POWER8 Sales Certification-Day1

IBM POWER8 Sales Certification
Day 1
John Banchy
Systems Architect
Version 4
IBM Corporation, 2015

POWER8 Sales Certification Agenda
Day 1 Day 2 Day 3

POWER8 Virtualization Power Cloud
Announcement Capacity on demand OpenStack
overview
Enterprise pools EnergyScale
Server details
Availability GlobalFoundries
POWER8 data design
Security Scale-up vs. Out
IBM Data Engine for
Analytics OpenPOWER
DB2 with BLU Accelerators
extensions Linux
2 IBM Corporation, 2015

3 $2.4B $1B
Years of In Direct In Linux and
Development Investment Open Technologies
100s 4.2 $3B

Of Billion Future Chip
Patents Transistors Research

Innovation Drives Performance
100%
Gain by Innovation
80% Gain by Technology Scaling
60%
40%
20%
0%
180 nm 130 nm 90 nm 65 nm 45 nm 32 nm 22 nm
P4 P4+ P5+ P6 P7 P7+ P8
Source: An Introduction to POWER8 Processor, Dr. Joel Tendler, IBM Corporation

IBM Research - 7 Nanometer and Beyond
Carbon Nanotubes
IBM demonstrated a 10,000 transistor chip
IBM demonstrated a 9nm transistor
5x-10x better performance
Graphene
IBM demonstrated a 100 GHz transistor
IBM demonstrated a functional circuit
10,000x better performance

Power - Continuous System Innovation
2004 2007 2010 2014
POWER5/5+ POWER6/6+ POWER7/7+ POWER8

130/90 nm 65/65 nm 45/32 nm 22 nm
64 cores 8-core chips 256 cores 12-core chips
4TB memory 8TB memory 16TB memory 8-way SMT
Micro-partitioning Larger L2 8-core chips CAPI
Virtual I/O Up to 5.0 GHz 80 MB on-chip Over 19MB cache
Unified POWER On-chip L3 eDRAM L3 cache per core
virtualization controller 4-way SMT Transactional
2-way SMT Dynamic CPU Enterprise pools memory
On-chip memory sparing Hypervisor memory Multi-path
controller Partition mobility mirroring interconnect
Storage keys Spare DRAMs PCIe Gen3
On-chip controller

For 22 Straight Years, IBM Leads in Patents
2014 U.S. Patents

8,000 7534
7,000
6,000
5,000
4,000 #1
2829
3,000 2566
2,000 1578 1474
1,000 804
0
IBM Microsoft Google Intel HP Oracle
Source: http://www.ificlaims.com/index.php?page=misc_top_50_2014, as of January 12, 2015

IBM POWER9, NVIDIA, and Mellanox
$325M supercomputer contract

Expected on-line in 2017
Oak Ridge National Labs

Lawrence Livermore
National Labs
US Department of Energy
Courtesy of Oak Ridge National Laboratory, U.S. Dept. of Energy

POWER8 Announcement Focus
Optimized for Open Innovation Superior Cloud

Data Platform Economics

POWER8
Announcement Highlights

POWER8 Chips
Scale Out Systems Enterprise Systems

Dual Chip Module Single Chip Module
6 Cores per Chip 12 Cores per Chip

POWER8 Scale-Out Family
S822 S814 S824

1 or 2 socket, 2U 1 socket, 4U 2 socket, 4U
Up to 20 cores Up to 8 cores Up to 24 cores
S812L S822L S824L

1 socket, 2U, Linux 2 socket, 2U, Linux 2 socket, 4U, Linux
Up to 12 cores Up to 24 cores Up to 24 cores

POWER8 E870 and E880 Nodes
EXP24S SAS Drawers (2U)
24 SFF SSD/HDD
Connects via 2 SAS adapters
PCIe I/O Drawers (4U)

12 PCIe expansion slots
Connects via 2 PCIe adapter slots
System Control Unit (2U)
System Nodes (5U)

32 48 cores / node
32 DIMM slots / node
8 PCIe Gen3 I/O slots / node
19-inch Rack
(E880 Shown)

POWER8 Enterprise E870 and E880
Node 4 E870 E880
32-core 40-core 32-core 48-core

Node 4.02 4.19 4.35 2015
Node 1 GHz GHz GHz SOD *
System 1 32 40 32 48
Control Node cores cores cores SOD
Unit 2 64 80 64 96
Nodes cores cores cores SOD
Node 2
3 96 144
Nodes SOD SOD
Node 3 4 128 192

Nodes SOD SOD
* IBM Statement of Direction for 2015. For more details see the IBM Power E880 Announcement Letter released on October 6, 2014. IBMs
statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBMs sole discretion.
Server Details

POWER8 S824
System (8286-42A) 4U
One or two 6-core 3.89 GHz
POWER8
One or two 8-core 4.15 GHz
Processors
Two 12-core 3.52 GHz
Sockets 1 or 2
512 GB (1S)
Max Memory
1 TB (2S)
Media Bays 1 slim line DVD

Four x16 + Seven x8 PCIe Gen3
Integrated PCIe
1 x8 slot must have 4-port Ethernet
12 SFF Disk/SSD
Internal SAS Bays
or 18 SFF and 8 SSD
Max I/O Drawers* SOD PCIe Gen3
Max PCIe Slots 11 (Without I/O Drawers)
* Statements of direction for 2015
All statements regarding IBM future direction and intent are subject to change or withdrawal without notice.
POWER8 S814
One 4-core 3.02 GHz (rack/tower)
POWER8
One 6-core 3.02 GHz (rack/tower)
Processors
One 8-core 3.72 GHz (rack)
Sockets 1
64 GB (4-core)
Max Memory
512 GB (6 or 8-core)

Two x16 + Five x8 PCIe Gen3
Integrated PCIe
12 SFF Disk/SSD
Internal SAS Bays
or 18 SFF Disk/SSD (6 or 8 core)
Max I/O Drawers* SOD PCIe Gen3 6/8 core models
POWER8 S822
POWER8 One or two 6-core 3.89 GHz

Processors One or two 10-core 3.42 GHz
Sockets 1 or 2
512 GB (1S)
Max Memory
1 TB (2S)

Four x16 + Five x8 PCIe Gen3
Integrated PCIe
12 SFF Disk/SSD
Internal SAS Bays
Or 8 SFF Disk/SSD + 6 SSD
POWER8 S824L
System (8247-42L) 4U
POWER8 Two 10-core 3.42 GHz

Processors Two 12-core 3.02 GHz
Sockets 2
Max Memory 1 TB

Four x16 + Seven x8 PCIe Gen3
Integrated PCIe
Internal SAS Bays 12 SFF Disk/SSD
POWER8 S812L
POWER8 One 10-core 3.42 GHz

Processors One 12-core 3.02 GHz
Sockets 1
Max Memory 512 GB

Two x16 + Four x8 PCIe Gen3
Integrated PCIe
12 SFF Disk/SSD
Internal SAS Bays
POWER8 S822L
POWER8 Two 10-core 3.42 GHz

Processors Two 12-core 3.02 GHz
Sockets 1 or 2
Max Memory 1 TB

Four x16 + Five x8 PCIe Gen3
Integrated PCIe
12 SFF Disk/SSD
Internal SAS Bays
POWER8 E880
9119-MHE Building Block System Maximum
POWER8 32 x 4.35 GHz 128 x 4.35 GHz
Processors 48 POWER8 * 192 POWER8 *
Sockets 4 8 going to 16 *
64 DDR3 1600 MHz

32 DDR3 1600 MHz DIMMs, Up to 8 TB
Max Memory
DIMMs, Up to 4 TB Increasing to 128
DIMMs and 16 TB*
DVD Bays 1 1
Max Disk Drawer 32, 64,

(24 SFF bays) Increasing to 128* Increasing to 256*
Integrated PCIe 8 PCIe Gen3 x16 16 going to 32*

Max I/O Drawers* 2 going to 4* 4 going to 16*
Max PCIe Slots* 24 going to 48* 48 going to 192*

POWER8 E870
9119-MME Building Block System Maximum
POWER8 32 x 4.02 GHz 64 x 4.02 GHz
Processors 40 x 4.19 GHz 80 x 4.19 GHz
Sockets 4 8
32 DDR3 1600 MHz 64 DDR3 1600 MHz

Max Memory DIMMs, Up to 2 TB DIMMs, Up to 4 TB
Increasing to 4 TB* Increasing to 8 TB*
DVD Bays 1 1
Max Disk
Drawers 64 64
(24 SFF bays)
Integrated PCIe 8 PCIe Gen3 x16 16 PCIe Gen3 x16
Max I/O Drawers* 2 going to 4* 4 going to 8 *
Max PCIe Slots* 24 going to 48* 48 going to 96*

POWER8 System Control Unit
Power Hot-Plug Power
Ports Clock Batteries Ports
Right-half
Left-half
Service Clock Clock Service

Processor Card Card Card Processor Card
HMC Ports HMC Ports
Improves availability of all E870 and E880 configurations

Redundant Power to System Control Unit
Power Power System

Supply Supply Node 1
Left Right
System
FSP Clock Clock FSP
Card Card Card Card Control Unit
Power Power System

Supply Supply Node 2

POWER8 E870 and E880 I/O Drawer
PCIe Optical Interface to System Node
Dual
Power
Cords
Fan-out Module Fan-out Module

6 PCIe Gen3 slots 6 PCIe Gen3 slots
4 x8 and 2 x16 4 x8 and 2 x16

POWER8 Enterprise I/O Drawers
System
Node

Statement
POWER8 Enterprise I/O Drawers of Direction
System
Node
IBMs statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBMs sole discretion.
EXP24S SFF Gen2-bay Drawer
(24) 2.5 inch hot-swap

SAS or SSD disks
Ordered as 1,2, or 4 Front

sets of disks*
Redundant power
Rear
* Applies to orders for AIX, Linux, and VIOS, IBM i is ordered as 1 set
Optimized for Data

POWER8 Optimized for Data
Systems of Systems of Systems of

Record Insight Engagement

Systems of Record
Core to business
Update transactional
High volume
Secure

Systems of Insight
Competitive advantage
Ubiquitous
Large data footprint
Unpredictable

Systems of Engagement
Competitive advantage
Anytime, anywhere
Untrusted devices
Exposes internal IT

Systems of Record - Performance
Batch
System of Record Performance is About Minimizing Waiting

Cache is Critical to Good Performance
Memory is slow
1
clock cycle
Core relative to
cache
1-100
Cache
clock cycles
400-800
Memory
clock cycles

Real Workloads Benefit from Large Caches
Ejected New
Cache
Multiple Working Sets

Industry Benchmarks Dont Stress Caches
Cache
Single Working Set

POWER8 Four Level Cache Design
C C C C C C
Mem L4 L4 Mem
L1 L1 L1 L1 L1 L1
L2 L2 L2 L2 L2 L2
Mem L4 L4 Mem
Shared L3 Cache
Mem L4 L4 Mem
L2 L2 L2 L2 L2 L2
L1 L1 L1 L1 L1 L1
Mem L4 L4 Mem
C C C C C C

Workloads That Benefit From Large Caches
Single thread sensitive

Transactions that lock data
Core
Long running batch
Shared or mixed environments

Cache Shared data
Virtualized environments
Many concurrent threads
Other
Large working sets
Memory Write burst traffic
Mixed reads and writes

Cache and Core Speed
Core L1 and L2 Approximate

Frequency Cache per Cache per
Chip Family (GHz) Core Core (MB)
64 KB
Intel EN E5-v2 (8+ core) 1.7 2.4 2.81
256 KB
64 KB
Intel EP E5-v3 (8+ core) 1.8 3.2 2.81
256 KB
64 KB
Intel E7-v2 (8+ core) 2.0 3.2 2.81
256 KB
96 KB
POWER8 (8+ core) 3.4 4.35 19.27
512 KB
224 KB
IBM z13 5.0 32.22
4 MB

POWER7 Low Latency Interconnect
On-Module Off-Module
1 Hop 1 to 3 Hops

POWER8 Lower Latency Improves Scaling
Maximum of 2 hops

POWER8 Two Hop Alternative
Multiple alternatives allows greater concurrency

Single Thread Performance is Increasing
82
64
56
+14 % +28%
POWER7 740 POWER7+ 740 POWER8 S824

3.7 GHz 4.2 GHz 4.1 GHz
8 Cores 8 Cores 8 Cores
SMT1 SMT1 SMT1
Performance measured in rperfs

Acquiring Locks has Trade-Offs
Course Grain Fine Grain

(Throughput Risk) (Deadlock Risk)
A A
B B
C C
D D
E E

Transactional Memory Improves Throughput
T1 T2 T3 T1 T2 T3
Restart
Time
Traditional Locking Transactional Memory

Parallel Workloads
Systems of Insight
Systems of Engagement

Threading to Match Workload Needs
Set at LPAR level 2.65
Dynamically shift between

2.23
modes as needed
Hardware enforced fairness 1.59
1.00
SMT1 SMT2 SMT4 SMT8

POWER8 More Than 2X Peak I/O Bandwidth
POWER7+ POWER8
x x x x
GX++ PCIe Gen3 x16 8 1 8 1 PCIe Gen3 x8
(2) 20 GB/s (2) 32 GB/s 6 6 (2) 16 GB/s
40 GB/s 96 GB/s
Peak Bandwidth Peak Bandwidth

POWER8 Peak I/O Bandwidth
POWER8 SCM POWER8 DCM
x x x x x x
PCIe Gen3 x16 1 1 PCIe Gen3 x16 8 1 8 1 PCIe Gen3 x8
(2) 32 GB/s 6 6 (2) 32 GB/s 6 6 (2) 16 GB/s
64 GB/s 96 GB/s
Peak Bandwidth Peak Bandwidth

Peak I/O Bandwidth (2-Socket Example)
POWER8
192 GB/s
S824
POWER7+
60 GB/s
740
POWER7
50 GB/s
740
0 50 100 150 200

I/O Bandwidth (GB/s)

Designed for Memory Intensive Workloads
DRAM Memory Up to 1 TB per socket
Chips Buffer Up to 230 GB/s sustained
Consistent speed
POWER8
Large in-memory databases Train of thought analytics

Large virtualized environments Data-in-motion analytics

Sustained Memory Bandwidth per Socket
POWER8
230 GB/s
Enterprise
POWER7 68 GB/s
32
POWER6
GB/s
0 50 100 150 200 250

Memory Bandwidth (GB/s)

Bandwidth and Threading
Memory Peak I/O Threads

Bandwidth Bandwidth per
Chip Family per Socket per Socket Core
Intel EN E5-v2 (8+ core) 38.4 GB/s 48 GB/s 1, 2
Intel EP E5-v3 (8+ core) 68 GB/s 80 GB/s 1, 2
Intel E7-v2 (8+ core) 85 GB/s 64 GB/s 1, 2
POWER8 (S Models) 192 GB/s 96 GB/s 1, 2, 4, 8
POWER8 (E Models) 230 GB/s 64 GB/s 1, 2, 4, 8

Chip Transistor Budget
POWER8 (8.7B Equivalent) Intel Haswell (5.6B)

Fewer bigger cores More smaller cores
Large scale virtualization Light weight virtualization
EMR, ERP, database Core centric workloads
Core based software

Bandwidth is Central to Big Data
Read and write

data to and from
Memory
memory
multiple times
CPU
Read and write
data to and from
network or storage

Traditional Hadoop Architecture
1 Gb Ethernet
Large
Memory Memory Memory number of
nodes
Scale server
and disk
together
Replicated
local disk

IBM Data Engine for Analytics
Memory Memory
GZIP
Compression 10 Gb Ethernet
Accelerator
1/3 1/2
Spectrum
Of the Storage Number of Servers
Scale (TeraSort Benchmark)

Analytics Are Moving to Real-Time
Later
Pre-Defined Real-Time
Limited user mix Broad user mix
Historical data Actionable data
Batch like queries Speed matters
Human tuned Self optimizing

DB2 BLU: Speed of Thought Analytics
Avoid examining data
Efficient use of memory
Actionable compression
Exploit POWER8 parallelism
Exploit POWER8 hardware

Avoid Examining Data
c1 c2 c3 c4 c5 c6 Columnar store
Compression
Data skipping
No indexes

Efficient Use of Memory
Data In Raw
Memory Data
Compressed columnar store Scan friendly caching

Actionable Compression
Data In Data In Data On

Use Memory Disk

Exploit POWER8 Parallelism
POWER8 Single
POWER8 Threading
Instruction Multiple Data
64 Registers vs.16 on Intel
A B C D
Compare
B
Result

Exploit POWER8 Hardware
Up to 230 GB/s sustained memory

bandwidth per socket
Up to 96 GB/s peak I/O bandwidth

per socket
Up to 4.35 GHz processors
Optimized for POWER8 cache sizes
IBM FlashSystem for added performance

DB2 BLU on POWER8 Results
With DB2 BLU Acceleration and POWER8

hardware, we observed an average
82X performance improvement of 82 times on

report generation compared to competitor
running on x86 platform.
Based on IBM internal tests as of April 7, 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 S824, 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 calculation based on geometric mean calculation giving equal weighting to the report per hour (RPH) improvements in the three categories of
simple, intermediate, and complex reports. GEOMEAN(RPH_simple,RPH_intermediate,RPH_complex) = GEOMEAN(18.85,40.07,747.63)=82.66

What Does This Mean to You?
Better real-world Happier more productive users, more speed-

performance of-thought analytics, more transactions
Less on-going
More productive staff
tuning
IBM Data Engine
Fewer servers, less storage, lower cost
for Analytics

End of
Day 1

Special Notices
This document was developed for IBM offerings in the United States as of the date of publication. IBM may not make
these offerings available in other countries, and the information is subject to change without notice. Consult your local
IBM business contact for information on the IBM offerings available in your area.
Information in this document concerning non-IBM products was obtained from the suppliers of these products or other
public sources. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those
products.
IBM may have patents or pending patent applications covering subject matter in this document. The furnishing of this
document does not give you any license to these patents. Send license inquires, in writing, to IBM Director of Licensing,
IBM Corporation, New Castle Drive, Armonk, NY 10504-1785 USA.
All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and
represent goals and objectives only.
The information contained in this document has not been submitted to any formal IBM test and is provided "AS IS" with
no warranties or guarantees either expressed or implied.
All examples cited or described in this document are presented as illustrations of the manner in which some IBM
products can be used and the results that may be achieved. Actual environmental costs and performance
characteristics will vary depending on individual client configurations and conditions.
IBM Global Financing offerings are provided through IBM Credit Corporation in the United States and other IBM
subsidiaries and divisions worldwide to qualified commercial and government clients. Rates are based on a client's
credit rating, financing terms, offering type, equipment type and options, and may vary by country. Other restrictions
may apply. Rates and offerings are subject to change, extension or withdrawal without notice.
IBM is not responsible for printing errors in this document that result in pricing or information inaccuracies.
IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty
terms apply.
Any performance data contained in this document was determined in a controlled environment. Actual results may vary
significantly and are dependent on many factors including system hardware configuration and software design and
configuration. Some measurements quoted in this document may have been made on development-level systems.
There is no guarantee these measurements will be the same on generally- available systems. Some measurements
quoted in this document may have been estimated through extrapolation. Users of this document should verify the
applicable data for their specific environment.
Revised November 28, 2012

Special Notices Continued
IBM, the IBM logo, ibm.com AIX, AIX (logo), AIX 5L, AIX 6 (logo), AS/400, BladeCenter, Blue Gene, ClusterProven, DB2, ESCON, i5/OS, i5/OS (logo),
IBM Business Partner (logo), IntelliStation, LoadLeveler, Lotus, Lotus Notes, Notes, Operating System/400, OS/400, PartnerLink, PartnerWorld,
PowerPC, pSeries, Rational, RISC System/6000, RS/6000, THINK, Tivoli, Tivoli (logo), Tivoli Management Environment, WebSphere, xSeries, z/OS,
zSeries, Active Memory, Balanced Warehouse, CacheFlow, Cool Blue, IBM Watson, IBM Systems Director VMControl, pureScale, TurboCore,
Chiphopper, Cloudscape, DB2 Universal Database, DS4000, DS6000, DS8000, EnergyScale, Enterprise Workload Manager, General Parallel File
System, , GPFS, HACMP, HACMP/6000, HASM, IBM Systems Director Active Energy Manager, iSeries, Micro-Partitioning, POWER, PowerLinux,
PowerExecutive, PowerVM, PowerVM (logo), PowerHA, Power Architecture, Power Everywhere, Power Family, POWER Hypervisor, Power Systems,
Power Systems (logo), Power Systems Software, Power Systems Software (logo), POWER2, POWER3, POWER4, POWER4+, POWER5, POWER5+,
POWER6, POWER6+, POWER7, POWER7+, POWER8, Systems, System i, System p, System p5, System Storage, System z, TME 10, Workload
Partitions Manager and X-Architecture are trademarks or registered trademarks of International Business Machines Corporation in the United States,
other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol ( or
TM), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may
also be registered or common law trademarks in other countries.
A full list of U.S. trademarks owned by IBM may be found at: http://www.ibm.com/legal/copytrade.shtml.
Adobe, the Adobe logo, PostScript, and the PostScript logo are either registered trademarks or trademarks of Adobe Systems Incorporated in the United
States, and/or other countries.
AltiVec is a trademark of Freescale Semiconductor, Inc.
AMD Opteron is a trademark of Advanced Micro Devices, Inc.
InfiniBand, InfiniBand Trade Association and the InfiniBand design marks are trademarks and/or service marks of the InfiniBand Trade Association.
Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are
trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries.
IT Infrastructure Library is a registered trademark of the Central Computer and Telecommunications Agency which is now part of the Office of
Government Commerce. Java and all Java-based trademarks and logos are trademarks or registered trademarks of Oracle and/or its affiliates.
Linear Tape-Open, LTO, the LTO Logo, Ultrium, and the Ultrium logo are trademarks of HP, IBM Corp. and Quantum in the U.S. and other countries.
Linux is a registered trademark of Linus Torvalds in the United States, other countries or both.
PowerLinuxTM uses the registered trademark Linux pursuant to a sublicense from LMI, the exclusive licensee of Linus Torvalds, owner of the Linux
mark on a worldwide basis.
Microsoft, Windows and the Windows logo are registered trademarks of Microsoft Corporation in the United States, other countries or both.
NetBench is a registered trademark of Ziff Davis Media in the United States, other countries or both.
SPECint, SPECfp, SPECjbb, SPECweb, SPECjAppServer, SPEC OMP, SPECviewperf, SPECapc, SPEChpc, SPECjvm, SPECmail, SPECimap and
SPECsfs are trademarks of the Standard Performance Evaluation Corp (SPEC).
The Power Architecture and Power.org wordmarks and the Power and Power.org logos and related marks are trademarks and service marks licensed by
Power.org. TPC-C and TPC-H are trademarks of the Transaction Performance Processing Council (TPPC).
UNIX is a registered trademark of The Open Group in the United States, other countries or both.
Other company, product and service names may be trademarks or service marks of others.
Revised November 28, 2012

POWER8 Sales Certification-Day1

Transféré par

Informations du document

Titre original

Copyright

Formats disponibles

Partager ce document

Partager ou intégrer le document

Options de partage

Avez-vous trouvé ce document utile ?

Ce contenu est-il inapproprié ?

Droits d'auteur :

Formats disponibles

POWER8 Sales Certification-Day1

Transféré par

Droits d'auteur :

Formats disponibles

IBM POWER8 Sales Certification

IBM Corporation, 2015

Day 1 Day 2 Day 3

2 IBM Corporation, 2015

100s 4.2 $3B

3 IBM Corporation, 2015

Source: An Introduction to POWER8 Processor, Dr. Joel Tendler, IBM Corporation

5 IBM Corporation, 2015

POWER5/5+ POWER6/6+ POWER7/7+ POWER8

6 IBM Corporation, 2015

2014 U.S. Patents

Source: http://www.ificlaims.com/index.php?page=misc_top_50_2014, as of January 12, 2015

$325M supercomputer contract

Oak Ridge National Labs

Courtesy of Oak Ridge National Laboratory, U.S. Dept. of Energy

Optimized for Open Innovation Superior Cloud

9 IBM Corporation, 2015

10 IBM Corporation, 2015

Scale Out Systems Enterprise Systems

11 IBM Corporation, 2015

S822 S814 S824

S812L S822L S824L

12 IBM Corporation, 2015

PCIe I/O Drawers (4U)

System Control Unit (2U)

System Nodes (5U)

13 IBM Corporation, 2015

Node 4 E870 E880

32-core 40-core 32-core 48-core

Node 3 4 128 192

15 IBM Corporation, 2015

Media Bays 1 slim line DVD

* Statements of direction for 2015

Media Bays 1 slim line DVD

* Statements of direction for 2015

POWER8 One or two 6-core 3.89 GHz

Media Bays 1 slim line DVD

* Statements of direction for 2015

POWER8 Two 10-core 3.42 GHz

Media Bays 1 slim line DVD

* Statements of direction for 2015

POWER8 One 10-core 3.42 GHz

Max Memory 512 GB

Media Bays 1 slim line DVD

* Statements of direction for 2015

POWER8 Two 10-core 3.42 GHz

Media Bays 1 slim line DVD

* Statements of direction for 2015

64 DDR3 1600 MHz

Max Disk Drawer 32, 64,

Integrated PCIe 8 PCIe Gen3 x16 16 going to 32*

* Statements of direction for 2015

32 DDR3 1600 MHz 64 DDR3 1600 MHz

* Statements of direction for 2015

Service Clock Clock Service

Improves availability of all E870 and E880 configurations

24 IBM Corporation, 2015

Power Power System

Power Power System

25 IBM Corporation, 2015

PCIe Optical Interface to System Node

Fan-out Module Fan-out Module

26 IBM Corporation, 2015