SwePub
Sök i LIBRIS databas

  Utökad sökning

id:"swepub:oai:DiVA.org:mdh-29256"
 

Sökning: id:"swepub:oai:DiVA.org:mdh-29256" > A Stochastic Respon...

A Stochastic Response Time Analysis for Communications in On-Chip Networks

Liu, Meng (författare)
Mälardalens högskola,Inbyggda system
Behnam, Moris (författare)
Mälardalens högskola,Inbyggda system
Nolte, Thomas (författare)
Mälardalens högskola,Inbyggda system
 (creator_code:org_t)
2015
2015
Engelska.
  • Konferensbidrag (refereegranskat)
Abstract Ämnesord
Stäng  
  • Priority-based wormhole-switching has been proposed as a solution to handle real-time traffic in on-chip networks. In order to support real-time traffic, the predictability of end-toend delays need to be guaranteed. Several deterministic schedulability analysis approaches for wormhole-switched networks have been proposed. These approaches calculate a single upper-bound of the response time of each Network-on-Chip (NoC) flow, which is suitable for hard real-time applications. However, for many soft real-time applications, the performance does not depend on the worst-case scenario, which means that the calculated single upper-bounds are not sufficient to represent the performance. Therefore, in this paper, we present a stochastic Response Time Analysis (RTA) which can calculate a distribution of the response times of a real-time NoC flow. The estimated distributions can be utilized for multiple purposes, such as calculating deadline miss ratios, and computing upper-bounds regarding different probabilities. A number of simulation-based experiments are generated in order to investigate the pessimism involved in the analysis. Moreover, the processing time of the analysis is also measured from the experiments in order to examine the scalability of the proposed approach.

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Inbäddad systemteknik (hsv//swe)
ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Embedded Systems (hsv//eng)

Nyckelord

Stochastic Time AnalysisNetwork-on-ChipsReal-Time System

Publikations- och innehållstyp

ref (ämneskategori)
kon (ämneskategori)

Till lärosätets databas

Sök utanför SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy