Task Scheduling Methods for Composable and Predictable MPSoCs
Computer Engineering
2010
Mekelweg 4,
2628 CD Delft
The Netherlands http://ce.et.tudelft.nl/ MSc THESIS
Task Scheduling Methods for Composable and
Predictable MPSoCs
Ba Thang Nguyen
Abstract
Multiprocessor Systems on a Chip (MPSoCs) are suitable platforms for executing complex embedded applications. To reduce the cost of the hardware platform, applications share resources, which may result in inter-application timing interference due to resource request conflicts. Bounding or prohibiting this interference is crucial, as the timing of real-time applications has to be predicted in each possible
CE-MS-2010-29
case. Resources that allow sharing without application interference are denoted as composable. Composability is a desired platform property, as it enables the design and analysis of applications in isolation, and their integration with linear effort. Previous work demonstrates composability for different resources, i.e., processor, interconnect, memory. Processor composability is achieved by utilizing an Operating System (OS) that schedules fixed duration task slots, using a two-level, hierarchical approach. First, the OS determines which application owns the next slot following a strict, preemptive Time Division Multiplexing (TDM) policy, and then it picks and schedules a task of that application. As scheduling decisions are taken exclusively at slots borders, when a task finishes before its slot depletes, the time left is wasted. This may result in low processor utilization for streaming applications for which the execution of a task may start after its predecessor tasks have finished. In this work we propose a new task scheduling strategy, namely application-space task scheduling that eliminates wasted slot time. We make use of the fixed duration slots and the application TDM, to preserve composability, but the application invokes the task scheduler immediately after each task finish, inside its slot. As the application-space task
2010
Mekelweg 4,
2628 CD Delft
The Netherlands http://ce.et.tudelft.nl/ MSc THESIS
Task Scheduling Methods for Composable and
Predictable MPSoCs
Ba Thang Nguyen
Abstract
Multiprocessor Systems on a Chip (MPSoCs) are suitable platforms for executing complex embedded applications. To reduce the cost of the hardware platform, applications share resources, which may result in inter-application timing interference due to resource request conflicts. Bounding or prohibiting this interference is crucial, as the timing of real-time applications has to be predicted in each possible
CE-MS-2010-29
case. Resources that allow sharing without application interference are denoted as composable. Composability is a desired platform property, as it enables the design and analysis of applications in isolation, and their integration with linear effort. Previous work demonstrates composability for different resources, i.e., processor, interconnect, memory. Processor composability is achieved by utilizing an Operating System (OS) that schedules fixed duration task slots, using a two-level, hierarchical approach. First, the OS determines which application owns the next slot following a strict, preemptive Time Division Multiplexing (TDM) policy, and then it picks and schedules a task of that application. As scheduling decisions are taken exclusively at slots borders, when a task finishes before its slot depletes, the time left is wasted. This may result in low processor utilization for streaming applications for which the execution of a task may start after its predecessor tasks have finished. In this work we propose a new task scheduling strategy, namely application-space task scheduling that eliminates wasted slot time. We make use of the fixed duration slots and the application TDM, to preserve composability, but the application invokes the task scheduler immediately after each task finish, inside its slot. As the application-space task
Bibliography: [2] Christian Bienia, Sanjeev Kumar, Jaswinder Pal Singh, and Kai Li, The parsec benchmark suite: Characterization and architectural implications, Tech. report, Princeton University, 2008. [3] Z. Deng and J. W.-S. Liu, Scheduling real-time applications in an open environment, RTSS ’97: Proceedings of the 18th IEEE Real-Time Systems Symposium (Washington, DC, USA), IEEE Computer Society, 1997, p [4] R.P. Dick, The embedded system synthesis benchmarks suite (e3s), 2002. processing domain, Master’s thesis, Technical University of Lund, 2008. [7] G. Bilsen et al., Cyclo-static dataflow, IEEE Transactions on Signal Processing (1996), 44. chip: Concepts, architectures, and implementations, IEEE Design and Test of Computers (2005), no. 5, 414–421. Systems Design and Implementation(OSDI) (1996), 107–121. Characterization, Annual IEEE International Workshop (2001), 3–14. (2010), –. Trans. Des. Autom. Electron. Syst. (2009), no. 1, 1–24. of the IFIP Congress (1974), 74. [16] H. Kopetz, Real-time systems: Design principles for distibuted embedded applications, Kluwer Academic Publishers, 1997. [17] Tei-Wei Kuo and Ching-Hui Li, A fixed-priority-driven open environment for realtime applications, RTSS ’99: Proceedings of the 20th IEEE Real-Time Systems Symposium (Washington, DC, USA), IEEE Computer Society, 1999, p IEEE Int. Symp. on Workload Characterization, 2005, pp. 34–45. Time Technology and Applications Symposium (RTAS 2000) (Washington, DC, USA), IEEE Computer Society, 2000, p u Electronics architecture - time-triggered architecture: A consistent computing platform, IEEE Distributed Systems Online (2002), no [22] Anca Molnos and Kees Goossens, Conservative dynamic energy management for real-time dataflow applications mapped on multiple processors, DSD, 2009, pp A heterogeneous multi-processor architecture template and scalable and flexible protocol for the design of embedded signal processing systems, Design Automation for Embedded Systems (2002), no [25] Dongrui SHE, Fpga platform for emulation of composable and predictable mpsoc power management, Master’s thesis, Eindhoven University of Technology, 2009. Transactions on (2003), no. 7, 560 –576.