Architecture-level performance evaluation of component-based embedded systems

Russell, Jeffry T.; Jacome, Margarida F.

doi:10.1145/775832.775936

Cited by 16 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A static performance evaluation methodology was proposed in [RJ03] to support early, architecture-level design space exploration for component-based embedded systems. This approach evaluates the system performance based on a scenario.…”

Section: Hardware Simulation-related-workmentioning

confidence: 99%

Energy consumption and execution time estimation of embedded system applications

Callou

Maciel

Tavares

et al. 2011

Microprocessors and Microsystems

View full text Add to dashboard Cite

Over the last years, the issue of reducing energy consumption in embedded system applications has received considerable attention from the scientific community, since responsiveness and low energy consumption are often conflicting requirements. In this context, this dissertation proposes a methodology applied in early design phases for supporting design decisions on energy consumption and performance of embedded applications. In addition, this work proposes temporized discrete event models that have been evaluated through a stochastic simulation approach to represent different system scenarios in an easier way. For each scenario, it is important to decide the maximum number of simulations and the duration of each simulation, where both may impact the performance estimates. Such approach also considers an intermediate model which represents the system behavioral description and, through these models, the scenarios are analyzed. The intermediate model is based on timed Colored Petri Net, a formal behavioral model that not only allows the software execution analysis, but it is also supported by a set of well established methods for property verifications. In this context, a software, named ALUPAS, for estimating energy consumption and execution time of embedded systems is presented. Lastly, a real-world case study as well as customized examples are presented, showing the applicability of this work in which non-specialized users do not need to interact directly with the Petri net formalism.

show abstract

Section: Hardware Simulation-related-workmentioning

confidence: 99%

Energy consumption and execution time estimation of embedded system applications

Callou

Maciel

Tavares

et al. 2011

Microprocessors and Microsystems

View full text Add to dashboard Cite

show abstract

“…Static approaches, such as [17], on one side use purely analytical methods to compute application delays. Dynamic approaches on the other side, use platform models to generate a timed executable model of the design, which later produces the estimation data at run time.…”

Section: Related Workmentioning

confidence: 99%

Automatic Generation of Cycle-Approximate TLMs with Timed RTOS Model Support

Hwang

Schirner

Abdi³

2009

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. This paper presents a technique for automatically generating cycle-approximate transaction level models (TLMs) for multi-process applications mapped to embedded platforms. It incorporates three key features: (a) basic block level timing annotation, (b) RTOS model integration, and (c) RTOS overhead delay modeling. The inputs to TLM generation are application C processes and their mapping to processors in the platform. A processor data model, including pipelined datapath, memory hierarchy and branch delay model is used to estimate basic block execution delays. The delays are annotated to the C code, which is then integrated with a generated SystemC RTOS model. Our abstract RTOS provides dynamic scheduling and inter-process communication (IPC) with processor-and RTOS-specific pre-characterized timing. Our experiments using a MP3 decoder and a JPEG encoder show that timed TLMs, with integrated RTOS models, can be automatically generated in less than a minute. Our generated TLMs simulated three times faster than real-time and showed less than 10% timing error compared to board measurements.

show abstract

“…In [12], a static estimation based on a designer-specified evaluation scenario is proposed. However, the estimation is not cycle level and is not applicable to custom HW.…”

Section: Related Workmentioning

confidence: 99%