IBM Power Systems: Designed for Data Open innovation to put data to work across the enterprise

1. IBM Power Systems: Designed for Data Open innovation to put data to work across the enterprise

2. Digitized data will grow by 50% to 6 trillion TB in this year alone
80% of all data is unstructured and growing 15X the rate of structured data
73% of organizations have invested or plan to invest in Big Data & Analytics
Big Data is becoming the New Competitive Advantage
source: grow by 50% - IDC Predictions 2014: Battles for Dominance — and Survival — on the 3rd Platform; Frank Gens; December 2013, IDC #244606; http://www.sapexecutivenetwork.com/phocadownload/RTDP/retfeb/idc predictions 2014 battles for dominance - and survival - on the 3rd platform 2.pdf source: 73 percent of organizations - http://www.gartner.com/newsroom/id/2848718

3. The Opportunities from Big Data & Analytics are Infinite
1000X faster insights
75% productivity improvement
10X storage space savings
3.5X less infrastructure
68% less attrition among high-value customers
50% increase sales order capacity
140X faster queries
Source(s): Fiserv (Case Study), NC State Univ (Video), Coca Cola (eBook, Video, Case Study), STO (Case Study), Dillards (Video), BCBS of Tenn (eBook), BCBS of Tenn (eBook), Fossil (based on customer internal benchmarks)

4. First processor designed and optimized for big data & analytics with POWER8 innovative design
Delivering the world’s first open server ecosystem revolutionizing the way IT is developed & delivered
Superior cloud price / performance advantages & security to move data-centric applications to the cloud
Designed for big data
Open Innovation platform
Superior cloud economics
Power Systems with POWER8 are built with open innovation to put data to work across the enterprise
IBM Power Systems built on

5. Processors flexible, fast execution of analytics algorithms
Memory large, fast workspace to maximize business insight
Data Bandwidth bring massive amounts of information to compute resources in real-time
4X
threads per core vs. x86
(up to 1500 threads per system)
4X
memory bandwidth vs. x86
(up to 16TB of memory)
2.4X more I/O bandwidth than POWER7
Designed for Big Data: optimized Big Data & Analytics performance
Optimized for a broad range of big data & analytics workloads:
82X is based on IBM internal tests as of April 17, 2014 comparing IBM DB2 with BLU Acceleration on Power with a comparably tuned competitor row store database server on x86 executing a materially identical 2.6TB BI workload in a controlled laboratory environment. Test measured 60 concurrent user report throughput executing identical Cognos report workloads. Competitor configuration: HP DL380p, 24 cores, 256GB RAM, Competitor row-store database, SuSE Linux 11SP3 (Database) and HP DL380p, 16 cores, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). IBM configuration: IBM S824, 24 cores, 256GB RAM, DB2 10.5, AIX 7.1 TL2 (Database) and IBM S822L, 16 of 20 cores activated, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). Results may not be typical and will vary based on actual workload, configuration, applications, queries and other variables in a production environment.
Industry Solutions
5X Faster

6. Power S812L
Power S822L
Power S824L*

1 or 2 sockets

10 or 12 cores/socket

Up to 1 TB of Memory

1 or 2 sockets

6, 8,10 or 12 cores/socket

Up to 2 TB of Memory*
Expanding the POWER8 Scale-out server offerings
Power S814
Power S822
Power S824
Source: http://www.ibm.com/systems/power/announcement.html

7. Introducing record breaking Enterprise Systems with POWER8 designed to take on the most complex data challenges

Tackle your largest workloads with increased system scalability

Deliver insights in real time with increased performance per-core

Maximize your customers experience with Enterprise RAS
Power E870
•
Up to 80 cores
•
32 or 40 core nodes (5U)
•
Up to 4TB Memory
•
1 or 2 Nodes per system
Power E880
•
Up to 128* cores
•
32 or 48 core nodes (5U)
•
Up to 16* TB Memory
•
1 to 4 Nodes per system

Reduce costs with increased energy efficiency

Manage the peaks and valleys of workloads Power Enterprise Pools

Manage a wider range of workloads with up to 20 VMs per-core
Power E880
Power E870
* Initial GA supports 2 nodes, 64 cores, 8 TB with MES to 3 or 4 nodes in 2015

8. Designed for Data: Big Memory for Big Data
Speed access to data with larger in- memory databases and consolidate more applications with 2TB of installed memory in Scale-out Systems
Support the bigger data demands and consolidate large databases of complex mission critical applications securely with 16TB of memory on new Power Enterprise Systems

9. 24:1 consolidation
8X faster insights
Data Engine for Analytics
CAPI-attached Flash
3X less storage
Open innovation to deliver insight to the point of impact with Big Data & Analytics on Power Systems
NVIDIA GPU Accelerator
82X faster insights
Next Generation In-Memory
source: for 24:1 system consolidation ratio (12:1 rack density improvement) based on a single IBM S824, (24 cores, POWER8 3.5 GHz), 256GB RAM, AIX 7.1 with 40 TB memory based Flash replacing 24 HP DL380p, 24 cores, E5-2697 v2 2.7 GHz), 256GB RAM, SuSE Linux 11SP3 . Inbound network limits performance to 1M IOPs in both scenarios, equal capacity (#user, data) in both cases. x86 cost includes 10k$ for 2x 1U switches source: for 82X is based on IBM internal tests as of April 17, 2014 comparing IBM DB2 with BLU Acceleration on Power with a comparably tuned competitor row store database server on x86 executing a materially identical 2.6TB BI workload in a controlled laboratory environment. Test measured 60 concurrent user report throughput executing identical Cognos report workloads. Competitor configuration: HP DL380p, 24 cores, 256GB RAM, Competitor row-store database, SuSE Linux 11SP3 (Database) and HP DL380p, 16 cores, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). IBM configuration: IBM S824, 24 cores, 256GB RAM, DB2 10.5, AIX 7.1 TL2 (Database) and IBM S822L, 16 of 20 cores activated, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). Results may not be typical and will vary based on actual workload, configuration, applications, queries and other variables in a production environment.

10. Designed for Big Data: Drive Infrastructure Optimization
24X infrastructure
consolidation savings
vs. x86 for in-memory data
IBM Data Engine for NoSQL Solution allows clients to crunch data faster and shrink data center footprints

Reduce server footprint with in-memory consolidation

Cost efficient with 3x lower cost per user
IBM Data Engine for NoSQL Solution
•
IBM Power S822L
•
CAPI-Attached FPGA Accelerator
•
IBM FlashSystem 840
•
Ubuntu Linux
•
Redis Software
source: for 24:1 system consolidation ratio (12:1 rack density improvement) based on a single IBM S824, (24 cores, POWER8 3.5 GHz), 256GB RAM, AIX 7.1 with 40 TB memory based Flash replacing 24 HP DL380p, 24 cores, E5-2697 v2 2.7 GHz), 256GB RAM, SuSE Linux 11SP3 . Inbound network limits performance to 1M IOPs in both scenarios, equal capacity (#user, data) in both cases. x86 cost includes 10k$ for 2x 1U switches

11. Deliver new acceleration capabilities for Analytics, Big Data, Java and other technical computing workloads

Runs pattern extraction analytic workloads faster

Delivers faster results and lower energy costs by accelerating processor intensive applications
Power System S824L
•
Up to 24 POWER8 cores
•
Up to 1 TB of memory
•
Up to 2 NVIDIA K40 GPU Accelerators
•
Ubuntu Linux running bare metal
8X faster analytics workloads that extract patterns from large amounts of data
Open innovation with POWER8 and NVIDIA GPU technology borne of the OpenPOWER Foundation

12. Big Data & Analytics Solutions for Fastest Time to Value
DataStage
POWER8 Data Optimized Solutions:
•
Simple to Acquire Order server, storage, software and support from a single vendor
•
Simple to Deploy Pre-installed and pre-optimized server, storage & software
•
Simple to Implement Highly scalable to grow as your analytics need change
IBM BLU Acceleration Solution Next generation in-memory database technology for analytics at the speed of thought
IBM Solution for Analytics Enable rapid deployment of business and predictive analytics
IBM Data Engine for Analytics Innovation that optimizes unstructured big data performance

13. “While traditional TV ratings research will continue to be important, it must be augmented by social media intelligence.”
-- KC Leung, Senior Manager, Marketing Research and Information Department,
Unlock the value of customer sentiment in social media TVB will mine more than three decades of program ratings data to understand the trends of media consumption habits.
•
IBM Social Media Analytics (SaaS)
•
IBM DB2 with BLU Acceleration
•
IBM Cognos BI, IBM DataStage
•
IBM Power Systems
•
IBM Storwize V7000
Hong Kong’s first wireless commercial television station implements social media analytics to increase ratings
Learn more (Press)

14. “We cut report runtimes by up to 98 percent thanks to IBM DB2 with BLU Acceleration (on Power Systems) technology – without changing operations processes or investing in new hardware or software.” -- Bernhard Herzog, Team Manager Information Technology SAP, Balluff.
Faster insight into critical data for better business decisions Achieved 98% faster access to business data, 50% faster SAP ERP response times, 7x faster access to documents, and near real-time access to essential information.
•
IBM Power Systems
•
IBM PowerVM, PowerHA
•
IBM DB2 with BLU Acceleration
•
SAP Business Warehouse, ERP
•
IBM Storage & Services
World-leading manufacturer of sensor solutions gained faster insight into markets and customers
Learn more (Press, Case Study)

15. Instructions
Data
Results
C1C2C3C4C5C6C7C8C1C2C3C4C5C6C7C8
Next Generation In-Memory In-memory columnar processing with dynamic movement of data from storage
Actionable Compression Patented compression that preserves order so data can be used without decompressing
Parallel Vector Processing Multi-core and SIMD parallelism (Single Instruction Multiple Data)
Data Skipping Skips unnecessary processing of irrelevant data
Encoded
IBM DB2 with BLU Acceleration Unmatched Innovation from IBM Research & Development

16. 
The System: 32 cores, 1TB memory, 10TB table with 100 columns and 10 years of data

The Query: How many “sales” did we have in 2010?
–
SELECT COUNT(*) from MYTABLE where YEAR = ‘2010’

The Result: In seconds or less as each CPU core examines the equivalent of just 8MB of data
10TB data
Actionable Compression reduces to 1TB In-memory
Parallel Processing
32MB linear scan on each core via
Vector Processing Scans as fast as 8MB through SIMD
Result in seconds or less
Column Processing reduces to 10GB
Data Skipping
reduces to 1GB
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
DATA
BLU Acceleration Illustration: 10TB query in seconds or less

17. Cognos BI and DB2 with BLU Acceleration on POWER8 Fast on Fast on Fast
Acceleration of analytics queries for reporting
82X is based on IBM internal tests as of April 17, 2014 comparing IBM DB2 with BLU Acceleration on Power with a comparably tuned competitor row store database server on x86 executing a materially identical 2.6TB BI workload in a controlled laboratory environment. Test measured 60 concurrent user report throughput executing identical Cognos report workloads. Competitor configuration: HP DL380p, 24 cores, 256GB RAM, Competitor row-store database, SuSE Linux 11SP3 (Database) and HP DL380p, 16 cores, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). IBM configuration: IBM S824, 24 cores, 256GB RAM, DB2 10.5, AIX 7.1 TL2 (Database) and IBM S822L, 16 of 20 cores activated, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). Results may not be typical and will vary based on actual workload, configuration, applications, queries and other variables in a production environment.
82X
faster

18. The more concurrency and complexity, the greater the performance gains from POWER8 versus x86
Based on IBM internal tests as of April 17, 2014 comparing IBM DB2 with BLU Acceleration on Power with a comparably tuned competitor row store database server on x86 executing a materially identical 2.6TB BI workload in a controlled laboratory environment. Test measured 60 concurrent user report throughput executing identical Cognos report workloads. Competitor configuration: HP DL380p, 24 cores, 256GB RAM, Competitor row-store database, SuSE Linux 11SP3 (Database) and HP DL380p, 16 cores, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). IBM configuration: IBM S824, 24 cores, 256GB RAM, DB2 10.5, AIX 7.1 TL2 (Database) and IBM S822L, 16 of 20 cores activated, 384GB RAM, Cognos 10.2.1.1, SuSE Linux 11SP3 (Cognos). Results may not be typical and will vary based on actual workload, configuration, applications, queries and other variables in a production environment.

19. What are Industry Analysts saying about BLU Acceleration on Power Systems
http://bit.ly/1ndCUmA
http://bit.ly/1ndGxZU
IBM DB2 with BLU Acceleration on POWER8 for SAP: A No-Compromise Transactional and Analytic Platform
IBM DB2 with BLU Acceleration on POWER8 for Cognos BI: Delivers higher levels of performance, while controlling costs

20. IBM can help you build your solution on the platform that was designed for big data & analytics
All Data
Key
Business Processes
Unstructured Data
Structured Data
Industry Solutions
IBM Watson Cognitive
Business & Predictive Analytics

21. Power Systems are designed for Big Data & Analytics
3X less storage infrastructure for Hadoop deployments vs typical x862
IBM Data Engine for Analytics
designed to help clients speed up insights on massive amounts of data

Simplify operations - easy deploy and manage with 3x less storage infrastructure

Adapt and scale to your changing analytics needs
IBM Data Engine for Analytics
•
POWER8 Scale-out servers
•
Red Hat Linux
•
BigInsights (Hadoop) & Streams
•
Platform Computing
•
Elastic Storage Server (GPFS)

22. Delivering Customer Value
Computing environment allowing students to run analytics models on structured and unstructured data with IBM Power Systems
37x FASTER INDEXING
14 days to 9 hours
3.5x LESS INFRASTRUCTURE
14 x86 servers to 4 Power servers

23. The Business Case for Using Unstructured Text Analytics on IBM Power Systems for Critical Decision Making
http://bit.ly/1eCTJVu
Industry: Company
Question
Sources
Outcome
Temporary workforce:
Kelly Services
Develop new service offerings in healthcare staffing
SEC, URLs,
trade journals,
professional journals,
insurance providers
Decision to move forward in an unexpected healthcare domain
Industrial Gases:
Air Products
Find new customers and market opportunities
SEC, news feeds,
industry publications, building permits
Identification of a new customer planning to build new facilities
University:
NC State
Identify commercial partners for new technologies
SEC, URLs,
industry publications
Potential partners identified for collaborations
Clinical Research
Organization:
PRA International
Provide business intelligence for new clinical trials
Clintrials, PubMed
Identify new physicians/hospitals with expertise in areas of clinical trials
Non-Governmental Organization:
Clinton Health Care Access Initiative (CHAI)
Find the fit between new technologies and market opportunities for disease diagnostics
Clintrials, PubMed
VC firms
Identification of research labs active in cutting edge diagnostic research

24. What are Industry Analysts saying about Hadoop and Streams on Power Systems
http://ibm.co/1pdGES9
http://...
Why Linux on Power Systems should be your system of choice for unstructured big data & analytics
How companies are gaining high value insights with big data & analytics solutions built on IBM Power Systems

25. Join Power Systems in social media!
Where to learn more about Big Data & Analytics on IBM Power Systems
Start the conversation with your IBM Representative or Business Partner

Connect with Power on Linkedin: bit.ly/poweronlinkedin

Like us on Facebook: bit.ly/poweronfacebook

Watch us on YouTube: bit.ly/poweronyoutube

Follow us on Twitter: #PowerSystems, #OpenPower, #IBMBigData, #IBMAnalytics, #IBMWatson, #IBMBLU, #IBMCognos, #IBMSPSS, #IBMStream, #IBMBigInsights, #BobFriske
www.ibm.com/power
Open innovation to put data to work across the enterprise

26. Open innovation to put data to work across the enterprise

27. Trademarks and notes
IBM Corporation 2014
IBM, the IBM logo and ibm.com are registered trademarks, and other company, product, or service names may be trademarks or service marks of International Business Machines Corporation in the United States, other countries, or both. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml
Other company, product, and service names may be trademarks or service marks of others.
References in this publication to IBM products or services do not imply that IBM intends to make them available in all countries in which IBM operates.
IBM and IBM Credit LLC do not, nor intend to, offer or provide accounting, tax or legal advice to clients. Clients should consult with their own financial, tax and legal advisors. Any tax or accounting treatment decisions made by or on behalf of the client are the sole responsibility of the customer.
IBM Global Financing offerings are provided through IBM Credit LLC in the United States, IBM Canada Ltd. in Canada, and other IBM subsidiaries and divisions worldwide to qualified commercial and government clients. Rates and availability are based on a client’s credit rating, financing terms, offering type, equipment type and options, and may vary by country. Some offerings are not available in certain countries. Other restrictions may apply. Rates and offerings are subject to change, extension or withdrawal without notice.