Upload
ibminterconnect
View
52
Download
0
Tags:
Embed Size (px)
Citation preview
David MossAdvanced Technologies
Solutions Manager
The Democratisation of Advanced Technologies
@DaveMossTechBod
Agenda
• Introduction to STFC
• Government investment and associated challenges
• “Democratisation” and reducing complexity
• A UK Research Council which funds, designs, builds and operates world-class science infrastructure.
• Offers industry, government, and academia:
• unique scientific insight
• innovative technology
Particle Accelerators / Particle PhysicsAstronomy / Radio Telescopes
LasersSpace Science
Electron MicroscopyHigh Performance Computing
High Performance Computing and Big Data has been a feature of STFC since 1967.
IBM 360/165.This had a stunning 12.5 MHz cpu and 3 MB of main memory.
Today, Blue Joule is:• The UK’s first Petaflop system• Is capable of over a thousand trillion calculations per second.
• Hartree Cloud services – access to previously inaccessible capabilities via the Cloud.
Why is HPC important?
“It costs £500,000 to do a physical test of a car crash and it’s not repeatable. It costs £12 to run a virtual simulation of a car crash, and it’s fully repeatable”
Andy Searle, Head of Computer Aided Engineering, Jaguar Land Rover.
"Today the computer is just as important a tool for chemists as the test tube”.
The Royal Swedish Academy of Sciences
Government Investment in UK e-infrastructure
Government Investment
• 2011 Tildesley Report – e-Infrastructure Leadership Council
• £160m investment from BIS across the UK.
Government Challenges
• “Democratisation” of HPC
• Wider use throughout industry
4 Key Drivers
IndustrialEngagement
• Funding models demanding economic impact
• Using existing computational modelling in industrial workflows
• Better outcomes, developed faster and cheaper
• New engagement models, delivery disciplines, cadence & language
DemocratisationPower
• Unprecedented scaling of systems needed
• Availability and Affordability
• Existing architectures are not sustainable
• Moore’s Law ending
• Emerging platforms and new Architectures
• New languages, compilers, middleware and applications
• Cloud
Big Data
• Everything will change• 3 V’s• Internet of Things• Security
standards• Todays architectures
will be obsolete in 5 years
• Emerging platforms and new Architectures
• New algorithms, languages, compilers, middleware and applications
• Open data is great – but useless on its own
• Analytics is the key to
• Availability of skills will remain a bottleneck
• Science and Knowledge workers
• Build the Data Scientist in to the Machine / Software
• New ways of interaction• Speech• Visualisation• Mobile
• Emerging platforms and new Architectures
• New algorithms, languages, compilers, middleware and applications
IndustrialEngagement
• Funding models demanding economic impact
• Using existing computational modelling in industrial workflows
• Better outcomes, developed faster and cheaper
• New engagement models, delivery disciplines, cadence & language
The Hartree Centre’s visualisation facilities enable us to look examine and analyse huge amounts of data which would not be possible using conventional methods.
This is a subset of the data represented on the previous slide. This is a simpler network diagram and again allows us to examine the data in more detail, with ability to manipulate the data and examine it in 3D.
Democratisation
• Availability of skills will remain a bottleneck
• Science and Knowledge workers
• Build the Data Scientist in to the Machine / Software
• New ways of interaction• Speech• Visualisation• Mobile
• Emerging platforms and new Architectures
• New algorithms, languages, compilers, middleware and applications
Unilever
• Unilever Sustainable Living Plan– Business growth and bold environmental
challenges.• Product Design
– Personal Care complexity and timeframes.
The Traditional Method
Lessons Learnt
• Democratisation is ALWAYS about the END USER
• Cultural Change is required• Get it right and be rewarded for it!• These technologies are coming your way!
Consumable HPC 04/15/2023
…and how to make HPC easier to use Scenario: Chemists consult – change experimental design, run multiple simulations from mobile device in the lab to see what best choices of chemicals.
Parameters changed at bench on mobile device and results sent back to mobile device.
Multiple InputsResults
Overview of Running Jobs
Input data