Proceedings of the Fourth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPOPP '93 1993
DOI: 10.1145/155332.155333
|View full text |Cite
|
Sign up to set email alerts
|

LogP: towards a realistic model of parallel computation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

2
433
0
17

Year Published

1997
1997
2014
2014

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 1,028 publications
(452 citation statements)
references
References 28 publications
2
433
0
17
Order By: Relevance
“…Related Work: Formal models such as LogP [8] and LogGP [9] have been used to analyze the communication in parallel applications for a long time. Subsequently, based on the LogP model, models such as LoPC [10], LoGPC [11], LoGPG [12], LogGPO [13], and LoOgGP [14] were developed to account for network congestion.…”
Section: The Dragonfly Interconnectmentioning
confidence: 99%
“…Related Work: Formal models such as LogP [8] and LogGP [9] have been used to analyze the communication in parallel applications for a long time. Subsequently, based on the LogP model, models such as LoPC [10], LoGPC [11], LoGPG [12], LogGPO [13], and LoOgGP [14] were developed to account for network congestion.…”
Section: The Dragonfly Interconnectmentioning
confidence: 99%
“…Culler et al introduced the LogP model [1]. It assumes a finite number of processors with local memory linked by a network connection.…”
Section: Basicsmentioning
confidence: 99%
“…In addition to L, o, and g, a parameter P describes the number of Processors. These parameters have been determined for a number of parallel machines including the CM-5 [1], the IBM SP1 machine [3], a network of workstations and a powerXplorer [2]. In addition to the machine parameters, we need the input size of the problem and the runtime of the single tasks to predict the runtime of the scheduled program.…”
Section: Basicsmentioning
confidence: 99%
“…Segundo Culler (CULLER et al, 1993), o modelo de computação paralela mais utilizado, chamado PRAM, nãoé um modelo realístico, pois considera que todos os processadores trabalham do modo síncrono e que a comunicação entre eles utiliza uma largura de banda infinita, sem latência e nenhum atraso na comunicação. Para Harris (HARRIS, 1994) o PRAMé um modelo abstrato que pode serútil para o estudo de alguns aspectos da com-putação paralela, mas nãoé possível implementá-lo fisicamente em hardware.…”
Section: Bspunclassified
“…Na literatura, e possível encontrar alguns trabalhos elaborados para auxiliar atividades relacionadas a estudos de desempenho de aplicações paralelas e distribuídas (DIAS, 2006;GROVE, 2003;CULLER et al, 1993;SCHOPF, 1998). Entretanto, nenhum deles aborda todos os aspectos de interesse desta tese.…”
unclassified