Task-FIFO co-scheduling of streaming applications on MPSoCs with predictable memory hierarchy
| Autor: | Sander Stuijk, Qi Tang, Twan Basten, Marc Geilen, Ji-Bo Wei |
|---|---|
| Přispěvatelé: | Electronic Systems, Cyber-Physical Systems Center Eindhoven, CompSOC Lab- Predictable & Composable Embedded Systems |
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Schedule
Informatics Flat memory model Computer science Dataflow Distributed computing Multiprocessing 02 engineering and technology Parallel computing MPSoC Scheduling (computing) 0202 electrical engineering electronic engineering information engineering Co scheduling Latency (engineering) Direct memory access TS - Technical Sciences 020203 distributed computing Industrial Innovation Hardware_MEMORYSTRUCTURES Memory hierarchy Job shop scheduling SDFG Scheduling Pareto principle FIFO Uniform memory access Load balancing (computing) 020202 computer hardware & architecture ESI - Embedded Systems Innovations Hardware and Architecture Scratch pad memory 2016 ICT Self-timed Software |
| Zdroj: | ACM Transactions on Embedded Computing Systems, 16(2):49, 49:1-49:25. Association for Computing Machinery, Inc ACSD ACM Transactions on Embedded Computing Systems, 2, 16 Application of Concurrency to System Design, 15th International Conference, ACSD 2015, Brussels, Belgium, 21-26 June 2015, 90-99 STARTPAGE=90;ENDPAGE=99;TITLE=Application of Concurrency to System Design, 15th International Conference, ACSD 2015, Brussels, Belgium, 21-26 June 2015 |
| ISSN: | 1539-9087 |
| Popis: | Multi-processor systems-on-chips are widely adopted in implementing modern streaming applications to satisfy the ever increasing computing requirements. Predictable memory hierarchies, which make memory access predictable, can better satisfy the strict timing requirements of streaming applications. However, different levels of the memory hierarchy vary in latency and capacity. Hence, the system performance not only depends on the task schedule but also closely relates with the FIFO size distribution and FIFO allocation, which makes the scheduling problem much more complex. We propose an efficient Iteration-based Task-FIFO Co-Scheduling algorithm to optimize the FIFO size distribution and task/FIFO assignment. Randomly generated Synchronous Dataflow Graphs with different sizes and a set of practical applications are used to evaluate the performance of the proposed method. The experimental results demonstrate that the proposed algorithm outperforms the load balancing method and the Highest Access Frequency First algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|