Let’s start with a quick look at where we are in the market and update on where we’ve come through 2009. IBM Power continued to gain share through a challenging year for the IT industry... and UNIX as a platform gained share most of the year against other alternatives. HP continued to decline as PA-RISC customers looked to other alternatives versus moving to Itanium... which has continued to have roadmap delays... Tukwila is now 4 years late and still a question mark. Sun has continued to be in near free fall as uncertainty over their future hung over them. Now that Oracle has competed the acquisition, we’ll see where they go from here... they have certainly started with some wild claims and not much news on the roadmap front. In the midst of all of this uncertainty, IBM’s solid performances and stability have been a beacon for customers moving to higher value with IBM Power... and as a result we have seen the largest shift in client spending from HP and Sun to Power in UNIX history... putting IBM Power at the highest revenue share ever achieved by a UNIX vendor. POWER4 LPARs is 4Q01 POWER5 APV is 3Q04 (July 2004 was announce date) POWER6 Live Partition Mobility is 2Q07 (May 2007 was announce date for first POWER6 570)
As a result, IBM has successfully helped over 2100 companies migrate from HP and Sun UNIX platforms as well as help many clients consolidate x86 applications to Power... leveraging the expertise we have developed over the years to do these migrations in a very methodical way... helping the customer assess what can be achieved, what TCO they should expect, and how to do the migration with minimal to no disruption to their business. It’s about addressing the fear of risk that clients have when they do a major platform move... and we have been able to demonstrate that we can help them manage that risk such that the returns they receive from the migration to Power far exceed any risk that may be percieved to exist. With that look back, let’s turn to the future and why we are here today.
[Our vision] This is our vision. Designed, integrated systems are more essential for our clients' business than they have ever been before. And if there was ever a time that reminded us of this, it's today when our clients are facing more complex challenges than ever before: A medical system that holds the promise of unlocking new cures and treatments — attached to a fragmented and antiquated health care system; A system of energy that powers our economy, but simultaneously endangers our planet; Threats to the security of their businesses that seek to exploit the very interconnectedness and openness so essential to global commerce. For all the reasons our company -- and our clients -- are so energized by the opportunities of a smarter planet; these are the same reasons I am so optimistic about the future of our business in IBM Systems and Technology No one can predict the magnitude of new applications that will come from a smarter planet. In no area will innovation be more important than in the development of new technologies to make new applications possible. [Transition] And IBM Systems will lay the foundation for smarter planet applications. Let me explain.
[IBM Systems and Technology lay the foundation] First and foremost is our understanding of our clients and having a deep appreciation of their environment and the types of applications and workloads that they need to run to allow their businesses to reach the markets they serve. We have a comprehensive portfolio, second to no one else in the industry. And our technology leadership and the investments we'll continue to make, securing our future leadership and differentiation. STG is laying the foundation for the workload optimization that is necessary on a smarter planet. On a smarter planet, the new types of applications and workloads will span across all industries and will have new capabilities. Just think about areas like video surveillance, financial analytics, network security and threat management. Or on-line infotainment and advanced search. [Transition] These workloads require systems that can optimize specifically for them.
[IBM delivers the solution] Workload optimization connects what we do in STG to the rest of IBM. Our role is to deliver the hardware that's optimized to support the infrastructure needs of our clients. Whether it's within or outside of the data center. This only works when you can connect it with the software that will drive new capabilities and manage IT resources. So in combination with Software Group, we will deliver integrated service management that will offer a fully virtualized infrastructure. And the third part of the equation is to address the different ways in which people want IT delivered. In partnership with Software Group and Global Services, we will provide multiple delivery options. This may be through managed services or outsourcing, but also through cloud-based offerings or new integrated offerings like IBM’s Smart Analytics System. Systems and Technology Group lays the foundation with workload optimization, and then we work with the rest of IBM to deliver systems designed for a smarter planet. [Transition] IBM - and more importantly our clients - rely on our advances in enabling technologies, new system designs and systems software to help build a smarter planet.
Let’s talk about building a smarter planet. As you may know, this has been the central focus of IBM now for awhile... and our chairman just declared this “The Decade of Smart”. As a reminder... what does it mean to be smarter?
Building a smarter planet is based on three key characteristics First... something is smarter if it is instrumented and enabled to provide key information about the environment, the packaging and condition of items, usage, thermals, traffic flow or any other number of factors As of 2010, there are estimated to be over a billion transistors per human on our planet... each at less than one ten-millionth of a US penny of cost. All this instrumentation including RFID tags on everything from food to cars... two way energy and water meters... health sensors... traffic sensors in the roads and toll stations... This instrumentation is all interconnected into an “internet of things”... we’ve seen the internet grow from just connecting people to connecting devices... over a trillion networked things creating information at an exponential rate. And buried in all of the resulting mountains of data lie jewels of intelligence... of information that we can mine to gain insights into actions that can be taken to make the world better... Smarter. Let’s look at a few examples...
Healthcare is an area that is ripe for a transformation. You may not realize that some 30% of the total data in the world - petabyte after petabyte of data - is used to store medical images...and this will continue to grow. As the health system moves to a digital system with every human - and even pets or other animals - have a digital health record full of images and data... We can connect health care professionals to that data so that they can spot trends of diseases... genomic patterns... and develop insights that help deliver better preventative and therapuetic care to help stop disease.
Rice University in Houston Texas has a small size that allows personal interaction between students and professors, while its eminent faculty foster the intellectual excitement of a major research university. At Rice, undergraduates at all levels participate in cutting-edge research with world-class faculty in the humanities, social sciences, engineering and natural sciences. Rice University uses POWER7 performance and analytic ability for smarter healthcare research. The challenge To accelerate the understanding of the molecular basis of cancer through the application of genome analysis technologies, especially large-scale genome sequencing. The solution Leverage the performance and virtualization of POWER7 systems to provide researchers with more flexibility and efficiency in analysis across a range of problems. Intelligent, workload-optimizing systems deliver the best approach for shared research computing. Align research workload requirements to virtual machine characteristics. Manage wide variety of computational and data needs for a single project workflow
The world’s energy grid is another area crying out for transformation. Because of the nearly 100 year old design of most of the grid, with little or no built-in intelligence, enough electricity is lost to power India, Germany and Canada for an entire year. Where smart grids have been implemented, energy provides have seen a 15% reduction in power usage during peak hours due to smarter use of the available electricity. With the deployment of millions of two way energy meters, your energy usage can be monitored in intervals of seconds every hour of every day versus the single reading taken once a month by a meter reader. These continuous readings create a huge amount of data which can be analyzed for usage patterns and opportunities to save energy or shift usage to lower demand periods at lower prices for the consumer
The challenge: Malta's electricity and water systems are inexorably intertwined. Malta depends entirely on foreign fuel oil for the production of all of its electricity and for more than half of its water supply, which filters through an energy-intensive desalination process. In addition, to meet this challenge, both Enemalta and Water Services Corporations are undergoing an internal transformation process geared towards increased efficiency. The solution: In assisting in the transformation of both utilities, IBM is entrusted to implement a customer relationship management (CRM) and Billing solution, as well as Enterprise Resource Planning (ERP) core modules, while a new Web portal will be instilled for both utilities to better interact with their end customers. IBM Global Business Services, IBM Research, IBM Power Systems, System x IBM Tivoli, Lotus, WebSphere The benefits: Data from the intelligent meters can be analyzed to help lower costs, adopt efficient and sustainable consumption patterns and cut greenhouse gas emissions. By addressing water and power issues as a system citizens can make smarter decisions about how and when they use power
Organizations are increasingly understanding the potential benefits of becoming “smarter” ... and are now starting to ask “how do I get started?” The questions aren’t just about the technology they need, but also about how to deal with unclear ownership of large systems... of dealing with a wide array of stakeholders. They are asking how they build a business case for the budget or how they get the solution through procurement? If a public sector organization, how do they build support among voters or agencies? Where exactly do they start and how fast can they move? IBM can help with these questions as we have started to build experience with hundreds and thousands of organizations, governments, and businesses who have successfully embarked on these transformations One such agency is Queensland Motorways in Brisbane, Australia (next chart)
IBM worked with the Brisbane government and Queensland Motorways to build a fully integrated system that give their citizens better mobility at 25% lower cost of ownership for the systems involved They migrated several applications from x86 systems to IBM Power and implemented a free flow toll system on a Power 570 that gives them high availability and reduces traffic congestion for their citizens The challenge: Implement new free flow tolling Central System to transform QML’s business operations for efficiencies and to set a platform for growth. The solution: Optimized infrastructure and increased interconnectedness through a portfolio of IBM and Partner applications on Red Hat Linux on Power 570, IBM Electronic Toll Collection solution, IBM WebSphere Application Server, MQ, Message Broker, Proxy Server, Load Balancer, IBM Tivoli Access Manager IBM TotalStorage DS8000, DS800 Metro (Data) Mirroring, SAP full landscape (CRM, ERP, BI, etc.), Oracle Database The benefits: Robustness to achieve highest service levels and increased efficiencies Intelligent Data mirroring and 24x7x365 availability
Smarter systems: Scale quickly and efficiently to manage and analyze large amounts of information Optimize performance to differing requirements across multiple workloads Flexibly adapt to changing requirements and demands - flowing resources where needed instantly for high utilization and ROI Avoid downtime by being highly reliable, available and resilient Save energy by intelligently balancing performance needs with efficiency requirements Automate management tasks to save on labor and staffing in resource constrained environments
That’s why we are proud to introduce the first of a family of systems designed specifically for the needs of a smarter planet - the next generation of Power Systems with POWER7 processors We want to help clients - business and organizations of all kinds - to Power their planets with these new smarter systems To bring workloads from all over - consolidate them - optimize them - and support the scaling, resiliency, flexibility, energy and automation needs those workloads demand As we said earlier... it all starts with technology leadership... the kind of leadership embodied in the all-new POWER7 family of processors
The new POWER7 processor is the first multi-core processor - in 4, 6 and 8 core options - to deliver more cores and more threads - up to 32 threads per socket - with more per core performance as well than it’s predecessor POWER6 The new POWER7 processor runs up to 4.14GHz... still faster than any competitive processor... and provides up 1, 2 or 4 threads per core as workloads require The new integrated eDRAM Level 3 cache of up to 32MB is intelligent and can freely flow from core to core as needed. The eDRAM technology means that POWER7 has only 1.2B transistors where competitive processors have up to 2.4B transistors... or twice as many transistors using energy or acting as points of failure. That makes POWER7 the most energy efficient and reliable processor of its kind ever built The Dynamic Energy Optimization capabilities of POWER7 allow it to overclock at up to 10% above rated frequency or to slew down to as low as 50% of rated frequency depending on thermal conditions and utilization POWER7 is the first to offer either TurboCore or MaxCore modes... we’ll talk about that more later... Now let’s look at four all new systems based on this processor technology... the only systems in the industry with IBM designed processors, virtualization, operating systems and middleware integrated.
The first of the new systems is the Power 750 Express. The IBM Power 750 Express™ server delivers the outstanding performance of the POWER7™ processor. The performance, capacity, energy efficiency and virtualization capabilities of the Power 750 Express make it an ideal consolidation, database or multi-application server. As a consolidation or highly virtualized multi-application server, the Power 750 Express offers tremendous configuration flexibility to meet the most demanding capacity and growth requirements. Utilize the full capability of the system by leveraging industrial-strength PowerVM virtualization for AIX®, IBM i, and Linux®. PowerVM offers the capability to dynamically adjust system resources based on workload demands so that each partition gets the resources it needs. The 750 Express is a 4U, 4 socket system capable of either 6 or 8 cores per socket for up to 32 cores at 3.55GHz The 750 carries forward the highly configurable and scalable design of the Power 550 - the industry’s most popular 4 socket system in revenue market share - meaning you can start with one socket processor card with 6 or 8 cores, then add from 1 to 3 more processor cards as you need to The 750 fully support PowerVM virtualization for up to 160 partitions now ... and we plan to increase that to 320 partitions by the end of the year.
POWER7 breaks all the rules that many in the industry thought were true... that frequencies for multi-core processors leveled at about 3GHz... that you couldn’t increase per core performance and threads and cores all at the same time.... POWER7 shows that - like POWER6 - it continues to have the leading performance per core over Itanium, SPARC and even the current best of x86 processors - AMD’s Istanbul - in 4 socket systems
The Power 750 continues to break the rules by being not only the best performing, but also the most energy efficient 4 socket system on the planet. The Power 750 delivers more SPECint_rate performance per watt than any competitive 4-socket system... better than HP rx6600, better than Sun T5440, better than any Intel Dunnington (remember Nehalem-EX isn’t shipping yet in 4 socket systems as of 2/8/2010) The Power 750 is certified by the US Government Environmental Protection Agency (EPA) to be Energy Star certified - the first RISC system to be certified. ENERGY STAR is the trusted, government-backed symbol for energy efficiency helping us all save money and protect the environment through energy-efficient products and practices. The ENERGY STAR label was established to: Reduce greenhouse gas emissions and other pollutants caused by the inefficient use of energy; and Make it easy for consumers to identify and purchase energy-efficient products that offer savings on energy bills without sacrificing performance, features, and comfort. Products can earn the ENERGY STAR label by meeting the energy efficiency requirements set forth in ENERGY STAR product specifications.
The new Power 750 delivers 15,600 SAP users on the SAP SD 2 Tier benchmark - more than any competitive 4 or 8 socket system and nearly equaling the result for a 128-core Sun M9000
IBM looked at what it would take to support a requirement for 110,000 SAPs - 27,500 SAPs for the database (and 3X peak capacity) and 72,500 SAPs for application servers Two Power 750s deliver 144,000 SAPs (at 77% utilization) with PowerVM and DB2 pureScale support Two HP DL785 G6 systems deliver 45,000 SAPs each but run at an average of 30% utilization as they are sized for 3X peak capacity - or roughly 15,000 SAPs each Nine HP DL380 G6 Nehalem-EP systems can deliver 13,600 SAPs each and we generously assumed that with VMware each would run at 66% utilization - but VMware has a 20% performance penalty on each (13,600 * (1-0.2) * 0.66 = 7,180.8 each; x 9 = 64,627 SAPs or just under our 72,500 objective) The HP systems have a total list price of $447,969 compared to the two IBM Power 750’s at US List of $387,760 for the Hardware and OS ONLY Cost comparison does not account for 90% fewer network connections - thus fewer switches - on Power, or the use of 75% less space and 72% fewer systems to manage. TCO would be significantly less for Power vs. HP DL systems
Using SPECint_rate benchmarks, a single IBM Power 750 at 80% utilization can provide the same capacity as 92 SPARC Enterprise T2000’s at 20% utilization (typical for Sun servers running a single application) This saves 95% of the cores for software licensing, 97% of the floorspace and 95% of the energy
IDC estimates that nearly 92,000 SPARC T2000 servers have been sold since late 2005 when they first shipped. If all of those servers were consolidated into Power 750’s at the rate of 92 to 1 and the 750s were at 80% utilization and the T2000’s were assumed at 20% utilization, then it would take 1000 Power 750’s to provide all the computing capacity of the 92,000 SPARC Enterprise T2000’s Using the rated maximum energy of each system (450 watts for the single socket T2000 vs. 1,950 watts for a 4 socket Power 750), consolidating all the T2000’s into 1000 Power 750s would save 345 million kilowatt-hours of electricity per year - or enough to supply 34,500 homes for a year Uses Wikipedia estimate of 10,000 kwH of electricity usage per home per year
A 64 core HP Integrity Superdome provides performance of 824 on SPECint_rate2006 in a 30” wide, 77” tall, and 48” deep frame, using 11,586 watts of electricity A single Power 750 in a 4U 19” wide cabinet uses only 1,950 watts and provides 1060 on the SPECint_rate2006 benchmark. The Power 750 provides 28% more performance with 83% less energy usage than the Superdome - at a fraction of the price of the Superdome So if the HP machine is “Superdome”... perhaps the 750 is better known as “Super Power”?
Designed for virtualized consolidation of business-critical workloads, the IBM Power® 770 delivers on performance, availability, efficiency and virtualization in a way that is unique in the industry. PowerVM virtualization enables continuous, dynamic resource adjustments across all partitions and operating environments, independent of physical placement, to optimize performance while minimizing energy usage. Supported environments include AIX®, IBM i, Linux® for Power and x86 Linux applications, all on the same system. The Power 770 is the POWER7 successor to the 570 line of products that started with POWER5 in July 2004... extending the industry’s most popular midrange system on any OS up to 64 cores and POWER7 performance Each node can now have more performance than a complete 16-core 570 - meaning you can get more performance in 70% less energy - or use two nodes and get more than 2X the performance in one half the space with nearly half the energy - and still have the resiliency and modularity that clients love about the 570 The Power 770 comes in either 12 core nodes at 3.5GHz or 16 core nodes at 3.1GHz - allowing clients to choose higher per core performance for software savings with up to 48 cores; or more throughput and capacity with up to 64 cores per system The Power 770 has all the enterprise characteristics you expect of a Power modular product with Capacity on Demand and Enterprise level RAS With Capacity on Demand you can have a core of Power 770 performance with 8GB of memory for as little as $16 per day!!
Designed for virtualized consolidation of business critical workloads, the IBM Power® 780 delivers on performance, availability, efficiency and virtualization in a way that is unique in the industry. IBM married the modular design of the Power 770 with the Enterprise RAS, 24x7 warranty and PowerCare services of the Power 595 to create the new Power 780 - a new breed of modular high-end systems with up to 64 cores at 3.86GHz in MaxCore mode - or the ability to run in TurboCore mode at 4.14GHz with up to 32 cores for our fastest POWER7 per core performance and the most software savings on licensing for software licensed per core The Power 780 gives clients the ability to move applications and middleware with demand per core performance requirements - like databases, OLTP or ERP systems - from their current Power 570’s, p5-590’s or p5-595’s and gain the most in per core performance with TurboCore mode. When ready to maximize the capacity of the Power 780, simply reboot in MaxCore mode and buy more CoD activations to go up to 64 cores of 3.86GHz performance - with better per core performance than any other POWER7 option available and up to 64 cores and 256 threads of Power performance, capacity and throughput. As the POWER7 processor with 8 cores and 32 threads extends the capacity and throughput of the Power high-end up to 256 cores, 1024 threads by year end per our statement of direction for the high-end. IBM felt that clients would benefit from a new, modular entry to the high-end that continues the 64 core tradition of the Power 595 with many of the same enterprise characteristics
The performance of the Power 780 is such that, when run at 80% utilization, a single Power 780 can consolidate the capacity of 8 HP Integrity Superdome systems with 64 cores each running at 30% utilization. The superior PowerVM virtualization, high bandwidths for memory and I/O, combined with the scalability of AIX means that a single Power 780 can save 87% of the cores for software licensing, over 90% of the floorspace, and 92% of the energy of eight Superdomes. Super Power indeed.
Clients with POWER5 systems have a great opportunity to leverage the performance and efficiency of POWER7 to reduce costs and cut monthly operational expenses Here we see two scenarios - one with a client that has 2 p5-590’s and another with 4 p5-570’s contained within two racks (or four racks for more space savings). Many of our POWER5 clients tell us that they are using their p5 systems at 30% utilization as they hadn’t fully exploited the virtualization capabilities when those systems were first deployed. In either case, the client can move to a single Power 770 with 24 cores at 3.5Ghz running at 60% utilization. The p5-590 customer moving to Power 770 will get up to 30% additional effective capacity and save up to 90% in energy costs, over $600K in maintenance over 3 years, and over $1M in software licensing. The p5-570 customer moving to Power 770 will get up to 50% additional effective capacity, save up to 84% in energy costs, over $250K in maintenance over 3 years, and over $1M in software licensing. In either case you have enough capacity left over to consolidate more workloads - including x86 workloads from those application servers that talk to the databases and ERP systems moving to the new Power 770.
With our new Capacity on Demand pricing for the Power 770 and Power 780, we have extended the time to breakeven vs. a full purchase to one year - making Capacity on Demand a more attractive option than ever! Consider this... you need to add a new application server to handle the buying season or a peak demand due to a promotion. You can either go buy another x86 server with software licenses for thousands OR you can simply add another activated core of Power performance with 8GB of memory for as little as US$16 per day. Yes - $16 per day. (prices vary by country) Thus you can use 3 months of that CoD processor core for less than a quarter of the cost of another 2 socket x86 system - and get similar capacity due to the ability to run your Power system at higher utilization and efficiency.
This chart provides a summary of the value of Power Systems, combining both the leading technology of our workload-optimized POWER7 systems, with the IBM systems software stack, including PowerVM, PowerHA, Systems Director, and our 3 operating environments: AIX, IBM i and Linux. IBM has invested in the software stack to optimize the performance and value companies can derive from Power Systems. Virtualization without limits with PowerVM helps companies drive to over 90% system utilization, and dynamically adjust platform resources to balance changing demands on the business. Resiliency with downtime is achievable through the RAS features built into Power Systems, and clustering software such as PowerHA SystemMirror. Dynamic Energy Optimization is achieved through the combination of EnergyScale technology in Power servers, managed and optimized via Systems Director Active Energy Manager software. Management with automation is made available through IBM Systems Director Editions for platform and integrated service management, plus VMControl for advanced virtualization image and systems pools management.
The new features of POWER7 provide features to optimize workloads - sometimes automatically and dynamically - to provide the best possible workload performance and throughput POWER7’s per core performance give it leadership transaction computing as evidenced by the leadership SAP SD 2 Tier results on the Power 750 - along with the top throughput computing results as evidenced by the leadership SPECjbb and SPECint_rate results The Power 780’s unique TurboCore mode allows the client to get the highest per core performance at 4.14GHz with the most cache per core... by booting in TurboCore mode, the system increases the frequency of 4 of the 8 cores, uses all 32MB of L3 cache across those 4 cores and provides outstanding performance per core and per thread. When you want to exploit the full parallelism of the 32 threads of an 8 core POWER7 processor, you can boot your system in MaxCore mode, simply buy additional CoD activations, and use up to all 8 cores in the socket at 3.8GHz on the Power 780. MaxCore is the default mode for all other POWER7 systems below the 780 - providing the maximum capacity and parallelization of POWER7. Power’s Intelligent Threads capability lets the system dynamically switch from single thread (ST) to dual thread (SMT2) to quad thread (SMT4) modes per core without rebooting the partition or system - it happens dynamically on the fly. IBM provides the flexibility to set the thread mode per virtual machine - e.g., to maximize database performance (ST or SMT2) or web application capacity (SMT4) - or let the system automatically and intelligently optimize the threading based on application demands and system utilization. Power’s Intelligent Cache technology provides the most performance per core by intelligently and dynamically flowing cache from core-to-core as demands dicate, always responding to the demands of the various cores on each processor. Intelligent Energy Optimization marries the system intelligence of EnergyScale(TM) features with the management of IBM Systems Director Standard Edition with Active Energy Manager to allow you to favor performance or favor energy savings for the best possible balance of performance and energy efficiency. Active Memory Expansion is an all-new capability that allows capacity to be increased for memory constrained environments like SAP or virtualization by making the system’s physical memory appear as being up to twice as large as it actually is - e.g., making 32GB look like 64GB to SAP or PowerVM. If you have used all available DIMM slots or have the full capacity of memory on your system, simply turning on Active Memory Expansion will give you additional memory capacity for more application throughput. IBM Solid State Drives provide OLTP applications or apps that require high I/O rates incredible performance. IBM i is optimized for SSD as i’s unique single level storage model can place “hot” pages on SSD while moving “colder” pages to mechanical hard disk drives (HDD). AIX and Linux gain similarly and will continue to be optimized for SSD through 2010.
As businesses look for ways to maximize their IT infrastructure investment returns, they turn to PowerVM virtualization to consolidate multiple workloads onto fewer systems—increasing server utilization and reducing cost. PowerVM provides a secure and scalable virtualization environment for AIX, i and Linux applications built upon the advanced RAS features and leading performance of the Power Systems platform. Unlike other systems, all Power Systems benchmarks are run and measured in a virtualized environment, ensuring that companies can take advantage of costs savings of consolidation, with near linear scalability and without paying a performance penalty. Compare that efficiency with the significant performance overhead of running VMWare. Also, VMWare has significant limits to its size and flexibility of its virtual machine scalability – unlike PowerVM which enables up to 32 times the virtual machine size of VMware, and enables dynamic add and removal of virtual machine system resources. PowerVM offers Micro-Partitioning™ with the ability to run up to 10 partitions per processor core, and dynamically move processor, memory, and I/O resources between partitions to support changing workload requirements. PowerVM Live Partition Mobility enables active partitions to be moved between servers, virtually eliminating planned downtime. Live partition mobility can also be used to upgrade workloads between POWER6 and POWER7 processor-based servers without an application outage. VMControl™ complements PowerVM by providing automated virtualization management that minimizes time to provision virtual machine images and enables management of system pools. With POWER7, PowerVM and VMControl virtualization software will support up to 1,000 virtual machines on a single system, providing massive consolidation capability for exceptional costs savings.
AIX exploits decades of IBM technology innovation and is designed to provide the highest level of performance and reliability of any UNIX operating system. According to ITIC’s 2009 survey, AIX scored the highest reliability ratings among 15 different server operating system platforms. AIX 6.1 is binary compatible with previous versions of AIX, including AIX 5L™. This means that applications that ran on earlier versions will continue to run on AIX 6.1—guaranteed.4 AIX 6.1 is an open standards-based UNIX OS designed to comply with the Open Group’s Single UNIX Specification Version 3. IBM i is an integrated operating environment with a more than 20-year reputation for exceptional security and business resilience. IBM i integrates a trusted combination of relational DB2® database, security, Web services, networking and storage management capabilities. ITG reports that costs to use Power Systems and IBM i 6.1 average 41 percent less than x86 servers and Microsoft® Windows®. IBM i 6.1 includes expanded options for virtualization, upgraded storage and availability management, breakthrough Java™ performance, support for POWER6 and POWER7 and BladeCenter, and a broad range of middleware and tools to help drive application transformation. Both Red Hat and Novell SUSE Linux run natively on Power Systems, offering a scalable alternative for open source applications. Reducing x86 server sprawl through consolidation and virtualization is a key priority for many companies today. Linux on Power Systems with PowerVM provide a scalable, virtualized alternative to running Linux on x86 servers. PowerVM Lx86 cross-platform virtualization technology also enables x86 Linux workloads to run without recompilation and take advantage of the scalability of Power Systems. This means Power Systems clients can immediately benefit from the latest Linux applications. Note that POWER7 is the first POWER processor technology generation to support all three operating environments at the first system GA POWER7 supports the following releases:. AIX 5.3 and 6.1 at GA) IBM i 6.1.1 at GA and will support 7.1 (SOD) Linux: SUSE 10 & 11 at GA, and will support Red Hat 5.5 (SOD)
Power Systems solutions benefit from decades of IBM experience in designing and deploying high availability hardware and software. PowerHA SystemMirror disk clustering solutions are available to help keep your systems—and your business—running 24x7x365. PowerHA SystemMirror for AIX and IBM i Editions are data center and multi-site resiliency solutions designed to help protect critical business applications from outages: planned or unplanned. PowerHA pureScale™ technology delivers levels of database scalability and availability unmatched on UNIX or x86 systems, and is offered as a component of DB2 pureScale. Live Partition Mobility* supports the movement of a running AIX or Linux partition from one physical server to another compatible server without application downtime, helping avoid application interruption for planned system maintenance, provisioning, and workload management. Live Partition Mobility can be used to easily migrate operating environments to new servers temporarily or permanently, even to upgrade between POWER6 and POWER7 servers.
Power Systems energy management solutions monitor and control energy usage to help you manage energy efficiency in your data center. Each Power server has EnergyScale technology built into the POWER6 and POWER7 processor. Through consolidation and virtualization with PowerVM, businesses have realized dramatic energy savings. And, with IBM Systems Director Active Energy Manager™, you can identify trends in your energy usage and thermal profile, turn off processor cores or limit the energy draw across one or a group of Power servers, and track environmental data from applications used to monitor air conditioning units, Uninterruptible Power Supplies and Intelligent Power Distribution Units. POWER7 includes Intelligent Energy features that help to dynamically optimize energy usage and performance so that the best possible balance is maintained. Intelligent Energy EnergyScale technology with Active Energy Manager to dynamically optimize processor speed based on thermal conditions and system utilization. If the system's environment is favorable, the system can speed up processor cores to a frequency up to 10% higher than the normal rated speed to better handle demanding workloads. When utilization is lighter, or if environmental conditions are less favorable, the system can slow processor cores by as much as 50% to save energy. Users can select whether Intelligent Energy Optimization favors maximizing performance or energy savings based on their needs.
With platform management technologies on Power Systems, businesses not only get a complete picture of their systems and how well they are operating, but also the tools to deploy, optimize and maintain these systems at maximum effectiveness and efficiency. The result is optimized workload performance, energy efficiency and cost control. On Power Systems, server virtualization management is integrated with network and storage management for complete resource control. IBM System Director Editions for Power are sized for every data center. It’s now simpler than ever for a single operator to manage both physical assets and virtual resources. With IBM Systems Director for platform management and Tivoli® for enterprise service management solutions, Power Systems offer a unified systems management solution that can improve service delivery. VMControl provides automated virtualization management and minimizes the time it takes to provision virtual images and manage system pools.
Systems Director Editions deliver integrated service management. Systems Director helps reduce the time required to identify and troubleshoot services. Express Edition provides a common console to collaborate when troubleshooting problems. Options to immediately or schedule repairs. Standard Edition adds monitoring of energy and thermal characteristics across the datacenter. Networking system health and relationships with servers. Enterprise Edition adds Identifying changes that may impact availability Systems Director enables faster deployment and optimized system utilization. Express Edition provides Lifecycle virtual machine management for PowerVM, zVM®, VMware ESX™, and Microsoft Hyper-V. Tools to configure mobility of virtual machines for increased utilization. Standard Edition adds virtual image management from a central repository. Features to cap or dynamically optimize energy use across one or more systems. Enterprise Edition adds automated provisioning within a pool of server resources Systems Director provides critical data to document and plan system capacity. Express Edition provides automated discovery of physical and virtual servers and interconnections. Server resource utilization by virtual machine or across a rack of systems. Standard Edition adds discovery of supported networking systems, PDUs and CRAC units. Trend analysis of energy use and thermal output. Enterprise Edition adds automated discovery of applications associated with servers and LPARs. Predictive server resource performance analysis and reporting.
All of the capabilities of the new Power Systems - POWER7 processors, advanced firmware, PowerVM, operating systems like AIX and i, management software, integrated with IBM middleware provide the smarter systems needed to build a smarter planet. Leverage Power 780’s TurboCore mode to create a pool of systems or virtual processor pools for PowerVM to run DB2 and manage the vast amounts of data created by the “internet of things” on a Smarter Planet. Leverage MaxCore mode and Intelligent Threads for maximum throughput for web or collaboration servers that are interacting with the trillions of devices interconnected into the “internet of things”... or the people on social media networks collaborating on the “internet of people”.... and bring in all the data that’s stored on the database pool more efficiently than any other alternative. Draw new intelligence from those mountains of data using the Analytics capabilities of Power...ranging from InfoSphere Balanced Warehouse to Smart Analytics to IBM i with DB2 Web Query... discovering insights from the relationships in the data that can define the actions needed to respond quickly or act preventatively to stave off undesired results. IBM Systems Director Enterprise Edition with VMControl Enterprise Edition - working with PowerVM - gives you the flexibility to optimize workloads by creating pools of systems optimized to a transaction performance workload like databases - or another pool optimized to throughput oriented workloads like web - or mix the workloads on single systems using PowerVM and the Intelligent Threads, Cache, and Energy capabilities on every POWER7 system to optimize performance, throughput and efficiency.
Smarter planet solutions will impose increased demands on IT Infrastructure, for example being able to scale, be agile, deliver the best performance at the lowest cost, etc. POWER7 provides a hardware platform that can meet these demanding requirements. The large number of parallel threads available on the platform coupled with the IBM software designed to exploit those threads, represent the best combination available to meet these requirements.
As the planet and companies become smarter, the demands on their storage systems are unprecedented Information is doubling every 18 months The requirement for storage capacity is increasing 45% per year Our clients are asking for help in managing the crush of information growth IBM can address your storage needs – from the assessment of your current information infrastructure through their evolution to a dynamic, future-proof system. IBM Scale Out Network Attached Storage (SONAS) The “C:” drive of the enterprise Reduces pain of managing files on drives and in directories SONAS makes it easy with single namespace and up to 14 Petabytes of storage Excellent storage solution for cloud implementations IBM XIV – Next generation storage with exceptionally low Total Cost of Ownership Capacity without complexity Advanced grid architecture Storage administration made easy IBM SAN Volume Controller – Storage virtualization Simplify operations Better utilize disk capacity Excellent data migration capability
IBM Power 7
IBM Power Systems Power your planet. Smarter Systems for a Smarter Planet
<ul><li>REQUIRED CHARTS </li></ul><ul><li>The presenter must display the Special Notices chart, the Notes on Benchmarks and Values charts (if the referenced values are given), and the Notes on Performance Estimates chart (if the referenced performance estimates are given) during the course of the presentation. Any printed copies of this presentation that are distributed must include legible copies of these charts. If printed copies are not distributed, the attendees must be offered the option to receive legible printed copies of these charts. </li></ul><ul><li>TRADEMARKS </li></ul><ul><li>Please review the Special Notices page prior to updating this presentation to ensure all trademarks used are given proper attribution. </li></ul><ul><li>SPEAKER NOTES </li></ul><ul><li>This presentation may contain speaker notes available imbedded or as a separate file. Please ensure these are utilized if available. </li></ul>Notes to presenter Revised January 9, 2003
Source: IDC Quarterly Server Tracker Q309 release, November 2009 UNIX Server Rolling Four Quarter Average Revenue Share POWER4 Dynamic LPARs POWER6 Live Partition Mobility POWER5 Micro-Partitioning Customers are moving to higher value … as shown by the largest shift of customer spending in UNIX History
successful Power Migration Factory migrations to date. There were over 500 Power migrations during 2009, with more than 90% from Sun and HP customers (including x86 consolidation). In 4Q09 alone, Power achieved nearly 200 competitive migrations. 2,100
Our vision Designed, integrated systems are part of the transformational story of the next decade.
IBM Systems & Technology lay the foundation Workload Optimization Deep Understanding of Client Needs Approach challenge from the client’s perspective A Comprehensive Portfolio A family of “fit-for-purpose” servers, storage & system software Technology Leadership Investing in future technology for differentiation and sustained leadership
Providing an integrated solution of systems, software and services Systems designed for a smarter planet New Delivery Models will offer multiple delivery options: managed services, outsourcing, cloud and system offerings Integrated Service Management will enable a fully virtualized infrastructure providing rapid deployment and lower cost Workload Optimizing Systems will deliver systems that optimize for specific client workloads Integrated Services Integrated Software Integrated Systems
Instrumented. Interconnected. Intelligent. There are one billion transistors per human, each costing one ten-millionth of a cent. The information created by a trillion networked things grows exponentially. Algorithms and systems turn mountains of data into actions that make the world better. Smarter.
Smarter Healthcare Health systems can connect people to information, to experts and to each other and can act proactively to better manage and deliver preventive and therapeutic care. 30% Percentage of total data in the world used for medical images
The challenge To accelerate the understanding of the molecular basis of cancer through the application of genome analysis technologies, especially large-scale genome sequencing. The solution Leveraged the performance and virtualization of POWER7 systems to provide researchers with more flexibility and efficiency in analysis across a range of research projects. Using POWER7 to better understand cancer The POWER7 architecture has enabled us to pursue a broader range of research problems on a single system than was possible before … -- Dr. B. Kim Andrews Manager of Research Computing 50% of the roughly 30,000 identified genes have functions that are unknown.
Smarter Energy With little or no intelligence to balance loads or monitor energy flows, enough electricity is lost annually to power India, Germany and Canada for an entire year. 15% Reduction in power usage during peak hours by consumers connected to smart grid systems
The world’s first “smart grid” country Enemalta and Water Services Corporation uses Power Systems to provide Malta with smarter energy and water management The challenge: Malta depends entirely on foreign fuel oil for the production of all of its electricity and for more than half of its water supply, which filters through an energy-intensive desalination process. The solution: After the transformation of both utilities, data from intelligent meters can be analyzed to help lower costs, adopt efficient and sustainable consumption patterns and cut greenhouse gas emissions. Citizens can make smarter decisions about how and when they use power 250,000 interactive meters will monitor electricity usage in real time, set variable rates, and reward customers who consume less energy and water.
Smarter Money Power Systems performance, security and availability are capabilities that provide the world’s largest banks with the ability to move today’s money - intangible, invisible information - from a paycheck to a bank to a retailer and back into another business account. Smarter Cities Cities large and small depend on the ability of Power Systems to sift through the data needed to not only solve crimes and respond to emergencies, but to help prevent them. Power Systems help manage traffic, share information across city agencies, keep citizens informed and give them access to services. Smarter Telecom Telcos are using Power Systems to deliver new services dynamically to an exploding number of devices - and Power’s scalability means that new services can be added quickly, new clients can be billed accurately, and costs can be reduced with consolidation.
Organizations are moving from “what” to “how” How do I infuse intelligence into a system for which no one enterprise or agency is responsible? How do I bring all the necessary constituents together? How do I make the case for budget? How do I get a complex solution through procurement? How do I coalesce support with citizens? Where should I start? How fast should I move? “ ”
Clients are working with IBM to find answers Queensland Motorways leads the way to smart traffic management with IBM Power Systems and SAP The challenge: Implement new free flow tolling Central System to transform QML’s business operations for efficiencies and to set a platform for growth. The solution: Optimized infrastructure, intelligent data mirroring, and increased interconnectedness that helped achieve highest service levels and increased efficiencies 25% total cost of ownership savings due to a fully integrated system that gives citizens total mobility around the city of Brisbane, Australia. In all my years in the workforce I have never been associated with a system implementation that has been as professionally delivered with such commitment. Jeremy Turner - CFO, Queensland Motorways Ltd.
Transformations to “smarter” solutions require smarter systems that: <ul><li>Scale quickly and efficiently </li></ul><ul><li>Optimize workload performance </li></ul><ul><li>Flexibly flow resources </li></ul><ul><li>Avoid downtime </li></ul><ul><li>Save energy </li></ul><ul><li>Automate management tasks </li></ul>
Power your planet. Smarter systems for a Smarter Planet.
Technology leadership <ul><li>4, 6 or 8 cores per socket </li></ul><ul><li>3.0 to 4.14 GHz </li></ul><ul><li>Up to 4 threads per core </li></ul><ul><li>Integrated eDRAM L3 Cache </li></ul><ul><li>Dynamic Energy Optimization </li></ul>
<ul><li>4 Socket 4U </li></ul><ul><li>6 or 8 cores per socket </li></ul><ul><li>3.0 to 3.55 GHz </li></ul><ul><li>Energy-Star Qualified </li></ul>Power 750 Express
POWER7 continues to break the rules with more performance SPECint_rate Itanium HP rx6600 SPARC Sun T5440 x86 HP DL585 POWER7 Power 750 with PowerVM The highest performing 4-socket system on the planet Power 750
The most energy efficient 4-socket system on the planet The first Energy Star certified RISC system Performance Per Watt Most energy efficient systems Power 750 Itanium HP rx6600 SPARC Sun T5440 x86 HP DL585 POWER7 Power 750 with PowerVM
More SAP performance than any 8-socket system in the industry 4-sockets 8-sockets 32-sockets 24-core HP DL585 AMD 32-core Sun T5440 32-core Power 750 48-core Sun x4640 AMD 128-core Sun M9000 48-core HP DL785 AMD 2-sockets 8-core Sun Fire X4270 Xeon 5500 Comparable to a 128-core, 32-socket Sun M9000 15,600 SAP users on SAP SD 2 Tier Power 750 Express with DB2 <ul><li>Best SAP 2-Tier Results for 2, 4 , 8 and 16 sockets. </li></ul><ul><li>See SAP Benchmarks chart for detail or SAP website </li></ul><ul><li>http://www.sap.com/solutions/benchmark/sd2tier.epx </li></ul>
Source: Capacity based on IBM Sizing of typical ERP landscape and IBM estimates of system utilization. Pricing from www.hp.com US$447,969 US$387,760 At equal capacity for two 32 core IBM Power 750 Express systems compared to two HP DL785 G6‘s and nine HP DL380 G6 systems leveraging the higher utilization and virtualization efficiency capabilities of Power. The IBM Power 750 Express configuration saves 75% of the space, 90% of the network connections, and 72% of the systems to manage. Lower TCA
Number of Sun SPARC Enterprise T2000’s that can be consolidated into a single IBM Power 750 4 socket system saving 95% of the cores for software licensing, 97% on floor space, and 95% on energy. 92 to 1
used yearly by the 91,920* Sun SPARC Enterprise T2000 servers shipped since 2005 above what would be used yearly if consolidated into 1,000 IBM Power 750s at the rate of 92 to 1. That’s enough electricity to supply 34,500 homes for a year. 345 million kilowatt-hours 91,920 Sun T2000s 1,000 IBM Power 750s Source: IDC Server Tracker; Wikipedia estimate of average annual household energy use of 10,000 kwH
Superdome or Super Power? Shown to actual scale See Power 750 server compared to HP Integrity Superdome substantiation detail. Source: SPECiint_rate2006. For the latest SPEC benchmark results, visit http://www.spec.org . <ul><li>HP Integrity Superdome 64c </li></ul><ul><li>1.6GHz dual-core Itanium2 in a 30”x77.2”x48” frame </li></ul><ul><li>Maximum energy requirement of 11,586 Watts </li></ul><ul><li>SPECint_rate2006: 824 </li></ul><ul><li>IBM Power 750 Express </li></ul><ul><li>4 socket, 32 Core 4Ux19” wide </li></ul><ul><li>POWER7 Processors </li></ul><ul><li>Maximum energy requirement of 1,950 Watts </li></ul><ul><li>SPECint_rate2006: 1060 </li></ul>83% savings on energy costs with 28% more performance at a fraction of the price using a single IBM Power 750 instead of a 64-core HP Integrity Superdome.
<ul><li>12 or 16 core 4U Nodes </li></ul><ul><li>Up to 4 Nodes per system </li></ul><ul><li>3.1 and 3.5 GHz </li></ul><ul><li>Capacity on Demand </li></ul><ul><li>Enterprise RAS </li></ul>Power 770
<ul><li>New Modular High-End </li></ul><ul><li>Up to 64 Cores </li></ul><ul><li>TurboCore </li></ul><ul><li>3.86 or 4.14 GHz </li></ul><ul><li>Capacity on Demand </li></ul><ul><li>Enterprise RAS </li></ul><ul><li>24x7 Warranty </li></ul><ul><li>PowerCare </li></ul>Power 780
Super Power indeed. Number of HP Integrity Superdome 64-core systems utilized at 30% that can be consolidated into a single IBM Power 780 modular high-end system utilized at 80% saving 87% of the cores for software licensing, reduces floor space required from 80 square feet to just 7.6, and reduces energy costs by 92%. 8 to 1
84% Reduction in energy usage moving from POWER5 to POWER7. Savings extend to floor space, software license costs, and maintenance. Increase your performance and capacity. With room to spare to consolidate x86 workloads POWER5 570 systems 64 cores @ 1.9 GHz 30% utilization 4 50% effective capacity increase 84% reduction in energy usage ~$250K maintenance savings over 3 years > $1M savings in software licensing Power 770 24 cores @ 3.5 GHz 60% utilization 1
IBM Capacity on Demand buys one core of POWER7 performance with up to 8GB of memory on an IBM Power 770 using On/Off Capacity on Demand. If you need to add a temporary Linux server to run a new application server front-end for a few days, would you rather spend thousands on yet another x86 server or just use the Power capacity you need for less than $100 for a business week? US $16 per day
POWER7 High-End Server Statement of Direction <ul><li>IBM plans to deliver a new high-end server in 2010 with up to 256 POWER7 processor cores </li></ul><ul><li>Designed to operate within the same physical footprint and energy envelope of the current 64-core Power 595 server. </li></ul><ul><li>High-Voltage DC Power option </li></ul><ul><li>IBM also plans to provide an upgrade path from the current IBM Power 595 server with 12X I/O to the new POWER7 high-end server. </li></ul><ul><li>Enterprises with multiple systems leveraging PowerVM Live Partition Mobility may use this function to maintain application availability during the upgrade process. </li></ul>All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.
Workload-Optimizing Systems AIX - the future of UNIX Total integration with i Scalable Linux ready for x86 consolidation Power your planet. + Smarter Systems for a Smarter Planet. <ul><li>Virtualization without Limits </li></ul><ul><li>Drive over 90% utilization </li></ul><ul><li>Dynamically scale per demand </li></ul><ul><li>Dynamic Energy Optimization </li></ul><ul><li>70-90% energy cost reduction </li></ul><ul><li>EnergyScale™ technologies </li></ul><ul><li>Resiliency without Downtime </li></ul><ul><li>Roadmap to continuous availability </li></ul><ul><li>High availability systems & scaling </li></ul><ul><li>Management with Automation </li></ul><ul><li>VMControl to manage virtualization </li></ul><ul><li>Automation to reduce task time </li></ul>
Power Systems offers balanced systems designs that automatically optimize workload performance and capacity at either a system or VM level <ul><li>TurboCore ™ for max per core performance for databases </li></ul><ul><li>MaxCore for incredible parallelization and high capacity </li></ul><ul><li>Intelligent Threads utilize more threads when workloads benefit </li></ul><ul><li>Intelligent Cache technology optimizes cache utilization flowing it from core to core </li></ul><ul><li>Intelligent Energy Optimization maximizes performance when thermal conditions allow </li></ul><ul><li>Active Memory ™ Expansion provides more memory for SAP </li></ul><ul><li>Solid State Drives optimize high I/O access applications </li></ul>Workload-Optimizing Features make POWER7 #1 in Transaction and Throughput Computing Power is Workload Optimization
Power is Virtualization without Limits Performance without penalty - all benchmarks published in a virtualized environment Consolidate AIX & i databases with Linux application servers on one system or a system pool Up to 32x the VM size & 8x the memory of VMware and D ynamically add & remove VM resources unlike VMware Live Partition Mobility with VM’s of any size up to entire system unlike VMware Drive systems to over 90% utilization for maximum ROI
All 3 operating environments available with POWER7 The future of UNIX “ For the second year in a row, AIX scored the highest reliability ratings among 15 different server operating system platforms” - ITIC 2009 Total integration with i “ Costs for use of Power Systems and IBM i 6.1 average 41 % less than x86 servers and Microsoft Windows” - ITG 2010 Scalable Linux ready for x86 consolidation Queensland Motorways replaced legacy Windows x86 traffic management systems with new SAP running Linux on Power
PowerHA SystemMirror for AIX and i provide active/standby datacenter and multi-site disk clustering solutions for resiliency PowerHA pureScale provides active/active high performance data transfer, cluster coordination, and centralized locking and is built-into DB2 pureScale PowerVM Live Partition Mobility enables planned system downtime without application downtime Power is Resiliency without Downtime
Power is Dynamic Energy Optimization POWER7 delivers up to 3 - 4X the performance with less energy than POWER6 Increased consolidation drives higher utilization and more energy savings EnergyScale™ intelligently and dynamically optimizes performance for energy efficiency IBM Systems Director Active Energy Manager helps lower energy usage per system and across systems
Physical assets & virtual resources at your fingertips with easy health monitoring & reporting, as well as updates & optimization VMControl™ for automation of virtualization management to minimize time to provision images and manage system pools Easy integration with enterprise service management tools from Tivoli as well as other third party providers Power is Management with Automation Server and virtualization management integrated with network and storage management for complete resource control
Express Edition Included with every Power System Standard Edition Express + virtual images, energy, network IBM Systems Director Editions Enterprise Edition Standard + manages systems pools, Tivoli additions
IBM Systems Director Editions IBM Smart Analytics System IBM DB2 pureScale IBM Lotus Domino Consolidation on Power IBM Rational Developer for Power IBM WebSphere Application Server Parallelization SAP on IBM DB2 and Power Systems Power is Integrated Value
Workload Optimized Pools Smarter systems for a Smarter Planet. Database Pool TurboCore MaxCore Intelligent Threads Active Memory Expansion Analytics Pool Web Applications Pool New volume, velocity and nature of data <ul><li>Manage the mountains of data from devices, sensors, clients and partners </li></ul>New instrumented applications <ul><li>Connections to the “Internet of things” - the trillions of interconnected devices feeding real-time information in parallel </li></ul>New intelligence <ul><li>Gain valuable insights and intelligence from advanced analytics across the data and incoming streams </li></ul>
Power Systems and IBM Software Massive parallelism for smarter planet solutions <ul><li>Massively parallel - up to 1024 threads </li></ul><ul><li>Middleware that transparently leverages massively parallel threads </li></ul><ul><li>Superior qualities of service </li></ul><ul><li>Hardware exploitation without application redesign </li></ul><ul><li>Best performance and lowest TCO </li></ul>
Power Systems and IBM Storage Systems Designed together to meet the demands of a smarter planet <ul><li>IBM Scale Out Network Attached Storage (SONAS) provides enterprise-wide access to information for cloud implementations, with an easy-to-use single namespace and up to 14 PBs of storage </li></ul><ul><li>IBM XIV delivers next generation storage with exceptionally low TCO, capacity without complexity and storage administration made easy </li></ul><ul><li>IBM SAN Volume Controller for storage virtualization to simplify operations and better utilize disk capacity </li></ul>45% <ul><ul><li>The increase in storage capacity requirements per year, while information is doubling every 18 months </li></ul></ul>
Power is... Workload-Optimizing Systems Virtualization without Limits Resiliency without Downtime Dynamic Energy Optimization Management with Automation Integrated Value
Power your planet. Smarter systems for a Smarter Planet.
The IBM Power™ 750 Express is the highest performing 4-socket system on the planet. In addition it outperforms all other non-IBM 8 and 16-socket systems <ul><li>Substantiation : </li></ul><ul><li>Competitive benchmark results reflect results published as of February 3, 2010. The results are the best results for four-socket single (non-clustered) systems using POWER ™ , Intel® x86, AMD Opteron ™ x86, SPARC and Intel Itanium® processors. IBM Power 750 result submitted on February 8, 2010. </li></ul><ul><li>SPEC® and the benchmark names SPECrate®, SPECint®, and SPECjbb® are registered trademarks of the Standard Performance Evaluation Corporation. For the latest SPEC benchmark results, visit http:// www.spec.org </li></ul>* Peak = SPECint_rate2006 (Peak) 753 2 4 16 64 Sun SPARC Enterprise M8000 1049 1 6 16 96 Unisys ES7000 Model 7600R, Intel Xeon X7460, 2.66 GHz 209 1 2 8 16 HP Integrity rx8640 (1.6 GHz/24MB Dual-core Intel Itanium 2) 296 2 4 8 32 Sun SPARC Enterprise M5000 527 1 6 8 48 Unisys ES7000 Model 7600R, Intel Xeon X7460, 2.66 GHz 800 1 6 8 48 HP ProLiant DL 785 G6 (2.8 GHz AMD Opteron 8439 SE) 152 2 4 4 16 Sun SPARC Enterprise M4000 360 8 8 4 32 Sun SPARC Enterprise T5440 291 1 6 4 24 HP ProLiant DL580 G5 (2.66 GHz, Intel Xeon X7460) 102 1 2 4 8 HP Integrity rx6600 (1.6 GHz/24MB Dual-core Intel Itanium 2) 416 1 6 4 24 HP ProLiant DL585 G6 (2.8 GHz AMD Opteron 8439 SE) 1060 4 8 4 32 IBM Power 750 Peak* Threads/Core Cores/Chip Chips Cores System Name
The IBM Power 750 Express is the most energy efficient 4-socket system on the planet. <ul><li>Substantiation : </li></ul><ul><li>Competitive benchmark results reflect results published as of February 3, 2010. The results are the best results for four-socket single (non-clustered) systems using POWER, Intel x86, Opteron x86, SPARC and Itanium processors. IBM Power 750 result submitted on February 8, 2010. </li></ul><ul><li>SPEC and the benchmark names SPECrate, SPECint, and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. For the latest SPEC benchmark results, visit http:// www.spec.org </li></ul><ul><li>Performance/WATT is calculated by dividing the performance from the tables below by the recommended maximum power usage for site planning. This defines the requirement for the power infrastructure. Actual power used by the systems will be less than this value for all of the systems. For Power Systems™ servers, this information is available in the site planning guides available through www.ibm.com. For HP systems, this information is contained in the QuickSpecs for each system available through www.hp.com . </li></ul><ul><li>For Sun systems, this information is available through the Site Planning Guides available through www.sun.com . </li></ul>* Peak = SPECint_rate2006 (Peak) 0.07 2016 152 2 4 4 16 Sun SPARC Enterprise M4000 0.13 2700 360 8 8 4 32 Sun SPARC Enterprise T5440 0.20 1412 291 1 6 4 24 HP ProLiant DL580 G5 (2.66 GHz, Intel Xeon X7460) 0.06 1600 102 1 2 4 8 HP Integrity rx6600 (1.6 GHz/24MB Dual-core Intel Itanium 2) 0.26 1548 416 1 6 4 24 HP ProLiant DL585 G6 (2.8 GHz AMD Opteron 8439 SE) 0.54 1950 1060 4 8 4 32 IBM Power 750 Peak / WATT WATTs Peak* Threads/Core Cores/Chip Chips Cores System Name
The IBM Power 750 Express has more SAP performance than any 8-socket system in the industry – and is even comparable to a 128-core, 32-socket Sun M9000. <ul><li>Substantiation : </li></ul><ul><li>All results are 2-tier, SAP EHP 4 for SAP ERP 6.0 (Unicode). IBM results valid as of 2/8/2010. Competitive results valid as of 2/3/2010. </li></ul><ul><li>IBM Power 750 Express certification number not available at press time and can be found at www.sap.com /benchmarks . </li></ul><ul><li>IBM Power 750 Express: 4p / 32–c / 128 – t, POWER7™, 3.55 GHz, 256 GB memory, 15,600 SD users, dialog resp.: 0.98s, line items/hour: 1,704,330, Dialog steps/hour: 5,113,000, SAPS: 85,220, DB time (dialog/ update):0.015s / 0.028s, CPU utilization: 99%, AIX® 6.1, DB2® 9.7 </li></ul><ul><li>Sun SPARC Enterprise T5540: 4p / 32-c / 256 –t, UltraSPARC T2 plus OC, 1.6 GHz, 256 GB memory, 4720 SD users, dialog resp: 0.97s, line items/hour: 516,670, dialog steps/hour: 1,550,000, SAPS: 25,830, Solaris 10, Oracle 10g , cert# 2009026-1 </li></ul><ul><li>HP DL585 G6: 4p / 24-c / 24-t, AMD Opteron 8439 SE, 2.8 GHz, 64 GB memory, 4665 SD users, dialog resp: 0.96s, line items/hour: 510,670, dialog steps/hour: 1,532,000, SAPS: 25,530, Windows Server 2008 EE, , SQL Server 2008, cert#: 2009025 </li></ul><ul><li>HP DL785 G6: 8p / 48-c / 48-t, AMD Opteron 8439 SE, 2.8 GHz, 128 GB memory, 8280 SD users, dialog resp: 0.96s, line items/hour: 907,000, dialog steps/hour: 2,721,000, SAPS: 45,350, Windows Server 2008 EE, , SQL Server 2008, cert#: 2009035 </li></ul><ul><li>Sun Fire x4640: 8 p / 48-c / 48–t, Six-core AMD Opteron 8435, 2.6 GHz, 256 GB memory, 10,000 SD users, dialog resp: 0.9s, line items/hour: 1,101,330, dialog steps/hour: 3,304,000, SAPS: 55,070, Solaris 10, Oracle 10g, cert# 2009049 </li></ul><ul><li>HP DL380 G6: 2p / 8-c / 16-t, Intel Xeon® X5570, 2.93 GHz, 48 GB memory, 3171 SD users, dialog resp: 0.94s, line items/hour: 347,670, dialog steps/hour: 1,043,000, SAPS: 17,380, SUSE Linux® Enterprise Server 10, MaxDB 7.8, cert#: 2009006 </li></ul><ul><li>Sun SPARC Enterprise M9000: 32 p / 128-c / 256–t, Six-core AMD Opteron 8435, 2.6 GHz, 1 TB memory, 17,430 SD users, dialog resp: 0.95s, line items/hour: 1,909,670, dialog steps/hour: 5,729,000, SAPS: 95,480, Solaris 10, Oracle 10g, cert# 2009038 </li></ul>
Consolidation onto POWER7 can deliver significant savings. Ninety-two Sun SPARC Enterprise T2000 servers can be consolidated into a single IBM Power 750 Express system, saving 95% of the cores for software licensing, 97% on floorspace, and 95% on energy. Calculation Summary : the Power 750 has 30.93 better SPECjbb2005 performance than the Sun T2000. Assuming a 3x virtualization factor for greater consolidation - then 92 Sun Fire T2000 servers could be consolidated onto one Power 750 Express server (30.93 * 3 = 92.8 servers rounded to 92 T2000 servers) Substantiation 1. SPEC and the benchmark names SPECrate, SPECint, and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. Competitive benchmark results stated reflect results published on www.spec.org as of February 08, 2010. The comparison presented below is based on a consolidation of a legacy 8-core Sun SPARC Enterprise T2000 UltraSPARC T1 servers into a 32 core IBM Power 750. For the latest SPEC benchmark results, visit http:// www.spec.org . 2. SPECjbb2005 results are: POWER7 : IBM Power 750 Express with 4 chips, and 32 cores and four threads per core with a result of 2,300,000 bops and 71,875 bops/jvm submitted to SPEC on February 8, 2010. SPARC : Sun Microsystems Sun SPARC Enterprise T2000 with 1 chip, 8 cores and 4 threads per core with a result of 74,356 bops and 18,591 bops/jvm * The virtualized system count and energy savings were derived from several factors: - A performance ratio factor of 30.93X was applied to the virtualization scenario. The performance factor is the SPECjbb2005 result of the Power 750 Express divided by the result of the competitive Sun SPARC Enterprise T2000 server. - A virtualization factor of 3X was applied to the virtualization scenario using utilization assumptions derived from an Alinean white paper on server consolidation. The tool assumes 19% utilization of existing servers and 60% utilization of new servers. Source - www.ibm.com/services/us/ cio / optimize / opt_wp_ibm_systemp.pdf . Space calculation: The Sun T2000 is 2U in height and 21 can fit into a 42U rack. The 750 is 4U in height. Power consumption figures of 1950W for the IBM Power 750 and 450W for the Sun T2000 were based on the maximum rates published by IBM and Sun Microsystems, respectively. This information for the Power 750 is in "Model 8233-E8B server specifications" available at http://www-01.ibm.com/common/ssi/index.wss - search for Power 750. Sun T2000 Maximum AC power consumption of 450 WATTs was sourced from Sun SPAC Enterprise T2000 Servers site planning guide at http://docs.sun.com/app/docs/doc/819-2545-11 as of 2/9/2010. 18,591 74,365 Yes 1 8 4 Sun File T2000 77,467 2,478,929 Yes 4 32 32 IBM Power 750 Express bops/JVM bops HW Threading Processor chips Cores JVM Instances HW System Name 97.8% 95.2% 95.6% Savings with Power 750 Express 184 41,400 736 1,368,150 92 8 2 450 74,365 Sun File T2000 4 1950 32 1,380,000 1 32 4 1950 2,478,929 IBM Power 750 Express Total Rack Space Total Watts Total Cores Total Perf Systems Cores Rack space Max Watts SPECjbb2005 System Name
345 million kilowatt-hours are used yearly by the 91,920* Sun SPARC Enterprise T2000 servers shipped since 2005 above what would be used yearly if consolidated into 1,000 IBM Power 750 Express servers at the rate of 92 to 1. That’s enough electricity to supply 34,500 homes for a year.** <ul><li>Substantiation </li></ul><ul><li>- Maximum power for 1 IBM Power 750 Express server = 1950 watts </li></ul><ul><li>- Maximum power for 92 Sun Fire T2000 servers = 92 x 450 = 41,400 watts </li></ul><ul><li>- Excess power per consolidation instance (92 Sun T2000’s into one Power 750) = 39,450 watts </li></ul><ul><li>- Number of consolidations required = 1,000 (91,320 / 92) </li></ul><ul><li>- Total excess kilowatt-hours per year = </li></ul><ul><li>39,450 watts x 24 hrs/day x 365 days/yr x 1,000 = 345 million kilowatt-hours per year </li></ul><ul><li>* Source: 3Q09 IDC Server Tracker </li></ul><ul><li>** Source: Wikipedia estimate of average annual household energy use of 10,000 kilowatt-hours </li></ul>
The IBM Power 750 Express has 28% more performance than a 64-core HP Integrity Superdome and requires only 83% as much power to run – at a fraction of the price. <ul><li>Substantiation : </li></ul><ul><li>Notes: </li></ul><ul><li>1. SPEC and the benchmark names SPECrate, SPECint, and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. HP Integrity Superdome benchmark results stated reflect results published on www.spec.org as of February 08, 2010. For the latest SPEC benchmark results, visit http:// www.spec.org . </li></ul><ul><li>2. SPECint_rate2006 Peak results are: </li></ul><ul><li>POWER7: IBM Power 750 Express with 4 chips, and 32 cores and four threads per core with a result of 1060 submitted to SPEC on February 8, 2010. </li></ul><ul><li>Itanium: Hewlett-Packard Integrity Superdome with 32 chips, 64 cores, and one thread per core with a result of 824. </li></ul><ul><li>3. The HP Integrity Superdome is a rack cabinet. The 750 is 4U in height. </li></ul><ul><li>Power consumption is derived from the recommended maximum power for site planning. Actual power used by the systems will be less than this value for all of the systems. </li></ul><ul><li>This information for the Power 750 Express is available at http://www-01.ibm.com/common/ssi/index.wss - search for Power 750. The maximum power requirement for the Power 750 is 1,950 Watts. </li></ul><ul><li>The information for the Integrity Superdome is in "QuickSpecs HP Integrity rx6600 Server" available at http://h18000.www1.hp.com/products/quickspecs/11717_div/11717_div.HTML , which shows the maximum power requirement for the Integrity Superdome of 12,196 VA. Using the Power Factor of 0.95 shown at http:// www.spectra.com/pdfs/superdome.pdf , the maximum input power is 11,586 Watts. </li></ul><ul><li>Price comparison based on IBM analysis : </li></ul><ul><li>HP Superdome price estimated at $2,117,000 for the configuration described in the SPECint_rate2006 benchmark </li></ul><ul><li>IBM Power 750 Express U.S. list price = $275,420 </li></ul>
The IBM Power 780 delivers leadership performance and consolidation capability vs. HP and Sun high-end servers. For example, eight HP Integrity Superdome 64‑core systems utilized at 30% can be consolidated into a single IBM Power 780 server utilized at 80%, thus saving 87% of the cores for software licensing, reducing floorspace from 80 square feet to 7.6 square feet, and reducing energy costs by 92%. <ul><li>Performance per watt is calculated by dividing the performance in the table above by the recommended maximum power for site planning. Actual power used by the systems will be less than this value for all of the systems. The maximum power requirement for the Power 780 is 6,400 Watts and is available at http://www-01.ibm.com/common/ssi/index.wss - search for Power 780. </li></ul><ul><li>Power consumption figures of 6400 W for the IBM Power 780, 12,196 W / 24,392 W for the HP Superdome and 44,800 W for the Sun SPARC Enterprise M9000 were based on the maximum rates published by IBM, HP and Sun Microsystems, respectively. The information for the HP Integrity Superdome is in “QuickSpecs HP Integrity Superdome Servers 16- processor, 32-processor, and 64- processor Systems” available at www.hp.com . The information for the Sun SPARC Enterprise M9000 is in the "Sun SPARC Enterprise M9000 Servers Site Planning Guide" available at www.sun.com </li></ul><ul><li>. </li></ul><ul><li>The virtualized system count and energy savings were derived from several factors: </li></ul><ul><li>A performance ratio factor was applied to the virtualization scenario based on SPECint_rate2006. The performance factor is simply the SPECint_rate2006 result per core of the Power 780 divided by the per core result of the HP or Sun system. </li></ul><ul><li>Power 780 (64-core, 8 chips, 8 cores per chip, 3.8 GHz) SPECint_rate2006 2,530 peak as of 2/8/2010. HP Superdome (64-core, 32 chips, 2 cores per chip) 1.6 GHz, SPECint_rate2006 824 peak published October 2006. Data valid as of 2/3/2010. </li></ul><ul><li>Sun SPARC Enterprise M9000 (256-core, 64 chips, 4 cores per chip) 2.88 GHz, SPECint_rate2006 2,586 peak published October 2009. Data valid as of 2/3/2010. SPEC® results available at: www.spec.org . </li></ul><ul><li>A virtualization factor of 3.157X was applied to the virtualization scenario using utilization assumptions derived from an Alinean white paper on server consolidation. The tool assumes 19% utilization of existing servers and 60% utilization of new servers. Source - www.ibm.com/services/us/ cio / optimize / opt_wp_ibm_systemp.pdf . </li></ul><ul><li>Air conditioning power requirement estimated at 50% of system power requirement. </li></ul><ul><li>Energy cost of $.1031 per kWh is based on 2009 YTD US Average Retail price to commercial customers per US DOE at http://www.eia.doe.gov/cneaf/electricity/epm/table5_6_b.html as of 1/27/2010. </li></ul><ul><li>The reduction in floor space, power, cooling and software costs depends on the specific customer, environment, application requirements, and the consolidation potential. Actual numbers of virtualized systems supported will depend on workload levels for each replaced system. </li></ul><ul><li>System data for HP from the HP Superdome Datasheet and HP Integrity Superdome Server — specifications both available at www.hp.com . System data for Sun from the Sun SPARC Enterprise M9000 Tech Specs available at www.sun.com . Data is current as of January 27, 2010. </li></ul>Substantiation :
The modular enterprise class POWER systems have continued to deliver significant improvements year over year. With the Power 770 server, clients can consolidate four POWER5™ processor-based Power 570 systems onto one Power 770. In fact, it only takes two nodes and moving to the Power 770 still has an effective capacity increase of 50%. Substantiation : 84% Less Energy > 50% Capacity 87% Less Space Advantage / Savings 20,800 92.9 30% 309.8 16 64 IBM System p® 570 (x4) 3200 156.7 60% 261.19 2 24 IBM Power 770 Maintenance WATTs Effective Performance Utilization rPerf Nodes Cores System Name
POWER7 systems deliver up to three or four times the energy efficiency of POWER6™ based systems. <ul><li>Substantiation : </li></ul><ul><li>SPEC and the benchmark names SPECrate, SPECint, and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. Benchmark results stated reflect results published on www.spec.org as of </li></ul><ul><li>February 8, 2010. The comparison used in the claim is based on a consolidation of the best high-end POWER6 result (Power 595) to the Power 780, the best mid-range POWER6 result (Power 570) to the Power 770, and the best four-socket and above POWER6 Express results with the Power 750 Express. For the latest SPEC benchmark results, visit http:// www.spec.org . </li></ul><ul><li>Performance/WATT is calculated by dividing the performance from the tables below by the recommended maximum power usage for site planning. This defines the requirement for the power infrastructure. Actual power used by the systems will be less than this value for all of the systems. This information is available in the site planning guides available through www.ibm.com . </li></ul>0.18 1400 263 2 2 4 8 IBM Power 550 Express 0.15 2400 363 2 2 8 16 IBM Power 560 Express 0.54 1950 1060 4 8 4 32 IBM Power 750 Express 0.09 5600 542 2 2 8 16 IBM Power 570 0.31 6400 2013 4 8 8 64 IBM Power 770 0.07 28300 2160 2 2 32 64 IBM Power 595 0.39 6400 2530 4 8 8 64 IBM Power 780 Peak / WATT WATTs Peak Threads/ Core Cores/ chip Chips Cores System Name SPECint_rate2006 results as of January 7, 2010
POWER7 systems deliver up to three or four times the performance with less energy than POWER6 based systems. <ul><li>Substantiation : </li></ul><ul><li>rPerf (Relative Performance) is an IBM estimate of commercial processing performance relative to other IBM UNIX® systems. </li></ul><ul><li>The comparison used in the claim is based on these comparisons: </li></ul><ul><ul><li>4-node Power 570 (POWER6+™) to a 1-node Power 780 (POWER7) </li></ul></ul><ul><ul><li>4-node Power 570 (POWER6+) to a 3‑node Power 780 (POWER7) </li></ul></ul><ul><ul><li>4-node Power 570 (POWER6+) to a 3-node Power 770 (POWER7) </li></ul></ul><ul><ul><li>2-node Power 560 Express (POWER6+) to Power 750 Express (POWER7) </li></ul></ul><ul><li>Performance/WATT is calculated by dividing the performance (rPerf) from the tables below by the recommended maximum power usage for site planning. This defines the requirement for the power infrastructure. Actual power used by the systems will be less than this value for all of the systems. This information is available in the site planning guides available through www.ibm.com . </li></ul>* Factor = Performance increase factor of POWER7 system over POWER6 system for less energy - 100 2400 3.6 Ghz POWER6+ 2 IBM Power 560 Express 3.3 331 1950 3.55 GHz POWER7 1 IBM Power 750 Express - 141 5600 5.0 GHz POWER6+ 4 IBM Power 570 3.1 443 4800 3.1 GHz POWER7 3 IBM Power 770 - 141 5600 5.0 GHz POWER6+ 4 IBM Power 570 3.7 523 4800 3.8 GHz POWER7 3 IBM Power 780 - 141 5600 5.0 GHz POWER6+ 4 IBM Power 570 1.38 195 1600 3.8 GHz POWER7 1 IBM Power 780 Factor* (P7 over P6) rPerf Energy (Watts) Proc. Freq. Processor Technology Nodes System Name
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. All prices shown are IBM's United States suggested list prices and are subject to change without notice; reseller prices may vary. 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 September 26, 2006
Special notices (cont.) IBM, the IBM logo, ibm.com AIX, AIX (logo), AIX 6 (logo), AS/400, Active Memory, BladeCenter, Blue Gene, CacheFlow, 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, AIX 5L, Chiphopper, Chipkill, Cloudscape, DB2 Universal Database, DS4000, DS6000, DS8000, EnergyScale, Enterprise Workload Manager, General Purpose File System, , GPFS, HACMP, HACMP/6000, HASM, IBM Systems Director Active Energy Manager, iSeries, Micro-Partitioning, POWER, 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, POWER7, pureScale, System i, System p, System p5, System Storage, System z, Tivoli Enterprise, TME 10, TurboCore, 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 ™), 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 current list of IBM trademarks is available on the Web at "Copyright and trademark information" at www.ibm.com/legal/copytrade.shtml 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. UNIX is a registered trademark of The Open Group in the United States, other countries or both. Linux is a registered trademark of Linus Torvalds in the United States, other countries or both. Microsoft, Windows and the Windows logo are registered trademarks of Microsoft Corporation in the United States, other countries or both. Intel, Itanium, Pentium are registered trademarks and Xeon is a trademark of Intel Corporation or its subsidiaries in the United States, other countries or both. AMD Opteron is a trademark of Advanced Micro Devices, Inc. Java and all Java-based trademarks and logos are trademarks of Sun Microsystems, Inc. in the United States, other countries or both. TPC-C and TPC-H are trademarks of the Transaction Performance Processing Council (TPPC). SPECint, SPECfp, SPECjbb, SPECweb, SPECjAppServer, SPEC OMP, SPECviewperf, SPECapc, SPEChpc, SPECjvm, SPECmail, SPECimap and SPECsfs are trademarks of the Standard Performance Evaluation Corp (SPEC). NetBench is a registered trademark of Ziff Davis Media in the United States, other countries or both. AltiVec is a trademark of Freescale Semiconductor, Inc. Cell Broadband Engine is a trademark of Sony Computer Entertainment Inc. InfiniBand, InfiniBand Trade Association and the InfiniBand design marks are trademarks and/or service marks of the InfiniBand Trade Association. Other company, product and service names may be trademarks or service marks of others. Revised February 9, 2010
Notes on benchmarks and values 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, AIX Version 4.3, AIX 5L or AIX 6 were used. All other systems used previous versions of AIX. The SPEC CPU2006, SPEC2000, 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 Enterprise Edition V7.0 for AIX, XL C/C++ Enterprise Edition V7.0 for AIX, XL FORTRAN Enterprise Edition V9.1 for AIX, XL C/C++ Advanced Edition V7.0 for Linux, and XL FORTRAN Advanced Edition V9.1 for Linux. The SPEC CPU95 (retired in 2000) tests used preprocessors, KAP 3.2 for FORTRAN and KAP/C 1.4.2 from Kuck & Associates and VAST-2 v4.01X8 from Pacific-Sierra Research. The preprocessors were purchased separately from these vendors. Other software packages like IBM ESSL for AIX, MASS for AIX and Kazushige Goto’s BLAS Library for Linux were also used in some benchmarks. 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 Applications http://www.oracle.com/apps_benchmark/ PeopleSoft - To get information on PeopleSoft benchmarks, contact PeopleSoft directly Siebel http://www.siebel.com/crm/performance_benchmark/index.shtm 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 March 12, 2009
Notes on HPC benchmarks and values Revised March 12, 2009 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, AIX Version 4.3 or AIX 5L were used. All other systems used previous versions of AIX. The SPEC CPU2000, 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 Enterprise Edition V7.0 for AIX, XL C/C++ Enterprise Edition V7.0 for AIX, XL FORTRAN Enterprise Edition V9.1 for AIX, XL C/C++ Advanced Edition V7.0 for Linux, and XL FORTRAN Advanced Edition V9.1 for Linux. The SPEC CPU95 (retired in 2000) tests used preprocessors, KAP 3.2 for FORTRAN and KAP/C 1.4.2 from Kuck & Associates and VAST-2 v4.01X8 from Pacific-Sierra Research. The preprocessors were purchased separately from these vendors. Other software packages like IBM ESSL for AIX, MASS for AIX and Kazushige Goto’s BLAS Library for Linux were also used in some benchmarks. 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
Notes on performance estimates <ul><li>rPerf for AIX </li></ul><ul><li>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. </li></ul><ul><li>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. </li></ul><ul><li>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. </li></ul><ul><li>======================================================================== </li></ul><ul><li>CPW for IBM i </li></ul><ul><li>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 </li></ul>Revised April 2, 2007