View in EDS

Marmot: Extraction of Fine-Grain Memory Access Profiles for real-time software

Saved in:
Bibliographic Details
Title: Marmot: Extraction of Fine-Grain Memory Access Profiles for real-time software
Authors: Chabot, Hector, Puaut, Isabelle, Carle, Thomas, Cassé, Hugues
Contributors: CHABOT, Hector
Source: Proceedings of the 32nd International Conference on Real-Time Networks and Systems. :117-141
Publisher Information: ACM, 2024.
Publication Year: 2024
Subject Terms: Multicore, Worst-Case Execution Time Estimation, Event arrival function, Interference, Static analysis, [INFO.INFO-ES] Computer Science [cs]/Embedded Systems
Description: Enforcing deadlines in real-time systems calls for the computation of an upper-bound of the Worst-Case Execution Time (WCET) of tasks. In multi-core systems, shared-resource usage leads to interference between tasks running on parallel cores, resulting in additional delays in the execution time of tasks.Schedulability analysis techniques rely on Interference-Aware WCET of tasks (IA-WCET, WCET integrating delays resulting from interference) to safely consider these delays. Calculation of IA-WCET requires knowledge about the worst-case shared-resource usage of tasks, in the form of a memory access profile as far as shared memory accesses are concerned. State-of-the-art memory profiles only provide coarse-grain information (at the level of an entire task), resulting in pessimism in IA-WCET computation. More recent solutions propose to refine the information available in memory profiles, but are still limited: they lack information about shared-resource usage of code inside loops and are unable to use contextual information, which leads to over-approximation. This paper presents Marmot, a technique that extends recent memory access profile extraction solutions for real-time software. In Marmot, tasks are split in successive intervals, with the worst-case resource usage of each interval described as a distribution instead of a single value. Experimental results show that IA-WCET computation and schedulability analysis can take advantage of the fine-grain intervals produced by Marmot to obtain more precise IA-WCET and therefore higher schedulability than coarser-grain profiles.
Document Type: Article
Conference object
File Description: application/pdf
DOI: 10.1145/3696355.3696360
Access URL: https://hal.science/hal-04782265v1
https://hal.science/hal-04782265v1/document
https://doi.org/10.1145/3696355.3696360
Rights: CC BY
Accession Number: edsair.doi.dedup.....701eea28de10c1326224c4428bca6fb5
Database: OpenAIRE
Description
Abstract:Enforcing deadlines in real-time systems calls for the computation of an upper-bound of the Worst-Case Execution Time (WCET) of tasks. In multi-core systems, shared-resource usage leads to interference between tasks running on parallel cores, resulting in additional delays in the execution time of tasks.Schedulability analysis techniques rely on Interference-Aware WCET of tasks (IA-WCET, WCET integrating delays resulting from interference) to safely consider these delays. Calculation of IA-WCET requires knowledge about the worst-case shared-resource usage of tasks, in the form of a memory access profile as far as shared memory accesses are concerned. State-of-the-art memory profiles only provide coarse-grain information (at the level of an entire task), resulting in pessimism in IA-WCET computation. More recent solutions propose to refine the information available in memory profiles, but are still limited: they lack information about shared-resource usage of code inside loops and are unable to use contextual information, which leads to over-approximation. This paper presents Marmot, a technique that extends recent memory access profile extraction solutions for real-time software. In Marmot, tasks are split in successive intervals, with the worst-case resource usage of each interval described as a distribution instead of a single value. Experimental results show that IA-WCET computation and schedulability analysis can take advantage of the fine-grain intervals produced by Marmot to obtain more precise IA-WCET and therefore higher schedulability than coarser-grain profiles.
DOI:10.1145/3696355.3696360