responsible not only for managing data transferences between objects but also for transparently handling other aspects such as state storage and retrieval or controlled object stopping and resuming. INTRODUCTIONMost of the research effort in reconfiguration techniques and design methodologies, is highly technology-dependent [5][6]. Other research efforts have concentrated on higher abstraction levels [7]. However, it is still not clear how to map such high-level services onto current reconfiguration technology. Currently, it is the designer of the reconfigurable application the responsible for solving nontrivial problems, such as structural consistency, state persistence, etcThe solution we propose in this paper is based on the object-oriented paradigm, instead of the task-based approach that has been normally used as the programming model for reconfigurable applications. Object technology is better suited to nowadays reconfiguration technology since it enforces a systematic way to deal with state, execution of operations and encapsulation. The definition of a clear object interface, and the use of the distributed objects communication model, properly extended to support dynamic reconfiguration, will provide the necessary orthogonalization between object functionality and communication-reconfiguration tasks.

show abstract

Section: Layer 3: Dynamic Objects Managementmentioning

confidence: 98%

Dynamic Reconfiguration Management Based on a Distributed Object Model

Dondo

Rincón

Barba

et al. 2007

2007 International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

show abstract

“…Past work has considered the use of dynamically reconfigurable FPGAs in high-level synthesis [34]- [36], [70]. However, in system-level synthesis, the problem is much more complex.…”

Section: A Previous Workmentioning

confidence: 99%

SLOPES: Hardware–Software Cosynthesis of Low-Power Real-Time Distributed Embedded Systems With Dynamically Reconfigurable FPGAs

Shang

Dick

Jha

2007

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

In this paper, we present a multiobjective hardwaresoftware cosynthesis system, called SLOPES, for multirate low-power real-time distributed embedded systems consisting of dynamically reconfigurable field-programmable gate arrays (FPGAs), processors, and heterogeneous communication resources. This cosynthesis algorithm simultaneously optimizes system price and average power consumption. First, we present an evolutionary algorithm that automatically determines the quantities and types of system resources, assigns tasks to different potentially reconfigurable processing elements, and assigns communication events to communication resources. Second, we propose a dynamic priority multirate scheduling algorithm to determine the times at which all the tasks and communication events in the system occur. This two-dimensional scheduling algorithm determines task priorities based on real-time constraints and detailed frame-by-frame FPGA reconfiguration overhead information. Experimental results indicate that the proposed method reduces schedule length by an average of 34.3% and reconfiguration energy by an average of 40.4%, compared to a method that does not consider the effect of partial reconfiguration during synthesis. SLOPES yields multiple system architectures that tradeoff system price and average power consumption under real-time constraints.Index Terms-Hardware-software co-design, low-power design, reconfigurable architectures, system-level synthesis.

show abstract

“…Each block can accommodate one task at a time. Such a partitioning has been proposed by Merino et al [8] and Marescaux et al [9]. Partitioning the area simplifies scheduling and placement and makes a practical implementation on current technology more realistic.…”

Section: D Area Modelsmentioning

confidence: 97%

“…The scheduler runs in EDF mode; the placer in the prefer mode. The example details the scheduling of a task set with following four tasks t x (a x , w x , c x , d x ): t 1 (1, 5, 8, 26), t 2 (2, 5, 8, 24), t 3 (8, 5, 4, 23), t 4 (9,8,4,20) The configuration and readback times for t 1 ,t 2 and t 3 are 2, for task t 4 3 time units. At time 1, t 1 arrives and starts to configure onto b 1 .…”

Section: Influence Of Configuration and Readbackmentioning

confidence: 99%

Online scheduling for block-partitioned reconfigurable devices

Walder¹,

Platzner²

2003 Design, Automation and Test in Europe Conference and Exhibition

View full text Add to dashboard Cite

This paper presents our work toward an operating system that manages the resources of a reconfigurable device in a multitasking manner. We propose an online scheduling system that allocates tasks to a block-partitioned reconfigurable device. The blocks are statically-fixed but can have different widths, which allows to match the computational resources with the task requirements. We implement several non-preemptive and preemptive schedulers as well as different placement strategies. Finally, we present a simulation environment that allows to experimentally investigate the effects of specific partitioning, placement, and scheduling methods.

show abstract

A methodology for task based partitioning and scheduling of dynamically reconfigurable systems

Cited by 11 publications

References 2 publications

Dynamic Reconfiguration Management Based on a Distributed Object Model

Dynamic Reconfiguration Management Based on a Distributed Object Model

SLOPES: Hardware–Software Cosynthesis of Low-Power Real-Time Distributed Embedded Systems With Dynamically Reconfigurable FPGAs

Online scheduling for block-partitioned reconfigurable devices

Contact Info

Product

Resources

About