Identifying "representative" workloads in designing MpSoC platforms for media processing

Maxiaguine, A.; Liu, Yanhong; Chakraborty, Samarjit; Ooi, Wei Tsang

doi:10.1109/estmed.2004.1359702

Cited by 15 publications

(9 citation statements)

References 12 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To find a representative training bitstream that covers most of the behaviors which may appear during the application life-time, particularly including the most frequent ones, is in general a difficult problem. However, an approach similar to the one presented in [19], where the authors show a technique for classifying different multimedia streams, could be used. The analysis performed on the collected trace information aims to discover if the trace contains data variables.…”

Section: Control Variable Identificationmentioning

confidence: 99%

Scenario Selection and Prediction for DVS-Aware Scheduling of Multimedia Applications

Gheorghita

Basten

Corporaal

2007

J Sign Process Syst Sign Image

View full text Add to dashboard Cite

Abstract. Modern multimedia applications usually have real-time constraints and they are implemented using application-domain specific embedded processors. Dimensioning a system requires accurate estimations of resources needed by the applications. Overestimation leads to over-dimensioning. For a good resource estimation, all the cases in which an application can run must be considered. To avoid an explosion in the number of different cases, those that are similar with respect to required resources are combined into, so called application scenarios. This paper presents a methodology and a tool that can automatically detect the most important variables from an application and use them to select and dynamically predict scenarios, with respect to the necessary time budget, for soft real-time multimedia applications. The tool was tested for three multimedia applications. Using a proactive scenario-based dynamic voltage scheduler based on the scenarios and the runtime predictor generated by our tool, the energy consumption decreases with up to 19%, while guaranteeing a frame deadline miss ratio close to zero.

show abstract

Section: Control Variable Identificationmentioning

confidence: 99%

Scenario Selection and Prediction for DVS-Aware Scheduling of Multimedia Applications

Gheorghita

Basten

Corporaal

2007

J Sign Process Syst Sign Image

View full text Add to dashboard Cite

show abstract

“…To find a representative training bitstream that covers most of the behaviors which may appear during the application life-time, particularly including the most frequent ones, is in general a difficult problem. However, an approach similar to the one presented in [10], where the authors show a technique for classifying different multimedia streams, could be used. The analysis done on the collected trace information aims to discover if the trace contains data variables.…”

Section: Control Variable Identificationmentioning

confidence: 99%

Profiling Driven Scenario Detection and Prediction for Multimedia Applications

Gheorghita

Basten

Corporaal

2006

2006 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation

View full text Add to dashboard Cite

Abstract-Modern multimedia applications usually have realtime constraints and they are implemented using heterogeneous multiprocessor systems-on-chip. Dimensioning a system requires accurate estimations of resources needed by the applications. Overestimation leads to over-dimensioning. For a good resource estimation, all the cases in which an application can run must be considered. To avoid an explosion in the number of different cases, those that are similar with respect to required resources are combined into, so called, scenarios. This paper presents a method and a tool that can automatically detect the most important variables from an application and use them to define and dynamically predict scenarios, with respect to the necessary time budget, for soft real-time multimedia applications. The tool was tested for two multimedia applications. Using a proactive scenario-based scheduler based on the scenarios and the runtime predictor generated by our tool, the cycle budget over-estimation decreases with up to 83.50%, paying an acceptable cost of up to 1.74% in the number of missed deadlines.

show abstract

“…A previous work [10] introduced a novel concept of variability characterization curves (VCCs) where each video clip was represented using its VCC. This concept of VCCs was also suggested to be appropriate in [3] for identification of different application scenarios.…”

Section: A New Model For Idct Workload Was Developedmentioning

confidence: 99%

“…The buffer occupancy keeps increasing as new MBs enter the particular stage of the architecture and it reduces as they are completely processed by the PE and sent to the next stage. The worst case delay for one MB can be computed using the equation (10) where τ mbcyc i is the processor cycle time required for (i) th macroblock. The expression of worst case delay for 1 MB given by Equation(10) takes the following two cases into consideration 1.…”

Section: Validationmentioning

confidence: 99%

Fast model-based test case classification for performance analysis of multimedia MPSoC platforms

Gangadharan

Chakraborty²,

Zimmermann

2009

Proceedings of the 7th IEEE/ACM International Conference on Hardware/Software Codesign and System Synthesis

View full text Add to dashboard Cite

Currently, performance analysis of multimedia-MPSoC platforms largely rely on simulation. The execution of one or more applications on such a platform is simulated for a library of test video clips. If all specified performance constraints are satisfied for this library, then the architecture is assumed to be well-designed. This is similar to testing software for functional correctness. However, in contrast to functional testing, simulating a set of video clips for a complex application/architecture is extremely time consuming. In this paper we propose a technique for clustering a library of video clips, such that it is sufficient to simulate only one clip from each cluster rather than the entire library. Our clustering is scalable, i.e., the number of clusters may be determined based on the number of clips that the system designer wishes to simulate (which is independent of the input library size). For each video clip in the library, we perform a fast bitstream analysis from which the workload generated while processing this clip on the given architecture may be estimated. This workload information, in conjunction with a workload model and a performance model of the architecture, is used for the clustering. This entire process does not involve any simulation and is hence extremely fast. We illustrate its utility through a detailed case study using an MPEG-2 decoder application running on an MPSoC platform. As part of validation of our methodology, it was observed that video clips falling into the same cluster exhibit similar worst case buffer backlogs and worst case delays for one macroblock. Overall the results demonstrate that the proposed method provides a very fast and accurate analysis and hence can be of significant benefit to the system designer.

show abstract

Identifying "representative" workloads in designing MpSoC platforms for media processing

Cited by 15 publications

References 12 publications

Scenario Selection and Prediction for DVS-Aware Scheduling of Multimedia Applications

Scenario Selection and Prediction for DVS-Aware Scheduling of Multimedia Applications

Profiling Driven Scenario Detection and Prediction for Multimedia Applications

Fast model-based test case classification for performance analysis of multimedia MPSoC platforms

Contact Info

Product

Resources

About