SGI® Solutions with Intel®
Xeon® E5-2600v2
Bill Mannel
General Manager
Compute
Under Embargo until 12:01 a.m. September 10, 2014
• Better performance and features in our
SGI® ICE™ X, Rackable®, and Modular
InfiniteStorage™ lines via the new Intel
E5-2600v2 processor family
• Notable & relevant customer wins
2
What We’re Announcing
Under Embargo until 12:01 a.m. September 10, 2014
• SGI ICE X:
– Top performance, nearly 40%
increase over E5-2600 rack level
performance
– Scalability: Total, top Commercial
system (2.33 Peak Petaflops)
– Efficiency: typical 90%+ processing
efficiency and leading power
efficiency
• Standards-based Compute!
– X86, Infiniband, vanilla RedHat or
SUSE
3
SGI® ICE™ X with Intel Xeon E5-2600v2
Under Embargo until 12:01 a.m. September 10, 2014
4
SGI® ICE™ X Placeholder for Benchmark
• We expect that ICE X will
achieve the MPIL2007 record
again with Intel® Xeon® E5-
2600v2
• 4608 MPI ranks will be tested
Under Embargo until 12:01 a.m. September 10, 2014
5
SGI® ICE™ X
• Available in M-Cell and
standard D-rack deployments
– 32C warm water cooling
– On-processor cold-sink
• Supports multiple Infiniband
topologies to optimize for
specific workloads
Under Embargo until 12:01 a.m. September 10, 2014
Common InfiniBand Topologies
All-to-All
Fat Tree
(CLOS
Networks)
Hypercube
Enhanced
Hypercube
All Supported on SGI ICE X
Under Embargo until 12:01 a.m. September 10, 2014
7
"The efficiency of the SGI ICE X
system, which represents high
computational power using a
minimal amount of energy,
gives Total the smallest
footprint and lowest TCO
possible. This was a key factor
in our selection of SGI ICE X for
the Pangea system."
Philippe Malzac, CIO Exploration and
Production for Total
Pangea featured at http://www.sgi.com/products/servers/ice/x/feature.html
Under Embargo until 12:01 a.m. September 10, 2014
• Rackable:
– Solutions-based Compute!
– Tested at the system level
– Factory-integrated
• Example Solutions:
– HPC Clusters, GigE or IB
– SGI Clusters for Hadoop
– SGI DataRaptor™, NoSQL appliance
8
Rackable® with Intel Xeon E5-2600v2
Under Embargo until 12:01 a.m. September 10, 2014
• World-record benchmarks
for two-socket servers:
– SPEC MPIM2007
– SPEC OMP2012
• Terasort benchmark (for
Hadoop) TBA!
9
Rackable® with Intel Xeon E5-2600v2
Under Embargo until 12:01 a.m. September 10, 2014
SGI® Modular InfiniteStorage™
10
One modular platform =
multiple differentiated products
Under Embargo until 12:01 a.m. September 10, 2014
• Highly dense, modular design
– Up to 324 raw TB in a 4U
– 19 in. form factor
• Flexible deployments
– Storage Server or JBOD
– SAS, SATA & SSD storage
• High throughput
– 6GB/s per chassis
• Designed to meet stringent availability requirements
– Redundant components
– Multiple RAID options - 0, 1, 5, 6, 10
– Hot swap components
SGI Modular InfiniteStorage
Under Embargo until 12:01 a.m. September 10, 2014
• SGI MIS Server
– Integrated into 4U chassis
• 2 two socket motherboard
• Intel® E5-2600v2 processors
– Each chassis supports SATA/SAS/SSD drive types:
• Up to 72 x 3.5” drives
• Or 144 x 2.5” 9.5mm SSD drives
– Onboard and optional network connectivity
• SGI MIS JBOD
– Up to 81 x 3.5” drives
– Or 162 x 2.5” 9.5mm SSD drives
Two Chassis Options
Under Embargo until 12:01 a.m. September 10, 2014
13
Customer Win: NASA Pleiades
Addition
• 45 racks of SGI ICE X
with Intel® Xeon E5-
2600v2
• 2.88 Peak Petaflops for
total system
• Installed in chunks, most
coming on line in a day
or two; complete
expansion in place in
less than one month with
no user down-time
Discovering 136 New Planets!
Under Embargo until 12:01 a.m. September 10, 2014
14
“The unique architectural design of the SGI ICE
platform allows us to expand the system without
downtime, saving us precious compute hours as
we increase and adapt system size to NASA's
evolving missions”
Rupak Biswas,
Division Chief
NASA Ames Research Center
Under Embargo until 12:01 a.m. September 10, 2014
15
Customer Win: ICHEC
• Irish Center for High-End
Computing
• 10 racks of SGI hardware
• 8,320 cores of the new Intel
Xeon E5-2600 v2 processor
in an ICE X as well as a large
1.7TB shared memory system
and 64 Intel Xeon Phi and
NVidia K20 accelerators
Under Embargo until 12:01 a.m. September 10, 2014
16
“Over a two week period SGI delivered and installed ICHEC's
new HPC system to the point where application porting and
testing on the new platform could proceed. The new SGI
systems will enable much larger and more detailed problems to
be simulated and analyzed in fields such as weather and
climate forecasting, materials science and bioinformatics.”
Niall Wilson,
Principal System Administrator
Irish Centre for High-End Computing
17

More Related Content

PPTX
Summit supercomputer
PDF
Web後端技術的演變
PPTX
Persistent Storage for Containerized Applications
PDF
Spinnaker Chadev
PDF
Spinnaker - Bay Area AWS Meetup - 20160726
PPTX
Continuous Deployment to the Cloud using Spinnaker
PDF
Helix core on aws webinar
PPTX
Openstack portal-bestpractices-campbell mcneill
Summit supercomputer
Web後端技術的演變
Persistent Storage for Containerized Applications
Spinnaker Chadev
Spinnaker - Bay Area AWS Meetup - 20160726
Continuous Deployment to the Cloud using Spinnaker
Helix core on aws webinar
Openstack portal-bestpractices-campbell mcneill

What's hot (20)

PDF
How to deliver High Performance OpenStack Cloud: Christoph Dwertmann, Vault S...
PPTX
Stateful Applications On the Cloud: A PayPal Journey
PDF
OpenStack and Rackspace – an Australian perspective: Tony Breeds, Rackspace
PDF
dodai_grizzly.pdf
PDF
Spinnaker at DevOpsDays Montreal
PDF
Addressing Issues of Risk & Governance in OpenStack without sacrificing Agili...
PDF
Elastic{ON} Seminar New York (2017)
PPTX
Deploying OpenStack with Ansible
PPTX
OpenStack at Scale Inside NetApp
PDF
Presto: Query Anything - Data Engineer’s perspective
PPTX
Leveraging OpenStack to Run Mesos/Marathon at Charter Communications
ODP
Learning to Scale OpenStack: An Update from the Rackspace Public Cloud
PPTX
OpenStack in the Enterprise
PPTX
Operating OpenStack - Case Study in the Rackspace Cloud
ODP
Red Hat OpenStack Deployment
PPT
OpenStack What's New in Essex
PPTX
Taking Cloud to Extremes: Scaled-down, Highly Available, and Mission-critical...
PPTX
Hostvn ceph in production v1.1 dungtq
PDF
Ceph Deployment with Dell Crowbar - Ceph Day Frankfurt
PPTX
Challenges of Kubernetes On-premise Deployment
How to deliver High Performance OpenStack Cloud: Christoph Dwertmann, Vault S...
Stateful Applications On the Cloud: A PayPal Journey
OpenStack and Rackspace – an Australian perspective: Tony Breeds, Rackspace
dodai_grizzly.pdf
Spinnaker at DevOpsDays Montreal
Addressing Issues of Risk & Governance in OpenStack without sacrificing Agili...
Elastic{ON} Seminar New York (2017)
Deploying OpenStack with Ansible
OpenStack at Scale Inside NetApp
Presto: Query Anything - Data Engineer’s perspective
Leveraging OpenStack to Run Mesos/Marathon at Charter Communications
Learning to Scale OpenStack: An Update from the Rackspace Public Cloud
OpenStack in the Enterprise
Operating OpenStack - Case Study in the Rackspace Cloud
Red Hat OpenStack Deployment
OpenStack What's New in Essex
Taking Cloud to Extremes: Scaled-down, Highly Available, and Mission-critical...
Hostvn ceph in production v1.1 dungtq
Ceph Deployment with Dell Crowbar - Ceph Day Frankfurt
Challenges of Kubernetes On-premise Deployment
Ad

Viewers also liked (7)

PPT
Introduction To Windows Workflow In Windows Share Point
PPTX
Shri U.S.B. Group Of Colleges Abu Road
PDF
Intel's "Ivy Bridge" Overview
PPTX
Processor powerpoint 2
PPT
Intel Core i7 Processors
PPTX
Processor powerpoint
PPTX
Intel I3,I5,I7 Processor
Introduction To Windows Workflow In Windows Share Point
Shri U.S.B. Group Of Colleges Abu Road
Intel's "Ivy Bridge" Overview
Processor powerpoint 2
Intel Core i7 Processors
Processor powerpoint
Intel I3,I5,I7 Processor
Ad

Similar to Sgi Ivy Bridge Podcast (20)

PPT
Sgi hadoop
PDF
SGI HPC Update for June 2013
PPT
IBM Special Announcement session Intel #IDF2013 September 10, 2013
PDF
Blade Svr Comaprision sheet.pdf
PPTX
Xeon Azure Local Pitch Deck - 25Q1v3.pptx
PDF
The latest developments from OVHcloud’s bare metal ranges
PDF
Compare X86 Servers
PDF
IBM System x iDataPlex dx360 M4
PDF
IBM System x en BladeCenter overzicht (june 2012)
PDF
Hadoop World 2011: I Want to Be BIG - Lessons Learned at Scale - David "Sunny...
PDF
IBM Redbooks Product Guide: IBM System x3630 M4
PDF
Inside story on Intel Data Center @ IDF 2013
PPTX
Ibm and Erb's Presentation Insider's Edition Event . September 2010
PDF
cxl introduction of intel compute expresser link.pdf
PDF
IBM® SYSTEM X M4 SERVERS DELIVER COMPELLING PERFORMANCE AND ENERGY EFFICIENCY
PPT
New high-density storage server - IBM System x3650 M4 HD
PDF
Intel Knights Landing Slides
PDF
Accelerating Insights in the Technical Computing Transformation
PDF
IBM System x3500 M4
PDF
Workshop actualización SVG CESGA 2012
Sgi hadoop
SGI HPC Update for June 2013
IBM Special Announcement session Intel #IDF2013 September 10, 2013
Blade Svr Comaprision sheet.pdf
Xeon Azure Local Pitch Deck - 25Q1v3.pptx
The latest developments from OVHcloud’s bare metal ranges
Compare X86 Servers
IBM System x iDataPlex dx360 M4
IBM System x en BladeCenter overzicht (june 2012)
Hadoop World 2011: I Want to Be BIG - Lessons Learned at Scale - David "Sunny...
IBM Redbooks Product Guide: IBM System x3630 M4
Inside story on Intel Data Center @ IDF 2013
Ibm and Erb's Presentation Insider's Edition Event . September 2010
cxl introduction of intel compute expresser link.pdf
IBM® SYSTEM X M4 SERVERS DELIVER COMPELLING PERFORMANCE AND ENERGY EFFICIENCY
New high-density storage server - IBM System x3650 M4 HD
Intel Knights Landing Slides
Accelerating Insights in the Technical Computing Transformation
IBM System x3500 M4
Workshop actualización SVG CESGA 2012

More from inside-BigData.com (20)

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

Recently uploaded (20)

PDF
giants, standing on the shoulders of - by Daniel Stenberg
PDF
Aug23rd - Mulesoft Community Workshop - Hyd, India.pdf
PDF
5-Ways-AI-is-Revolutionizing-Telecom-Quality-Engineering.pdf
PDF
Transform-Your-Factory-with-AI-Driven-Quality-Engineering.pdf
PDF
Electrocardiogram sequences data analytics and classification using unsupervi...
PDF
A symptom-driven medical diagnosis support model based on machine learning te...
PDF
Convolutional neural network based encoder-decoder for efficient real-time ob...
PDF
The-2025-Engineering-Revolution-AI-Quality-and-DevOps-Convergence.pdf
PDF
AI.gov: A Trojan Horse in the Age of Artificial Intelligence
PDF
Transform-Your-Supply-Chain-with-AI-Driven-Quality-Engineering.pdf
PDF
Co-training pseudo-labeling for text classification with support vector machi...
PDF
4 layer Arch & Reference Arch of IoT.pdf
PPTX
GROUP4NURSINGINFORMATICSREPORT-2 PRESENTATION
PDF
Early detection and classification of bone marrow changes in lumbar vertebrae...
PDF
Transform-Quality-Engineering-with-AI-A-60-Day-Blueprint-for-Digital-Success.pdf
PDF
Enhancing plagiarism detection using data pre-processing and machine learning...
PDF
Data Virtualization in Action: Scaling APIs and Apps with FME
PDF
Connector Corner: Transform Unstructured Documents with Agentic Automation
PPTX
Module 1 Introduction to Web Programming .pptx
PDF
IT-ITes Industry bjjbnkmkhkhknbmhkhmjhjkhj
giants, standing on the shoulders of - by Daniel Stenberg
Aug23rd - Mulesoft Community Workshop - Hyd, India.pdf
5-Ways-AI-is-Revolutionizing-Telecom-Quality-Engineering.pdf
Transform-Your-Factory-with-AI-Driven-Quality-Engineering.pdf
Electrocardiogram sequences data analytics and classification using unsupervi...
A symptom-driven medical diagnosis support model based on machine learning te...
Convolutional neural network based encoder-decoder for efficient real-time ob...
The-2025-Engineering-Revolution-AI-Quality-and-DevOps-Convergence.pdf
AI.gov: A Trojan Horse in the Age of Artificial Intelligence
Transform-Your-Supply-Chain-with-AI-Driven-Quality-Engineering.pdf
Co-training pseudo-labeling for text classification with support vector machi...
4 layer Arch & Reference Arch of IoT.pdf
GROUP4NURSINGINFORMATICSREPORT-2 PRESENTATION
Early detection and classification of bone marrow changes in lumbar vertebrae...
Transform-Quality-Engineering-with-AI-A-60-Day-Blueprint-for-Digital-Success.pdf
Enhancing plagiarism detection using data pre-processing and machine learning...
Data Virtualization in Action: Scaling APIs and Apps with FME
Connector Corner: Transform Unstructured Documents with Agentic Automation
Module 1 Introduction to Web Programming .pptx
IT-ITes Industry bjjbnkmkhkhknbmhkhmjhjkhj

Sgi Ivy Bridge Podcast

  • 1. SGI® Solutions with Intel® Xeon® E5-2600v2 Bill Mannel General Manager Compute
  • 2. Under Embargo until 12:01 a.m. September 10, 2014 • Better performance and features in our SGI® ICE™ X, Rackable®, and Modular InfiniteStorage™ lines via the new Intel E5-2600v2 processor family • Notable & relevant customer wins 2 What We’re Announcing
  • 3. Under Embargo until 12:01 a.m. September 10, 2014 • SGI ICE X: – Top performance, nearly 40% increase over E5-2600 rack level performance – Scalability: Total, top Commercial system (2.33 Peak Petaflops) – Efficiency: typical 90%+ processing efficiency and leading power efficiency • Standards-based Compute! – X86, Infiniband, vanilla RedHat or SUSE 3 SGI® ICE™ X with Intel Xeon E5-2600v2
  • 4. Under Embargo until 12:01 a.m. September 10, 2014 4 SGI® ICE™ X Placeholder for Benchmark • We expect that ICE X will achieve the MPIL2007 record again with Intel® Xeon® E5- 2600v2 • 4608 MPI ranks will be tested
  • 5. Under Embargo until 12:01 a.m. September 10, 2014 5 SGI® ICE™ X • Available in M-Cell and standard D-rack deployments – 32C warm water cooling – On-processor cold-sink • Supports multiple Infiniband topologies to optimize for specific workloads
  • 6. Under Embargo until 12:01 a.m. September 10, 2014 Common InfiniBand Topologies All-to-All Fat Tree (CLOS Networks) Hypercube Enhanced Hypercube All Supported on SGI ICE X
  • 7. Under Embargo until 12:01 a.m. September 10, 2014 7 "The efficiency of the SGI ICE X system, which represents high computational power using a minimal amount of energy, gives Total the smallest footprint and lowest TCO possible. This was a key factor in our selection of SGI ICE X for the Pangea system." Philippe Malzac, CIO Exploration and Production for Total Pangea featured at http://www.sgi.com/products/servers/ice/x/feature.html
  • 8. Under Embargo until 12:01 a.m. September 10, 2014 • Rackable: – Solutions-based Compute! – Tested at the system level – Factory-integrated • Example Solutions: – HPC Clusters, GigE or IB – SGI Clusters for Hadoop – SGI DataRaptor™, NoSQL appliance 8 Rackable® with Intel Xeon E5-2600v2
  • 9. Under Embargo until 12:01 a.m. September 10, 2014 • World-record benchmarks for two-socket servers: – SPEC MPIM2007 – SPEC OMP2012 • Terasort benchmark (for Hadoop) TBA! 9 Rackable® with Intel Xeon E5-2600v2
  • 10. Under Embargo until 12:01 a.m. September 10, 2014 SGI® Modular InfiniteStorage™ 10 One modular platform = multiple differentiated products
  • 11. Under Embargo until 12:01 a.m. September 10, 2014 • Highly dense, modular design – Up to 324 raw TB in a 4U – 19 in. form factor • Flexible deployments – Storage Server or JBOD – SAS, SATA & SSD storage • High throughput – 6GB/s per chassis • Designed to meet stringent availability requirements – Redundant components – Multiple RAID options - 0, 1, 5, 6, 10 – Hot swap components SGI Modular InfiniteStorage
  • 12. Under Embargo until 12:01 a.m. September 10, 2014 • SGI MIS Server – Integrated into 4U chassis • 2 two socket motherboard • Intel® E5-2600v2 processors – Each chassis supports SATA/SAS/SSD drive types: • Up to 72 x 3.5” drives • Or 144 x 2.5” 9.5mm SSD drives – Onboard and optional network connectivity • SGI MIS JBOD – Up to 81 x 3.5” drives – Or 162 x 2.5” 9.5mm SSD drives Two Chassis Options
  • 13. Under Embargo until 12:01 a.m. September 10, 2014 13 Customer Win: NASA Pleiades Addition • 45 racks of SGI ICE X with Intel® Xeon E5- 2600v2 • 2.88 Peak Petaflops for total system • Installed in chunks, most coming on line in a day or two; complete expansion in place in less than one month with no user down-time Discovering 136 New Planets!
  • 14. Under Embargo until 12:01 a.m. September 10, 2014 14 “The unique architectural design of the SGI ICE platform allows us to expand the system without downtime, saving us precious compute hours as we increase and adapt system size to NASA's evolving missions” Rupak Biswas, Division Chief NASA Ames Research Center
  • 15. Under Embargo until 12:01 a.m. September 10, 2014 15 Customer Win: ICHEC • Irish Center for High-End Computing • 10 racks of SGI hardware • 8,320 cores of the new Intel Xeon E5-2600 v2 processor in an ICE X as well as a large 1.7TB shared memory system and 64 Intel Xeon Phi and NVidia K20 accelerators
  • 16. Under Embargo until 12:01 a.m. September 10, 2014 16 “Over a two week period SGI delivered and installed ICHEC's new HPC system to the point where application porting and testing on the new platform could proceed. The new SGI systems will enable much larger and more detailed problems to be simulated and analyzed in fields such as weather and climate forecasting, materials science and bioinformatics.” Niall Wilson, Principal System Administrator Irish Centre for High-End Computing
  • 17. 17

Editor's Notes

  • #10: Overall world record SPEC MPIM2007 performance based on the SPECmpiM_2007 metricBest-in-class performance for SPEC MPIM2007 at 2, 4, 8, 16, and 32 sockets based on the SPECmpiM_2007 metricBest-in-class performance for SPEC MPIL2007 at 8, 16, 32, 64, and 128 chips based on the SPECmpiL_2007 metricBest-in-class performance for SPEC OMPG2012 at 2 sockets based on the SPECompG_2012 metric
  • #11: Modularity is all about giving the customer the choices to get what they need, not what the manufacture wants to offer. This means the customer can address a wide range of needs with a flexible system for applications, pure storage, etc.As needs grow and change, the customer can adapt the system based on the modular in common core platform, continually keeping pace with the evolving demands of their business. Scalability is important, but is not unique to SGI. Where it matters is that coupled with the other attributes, customers can scale up and out in precisely the way they need to keep pace with their rapidly expanding data and application requirements. Other systems require the customer to adapt to their system limitations, scale only within the constraints of their platforms, and thus limit flexibility.