SlideShare a Scribd company logo
An Open Software Platform
for the SKA?
Nicolás Erdödy
Founder, CEO – Open Parallel Ltd
SKA in Seoul:
Asia-Pacific Regional Workshop in HI Science
Seoul, Korea - November 2, 2015
Brief
● The Problem: “data deluge”
● The Opportunity: We see the SKA SDP
compute model as the general case
● TOPS - A Distributed OS for Rack Scale
Computing.
● How to start: Open Source & Open Stack
● We need your help...
Efficient recognition of signals
from a massive amount
of data noise
improves operational efficiencies,
scientific discovery and
forms the cradle of
adaptive service delivery.
As today's HPC
becomes tomorrow's
Cloud computing platform
it will enable a wider application of
Machine Understanding
-the near real-time
complex modelling
and analysis of data
that leads to insight
and faster decisions.
Today's problems and beyond
● Non-professional software development (in
many scientific environments) lead to limited or
null software stack reuse.
● Data deluge (44 ZettaBytes by 2020 – IDC).
● The exascale challenge: 10^18 calculations p/s
● Power consumption.
● Heterogeneous hardware.
● Compute Islands?
● Software Defined Everything (SDN, SDI, SDS).
SDP Preliminary Compute Platform
Design (*)
● Quite different than on a general-purpose
supercomputer
● Workload-driven system design philosophy to
tune SDP hardware.
● SDP Compute Islands - “self-contained,
independent collection of compute nodes”.
● Only process data contained in the island itself.
● (*) Broekema, van Nieuwpoort, Bal (July 2015)
TOPS – What are we doing
● Conceived as a Rack Scale distributed
Operating System for the Data Centre.
● TOPS workshop #2 (Multicore World 2016, Wellington, NZ)
● CSP's Software Development Plan.
● Panel “Towards an Open Software Stack for
Exascale Computing” at SuperComputing15 – Austin,
Texas, USA (15-20 Nov).
● OpenStack - South Africa - 2015 CHPC conference,
Pretoria (1-4 Dec)
“Towards an Open Software Stack for
Exascale Computing” (SC15 – 19Nov – Austin, USA ).
● Prof. Jack Dongarra (Tennessee, Turing Fellow –
Manchester, scientific advisory board for SKA, LINPACK).
● Prof. Thomas Sterling (Indiana, Centre for Research
Extreme Scale Technologies, Beowulf clusters, MCW15).
● Dr. Pete Beckman (Exascale Technology & Computing
Institute, Argonne Labs – Chicago, Argo OS).
● Dr. John Gustafson (fmr AMD Chief Product Architect,
Director Intel Labs, Sun, Gustafson's Law, MCW14).
● Dr. Robert Wisniewski (Chief Software Architect Exascale
Computing, Intel -formerly Chief Software Architect Blue
Gene Supercomputer, IBM).
● Chris Broekema (SDP COMP Task Leader, ASTRON,
Netherlands).
Your input
● What should TOPS be / do for you?
● Let's start a chat -this is a 2-5 years
conversation.
● Thank you!
● OpenParallel.com
● MulticoreWorld.com
● Nicolas.Erdody@openparallel.com
● Oamaru, South Island, New Zealand
The data deluge will change
how we build and manage
new systems to store
and understand data
“This time, we have time”
a) How should software evolve to address exascale demands? Are OpenStack
or other platforms part of the solution? Algorithms should evolve, and most
legacy software will be replaced: so what should be the focus of the new ones?
To save power? To increase speed? To improve programmability?
b) How heterogeneous would/should “your” exascale system be? Is there a role
for Co-design towards exascale?
c) The SKA project is an example where once it becomes operational, exascale
problems will appear very early. But venture capitalists don't invest in radio-
telescopes. What killer app would attract them towards early adoption of
exascale computing? Which industries will migrate first?
d) Would HPC in the cloud be possible for exascale computing? Which
technologies do we need to change / challenge to make it feasible? Data
transport? Servers? What are those technologies most important for your work?
e) Do you envisage a similar development effort as we had with OSS over
decades, or will bottlenecks develop due to lack of specialised talent globally?
Will proprietary solutions continue to emerge or co-exist? Who will “own” the
exascale era? Microsoft? Google? Will there be competition between existing
companies and “not yet founded” start-ups, or will each organisation have its
own in-house development shop?
Open Parallel Ltd.
● NZ Company – involved with SKA since 2011.
● 3 NZ organisations (AUT, VUW & OP) were
formally pre-selected in 2012 by the NZ Govt
-after international peer-review, as viable
prospects for engagement in SDP and CSP.
● Since 2013 Open Parallel is formally:
- Work Package Manager of the Software
Development Environment for the CSP,
- Contributing to SDP Compute Platform,
- Member of the NZ SKA Alliance (lead by AUT
university).
OP's work for the SKA
What's done (2013 - 2015)
Version 1 of “SKA CSP Element Software Development Plan”
(SE-23). How the CSP element “will develop and deliver software
and/or firmware in accordance to a design specification.”
Incorporated into SDP’s Architecture Reference Document (2014)
and referenced in SDP’s “Compute Platform: Software stack
developments and considerations” (SDP’s PDR 2015).
To be fully delivered over Stage 2 timeframe (2015 - 2017).
Most recent task: provide CSP Consortium with SW/FW process
requirements to support the effective re-use of SW and FW
developed during pre- construction for construction.
Note:
CSP = Central Signal Processor
SDP = Science Data Processor
Could SKA's IT be a Black Swan?
• “Black Swan” = high-impact events that are rare and
unpredictable but in retrospect seem not so
improbable.
• One in six IT projects (is) a black swan, with a cost
overrun of 200%, on average (*).
• Developers struggle to combine different software
systems.
• 61% of managers report major conflicts between
project and line organisations.
• (*) “Why your IT Project may be riskier than you think”. B.
Flyvbjerg et al. HBR, Sept. 2011.
What is the SKA?
● The world's largest radio telescope
● The ultimate big data project
● The largest supercomputer in the world
● A technological management challenge
and...
● The general case of future HPC + Cloud...
Our world is full of data
● “Every year we collect more data than the
rest of the data collected since the
beginning of the Mankind”
(Prof. Alex Szalay, Johns Hopkins University. TEDx
Caltech 2011 – Keynote at Multicore World 2016).
● Exponentially faster computing + successive
generations of inexpensive sensors + you on
your smartphone sharing all those images.
● Data intensive science, synthesizing theory
(equations), experiments and computation with
analytics → new way of thinking is required!
“80 percent of success is showing up”
(Woody Allen)
SKA_in_Seoul_2015_NicolasErdody v2.0
SKA_in_Seoul_2015_NicolasErdody v2.0
SKA_in_Seoul_2015_NicolasErdody v2.0

More Related Content

What's hot

BioIT Trends - 2014 Internet2 Technology Exchange
BioIT Trends - 2014 Internet2 Technology ExchangeBioIT Trends - 2014 Internet2 Technology Exchange
BioIT Trends - 2014 Internet2 Technology Exchange
Chris Dagdigian
 
Optalysys Optical Processing for HPC
Optalysys Optical Processing for HPCOptalysys Optical Processing for HPC
Optalysys Optical Processing for HPC
inside-BigData.com
 
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
Tomasz Bednarz
 
Big Data Rampage
Big Data RampageBig Data Rampage
Big Data Rampage
Niko Vuokko
 
Bulding a modern infrastructure & data center
Bulding a modern infrastructure & data centerBulding a modern infrastructure & data center
Bulding a modern infrastructure & data center
Future Cloud Summit
 
HPC Market Update from IDC
HPC Market Update from IDCHPC Market Update from IDC
HPC Market Update from IDC
inside-BigData.com
 
NVIDIA Corporation Brochure: Who We Are
NVIDIA Corporation Brochure: Who We AreNVIDIA Corporation Brochure: Who We Are
NVIDIA Corporation Brochure: Who We Are
NVIDIA
 
2013: Trends from the Trenches
2013: Trends from the Trenches2013: Trends from the Trenches
2013: Trends from the Trenches
Chris Dagdigian
 
From Lab to Factory: Or how to turn data into value
From Lab to Factory: Or how to turn data into valueFrom Lab to Factory: Or how to turn data into value
From Lab to Factory: Or how to turn data into value
Peadar Coyle
 
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
Revolution Analytics
 
How Do I Understand Deep Learning Performance?
How Do I Understand Deep Learning Performance?How Do I Understand Deep Learning Performance?
How Do I Understand Deep Learning Performance?
NVIDIA
 
Dataiku - for Data Geek Paris@Criteo - Close the Data Circle
Dataiku  - for Data Geek Paris@Criteo - Close the Data CircleDataiku  - for Data Geek Paris@Criteo - Close the Data Circle
Dataiku - for Data Geek Paris@Criteo - Close the Data Circle
Dataiku
 
The 3 Key Barriers Keeping Companies from Deploying Data Products
The 3 Key Barriers Keeping Companies from Deploying Data Products The 3 Key Barriers Keeping Companies from Deploying Data Products
The 3 Key Barriers Keeping Companies from Deploying Data Products
Dataiku
 
NVIDIA 2017 Overview
NVIDIA 2017 OverviewNVIDIA 2017 Overview
NVIDIA 2017 Overview
NVIDIA
 
Vertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IVVertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Holdings
 
Applications of R (DataWeek 2014)
Applications of R (DataWeek 2014)Applications of R (DataWeek 2014)
Applications of R (DataWeek 2014)
Revolution Analytics
 
HPC Top 5 Stories: May 3, 2017
HPC Top 5 Stories: May 3, 2017HPC Top 5 Stories: May 3, 2017
HPC Top 5 Stories: May 3, 2017
NVIDIA
 
frog IoT Big Design IoT World Congress 2015
frog IoT Big Design IoT World Congress 2015frog IoT Big Design IoT World Congress 2015
frog IoT Big Design IoT World Congress 2015
Patrick Kalaher
 
2014 BioIT World - Trends from the trenches - Annual presentation
2014 BioIT World - Trends from the trenches - Annual presentation2014 BioIT World - Trends from the trenches - Annual presentation
2014 BioIT World - Trends from the trenches - Annual presentation
Chris Dagdigian
 
Data Science in the Enterprise
Data Science in the EnterpriseData Science in the Enterprise
Data Science in the Enterprise
The Hive
 

What's hot (20)

BioIT Trends - 2014 Internet2 Technology Exchange
BioIT Trends - 2014 Internet2 Technology ExchangeBioIT Trends - 2014 Internet2 Technology Exchange
BioIT Trends - 2014 Internet2 Technology Exchange
 
Optalysys Optical Processing for HPC
Optalysys Optical Processing for HPCOptalysys Optical Processing for HPC
Optalysys Optical Processing for HPC
 
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
Platform for Big Data Analytics and Visual Analytics: CSIRO use cases. Februa...
 
Big Data Rampage
Big Data RampageBig Data Rampage
Big Data Rampage
 
Bulding a modern infrastructure & data center
Bulding a modern infrastructure & data centerBulding a modern infrastructure & data center
Bulding a modern infrastructure & data center
 
HPC Market Update from IDC
HPC Market Update from IDCHPC Market Update from IDC
HPC Market Update from IDC
 
NVIDIA Corporation Brochure: Who We Are
NVIDIA Corporation Brochure: Who We AreNVIDIA Corporation Brochure: Who We Are
NVIDIA Corporation Brochure: Who We Are
 
2013: Trends from the Trenches
2013: Trends from the Trenches2013: Trends from the Trenches
2013: Trends from the Trenches
 
From Lab to Factory: Or how to turn data into value
From Lab to Factory: Or how to turn data into valueFrom Lab to Factory: Or how to turn data into value
From Lab to Factory: Or how to turn data into value
 
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
Order Fulfillment Forecasting at John Deere: How R Facilitates Creativity and...
 
How Do I Understand Deep Learning Performance?
How Do I Understand Deep Learning Performance?How Do I Understand Deep Learning Performance?
How Do I Understand Deep Learning Performance?
 
Dataiku - for Data Geek Paris@Criteo - Close the Data Circle
Dataiku  - for Data Geek Paris@Criteo - Close the Data CircleDataiku  - for Data Geek Paris@Criteo - Close the Data Circle
Dataiku - for Data Geek Paris@Criteo - Close the Data Circle
 
The 3 Key Barriers Keeping Companies from Deploying Data Products
The 3 Key Barriers Keeping Companies from Deploying Data Products The 3 Key Barriers Keeping Companies from Deploying Data Products
The 3 Key Barriers Keeping Companies from Deploying Data Products
 
NVIDIA 2017 Overview
NVIDIA 2017 OverviewNVIDIA 2017 Overview
NVIDIA 2017 Overview
 
Vertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IVVertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IV
 
Applications of R (DataWeek 2014)
Applications of R (DataWeek 2014)Applications of R (DataWeek 2014)
Applications of R (DataWeek 2014)
 
HPC Top 5 Stories: May 3, 2017
HPC Top 5 Stories: May 3, 2017HPC Top 5 Stories: May 3, 2017
HPC Top 5 Stories: May 3, 2017
 
frog IoT Big Design IoT World Congress 2015
frog IoT Big Design IoT World Congress 2015frog IoT Big Design IoT World Congress 2015
frog IoT Big Design IoT World Congress 2015
 
2014 BioIT World - Trends from the trenches - Annual presentation
2014 BioIT World - Trends from the trenches - Annual presentation2014 BioIT World - Trends from the trenches - Annual presentation
2014 BioIT World - Trends from the trenches - Annual presentation
 
Data Science in the Enterprise
Data Science in the EnterpriseData Science in the Enterprise
Data Science in the Enterprise
 

Viewers also liked

The Legends Foundation Outreach - Churches
The Legends Foundation Outreach - ChurchesThe Legends Foundation Outreach - Churches
The Legends Foundation Outreach - ChurchesJoseph Hoffman
 
A Unique and Life Changing Open Business Opportunity.
A Unique and Life Changing Open Business Opportunity.A Unique and Life Changing Open Business Opportunity.
A Unique and Life Changing Open Business Opportunity.
Vilas Gedam
 
From the South: building together a high-tech ecosystem
From the South: building together a high-tech ecosystemFrom the South: building together a high-tech ecosystem
From the South: building together a high-tech ecosystemNicolás Erdödy
 
Vrouwenportretten van Mirjam Voets, Artrijk
Vrouwenportretten van Mirjam Voets, ArtrijkVrouwenportretten van Mirjam Voets, Artrijk
Vrouwenportretten van Mirjam Voets, Artrijk
mirjam voets
 
НЕ НА ПУШЕНЕТО
НЕ НА ПУШЕНЕТО НЕ НА ПУШЕНЕТО
НЕ НА ПУШЕНЕТО
Gdarkness
 
Final RSMeans from TGG Cooley Waire presentation prep edits Autosaved
Final RSMeans from TGG Cooley  Waire presentation prep edits AutosavedFinal RSMeans from TGG Cooley  Waire presentation prep edits Autosaved
Final RSMeans from TGG Cooley Waire presentation prep edits AutosavedLisa Cooley, LEED AP
 
Coke defina dan nadia pis 13 02
Coke defina dan nadia pis 13 02Coke defina dan nadia pis 13 02
Coke defina dan nadia pis 13 02Defina Iskandar
 
Why most lucerative employee referral schemes fail?
Why most lucerative employee referral schemes fail?Why most lucerative employee referral schemes fail?
Why most lucerative employee referral schemes fail?
Roshan Kumar Sr Manager - Talent Acquisition
 
Mi1274 alpro lanjut 6 - perulangan - 2 - for, do-while
Mi1274 alpro lanjut   6 - perulangan - 2 - for, do-whileMi1274 alpro lanjut   6 - perulangan - 2 - for, do-while
Mi1274 alpro lanjut 6 - perulangan - 2 - for, do-whileDefina Iskandar
 
project-delivery-methods-final-for-presentation.pptx
project-delivery-methods-final-for-presentation.pptxproject-delivery-methods-final-for-presentation.pptx
project-delivery-methods-final-for-presentation.pptxLisa Cooley, LEED AP
 
Chabot is a not a product, it's a feature
Chabot is a not a product, it's a featureChabot is a not a product, it's a feature
Chabot is a not a product, it's a feature
Michael Vakulenko
 

Viewers also liked (14)

The Legends Foundation Outreach - Churches
The Legends Foundation Outreach - ChurchesThe Legends Foundation Outreach - Churches
The Legends Foundation Outreach - Churches
 
Sim airlines
Sim airlinesSim airlines
Sim airlines
 
A Unique and Life Changing Open Business Opportunity.
A Unique and Life Changing Open Business Opportunity.A Unique and Life Changing Open Business Opportunity.
A Unique and Life Changing Open Business Opportunity.
 
From the South: building together a high-tech ecosystem
From the South: building together a high-tech ecosystemFrom the South: building together a high-tech ecosystem
From the South: building together a high-tech ecosystem
 
Vrouwenportretten van Mirjam Voets, Artrijk
Vrouwenportretten van Mirjam Voets, ArtrijkVrouwenportretten van Mirjam Voets, Artrijk
Vrouwenportretten van Mirjam Voets, Artrijk
 
НЕ НА ПУШЕНЕТО
НЕ НА ПУШЕНЕТО НЕ НА ПУШЕНЕТО
НЕ НА ПУШЕНЕТО
 
2013 Federal D-B Downsized
2013 Federal D-B Downsized2013 Federal D-B Downsized
2013 Federal D-B Downsized
 
Final RSMeans from TGG Cooley Waire presentation prep edits Autosaved
Final RSMeans from TGG Cooley  Waire presentation prep edits AutosavedFinal RSMeans from TGG Cooley  Waire presentation prep edits Autosaved
Final RSMeans from TGG Cooley Waire presentation prep edits Autosaved
 
Coke defina dan nadia pis 13 02
Coke defina dan nadia pis 13 02Coke defina dan nadia pis 13 02
Coke defina dan nadia pis 13 02
 
Why most lucerative employee referral schemes fail?
Why most lucerative employee referral schemes fail?Why most lucerative employee referral schemes fail?
Why most lucerative employee referral schemes fail?
 
AGC Webinar
AGC WebinarAGC Webinar
AGC Webinar
 
Mi1274 alpro lanjut 6 - perulangan - 2 - for, do-while
Mi1274 alpro lanjut   6 - perulangan - 2 - for, do-whileMi1274 alpro lanjut   6 - perulangan - 2 - for, do-while
Mi1274 alpro lanjut 6 - perulangan - 2 - for, do-while
 
project-delivery-methods-final-for-presentation.pptx
project-delivery-methods-final-for-presentation.pptxproject-delivery-methods-final-for-presentation.pptx
project-delivery-methods-final-for-presentation.pptx
 
Chabot is a not a product, it's a feature
Chabot is a not a product, it's a featureChabot is a not a product, it's a feature
Chabot is a not a product, it's a feature
 

Similar to SKA_in_Seoul_2015_NicolasErdody v2.0

How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?
Amazon Web Services
 
The Environment for Innovation: Tristan Goode, Aptira
The Environment for Innovation: Tristan Goode, AptiraThe Environment for Innovation: Tristan Goode, Aptira
The Environment for Innovation: Tristan Goode, Aptira
OpenStack
 
OA centre of excellence
OA centre of excellenceOA centre of excellence
Machine Learning - Intro
Machine Learning - IntroMachine Learning - Intro
Machine Learning - Intro
Giorgio Alfredo Spedicato
 
Sourav_Giri_Resume_2015
Sourav_Giri_Resume_2015Sourav_Giri_Resume_2015
Sourav_Giri_Resume_2015sourav giri
 
OpenPOWER SC16 Recap: Day 2
OpenPOWER SC16 Recap: Day 2OpenPOWER SC16 Recap: Day 2
OpenPOWER SC16 Recap: Day 2
OpenPOWERorg
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
Wes McKinney
 
Future of hpc
Future of hpcFuture of hpc
Future of hpc
Putchong Uthayopas
 
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark StreamingTiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
Paco Nathan
 
At the Crossroads of HPC and Cloud Computing with Openstack
At the Crossroads of HPC and Cloud Computing with OpenstackAt the Crossroads of HPC and Cloud Computing with Openstack
At the Crossroads of HPC and Cloud Computing with Openstack
Ryan Aydelott
 
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
Daryna Dubitska
 
OpenStack - What is it and why you should know about it!
OpenStack - What is it and why you should know about it!OpenStack - What is it and why you should know about it!
OpenStack - What is it and why you should know about it!
OpenStack
 
Pioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSCPioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSC
inside-BigData.com
 
Nikravesh australia long_versionkeynote2012
Nikravesh australia long_versionkeynote2012Nikravesh australia long_versionkeynote2012
Nikravesh australia long_versionkeynote2012
Masoud Nikravesh
 
The Future is Big Graphs: A Community View on Graph Processing Systems
The Future is Big Graphs: A Community View on Graph Processing SystemsThe Future is Big Graphs: A Community View on Graph Processing Systems
The Future is Big Graphs: A Community View on Graph Processing Systems
Neo4j
 
Sc10 slide share
Sc10 slide shareSc10 slide share
Sc10 slide share
Guy Tel-Zur
 
DDDP 2019 - Brown to Green
DDDP 2019  - Brown to GreenDDDP 2019  - Brown to Green
DDDP 2019 - Brown to Green
John Archer
 
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
Nane Kratzke
 

Similar to SKA_in_Seoul_2015_NicolasErdody v2.0 (20)

How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?
 
The Environment for Innovation: Tristan Goode, Aptira
The Environment for Innovation: Tristan Goode, AptiraThe Environment for Innovation: Tristan Goode, Aptira
The Environment for Innovation: Tristan Goode, Aptira
 
OA centre of excellence
OA centre of excellenceOA centre of excellence
OA centre of excellence
 
Resume (1)
Resume (1)Resume (1)
Resume (1)
 
Resume (1)
Resume (1)Resume (1)
Resume (1)
 
Machine Learning - Intro
Machine Learning - IntroMachine Learning - Intro
Machine Learning - Intro
 
Sourav_Giri_Resume_2015
Sourav_Giri_Resume_2015Sourav_Giri_Resume_2015
Sourav_Giri_Resume_2015
 
OpenPOWER SC16 Recap: Day 2
OpenPOWER SC16 Recap: Day 2OpenPOWER SC16 Recap: Day 2
OpenPOWER SC16 Recap: Day 2
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
 
Future of hpc
Future of hpcFuture of hpc
Future of hpc
 
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark StreamingTiny Batches, in the wine: Shiny New Bits in Spark Streaming
Tiny Batches, in the wine: Shiny New Bits in Spark Streaming
 
At the Crossroads of HPC and Cloud Computing with Openstack
At the Crossroads of HPC and Cloud Computing with OpenstackAt the Crossroads of HPC and Cloud Computing with Openstack
At the Crossroads of HPC and Cloud Computing with Openstack
 
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
SoftElegance Services: Data Science, Data Engineering, Big Data Architecture
 
OpenStack - What is it and why you should know about it!
OpenStack - What is it and why you should know about it!OpenStack - What is it and why you should know about it!
OpenStack - What is it and why you should know about it!
 
Pioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSCPioneering and Democratizing Scalable HPC+AI at PSC
Pioneering and Democratizing Scalable HPC+AI at PSC
 
Nikravesh australia long_versionkeynote2012
Nikravesh australia long_versionkeynote2012Nikravesh australia long_versionkeynote2012
Nikravesh australia long_versionkeynote2012
 
The Future is Big Graphs: A Community View on Graph Processing Systems
The Future is Big Graphs: A Community View on Graph Processing SystemsThe Future is Big Graphs: A Community View on Graph Processing Systems
The Future is Big Graphs: A Community View on Graph Processing Systems
 
Sc10 slide share
Sc10 slide shareSc10 slide share
Sc10 slide share
 
DDDP 2019 - Brown to Green
DDDP 2019  - Brown to GreenDDDP 2019  - Brown to Green
DDDP 2019 - Brown to Green
 
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
We have the Bricks to Build Cloud-native Cathedrals - But do we have the mortar?
 

SKA_in_Seoul_2015_NicolasErdody v2.0

  • 1. An Open Software Platform for the SKA? Nicolás Erdödy Founder, CEO – Open Parallel Ltd SKA in Seoul: Asia-Pacific Regional Workshop in HI Science Seoul, Korea - November 2, 2015
  • 2.
  • 3. Brief ● The Problem: “data deluge” ● The Opportunity: We see the SKA SDP compute model as the general case ● TOPS - A Distributed OS for Rack Scale Computing. ● How to start: Open Source & Open Stack ● We need your help...
  • 4. Efficient recognition of signals from a massive amount of data noise improves operational efficiencies, scientific discovery and forms the cradle of adaptive service delivery.
  • 5. As today's HPC becomes tomorrow's Cloud computing platform it will enable a wider application of Machine Understanding -the near real-time complex modelling and analysis of data that leads to insight and faster decisions.
  • 6.
  • 7. Today's problems and beyond ● Non-professional software development (in many scientific environments) lead to limited or null software stack reuse. ● Data deluge (44 ZettaBytes by 2020 – IDC). ● The exascale challenge: 10^18 calculations p/s ● Power consumption. ● Heterogeneous hardware. ● Compute Islands? ● Software Defined Everything (SDN, SDI, SDS).
  • 8. SDP Preliminary Compute Platform Design (*) ● Quite different than on a general-purpose supercomputer ● Workload-driven system design philosophy to tune SDP hardware. ● SDP Compute Islands - “self-contained, independent collection of compute nodes”. ● Only process data contained in the island itself. ● (*) Broekema, van Nieuwpoort, Bal (July 2015)
  • 9. TOPS – What are we doing ● Conceived as a Rack Scale distributed Operating System for the Data Centre. ● TOPS workshop #2 (Multicore World 2016, Wellington, NZ) ● CSP's Software Development Plan. ● Panel “Towards an Open Software Stack for Exascale Computing” at SuperComputing15 – Austin, Texas, USA (15-20 Nov). ● OpenStack - South Africa - 2015 CHPC conference, Pretoria (1-4 Dec)
  • 10. “Towards an Open Software Stack for Exascale Computing” (SC15 – 19Nov – Austin, USA ). ● Prof. Jack Dongarra (Tennessee, Turing Fellow – Manchester, scientific advisory board for SKA, LINPACK). ● Prof. Thomas Sterling (Indiana, Centre for Research Extreme Scale Technologies, Beowulf clusters, MCW15). ● Dr. Pete Beckman (Exascale Technology & Computing Institute, Argonne Labs – Chicago, Argo OS). ● Dr. John Gustafson (fmr AMD Chief Product Architect, Director Intel Labs, Sun, Gustafson's Law, MCW14). ● Dr. Robert Wisniewski (Chief Software Architect Exascale Computing, Intel -formerly Chief Software Architect Blue Gene Supercomputer, IBM). ● Chris Broekema (SDP COMP Task Leader, ASTRON, Netherlands).
  • 11. Your input ● What should TOPS be / do for you? ● Let's start a chat -this is a 2-5 years conversation. ● Thank you! ● OpenParallel.com ● MulticoreWorld.com ● Nicolas.Erdody@openparallel.com ● Oamaru, South Island, New Zealand
  • 12. The data deluge will change how we build and manage new systems to store and understand data
  • 13. “This time, we have time” a) How should software evolve to address exascale demands? Are OpenStack or other platforms part of the solution? Algorithms should evolve, and most legacy software will be replaced: so what should be the focus of the new ones? To save power? To increase speed? To improve programmability? b) How heterogeneous would/should “your” exascale system be? Is there a role for Co-design towards exascale? c) The SKA project is an example where once it becomes operational, exascale problems will appear very early. But venture capitalists don't invest in radio- telescopes. What killer app would attract them towards early adoption of exascale computing? Which industries will migrate first? d) Would HPC in the cloud be possible for exascale computing? Which technologies do we need to change / challenge to make it feasible? Data transport? Servers? What are those technologies most important for your work? e) Do you envisage a similar development effort as we had with OSS over decades, or will bottlenecks develop due to lack of specialised talent globally? Will proprietary solutions continue to emerge or co-exist? Who will “own” the exascale era? Microsoft? Google? Will there be competition between existing companies and “not yet founded” start-ups, or will each organisation have its own in-house development shop?
  • 14. Open Parallel Ltd. ● NZ Company – involved with SKA since 2011. ● 3 NZ organisations (AUT, VUW & OP) were formally pre-selected in 2012 by the NZ Govt -after international peer-review, as viable prospects for engagement in SDP and CSP. ● Since 2013 Open Parallel is formally: - Work Package Manager of the Software Development Environment for the CSP, - Contributing to SDP Compute Platform, - Member of the NZ SKA Alliance (lead by AUT university).
  • 15. OP's work for the SKA What's done (2013 - 2015) Version 1 of “SKA CSP Element Software Development Plan” (SE-23). How the CSP element “will develop and deliver software and/or firmware in accordance to a design specification.” Incorporated into SDP’s Architecture Reference Document (2014) and referenced in SDP’s “Compute Platform: Software stack developments and considerations” (SDP’s PDR 2015). To be fully delivered over Stage 2 timeframe (2015 - 2017). Most recent task: provide CSP Consortium with SW/FW process requirements to support the effective re-use of SW and FW developed during pre- construction for construction. Note: CSP = Central Signal Processor SDP = Science Data Processor
  • 16. Could SKA's IT be a Black Swan? • “Black Swan” = high-impact events that are rare and unpredictable but in retrospect seem not so improbable. • One in six IT projects (is) a black swan, with a cost overrun of 200%, on average (*). • Developers struggle to combine different software systems. • 61% of managers report major conflicts between project and line organisations. • (*) “Why your IT Project may be riskier than you think”. B. Flyvbjerg et al. HBR, Sept. 2011.
  • 17. What is the SKA? ● The world's largest radio telescope ● The ultimate big data project ● The largest supercomputer in the world ● A technological management challenge and... ● The general case of future HPC + Cloud...
  • 18. Our world is full of data ● “Every year we collect more data than the rest of the data collected since the beginning of the Mankind” (Prof. Alex Szalay, Johns Hopkins University. TEDx Caltech 2011 – Keynote at Multicore World 2016). ● Exponentially faster computing + successive generations of inexpensive sensors + you on your smartphone sharing all those images. ● Data intensive science, synthesizing theory (equations), experiments and computation with analytics → new way of thinking is required!
  • 19. “80 percent of success is showing up” (Woody Allen)