2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) 2016
DOI: 10.1109/ccgrid.2016.58
|View full text |Cite
|
Sign up to set email alerts
|

Landrush: Rethinking In-Situ Analysis for GPGPU Workflows

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 30 publications
0
4
0
Order By: Relevance
“…The TINS 45 package leverages work‐stealing strategies to execute analytics tasks when there are no available simulation tasks scheduled. GoldRush 46 and Landrush 47 employ smart co‐scheduling of analytics routines alongside MPI‐OpenMP and GPU simulation tasks. They combine monitoring data with a scheduler to identify regions of idle time on the processor that can be used to run these routines demonstrating significant cost savings without perturbing the execution of the simulation.…”
Section: Related Workmentioning
confidence: 99%
“…The TINS 45 package leverages work‐stealing strategies to execute analytics tasks when there are no available simulation tasks scheduled. GoldRush 46 and Landrush 47 employ smart co‐scheduling of analytics routines alongside MPI‐OpenMP and GPU simulation tasks. They combine monitoring data with a scheduler to identify regions of idle time on the processor that can be used to run these routines demonstrating significant cost savings without perturbing the execution of the simulation.…”
Section: Related Workmentioning
confidence: 99%
“…There have been more works exploring elastic in situ [28], i.e., resource adaptation over the execution between simulation and visualization. Goldrush [29] identified when simulation resources were idle and used them to perform analysis tasks, and Landrush [30] extended this idea to use idle cycles on GPUs. Melissa [31] supports a design where a server processes data from multiple independent simulation groups that connect dynamically.…”
Section: Related Workmentioning
confidence: 99%
“…Our infrastructure leverages the SENSEI generic in situ interface for portability, but we extend this work to support hybrid in situ summarization with a portable data parallel framework. Previous work centered on the batch in situ visualization use case utilizing multi-core, stream and many-core processors [23,25], while others [18] studied idle time and GPU context switching. Our work builds on these explorations but is focused on summarization use cases to efficiently condense usable information from data residing in memory on the compute nodes of DHCSs.…”
Section: Related Workmentioning
confidence: 99%