| 1. |
- Jiang, Xu, et al.
(author)
-
Analysis and Optimization of Worst-Case Time Disparity in Cause-Effect Chains
- 2023
-
In: 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE). - : IEEE. - 9798350396249 - 9783981926378 ; , s. 1-6
-
Conference paper (peer-reviewed)abstract
- In automotive systems, an important timing requirement is that the time disparity (the maximum difference among the timestamps of all raw data produced by sensors that an output originates from) must be bounded in a certain range, so that information from different sensors can be correctly synchronized and fused. In this paper, we study the problem of analyzing the worst-case time disparity in cause-effect chains. In particular, we present two bounds, where the first one assumes all chains are independent from each other and the second one takes the fork-join structures into consideration to perform more precise analysis. Moreover, we propose a solution to cut down the worst-case time disparity for a task by designing buffers with proper sizes. Experiments are conducted to show the correctness and effectiveness of both our analysis and optimization methods.
|
|
| 2. |
- Pang, Weiguang, et al.
(author)
-
Efficient CUDA stream management for multi-DNN real-time inference on embedded GPUs
- 2023
-
In: Journal of systems architecture. - : Elsevier BV. - 1383-7621 .- 1873-6165. ; 139
-
Journal article (peer-reviewed)abstract
- Deep Neural Networks (DNNs) are widely used in Cyber-Physical Systems (CPS) that often involve multiple DNN tasks with varying real-time requirements. These tasks need to be deployed on a single embedded hardware platform with limited resources, such as an embedded GPU. Efficiently sharing the same embedded GPU among multiple real-time DNN tasks is a complex challenge. While existing DNN frameworks (e.g., PyTorch and TensorFlow) focus on maximizing average performance and high throughput on GPU, they lack scheduling management mechanisms considering multiple DNNs with different timing requirements. In this paper, we address this challenge by thoroughly examining and summarizing the scheduling rules for multiple kernels with different priorities in CUDA streams. Based on these rules, we design a framework that supports multi-DNN real-time inference and propose a method for allocating CUDA streams to DNN kernels to meet schedulability requirements while maximizing GPU resource utilization. Our proposed approach is implemented on an NVIDIA Jetson AGX Xavier embedded GPU system and validated using several popular DNNs. The results show that our approach achieves shorter response times compared with several state-of-the-art methods.
|
|
| 3. |
- Tang, Yue, et al.
(author)
-
Real-Time Performance Analysis of Processing Systems on ROS 2 Executors
- 2023
-
In: 2023 IEEE 29th Real-Timea and Embedded Technology and Applications Symposium, RTAS. - : IEEE. - 9798350321760 - 9798350321777 ; , s. 80-92
-
Conference paper (peer-reviewed)abstract
- ROS (Robot Operating System) is one of the most popular robotic software development frameworks. Robotic systems in safety-critical domains are usually subject to hard real-time constraints, so timing behaviors must be formally modeled and analyzed to guarantee that real-time constraints are always honored at run-time. Although a series of analysis techniques has been proposed to analyze the timing performance of ROS 2, the state-of-the-art still generates pessimistic results for ROS 2 systems modeled as DAG (Directed Acyclic Graph). This paper focuses on the analysis of such systems, and proposes techniques to analyze the timing performance in a more precise manner. Experiments with both randomly generated workload and a case study are conducted to evaluate and demonstrate our results.
|
|
