Under current analysis, soft real-time tardiness bounds applicable to global earliest-deadline-first scheduling and related policies depend on per-task worst-case execution times. By splitting job budgets to create sub jobs with shorter periods and worst-case execution times, such bounds can be reduced to near zero for implicit-deadline sporadic task systems. However, doing so could potentially cause more preemptions and create problems for synchronization protocols. This paper analyzes this tradeoff between theory and practice by presenting an overhead-aware schedulability study pertaining to job splitting. In this study, real overhead data from a scheduler implementation in LITMUSRT was factored into schedulability analysis. This study shows that despite practical issues affecting job splitting, it can still yield substantial reductions in tardiness bounds for soft real-time systems.
{"title":"Reducing Tardiness under Global Scheduling by Splitting Jobs","authors":"J. Erickson, James H. Anderson","doi":"10.1109/ECRTS.2013.13","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.13","url":null,"abstract":"Under current analysis, soft real-time tardiness bounds applicable to global earliest-deadline-first scheduling and related policies depend on per-task worst-case execution times. By splitting job budgets to create sub jobs with shorter periods and worst-case execution times, such bounds can be reduced to near zero for implicit-deadline sporadic task systems. However, doing so could potentially cause more preemptions and create problems for synchronization protocols. This paper analyzes this tradeoff between theory and practice by presenting an overhead-aware schedulability study pertaining to job splitting. In this study, real overhead data from a scheduler implementation in LITMUSRT was factored into schedulability analysis. This study shows that despite practical issues affecting job splitting, it can still yield substantial reductions in tardiness bounds for soft real-time systems.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116747639","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}
M. Maggio, Enrico Bini, Georgios C. Chasparis, Karl-Erik Årzén
The management of resources among competing QoS-aware applications is often solved by a resource manager (RM) that assigns both the resources and the application service levels. However, this approach requires all applications to inform the RM of the available service levels. Then, the RM has to maximize the "overall quality" by comparing service levels of different applications which are not necessarily comparable. In this paper we describe a Linux implementation of a game-theoretic framework that decouples the two distinct problems of resource assignment and quality setting, solving them in the domain where they naturally belong to. By this approach the RM has linear time complexity in the number of the applications. Our RM is built over the SCHED_DEADLINE Linux scheduling class.
{"title":"A Game-Theoretic Resource Manager for RT Applications","authors":"M. Maggio, Enrico Bini, Georgios C. Chasparis, Karl-Erik Årzén","doi":"10.1109/ECRTS.2013.17","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.17","url":null,"abstract":"The management of resources among competing QoS-aware applications is often solved by a resource manager (RM) that assigns both the resources and the application service levels. However, this approach requires all applications to inform the RM of the available service levels. Then, the RM has to maximize the \"overall quality\" by comparing service levels of different applications which are not necessarily comparable. In this paper we describe a Linux implementation of a game-theoretic framework that decouples the two distinct problems of resource assignment and quality setting, solving them in the domain where they naturally belong to. By this approach the RM has linear time complexity in the number of the applications. Our RM is built over the SCHED_DEADLINE Linux scheduling class.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"126 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128697855","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}
Lock-based resource sharing protocols for single processor systems are well understood and supported in programming languages and in Real-Time Operating Systems. In contrast, multiprocessor resource sharing protocols are less well developed with no agreed best practice. In this paper we propose a new multiprocessor variant of a protocol based on the single processor priority ceiling protocol. The distinctive nature of the new protocol is that tasks waiting to gain access to a resource must service the resource on behalf of other tasks that are waiting for the same resource (but have been preempted). The form of the protocol is motivated by the desire to link the protocol with effective schedulability analysis. The protocol is general purpose, but is developed in this paper for partitioned fixed priority systems with the sporadic task model. Two methods of supporting the protocol are described, as is a prototype `proof of concept' implementation for one of these schemes.
{"title":"A Schedulability Compatible Multiprocessor Resource Sharing Protocol -- MrsP","authors":"A. Burns, A. Wellings","doi":"10.1109/ECRTS.2013.37","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.37","url":null,"abstract":"Lock-based resource sharing protocols for single processor systems are well understood and supported in programming languages and in Real-Time Operating Systems. In contrast, multiprocessor resource sharing protocols are less well developed with no agreed best practice. In this paper we propose a new multiprocessor variant of a protocol based on the single processor priority ceiling protocol. The distinctive nature of the new protocol is that tasks waiting to gain access to a resource must service the resource on behalf of other tasks that are waiting for the same resource (but have been preempted). The form of the protocol is motivated by the desire to link the protocol with effective schedulability analysis. The protocol is general purpose, but is developed in this paper for partitioned fixed priority systems with the sporadic task model. Two methods of supporting the protocol are described, as is a prototype `proof of concept' implementation for one of these schemes.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133633001","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}
Scratchpad memory is an attractive alternative to caches in real-time embedded systems due to its advantages in terms of timing predictability and power consumption. However, dynamic management of scratchpad content is challenging in multitasking environments. To address this issue, we propose the design of a novel Real-Time Scratchpad Memory Unit (RSMU). Our RSMU can be integrated in existing systems with minimal architectural modifications. Furthermore, scratchpad management is performed at the OS level, requiring no application changes. Compared to existing multitasking scratchpad management schemes, our approach improves schedulability by hiding the latency of memory transfers. We demonstrate and evaluate our system design on an embedded FPGA platform.
{"title":"A Dynamic Scratchpad Memory Unit for Predictable Real-Time Embedded Systems","authors":"Saud Wasly, R. Pellizzoni","doi":"10.1109/ECRTS.2013.28","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.28","url":null,"abstract":"Scratchpad memory is an attractive alternative to caches in real-time embedded systems due to its advantages in terms of timing predictability and power consumption. However, dynamic management of scratchpad content is challenging in multitasking environments. To address this issue, we propose the design of a novel Real-Time Scratchpad Memory Unit (RSMU). Our RSMU can be integrated in existing systems with minimal architectural modifications. Furthermore, scratchpad management is performed at the OS level, requiring no application changes. Compared to existing multitasking scratchpad management schemes, our approach improves schedulability by hiding the latency of memory transfers. We demonstrate and evaluate our system design on an embedded FPGA platform.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123661268","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}
A number of preemptive real-time scheduling algorithms, such as Earliest Deadline First (EDF), are known to be optimal on uni-processor systems under specified assumptions. However, no uni-processor optimal algorithm exists under the non-preemptive scheduling paradigm. Hence preemptive schemes strictly dominate non-preemptive schemes with respect to uni-processor feasibility. However, the 'goodness' of non-preemptive schemes, compared to uni-processor optimal preemptive scheduling schemes such as EDF, which can also be referred to as its sub-optimality, has not been fully investigated yet. In this paper, we apply resource augmentation, specifically processor speed-up, to quantify the sub-optimality of non-preemptive scheduling with respect to EDF, and apply the results to guarantee user specified upper-bounds on the preemption related scheduling costs. In particular, we derive an upper bound on the minimum processor speed-up required to guarantee the non-preemptive feasibility of tasks that are deemed feasible under the preemptive EDF, and we prove that, in the cases where, for all tasks in the task set, the largest execution requirement is not greater than the shortest deadline, this bound is equal to 4. We also show how the proposed approach enables a system designer to choose an optimal processor, in order to, e.g., guarantee specified upper bounds on the preemption related overheads.
{"title":"Quantifying the Sub-optimality of Non-preemptive Real-Time Scheduling","authors":"Abhilash Thekkilakattil, R. Dobrin, S. Punnekkat","doi":"10.1109/ECRTS.2013.22","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.22","url":null,"abstract":"A number of preemptive real-time scheduling algorithms, such as Earliest Deadline First (EDF), are known to be optimal on uni-processor systems under specified assumptions. However, no uni-processor optimal algorithm exists under the non-preemptive scheduling paradigm. Hence preemptive schemes strictly dominate non-preemptive schemes with respect to uni-processor feasibility. However, the 'goodness' of non-preemptive schemes, compared to uni-processor optimal preemptive scheduling schemes such as EDF, which can also be referred to as its sub-optimality, has not been fully investigated yet. In this paper, we apply resource augmentation, specifically processor speed-up, to quantify the sub-optimality of non-preemptive scheduling with respect to EDF, and apply the results to guarantee user specified upper-bounds on the preemption related scheduling costs. In particular, we derive an upper bound on the minimum processor speed-up required to guarantee the non-preemptive feasibility of tasks that are deemed feasible under the preemptive EDF, and we prove that, in the cases where, for all tasks in the task set, the largest execution requirement is not greater than the shortest deadline, this bound is equal to 4. We also show how the proposed approach enables a system designer to choose an optimal processor, in order to, e.g., guarantee specified upper bounds on the preemption related overheads.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125368036","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 increasing complexity and heterogeneity of avionics networks make resource optimization a challenging task. In contrast to many previous approaches pursuing the optimization of traffic-source mapping and backbone network analysis, our work presented herein mainly focuses on the optimization of interconnection devices for multi-cluster avionics networks. In this paper, we introduce an optimized interconnection device, integrating novel frame packing strategies and schedulability analysis to enhance the communications between an AFDX-like backbone network and various peripheral sensor/actuator networks in terms of resource savings. The performance analysis conducted on a representative avionics communication architecture highlights the efficiency of our proposal to save resources particularly consumed bandwidth. These latter is considered as an important feature for avionics applications to guarantee easy incremental design during the long lifetime of an aircraft.
{"title":"Interconnection Optimization for Multi-cluster Avionics Networks","authors":"H. Ayed, A. Mifdaoui, C. Fraboul","doi":"10.1109/ECRTS.2013.25","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.25","url":null,"abstract":"The increasing complexity and heterogeneity of avionics networks make resource optimization a challenging task. In contrast to many previous approaches pursuing the optimization of traffic-source mapping and backbone network analysis, our work presented herein mainly focuses on the optimization of interconnection devices for multi-cluster avionics networks. In this paper, we introduce an optimized interconnection device, integrating novel frame packing strategies and schedulability analysis to enhance the communications between an AFDX-like backbone network and various peripheral sensor/actuator networks in terms of resource savings. The performance analysis conducted on a representative avionics communication architecture highlights the efficiency of our proposal to save resources particularly consumed bandwidth. These latter is considered as an important feature for avionics applications to guarantee easy incremental design during the long lifetime of an aircraft.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128796450","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}
Philip Axer, Sophie Quinton, M. Neukirchner, R. Ernst, Björn Döbel, Hermann Härtig
The advent of multi- and many-core processors comes with new challenges and opportunities for the designer of embedded real-time applications. By using parallel programming techniques (e.g. OpenMP) software engineers can leverage from the available hardware parallelism and speed up the algorithms. The inherent redundancy of multi-core architectures can also be used to implement fault-tolerance by executing code redundantly on multiple cores in parallel. Parallel programming and redundant execution are typical examples for fork-join tasks in which the program is partially parallelized. However, complex synchronization of parallel segments across multiple cores can cause unanticipated effects. This is especially problematic in hard real-time applications where data must be available in bounded time (e.g. stereo vision for pedestrian detection). The contribution of this work is a novel worst-case response time analysis which accounts for synchronization of fork-join tasks with arbitrary deadlines. We apply the analysis to the Romain framework which extends the L4 micro kernel by redundant multithreading targeted towards fault-tolerant embedded systems. By using formal analysis, we show that parallelizing workloads can lead to drastic performance impairments compared to traditional sequential execution if not done carefully.
{"title":"Response-Time Analysis of Parallel Fork-Join Workloads with Real-Time Constraints","authors":"Philip Axer, Sophie Quinton, M. Neukirchner, R. Ernst, Björn Döbel, Hermann Härtig","doi":"10.1109/ECRTS.2013.31","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.31","url":null,"abstract":"The advent of multi- and many-core processors comes with new challenges and opportunities for the designer of embedded real-time applications. By using parallel programming techniques (e.g. OpenMP) software engineers can leverage from the available hardware parallelism and speed up the algorithms. The inherent redundancy of multi-core architectures can also be used to implement fault-tolerance by executing code redundantly on multiple cores in parallel. Parallel programming and redundant execution are typical examples for fork-join tasks in which the program is partially parallelized. However, complex synchronization of parallel segments across multiple cores can cause unanticipated effects. This is especially problematic in hard real-time applications where data must be available in bounded time (e.g. stereo vision for pedestrian detection). The contribution of this work is a novel worst-case response time analysis which accounts for synchronization of fork-join tasks with arbitrary deadlines. We apply the analysis to the Romain framework which extends the L4 micro kernel by redundant multithreading targeted towards fault-tolerant embedded systems. By using formal analysis, we show that parallelizing workloads can lead to drastic performance impairments compared to traditional sequential execution if not done carefully.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128114405","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}
Several models have been proposed to represent conditional executions and dependencies among real-time concurrent tasks for the purpose of schedulability analysis. Among them, task graphs with cyclic recurrent behavior, i.e., those modeled with a single source vertex and a period parameter specifying the minimum amount of time that must elapse between successive activations of the source job, allow for efficient schedulability analysis based on the periodicity of the request and demand bound functions (em rbf and dbf). We leverage results from max-plus algebra to identify a recurrent term in rbf and dbf of general task graph models, even when the execution is neither recurrent nor controlled by a period parameter. As such, the asymptotic complexity of calculating rbf and dbf is independent from the length of the time interval. Experimental results demonstrate significant improvements on the runtime for system schedulability analysis.
{"title":"Outstanding Paper Award: Using Max-Plus Algebra to Improve the Analysis of Non-cyclic Task Models","authors":"Haibo Zeng, M. Natale","doi":"10.1109/ECRTS.2013.30","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.30","url":null,"abstract":"Several models have been proposed to represent conditional executions and dependencies among real-time concurrent tasks for the purpose of schedulability analysis. Among them, task graphs with cyclic recurrent behavior, i.e., those modeled with a single source vertex and a period parameter specifying the minimum amount of time that must elapse between successive activations of the source job, allow for efficient schedulability analysis based on the periodicity of the request and demand bound functions (em rbf and dbf). We leverage results from max-plus algebra to identify a recurrent term in rbf and dbf of general task graph models, even when the execution is neither recurrent nor controlled by a period parameter. As such, the asymptotic complexity of calculating rbf and dbf is independent from the length of the time interval. Experimental results demonstrate significant improvements on the runtime for system schedulability analysis.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131439602","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}
Computation offloading concept has been recently adopted to improve the performance of embedded systems by moving some computation-intensive tasks (partially or wholly) to a powerful remote server. In this paper, we consider a computation offloading problem for frame-based real-time tasks, in which all the tasks have the same arrival time and the same relative deadline/period, by adopting the total bandwidth server (TBS) as resource reservations in the server side (remote execution unit). We prove that the problem is N P-complete and propose two algorithms in this paper. The first algorithm is a greedy algorithm with low complexity and provides a quick heuristic approach to decide which tasks to be offloaded and how the tasks are scheduled. The maximum finishing time of the solution derived from the greedy algorithm is at most twice of the finishing time (make span, maximal on the client and on the server) of any schedule. The second algorithm is a dynamic programming approach, which builds a three-dimensional table and requires pseudo-polynomial time complexity, to make an optimal decision for computation offloading. The algorithms are evaluated with a case study of a surveillance system and synthesized benchmarks.
{"title":"Computation Offloading for Frame-Based Real-Time Tasks with Resource Reservation Servers","authors":"Anas Toma, Jian-Jia Chen","doi":"10.1109/ECRTS.2013.21","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.21","url":null,"abstract":"Computation offloading concept has been recently adopted to improve the performance of embedded systems by moving some computation-intensive tasks (partially or wholly) to a powerful remote server. In this paper, we consider a computation offloading problem for frame-based real-time tasks, in which all the tasks have the same arrival time and the same relative deadline/period, by adopting the total bandwidth server (TBS) as resource reservations in the server side (remote execution unit). We prove that the problem is N P-complete and propose two algorithms in this paper. The first algorithm is a greedy algorithm with low complexity and provides a quick heuristic approach to decide which tasks to be offloaded and how the tasks are scheduled. The maximum finishing time of the solution derived from the greedy algorithm is at most twice of the finishing time (make span, maximal on the client and on the server) of any schedule. The second algorithm is a dynamic programming approach, which builds a three-dimensional table and requires pseudo-polynomial time complexity, to make an optimal decision for computation offloading. The algorithms are evaluated with a case study of a surveillance system and synthesized benchmarks.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131235552","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}
H. Chwa, Jinkyu Lee, Kieu-My Phan, A. Easwaran, I. Shin
The trend towards multi-core/many-core architectures is well underway. It is therefore becoming very important to develop software in ways that take advantage of such parallel architectures. This particularly entails a shift in programming paradigms towards fine-grained, thread-parallel computing. Many parallel programming models have been introduced targeting such intra-task thread-level parallelism. However, most successful results on traditional multi-core real-time scheduling are focused on sequential programming models. For example, thread-level parallelism is not properly captured into the concept of interference, which is key to many schedulability analysis techniques. Thereby, most interference-based analysis techniques are not directly applicable to parallel programming models. Motivated by this, we extend the notion of interference to capture thread-level parallelism more accurately. We then leverage the proposed notion of parallelism-aware interference to derive efficient EDF schedulability tests that are directly applicable to synchronous parallel task models on multi-core platforms. Our evaluation results indicate that the proposed analysis significantly advances the state-of-the-art in EDF schedulability analysis for synchronous parallel tasks.
{"title":"Global EDF Schedulability Analysis for Synchronous Parallel Tasks on Multicore Platforms","authors":"H. Chwa, Jinkyu Lee, Kieu-My Phan, A. Easwaran, I. Shin","doi":"10.1109/ECRTS.2013.14","DOIUrl":"https://doi.org/10.1109/ECRTS.2013.14","url":null,"abstract":"The trend towards multi-core/many-core architectures is well underway. It is therefore becoming very important to develop software in ways that take advantage of such parallel architectures. This particularly entails a shift in programming paradigms towards fine-grained, thread-parallel computing. Many parallel programming models have been introduced targeting such intra-task thread-level parallelism. However, most successful results on traditional multi-core real-time scheduling are focused on sequential programming models. For example, thread-level parallelism is not properly captured into the concept of interference, which is key to many schedulability analysis techniques. Thereby, most interference-based analysis techniques are not directly applicable to parallel programming models. Motivated by this, we extend the notion of interference to capture thread-level parallelism more accurately. We then leverage the proposed notion of parallelism-aware interference to derive efficient EDF schedulability tests that are directly applicable to synchronous parallel task models on multi-core platforms. Our evaluation results indicate that the proposed analysis significantly advances the state-of-the-art in EDF schedulability analysis for synchronous parallel tasks.","PeriodicalId":247550,"journal":{"name":"2013 25th Euromicro Conference on Real-Time Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133220629","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：