Synergistic Challenges in Data-Intensive Science and Extreme Scale - PowerPoint PPT Presentation

Synergistic Challenges in Data-Intensive Science and Extreme Scale Computing Vivek Sarkar Department of Computer Science Rice University vsarkar@rice.edu NSF workshop on Big Data and Extreme-scale Computing (BDEC) April 30 - May 1, 2013

Outline 1. DOE ASCAC Subcommittee report on Synergistic Challenges in Data-Intensive Science and Exascale Computing 2. Selected Research Topics in Big Data and Extreme Scale 2

ASCAC Subcommittee Report Available via “Relevant Background Material” link in BDEC workshop web site 3

ASCAC Subcommittee Members Last name First name Affiliation Chen (*) Jacqueline Sandia Choudhary Alok Northwestern U. Feldman Stuart Google Hendrickson Bruce Sandia Johnson Chris U. Utah Mount Richard SLAC Sarkar (**) Vivek Rice U. White (*) Victoria FermiLab Williams (*) Dean LLNL (*) ASCAC member, (**) Subcommittee chair ASCAC ¡ 4 § 4

Our Charge �� “By this letter, I am charging the �� ASCAC to examine the �� potential synergies between the �� challenges of data-intensive �� science and exascale. The �� subcommittee should take into �� account the Department’s �� mission needs, which define the �� Office of Science’s unique rile in �� data-intensive science vis-à-vis other agencies.” �� ASCAC ¡ 5 § 5

Data Challenges in Science Overall trend: most science domains will become data-intensive in the exascale timeframe (and many well before then) 18" 16" CAGR = 72% Detector" 14" Sequencer" 12" Processor" Memory" 10" CAGR = 60% 8" 6" CAGR = 36% 4" 2" CAGR = 20% 0" 2010" 2011" 2012" 2013" 2014" 2015" Source: notional figure, Source: Bill Harrod, SC12 courtesy of Kathy Yelick plenary presentation ASCAC ¡ 6 § 6

Synergistic Challenges in Data-Intensive Science and Extreme Scale - PowerPoint PPT Presentation

Synergistic Challenges in Data-Intensive Science and Extreme Scale Computing Vivek Sarkar Department of Computer Science Rice University vsarkar@rice.edu NSF workshop on Big Data and Extreme-scale Computing (BDEC) April 30 - May 1, 2013

and Observational Science The Convergence of Data-Intensive and Compute-Intensive Infrastructure

Data-Intensive Research in Education: NSF Initiatives in Big Data and Data Science Chris

Extreme Data-Intensive Scientific Computing Alex Szalay JHU Big Data in Science Data

The Moore/Sloan Data Science Environments: Advancing Data-Intensive

The Revolution in Experimental and Observational Science: The Convergence of Data-Intensive and

Data-Intensive Science Using GPUs Alex Szalay, JHU Data in HPC Simulations HPC is an

Big Data, Big Problem Data-intensive systems are highly complex Manipulate large-scale

Data-Intensive Workfmows A journey to a Holistjc Framework for Data-Intensive Workfmows Ian

CS6453 Data-Intensive Systems: Technology trends, Emerging challenges & opportuni=es Rachit

Turning Data Into Business Value Qwertee 101: Finding Your Next Data Partner Data-Intensive

Future Infrastructure for Data-Intensive Science David Schade Canadian Astronomy Data Centre

memory-intensive VMs in a data center Kasidit Chanchio Vasabilab Dept of Computer Science,

MapReduce Data Intensive Computing Data-intensive computing is a class of parallel

Enabling Enabling Data- -Intensive Science Intensive Science Data with Tactical Storage

SYNERGISTIC FLAME RETARDANT EFFECT OF ATTAPULGITE ON PP/APP/PER COMPERSITES XQ Su, J Tao *, YW

Collaborative Data Intensive Science Arun Jagatheesan San Diego Supercomputer Center and

Scientific Workflows at DataWarp-Speed: Accelerated Data-Intensive Science using NERSCs Burst

OCIO UFOs Template 4 April 26, 2011 4 April 26, 2011 Objectives 1. Provide an interoperable

The Dark Energy Survey Data Management System as a Data Intensive Science Gateway Kailash Kotwani

for Data Intensive Scalable Computing CAP3 Gene Assembly Program Compute intensive

Data-Intensive Distributed Computing CS 451/651 431/631 (Winter 2018) Part 9: Real-Time Data

Data- Intensive

Current and Future Data Intensive Computing at DOE BES User Facilities Steve Miller Scientific

Data-Intensive Distributed Computing CS 451/651 (Fall 2018) Part 9: Real-Time Data Analytics (1/2)

Synergistic Challenges in Data-Intensive Science and Extreme Scale - PowerPoint PPT Presentation

Synergistic Challenges in Data-Intensive Science and Extreme Scale Computing Vivek Sarkar Department of Computer Science Rice University vsarkar@rice.edu NSF workshop on Big Data and Extreme-scale Computing (BDEC) April 30 - May 1, 2013

and Observational Science The Convergence of Data-Intensive and Compute-Intensive Infrastructure

Data-Intensive Research in Education: NSF Initiatives in Big Data and Data Science Chris

Extreme Data-Intensive Scientific Computing Alex Szalay JHU Big Data in Science Data

The Moore/Sloan Data Science Environments: Advancing Data-Intensive

The Revolution in Experimental and Observational Science: The Convergence of Data-Intensive and

Data-Intensive Science Using GPUs Alex Szalay, JHU Data in HPC Simulations HPC is an

Big Data, Big Problem Data-intensive systems are highly complex Manipulate large-scale

Data-Intensive Workfmows A journey to a Holistjc Framework for Data-Intensive Workfmows Ian

CS6453 Data-Intensive Systems: Technology trends, Emerging challenges &amp; opportuni=es Rachit

Turning Data Into Business Value Qwertee 101: Finding Your Next Data Partner Data-Intensive

Future Infrastructure for Data-Intensive Science David Schade Canadian Astronomy Data Centre

memory-intensive VMs in a data center Kasidit Chanchio Vasabilab Dept of Computer Science,

MapReduce Data Intensive Computing Data-intensive computing is a class of parallel

Enabling Enabling Data- -Intensive Science Intensive Science Data with Tactical Storage

SYNERGISTIC FLAME RETARDANT EFFECT OF ATTAPULGITE ON PP/APP/PER COMPERSITES XQ Su, J Tao *, YW

Collaborative Data Intensive Science Arun Jagatheesan San Diego Supercomputer Center and

Scientific Workflows at DataWarp-Speed: Accelerated Data-Intensive Science using NERSCs Burst

OCIO UFOs Template 4 April 26, 2011 4 April 26, 2011 Objectives 1. Provide an interoperable

The Dark Energy Survey Data Management System as a Data Intensive Science Gateway Kailash Kotwani

for Data Intensive Scalable Computing CAP3 Gene Assembly Program Compute intensive

Data-Intensive Distributed Computing CS 451/651 431/631 (Winter 2018) Part 9: Real-Time Data

Data- Intensive

Current and Future Data Intensive Computing at DOE BES User Facilities Steve Miller Scientific

Data-Intensive Distributed Computing CS 451/651 (Fall 2018) Part 9: Real-Time Data Analytics (1/2)

CS6453 Data-Intensive Systems: Technology trends, Emerging challenges & opportuni=es Rachit