OASIcs.WCET.2010.124.pdf
- Filesize: 317 kB
- 12 pages
Document
Precomputing Memory Locations for Parametric Allocations
Authors
-
Part of:
Volume:
10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010)
Series: Open Access Series in Informatics (OASIcs)
Conference: Workshop on Worst-Case Execution Time Analysis (WCET) - License:
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license
- Publication Date: 2010-11-26
Cite AsGet BibTex
Jörg Herter and Sebastian Altmeyer. Precomputing Memory Locations for Parametric Allocations. In 10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010). Open Access Series in Informatics (OASIcs), Volume 15, pp. 124-135, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)
https://doi.org/10.4230/OASIcs.WCET.2010.124
https://doi.org/10.4230/OASIcs.WCET.2010.124
Abstract
Current worst-case execution time (WCET) analyses do not support programs using dynamic memory allocation. This is mainly due to the unpredictability of cache performance introduced by standard memory allocators. To overcome this problem, algorithms have been proposed that precompute static allocations for dynamically allocating programs with known numeric bounds on the number and sizes of allocated memory blocks. In this paper, we present a novel algorithm for computing such static allocations that can cope with parametric bounds on the number and sizes of allocated blocks. To demonstrate the usefulness of our approach, we precompute static allocations or a set of existing real-time applications and academic examples.
Keywords
- WCET analysis
- cache analysis
- dynamic/static memory allocation
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads