2021
DOI: 10.1145/3473570
|View full text |Cite
|
Sign up to set email alerts
|

An order-aware dataflow model for parallel Unix pipelines

Abstract: We present a dataflow model for modelling parallel Unix shell pipelines. To accurately capture the semantics of complex Unix pipelines, the dataflow model is order-aware, i.e., the order in which a node in the dataflow graph consumes inputs from different edges plays a central role in the semantics of the computation and therefore in the resulting parallelization. We use this model to capture the semantics of transformations that exploit data parallelism available in Unix shell computations and prove their cor… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 59 publications
0
3
0
Order By: Relevance
“…Existing work has pushed towards improved performance through data parallelism ( [14,23,24]) and distribution ( [6,19]). Approaches in this area rely on annotations of commonly used commands, which the optimizers/planners use to rearrange programs.…”
Section: Discussionmentioning
confidence: 99%
“…Existing work has pushed towards improved performance through data parallelism ( [14,23,24]) and distribution ( [6,19]). Approaches in this area rely on annotations of commonly used commands, which the optimizers/planners use to rearrange programs.…”
Section: Discussionmentioning
confidence: 99%
“…This sequential execution often leaves available data parallelism, in which a command operates on different parts of an input stream in parallel, unexploited. This observation has motivated the development of systems that exploit data parallelism in shell pipelines [5,10,14]. A key prerequisite is obtaining the combiners necessary for merging the resulting multiple parallel output streams correctly into a single output.…”
Section: Introductionmentioning
confidence: 99%
“…A key prerequisite is obtaining the combiners necessary for merging the resulting multiple parallel output streams correctly into a single output. Previous systems rely on developers to manually implement such combiners and associate them with their corresponding shell commands [5,10,14].…”
Section: Introductionmentioning
confidence: 99%