Adaptive Multiprocessor System-on-Chip Architecture: New Degrees of Freedom in System Design and Runtime Support

Göhringer, Diana; Hübner, Michael; Becker, Jürgen

doi:10.1007/978-1-4419-6460-1_6

Cited by 4 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 shows an example of some subsystem that consists of six 𝐶𝑀s in the case of (N,4,4) graph of inter-computer system connections Let the input and output streams of 𝐶𝑀 be labeled 𝑝 𝑖 , 𝑝 ∈ {1, … , 𝑣}, where 𝑣 is the degree of vertices of the graph of inter-module connections. It should be taken into account that 𝐶𝑀s communicate with each other using a connection switch, which is implemented as a multi-channel interface [1]. Moreover, if 𝐶𝑀 𝑖 and 𝐶𝑀 𝑗 are connected by a channel (𝑖 𝑝 , 𝑖 𝑝 ), then these modules are also connected by channels (𝑗 𝑞 , 𝑗 𝑝 ), where (𝑗 𝑝 , 𝑗 𝑝 ) is a channel that is ISSN 2710-0766…”

Section: Development Of the Methods Of Organizing Inter-module Data E...mentioning

confidence: 99%

“…The presence of these two problems during the creation of MPCSs requires looking for options for their construction and organization of processes, which, with some limitations, would ensure, on the one hand, the simplification of the system, and on the other hand, would not reduce efficiency much. This has led to several structural developments (constructions) of MPCS and several ways of organizing computing processes [1,2,3]. The key to the classification of MPCSs is the system of interrelationships, organization and functioning of the system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Method of Organizing Inter-Module Data Exchange

KHOROSHKO,

ZYBIN

2024

CSIT

View full text Add to dashboard Cite

The purpose of this article is the development and description of the method of organizing inter-module data exchange, that is based on the parametric presented subsystems, as well as the evaluation of the effectiveness of the developed multiprocessor computing systems. The authors propose a method of organizing inter-modular exchanges, which is based on the parametric presented subsystem. When developing programs using parallelization algorithms, parameters are used that set specific values for the subsystem. These values are determined during the formation of the subsystem. This makes the program independent of the graph of subsystem inter-module connections, on the basis of which this program will be implemented. The effectiveness of the computer system depends on a set of characteristics, which include: performance, reliability, probability of results, stability, manufacturability and others. To compare computer systems as a criterion of efficiency, it is necessary to adopt a comprehensive indicator that will take into account the main indicators. The real efficiency of a computer system is determined by the time it fulfils its functional purpose. Accordingly, the more reliable the system, the more relative time it is used for its intended purpose and the greater its efficiency. Thus, when comparing computer systems, it is necessary to compare their performance taking into account the real reliability of the system. At the same time, depending on the classes of problems being solved, the influence of various indicators (including reliability) on the efficiency of the system changes. Based on the results of the research, the following conclusions can be drawn: the most effective are the computer systems that are implemented on the developed MO. This fact is clearly visible from the comparison of the time spent on calculating not only the test task, but also when calculating the test equation with the test parameters.

show abstract

Section: Development Of the Methods Of Organizing Inter-module Data E...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Method of Organizing Inter-Module Data Exchange

KHOROSHKO,

ZYBIN

2024

CSIT

View full text Add to dashboard Cite

show abstract

“… Interface between user and the MPSoC architecture  Virtualization/management of MPSoC architecture  Scheduling of the partitioned applications  Task allocation to the clients  Loading software executables into existing clients  Reconfiguring clients or NoC-infrastructure To fulfill these tasks, the RAMPSoCVM processor needs the following files and information, which can be generated automatically by the RAMPSoC design flow [2]:  Layout.xml: XML-file including the application task graph and the allocation of each task within the Star-Wheels NoC [6]  Partial bitstreams for reconfiguration  ELF files for the software tasks The RAMPSoCVM server stores this information in internal structures. It is aware of the available clients, their utilization and physical location.…”

Section: Structure and Functionality Of Rampsocvmmentioning

confidence: 99%

“…The RAMPSoCVM server schedules the tasks of the applications and allocates them to specific clients. For this purpose, the Configuration Access Port -Operating System (CAP-OS) (see [2]) has been adapted and integrated as a Linux kernel module. The scheduling approach of CAP-OS assures that the real-time constraints of the applications running on RAMPSoC are met.…”

Section: Structure and Functionality Of Rampsocvmmentioning

confidence: 99%

See 1 more Smart Citation

RAMPSoCVM: Runtime Support and Hardware Virtualization for a Runtime Adaptive MPSoC

Göhringer

Werner

Hübner

et al. 2011

2011 21st International Conference on Field Programmable Logic and Applications

View full text Add to dashboard Cite

Virtualizing complex hardware, such as heterogeneous multiprocessor systems, enables developers to use standard Application Programming Interfaces (APIs) for application integration. Especially, the supply of an Operating System (OS) is well appreciated since many features such as drivers, the runtime environment and scheduling mechanisms are available and well established. For this purpose, Embedded Linux was used as basis OS and extended in order to be able to manage a Runtime Adaptive Multi-Processor System-on-Chip (RAMPSoC) and to provide the standard Message Passing Interface (MPI). This paper describes the adaptation of the Linux kernel supporting MPI with runtime libraries as well as the integration of the software/hardware drivers which supply the message transfer over a reconfigurable and heterogeneous Network-on-Chip (NoC).

show abstract

Reconfigurable MPSoC versus GPU: Performance, power and energy evaluation

Göhringer

Birk

Dasse-Tiyo

et al. 2011

2011 9th IEEE International Conference on Industrial Informatics

View full text Add to dashboard Cite

Different characteristics of algorithms, perform better or worse on various target hardware. The consequent of this is, that the selection of one suitable hardware, such as Graphic Processing Units (GPU), Field Programmable Gate Arrays (FPGAs) or traditional processor cores is a challenging task for developers. The challenge is to choose the most suitable platform satisfying the requirements of the given application, such as real-time and power-/energy consumption constraints. Due to short time to market pressure, a fast development cycle is also a very important characteristic in industrial applications. This work evaluates the performance, power-/energy consumption and the development effort for three processor-based systems: an FPGA-based multiprocessor platform called RAMPSoC, a GPU and a CPU. Two real-world applications have been selected for this evaluation: 3D Ultrasound Computer Tomography and Object Recognition. The paper presents the realization of the applica tions on the different target hardware and discusses the results of the power and performance evaluation

show abstract

Adaptive Multiprocessor System-on-Chip Architecture: New Degrees of Freedom in System Design and Runtime Support

Cited by 4 publications

References 19 publications

Method of Organizing Inter-Module Data Exchange

Method of Organizing Inter-Module Data Exchange

RAMPSoCVM: Runtime Support and Hardware Virtualization for a Runtime Adaptive MPSoC

Reconfigurable MPSoC versus GPU: Performance, power and energy evaluation

Contact Info

Product

Resources

About