SlideShare une entreprise Scribd logo
1  sur  21
Télécharger pour lire hors ligne
Εuropean Exascale
System Ιnterconnect & Storage
Peter Hopton (peter.hopton@iceotope.com)
Iceotope, UK
The Foundations For ExaScale
www.exanest.eu
Project Group Landscape
• “EuroExa” Group Of Projects
• Historic Input Effort (from 2010)
– EuroServer, Mont Blanc, Encore
• Currently Running Projects (2014-2018)
– ExaNeSt
– EcoScale
– ExaNode
• Follow Through Project (2017-2020)
– To Be Announced... ;-)
2
What ExaNeSt is about
• ARMv8, UNIMEM Partitioned Global Address Space (PGAS)
– low energy compute
– low overhead communicate
– FPGA-assisted acceleration
– working closely with Other Projects…
• Network: unified compute & storage, low latency
• Storage: distributed, in-node non-volatile memories
• Real Applications: Scientific, Engineering, Data Analytics
• Data Centre Infrastructure (Power and Cooling): Total
Liquid Cooling
• Prototype: 1K cores, 16GBytes DDR4 per FPGA
3HPC User Forum 1st March 2017, Stuttgart
The ExaNeSt Consortium
4
Storage&data
UK
Italy
Greece - coordinator
UK
UKUPV - ES
Technology
Interconnects
Netherlands
France
Germany
Applications
Italy
Italy Italy
www.exanest.eu
HPC User Forum 1st March 2017, Stuttgart
Network
5
Interconnection Network
• Now: Simulations, Studies:
– at the Packet/flit level, for protocol behavior and interactions (using
INSEE and Omnet+);
– Traffic Inputs: Synthetic models, real App Traces, or running App’s.
• Later: Experiments on real Prototype running real App’s
• Packaging & interconnect considered in tandem
– Hierarchical interconnect
• Design Goals:
– unified network for compute & storage
– flow prioritization: heavy / storage versus short / sync (compute)
– throttle congestive flows at network edges
– resiliency: error detect/correct, monitor links, multipath routing
– Zero-copy, user-level RDMA
– Global address space
– all-optical proof-of-concept TOR switch using 2×2/4×4 building blocks
6HPC User Forum 1st March 2017, Stuttgart
Storage
7
Storage: current Design work
Global Storage Layer +
+ per-job SSD/NVM on-demand Parallel Cache Layer
• Based on the BeeGFS parallel filesystem (open source),
with caching and replication extensions
• Low-latency memory-mapped storage access path in Linux
• Virtualization: RDMA from within VM’s; MPI remoting
• Acceleration for Host-to-VM and VM-to-VM interactions
8HPC User Forum 1st March 2017, Stuttgart
Applications
9
Applications, Traces
10
Main Applications:
• Material science: LAMMPS
• Climate change: REGCM
• Engineering CFD: openFoam, SailFish
• Astrophysics:
• Large-scale high-resolution simulations of cosmic formation
and evolution
• Gadget, Pinocchio, Changa, Swift
• Neuroscience – brain simulation: DPSNN
• High Energy Physics
• Lattice Quantum Chromodynamics simulations - LQCD
• Data Analytics: MonetDB
• Porting selected App’s to ARM
HPC User Forum 1st March 2017, Stuttgart
Infrastructure
11
Power
• 48V DC to POL Converter on Daughter Board
• 3 Phase 415V to 48V DC Liquid Cooled Power Conversion
• 48V DC Power Distribution
• Ambition to integrate renewable energy on-site
generation and energy storage at DC to remove
conversion cycles and give “green power” (Separate
Project)
12
AC
DC
48V
UPS AC
DC
12V
DC
PoL
AC DC 48V DC PoL
Old
New
Cooling
Combination of 3 Different Patented Cooling Technologies
• Immersion
– Natural Convection “Cells”
– Forced Convection “Fountains”
• Conduction
• Total Liquid Cooling
• Zero Airflow
• Potential for High Temperatures and Heat Capture
13
Prototypes
14
Our Nodes
15HPC User Forum 1st March 2017, Stuttgart
Thermal Proxies
16
Thermal Proxies
17
The 1st Major ExaNeSt Prototype (2017)
• Using Xilinx Zynq UltraScale+
FPGAs:
– Quad-core 64-bit ARM A53 per FPGA
– Cache-coherent low-latency I/O port
• On 120×130 mm2 Daughter Boards
– 4 FPGA’s
– 1 TB SSD
– 10× 16Gb/s I/O’s
• 1st Prototype
– Up to 8 DB’s per Blade, 9 Blades
• In Early Test Now
– First deployment = within 2017
18
Electronics
immersed in
PFPE liquids
Rack-level
water
circulation
HPC User Forum 1st March 2017, Stuttgart
The 2nd Major ExaNeSt Prototype (2018)
• Same FPGAs, Same Quad FPGA Daughter Board
• 16 DB’s, 1 Blade, 3.2kW in 1u, Small Footprint Cabs
• Our Ambition
– Hot Water Cooling (>50C), Heat Capture Functions
– 100kW cabinets, 1.0x PUE, >0.9 ERF Potential
– DC Power Distribution
– Potential for High Density Data Centres or Modular Facilities:
HPC User Forum 1st March 2017, Stuttgart 19
Aisle
Aisle
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
Aisle
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
Coolant and DC Power
Aisle
Aisle
600x600mm
cabinetwith6
chassis&2xCDUs
Aisle
2.5m
ICEOTOPE
CONFIDENTIAL
Batteries and Rectifiers for 250kW
of Load
Batteries and Rectifiers for 250kW
of Load
Coolant and DC Power600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
600x600mm
cabinetwith6
chassis&2xCDUs
Coolant and DC Power
Batteries and Rectifiers for 250kW
of Load
Batteries and Rectifiers for 250kW
of Load
Coolant and DC Power
10.6m
Wall
Wall
1MW DC
In 40ft ISO or
10mx2.4m
What ExaneSt offers to the Ecosystem
• Use of the Prototypes by ExaNoDe and EcoScale
• Use of the Prototype by the Ecosystem (2018 onwards)
• HPC technology components (2018 onwards):
– ARM/Unimem
– Fine-tuned Applications
– The Ultra-Dense Data Centre for Scaling HPC
– Packaging & Cooling
– Distributed NVM / Storage
– Interconnects
– DB compute-node prototype
20HPC User Forum 1st March 2017, Stuttgart
European Exascale
System Interconnect & Storage
• Interconnection Network
• In-node Storage
• Data Centre Infrastructure
• Advanced Cooling & Power
• Real Applications
www.exanest.eu Project Coordinator:
Prof. Manolis Katevenis (kateveni@ics.forth.gr)
HPC User Forum 1st March 2017, Stuttgart

Contenu connexe

Tendances

20181219 ucc open stack 5 years v3
20181219 ucc open stack 5 years v320181219 ucc open stack 5 years v3
20181219 ucc open stack 5 years v3Tim Bell
 
Introduction to High-Performance Computing (HPC) Containers and Singularity*
Introduction to High-Performance Computing (HPC) Containers and Singularity*Introduction to High-Performance Computing (HPC) Containers and Singularity*
Introduction to High-Performance Computing (HPC) Containers and Singularity*Intel® Software
 
Food Security Use Case - ExtremeEarth Open Workshop
Food Security Use Case - ExtremeEarth Open WorkshopFood Security Use Case - ExtremeEarth Open Workshop
Food Security Use Case - ExtremeEarth Open WorkshopExtremeEarth
 
Low Energy Task Scheduling based on Work Stealing
Low Energy Task Scheduling based on Work StealingLow Energy Task Scheduling based on Work Stealing
Low Energy Task Scheduling based on Work StealingLEGATO project
 
The OptIPuter as a Prototype for CalREN-XD
The OptIPuter as a Prototype for CalREN-XDThe OptIPuter as a Prototype for CalREN-XD
The OptIPuter as a Prototype for CalREN-XDLarry Smarr
 
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...Arghya Kusum Das
 
Device Data Directory and Asynchronous execution: A path to heterogeneous com...
Device Data Directory and Asynchronous execution: A path to heterogeneous com...Device Data Directory and Asynchronous execution: A path to heterogeneous com...
Device Data Directory and Asynchronous execution: A path to heterogeneous com...LEGATO project
 
Technological forecasting of supercomputer development: The march to exascale...
Technological forecasting of supercomputer development: The march to exascale...Technological forecasting of supercomputer development: The march to exascale...
Technological forecasting of supercomputer development: The march to exascale...dongjoon
 
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...IOSR Journals
 
Energy-aware VM Allocation on An Opportunistic Cloud Infrastructure
Energy-aware VM Allocation on An Opportunistic Cloud InfrastructureEnergy-aware VM Allocation on An Opportunistic Cloud Infrastructure
Energy-aware VM Allocation on An Opportunistic Cloud InfrastructureMario Jose Villamizar Cano
 
Modern Computing: Cloud, Distributed, & High Performance
Modern Computing: Cloud, Distributed, & High PerformanceModern Computing: Cloud, Distributed, & High Performance
Modern Computing: Cloud, Distributed, & High Performanceinside-BigData.com
 
High Performance Computing - The Future is Here
High Performance Computing - The Future is HereHigh Performance Computing - The Future is Here
High Performance Computing - The Future is HereMartin Hamilton
 
Moldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesMoldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesLEGATO project
 
High performance computing
High performance computingHigh performance computing
High performance computingMaher Alshammari
 
LCG project description
LCG project descriptionLCG project description
LCG project descriptionlouisponcet
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facilityinside-BigData.com
 
Introduction to HPC
Introduction to HPCIntroduction to HPC
Introduction to HPCChris Dwan
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecastsinside-BigData.com
 
High Performance Computing in the Cloud?
High Performance Computing in the Cloud?High Performance Computing in the Cloud?
High Performance Computing in the Cloud?Ian Lumb
 

Tendances (20)

20181219 ucc open stack 5 years v3
20181219 ucc open stack 5 years v320181219 ucc open stack 5 years v3
20181219 ucc open stack 5 years v3
 
Introduction to High-Performance Computing (HPC) Containers and Singularity*
Introduction to High-Performance Computing (HPC) Containers and Singularity*Introduction to High-Performance Computing (HPC) Containers and Singularity*
Introduction to High-Performance Computing (HPC) Containers and Singularity*
 
Food Security Use Case - ExtremeEarth Open Workshop
Food Security Use Case - ExtremeEarth Open WorkshopFood Security Use Case - ExtremeEarth Open Workshop
Food Security Use Case - ExtremeEarth Open Workshop
 
Low Energy Task Scheduling based on Work Stealing
Low Energy Task Scheduling based on Work StealingLow Energy Task Scheduling based on Work Stealing
Low Energy Task Scheduling based on Work Stealing
 
The OptIPuter as a Prototype for CalREN-XD
The OptIPuter as a Prototype for CalREN-XDThe OptIPuter as a Prototype for CalREN-XD
The OptIPuter as a Prototype for CalREN-XD
 
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...
Augmenting Amdahl's Second Law for Cost-Effective and Balanced HPC Infrastruc...
 
Device Data Directory and Asynchronous execution: A path to heterogeneous com...
Device Data Directory and Asynchronous execution: A path to heterogeneous com...Device Data Directory and Asynchronous execution: A path to heterogeneous com...
Device Data Directory and Asynchronous execution: A path to heterogeneous com...
 
High–Performance Computing
High–Performance ComputingHigh–Performance Computing
High–Performance Computing
 
Technological forecasting of supercomputer development: The march to exascale...
Technological forecasting of supercomputer development: The march to exascale...Technological forecasting of supercomputer development: The march to exascale...
Technological forecasting of supercomputer development: The march to exascale...
 
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
 
Energy-aware VM Allocation on An Opportunistic Cloud Infrastructure
Energy-aware VM Allocation on An Opportunistic Cloud InfrastructureEnergy-aware VM Allocation on An Opportunistic Cloud Infrastructure
Energy-aware VM Allocation on An Opportunistic Cloud Infrastructure
 
Modern Computing: Cloud, Distributed, & High Performance
Modern Computing: Cloud, Distributed, & High PerformanceModern Computing: Cloud, Distributed, & High Performance
Modern Computing: Cloud, Distributed, & High Performance
 
High Performance Computing - The Future is Here
High Performance Computing - The Future is HereHigh Performance Computing - The Future is Here
High Performance Computing - The Future is Here
 
Moldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devicesMoldable pipelines for CNNs on heterogeneous edge devices
Moldable pipelines for CNNs on heterogeneous edge devices
 
High performance computing
High performance computingHigh performance computing
High performance computing
 
LCG project description
LCG project descriptionLCG project description
LCG project description
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
 
Introduction to HPC
Introduction to HPCIntroduction to HPC
Introduction to HPC
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecasts
 
High Performance Computing in the Cloud?
High Performance Computing in the Cloud?High Performance Computing in the Cloud?
High Performance Computing in the Cloud?
 

Similaire à European Exascale System Interconnect & Storage

ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big Data
ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big DataABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big Data
ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big DataHitoshi Sato
 
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...Databricks
 
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...inside-BigData.com
 
Designing HPC & Deep Learning Middleware for Exascale Systems
Designing HPC & Deep Learning Middleware for Exascale SystemsDesigning HPC & Deep Learning Middleware for Exascale Systems
Designing HPC & Deep Learning Middleware for Exascale Systemsinside-BigData.com
 
How HPC and large-scale data analytics are transforming experimental science
How HPC and large-scale data analytics are transforming experimental scienceHow HPC and large-scale data analytics are transforming experimental science
How HPC and large-scale data analytics are transforming experimental scienceinside-BigData.com
 
XSEDE April 2017
XSEDE April 2017XSEDE April 2017
XSEDE April 2017SciCompIIT
 
OpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsOpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsHPCC Systems
 
Expectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software researchExpectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software researchRyousei Takano
 
Preparing OpenSHMEM for Exascale
Preparing OpenSHMEM for ExascalePreparing OpenSHMEM for Exascale
Preparing OpenSHMEM for Exascaleinside-BigData.com
 
TeraGrid and Physics Research
TeraGrid and Physics ResearchTeraGrid and Physics Research
TeraGrid and Physics Researchshandra_psc
 
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...BigDataEverywhere
 
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...IBM Research
 
Programming Trends in High Performance Computing
Programming Trends in High Performance ComputingProgramming Trends in High Performance Computing
Programming Trends in High Performance ComputingJuris Vencels
 
Exploring emerging technologies in the HPC co-design space
Exploring emerging technologies in the HPC co-design spaceExploring emerging technologies in the HPC co-design space
Exploring emerging technologies in the HPC co-design spacejsvetter
 

Similaire à European Exascale System Interconnect & Storage (20)

ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big Data
ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big DataABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big Data
ABCI: AI Bridging Cloud Infrastructure for Scalable AI/Big Data
 
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...
Experience of Running Spark on Kubernetes on OpenStack for High Energy Physic...
 
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...
Evolving Cyberinfrastructure, Democratizing Data, and Scaling AI to Catalyze ...
 
Japan's post K Computer
Japan's post K ComputerJapan's post K Computer
Japan's post K Computer
 
NSCC Training Introductory Class
NSCC Training Introductory Class NSCC Training Introductory Class
NSCC Training Introductory Class
 
Designing HPC & Deep Learning Middleware for Exascale Systems
Designing HPC & Deep Learning Middleware for Exascale SystemsDesigning HPC & Deep Learning Middleware for Exascale Systems
Designing HPC & Deep Learning Middleware for Exascale Systems
 
How HPC and large-scale data analytics are transforming experimental science
How HPC and large-scale data analytics are transforming experimental scienceHow HPC and large-scale data analytics are transforming experimental science
How HPC and large-scale data analytics are transforming experimental science
 
XSEDE April 2017
XSEDE April 2017XSEDE April 2017
XSEDE April 2017
 
OpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsOpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC Systems
 
NSCC Training - Introductory Class
NSCC Training - Introductory ClassNSCC Training - Introductory Class
NSCC Training - Introductory Class
 
Expectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software researchExpectations for optical network from the viewpoint of system software research
Expectations for optical network from the viewpoint of system software research
 
Exascale Capabl
Exascale CapablExascale Capabl
Exascale Capabl
 
Preparing OpenSHMEM for Exascale
Preparing OpenSHMEM for ExascalePreparing OpenSHMEM for Exascale
Preparing OpenSHMEM for Exascale
 
TeraGrid and Physics Research
TeraGrid and Physics ResearchTeraGrid and Physics Research
TeraGrid and Physics Research
 
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...
Big Data Everywhere Chicago: High Performance Computing - Contributions Towar...
 
K computer
K computerK computer
K computer
 
Available HPC Resources at CSUC
Available HPC Resources at CSUCAvailable HPC Resources at CSUC
Available HPC Resources at CSUC
 
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...
IBM and ASTRON 64-Bit Microserver Prototype Prepares for Big Bang's Big Data,...
 
Programming Trends in High Performance Computing
Programming Trends in High Performance ComputingProgramming Trends in High Performance Computing
Programming Trends in High Performance Computing
 
Exploring emerging technologies in the HPC co-design space
Exploring emerging technologies in the HPC co-design spaceExploring emerging technologies in the HPC co-design space
Exploring emerging technologies in the HPC co-design space
 

Plus de inside-BigData.com

Preparing to program Aurora at Exascale - Early experiences and future direct...
Preparing to program Aurora at Exascale - Early experiences and future direct...Preparing to program Aurora at Exascale - Early experiences and future direct...
Preparing to program Aurora at Exascale - Early experiences and future direct...inside-BigData.com
 
Transforming Private 5G Networks
Transforming Private 5G NetworksTransforming Private 5G Networks
Transforming Private 5G Networksinside-BigData.com
 
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...inside-BigData.com
 
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...inside-BigData.com
 
HPC Impact: EDA Telemetry Neural Networks
HPC Impact: EDA Telemetry Neural NetworksHPC Impact: EDA Telemetry Neural Networks
HPC Impact: EDA Telemetry Neural Networksinside-BigData.com
 
Biohybrid Robotic Jellyfish for Future Applications in Ocean Monitoring
Biohybrid Robotic Jellyfish for Future Applications in Ocean MonitoringBiohybrid Robotic Jellyfish for Future Applications in Ocean Monitoring
Biohybrid Robotic Jellyfish for Future Applications in Ocean Monitoringinside-BigData.com
 
HPC AI Advisory Council Update
HPC AI Advisory Council UpdateHPC AI Advisory Council Update
HPC AI Advisory Council Updateinside-BigData.com
 
Fugaku Supercomputer joins fight against COVID-19
Fugaku Supercomputer joins fight against COVID-19Fugaku Supercomputer joins fight against COVID-19
Fugaku Supercomputer joins fight against COVID-19inside-BigData.com
 
Energy Efficient Computing using Dynamic Tuning
Energy Efficient Computing using Dynamic TuningEnergy Efficient Computing using Dynamic Tuning
Energy Efficient Computing using Dynamic Tuninginside-BigData.com
 
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPOD
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPODHPC at Scale Enabled by DDN A3i and NVIDIA SuperPOD
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPODinside-BigData.com
 
Versal Premium ACAP for Network and Cloud Acceleration
Versal Premium ACAP for Network and Cloud AccelerationVersal Premium ACAP for Network and Cloud Acceleration
Versal Premium ACAP for Network and Cloud Accelerationinside-BigData.com
 
Zettar: Moving Massive Amounts of Data across Any Distance Efficiently
Zettar: Moving Massive Amounts of Data across Any Distance EfficientlyZettar: Moving Massive Amounts of Data across Any Distance Efficiently
Zettar: Moving Massive Amounts of Data across Any Distance Efficientlyinside-BigData.com
 
Scaling TCO in a Post Moore's Era
Scaling TCO in a Post Moore's EraScaling TCO in a Post Moore's Era
Scaling TCO in a Post Moore's Erainside-BigData.com
 
CUDA-Python and RAPIDS for blazing fast scientific computing
CUDA-Python and RAPIDS for blazing fast scientific computingCUDA-Python and RAPIDS for blazing fast scientific computing
CUDA-Python and RAPIDS for blazing fast scientific computinginside-BigData.com
 
Introducing HPC with a Raspberry Pi Cluster
Introducing HPC with a Raspberry Pi ClusterIntroducing HPC with a Raspberry Pi Cluster
Introducing HPC with a Raspberry Pi Clusterinside-BigData.com
 
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...inside-BigData.com
 

Plus de inside-BigData.com (20)

Major Market Shifts in IT
Major Market Shifts in ITMajor Market Shifts in IT
Major Market Shifts in IT
 
Preparing to program Aurora at Exascale - Early experiences and future direct...
Preparing to program Aurora at Exascale - Early experiences and future direct...Preparing to program Aurora at Exascale - Early experiences and future direct...
Preparing to program Aurora at Exascale - Early experiences and future direct...
 
Transforming Private 5G Networks
Transforming Private 5G NetworksTransforming Private 5G Networks
Transforming Private 5G Networks
 
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
 
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...
How to Achieve High-Performance, Scalable and Distributed DNN Training on Mod...
 
HPC Impact: EDA Telemetry Neural Networks
HPC Impact: EDA Telemetry Neural NetworksHPC Impact: EDA Telemetry Neural Networks
HPC Impact: EDA Telemetry Neural Networks
 
Biohybrid Robotic Jellyfish for Future Applications in Ocean Monitoring
Biohybrid Robotic Jellyfish for Future Applications in Ocean MonitoringBiohybrid Robotic Jellyfish for Future Applications in Ocean Monitoring
Biohybrid Robotic Jellyfish for Future Applications in Ocean Monitoring
 
HPC AI Advisory Council Update
HPC AI Advisory Council UpdateHPC AI Advisory Council Update
HPC AI Advisory Council Update
 
Fugaku Supercomputer joins fight against COVID-19
Fugaku Supercomputer joins fight against COVID-19Fugaku Supercomputer joins fight against COVID-19
Fugaku Supercomputer joins fight against COVID-19
 
Energy Efficient Computing using Dynamic Tuning
Energy Efficient Computing using Dynamic TuningEnergy Efficient Computing using Dynamic Tuning
Energy Efficient Computing using Dynamic Tuning
 
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPOD
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPODHPC at Scale Enabled by DDN A3i and NVIDIA SuperPOD
HPC at Scale Enabled by DDN A3i and NVIDIA SuperPOD
 
State of ARM-based HPC
State of ARM-based HPCState of ARM-based HPC
State of ARM-based HPC
 
Versal Premium ACAP for Network and Cloud Acceleration
Versal Premium ACAP for Network and Cloud AccelerationVersal Premium ACAP for Network and Cloud Acceleration
Versal Premium ACAP for Network and Cloud Acceleration
 
Zettar: Moving Massive Amounts of Data across Any Distance Efficiently
Zettar: Moving Massive Amounts of Data across Any Distance EfficientlyZettar: Moving Massive Amounts of Data across Any Distance Efficiently
Zettar: Moving Massive Amounts of Data across Any Distance Efficiently
 
Scaling TCO in a Post Moore's Era
Scaling TCO in a Post Moore's EraScaling TCO in a Post Moore's Era
Scaling TCO in a Post Moore's Era
 
CUDA-Python and RAPIDS for blazing fast scientific computing
CUDA-Python and RAPIDS for blazing fast scientific computingCUDA-Python and RAPIDS for blazing fast scientific computing
CUDA-Python and RAPIDS for blazing fast scientific computing
 
Introducing HPC with a Raspberry Pi Cluster
Introducing HPC with a Raspberry Pi ClusterIntroducing HPC with a Raspberry Pi Cluster
Introducing HPC with a Raspberry Pi Cluster
 
Overview of HPC Interconnects
Overview of HPC InterconnectsOverview of HPC Interconnects
Overview of HPC Interconnects
 
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...
Efficient Model Selection for Deep Neural Networks on Massively Parallel Proc...
 
Data Parallel Deep Learning
Data Parallel Deep LearningData Parallel Deep Learning
Data Parallel Deep Learning
 

Dernier

Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024The Digital Insurer
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Principled Technologies
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 

Dernier (20)

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 

European Exascale System Interconnect & Storage

  • 1. Εuropean Exascale System Ιnterconnect & Storage Peter Hopton (peter.hopton@iceotope.com) Iceotope, UK The Foundations For ExaScale www.exanest.eu
  • 2. Project Group Landscape • “EuroExa” Group Of Projects • Historic Input Effort (from 2010) – EuroServer, Mont Blanc, Encore • Currently Running Projects (2014-2018) – ExaNeSt – EcoScale – ExaNode • Follow Through Project (2017-2020) – To Be Announced... ;-) 2
  • 3. What ExaNeSt is about • ARMv8, UNIMEM Partitioned Global Address Space (PGAS) – low energy compute – low overhead communicate – FPGA-assisted acceleration – working closely with Other Projects… • Network: unified compute & storage, low latency • Storage: distributed, in-node non-volatile memories • Real Applications: Scientific, Engineering, Data Analytics • Data Centre Infrastructure (Power and Cooling): Total Liquid Cooling • Prototype: 1K cores, 16GBytes DDR4 per FPGA 3HPC User Forum 1st March 2017, Stuttgart
  • 4. The ExaNeSt Consortium 4 Storage&data UK Italy Greece - coordinator UK UKUPV - ES Technology Interconnects Netherlands France Germany Applications Italy Italy Italy www.exanest.eu HPC User Forum 1st March 2017, Stuttgart
  • 6. Interconnection Network • Now: Simulations, Studies: – at the Packet/flit level, for protocol behavior and interactions (using INSEE and Omnet+); – Traffic Inputs: Synthetic models, real App Traces, or running App’s. • Later: Experiments on real Prototype running real App’s • Packaging & interconnect considered in tandem – Hierarchical interconnect • Design Goals: – unified network for compute & storage – flow prioritization: heavy / storage versus short / sync (compute) – throttle congestive flows at network edges – resiliency: error detect/correct, monitor links, multipath routing – Zero-copy, user-level RDMA – Global address space – all-optical proof-of-concept TOR switch using 2×2/4×4 building blocks 6HPC User Forum 1st March 2017, Stuttgart
  • 8. Storage: current Design work Global Storage Layer + + per-job SSD/NVM on-demand Parallel Cache Layer • Based on the BeeGFS parallel filesystem (open source), with caching and replication extensions • Low-latency memory-mapped storage access path in Linux • Virtualization: RDMA from within VM’s; MPI remoting • Acceleration for Host-to-VM and VM-to-VM interactions 8HPC User Forum 1st March 2017, Stuttgart
  • 10. Applications, Traces 10 Main Applications: • Material science: LAMMPS • Climate change: REGCM • Engineering CFD: openFoam, SailFish • Astrophysics: • Large-scale high-resolution simulations of cosmic formation and evolution • Gadget, Pinocchio, Changa, Swift • Neuroscience – brain simulation: DPSNN • High Energy Physics • Lattice Quantum Chromodynamics simulations - LQCD • Data Analytics: MonetDB • Porting selected App’s to ARM HPC User Forum 1st March 2017, Stuttgart
  • 12. Power • 48V DC to POL Converter on Daughter Board • 3 Phase 415V to 48V DC Liquid Cooled Power Conversion • 48V DC Power Distribution • Ambition to integrate renewable energy on-site generation and energy storage at DC to remove conversion cycles and give “green power” (Separate Project) 12 AC DC 48V UPS AC DC 12V DC PoL AC DC 48V DC PoL Old New
  • 13. Cooling Combination of 3 Different Patented Cooling Technologies • Immersion – Natural Convection “Cells” – Forced Convection “Fountains” • Conduction • Total Liquid Cooling • Zero Airflow • Potential for High Temperatures and Heat Capture 13
  • 15. Our Nodes 15HPC User Forum 1st March 2017, Stuttgart
  • 18. The 1st Major ExaNeSt Prototype (2017) • Using Xilinx Zynq UltraScale+ FPGAs: – Quad-core 64-bit ARM A53 per FPGA – Cache-coherent low-latency I/O port • On 120×130 mm2 Daughter Boards – 4 FPGA’s – 1 TB SSD – 10× 16Gb/s I/O’s • 1st Prototype – Up to 8 DB’s per Blade, 9 Blades • In Early Test Now – First deployment = within 2017 18 Electronics immersed in PFPE liquids Rack-level water circulation HPC User Forum 1st March 2017, Stuttgart
  • 19. The 2nd Major ExaNeSt Prototype (2018) • Same FPGAs, Same Quad FPGA Daughter Board • 16 DB’s, 1 Blade, 3.2kW in 1u, Small Footprint Cabs • Our Ambition – Hot Water Cooling (>50C), Heat Capture Functions – 100kW cabinets, 1.0x PUE, >0.9 ERF Potential – DC Power Distribution – Potential for High Density Data Centres or Modular Facilities: HPC User Forum 1st March 2017, Stuttgart 19 Aisle Aisle 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs Aisle 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs Coolant and DC Power Aisle Aisle 600x600mm cabinetwith6 chassis&2xCDUs Aisle 2.5m ICEOTOPE CONFIDENTIAL Batteries and Rectifiers for 250kW of Load Batteries and Rectifiers for 250kW of Load Coolant and DC Power600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs 600x600mm cabinetwith6 chassis&2xCDUs Coolant and DC Power Batteries and Rectifiers for 250kW of Load Batteries and Rectifiers for 250kW of Load Coolant and DC Power 10.6m Wall Wall 1MW DC In 40ft ISO or 10mx2.4m
  • 20. What ExaneSt offers to the Ecosystem • Use of the Prototypes by ExaNoDe and EcoScale • Use of the Prototype by the Ecosystem (2018 onwards) • HPC technology components (2018 onwards): – ARM/Unimem – Fine-tuned Applications – The Ultra-Dense Data Centre for Scaling HPC – Packaging & Cooling – Distributed NVM / Storage – Interconnects – DB compute-node prototype 20HPC User Forum 1st March 2017, Stuttgart
  • 21. European Exascale System Interconnect & Storage • Interconnection Network • In-node Storage • Data Centre Infrastructure • Advanced Cooling & Power • Real Applications www.exanest.eu Project Coordinator: Prof. Manolis Katevenis (kateveni@ics.forth.gr) HPC User Forum 1st March 2017, Stuttgart