Filters








309 Hits in 8.3 sec

Reducing Response-Time Bounds for DAG-Based Task Systems on Heterogeneous Multicore Platforms

Kecheng Yang, Ming Yang, James H. Anderson
2016 Proceedings of the 24th International Conference on Real-Time Networks and Systems - RTNS '16  
This paper considers for the first time end-to-end responsetime analysis for DAG-based real-time task systems implemented on heterogeneous multicore platforms.  ...  It is shown that, by combining many such DAGs into one of higher utilization, response-time bounds can often be drastically lowered.  ...  Acknowledgments: We thank Alan Gatherer, Lee Mc-Fearin, and Peter Yan for bringing the problem studied in this paper to our attention and for answering many questions regarding cellular base stations.  ... 
doi:10.1145/2997465.2997486 dblp:conf/rtns/YangYA16 fatcat:cqfkmvjrxvaqxnyz24fmuk3e3y

High performance scheduling of mixed-mode DAGs on heterogeneous multicores [article]

Agnes Rohlin, Henrik Fahlgren, Miquel Pericas
2019 arXiv   pre-print
the amount of resources used for each task.  ...  At the same time, modern HPC systems are becoming increasingly heterogeneous to address the requirements of energy efficiency.  ...  Scheduling DAGs on heterogeneous multicores is a well studied problem in the context of single-threaded task DAGs [3-6, 11, 12] .  ... 
arXiv:1901.05907v2 fatcat:3j2mcdgimbd2hpp4f4remfjeey

Parallel Programming Models for Dense Linear Algebra on Heterogeneous Systems

2016 Supercomputing Frontiers and Innovations  
the next generation of parallel programming models for high-performance linear algebra libraries on heterogeneous systems.  ...  We present a review of the current best practices in parallel programming models for dense linear algebra (DLA) on heterogeneous architectures.  ...  Dense Linear Algebra on Heterogeneous Systems Parallel Programming Models for Dense Linear Algebra on Heterogeneous Systems  ... 
doi:10.14529/jsfi150405 fatcat:avnmwu4dozdmjksknrlznhpv7u

A Survey of Techniques for Reducing Interference in Real-time Applications on Multicore Platforms

Tamara Lugo, Santiago Lozano, Javier Fernandez, Jesus Carretero
2022 IEEE Access  
This survey reviews the scientific literature on techniques for reducing interference in real-time multicore systems, focusing on the approaches proposed between 2015 and 2020.  ...  INDEX TERMS Real-time systems, architecture, multicore, timing analysis, schedulability analysis, WCET, co-runner interference.  ...  They presented a schedulability analysis based on Timed Automata and the symbolic verification method for heterogeneous multicore real-time systems. Moulik et al.  ... 
doi:10.1109/access.2022.3151891 fatcat:vutgetjua5byxczcivmw2esqtq

Energy and Delay Optimization of Heterogeneous Multicore Wireless Multimedia Sensor Nodes by Adaptive Genetic-Simulated Annealing Algorithm

Xing Liu, Haiying Zhou, Jianwen Xiang, Shengwu Xiong, Kun Mean Hou, Christophe de Vaulx, Huan Wang, Tianhui Shen, Qing Wang
2018 Wireless Communications and Mobile Computing  
This platform uses both the heterogeneous multicore architecture and the dynamic voltage and frequency scaling (DVFS) technique.  ...  Then, based on this hardware platform, an energy and delay multiobjective optimization algorithm and a DVFS adaption algorithm are investigated.  ...  The M-GA is designed for the real-time tasks on the homogeneous multicore system. The T-GA is designed for the general tasks on the heterogeneous multicore system.  ... 
doi:10.1155/2018/7494829 fatcat:jsrrq5slcvg2rkamxdsue5ktve

Optimized partitioning and priority assignment of real-time applications on heterogeneous platforms with hardware acceleration

Daniel Casini, Paolo Pazzaglia, Alessandro Biondi, Marco Di Natale
2022 Journal of systems architecture  
To this end, this paper proposes a holistic framework to help designers partition real-time applications on heterogeneous platforms with hardware accelerators.  ...  Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities.  ...  A response time analysis for a DAG task on a heterogeneous platform with a single hardware accelerator is presented in [66] .  ... 
doi:10.1016/j.sysarc.2022.102416 fatcat:4ucvbckmjbbybc3lgz3xn6ymea

Analysis for supporting real-time computer vision workloads using OpenVX on multicore+GPU platforms

Kecheng Yang, Glenn A. Elliott, James H. Anderson
2015 Proceedings of the 23rd International Conference on Real Time and Networks Systems - RTNS '15  
OpenVX uses a graph-based software architecture designed to enable efficient computation on heterogeneous platforms that may include CPUs, graphics processing units (GPUs), digital signal processors (DSPs  ...  Additionally, they enable bounds on frame buffering requirements to be determined.  ...  Based on this, Elliott et al. [19] established an end-to-end latency bound L v i for each task τ v i in the original sporadic DAG task system τ.  ... 
doi:10.1145/2834848.2834863 dblp:conf/rtns/YangEA15 fatcat:dw2yhf2bmndhnlw3bifhtvwf5u

Virtual Gang based Scheduling of Real-Time Tasks on Multicore Platforms [article]

Waqar Ali and Rodolfo Pellizzoni and Heechul Yun
2020 arXiv   pre-print
We propose a virtual-gang based parallel real-time task scheduling approach for multicore platforms.  ...  real-time tasks on multicore.  ...  Conclusion We presented a virtual gang based parallel real-time task scheduling approach for multicore platforms.  ... 
arXiv:1912.10959v2 fatcat:rjuxnl7gwvgqfokwzfikzxnvca

Supporting Graph-Based Real-Time Applications in Distributed Systems

Cong Liu, James H. Anderson
2011 2011 IEEE 17th International Conference on Embedded and Real-Time Computing Systems and Applications  
In this paper, a clustered scheduling algorithm is proposed for soft real-time PGM-specified distributed task systems for which bounded deadline tardiness is acceptable.  ...  Prior work has shown how to schedule PGMspecified systems on uniprocessors and globally-scheduled multiprocessors.  ...  With the growing prevalence of multicore platforms, it is inevitable that such DAG-based real-time applications will be deployed in distributed systems where multicore machines are used as per-node computers  ... 
doi:10.1109/rtcsa.2011.72 dblp:conf/rtcsa/LiuA11 fatcat:fzzzffq3qzerlelvfb65r5hvrq

StarPU: a unified platform for task scheduling on heterogeneous multicore architectures

Cédric Augonnet, Samuel Thibault, Raymond Namyst, Pierre-André Wacrenier
2010 Concurrency and Computation  
The main goal of StarPU is to provide numerical kernel designers with a convenient way to generate parallel tasks over heterogeneous hardware on the one hand, and easily develop and tune powerful scheduling  ...  In addition to substantial improvements regarding execution times, we have obtained consistent superlinear parallelism by actually exploiting the heterogeneous nature of the machine.  ...  data parallelism on heterogeneous platforms.  ... 
doi:10.1002/cpe.1631 fatcat:dkvtciewkjbiro5hwadontmu4e

StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures [chapter]

Cédric Augonnet, Samuel Thibault, Raymond Namyst, Pierre-André Wacrenier
2009 Lecture Notes in Computer Science  
The main goal of StarPU is to provide numerical kernel designers with a convenient way to generate parallel tasks over heterogeneous hardware on the one hand, and easily develop and tune powerful scheduling  ...  In addition to substantial improvements regarding execution times, we have obtained consistent superlinear parallelism by actually exploiting the heterogeneous nature of the machine.  ...  data parallelism on heterogeneous platforms.  ... 
doi:10.1007/978-3-642-03869-3_80 fatcat:qdmzcpe4jjb4ximx5elua2bfye

Exploring Weak Dependencies in DAG Scheduling

Nam Ma, Yinglong Xia, Viktor K. Prasanna
2011 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum  
For a class of task graphs, on a state-of-the-art general-purpose multicore system, the weak dependency based scheduler runs 4x faster than a baseline scheduler that is based on the traditional scheduling  ...  We perform experiments to study the impact of weak dependency based scheduling method on the execution time using a representative set of task graphs for exact inference in junction trees.  ...  Platforms We conducted experiments on an 8-core AMD Opteron based system.  ... 
doi:10.1109/ipdps.2011.204 dblp:conf/ipps/MaXP11 fatcat:mzx35tvm4fa4fjqwrlevj5dzxi

Hierarchical Task-Based Programming With StarSs

Judit Planas, Rosa M. Badia, Eduard Ayguadé, Jesus Labarta, Jack Dongarra, Bernard Tourancheau
2009 The international journal of high performance computing applications  
Programming models for multicore and many-core systems are listed as one of the main challenges in the near future for computing research.  ...  A prototype implementation of such a hierarchical task-based programming model that combines a first task level with SMPSs and a second task level with CellSs is presented.  ...  Her current research interest are performance prediction and modeling of MPI programs and programming models for complex platforms (from multicore to the Grid).  ... 
doi:10.1177/1094342009106195 fatcat:ykbrmwbis5hxhpqskolh4zd5a4

Dynamic Task Scheduling Methods in Heterogeneous Systems: A Survey

D. I.GeorgeAmalarethinam, A. Maria Josphin
2015 International Journal of Computer Applications  
A Parallel application can be represented by a Directed Acyclic Graph (DAG), which represents the dependency among tasks, based on their execution time and communication time.  ...  In mapping of parallel tasks, scheduling plays an important role. The scheduling decisions are based on the dynamic parameters that may change during run time.  ...  CBHD Algorithm Abdelkader and Omara proposed Clustering based HEFT with Duplication, used for efficient scheduling and mapping for tasks on heterogeneous systems, to break the program into subtasks and  ... 
doi:10.5120/19318-0859 fatcat:qxnjvseeajcyfiyzdq4xxtonw4

A Runtime Approach to Dynamic Resource Allocation for Sparse Direct Solvers

Andra-Ecaterina Hugo, Abdou Guermouche, Pierre-Andre Wacrenier, Raymond Namyst
2014 2014 43rd International Conference on Parallel Processing  
In this paper, we show how runtime system-based scheduling contexts can be used to dynamically enforce locality of parallel tasks on multicore machines.  ...  To face the advent of multicore processors and the ever increasing complexity of hardware architectures, programming models based on DAG-of-tasks parallelism regained popularity in the high performance  ...  This hierarchy is eventually mapped on scheduling contexts at the runtime system level which is responsible for dynamic resource management.  ... 
doi:10.1109/icpp.2014.57 dblp:conf/icpp/HugoGWN14 fatcat:chugulbzhfd7xgv5vnongaoi3e
« Previous Showing results 1 — 15 out of 309 results