Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

A novel simulator for heterogeneous parallel and distributed systems

Tampouratzis Nikolaos

Full record


URI: http://purl.tuc.gr/dl/dias/A174E661-D18C-4EB9-A256-25E9C07EFB1E
Year 2018
Type of Item Doctoral Dissertation
License
Details
Bibliographic Citation Nikolaos Tampouratzis, "A novel simulator for heterogeneous parallel and distributed systems", Doctoral Dissertation, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2018 https://doi.org/10.26233/heallink.tuc.77407
Appears in Collections

Summary

In an era of complex networked heterogeneous systems, simulating independently only parts, components or attributes of a system-under-design is not a viable, accurate or efficient option. By considering each part of a system in an isolated manner, and due to the numerous and highly complicated interactions between the different components, the system optimization capabilities are severely limited. One of the main problems Cyber Physical Systems (CPS) and Highly Parallel Systems (HPS) designers face is the lack of simulation tools and models for system design and analysis. This is mainly because the majority of the existing simulation tools can handle efficiently only parts of a system (e.g. only the processing or only the network). Moreover, most of the existing simulators need extreme amounts of processing resources while faster approaches cannot provide the necessary precision and accuracy. On top of that, the growing use of hardware accelerators in both embedded systems (e.g. mobile phones) and high-end systems (e.g. HPC/Cloud systems) triggers an urgent demand for simulation frameworks that can simulate in an integrated manner all the components (i.e. CPUs, Memories, Networks, Hardware Accelerators) of a system-under-design (SuD). By utilizing such systems, software design can proceed in parallel with hardware development which will result in the reduction of the so important time-to-market. The main problem, however, is that such systems do not exist; most current simulators used for modelling the user applications (i.e. full-system CPU/Mem/Peripheral simulators) lack any type of support for tailor-made hardware accelerators. In this thesis we present the COSSIM simulation framework which is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals and networks; such an approach is very appealing to both CPS and Highly Parallel Heterogeneous Systems designers and application developers. In the context of COSSIM, a novel intercommunication and synchronization scheme is developed which is fully compliant with the IEEE HLA standard. Our highly integrated approach is further augmented with accurate power estimation that can tap on all system components and perform analysis of the overall system under design something which was unfeasible up to know. In addition, we present the ACSIM framework which is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals, networks and accelerators. ACSIM is an extension of the COSSIM simulation framework and it integrates, in a novel and efficient way, a combined system and network simulator with a SystemC simulator, in a transparent to the end-user way. Finally, a sophisticated Eclipse-based GUI has been developed to provide easy simulation set-up, execution and visualization of results.COSSIM and ACSIM have been evaluated when executing several real-world use cases; the end results demonstrate that the presented approach has up to 99% accuracy in the reported SuD aspects (when compared with the corresponding characteristics measured in the real systems), while the overall simulation time can be accelerated almost linearly with the number of CPUs utilized by the simulator. Finally, the presented ACSIM interconnection scheme between the Processing and the SystemC simulators is orders of magnitude faster than the existing solutions, while our simulation framework can efficiently simulate up to several hundreds of processing nodes with hardware accelerators interconnected together, in a full distributed manner.

Available Files

Services

Statistics