© 2012 IBM Corporation
Аппаратныерешениядля организацииколлективной
работыисоциального взаимодействия:
IBM Systems Power и IBM Systems Storage.
Сильнее. Разумнее. Надежнее.
СергейЛисин Специалистпоразвитиюбизнеса аппаратногообеспечения Sergey Lisin@ru ibm com
© 2012 IBM Corporation
Немного истории
© 2012 IBM Corporation
RISC RISC процессорыпроцессоры
1974-1978 – проект 801.
John Cocke – «отец» IBM RISC архитектуры
Source:JOHN COCKE AND V. MARKSTEIN –The evolutions of RICS technology at IBM
© 2012 IBM Corporation
ComputerWorld August 8 2012 http://www.computerworld.com/s/article/9230060/NASA_Your_smartphone_is_as_smart_as_the_Curiosity_rover
CBS News http://www.cbsnews.com/network/news/space/home/spacenews/files/081012_msl_update.html
«Because of this, he added that an Intel Core i7 processor, for example, wouldn't survive a day on Mars because of the extremes in temperature.»
The single-board computer aboard NASA's Curiosity rover is built around a PowerPC RAD750 microprocessor provided by BAE Systems.
RISC RISC процессорыпроцессоры нана МарсеМарсе
ЕстьЕсть лили жизньжизнь нана МарсеМарсе??
© 2012 IBM Corporation7
15%
20%
25%
30%
35%
40%
45%
50%
Q401
Q102
Q202
Q302
Q402
Q103
Q203
Q303
Q403
Q104
Q204
Q304
Q404
Q105
Q205
Q305
Q405
Q106
Q206
Q306
Q406
Q107
Q207
Q307
Q407
Q108
Q208
Q308
Q408
Q109
Q209
Q309
Q409
Q110
Q210
Q310
Q410
Q111
Q211
Q311
Q411
HP Sun/Oracle IBM
IBM’S 10-year march to UNIX leadership
UNIX Server Rolling Four Quarter Average Revenue Share
POWER4Dynamic LPARsDynamic LPARs
POWER6Live Partition Live Partition
MobilityMobilityPOWER5
MicroMicro--PartitioningPartitioning
POWER7Workload Optimized Workload Optimized
LeadershipLeadership
Source: IDC Worldwide Quarterly Server Tracker, http://www.idc.com/getdoc.jsp?containerId=IDC_P348
2Q12 R4Q53% share
+ 6.6 pts YTY
Oracle -24% YTY*
HP -16% YTY*
* As reported last fiscal quarter
Клиентывыбирают качественныерешения
© 2012 IBM Corporation
IBM POWER processor roadmapIBM POWER processor roadmap
2004 2001 2007 2010
POWER4/4+POWER4/4+
Dual CoreChip Multi ProcessingDistributed SwitchShared L2Dynamic LPARs (32)180nm, 130nm
POWER5/5+POWER5/5+
Dual Core & Quad Core MdEnhanced Scaling2 Thread SMTDistributed Switch +Core Parallelism +FP Performance +Memory bandwidth +130nm, 90nm
POWER6/6+POWER6/6+
Dual CoreHigh Frequencies Virtualization +Memory Subsystem +Altivec Instruction RetryDyn Energy Mgmt2 Thread SMT +Protection Keys65nm
POWER7/7+POWER7/7+
4,6,8 Core32MB On-Chip eDRAM Power Optimized CoresMem Subsystem ++4 Thread SMT++Reliability +VSM & VSXProtection Keys+45nm
POWER8POWER8
First Dual Core in Industry
HardwareVirtualizationfor Unix & Linux
Fastest ProcessorIn Industry
Most POWERful &ScalableProcessor inIndustry
Binary Compatible & Increased Core Performance
More CoresLarger Cache4th Gen SMTReliability ++Accelerators +more…22nm
High Level design completeand in implementation phase
Most POWERful, Scalableand Exclusive Performance
Power 7+ 32nmFasterVery large cacheAccelerators
IBM is the leader in Processor andServer design
~ 3годановое поколение~ 18месяцев “+” модели
© 2012 IBM Corporation11
POWER5 POWER5+ POWER6 POWER7 POWER7+Technology 130nm 90nm 65nm 45nm 32nm
Size 389 mm2 245 mm2 341 mm2 567 mm2 567 mm2
Transistors 276 M 276 M 790 M 1.2 B 2.1 BCores 2 2 2 8 8
Frequencies 1.65 GHz
1.9 GHz
4 - 5 GHz
3 – 4 GHz
3.6 – 4.4+ GHz
L2 Cache 1.9MB Shared 1.9MB Shared 4MB / Core 256 KBper Core
256 KBper Core
L3 Cache 36MB 36MB 32MB 4MB / Core 10MB / CoreMemory Cntrl 1 1 2 / 1 2 / 1 2 / 1 Architecture Out of Order Out of Order In of Order Out of Order Out of Order
LPAR 10 / Core 10 / Core 10 / Core 10 / Core 20 / Core
Дизайнпроцессоров IBM POWER
© 2012 IBM Corporation12
Преимущества eDRAM для POWER7+С
использова ниемeDRAM
Без eDRAM былобы
1Млрдтранзисторов567 mm2
5.4Млрдтранзисторов950 mm2
IBM’s eDRAM выигрыш:Большаяплотность: 1/3 площадиот 6T SRAMМеньшееэнергопотребление: 1/5
SRAMМеньшеошибок: в 250x меньшечемв
SRAMБольшаяпроизводительность
© 2012 IBM Corporation13
POWER7+ процесссорыи архитектура
13
До 40% большепроизводительности, идеальныдлятранзакционныхи бизнес-аналитическихнагрузокБольшая
масштабируемостьи гибкость
• 20 Виртуальныхмашиннаядро• Elastic Capacity on Demand
Выше производительност ь
• 10 MB L3 Cache• up to 4.4 GHz POWER7+ processors• Memory Compression Accelerator • Random number generator• Enhanced Single Precision Floating Point performance• Enhanced GX system bus
Улучшенная доступность
• Self-healing capability for L3 Cache functions• Dynamic processor fabric bus repair• Processor re-initialization• Hardware encryption support for AIX
Энергоэффективност
POWER7+ 32 nm
SMP Fabric
SMP Fabric
L3 Cache L3 Cache
L3 Cache L3 Cache
Core
L2
Core
L2
GXBus
Core
L2
Core
L2
Core
L2
Core
L2
Core
L2
AccEng
Power Bus
Core
L2
MC
MC
© 2012 IBM Corporation
Active Memory Expansion. Еще «больше» памяти
0
50
100
150
200
250125%
Возможностьрасширенияпамятидо 125%
КлиентполучаетбольшепамятииспользуяменьшересурсовPOWER7+
Большецикловпроцессорадляосновныхзадач
На 25% большепа
No AME P7 AME P7+ AME
14 29 October 2012
© 2012 IBM Corporation
Power 795
Портфолио IBM POWER Systems 2012
BladeCenterPS700/PS701/
PS702/PS703/PS704
Power 710 / 730
Power 720 / 740
Power 770
Power 780
Power 750
Power 755
Power 775
IBM PureFlex System
IBM Flex System p460
IBM Flex System p260
IBM Flex System p24L
© 2012 IBM Corporation27
high performance analytics, high performance computing & high performance UNIX
IBM WatsonПобедитель Jeopardy!
Power Systems – неограниченные системыдляинтенсивных вычислительныхнагрузок
1.7X more database
performance per core
125%more SAP SD Users than best Intel
LLNL SequoiaСамый быстрый Супекромпьтер
reduction in floor spacereduction in energy reduction in licensed cores
80% consolidation
PerformanceScalabilityVirtualizationAvailabilitySecurity
16petaflopsLLNL Sequoia
© 2012 IBM Corporation
Power Systems, PowerVM, AIX, IBM I, Linux, IBM SWТехнологииирешения, которые:
РазработанывместеПроизведенывместеПротестированывместеПоставляютсявместеПоддерживаютсявместе
0%
10%
20%
30%
40%
50%
60%
70%
80%
© 2012 IBM Corporation
Система хранения данных
IBM Storwize® V7000
© 2012 IBM Corporation30
VMWare optimizes the x86 server infrastructure. Now, consider doing the same for the storage infrastructure.
Virtual Server Infrastructure
ПолнаявиртуализацияИТ инфраструктуры
Virtual Storage Infrastructure
Tivoli Storage Productivity Center
Storage Hypervisor
Midrange Storwize V7000
Enterprise SAN Volume Controller
Manage
© 2012 IBM Corporation
© 2012 IBM Corporation
© 2012 IBM Corporation
Real-time Compression Экстраординарная эффективность• Новыйфункционал - Storwize V7000 Real-time Compression• Полнаяинтеграцияв Storwize V7000• Высокаяпроизводительностьдля всех типовнагрузки
• Real-time Compression builds on storage efficiency advantages of Storwize V7000
• Storwize V7000 Real-time Compression помогаетснизить использованиедисковойемкостидо 50% дляданныхкоторыенебылиещесжаты
• Компрессияпомогаетснизитьзатраты:- Наприобретение дополнительной емкости
- Наместовсерверной- Наохлаждение- Наприобретениелицензий
Компрессияпомогаетостановитьрост инфраструктурыхранения
© 2012 IBM Corporation
Storwize V7000 функционал
•Thin Provisioning (виртуальноевыделение дисковогопространства) – Включено
•FlashCopy (созданиеснимковиклоновтомов) – Включено
•Easy Tier (многоуровневоехранение) – Включено
•Data Migration(миграцияданных) – Включено
•Real-time Performance - Включено
•Metro and/or Global Mirror (удаленнаярепликация) – Опционально
•External Virtualization (виртуализациявешнихСХД)– Опционально
•Real time Compression(компрессияданных)
© 2012 IBM Corporation
IBM Systems DirectorEditions
IBM Smart Analytics System
IBM DB2 pureScale
IBM Lotus DominoConsolidation
on Power
IBM Rational Developer for Power
IBM WebSphere Application Server
Parallelization
SAP on IBM DB2 andPower Systems
Интегрированные решенияот IBM
© 2012 IBM Corporation
Спасибо!
© 2012 IBM Corporation
The IBM benchmarks results shown herein were derived using particular, well configured, development-level and generally-available computer systems. Buyers should consult other sources of information to evaluate the performance of systems they are considering buying and should consider conducting application oriented testing. For additional information about the benchmarks, values and systems tested, contact your local IBM office or IBM authorized reseller or access the Web site of the benchmark consortium or benchmark vendor.
IBM benchmark results can be found in the IBM Power Systems Performance Report at http://www.ibm.com/systems/p/hardware/system_perf.html .
All performance measurements were made with AIX or AIX 5L operating systems unless otherwise indicated to have used Linux. For new and upgraded systems, the latest versions of AIX were used. All other systems used previous versions of AIX. The SPEC CPU2006, LINPACK, and Technical Computing benchmarks were compiled using IBM's high performance C, C++, and FORTRAN compilers for AIX 5L and Linux. For new and upgraded systems, the latest versions of these compilers were used: XL C for AIX v11.1, XL C/C++ for AIX v11.1, XL FORTRAN for AIX v13.1, XL C/C++ for Linux v11.1, and XL FORTRAN for Linux v13.1.
For a definition/explanation of each benchmark and the full list of detailed results, visit the Web site of the benchmark consortium or benchmark vendor.
TPC http://www.tpc.orgSPEC http://www.spec.orgLINPACK http://www.netlib.org/benchmark/performance.pdfPro/E http://www.proe.comGPC http://www.spec.org/gpcVolanoMark http://www.volano.comSTREAM http://www.cs.virginia.edu/stream/SAP http://www.sap.com/benchmark/Oracle, Siebel, PeopleSoft http://www.oracle.com/apps_benchmark/Baan http://www.ssaglobal.comFluent http://www.fluent.com/software/fluent/index.htmTOP500 Supercomputers http://www.top500.org/Ideas International http://www.ideasinternational.com/benchmark/bench.htmlStorage Performance Council http://www.storageperformance.org/results
Revised December 2, 2010
Notes on benchmarks and values
29 October 201237
© 2012 IBM Corporation
Revised December 2, 2010
Notes on HPC benchmarks and valuesThe IBM benchmarks results shown herein were derived using particular, well configured, development-level and generally-available computer systems. Buyers should consult other sources of information to evaluate the performance of systems they are considering buying and should consider conducting application oriented testing. For additional information about the benchmarks, values and systems tested, contact your local IBM office or IBM authorized reseller or access the Web site of the benchmark consortium or benchmark vendor.
IBM benchmark results can be found in the IBM Power Systems Performance Report at http://www.ibm.com/systems/p/hardware/system_perf.html .
All performance measurements were made with AIX or AIX 5L operating systems unless otherwise indicated to have used Linux. For new and upgraded systems, the latest versions of AIX were used. All other systems used previous versions of AIX. The SPEC CPU2006, LINPACK, and Technical Computing benchmarks were compiled using IBM's high performance C, C++, and FORTRAN compilers for AIX 5L and Linux. For new and upgraded systems, the latest versions of these compilers were used: XL C for AIX v11.1, XL C/C++ for AIX v11.1, XL FORTRAN for AIX v13.1, XL C/C++ for Linux v11.1, and XL FORTRAN for Linux v13.1. Linpack HPC (Highly Parallel Computing) used the current versions of the IBM Engineering and Scientific Subroutine Library (ESSL). For Power7 systems, IBM Engineering and Scientific Subroutine Library (ESSL) for AIX Version 5.1 and IBM Engineering and Scientific Subroutine Library (ESSL) for Linux Version 5.1 were used.
For a definition/explanation of each benchmark and the full list of detailed results, visit the Web site of the benchmark consortium or benchmark vendor.SPEC http://www.spec.orgLINPACK http://www.netlib.org/benchmark/performance.pdfPro/E http://www.proe.comGPC http://www.spec.org/gpcSTREAM http://www.cs.virginia.edu/stream/Fluent http://www.fluent.com/software/fluent/index.htmTOP500 Supercomputers http://www.top500.org/AMBER http://amber.scripps.edu/FLUENT http://www.fluent.com/software/fluent/fl5bench/index.htmGAMESS http://www.msg.chem.iastate.edu/gamessGAUSSIAN http://www.gaussian.comANSYS http://www.ansys.com/services/hardware-support-db.htm
Click on the "Benchmarks" icon on the left hand side frame to expand. Click on "Benchmark Results in a Table" icon for benchmark results.ABAQUS http://www.simulia.com/support/v68/v68_performance.phpECLIPSE http://www.sis.slb.com/content/software/simulation/index.asp?seg=geoquest&MM5 http://www.mmm.ucar.edu/mm5/MSC.NASTRAN http://www.mscsoftware.com/support/prod%5Fsupport/nastran/performance/v04_sngl.cfmSTAR-CD www.cd-adapco.com/products/STAR-CD/performance/320/index/htmlNAMD http://www.ks.uiuc.edu/Research/namdHMMER http://hmmer.janelia.org/
http://powerdev.osuosl.org/project/hmmerAltivecGen2mod
29 October 201238
© 2012 IBM Corporation
Revised April 2, 2007
Notes on performance estimatesrPerf for AIX
rPerf (Relative Performance) is an estimate of commercial processing performance relative to other IBM UNIX systems. It is derived from an IBM analytical model which uses characteristics from IBM internal workloads, TPC and SPEC benchmarks. The rPerf model is not intended to represent any specific public benchmark results and should not be reasonably used in that way. The model simulates some of the system operations such as CPU, cache and memory. However, the model does not simulate disk or network I/O operations.
rPerf estimates are calculated based on systems with the latest levels of AIX and other pertinent software at the time of system announcement. Actual performance will vary based on application and configuration specifics. The IBM eServerpSeries 640 is the baseline reference system and has a value of 1.0. Although rPerf may be used to approximate relative IBM UNIX commercial processing performance, actual system performance may vary and is dependent upon many factors including system hardware configuration and software design and configuration. Note that the rPerf methodology used for the POWER6 systems is identical to that used for the POWER5 systems. Variations in incremental system performance may be observed in commercial workloads due to changes in the underlying system architecture.
All performance estimates are provided "AS IS" and no warranties or guarantees are expressed or implied by IBM. Buyers should consult other sources of information, including system benchmarks, and application sizing guides to evaluate the performance of a system they are considering buying. For additional information about rPerf, contact your local IBM office or IBM authorized reseller.
========================================================================
CPW for IBM i
Commercial Processing Workload (CPW) is a relative measure of performance of processors running the IBM i operating system. Performance in customer environments may vary. The value is based on maximum configurations. More performance information is available in the Performance Capabilities Reference at: www.ibm.com/systems/i/solutions/perfmgmt/resource.html
29 October 201239