Upload
winfred-hicks
View
218
Download
0
Embed Size (px)
DESCRIPTION
Provenance for Reproducibility and Performance Provenance Provenance for Reproducibility Work towards achieving numerical, experimental and execution reproducibility. Performance Provenance Augment/replace existing strategies with the Open Provenance Model-based WorkFlow Performance Provenance (OPM-WFPP): Capture empirical performance information from workflows and systems Links provenance information and performance metrics 3 Input Appl. Input Appl. Output WFM Output StorageNetwork Core Inter connect Core Network Storage Protocol OSProtocol OS Access Protocol Workflow System Software Systems Access Protocol
Citation preview
1
Provenance Research
BIBI RAJU, TODD ELSETHAGEN, ERIC STEPHAN
Pacific Northwest National Laboratory, Richland, WA
2
Provenance Goals
Provenance Overarching GoalsProvide thorough results explanationReuse, repeat, or reproduce workflowsEnable performance optimization
Provenance Work in FY15Developed a provenance capture ontologyProvenance infrastructure build outScalable provenance capture mechanismDeveloped a Client API that aids in production of provenance
Provenance for Reproducibility and Performance ProvenanceProvenance for Reproducibility
Work towards achieving numerical, experimental and execution reproducibility.Performance Provenance
Augment/replace existing strategies with the Open Provenance Model-based WorkFlow Performance Provenance (OPM-WFPP):
Capture empirical performance information from workflows and systemsLinks provenance information and performance metrics
3
Input Appl.
Input
Appl. Output
WFM WFM WFM
Output
Storage Network Core Interconnect
Core Network Storage
Protocol OS Protocol ProtocolOSAccess Protocol
Workflow
System Software
Systems
Access Protocol
4
Status
Roadmap for FY16Incorporate time-series system environment metrics store (In Progress)Add provenance capture mechanism that can handle the high-velocity provenance information – scalability (In Progress)Develop different language bindings for ProvEn Client API Design services supporting the harvesting of provenance from native source typesPerformance metrics reporting user interface
ACME – IPPD – Panorama Collaboration
Joint route forward, where the Panorama Pegasus workflow is used to implement an ACME workflow and capture provenance. ACME workflow with ASCR Integrated end-to-end Performance Prediction and Diagnosis for Extreme Scientific Workflows (IPPD) provenance model adapted for ACMEIPPD developed provenance store instance for ACME.
5
Thank [email protected]
6