OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

NoC-based Architectures for Real-Time Applications : Performance Analysis and Design Space Exploration

Giroudot, Frédéric. NoC-based Architectures for Real-Time Applications : Performance Analysis and Design Space Exploration. PhD, Informatique et Télécommunications, Institut National Polytechnique de Toulouse, 2019

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB

Abstract

Monoprocessor architectures have reached their limits in regard to the computing power they offer vs the needs of modern systems. Although multicore architectures partially mitigate this limitation and are commonly used nowadays, they usually rely on intrinsically non-scalable buses to interconnect the cores. The manycore paradigm was proposed to tackle the scalability issue of bus-based multicore processors. It can scale up to hundreds of processing elements (PEs) on a single chip, by organizing them into computing tiles (holding one or several PEs). Intercore communication is usually done using a Network-on-Chip (NoC) that consists of interconnected onchip routers allowing communication between tiles. However, manycore architectures raise numerous challenges, particularly for real-time applications. First, NoC-based communication tends to generate complex blocking patterns when congestion occurs, which complicates the analysis, since computing accurate worst-case delays becomes difficult. Second, running many applications on large Systems-on-Chip such as manycore architectures makes system design particularly crucial and complex. On one hand, it complicates Design Space Exploration, as it multiplies the implementation alternatives that will guarantee the desired functionalities. On the other hand, once a hardware architecture is chosen, mapping the tasks of all applications on the platform is a hard problem, and finding an optimal solution in a reasonable amount of time is not always possible. Therefore, our first contributions address the need for computing tight worst-case delay bounds in wormhole NoCs. We first propose a buffer-aware worst-case timing analysis (BATA) to derive upper bounds on the worst-case end-to-end delays of constant-bit rate data flows transmitted over a NoC on a manycore architecture. We then extend BATA to cover a wider range of traffic types, including bursty traffic flows, and heterogeneous architectures. The introduced method is called G-BATA for Graph-based BATA. In addition to covering a wider range of assumptions, G-BATA improves the computation time; thus increases the scalability of the method. In a second part, we develop a method addressing design and mapping for applications with real-time constraints on manycore platforms. It combines model-based engineering tools (TTool) and simulation with our analytical verification technique (G-BATA) and tools (WoPANets) to provide an efficient design space exploration framework. Finally, we validate our contributions on (a) a serie of experiments on a physical platform and (b) two case studies taken from the real world: an autonomous vehicle control application, and a 5G signal decoder application

Item Type:PhD Thesis
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Laboratory name:
Research Director:
Mifdaoui, Ahlem and Lochin, Emmanuel
Statistics:download
Deposited On:17 Apr 2020 11:49

Repository Staff Only: item control page