Landrush: Rethinking In-Situ Analysis for GPGPU Workflows

Goswami, Anshuman; Tian, Yuan; Schwan, Karsten; Zheng, Fang; Young, Jeffrey; Wolf, Matthew; Eisenhauer, Greg; Klasky, Scott

doi:10.1109/ccgrid.2016.58

Cited by 11 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

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%

SOMA: Observability, monitoring, and in situ analytics for exascale applications

Yokelson,

Lappi,

Ramesh

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryWith the rise of exascale systems and large, data‐centric workflows, the need to observe and analyze high performance computing (HPC) applications during their execution is becoming increasingly important. HPC applications are typically not designed with online monitoring in mind, therefore, the observability challenge lies in being able to access and analyze interesting events with low overhead while seamlessly integrating such capabilities into existing and new applications. We explore how our service‐based observation, monitoring, and analytics (SOMA) approach to collecting and aggregating both application‐specific diagnostic data and performance data addresses these needs. We present our SOMA framework and demonstrate its viability with LULESH, a hydrodynamics proxy application. Then we focus on Astaroth, a multi‐GPU library for stencil computations, highlighting the integration of the TAU and APEX performance tools and SOMA for application and performance data monitoring.

show abstract

Section: Related Workmentioning

confidence: 99%

SOMA: Observability, monitoring, and in situ analytics for exascale applications

Yokelson,

Lappi,

Ramesh

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…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%

A Hybrid in Situ Approach for Cost Efficient Image Database Generation

Bruder

Larsen

Ertl

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

“…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%

In Situ Summarization with VTK-m

Thompson

Jourdain

Bauer

et al. 2017

Proceedings of the in Situ Infrastructures on Enabling Extreme-Scale Analysis and Visualization

View full text Add to dashboard Cite

Summarization and compression at current and future scales requires a framework for developing and benchmarking algorithms. We present a framework created by integrating existing, productionready projects and provide timings of two particular algorithms that serve as exemplars for summarization: a wavelet-based data reduction filter and a generator for creating image-like databases of extracted features (isocontours in this case). Both support browserbased, post-hoc, interactive visualization of the summary for decisionmaking. A study of their weak-scaling on a distributed multi-GPU system is included.

show abstract

Landrush: Rethinking In-Situ Analysis for GPGPU Workflows

Cited by 11 publications

References 30 publications

SOMA: Observability, monitoring, and in situ analytics for exascale applications

SOMA: Observability, monitoring, and in situ analytics for exascale applications

A Hybrid in Situ Approach for Cost Efficient Image Database Generation

In Situ Summarization with VTK-m

Contact Info

Product

Resources

About