SlideShare a Scribd company logo
“The Pacific Research Platform
The First Six Years”
PRP Capstone Symposium
Virtual Meeting
June 22, 2021
1
Dr. Larry Smarr
Founding Director Emeritus, California Institute for Telecommunications and Information Technology;
Distinguished Professor Emeritus, Dept. of Computer Science and Engineering
Jacobs School of Engineering, UCSD
http://lsmarr.calit2.net
(GDC)
2015 Vision: The Pacific Research Platform Will Connect Science DMZs
Creating a Regional End-to-End Science-Driven Community Cyberinfrastructure
NSF CC*DNI Grant
$6.3M 10/2015-10/2020
In Year 5 Now
PI: Larry Smarr, UC San Diego Calit2
Co-PIs:
• Camille Crittenden, UC Berkeley CITRIS,
• Philip Papadopoulos, UCI
• Tom DeFanti, UC San Diego Calit2/QI,
• Frank Wuerthwein, UCSD Physics and SDSC
Source: John Hess, CENIC
Supercomputer
Centers
ESnet: Given Fast Networks, Need
DMZs and Fast/Tuned DTNs
Terminating the Fiber Optics - Data Transfer Nodes (DTNs):
Flash I/O Network Appliances (FIONAs)
UCSD-Designed FIONAs Solved the Disk-to-Disk Data Transfer Problem
at Near Full Speed on Best-Effort 10G, 40G and 100G Networks
FIONAs Designed by UCSD’s Phil Papadopoulos, John Graham,
Joe Keefe, and Tom DeFanti
Two FIONA DTNs at UC Santa Cruz: 40G & 100G
Up to 192 TB Rotating Storage
Add Up to 8 Nvidia GPUs Per 2U FIONA
To Add Machine Learning Capability
2018/2019: Installing Community Shared FIONA CPU/GPU/Storage Systems
on Campuses and Working With Campus CIOs on DMZs
UC Merced
Stanford
UC Santa Barbara
UC Riverside
UC Santa Cruz
UC Irvine
Ann Kovalchick
Panel 2
2017-2020: CHASE-CI Grant Adds a Machine Learning Layer
Built on Top of the Pacific Research Platform
Caltech
UCB
UCI UCR
UCSD
UCSC
Stanford
MSU
UCM
SDSU
NSF Grant for 256 High Speed “Cloud” GPUs
For 32 ML Faculty & Their Students at 10 Campuses
To Train AI Algorithms on Big Data
Original PRP
CENIC/PW Link
2018-2021: Toward the National Research Platform (NRP) -
Using CENIC & Internet2 to Connect Quilt Regional R&E Networks
“Towards
The NRP”
3-Year Grant
Funded
by NSF
$2.5M
October 2018
PI Smarr
Co-PIs Altintas
Papadopoulos
Wuerthwein
Rosing
DeFanti
NSF CENIC Link
Original PRP
CENIC/PW Link
Sana Bellamine
Panel 2
Jim Kyriannis
Panel 2
2018/2019: PRP Game Changer!
Using Kubernetes to Orchestrate Containers Across the PRP
User
Applications
Containers
Clouds
PRP’s Nautilus Hypercluster Adopted Kubernetes to Orchestrate Software Containers
and Rook, Which Runs Inside of Kubernetes, to Manage Distributed Storage
https://rook.io/
“Kubernetes with Rook/Ceph Allows Us to Manage Petabytes of Distributed Storage
and GPUs for Data Science,
While We Measure and Monitor Network Use.”
--John Graham, Calit2/QI UC San Diego
Rotating Storage
4000 TB
PRP’s Nautilus is a Multi-Institution Hypercluster
Connected by Optical Networks
180 FIONAs on 25 Partner Campuses
Networked Together at 10-100Gbps
PRP Principles:
Technology Evolution and Community Building
• Innovation
– Identify technologies nearing tipping points & evolve them into PRP stable services
– Early access to new hardware is critical (FPGA/GPU/TPU/DPU…)
– Aggressively adopt automation software systems
• Adoption
– Early engagement with opensource software projects ( Rook / Admiralty … )
– Share experience with the community (Workshops, Portal docs, Matrix chat, and weekly PRP call)
• Scaling
– Reduce complexity for initial onboarding of hardware, projects and users
– Build more turnkey solutions supporting both research and instructional computing needs
• Sustaining
– Actively seek new collaborations
– Grow the Nautilus user support service Social Network in the Matrix chat federation
– Promote the Pot-Luck-Supercomputing paradigm
John Graham
Panel 2
PRP is Science-Driven:
Connecting Multi-Campus Application Teams and Devices
Earth
Sciences
UC San Diego UCBerkeley UC Merced
Frank Wuerthwein
Panel 1
Scott Sellars
Panel 1
Alex Feltus
Panel 1
Jeff Weekley
Panel 1
Supporting and Expanding Emerging
High-Priority PRP Applications
– Climate Change-Induced Natural Hazards Prediction and Mitigation
– Wildfires
– Data Analysis from Large-Scale Scientific Instruments
– CASPER
– Community Biological Database Generation
– Better Forcefields for COVID-19 Simulations
– Understanding the Brain
– NSF’s NeuroNex
Ilkay Altintas
Panel 1
Peak 1100 PRP CPU-Cores
Top 20 GPU Users Out of 400 Nautilus Namespace Applications:
Together They Consumed Nearly 500 GPUs in 2020
Frank Wuerthwein, UCSD
osggpus [IceCube]
Mark Alber, UCR
markalbergroup
Nuno Vasconcelos, UCSD
domain-adaptation
Ravi Ramamoorthi, UCSD
ucsd-ravigroup
Hao Su, UCSD
ucsd-haosulab
Folding@Home
folding
Igor Sfiligoi, UCSD
isfiligoi
Xiaolong Wang, UCSD
rl-multitask
Xiaolong Wang, UCSD
rl-multitask
Xiaolong Wang, UCSD
self-supervised-video
Xiaolong Wang, UCSD
hand-object-interaction
Dinesh Bharadia, UCSD
ecepxie
Manmohan Chandraker, UCSD
mc-lab
Frank Wuerthwein, UCSD
cms-ml
Nuno Vasconcelos, UCSD
svcl-oowl
Vineet Bafna, UCSD
ecdna
Larry Smarr, UCSD
jupyterlab
Rose Yu, UCSD
deep-forecast
Nuno Vasconcelos, UCSD
svcl-multimodal-learning
Gary Cottrell, UCSD
guru-research
Community Building
Through Large-Scale Workshops
Ana Hunsinger
Futures
Increasing Participation Through
PRP Science Engagement Workshops
Source: Camille Crittenden, UC Berkeley
UC Merced
UC Davis
UC Berkeley
UC San Diego
Chris Hoffman
Futures
PRP Weekly Engineering Zoom Meeting
Tom DeFanti
Futures
Community Building Though Inclusion and Diversity:
Workshops With Minority Serving Universities
Richard Alo
Panel 2

More Related Content

PPTX
The Pacific Research Platform- a High-Bandwidth Distributed Supercomputer
PPTX
The PRP and Its Applications
PPTX
The National Research Platform Enables a Growing Diversity of Users and Appl...
PPTX
Toward a National Research Platform to Enable Data-Intensive Computing
PPTX
National Federated Compute Platforms: The Pacific Research Platform
PPTX
Utilizing Nautilus and the National Research Platform for Big Data Research a...
PPTX
The Pacific Research Platform Connects to CSU San Bernardino
PPTX
The Pacific Research Platform: Building a Distributed Big Data Machine Learni...
The Pacific Research Platform- a High-Bandwidth Distributed Supercomputer
The PRP and Its Applications
The National Research Platform Enables a Growing Diversity of Users and Appl...
Toward a National Research Platform to Enable Data-Intensive Computing
National Federated Compute Platforms: The Pacific Research Platform
Utilizing Nautilus and the National Research Platform for Big Data Research a...
The Pacific Research Platform Connects to CSU San Bernardino
The Pacific Research Platform: Building a Distributed Big Data Machine Learni...

Similar to The Pacific Research Platform: The First Six Years (20)

PPTX
Looking Back, Looking Forward NSF CI Funding 1985-2025
PPTX
Toward a National Research Platform to Enable Data-Intensive Open-Source Sci...
PPTX
Berkeley cloud computing meetup may 2020
PPTX
The Pacific Research Platform 18 Months In
PPTX
From the Pacific Research Platform to a National Research Platform
PPTX
The Pacific Research Platform Enables Distributed Big-Data Machine-Learning
PPTX
Security Challenges and the Pacific Research Platform
PPTX
Panel Presentation - Tom DeFanti with Larry Smarr and Frank Wuerthwein - Naut...
PPTX
Getting Started Using the National Research Platform
PPTX
The Pacific Research Platform Two Years In
PPTX
The CENIC-AI Resource: The Right Connection
PPTX
The Pacific Research Platform: Building a Distributed Big-Data Machine-Learni...
PPTX
Toward A National Big Data Superhighway
PPTX
The Pacific Research Platform: Building a Distributed Big-Data Machine-Learni...
PPTX
Creating a Science-Driven Big Data Superhighway
PPTX
PRP, CHASE-CI, TNRP and OSG
PPTX
The PRP and Its Applications - Nautilus and the National Research Platform
PPTX
Toward a Global Research Platform for Big Data Analysis
PPTX
The Pacific Research Platform
PPTX
Toward a National Research Platform
Looking Back, Looking Forward NSF CI Funding 1985-2025
Toward a National Research Platform to Enable Data-Intensive Open-Source Sci...
Berkeley cloud computing meetup may 2020
The Pacific Research Platform 18 Months In
From the Pacific Research Platform to a National Research Platform
The Pacific Research Platform Enables Distributed Big-Data Machine-Learning
Security Challenges and the Pacific Research Platform
Panel Presentation - Tom DeFanti with Larry Smarr and Frank Wuerthwein - Naut...
Getting Started Using the National Research Platform
The Pacific Research Platform Two Years In
The CENIC-AI Resource: The Right Connection
The Pacific Research Platform: Building a Distributed Big-Data Machine-Learni...
Toward A National Big Data Superhighway
The Pacific Research Platform: Building a Distributed Big-Data Machine-Learni...
Creating a Science-Driven Big Data Superhighway
PRP, CHASE-CI, TNRP and OSG
The PRP and Its Applications - Nautilus and the National Research Platform
Toward a Global Research Platform for Big Data Analysis
The Pacific Research Platform
Toward a National Research Platform
Ad

More from Larry Smarr (20)

PPTX
Smart Patients, Big Data, NextGen Primary Care
PPTX
Internet2 and QUILT Initiatives with Regional Networks -6NRP Larry Smarr and ...
PPTX
Internet2 and QUILT Initiatives with Regional Networks -6NRP Larry Smarr and ...
PPTX
National Research Platform: Application Drivers
PPT
From Supercomputing to the Grid - Larry Smarr
PPTX
The CENIC-AI Resource - Los Angeles Community College District (LACCD)
PPT
Redefining Collaboration through Groupware - From Groupware to Societyware
PPT
The Coming of the Grid - September 8-10,1997
PPT
Supercomputers: Directions in Technology, Architecture, and Applications
PPT
High Performance Geographic Information Systems
PPT
Data Intensive Applications at UCSD: Driving a Campus Research Cyberinfrastru...
PPT
Enhanced Telepresence and Green IT — The Next Evolution in the Internet
PPTX
The CENIC AI Resource CENIC AIR - CENIC Retreat 2024
PPTX
The NSF Grants Leading Up to CHASE-CI ENS
PPTX
Integrated Optical Fiber/Wireless Systems for Environmental Monitoring
PPTX
Digital Twins of Physical Reality - Future in Review
PPTX
Larry Smarr’s Prostate Cancer Early Detection and Focal Therapy
PPTX
The Increasing Use of the National Research Platform by the CSU Campuses
PPTX
The CENIC-Connected Cyberinfrastructure Commons: Enabling AI for Research and...
PPTX
The Rise of Supernetwork Data Intensive Computing
Smart Patients, Big Data, NextGen Primary Care
Internet2 and QUILT Initiatives with Regional Networks -6NRP Larry Smarr and ...
Internet2 and QUILT Initiatives with Regional Networks -6NRP Larry Smarr and ...
National Research Platform: Application Drivers
From Supercomputing to the Grid - Larry Smarr
The CENIC-AI Resource - Los Angeles Community College District (LACCD)
Redefining Collaboration through Groupware - From Groupware to Societyware
The Coming of the Grid - September 8-10,1997
Supercomputers: Directions in Technology, Architecture, and Applications
High Performance Geographic Information Systems
Data Intensive Applications at UCSD: Driving a Campus Research Cyberinfrastru...
Enhanced Telepresence and Green IT — The Next Evolution in the Internet
The CENIC AI Resource CENIC AIR - CENIC Retreat 2024
The NSF Grants Leading Up to CHASE-CI ENS
Integrated Optical Fiber/Wireless Systems for Environmental Monitoring
Digital Twins of Physical Reality - Future in Review
Larry Smarr’s Prostate Cancer Early Detection and Focal Therapy
The Increasing Use of the National Research Platform by the CSU Campuses
The CENIC-Connected Cyberinfrastructure Commons: Enabling AI for Research and...
The Rise of Supernetwork Data Intensive Computing
Ad

Recently uploaded (20)

PPT
Chemical bonding and molecular structure
PDF
Unveiling a 36 billion solar mass black hole at the centre of the Cosmic Hors...
PDF
An interstellar mission to test astrophysical black holes
PPTX
cpcsea ppt.pptxssssssssssssssjjdjdndndddd
PDF
AlphaEarth Foundations and the Satellite Embedding dataset
DOCX
Viruses (History, structure and composition, classification, Bacteriophage Re...
PPT
protein biochemistry.ppt for university classes
PPTX
7. General Toxicologyfor clinical phrmacy.pptx
PPTX
microscope-Lecturecjchchchchcuvuvhc.pptx
PPT
The World of Physical Science, • Labs: Safety Simulation, Measurement Practice
PPTX
INTRODUCTION TO EVS | Concept of sustainability
PPTX
2. Earth - The Living Planet earth and life
PPTX
2. Earth - The Living Planet Module 2ELS
PPTX
ANEMIA WITH LEUKOPENIA MDS 07_25.pptx htggtftgt fredrctvg
PDF
HPLC-PPT.docx high performance liquid chromatography
PDF
SEHH2274 Organic Chemistry Notes 1 Structure and Bonding.pdf
PDF
MIRIDeepImagingSurvey(MIDIS)oftheHubbleUltraDeepField
PPTX
SCIENCE10 Q1 5 WK8 Evidence Supporting Plate Movement.pptx
PPTX
EPIDURAL ANESTHESIA ANATOMY AND PHYSIOLOGY.pptx
PPTX
Taita Taveta Laboratory Technician Workshop Presentation.pptx
Chemical bonding and molecular structure
Unveiling a 36 billion solar mass black hole at the centre of the Cosmic Hors...
An interstellar mission to test astrophysical black holes
cpcsea ppt.pptxssssssssssssssjjdjdndndddd
AlphaEarth Foundations and the Satellite Embedding dataset
Viruses (History, structure and composition, classification, Bacteriophage Re...
protein biochemistry.ppt for university classes
7. General Toxicologyfor clinical phrmacy.pptx
microscope-Lecturecjchchchchcuvuvhc.pptx
The World of Physical Science, • Labs: Safety Simulation, Measurement Practice
INTRODUCTION TO EVS | Concept of sustainability
2. Earth - The Living Planet earth and life
2. Earth - The Living Planet Module 2ELS
ANEMIA WITH LEUKOPENIA MDS 07_25.pptx htggtftgt fredrctvg
HPLC-PPT.docx high performance liquid chromatography
SEHH2274 Organic Chemistry Notes 1 Structure and Bonding.pdf
MIRIDeepImagingSurvey(MIDIS)oftheHubbleUltraDeepField
SCIENCE10 Q1 5 WK8 Evidence Supporting Plate Movement.pptx
EPIDURAL ANESTHESIA ANATOMY AND PHYSIOLOGY.pptx
Taita Taveta Laboratory Technician Workshop Presentation.pptx

The Pacific Research Platform: The First Six Years

  • 1. “The Pacific Research Platform The First Six Years” PRP Capstone Symposium Virtual Meeting June 22, 2021 1 Dr. Larry Smarr Founding Director Emeritus, California Institute for Telecommunications and Information Technology; Distinguished Professor Emeritus, Dept. of Computer Science and Engineering Jacobs School of Engineering, UCSD http://lsmarr.calit2.net
  • 2. (GDC) 2015 Vision: The Pacific Research Platform Will Connect Science DMZs Creating a Regional End-to-End Science-Driven Community Cyberinfrastructure NSF CC*DNI Grant $6.3M 10/2015-10/2020 In Year 5 Now PI: Larry Smarr, UC San Diego Calit2 Co-PIs: • Camille Crittenden, UC Berkeley CITRIS, • Philip Papadopoulos, UCI • Tom DeFanti, UC San Diego Calit2/QI, • Frank Wuerthwein, UCSD Physics and SDSC Source: John Hess, CENIC Supercomputer Centers ESnet: Given Fast Networks, Need DMZs and Fast/Tuned DTNs
  • 3. Terminating the Fiber Optics - Data Transfer Nodes (DTNs): Flash I/O Network Appliances (FIONAs) UCSD-Designed FIONAs Solved the Disk-to-Disk Data Transfer Problem at Near Full Speed on Best-Effort 10G, 40G and 100G Networks FIONAs Designed by UCSD’s Phil Papadopoulos, John Graham, Joe Keefe, and Tom DeFanti Two FIONA DTNs at UC Santa Cruz: 40G & 100G Up to 192 TB Rotating Storage Add Up to 8 Nvidia GPUs Per 2U FIONA To Add Machine Learning Capability
  • 4. 2018/2019: Installing Community Shared FIONA CPU/GPU/Storage Systems on Campuses and Working With Campus CIOs on DMZs UC Merced Stanford UC Santa Barbara UC Riverside UC Santa Cruz UC Irvine Ann Kovalchick Panel 2
  • 5. 2017-2020: CHASE-CI Grant Adds a Machine Learning Layer Built on Top of the Pacific Research Platform Caltech UCB UCI UCR UCSD UCSC Stanford MSU UCM SDSU NSF Grant for 256 High Speed “Cloud” GPUs For 32 ML Faculty & Their Students at 10 Campuses To Train AI Algorithms on Big Data
  • 6. Original PRP CENIC/PW Link 2018-2021: Toward the National Research Platform (NRP) - Using CENIC & Internet2 to Connect Quilt Regional R&E Networks “Towards The NRP” 3-Year Grant Funded by NSF $2.5M October 2018 PI Smarr Co-PIs Altintas Papadopoulos Wuerthwein Rosing DeFanti NSF CENIC Link Original PRP CENIC/PW Link Sana Bellamine Panel 2 Jim Kyriannis Panel 2
  • 7. 2018/2019: PRP Game Changer! Using Kubernetes to Orchestrate Containers Across the PRP User Applications Containers Clouds
  • 8. PRP’s Nautilus Hypercluster Adopted Kubernetes to Orchestrate Software Containers and Rook, Which Runs Inside of Kubernetes, to Manage Distributed Storage https://rook.io/ “Kubernetes with Rook/Ceph Allows Us to Manage Petabytes of Distributed Storage and GPUs for Data Science, While We Measure and Monitor Network Use.” --John Graham, Calit2/QI UC San Diego
  • 9. Rotating Storage 4000 TB PRP’s Nautilus is a Multi-Institution Hypercluster Connected by Optical Networks 180 FIONAs on 25 Partner Campuses Networked Together at 10-100Gbps
  • 10. PRP Principles: Technology Evolution and Community Building • Innovation – Identify technologies nearing tipping points & evolve them into PRP stable services – Early access to new hardware is critical (FPGA/GPU/TPU/DPU…) – Aggressively adopt automation software systems • Adoption – Early engagement with opensource software projects ( Rook / Admiralty … ) – Share experience with the community (Workshops, Portal docs, Matrix chat, and weekly PRP call) • Scaling – Reduce complexity for initial onboarding of hardware, projects and users – Build more turnkey solutions supporting both research and instructional computing needs • Sustaining – Actively seek new collaborations – Grow the Nautilus user support service Social Network in the Matrix chat federation – Promote the Pot-Luck-Supercomputing paradigm John Graham Panel 2
  • 11. PRP is Science-Driven: Connecting Multi-Campus Application Teams and Devices Earth Sciences UC San Diego UCBerkeley UC Merced Frank Wuerthwein Panel 1 Scott Sellars Panel 1 Alex Feltus Panel 1 Jeff Weekley Panel 1
  • 12. Supporting and Expanding Emerging High-Priority PRP Applications – Climate Change-Induced Natural Hazards Prediction and Mitigation – Wildfires – Data Analysis from Large-Scale Scientific Instruments – CASPER – Community Biological Database Generation – Better Forcefields for COVID-19 Simulations – Understanding the Brain – NSF’s NeuroNex Ilkay Altintas Panel 1 Peak 1100 PRP CPU-Cores
  • 13. Top 20 GPU Users Out of 400 Nautilus Namespace Applications: Together They Consumed Nearly 500 GPUs in 2020 Frank Wuerthwein, UCSD osggpus [IceCube] Mark Alber, UCR markalbergroup Nuno Vasconcelos, UCSD domain-adaptation Ravi Ramamoorthi, UCSD ucsd-ravigroup Hao Su, UCSD ucsd-haosulab Folding@Home folding Igor Sfiligoi, UCSD isfiligoi Xiaolong Wang, UCSD rl-multitask Xiaolong Wang, UCSD rl-multitask Xiaolong Wang, UCSD self-supervised-video Xiaolong Wang, UCSD hand-object-interaction Dinesh Bharadia, UCSD ecepxie Manmohan Chandraker, UCSD mc-lab Frank Wuerthwein, UCSD cms-ml Nuno Vasconcelos, UCSD svcl-oowl Vineet Bafna, UCSD ecdna Larry Smarr, UCSD jupyterlab Rose Yu, UCSD deep-forecast Nuno Vasconcelos, UCSD svcl-multimodal-learning Gary Cottrell, UCSD guru-research
  • 14. Community Building Through Large-Scale Workshops Ana Hunsinger Futures
  • 15. Increasing Participation Through PRP Science Engagement Workshops Source: Camille Crittenden, UC Berkeley UC Merced UC Davis UC Berkeley UC San Diego Chris Hoffman Futures
  • 16. PRP Weekly Engineering Zoom Meeting Tom DeFanti Futures
  • 17. Community Building Though Inclusion and Diversity: Workshops With Minority Serving Universities Richard Alo Panel 2