Data Management and So-ware Centre



Similar documents
How To Understand The World Through Neutron Colored Eyes

NERSC Data Efforts Update Prabhat Data and Analytics Group Lead February 23, 2015

Data Lab System Architecture

INCREMENTAL, APPROXIMATE DATABASE QUERIES AND UNCERTAINTY FOR EXPLORATORY VISUALIZATION. Danyel Fisher Microso0 Research

Big Data and Cloud Computing for GHRSST

BENCHMARKING V ISUALIZATION TOOL

Return on Experience on Cloud Compu2ng Issues a stairway to clouds. Experts Workshop Nov. 21st, 2013

Cyber Supply Chain Risk Management Portal

Cloud Compu)ng in Educa)on and Research

Next Generation Operating Systems

Chapter 3. Database Architectures and the Web Transparencies

Case Studies in Solving Testing Constraints using Service Virtualization

An Open Dynamic Big Data Driven Applica3on System Toolkit

OpenDaylight: Introduction, Lithium and Beyond

DDC Sequencing and Redundancy

Effec%ve AX 2012 Upgrade Project Planning and Microso< Sure Step. Arbela Technologies

Introduc)on to Version Control with Git. Pradeep Sivakumar, PhD Sr. Computa5onal Specialist Research Compu5ng, NUIT

OS/Run'me and Execu'on Time Produc'vity

The Virtualization Practice

Data Management in the Cloud: Limitations and Opportunities. Annies Ductan

Materials Design and Discovery, and the Challenges of the Materials Genome Nicola Marzari, EPFL

Globus Striped GridFTP Framework and Server. Raj Kettimuthu, ANL and U. Chicago

Interna'onal Standards Ac'vi'es on Cloud Security EVA KUIPER, CISA CISSP HP ENTERPRISE SECURITY SERVICES

Part I Courses Syllabus

Stream Deployments in the Real World: Enhance Opera?onal Intelligence Across Applica?on Delivery, IT Ops, Security, and More

Cloud Compu)ng. Yeow Wei CHOONG Anne LAURENT

Performance Management in Big Data Applica6ons. Michael Kopp, Technology

Portable, Scalable, and High-Performance I/O Forwarding on Massively Parallel Systems. Jason Cope

Managing Complexity in Distributed Data Life Cycles Enhancing Scientific Discovery

Sonatype Nexus Professional

Cloud Sure - Virtual Machines

Protec'ng Informa'on Assets - Week 8 - Business Continuity and Disaster Recovery Planning. MIS 5206 Protec/ng Informa/on Assets Greg Senko

Assignment # 1 (Cloud Computing Security)

Managing Large Imagery Databases via the Web

Hadoop: Embracing future hardware

HPC Wales Skills Academy Course Catalogue 2015

Kaseya Fundamentals Workshop DAY THREE. Developed by Kaseya University. Powered by IT Scholars

Range of Organiza7onal Approaches

COMP/CS 605: Intro to Parallel Computing Lecture 01: Parallel Computing Overview (Part 1)

BornAgain: a versa.le framework for modelling and fi6ng GISAS

CS 378 Big Data Programming. Lecture 1 Introduc:on

Ibis: Scaling Python Analy=cs on Hadoop and Impala

Using GPUs in the Cloud for Scalable HPC in Engineering and Manufacturing March 26, 2014

Understanding Cloud Compu2ng Services. Rain in business success with amazing solu2ons in Cloud technology

So#ware quality assurance - introduc4on. Dr Ana Magazinius

Drupal in the Cloud. Scaling with Drupal and Amazon Web Services. Northern Virginia Drupal Meetup

HDFS Cluster Installation Automation for TupleWare

Investor Presenta,on Third Quarter ServiceNow All Rights Reserved 1

SQream Technologies Ltd - Confiden7al

Veeam Backup and Replication Architecture and Deployment. Nelson Simao Systems Engineer

HPC Cluster Decisions and ANSYS Configuration Best Practices. Diana Collier Lead Systems Support Specialist Houston UGM May 2014

THE CCLRC DATA PORTAL

HPC on AWS. Hiroshi Kobayashi, Dev./Lab. IT System HGST Japan, Ltd. Jun 3, 2015

On Demand Satellite Image Processing

Data Center Evolu.on and the Cloud. Paul A. Strassmann George Mason University November 5, 2008, 7:20 to 10:00 PM

The ASTRI SST- 2M ICT Infrastructure & The ASTRI MASS So>ware Test Bed

Graduate Systems Engineering Programs: Report on Outcomes and Objec:ves

Online Enrollment Op>ons - Sales Training Benefi+ocus.com, Inc. All rights reserved. Confiden>al and Proprietary 1

Cost effective methods of test environment management. Prabhu Meruga Director - Solution Engineering 16 th July SCQAA Irvine, CA

TEST AUTOMATION FRAMEWORK

Overview on Modern Accelerators and Programming Paradigms Ivan Giro7o

Open Science, Big Data and Research Reproducibility. Tony Hey Senior Data Science Fellow escience Ins>tute University of Washington

UNINETT Sigma2 AS: architecture and functionality of the future national data infrastructure

Transcription:

Data Management and So-ware Centre Mark Hagen Head of DMSC Mark.Hagen@esss.se www.europeanspalla:onsource.se Lithuanian Academy of Sciences, March 4 th 2014

What is DMSC? o Data Management and So-ware Centre (DMSC) o A Division of ESS Science Directorate Just like Neutron Technologies, Neutron Instruments etc. Two campuses: ESS Lund & ESS Copenhagen (Universitetsparken, Københavns Universitet) DMSC building to be constructed in Copenhagen o Responsibility: design, develop & implement for the ESS instruments: So-ware (user control interfaces, data acquisi:on, reduc:on & analysis) Hardware (servers, networks, worksta:ons, clusters, disks, pfs etc.) 2

ESS Organiza:on ESS BOARD OF DIRECTORS DIRECTOR GENERAL/CEO INFRASTRUCTURE DIRECTORATE MACHINE DIRECTORATE SCIENCE DIRECTORATE PROJECT SUPPORT & ADMINISTRATION DIRECTORATE CONVENTIONAL FACILITIES ACCELERATOR NEUTRON INSTRUMENTS GENERAL SERVICES SAFETY, HEALTH & ENVITONMENT TARGET NEUTRON TECHNOLOGIES HUMAN RESOURCES ENERGY SYSTEMS ENGINEERING SCIENTIFIC ACTIVITIES FINANCE INTEGRATED CONTROL SYSTEM SCIENTIFIC PROJECTS COMMUNICATIONS & EXTERNAL RELATIONS INTEGRATION & DESIGN SUPPORT DATA MANAGEMENT SOFTWARE CENTRE INFORMATION TECHNOLOGY LEGAL SUPPLY, PROCUREMENT & LOGISTICS

What is the ESS? DMSC ESS

What will DMSC do for ESS? o DMSC is involved. From idea to publica0on o So-ware and servers for the user proposals & the review o Coordina:on (scheduling) of experiments and equipment o The opera:on of the instruments/experiments Controlling the components of the instrument Acquiring the data from detectors & meta- data from instrument/samp. env. etc. Streaming the data (publish/subscribe) Recording/archiving/cataloguing the data Carrying out the data reduc:on o So-ware for Data Analysis Modeling & Simula:on o Finally a Publica:ons Database track the results from ESS

DMSC Organiza:on DMSC Data Systems & Technologies Inst. Control, Data Acq. & Reduc:on Data Management Data Analysis & Modeling User Office So-ware Copenhagen Data Centre DMSC servers in Lund Clusters, Worksta:ons Disks, Parallel File System Networks (inc. Lund CPH) Data transfer & Back- Up External Servers Instrument Control User Interfaces EPICS read/write Streaming data (ADARA) Data reduc:on (MANTID) File writers (ADARA) Data Catalogues Workflow Management Post- Processing. - - - - Reduc:on - - - - Analysis Messaging Services Web Interfaces MCSTAS support + dev. Instrument Integrators Analysis codes (e.g. SANSview, Rietveld, ) MD + DFT Framework User Database Proposal System Training Database Publica:ons Database Ini:ally one work package (2 work units) 6

General Framework + Customiza:on Generic Data Framework o Event mode data for later reprocessing/filtering o Stream the data è on the fly data processing (live view) è on the fly file crea:on è to a loca:on where appropriate post- acq. resources are available o Create standard HDF5 data files (NeXus or other) o (Where possible) Automate data reduc:on & analysis o Catalogue the data & meta- data for fast processing Don t re- invent the wheel è Exis:ng projects: ICAT, MANTID, ADARA Join these Customize for ESS Instruments o User Control Interface, detector type, IOC s for sample environment etc. 7

Data Acquisi:on, Reduc:on & Control NEUTRON TECHNOLOGIES Generic Framework o Instrument Control o Data Acquisi:on o Data Reduc:on & Visualiza:on Choppers Mo:on Control Sample Environment Fast Sample Environment Timing Bulk Data Readout (Detector Group) Control Box INTEGRATED CONTROL SYSTEMS User Control Interface Live, Local & Remote Data Reduc:on Data Analysis Interfaces Instrument Control Room Detectors & Monitors DATA MANAGEMENT & SOFTWARE CENTRE Automated Data Reduc:on Lund Server Room Data Aggregator & Streamer ( ) Automated Data Reduc:on Copenhagen Server Room 8

Control & DAQ Components Data AcquisiMon, Streaming & ReducMon Used by ESS accelerator/target, SLS, Diamond, US light sources, to be used by ISIS & SNS Publish/subscribe so-ware & protocol for streaming data (neutron + meta) Data reduc:on framework in Python & C++ developed by ISIS & SNS Data Management ICAT data cataloguing so-ware developed under NMI3 by PanData collabora:on of 19 European facili:es (+ SNS in US) 9

Data Analysis & Modeling o Data on disk is useless! It is published results from the data that makes progress o Need to ensure that ESS users have access to appropriate so-ware packages for data analysis the necessary computa:onal resources to exploit the so-ware to obtain those results analysis so-ware during experiment to influence the data taking strategies o Roll out in- sync with instruments Structure of Nanomaterials K. L. Krycka et al. Core Shell MagneMc Morphology of Structurally Uniform MagneMte NanoparMcles PRL 104, 207203 (2010) Polarized SANS demonstrated that these nanopar:cles have uniform nuclear structure but core- shell magne:c structure. Required development of both data reduc:on and data analysis methods and tools. 10

Data Analysis Development Original force- field IntegraMon of Analysis with Advanced Modeling Techniques Molecular Dynamics & Density Func:onal Theory (DFT) Techniques Jose Borreguero (SNS/NDAV) Mike Crawford (Dupont) & Niina Jalarvo (Julich): BASIS experiment / MD simula:on studies of Methyl rota:ons in methyl- Polyhedral oligomeric silsesquioxanes (POSS) Op:miza:on of dihedral poten:al governing the rota:onal jumps in methyl hydrogens. Preliminary simula:ons indicate that the dihedral poten:al barrier must be decreased ~37% in order to match experimental data OpMmized force- field

Data Systems & Technologies o DMSC will not be a supercomputer centre o Data (disk) storage: Back of the envelope è 2 3 PBytes/yr Spectrum of file sizes: ~100MByte - ~10 s GByte ~1TByte Fast disk (200MByte/s) & Parallel File System (10GByte/s) o Cluster(s) for data reduc:on & (modest) data analysis - ~2048 cores Architecture CPU, GPU visualiza:on cluster/server o Data download servers s-p & grid-p o Remote login capability for ESS users: Re- reduce data using cluster Data analysis so-ware available for users o So-ware development servers repositories, bug trackers, build servers 12

During the Construc:on Years o Primary goal: To be ready for hot commissioning of first ESS instruments in 2020. o Includes significant amount of NRE (Non- Recurrent Engineering) for subsequent ESS instruments. o Establish the basic facili:es at both campuses. o Front loaded with instrument- centric work + scope to grow analysis in an integrated way 13

Conclusion o DMSC s mission is the computa:onal (so-ware/hardware) infrastructure for the ESS data chain - instrument control, data acquisi:on, reduc:on & analysis o Generic framework customized for each of the instruments u:lizes data streaming to account for large data files/live processing o Don t re- invent the wheel work with collaborators ISIS, SNS, PanData (+ others?) to develop/customize exis:ng so-ware EPICS, ADARA, MANTID, ICAT o Customize for each of the ESS instruments in- sync as they roll out o In- sync with instrument roll out work with instrument teams to ensure analysis so-ware is available (doesn t necessarily mean develop) o Longer term goal to develop new data analysis methods for ESS instruments 14

Ques:ons QUESTIONS