View
216
Download
0
Category
Preview:
Citation preview
Building a secure foundation
for the cognitive eraDoug BalogGeneral Manager,
IBM Power Systems
©2016 IBM Corporation2
The industry is in a state of disruption
More than 80% is
unstructured – reaching
44 zettabytes by 2020
Systems that
understand,
reason, and learn
DATA COGNITIVE
The platform for digital
builders – 18.2M software
developers and growing
CLOUD
©2016 IBM Corporation3
Lenovo GLOBALFOUNDRIES
Phytel Explorys
SoftBank Box American Cancer Society
IBM Patent leadership for 23 consecutive years
IBM continues to transform…emerging as the
cognitive solutions and cloud platform company
©2016 IBM Corporation4
Offering Management
IBM Design Thinking
Agile
What the
Market
Needs
The
Right User
Experience
How we Work –
Iteratively &
Rapidly
We are working in new ways and will collaborate
more extensively than ever before
©2016 IBM Corporation5
Design for
Cognitive Business
To act at the
speed of thought.
Build with
Collaborative Innovation
To accelerate technology
breakthroughs.
Deliver through
Cloud Platform
To extend the value of
systems and data.
Outthink the status quo. Think IT infrastructure for the cognitive era.
IT leaders are becoming the architects of the future
IBM Systems can help clients transform for this new era
©2016 IBM Corporation6
Displacing competitors with
IBM Spectrum Storage
Engaging new clients
with new workloads on
z13 and Linux
Managing unstructured
data in the cloud with
object-based storage
Replacing spinning disk
with IBM FlashSystem
Driving x86 alternatives
with OpenPOWER
Scaling Digital Operations
by connecting Digital
Marketing to Digital Sales
How we will execute and win
We will scale our Systems capabilities for
cognitive workloads and hybrid cloud
©2016 IBM Corporation7
Fundamental forces are accelerating change in our industryP
rice
/Pe
rfo
rma
nce
Full system stack innovation required
Moore’s Law
IT innovation can no longer come from
just the processor
Cognitive
Custom Hyperscale
Data Centers
Hybrid Cloud
Open Solutions
IT consumption models
are expanding
Technology and
Processors
2000 2020
Firmware / OS
Accelerators
Software
Storage
NetworkFull Stack
Acceleration(Lower is
better)
©2016 IBM Corporation8
Transforming IBM Power Systems for growth
Designed for cognitive era
Power technology designed for
big data and analytics workloads
Cloud delivery
Hyperscale or hybrid cloud
with improved economics
Open, collaborative innovation platform
Enabling cognitive business and cloud economics
through Linux and open collaborations
©2016 IBM Corporation9
POWER8 Architecture POWER9 Architecture
2014POWER8
12 cores
22nm
New Micro-Architecture
New ProcessTechnology
2016POWER8w/ NVLink
12 cores
22nm
EnhancedMicro-
ArchitectureWith NVLink
2017P9 SO24 cores
14nm
New Micro-Architecture
Direct attachmemory
New ProcessTechnology
Optimized for Data-Centric Workloads
Integrated PCIe
CAPI Acceleration / I/O
Scale-Out Datacenter TCO Optimization
Scale-up performance Optimization
Acceleration Enhancements to CAPI and NVLINK
Modularity for OpenPOWER
TBDP9 SU
TBD cores
14nm
EnhancedMicro-
Architecture
BufferedMemory
POWER6 Architecture POWER7 Architecture
2007POWER6
2 cores
65nm
New Micro-Architecture
New ProcessTechnology
2008POWER6+
2 cores
65nm+
EnhancedMicro-
Architecture
EnhancedProcess
Technology
2010POWER7
8 cores
45nm
New Micro-Architecture
New ProcessTechnology
2012POWER7+
8 cores
32nm
EnhancedMicro-
Architecture
New ProcessTechnology
High Frequency
Enhanced RAS
Dynamic Energy Management
Large eDRAM L3 Cache
Optimized VSX
Enhanced Memory Subsystem
Focus on EnterpriseTechnology and Performance Driven
Focus on Scale-Out and EnterpriseCost and Acceleration Driven
2018 - 20P8/9 SO
10nm - 7nm
Existing Micro-
Architecture
FoundryTechnology
Partner ChipPOWER8/9
OpenPOWEREcosystem
DesignTargeting
Partner Markets & SystemsLeveraging Modulatrity
Price, performance, feature and ecosystem innovation
2020+
New Micro-Architecture
NewTechnology
POWER10
New Features and
Functions
Future
T
B
D
POWER processor roadmap
©2016 IBM Corporation10
7.2 7.3 7.4 7.5
Scaling/Growth
• 96 core
• 16 TB memory
Database
• Row/Column Access
Control
• In-memory DB ease of
use
• JSON Definitions
Scaling/Growth
• 192 core SMT4 P8
• 32 TB memory P8
• IPL Time Improvements
Database
• Temporal (Time-based)
Analysis
• Integrated OLAP
• JSON Consumption
Continuous Availability
• DB2 Mirror offering
•24x7; PTF Rollback;
Horizontal Scale-out
•Cluster IFS/Objects to
complement DB2 Mirror
• IPL Time Improvements
• DLPAR Improvements
Continuous Availability• Apply DB2 Mirror to
Release Upgrade from 7.4
Database• DB2 Temporal Business
POWER9 and beyond: Semi-annual Technology Refreshes (TRs) on current releases for support of latest POWER
Systems, Storage, I/O & Cloud.
2014
** All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
2016 2019 2022
IBM i roadmap
©2016 IBM Corporation11
An open innovation platform is critical in the new era
• Improved performance, including increased
availability and scalability
• Reduced time spent on housekeeping
• Decreased data center footprint
–
Linux and Open Source
Drives unique and competitive
solutions with broad ecosystem
100K+ open source packages,
1,000s of software vendors and
dozens of solutions
OpenPOWER
Delivers new POWER-based collaborative
solutions from members to the marketplace
leveraging licensing model
Cognitive demands acceleration technology
and cloud requires new business models
Sweden
Department
of Defense
©2016 IBM Corporation12
Fueling ecosystem innovation with
12©2016 IBM Corporation
©2016 IBM Corporation13
Fueling ecosystem innovation with
13©2016 IBM Corporation
230+ Members 24 Countries 6 Continents
100+ Collaborative innovations under way
30+ Hardware and technology providers
…IN LESS THAN 2 YEARS
©2016 IBM Corporation14
OpenPOWER Ecosystem Propels Open Innovation in Data Center
• Google and Rackspace will jointly develop next-generation OpenPOWER POWER9
system with the Open Compute design construct and accelerators
• Rackspace announced its use of first OpenPOWER/Open Computer/OpenStack system
• 50+ new OpenPOWER innovations across system stack in 2016
• Power Systems scale-out portfolio to include Open Compute and SuperMicro systems
• SoD of next-gen high performance computing server with POWER8 with Nvidia Nvlink
Vision Innovation Adoption
2014 20162015
• 15 innovations revealed • Developer evangelism
• Hyperscale and client adoption
5
OpenPOWER poised for adoption in 2016
©2016 IBM Corporation15
POWER is designed for the cognitive era
Accelerating and expanding genomic
research into common childhood conditions
such as autism, congenital diseases and
the many unknown causes of illness.
Analytics
Delivering leadership business insights
with an ecosystem of software vendors
~2X more query results per core /
per hour than x86 servers15
Cognitive Platform
Optimized for cognitive workloads
running on Watson
Watson runs nearly 2X faster with
OpenPOWER acceleration innovations16
©2016 IBM Corporation16
Intended for mission critical 24x7 Enterprise customer operations
• Highest Reliable, Available, Serviceable (RAS) in the market
• On-Demand Capacity
• Integrate into and tailor to your environment
Throughput per core
• Significant Power SMT-8 throughput advantages: 1.5x to 2.0x
• Value: fewer cores, fewer footprints, and lower operating costs
Virtualization out of the box
• Lower virtualization layer overhead on multi-threaded HANA workloads
• Value: fewer cores, fewer footprints, and lower operating costs
Scalability with investment protection
The value of SAP HANA on IBM POWER
©2016 IBM Corporation17
POWER and OpenPOWER accelerating digital business in the cloud
Hybrid
Deliver seamless integration, management
and security for the broad POWER
install base
Only OpenStack converged infrastructure
with zero virtualization security
vulnerabilities17
Custom Hyperscale
Offering market-leading price points via
OpenPOWER innovation
OpenPOWER-based systems provide 45%
better price-performance than x86-based
servers18
Notes 17-18
Tencent and China Mobile join a growing list of
worldwide hyperscale data centers choosing
OpenPOWER-based servers as an alternative to x86.
©2016 IBM Corporation18
- Design and cost optimized for deployments of multiples (cloud and cluster)
- Broad number of optimal solutions
- Built within the OpenPower ecosystem
Supported by Canonical
IBM Support
Community / 3rd
Party Support
running
The LC Line
The L Line
PurePower
Enterprise& IFLs
- Enterprise level RAS for single system deployments
- Solutions for Big Data & Analytics
- Converged infrastructure offering
- Rapid time to value and simplicity of management
- Enterprise level robustness and IFL capability
- Solution editions for in memory databases
- (HANA, DB2 BLU)
- Hosted cloud and hybrid cloud solutions
- Rapid deployments and POCs Pipeline of in
novation
• Broad linux portfolio deliver
all your linux deployment
needs
• Expanding LC portfolio with
two servers for data centric
applications and 2nd
generation HPC server
POWER8 is designed for the Big Data
era and delivers price-performance
leadership to the Linux market
Cloud-optimized infrastructure across the spectrum
©2016 IBM Corporation19
• Servers leveraging the OpenPOWER ecosystem and technologies from the
world's most innovative companies
• Portfolio designed to accelerate the speed of insights with POWER8 designed
for data and accelerator rich offerings
• Designed to seamlessly integrate into existing data center environments and
deliver superior data center efficiency
Coming soon: Three new OpenPOWER servers joining the LC portfolio.
Two designed for data-rich Linux workloads and compute-intensive
applications, and the third is our Gen2 HPC server delivering embedded
NVLink technology for superior GPU acceleration
Introducing the IBM Power Systems LC Line – OpenPOWER servers
designed for Linux workloads deployed in clouds and clusters
©2016 IBM Corporation20
LC servers designed to meet data center needs
Compatibility with existing
datacenter environments
IBM end user experience
with ultra-flexible service and
support
Superior performance and
economics results in
leadership efficiency
regardless of deployment
The LC portfolio provides an
economical entry point and
the ability to scale
• Data centers require numerous building blocks to drive efficiency
• Homogeneous datacenter architecture DOES NOT automatically equal
efficiency, right workloads on the right infrastructure
Service
Integration
Performance
Scalability
Security
IBM LC
Servers
©2016 IBM Corporation21
Modernize your IBM i and AIX Power infrastructure
for the Cloud, get access to IBM Cloud for free
and cut your current operating costs by 50%
IBM Confidential21
On-Premises Cloud Hybrid Cloud
Transform traditional infrastructure with
automation, self-service and elastic
consumption models
Securely extend to Public Cloud for free
with rapid access to compute services
and API integration
New IBM Power Systems high-end cloud offerings (C-models)
©2016 IBM Corporation22
Transforming IBM Power Systems for growth
Designed for cognitive era
Power technology designed for
big data and analytics workloads
Cloud delivery
Hyperscale or hybrid cloud
with improved economics
Open, collaborative innovation platform
Enabling cognitive business and cloud economics
through Linux and open collaborations
©2016 IBM Corporation23
Timo YensenPoul Hansen
Danish Defense
©2016 IBM Corporation25
FOOTNOTES
1. Flash: Worldwide and U.S. Enterprise Storage Systems Forecast Update, 2015–2019; November 2015, IDC #US40560715
2. Private Cloud Infrastructure: IDC Cloud Infrastructure HW Forecast Dec2015, IDC #US40380015
3. Linux $6K+: IDC, WW Quarterly Server Forecast, 2015Q3Forecast Release, Publication Date: September 10, 2015
4. Hyperscale Data Center: Worldwide Hyperscale Server 2014–2018 Forecast: Strong Hyperscale Buildout Continues, #249972
5. z13-500 patents: https://www-03.ibm.com/press/us/en/pressrelease/45808.wss
6. 32% lower TCO over 3 years versus x86: Performance comparison based on IBM Internal tests comparing IBM z13 cloud with one comparably configured private x86 cloud and one comparably configured
public cloud running an aggregation of light, medium and heavy workloads designed to replicate typical IBM customer workload usage in the marketplace. System configurations are based on equivalence
ratios derived from IBM internal studies and are as follows: Public Cloud configuration: total of 219 instances (128 for light workloads, 64 for medium workloads and 27 for heavy workloads); x86 Cloud
configuration: total of eleven x86 systems each with 24 Intel E7-8857 v2 3.0GHz cores, 512GB memory, and 7x400GB SSDs; z13 Cloud configuration: total of 32 IFLs, 3806GB memory, and Storwize v7000
with 47x400GB SSDs. Price comparison estimates based on a 3YR Total Cost of Ownership (TCO) using publicly available U.S. prices (including a 20% discount for middleware) current as of January 1, 2015.
Public Cloud TCO estimate includes costs (US East Region) of infrastructure (instances, data out, storage, support, free tier/reserved tier discounts), middleware and labor. z13 and x86 TCO estimates include
costs of infrastructure (system, memory, storage, virtualization, OS, cloud management), middleware, power, floor space and labor. Results may vary based on actual workloads, system configurations,
customer applications, queries and other variables in a production environment and may produce different results. Users of this document should verify the applicable data for their specific
environment. (https://www-03.ibm.com/press/us/en/pressrelease/45808.wss)
7. Scaling of 8K virtual machines: http://www-03.ibm.com/press/us/en/pressrelease/47474.wss
8. 30B web interactions: http://www-03.ibm.com/systems/linuxone/enterprise-linux-systems/
9. Fastest processor in the industry: http://www-03.ibm.com/press/us/en/pressrelease/47474.wss
10. 50x better performance vs. disk arrays: Based on IBM internal testing comparing IBM Flash system technology to IBM disk arrays. Individual results will vary.
11. Manages 300+ different storage devices / 700+ patents: http://www-03.ibm.com/press/us/en/pressrelease/46093.wss
12. Cleversafe named a leader in the IDC MarketScape for Object-Based Storage IDC MarketScape: Worldwide Object-Based Storage 2014 Vendor Assessment. Dec 2014. Doc # 253055
13. Object storage patents: https://www-03.ibm.com/press/us/en/pressrelease/47776.wss
14. 5-10X faster: http://www-03.ibm.com/press/us/en/pressrelease/45387.wss
15. 2.03X more query results is based on IBM internal testing of a sample analytic workload; current as of October 20, 2015. Performance improvement figures are cumulative of all queries in the workload.
Individual results will vary depending on individual workloads, configurations and conditions. IBM Power System S822LC; 20 cores / 80 threads, POWER8; 3.5GHz, 768 GB memory, DB2 10.5 / Ubuntu 14.04.
Competitive stack: Intel x86 2-socket server with 36 cores / 72 threads; 2xIntel E5-2699 v3; 2.3 GHz; 768 GB; DB2 10.5 / RHEL 7.2
16. Watson using OpenPOWER acceleration innovations is at nearly 2X faster when running retrieve and rank workloads: http://www-03.ibm.com/press/us/en/pressrelease/48075.wss
17. Based on vulnerabilities identified at https://nvd.nist.gov - Specific URL searches: https://nvd.nist.gov/ - https://web.nvd.nist.gov/view/vuln/search-results?query=powervm&search_type=last3years&cves=on
- https://web.nvd.nist.gov/view/vuln/search-results?query=vmware&search_type=last3years&cves=on
18. Results are based on IBM internal testing of single system running multiple virtual machines with Sysbench read only work load and are current as of October 18, 2015. Performance figures are based on
running 24 M record scale factor per VM. Individual results will vary depending on individual workloads, configurations and conditions.
IBM Power System S822LC; 20 cores / 160 threads, POWER8; 2.9 GHz, 256 GB memory MariaDB 10.0.19. Ubuntu 14.04.03, PowerKVM 3.1
Competitive stack: HP Proliant DL380 Gen9; 24 cores / 48 threads; Intel E5-2690 v3; 2.6 GHz; 128 GB memory, MariaDB 10.0.20. Ubuntu 14.04.03, KVM
Each system was configured to run at similar per VM throughput levels and number of VMs were increased for each system until total system throughput showed maximum throughput levels. Competitive
pricing was taken from available web-based pricing. For more information about MariaDB running on IBM Power Systems, go to: http://www-
304.ibm.com/partnerworld/wps/servlet/ContentHandler/stg_com_sys-ibm-power-systems-and-mariadb
Recommended