IBM Power Systems:представляем процессоры POWER7+и новое поколение серверов класса предприятия

Алексей БойкоPOWER Product ManagerAlexey.Boyko@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

RISC RISC процессорыпроцессоры

Фиксированная длина машинных инструкций (например, 32/64 бита) и простой формат команды.

Специализированные команды для операций с памятью — чтения или записи.

Операции вида «прочитать-изменить-записать» отсутствуют.

Любые операции «изменить» выполняются только над содержимым регистров (т. н. архитектура load-and-store).

Большое количество регистров общего назначения (32 и более).

Отсутствие поддержки операций вида «изменить» над укороченными типами данных — байт, 16-битное словами.

Отсутствие микропрограмм внутри самого процессора.

Характерные особенности RISC-процессоров

© 2012 IBM Corporation

RISC RISC процессорыпроцессоры *ARM (Adwanced RISC Machines)— Apple iPods /iPhone/iPad Palm and PocketPC PDAs RIM BlackBerry smartphone/email devices Nintendo HTC(Qualcom proc) *PowerPC (Apple–IBM–Motorola alliance) *Motorola 68000 *MIPS(SGI computers and the PlayStation, PlayStation 2, Nintendo 64, PlayStation Portable game consoles) *IBM POWER(IBM's supercomputers, midrange servers and workstations, in Nintendo's Gamecube and Wii, Microsoft's Xbox 360 and Sony's PlayStation 3 game consoles, EMC's DMX range of the Symmetrix SAN, and in many embedded applications like printers and cars. * SPARC, by Oracle/Sun Microsystems and Fujitsu * Hewlett-Packard's PA-RISC, also known as HP-PA * Alpha * Hitachi's SuperH

© 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 на Марсена МарсеЕсть ли жизнь на Марсе?Есть ли жизнь на Марсе?

© 2012 IBM Corporation7

15%

20%

25%

30%

35%

40%

45%

50%

Q401Q10

2Q20

2Q30

2Q40

2Q10

3Q20

3Q30

3Q40

3Q10

4Q20

4Q30

4Q40

4Q10

5Q20

5Q30

5Q40

5Q10

6Q20

6Q30

6Q40

6Q10

7Q20

7Q30

7Q40

7Q10

8Q20

8Q30

8Q40

8Q10

9Q20

9Q30

9Q40

9Q11

0Q21

0Q31

0Q41

0Q11

1Q21

1Q31

1Q41

1

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

Micro-PartitioningMicro-Partitioning

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

Клиенты выбирают качественные решения

© 2012 IBM Corporation

IBM POWER processor roadmapIBM POWER processor roadmap

2004 2001 2007 2010

POWER4/4+POWER4/4+

Dual Core Chip Multi

Processing Distributed Switch Shared L2 Dynamic 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 Core High Frequencies Virtualization + Memory Subsystem

+ Altivec Instruction Retry Dyn Energy Mgmt 2 Thread SMT + Protection Keys 65nm

POWER7/7+POWER7/7+

4,6,8 Core 32MB On-Chip

eDRAM Power Optimized

Cores Mem Subsystem +

+ 4 Thread SMT++ Reliability + VSM & VSX Protection Keys+ 45nm

POWER8POWER8

First Dual Corein Industry

HardwareVirtualizationfor Unix & Linux

FastestProcessorIn Industry

MostPOWERful &ScalableProcessor inIndustry

Binary Compatible & Increased Core Performance

More Cores Larger Cache 4th Gen SMT Reliability ++ Accelerators + more… 22nmHigh Level design

completeand in implementation

phase

MostPOWERful, Scalableand ExclusivePerformance

Power 7+ 32nm Faster Very large

cache Accelerators

IBM is the leaderin Processor andServer design

~ 3года новое поколение~ 18месяцев “+” модели~ 3года новое поколение~ 18месяцев “+” модели

© 2012 IBM Corporation9

POWER7+32 nm

POWER7+

POWER745 nm

POWER732 nm

В 2.5 раза больше L3 cacheOn chip аппаратные ускорители

© 2012 IBM Corporation10

SMP Fabric

SMP Fabric

POWER7+ Design

Core

L2

Core

L2

GX

Bus

Core

L2

Core

L2

Core

L2

AccEng

Power Bus

Core

L2

MC

MC

L3 Cache L3 Cache

L3 Cache L3 Cache

Core

L2

Core

L2

Physical Design:• 8 cores with integrated Cache, Memory Controllers, and Accelerators• 3 / 4 / 6 / 8 Core options• 32nm technology

Features:• 2.5X increase in L3 Cache•eDRAM technology •Higher Frequencies• Memory Compression Engine• Active Memory Expansion with no

processor overhead penalty • Encryption / Cryptography Support• Random Number Generator• Enhanced Energy / Power Gating• 1/20 LPAR Core Granularity with FW7.6• 2X SPFP performance

© 2012 IBM Corporation11

POWER5 POWER5+ POWER6 POWER7 POWER7+Technology 130nm 90nm 65nm 45nm 32nmSize 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

Дизайн процессоров IBM POWER

© 2012 IBM Corporation12

Преимущества eDRAM для POWER7+С использованием

eDRAM Без eDRAM было бы

2.1Млрд транзисторов567 mm2

5.4Млрд транзисторов950 mm2

IBM’s eDRAM выигрыш: Большая плотность: 1/3 площади от 6T SRAM Меньшее энергопотребление: 1/5 SRAM Меньше ошибок: в 250x меньше чем в SRAM Большая производительность

© 2012 IBM Corporation13

POWER7+ процесссоры и архитектура

13

До 40% больше производительности, идеальны для транзакционных и бизнес-аналитических нагрузок

Большая масштабируемость и гибкость

• 20 Виртуальных машин на ядро• Elastic Capacity on Demand

Выше производительность• 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

Энергоэффективность• Delivering 5x more performance per watt• Enhanced energy / power gating 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

5 0

1 0 0

1 5 0

2 0 0

2 5 0

125% Возможность расширения

памяти до 125%

Клиент получает больше памяти используя меньше ресурсов POWER7+

Больше циклов процессора для основных задач

На 25% больше памяти

No AME P7 AME P7+ AME

14 18 октября, 2012

© 2012 IBM Corporation

Новые процессоры помогают защитить данные

Выигрыш клиента

Cryptography can be applied to a broader set of data creating a stronger security ecosystem.

Two primary AIX security applications will be enabled by default:

• Encrypted File Systems, protecting your data in storage or on backup media

• IPsec, protecting your data over the network.

• Processor performance remains focused on business applications.

At the core of cryptography is the need for high quality entropy or random numbers.

With the POWER7+ RNG offload providing this entropy, security is enhanced and processor performance remains focused on your business applications.

Технологии

Crypto Offload Accelerators provide cryptographic engines to relieve the P7+ processor from the performance intensive cryptographic algorithms of AES, SHA, and RSA.

High quality random numbers generated with high performance via the RNG offload feature of the P7+ processor.

15 18 октября, 2012

© 2012 IBM Corporation

Кое-что промодели

© 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 Corporation1818

Новые серверы IBM Power на процессорах POWER7+Power 770

•POWER7+ processors•До 48 ядер @ 4.2 GHz•До 64 ядер @ 3.8 GHz•12 или 16 core 4U узлы•До 4x узлов в системе•Dynamic Platform Optimizer

Increased performance and scaleNow up to 20 VMs per-core Increased energy efficiencyElastic Capacity on DemandEnterprise RAS

Power 780• POWER7+ processors• До 64 ядер @ 4.4 GHz • До128 ядер @ 3.7 GHz• 16 или 32 core 4U узлы• До 4x узлов в системе• Dynamic Platform Optimizer

Increased scalability to 128-cores Increased performance per-core Now up to 20 VMs per-core Increased energy efficiency Built-in Elastic Capacity on Demand Share resources in Power Systems Pool Enterprise RAS

© 2012 IBM Corporation

Категории Power 770 Power 770+ Преимущество

Processor • POWER7 45nm • POWER7+ 32 nm Faster performance

L3 cache • 4 MB per core • 10 MB per core Faster performance

Configurations • 64 cores @ 3.3 GHz• 48 cores @ 3.7 GHz

• 64 cores @ 3.8 GHz• 48 cores @ 4.2 GHz Faster performance

Hardware accelerators

• Software memory compression

• Software encryption

• Hardware assisted memory compression and AIX file system encryption

Faster performance

Other processor features

• Random number generator• Enhanced Single Precision

Floating Point performance Faster performance

RAS

• Self-healing capability for L3 cache functions

• Dynamic processor fabric bus repair

• Processor re-initialization

Better availability

Energy • Enhanced energy power gating More energy efficient

Virtualization • 10 VMs per core• 8 concurrent LPMs

• 20 VMs per core• 16 concurrent LPMs More efficient for virtualization

Software • Dynamic Platform Optimizer More efficient for virtualization Less complex to manage

CoD • Easier CoD enablement keys Less complex to manage

Storage • >1,300 direct disk drives • New 1U SSD storage enclosure• >3,000 direct attach disk drives

Greater performance/density Higher capacity

Что нового в Power 770 на POWER7+?

© 2012 IBM Corporation

Category POWER7 780 POWER7+ 780 Benefit

Processor • POWER7 45nm • POWER7+ 32nm Faster performance

L3 Cache • 4MB per core • 10MB per core Faster performance

Configurations • 96 cores @ 3.44GHz• 64 core @ 3.92GHz

• 128 cores @ 3.72GHz• 64 cores @ 4.42GHz

Faster performanceGreater scalability

Hardware Accelerators

• Memory Compression• AIX file system & IPsec encryption Faster performance

Other Processor Features

• Random number generator• Enhanced GX system buses• Enhanced single precision floating

Point performanceFaster performance

RAS• Multi-system pooling of compute

resources • Dynamic processor fabric bus

repairBetter availability

Energy • Enhanced energy power gating More energy efficient

Virtualization • 10 VMs per Core• 8 Concurrent LPMs

• 20 VMs per Core• 16 Concurrent LPMs

More efficient for virtualization

Software • Dynamic Platform OptimizerMore efficient for

virtualizationLess complex to manage

COD• Elastic COD processor and

memory days built-in• Flexible COD enablement keys

Greater flexibility

Что нового в Power 780 на POWER7+?

© 2012 IBM Corporation

Power 795• High-end POWER7 server• Up to 256 cores @ 4.0 GHz • Up to 128 cores @ 4.25 GHz• 1 - 8 processor books• Up to 1,000 VMs• Dynamic Platform Optimizer• Active Memory Mirroring

✓ Now up to 16 TB Memory✓ Now up to 20 VMs per-core ✓ New Integrated Bus & I/O adapters✓ Built-in Elastic Capacity on Demand✓ Share resources in a Power Systems Pool ✓ Enterprise RAS

21 18 октября, 2012

Новые свойства Power 795

© 2012 IBM Corporation

#1

(1) IBM Power 780 on the two-tier SAP SD standard application benchmark running SAP enhancement package 5 for the SAP ERP 6.0 application; certification number not available at press time and can be found at sap.com/benchmark . IBM Power System 780, 12 processors / 96 cores / 384 threads, POWER7+ 3.72 GHz, 1536 GB memory, 57,024 SD benchmark users, running AIX® 7.1 and DB2® 10, dialog resp.: 0.98s, line items/hour: 6,234,330, Dialog steps/hour: 18,703,000, SAPS: 311,720, DB time (dialog/ update): 0.009s / 0.014s, CPU utilization: 99%,  Certification #: (1).  Results valid as of 09/17/2012.  Source: http://www.sap.com/benchmark. Additional details on following pages.

Power Systems top all others in SAP Sales and Distribution Standard Application 2-Tier benchmarkSimple, single Power 780 delivers over 2X the users and 88% more users per-core than HP DL980 G7 & 46% more users and 191% more users per-core than the Oracle M9000

SAP

SD

ER

P 6 Be nchm

ark Users

Power 750POWER7 DB2 9.7

17,312 users4/32/128

# 2011043

Power 780POWER7DB2 9.7

37,000 users8/64/256

# 2010013

Sun M9000SPARC

Oracle 10g 39,100 users64/256/512# 2008042

57 ,024 Overall

8-processor

Power 795POWER7DB2 9.7

70,032 users16/128/512# 2010042

HP DL980 G7Xeon

SQL Server 200825,160 users

8/80/160# 2011021

4-processor

16-processor

Power 795POWER7DB2 9.7

126,063 users32/256/1024# 2010046

#1#1

#1SAP SD Users

Fujitsu RX500 S7 Xeon

SQL Server 200812,900 users

4/32/64# 2012029

Power 780POWER7+

DB2 1057,024 users

12/96/384# (1)

12-processor

#1

96-c oreP ow e r 780

w ith P OWE R 7+ & DB 2 ®10

© 2012 IBM Corporation

Power Systems top all others in SAP Sales and Distribution Standard Application 2-Tier benchmark

+88% more users/per-core than HP DL980 G7

SAP S

D E

RP

6 Be nchm

ark Users

Sun M9000 - SPARCOracle 10g

39,100 users64/256/512# 2008042

314 users/core

HP DL980 G7 - XeonSQL Server 2008

25,160 users8/80/160

# 2011021

152 users/core

Power 780 - POWER7+DB2 10

57,024 users12/96/768

# (1)

594 users/core

(1) IBM Power 780 on the two-tier SAP SD standard application benchmark running SAP enhancement package 5 for the SAP ERP 6.0 application; certification number not available at press time and can be found at sap.com/benchmark . IBM Power System 780, 12 processors / 96 cores / 384 threads, POWER7+ 3.72 GHz, 1536 GB memory, 57,024 SD benchmark users, running AIX® 7.1 and DB2® 10, dialog resp.: 0.98s, line items/hour: 6,234,330, Dialog steps/hour: 18,703,000, SAPS: 311,720, DB time (dialog/ update): 0.009s / 0.014s, CPU utilization: 99%,  Certification #: (1).  Results valid as of 09/17/2012.  Source: http://www.sap.com/benchmark. Additional details on following pages.

23 18 октября, 2012

© 2012 IBM Corporation24

Быстрое проникновение облаков

Формирование бизнес преимуществ на основе данных и аналитики

Повышенное внимание к безопасности

Проникновение социальных сетей и мобильных приложений

Консолидация и интеграция IT инфраструктуры

5 тенденций ускоряющих новую эру IT

© 2012 IBM Corporation25

Как разобраться с данным и использовать их для преимущества над конкурентами?

48% - рост данных в 2012 по сравнению с 2011

Как обезопасить информацию, имеющую значение для вашего бизнеса и ваших клиентов?

60,000 ежедневных атак на IT инфраструктуры

Как перенести инвестиции IT с обслуживания на инновации и сервисы?

Только 1 из 5 компаний выделяет расходы на инновации IT

Готова ли ваша IT инфраструктура?

DataData

SecuritySecurity

CloudCloud

© 2012 IBM Corporation26

Всем нужна IT инфраструктура, которая…

26

Безопасную облачная инфраструктура позволяет максимально эффективно доставить бизнес приложенияCloud

Критически важные данные,результаты их анализа доступны в реальном времени в масштабах всего предприятияData

Обеспечение полной безопасности данных, снижение рисков и повышения соответствия требованиям государства

Security

.готова к завтрашнему дню

© 2012 IBM Corporation27

high performance analytics, high performance computing & high performance UNIX

IBM WatsonПобедитель Jeopardy!

IBM WatsonПобедитель Jeopardy!

Power Systems – неограниченные системы для интенсивных вычислительных нагрузок

1.7X more database

performance per core

125%more SAP SD Users than best Intel

LLNL SequoiaСамый быстрый Супекромпьтер

LLNL SequoiaСамый быстрый Супекромпьтер

reduction in floor spacereduction in energy reduction in licensed cores

80% consolidation

Performance Scalability Virtualization Availability Security

16 petaflopsL L NL S equoia

© 2012 IBM Corporation

Power Systems, PowerVM, AIX, IBM I, Linux, IBM SW

Технологии и решения, которые:

Разработаны вместе Произведены вместе Протестированы вместе Поставляются вместе Поддерживаются вместе 0%

10%

20%

30%

40%

50%

60%

70%

80%

© 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

Power – интегрированные решения от IBM

© 2012 IBM Corporation

Thanks! Спасибо!

Вопросы?

Alexey.Boyko@ru.ibm.com

(495)-775-8800 ext 2904

© 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.org SPEC http://www.spec.org LINPACK http://www.netlib.org/benchmark/performance.pdf Pro/E http://www.proe.com GPC http://www.spec.org/gpc VolanoMark http://www.volano.com STREAM 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.com Fluent http://www.fluent.com/software/fluent/index.htm TOP500 Supercomputers http://www.top500.org/ Ideas International http://www.ideasinternational.com/benchmark/bench.html Storage Performance Council http://www.storageperformance.org/results

Revised December 2, 2010

Notes on benchmarks and values

18 октября, 201231

© 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.org LINPACK http://www.netlib.org/benchmark/performance.pdf Pro/E http://www.proe.com GPC http://www.spec.org/gpc STREAM http://www.cs.virginia.edu/stream/ Fluent http://www.fluent.com/software/fluent/index.htm TOP500 Supercomputers http://www.top500.org/ AMBER http://amber.scripps.edu/ FLUENT http://www.fluent.com/software/fluent/fl5bench/index.htm GAMESS http://www.msg.chem.iastate.edu/gamess GAUSSIAN http://www.gaussian.com ANSYS 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.php ECLIPSE 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.cfm STAR-CD www.cd-adapco.com/products/STAR-CD/performance/320/index/html NAMD http://www.ks.uiuc.edu/Research/namd HMMER http://hmmer.janelia.org/

http://powerdev.osuosl.org/project/hmmerAltivecGen2mod

18 октября, 201232

© 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 eServer pSeries 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

18 октября, 201233