Proceeding. 10th EUROMICRO Workshop on Real-Time Systems (Cat. No.98EX168)
DOI: 10.1109/emwrts.1998.685079
|View full text |Cite
|
Sign up to set email alerts
|

Facilitating worst-case execution times analysis for optimized code

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
26
0
1

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 40 publications
(27 citation statements)
references
References 15 publications
0
26
0
1
Order By: Relevance
“…Previous publications have already shown that it is relevant to combine WCET optimization with other criteria like e. g. code size. Using objectives and handlers, our -+ ------ [7] + --+ -- [12] --+ + ---+ [17,18] -+ + + ---+ [13] ----+ + [16] --+ + ± --+ …”
Section: Discussion Of the Structure Of Wccmentioning
confidence: 99%
See 1 more Smart Citation
“…Previous publications have already shown that it is relevant to combine WCET optimization with other criteria like e. g. code size. Using objectives and handlers, our -+ ------ [7] + --+ -- [12] --+ + ---+ [17,18] -+ + + ---+ [13] ----+ + [16] --+ + ± --+ …”
Section: Discussion Of the Structure Of Wccmentioning
confidence: 99%
“…In order to keep track of the influence of compiler optimization on high-level flow facts, [7] proposes co-transformation of flow facts. However, the cotransformer has never reached a fully working state, and several standard compiler optimizations can not be modeled at all due to insufficient data structures.…”
Section: Related Workmentioning
confidence: 99%
“…There is already a great deal of analysis available including [4,16], and Engblom provides a useful survey of these analyses in [5]. These approaches can be tailored for our use by taking advantage of the fact that software is written in a particularly disciplined way for the safetycritical domain.…”
Section: Worst-case Execution Time Analysismentioning
confidence: 99%
“…• there are greater variations in the execution times of the software [4]; • it is harder to deduce the actual WCET of the software as the analysis would have to include a model of the cache mechanism-it could be assumed that all memory accesses result in a cache miss but this gives results much greater than the actual WCET, leading to wasted resources [4]; • the more complex the processor is, the harder it is to validate the models used and the higher the likelihood of systematic design errors (in the processor and the accompanying models) [5].…”
Section: Memory Accessmentioning
confidence: 99%
“…Annotating the machine code is not a desirable solution as it requires that the programmer studies the compiler-generated machine code and understands the code transformations done by the compiler. Therefore, if there is need for annotations, the preferred solution is to annotate the program source with flow information and to transform the flow information automatically, while optimizing the code (Kirner and Puschner 2001;Engblom et al 1998).…”
Section: Introductionmentioning
confidence: 99%