Logo do repositório
 
A carregar...
Miniatura
Publicação

Buffer-aware bounds to multi-point progressive blocking in priority-preemptive NoCs

Utilize este identificador para referenciar este registo.
Nome:Descrição:Tamanho:Formato: 
COM26_CISTER_2018.pdf166.54 KBAdobe PDF Ver/Abrir

Orientador(es)

Resumo(s)

This paper aims to reduce the pessimism of the analysis of the multi-point progressive blocking (MPB) problem in real-time priority-preemptive wormhole networks-on-chip. It shows that the amount of buffering on each network node can influence the worst-case interference that packets can suffer along their routes, and it proposes a novel analytical model that can quantify such interference as a function of the buffer size. It shows that, perhaps counter-intuitively, smaller buffers can result in lower upper-bounds on interference and thus improved schedulability. Didactic examples and large-scale experiments provide evidence of the strength of the proposed approach.

Descrição

Palavras-chave

Network routing Network-on-chip Processor scheduling Scheduling

Contexto Educativo

Citação

Projetos de investigação

Unidades organizacionais

Fascículo

Editora

Institute of Electrical and Electronics Engineers

Licença CC

Métricas Alternativas