TY - GEN
T1 - A memory access detection methodology for accurate workload characterization
AU - Cesati, Marco
AU - Mancuso, Renato
AU - Betti, Emiliano
AU - Caccamo, Marco
N1 - Acknowledgment The material presented in this paper is based upon work supported by the National Science Foundation (NSF) under grant numbers CNS-1302563, and CNS-1219064. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the NSF. We gratefully thank Alessandra Cocozza, who worked on a preliminary version of MadT.
PY - 2015
Y1 - 2015
N2 - Tools for memory access detection are widely used, playing an important role especially in real-time systems. For example, on multi-core platforms, the problem of co-scheduling CPU and memory resources with hard real-time constraints requires a deep understanding of the memory access patterns of the deployed taskset. While code execution flow can be analyzed by considering the control-flow graph and reasoning in terms of basic blocks, a similar approach cannot apply to data accesses. In this paper, we propose MadT, a tool that uses a novel mechanism to perform memory access detection of general purpose applications. MadT does not perform binary instrumentation and always executes application code natively on the platform. Hence it can operate entirely in user-space without sand-boxing the task under analysis. Furthermore, MadT provides detailed symbolic information about the accessed memory structures, so it is able to translate the virtual addresses to their original symbolic variable names. Finally, it requires no modifications to application source code. The proposed methodology relies on existing OS-level capabilities. In this paper, we describe how MadT has been implemented on commercial hardware and compare its performance with state-of-the-art software techniques for memory access detection.
AB - Tools for memory access detection are widely used, playing an important role especially in real-time systems. For example, on multi-core platforms, the problem of co-scheduling CPU and memory resources with hard real-time constraints requires a deep understanding of the memory access patterns of the deployed taskset. While code execution flow can be analyzed by considering the control-flow graph and reasoning in terms of basic blocks, a similar approach cannot apply to data accesses. In this paper, we propose MadT, a tool that uses a novel mechanism to perform memory access detection of general purpose applications. MadT does not perform binary instrumentation and always executes application code natively on the platform. Hence it can operate entirely in user-space without sand-boxing the task under analysis. Furthermore, MadT provides detailed symbolic information about the accessed memory structures, so it is able to translate the virtual addresses to their original symbolic variable names. Finally, it requires no modifications to application source code. The proposed methodology relies on existing OS-level capabilities. In this paper, we describe how MadT has been implemented on commercial hardware and compare its performance with state-of-the-art software techniques for memory access detection.
UR - https://www.scopus.com/pages/publications/84962907339
UR - https://www.scopus.com/pages/publications/84962907339#tab=citedBy
U2 - 10.1109/RTCSA.2015.30
DO - 10.1109/RTCSA.2015.30
M3 - Conference contribution
AN - SCOPUS:84962907339
T3 - Proceedings - IEEE 21st International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2015
SP - 141
EP - 148
BT - Proceedings - IEEE 21st International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2015
A2 - O'Conner, Lisa
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE 21st International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2015
Y2 - 19 August 2015 through 21 August 2015
ER -