1. |
- Liang, Haochun, et al.
(författare)
-
Response Time Analysis and Optimization of DAG Tasks Exploiting Mutually Exclusive Execution
- 2023
-
Ingår i: 2023 60th ACM/IEEE Design Automation Conference (DAC). - : Institute of Electrical and Electronics Engineers (IEEE). - 9798350323481 - 9798350323498
-
Konferensbidrag (refereegranskat)abstract
- There is an increasing move towards implementing embedded real-time systems upon multiprocessors with parallel applications, which are usually modeled as Directed Acyclic Graphs (DAGs). Plentiful work has been presented to optimize the bound of Worst-Case Response Time (WCRT) since the cornerstone work proposed by Graham in 1969. However, all these works are developed on the basis of Graham's bound and failed to tackle the root of pessimism in it. In this work, we present a novel method to optimize the WCRT bound of a DAG task by designing mutually exclusive groups so that a sequential execution is enforced for some nodes, under which the problem of bounding WCRT becomes a problem of identifying a mutually exclusive path and thus does not suffer the pessimism in Graham's bound. Experiments are conducted to evaluate the performance of our method against other WCRT optimization approaches in the state-of-the-art.
|
|
2. |
- Tang, Yue, et al.
(författare)
-
Reaction Time Analysis of Event-Triggered Processing Chains with Data Refreshing
- 2023
-
Ingår i: 2023 60th ACM/IEEE Design Automation Conference (DAC). - : Institute of Electrical and Electronics Engineers (IEEE). - 9798350323481 - 9798350323498
-
Konferensbidrag (refereegranskat)abstract
- Many real-time systems process and react to external events by a chain of tasks, and have constraints on the maximum reaction time which describes how long it takes to respond to an external event. While a processing chain typically starts with a sampling task periodically triggered to sample the sensor data, other tasks in the chain could be triggered in two different ways: event-triggered or time-triggered, which have their own pros and cons. In this paper, we propose the third option to trigger the processing tasks in a chain, namely, the event-triggered with data refreshing approach, which combines the benefits of the event-triggered or time-triggered approaches. As the main technical contribution, we develop techniques to formally upper-bound its maximum reaction time and analytically compare it with the existing approaches. Experiments with synthetic workload are conducted to show the performance improvement by our proposed techniques.
|
|