{"title":"ICPE '20: ACM/SPEC International Conference on Performance Engineering, Edmonton, AB, Canada, April 20-24, 2020","authors":"","doi":"10.1145/3358960","DOIUrl":"https://doi.org/10.1145/3358960","url":null,"abstract":"","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"158 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73565443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the near future, the internet-of-things (IoT) will encompass billions of (small) devices, many of which will only communicate wireless, and will not be connected to a fixed power supply. Powering these devices with replaceable batteries will not be an option, hence, we have to come to self-powered IoT nodes. This talk addresses some of the major challenges and paths to solutions for self-contained IoT devices, building on our experience in two recently completed FP7 projects (Sensation and e-balance) as well upon our plans in the newly started research program ZERO.
{"title":"Zero-Energy Internet-of-Things: Energy-SIM'18 Workshop Keynote Abstract","authors":"B. Haverkort","doi":"10.1145/3185768.3186314","DOIUrl":"https://doi.org/10.1145/3185768.3186314","url":null,"abstract":"In the near future, the internet-of-things (IoT) will encompass billions of (small) devices, many of which will only communicate wireless, and will not be connected to a fixed power supply. Powering these devices with replaceable batteries will not be an option, hence, we have to come to self-powered IoT nodes. This talk addresses some of the major challenges and paths to solutions for self-contained IoT devices, building on our experience in two recently completed FP7 projects (Sensation and e-balance) as well upon our plans in the newly started research program ZERO.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"52 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74574077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Erwin Van Eyk, A. Iosup, Cristina L. Abad, Johannes Grohmann, Simon Eismann
As a key part of the serverless computing paradigm, Function-as-a-Service (FaaS) platforms enable users to run arbitrary functions without being concerned about operational issues. However, there are several performance-related issues surrounding the state-of-the-art FaaS platforms that can deter widespread adoption of FaaS, including sizeable overheads, unreliable performance, and new forms of the cost-performance trade-off. In this work we, the SPEC RG Cloud Group, identify six performance-related challenges that arise specifically in this FaaS model, and present our roadmap to tackle these problems in the near future. This paper aims at motivating the community to solve these challenges together.
{"title":"A SPEC RG Cloud Group's Vision on the Performance Challenges of FaaS Cloud Architectures","authors":"Erwin Van Eyk, A. Iosup, Cristina L. Abad, Johannes Grohmann, Simon Eismann","doi":"10.1145/3185768.3186308","DOIUrl":"https://doi.org/10.1145/3185768.3186308","url":null,"abstract":"As a key part of the serverless computing paradigm, Function-as-a-Service (FaaS) platforms enable users to run arbitrary functions without being concerned about operational issues. However, there are several performance-related issues surrounding the state-of-the-art FaaS platforms that can deter widespread adoption of FaaS, including sizeable overheads, unreliable performance, and new forms of the cost-performance trade-off. In this work we, the SPEC RG Cloud Group, identify six performance-related challenges that arise specifically in this FaaS model, and present our roadmap to tackle these problems in the near future. This paper aims at motivating the community to solve these challenges together.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74820978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applying model-based performance prediction requires that an up-to-date Performance Model (PM) is available throughout the development process. Creating such a model manually is an expensive process that is unsuitable for agile software development aiming to produce rapid releases in short cycles. Existing approaches automate the extraction of a PM based on reverse engineering and/or measurements techniques. However, these approaches require to monitor and analyse the whole application. Thus, they are too costly to be applied frequently, up to after each code change. Moreover, keeping potential manual changes of the PM is another challenge as long the PM is regenerated from scratch every time. To address these problems, this paper envisions an approach for efficient continuous integration of a parametrised performance model in an agile development process. Our work will combine static code analysis with adaptive, automatic, dynamic analysis covering updated parts of code to update the PM with parameters, like resource demands and branching probabilities. The benefit of our approach will be to automatically keep the PM up-to-date throughout the development process which enables the proactive identification of upcoming performance problems and provides a foundation for evaluating design alternatives at low costs.
{"title":"Continuous Integration of Performance Model","authors":"Manar Mazkatli, A. Koziolek","doi":"10.1145/3185768.3186285","DOIUrl":"https://doi.org/10.1145/3185768.3186285","url":null,"abstract":"Applying model-based performance prediction requires that an up-to-date Performance Model (PM) is available throughout the development process. Creating such a model manually is an expensive process that is unsuitable for agile software development aiming to produce rapid releases in short cycles. Existing approaches automate the extraction of a PM based on reverse engineering and/or measurements techniques. However, these approaches require to monitor and analyse the whole application. Thus, they are too costly to be applied frequently, up to after each code change. Moreover, keeping potential manual changes of the PM is another challenge as long the PM is regenerated from scratch every time. To address these problems, this paper envisions an approach for efficient continuous integration of a parametrised performance model in an agile development process. Our work will combine static code analysis with adaptive, automatic, dynamic analysis covering updated parts of code to update the PM with parameters, like resource demands and branching probabilities. The benefit of our approach will be to automatically keep the PM up-to-date throughout the development process which enables the proactive identification of upcoming performance problems and provides a foundation for evaluating design alternatives at low costs.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84356686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When processes join a common FCFS queue to acquire or release resources in an object pool of fixed size, deadlock occurs if the process at the head of the queue wishes to acquire a resource when the pool is empty, even if a process wishing to relinquish a resource is queued behind. We describe a state machine representation of this problem. We use the representation to develop a discrete time Markov chain analysis to identify the load conditions under which deadlock is most likely to occur and how soon it is likely to occur. We show that deadlock occurs almost surely regardless of the load, and that the time to the onset of deadlock depends on combinations of the request rate for resources in the pool, the average holding time of the resources, and the size of the pool. Calculations corroborate the intuition that deadlock will occur sooner at heavy loads or when the resource pool is small. A connection will be made between this problem and the problem of random walks with a single absorbing and a single reflecting barrier.
{"title":"Predicting the Time to Migrate Into Deadlock Using a Discrete Time Markov Chain","authors":"A. Bondi","doi":"10.1145/3185768.3186403","DOIUrl":"https://doi.org/10.1145/3185768.3186403","url":null,"abstract":"When processes join a common FCFS queue to acquire or release resources in an object pool of fixed size, deadlock occurs if the process at the head of the queue wishes to acquire a resource when the pool is empty, even if a process wishing to relinquish a resource is queued behind. We describe a state machine representation of this problem. We use the representation to develop a discrete time Markov chain analysis to identify the load conditions under which deadlock is most likely to occur and how soon it is likely to occur. We show that deadlock occurs almost surely regardless of the load, and that the time to the onset of deadlock depends on combinations of the request rate for resources in the pool, the average holding time of the resources, and the size of the pool. Calculations corroborate the intuition that deadlock will occur sooner at heavy loads or when the resource pool is small. A connection will be made between this problem and the problem of random walks with a single absorbing and a single reflecting barrier.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"101 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86180490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Cortellessa, A. Marco, Daniele Di Pompeo, Francesco Gallo, Stefano Pace, L. Pomante, Walter Tiberti
The reconfiguration of Wireless Sensor Networks is a well-known problem that has been tackled in the last few years mostly with approaches operating at the network level. In this paper, we introduce an approach for the automated reconfiguration of WSNs, driven by energy problems, at the level of software application. In particular, we define reconfiguration actions with Proteus, that is a framework to specify and implement reconfiguration plans on top of Agilla, that is a mobile agent middleware for Wireless Sensor Networks. A Reconfiguration Engine acts on agents within a WSN to activate reconfiguration plans when required, e.g. when the batteries of several sensors located in a critical geographical area are exhausted. We have started to experiment the approach on a real application.
{"title":"Energy-Driven Reconfiguration of Applications for Wireless Sensor Networks","authors":"V. Cortellessa, A. Marco, Daniele Di Pompeo, Francesco Gallo, Stefano Pace, L. Pomante, Walter Tiberti","doi":"10.1145/3185768.3186312","DOIUrl":"https://doi.org/10.1145/3185768.3186312","url":null,"abstract":"The reconfiguration of Wireless Sensor Networks is a well-known problem that has been tackled in the last few years mostly with approaches operating at the network level. In this paper, we introduce an approach for the automated reconfiguration of WSNs, driven by energy problems, at the level of software application. In particular, we define reconfiguration actions with Proteus, that is a framework to specify and implement reconfiguration plans on top of Agilla, that is a mobile agent middleware for Wireless Sensor Networks. A Reconfiguration Engine acts on agents within a WSN to activate reconfiguration plans when required, e.g. when the batteries of several sensors located in a critical geographical area are exhausted. We have started to experiment the approach on a real application.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"170 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76564618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This work focuses on Design Space Exploration for embedded systems based on heterogeneous parallel architectures and subjected to mixed-criticality constraints. In particular, it presents a criticality-aware evolutionary approach integrated into a reference Electronic System Level HW/SW Co-Design flow
{"title":"Criticality-aware Design Space Exploration for Mixed-Criticality Embedded Systems","authors":"V. Muttillo, G. Valente, L. Pomante","doi":"10.1145/3185768.3185769","DOIUrl":"https://doi.org/10.1145/3185768.3185769","url":null,"abstract":"This work focuses on Design Space Exploration for embedded systems based on heterogeneous parallel architectures and subjected to mixed-criticality constraints. In particular, it presents a criticality-aware evolutionary approach integrated into a reference Electronic System Level HW/SW Co-Design flow","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73651471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Model transformations are an essential operation on models which is applied at design time and even at run time. For this, the performance of transformations is an important aspect, which needs to be considered. The current research takes only the improvement of transformation engines into account but there is no method or tool support to help engineers to identify performance bottlenecks in their transformation definition. In this paper we present our proposed approach to develop a method for performance engineering of model transformations. This method should support engineers to improve the performance of their defined transformations by providing visualizations of reasons for performance problems and offering possible refactorings for a transformation which can improve its performance.
{"title":"Towards Performance Engineering of Model Transformation","authors":"Raffaela Groner, M. Tichy, Steffen Becker","doi":"10.1145/3185768.3186305","DOIUrl":"https://doi.org/10.1145/3185768.3186305","url":null,"abstract":"Model transformations are an essential operation on models which is applied at design time and even at run time. For this, the performance of transformations is an important aspect, which needs to be considered. The current research takes only the improvement of transformation engines into account but there is no method or tool support to help engineers to identify performance bottlenecks in their transformation definition. In this paper we present our proposed approach to develop a method for performance engineering of model transformations. This method should support engineers to improve the performance of their defined transformations by providing visualizations of reasons for performance problems and offering possible refactorings for a transformation which can improve its performance.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87983051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Software performance predictions are an established part of an engineering like software development process and therefore relevant to enable high quality and to ensure requirement fulfillment. Software Performance Engineers use for that model-based performance predictions approaches. However, current predictions approaches are based on the assumption of single core CPU systems. To enable Software Performance Engineers to further give accurate predictions also for multicore systems, which are by now state of the art, we need to adapt our current prediction models. On the poster, we discuss the upcoming challenges to be tackled to increase the accuracy of the performance predictions models.
{"title":"Challenges in Multicore Performance Predictions","authors":"Markus Frank, Floriment Klinaku, Steffen Becker","doi":"10.1145/3185768.3185773","DOIUrl":"https://doi.org/10.1145/3185768.3185773","url":null,"abstract":"Software performance predictions are an established part of an engineering like software development process and therefore relevant to enable high quality and to ensure requirement fulfillment. Software Performance Engineers use for that model-based performance predictions approaches. However, current predictions approaches are based on the assumption of single core CPU systems. To enable Software Performance Engineers to further give accurate predictions also for multicore systems, which are by now state of the art, we need to adapt our current prediction models. On the poster, we discuss the upcoming challenges to be tackled to increase the accuracy of the performance predictions models.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91516579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The modeling of the relationship between power usage and performance for complex computing systems is challenging due to the vast amount of tunable parameters that influence both metrics. To simplify the energy management of information systems from individual embedded machines to whole data centers we use a modular, hierarchical concept called Energy/Utility to model individual parts of a system. We present first results that show the decomposition of an individual asymmetric multi-processing system into hardware and software models. We show that using the Energy/Utility approach these models can stay manageable reducing total benchmark running time and modeling overhead while providing sufficiently high precision for performance and energy usage prediction.
{"title":"Modular Energy Modeling using Energy/Utility","authors":"Marcus Hähnel, Till Smejkal","doi":"10.1145/3185768.3186311","DOIUrl":"https://doi.org/10.1145/3185768.3186311","url":null,"abstract":"The modeling of the relationship between power usage and performance for complex computing systems is challenging due to the vast amount of tunable parameters that influence both metrics. To simplify the energy management of information systems from individual embedded machines to whole data centers we use a modular, hierarchical concept called Energy/Utility to model individual parts of a system. We present first results that show the decomposition of an individual asymmetric multi-processing system into hardware and software models. We show that using the Energy/Utility approach these models can stay manageable reducing total benchmark running time and modeling overhead while providing sufficiently high precision for performance and energy usage prediction.","PeriodicalId":10596,"journal":{"name":"Companion of the 2018 ACM/SPEC International Conference on Performance Engineering","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84658000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：