Tapis: An API Platform for Reproducible, Distributed Computational Research

Stubbs, Joe; Cardone, Richard; Packard, Mike; Jamthe, Anagha; Padhy, Smruti; Terry, Steve; Looney, Julia; Meiring, Joseph D.; Black, Steve; Dahan, Maytal; Cleveland, Sean B.; Jacobs, Gwen A.

doi:10.1007/978-3-030-73100-7_61

Cited by 27 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This challenge motivated Grid computing 133 , 134 and the superfacility concept. 135 Facilities have developed specialized interfaces for remote job submission 136 , 137 and for managing workloads on and across systems. 129 , 138 Remote execution has been integrated with Jupyter notebooks.…”

Section: Discussionmentioning

confidence: 99%

Linking scientific instruments and computation: Patterns, technologies, and experiences

Vescovi¹,

Chard²,

Saint³

et al. 2022

Patterns

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Linking scientific instruments and computation: Patterns, technologies, and experiences

Vescovi¹,

Chard²,

Saint³

et al. 2022

Patterns

View full text Add to dashboard Cite

“…Grid computing introduced remote connectivity and web services to manage remote execution, for example via Globus Grid Resource Allocation Manager (GRAM) [8]. Recently, facilities such as NERSC and TACC have developed web APIs for submitting and managing batch jobs with Newt [9] and Tapis [10], respectively. These approaches add each new task to a global queue, which can result in significant delays due to the need to wait for batch jobs to be scheduled in applications where new tasks are created dynamically.…”

Section: A Coordinating Remote Executionmentioning

confidence: 99%

Cloud Services Enable Efficient AI-Guided Simulation Workflows across Heterogeneous Resources

Ward¹,

Pauloski²,

Hayot‐Sasson³

et al. 2023

Preprint

View full text Add to dashboard Cite

Applications that fuse machine learning and simulation can benefit from the use of multiple computing resources, with, for example, simulation codes running on highly parallel supercomputers and AI training and inference tasks on specialized accelerators. Here, we present our experiences deploying two AIguided simulation workflows across such heterogeneous systems. A unique aspect of our approach is our use of cloud-hosted management services to manage challenging aspects of crossresource authentication and authorization, function-as-a-service (FaaS) function invocation, and data transfer. We show that these methods can achieve performance parity with systems that rely on direct connection between resources. We achieve parity by integrating the FaaS system and data transfer capabilities with a system that passes data by reference among managers and workers, and a user-configurable steering algorithm to hide data transfer latencies. We anticipate that this ease of use can enable routine use of heterogeneous resources in computational science.

show abstract

“…(García-Holgado et al, 2020;Strasser et al, 2019). New paradigms have emerged where citizens engage in collaborative relationships to analyze, improve, and discover information (McCurdy & Vinogradova-Shiffer, 2021;Stubbs et al, 2021). Such developments in Industry 4.0 technologies have spilt into the Education 4.0 framework, where learners experience real-life challenges and apply their knowledge to develop technology-based solutions using complex thinking skills (Miranda et al, 2021).…”

Section: From Cs Stagnation To the 21st-century Expresswaymentioning

confidence: 99%

A Threshold for Citizen Science Projects: Complex Thinking as a Driver of Holistic Development

Sanabria-Z

Espinosa

Alfaro-Ponce

et al. 2022

RIED

View full text Add to dashboard Cite

Emerging technologies and community empowerment have driven citizen science (CS) projects. However, their impact remains vague, partly because of the difficulties in monitoring and standardizing these projects. Notably, the development of citizens' complex thinking is not among the primary goals, despite the connection with the tenets of Education 4.0 and the training of socially committed citizens. Therefore, we propose a framework and typology to foster CS projects while scaling up complex thinking. We used the evidence-based educational innovation (EBEI) methodology and the Theory of Change (ToC) perspective, reviewing some of the most relevant frameworks under UNESCO's Open Science Recommendation. Findings from the CS projects analysis revealed that: (a) there is inattention to developing the sub-components of the complex thinking macro-competency; (b) a growing trend to develop frameworks for CS projects is taking place; (c) there is a prevalence of CS project frameworks focused on prevention and control, project evaluation and design, and education and research; (d) a framework with three dimensions based on ToC (Outbound, Threshold and Full-cycle) can guide the development of CS projects; and (e) an eight-component typology can measure the progress and impact of CS projects from the perspectives of Context-awareness, Citizen engagement, Infrastructure leverage, Technological innovation, Educational innovation, Outreach and Scale, Network building, and Complex Thinking. We envision that the integrated framework and typology proposed, scaffolded by complex thinking, can comprehensively broaden the impact of CS initiatives.

show abstract

Tapis: An API Platform for Reproducible, Distributed Computational Research

Cited by 27 publications

References 18 publications

Linking scientific instruments and computation: Patterns, technologies, and experiences

Linking scientific instruments and computation: Patterns, technologies, and experiences

Cloud Services Enable Efficient AI-Guided Simulation Workflows across Heterogeneous Resources

A Threshold for Citizen Science Projects: Complex Thinking as a Driver of Holistic Development

Contact Info

Product

Resources

About