Simulink®-based heterogeneous multiprocessor SoC design flow for mixed hardware/software refinement and simulation

Han, Sang-Hoon; Chae, Soo-Ik; Brisolara, Lisane; Carro, Luigi; Popovici, Katalin; Guerin, Xavier; Jerraya, Ahmed; Huang, Kai; Li, Lei; Yan, Xiao

doi:10.1016/j.vlsi.2008.08.003

Cited by 19 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method for MPSoC modeling is based on concepts introduced in previous works [Han et al 2006b[Han et al , 2009Huang et al 2007] and results in a Simulink system model that represents the functionality of the target system, including software threads and 59:4 K. Huang et al hardware architecture. This system model is specified as a three-layered hierarchy and includes information about the mapping between software threads and processors (the CPU subsystems [CPU SS]) as well as communication channels, as illustrated in Figure 2.…”

Section: Background Of Simulink Modelmentioning

confidence: 99%

Communication Optimizations for Multithreaded Code Generation from Simulink Models

Huang

Yan

et al. 2015

ACM Trans. Embed. Comput. Syst.

Self Cite

View full text Add to dashboard Cite

Communication frequency is increasing with the growing complexity of emerging embedded applications and the number of processors in the implemented multiprocessor SoC architectures. In this article, we consider the issue of communication cost reduction during multithreaded code generation from partitioned Simulink models to help designers in code optimization to improve system performance. We first propose a technique combining message aggregation and communication pipeline methods, which groups communications with the same destinations and sources and parallelizes communication and computation tasks. We also present a method to apply static analysis and dynamic emulation for efficient communication buffer allocation to further reduce synchronization cost and increase processor utilization. The existing cyclic dependency in the mapped model may hinder the effectiveness of the two techniques. We further propose a set of optimizations involving repartition with strongly connected threads to maximize the degree of communication reduction and preprocessing strategies with available delays in the model to reduce the number of communication channels that cannot be optimized. Experimental results demonstrate the advantages of the proposed optimizations with 11-143% throughput improvement.

show abstract

Section: Background Of Simulink Modelmentioning

confidence: 99%

Communication Optimizations for Multithreaded Code Generation from Simulink Models

Huang

Yan

et al. 2015

ACM Trans. Embed. Comput. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This work is based on the concepts of Simulink models, which have been introduced in previous works [12], [23]- [24]. A Simulink model represents the functionality of a target system with software functions and hardware architectures.…”

Section: Simulink Modelmentioning

confidence: 99%

“…2. To analyze timing relationships, we assume that applications are executed in cycles [12], [24] (a cycle means that from some point partitioned applications on all processors have been executed once). Thus, at the same time, from Fig.…”

Section: Software Pipelinementioning

confidence: 99%

Software Pipeline–Based Partitioning Method with Trade-Off between Workload Balance and Communication Optimization

Huang¹,

Xiu²,

Yu³

et al. 2015

ETRI J

Self Cite

View full text Add to dashboard Cite

For a multiprocessor System‐on‐Chip (MPSoC) to achieve high performance via parallelism, we must consider how to partition a given application into different components and map the components onto multiple processors. In this paper, we propose a software pipeline–based partitioning method with cyclic dependent task management and communication optimization. During task partitioning, simultaneously considering computation load balance and communication optimization can cause interference, which leads to performance loss. To address this issue, we formulate their constraints and apply an integer linear programming approach to find an optimal partitioning result — one that requires a trade‐off between these two factors. Experimental results on a reconfigurable MPSoC platform demonstrate the effectiveness of the proposed method, with 20% to 40% performance improvements compared to a traditional software pipeline–based partitioning method.

show abstract

“…In this paper, we adopt an extension of Simulink, where a subsystem can also be used to represent CPUs, threads, and communication capabilities, following the Simulink CAAM [11]. Similar to the stereotypes used in UML, parameters defined in the description of a subsystem are used to indicate when a special semantics should be considered for this subsystem.…”

Section: Simulinkmentioning

confidence: 99%

From UML diagrams to simulink models

Costa

Cavalheiro

Foss

et al. 2015

Proceedings of the 30th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

The last decade witnessed an enormous increase in the use and complexity of embedded systems. To enable a fast development of these systems while guaranteeing their quality, different kinds of models may be used. UML and Simulink are attractive languages for embedded systems design and modeling that allow to describe systems at different levels of abstraction. An automatic mapping from UML to Simulink is an useful resource in a seamless design flow, allowing designers to use UML as modeling language for the whole system and to use facilities for code generation of Simulink. In previous work, an UML to Simulink translation was formalised using graph grammars and prototyped using a Java implementation. The use of a formal language allowed the verification of important properties of the mapping, like termination and confluence (ensuring, e.g., that there is a unique model resulting from the transformation). In this work, an extension of this formal definition is presented to support nested method calls, reducing restrictions and keeping the compatibility and the properties of termination and confluence of the original translation.

show abstract

Simulink®-based heterogeneous multiprocessor SoC design flow for mixed hardware/software refinement and simulation

Cited by 19 publications

References 23 publications

Communication Optimizations for Multithreaded Code Generation from Simulink Models

Communication Optimizations for Multithreaded Code Generation from Simulink Models

Software Pipeline–Based Partitioning Method with Trade-Off between Workload Balance and Communication Optimization

From UML diagrams to simulink models

Contact Info

Product

Resources

About