2014 IEEE International Conference on Big Data (Big Data) 2014
DOI: 10.1109/bigdata.2014.7004236
|View full text |Cite
|
Sign up to set email alerts
|

Enabling composite applications through an asynchronous shared memory interface

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2015
2015
2019
2019

Publication Types

Select...
5
1

Relationship

2
4

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 10 publications
0
5
0
Order By: Relevance
“…There are several projects that look at combining Linux functionality with an LWK. Kitten/Palacios, Fused OS, McKernel, and mOS are driven by anticipated usage models of future machines [20,4]. The projects differ in how they provide Linux functionality while achieving LWK performance and scalability.…”
Section: Next-generation Lwkmentioning
confidence: 99%
“…There are several projects that look at combining Linux functionality with an LWK. Kitten/Palacios, Fused OS, McKernel, and mOS are driven by anticipated usage models of future machines [20,4]. The projects differ in how they provide Linux functionality while achieving LWK performance and scalability.…”
Section: Next-generation Lwkmentioning
confidence: 99%
“…This application, coupled using TCASM, was originally described elsewhere [27]. At the end of each time step, the SNAP simulation publishes its data via TCASM's copy-on-write approach.…”
Section: Neutronics Energy Spectrum Analysismentioning
confidence: 99%
“…As such, the United States Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only. and debugging systems [35,37,27,25,30,32,7]. This emergence is a result of the changing compute/memory/IO balance of high-end computer systems, the push toward increasing physical fidelity and realism in simulations motivating increasing use of coupled multiphysics simulations, and the generally increasing size and richness of data generated.…”
Section: Introductionmentioning
confidence: 97%
“…Historically, processes running on the same node used shared memory techniques, complemented by double-and multibuffer algorithms to improve performance. New techniques, such as TCASM [27] further improve the local sharing by eliminating most of the need of synchronization between applications. Across nodes, applications use three main techniques for sharing data: files on parallel filesystem, explicit message passing, and partitioned global address space (PGAS) approaches like SHMEM and GASNet.…”
Section: Evolving Sharing Considerationsmentioning
confidence: 99%
“…TCASM [27] is a shared-memory copy-on-write kernel that allows asynchronous progress between the publisher of data and one or more observer(s). TCASM consists of kernel-level modifications to multiple memory management functions, the most significant being the msync system call.…”
Section: Implementation 51 Existing Softwarementioning
confidence: 99%