11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'05)
DOI: 10.1109/rtcsa.2005.22
|View full text |Cite
|
Sign up to set email alerts
|

An Efficient Search Algorithm of Worst-Case Cache Flush Timings

Abstract: In recent years, the use of cache memory has been desired

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(7 citation statements)
references
References 8 publications
0
7
0
Order By: Relevance
“…8), the equation (1) can be rewritten as follows because τ (k l , k l+1 + 1) is independent from any other τ (k l , k l +1 + 1).…”
Section: Wcid Analysis With Multiple Interruptsmentioning
confidence: 99%
See 1 more Smart Citation
“…8), the equation (1) can be rewritten as follows because τ (k l , k l+1 + 1) is independent from any other τ (k l , k l +1 + 1).…”
Section: Wcid Analysis With Multiple Interruptsmentioning
confidence: 99%
“…Then Lee, et al 7) pointed out the importance of the effect on caches, and proposed an analytical method to bound cache miss penalty due to interruptions. This approach was extended in two directions; to incorporate the cache pollution by preemptors 12), 14) ; and to analyze more accurately using memory access trace obtained from the simulation or instrumented execution of a workload 8) . Although each of those work above has its own good feature, e.g., applicable without running 3),4) , efficiently handling multiple interruptions and/or preemptors 7),8),12), 14) , they commonly have the problem on accuracy.…”
Section: Related Workmentioning
confidence: 99%
“…While this approach should be too natural and trivial for typical WCET problems, it is still challenging for the preemption delay problem because we have a huge search space from which we have to find out the worst-case preemption points. In the first proposal using this approach, Miyamoto, et al 15) used it to find the worst case flush timings (WCFT) of direct-map caches for a process preempted F times. That is, WCFT is the set of preemption timings that maximizes the total cache misses in the execution of the process.…”
Section: Related Workmentioning
confidence: 99%
“…Their more recent report 14) showed a better algorithm whose time complexity is O(NF ) if we assume the average gap between two accesses to a cache block is a constant independent of N . This improvement is based on the fact that the effect of an access to a directmap cache is nullified by the following access to the same cache block because what resides in the block is determined only by the second access regardless of the first one.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation