Jump on the Cloud

Like this? Share it with your network

Share

Jump on the Cloud

  • 1,520 views
Uploaded on

In this session, Gordon Graylish will review how Intel is playing a leading role to enable internet expansion through the embedded internet and enabling Cloud computing to be realized through the......

In this session, Gordon Graylish will review how Intel is playing a leading role to enable internet expansion through the embedded internet and enabling Cloud computing to be realized through the evolution of infrastructure capabilities that hold the promise of greater efficiencies, less complexity, improved asset utilization and reduced TCO.

More in: Technology , Business
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
No Downloads

Views

Total Views
1,520
On Slideshare
1,520
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
37
Comments
0
Likes
1

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide
  • Good morning folks.On behalf of Intel, I’d like to thank you for investing your time with us.Now – if you were looking for a 65 slides roadmap pitch focused on feeds, speeds, bits, bytes, you might go home a little disappointed.This has a lot more to do with innovation, investment and opportunities for business growth by combining technological innovation, business savvy to create value add solutions and opportunities I would imagine and hope you would all care about. We’ll start with a quick reminder of some of the environmental factors we’re all dealing with – but how – in spite of those the environment is really an opportunity for shrewd investment, continued innovation and inspiring our customers to invest their way out the downturn – yes – I did say investing!
  • CIO’s wont be able to resist the forces that will drive innovation and the required changes in infrastructure, if they are to compete. In our view, these forces are:Faster clock speed – This is business clock speed and not CPU clock speed  FSI as the poster child. 1ms + $100M … and we know the thirst for performance doesn’t end with that industry.Innovation Beyond the Firewall – Companies focusing on core competencies and outsourcing many capabilities that are traditionally in house IT. Saas, Web2.0 play a role in this. IT becomes responsible for a virtual enterprise: manageability, security, QoS are all challenges in this environment.Extreme mobility – iPhone, WiMax, desktop/mobile cross-over (2009 it will hit), people expect the full experience in smaller form factors.The World is Green – power/thermal focus and the value-add environmental restrictions and compliance issues. No longer nice to have – now legislated compliance. The World is Flat – Tom Freidman book. Need to integrate seamlessly between companies supply chains. In fact, McKinsey predicts that 30% of the Global GDP in 2015 will consist of cross-border trade. SOA and Business Process play big roles here. What does it mean in our terms? There are lots of existing and emerging technologies that form the basis of and provide the ingredients for much of this. For our customers, it means that boundaries are blurring.
  • Cloud is a business/organization model and a trend in service delivery. The business model attracts the attention but it's the service delivery trend that is the most compelling. You have to adopt cloud to reduce you costs significantly. And, the cloud is made possible through technology innovation. This is Intels role – technology innovation for the infrastructure, or foundation for the cloud.
  • There are 2 types of primary cloud environments that exist today. Private enterprise clouds and public service provider clouds. An enterprise private cloud is a cloud architecture that’s for internal use behind the corporate firewall, designed to deliver “IT as a service”. Examples of software that enable private cloud deployments includes Canonical, Citrix, Red Hat, Univa, Vmware, among others. There are similarities with a public cloud in that enterprise private clouds are meant to be scalable and provide use based IT services. But compared to public clouds, private enterprise clouds typically deliver greater levels of security, much better ability to manage compliance and audit and provide for interoperability within the datacenter infrastructure. A public service provider cloud resides on the public internet, typically with pay as you go usage models. Example of public cloud services include commercial offerings that deliver applications (e.g. Salesforce CRM) or virtual infrastructure for a fee (e.g. Amazon’s EC2, AT&T Synaptic Hosting). Public clouds have the benefit of providing rapid deployments, reduced up front costs of new IT equipment, and ability to take advantage of expertise of external suppliers of IT. As an example, Intel IT is using public cloud service providers for Intel’s employee benefits information and expense processing. Virtual private clouds, like Amazon Virtual Private Cloud, is meant to provide secure access via a VPN to public cloud resources that are isolated and available to only one company vs a public cloud that is “multi-tenant” where multiple companies share the same resources. A virtual private cloud is also meant to extend existing company’s IT security protocols, firewalls and intrusion detection systems into a virtual provide cloud. VPN is an example of a hybrid cloud that provides the benefit of security and dedicated resources, but also the economies of a public cloud service provider. Another example of a hybrid cloud is ‘cloud bursting” where an enterprise can take advantage of a service providers capacity when internal capacity is exceeded.Cloud brokers – cloud brokers may emerge that provide linkages between cloud service providers and end users, providing guidance on choosing the right platforms, deploying apps, and managing the engagement. They may help federate data and apps across multiple clouds. This is still emerging. Some examples of SW vendors that are creating applications to enable enterprise to build private cloudsCanonical: Commercial sponsor of a leading open source Linux OS, Ubuntu (founded in 2004, HQ in Europe); Ubuntu Enterprise Cloud is an Open Source software stack that complements Eucalyptus allowing for the implementation of a private cloud infrastructure using a combination of Canonical and Eucalyptus Systems technologies; http://www.ubuntu.com/cloud Citrix: Citrix Cloud Center (C3) is an integrated portfolio of Citrix delivery infrastructure products packaged and marketed to the cloud service provider market. For our Cloud Builder program though, we are still discussing the specific products we will test. This is WIP.  Enomaly: Enomaly Elastic Compute Platform (ECP) Service Provider Edition is a complete "cloud in a box" solution, enabling telcos and hosting providers to deliver revenue-generating Infrastructure-on-demand (IaaS) cloud computing services to their customers, quickly and easily, with a compelling and highly differentiated feature set. founded in 2004, based in Toronto, Canada Microsoft: we plan is to run their Dynamic Datacenter Toolkit, targeted at Hosters, in Cloud Builder test bed near end of Q1/early Q2. Parallels: As part of ICBP program and MOU we put in place with Parallels, Intel and Parallels are working together to deliver an end-to end software and hardware stack. Parallels has their own open source based Cloud Automation architecture. Focus is to help Mass Market hosters and Telco Service Providers to launch new services and transition from traditional hosting to Cloud Services quickly and more cost effectively. Note: we are showcasing Cloud Builder and partnership during Parallels Summit event in February.  Red Hat: Red Hat’s cloud management stack is under development; continued discussions to align with their stack in Cloud Builder when ready.  Univa:Univa offers a full Cloud Lifecycle Management suite for building and enabling private, hybrid and public cloud infrastructures. They have a particular focus on enterprise and HPC segments. Founded in 2000, based in Illinois. We are doing a private cloud computing webcast with them next week (Billy Cox presenting)  VMware: Specific plans in development, offering the Vcloud suite of software. Plan to test in Cloud Builder test bed a version of vCloud/Redwood when ready.
  • There are several challenges to the ramp of cloud services and environments, both technology related and also business and IP related. Technology maturationSecurity / privacy is a major concern– once data is off premise in the cloud, it may be easier to access by criminals, spies or competitors. Today’s cloud services providers do not offer extensive guarantees or remedy in case of data breachLack of automation – to drive greater efficiencies and there is a need for more flexible, automated resource pools that scale dynamically to manage service level agreements, enable workload migration from server to server, and be more power aware to migrate workloads based on power consumption. This level of automation is still evolving. Energy Constraints– NOTE: Energy contraints will hold back build out of the build out of the cloud as data centre power/thermal limits are reached, in other words the physical constraints of the DC will inhibit growth. IDC is projecting datacenter power and cooling costs to grow at 8X faster than spend on new servers. Even greater levels of power efficiency are needed - across servers, racks, and entire datacenters - to improve TCO and keep a lid on power costs. Acceptance of risk IP protection – relating back to security, the need to protect core intellectual property, a company’s “crown jewels”, is of paramount importance to many companies. Interoperability and lock in – for cloud to be truly realized to provide for more automation, shared and dynamic resources and federation of multiple cloud environments together in a seamless way requires interoperability and standards based hardware and software. There is a lack of standards today to address the needs for interoperability. Governance may be an issue – public clouds are the least transparent externally sourced service delivery method, storing and processing data externally in multiple unspecified locations, often sourced from other unnamed providers and containing data from multiple customersQuality of service is not guaranteed – few public cloud providers offer any reassurances on continuity of service, mean time to repair or data recovery, meaning services are unreliable for mission-critical applicationsCompliance/audit becomes complex - For example, public cloud service providers could migrate data to another country where power is cheaper, but regulation laxer. Who will own the legal responsibilities for data management, data retention, record transparency and accounting accuracy as required by many regulatory agencies? To date, no major cloud offering company is willing (or financially able) to provide the kind of assurance and insurance that would be required for large companies to take this risk
  • Business unit expectations – illusion of infinite resource Sense of ownership and security Self service Data center requirement – massive scale, multi tenancy, low TCO Massive scale and multi tenancy relate to federated and automated.Multi tenancy relates to the automated and dynamically allocated resource model
  • To achieve the Cloud, we already discussed the need for a cloud architecture. And if we’re to address the barriers holding back the cloud today and enable a full realization of cloud attributes – there are some fundamental principles that need to be designed into the architecture from the start.Efficient: today data centers consume 1-2% of the world’s energy. If storage, network and compute grow at the hockey stick rates , then we’ll rapidly consume energy, deplete natural resources and spend a lot of unneeded money. We also need to maximize the resources we do have to get more out of them – higher server utilization, better throughput for network and storage traffic and storage optimized by data type and need.Secure: one of the top concerns in the industry related to cloud is security. Is the service I am using secure and reliable? Is it safe to have my company’s data located on the same server as someone else’s? Is my data safe from corruption, unauthorized access and loss? Can I meet security compliance and audit guidelines such as financial reporting, control of personnel data and indemnification? Some recent examples of security risks to users: Twitter was down for 2 hours due to a denial of service attack. In another incident the FBI seized the entire set of server assets from two hosting data centers due to investigation of a couple of the over 350 customers in a criminal investigation. Nearly 350 businesses lost control of their data and service due to an unknown and unrelated criminal business incident.Simplified: we had server sprawl, now we have vm sprawl. We increased server utilization through virtualization but have driven network bandwidth through the roof in complexity creating the next bottleneck in the system. IDC estimates that it costs roughly as much to manage a virtual server as a physical one. Garnter estimates that the cost to manage a server will exceed the cost to buy one. Infrastructure must be dramatically simplified to handle the rapid rate of growth and complexity challenging IT. We need fewer configurations, fewer ports, fewer cables, fewer servers, few points of management and seamless integration of vendors to enable a more simplified IT environment.Open: with the cloud comes opportunity. Rapid deployment and lower costs enable innovation to happen more quickly. To fully realize the potential we need to ensure the cloud remains open, interoperable and that it’s based on multi-vendor innovation vs. proprietary solutions. No single company or companies should control, limit or own the cloud. Few standards exist today to make this happen, but we need the industry to align on a core set of standards and to advocate for products/services that are interoperable to keep the cloud open.
  • 15.Intel, 2010 review of performance and performance efficiency benchmarks - SPECint and SPECpower - across multiple server generations and forecast for future improvement of future generation products16. Baidu whitepaper, 2009 posted at intel.com. Using Intel Node manager Baidu (Chinese search engine, similar to Google) achieved 40% power utilization improvement in POCs17. http://www.embedded.com/products/oem/212001590?_requestid=19579; The X-25E Extreme SATA solid-state drive improves storage subsystem performance 100X compared to conventional systems when measuring IO’s per seconds (IOPS). SSD’s can also lower energy usage by up to 5 times over conventional storage.Intel has worked for decades on delivery of energy efficient products to the marketplace, and this effort was re-doubled with the transition to core microarchitecture.  The foundation for our contributions to efficient data center deployments is the continued performance increases driven by Moore's Law. Every generation of server processors delivers approx 40% performance improvement on an annual cadence to the marketplace. This has been matched by a 40% increase in perf/efficiency generation to generation as we continue to deliver more performance for the same power envelope.  Intel has also placed a significant investment in delivery of "real world" efficiency, or managing our P and T states to ensure that power usage scales as linearly as possible with performance delivery. This means that a server will consume less energy when sitting idle but throttle up quickly when work is required. The instrumentation of the server platform extends to the delivery of Intel Node Manager technology enabling data center managers the ability to throttle system and rack power based on expected workloads. Early results of Node Manager deployment have led to up to 40% efficiency improvement.Source: Baidu whitepaper, 2009. We extend our focus on efficiency through delivery of SSD drives for the data center. SSD technology have yielded up to a 5x efficiency improvement vs. their spinning alternatives and shown to provide 100x the bandwidth with 80% less power. Finally, Intel is investing significant engineering hours to data center best practice work with a goal of driving PUE towards 1.0 in data centers across the world. Examples of this work include our work on the Green Grid, engagement with standards groups like Energy Star and SPEC, POC studies such as the Advanced Cooling Environment study with LBNL, IBM, HP and Emerson, and warmer temp data center engagements with ASHRAE. We’re looking for new technologies that enable use of “free cooling” in the data center and decrease dependence on expensive power and cooling subsystems.To begin the path to the most efficient Open Data, implement the next generation Intel® Xeon® EP processor (Westmere) with Node manager.
  • Securely sharing the DC resources lets IT effectively realize the scale and efficiency of their infrastructure How can we get safer execution programs running in the open data center and how can we better protect the data both “at rest” and “in flight”It starts with a pervasive use of data encryption. Encryption helps protect the data from those that aren’t suppose to view it. As an example, The biggest reported government data breach in history was part of a Oracle database RAID configuration.  The hard drive became defective and was sent to a vendor for repair.  If the data had been encrypted, no problem; but it wasn’t.  76,000,000 veteran’s SS#’s, DOB, and other personal identifiable information were potentially exposed. One of the barriers to using encryption more broadly has been the computational tax it puts on the hardware performance. Using Intel technology, AES-NI, the encryption can be accelerated in the processor lowering the overhead of encrypting data. By removing this key barrier, it enables it’s more pervasive use Additional info: AES-NI speeds up encryption algorithms up to 10X. This allows IT departments to deploy encryption of data not feasible before due to performance concerns. This could be the use of AES-NI optimized SSL and IPsec for protecting data in flight. And Intel NICs also have the ability to offload the IPsec computation. Together line speed encryption can be achieved for data in flight. Additionally, with the AES-NI hardware acceleration, full-disk encryption or database encryption is now feasible to be deployed widely to protect data at rest. Besides encrypting the data how can the virtual machines be protected in the multi-tenant environment of an open data center? A consistent top concern with multi-tenancy is security. How do we ensure that virtual machines and their respective data remain separate. In the physical world often different departments have the requirement to run on different physical servers. Sometimes this requirement is carried forward into the virtual world. Removing the requirement for different physical servers, helps to maximize agility and cost saving benefits available in a virtualized data center. To do this more assurances are needed that the data and execution can be protected from one another.Virtualization (Intel® VT) provides isolation of virtual machines not readily available in a non-virtual implementation. Trusted Execution Technology (Intel® TXT) locks down the virtualization configuration so that it can only be changed by entering into the TXT driven secure mode. It’s kind of an additional armor around the protections promised by virtualization isolation. Together with Intel FlexMigration pools of trusted servers can be created in the data center, which allows for flexible and safe migration of VMs.Protecting the data and execution is just a good idea, more and more it’s becoming a requirement. For example: laws in MA and NV require encrypting Personally Identifiable Information. To help with compliance there are audit and compliance tools that are enabled through new hardware features. This can help with reporting for to regulations like HIPPA and SOX.Finally a data center needs to be resilient. Using Intel Xeon –based server are able to take stay operational even when faults occur. Whether the fault are electronic glitches or maliciously induced in attempt to gain unauthorized to the systems.
  • One of the most significant complexity drivers in the data center is meeting the scale of growing infrastructure demands. However, in today’s data centers achieving scale often also means scaling complexity in the data center.  Rapid virtualization adoption for example exasperates the complexity challenge with six or more network connections demanded for each virtualized server. More connectivity and more virtualization means more cabling, more management domains and rising power consumption. With increasing demands and a continual push for higher levels of efficiency the network is a continual focus. Simplifying the data center is an imperative.  Intel is bringing the compelling economics of Moore’s law to compute, storage, and network. Intel has established clear leadership in the server market segment today. Intel is bringing the same performance and volume economics to storage with 80% of enterprise storage infrastructure solutions. Intel is also bringing IA innovation to core network infrastructure. Unified fabrics deliver simplicity by dramatically improving efficiency and reducing cabling by  unifying the network on 10 Gig Ethernet. IO virtualization with technologies like VT-d and SR-IOV allow the data center to reduce virtualization overhead while enabling dynamic allocation of bandwidth resources. Advances in Ethernet help to further reduce network latency and support a variety of storage technologies; SAN, NAS, or DAS.  Reducing complexity is also about reducing manageability complexity in a way that scales to the demands of increasingly dense environments. Intel has been driving simplification in manageability to support scale—over 1+ M nodes. DCMI and future manageability products will deliver a reliable mechanism with a common feature set to ensure interoperability across a diverse ecosystem.  The Intel Instruction Set Architecture and platform hardware exposes a common set of resources and instrumentation that will support innovative solutions for end-to-end innovation. Examples today, include, security instructions (AES-NI), media instructions (AVX), common platform instrumentation for power improved efficiency (p-states, c-state, power gating).
  • PUBLIC DISCLOSURE :Launching in 2010, the Nehalem-EX processor will feature up to eight cores inside a single chip supporting 16 threads and 24Mb of cache. Its performance increase will be dramatic, posting the highest-ever jump from a previous generation processor. Nehalem-EX will add new reliability, availability and serviceability (RAS) features traditionally found in the company’s Intel® Itanium processor family, such as Machine Check Architecture (MCA) Recovery.  Nehalem-EX will provide tremendous scalability, from large-memory two-socket systems through eight-socket systems capable of processing 128 threads simultaneously without the need for third-party chips to “glue” the platform together.
  • Standardization  the smallest amount of infrastructure diversity that allows executing the task, even if at a sacrifice in terms of user responsivenessOptimization  A diverse set of infrastructure resources that enable best application performance, maximize utilization of space and power resources.The original public cloud providers seemingly have achieved great efficiencies using very standard infrastructure implementations. In their environment all applications run on the same servers, with the same storage configuration and the same amount networking capacity. They could however afford to design (and redesign) their applications to run well on such infrastructure. However, you have a wider variety of applications and legacy applications. Your business value depends on your ability to run your legacy with much greater efficiency. You should consider subjecting your infrastructure to these considerations and optimize it to run this way. Some applications (e.g. transaction oriented apps) require great responsiveness, which other don’t for example. Some application scale across many threads, while other are single threaded. Many IT application scale up better than they scale out. And so on and so forth. However, you are under pressure to achieve a similar level of efficiency as the Public Cloud providers. Clearly that is going to require a significant transformation. But can you afford to redesign your applications? Can you afford to throw away your legacy? We believe there is an alternative
  • Along with an innovative Open Data Center architecture and roadmap, Intel has led the creation of the Intel Cloud Builder Program with key eco-system partners to enable the industry and end users to more easily build cloud solutions in their data center. There are 3 key areas of focus - Deployment Best Practices: When a company has a choice to build a private cloud or to create a cloud within a service provider, the hardware and software infrastructure trade-offs for cloud management can be daunting. Provides public cloud service providers, hosters, telco service providers and private enterprises with reference architecture white papers to simplify the design and operation of a cloud. The reference architectures combine the latest Intel-based servers with leading ISV cloud operating environment software. These reference architectures provide a starting point from which to build clouds and over time will highlight the use of software by Intel and other industry players to address needs such as trusted multi-tenancy. The majority of major cloud software management ISVs are collaborating with Intel in this program. More details on Intel Cloud Builder and references architectures - http://www.intel.com/software/cloudbuilder Building Optimized Clouds: When a company wants to assure that their cloud infrastructure is the most efficient and performant, a wide variety of technologies and solutions can be applied to achieve that end. Intel is working with large scale service providers to help build out optimized clouds via technology proof of concept tests using Intel’s latest products and technologies, such as Intel Xeon processor 5500 series and Intel Node Manager for power management. Intel is producing white papers, case studies, and related content derived from these POCs that are made available as part of the Intel Cloud Builder Program to help guide end users in building their own optimized clouds and take advantage of Intel technologies. In addition, IT@Intel continues to deliver best practice documents based on Intel IT’s own cloud strategy and implementation. Learn more at http://www.intel.com/it Advanced Cloud Research: Open Cirrus is an open cloud-computing research testbed, jointly formed by Intel, HP and Yahoo with more than 10 test beds worldwide, and designed to support research into the design, provisioning, and management of services at a global, multi-datacenter scale. The open nature of the testbed is designed to encourage research into all aspects of service and datacenter management. In addition, we hope to foster a collaborative community around the testbed, providing ways to share tools, lessons and best practices, and ways to benchmark and compare alternative approaches to service management at datacenter scale. To learn more about Open Cirrus – http://opencirrus.orgIntel is also an affiliate member of UC Berkeley’s RAD Lab, a research group focused on leveraging powerful techniques from statistical machine learning (SML), as well as recent insights from networking and distributed systems, to enable an individual developer to rapidly turn a prototype or idea into a robust distributed service. Findings and insights from some of these projects are published. Q&AQ: Who are the target users of the Intel Cloud Builder Program?A: The program will help telecommunications companies, hosters, Internet services providers and enterprise IT professionals who wish to deploy clouds. The program also aids ISVs that want to offer their applications through the cloud. Q: Which ISVs are participating in the Intel Cloud Builder Program to deliver reference architectures?A: The initial participants include seven ISVs; Canonical, Citrix, Microsoft, Parallels, Redhat, Univa and VMware. The Xen.org community is also involved. More are joining the program over time. Q: When will the first reference architectures be publicly available from Intel Cloud Builder Program? A: Canonical and Enomaly are already posted. More reference architecture papers are being posted in Q2 and beyond. Go to http://www.intel.com/software/cloudbuilder to learn more. Q: What content is included in the reference architecture white papers?A: The reference architecture papers provide an in depth description of the Intel test bed blueprint, detailed discussion on the ISV software solution used in the test bed, technical review of the specific cloud use cases, setup and configuration information, and key things to consider in implementing the specific reference architecture. The purpose of these papers is provide a starting point for end users to be able to deploy a cloud solution on Intel hardware using the ISV software stack.
  • Caution against perils of vertical solutions with vendor lock-in. Look to garner support from the end user base to assert need for open clouds back to vendors.Intel has a long history of open standards leadership within the IT industry and has played a historic role in the growth of non-proprietary solutions across the datacenter and the enterprise. That leadership is continuing in a number of areas critical to the future of cloud computing. Intel is active in multiple industry forums to enable key cloud computing standards. For example:Interoperability standards:Intel is co-chair of the Open Cloud Incubator within the Datacenter Manageability Task Force (DMTF), which is defining standards for interoperable cloud interfaces and portable workloads as well as standards for power management integrated with building management systems. Intel is also actively involved with the Open Grid Forum (OGF) which is defining the Open Cloud Computing Interface (OCCI), a practical solution to interface with cloud infrastructures exposed as a service (IaaS). As a major contributor to the Server System Infrastructure (SSI) standards body, Intel is helping create hardware standards that are well suited to cloud computing such as half-width motherboards, and the emerging low-end, entry-level single-socket server category of micro servers. Manageability standards:Intel was a leader in defining the Datacenter Manageability Interface (DCMI) specification, a subset of the IPMI specification providing low-cost, non-proprietary server manageability tailored to the specific needs of large-scale datacenters. Efficiency standards:As a member of the W3C HTML5 Working Group, Intel is helping to form the HTML5 specification to enable superior web/runtime experiences that can take advantage of Intel platform features. Intel is a key contributor in two forums on the Green Grid: the Power Management Data Collection Task Force, which is driving industry surveys and data collection for power management feature requirements; and the Container Data Center Task Force, working to standardize energy efficiency metrics. Intel is also investing significant engineering work and proof-of-concept efforts targeted at data center best practices, with a goal of driving datacenter Power Usage Effectiveness (PUE) towards 1.0. Examples of these efforts include Intel’s work on the Green Grid; engagement with standards groups like Energy Star; and proof-of-concept studies such as the Advanced Cooling Environment study with LBNL, IBM, HP and Emerson; and warmer temperature data center studies with ASHRAE . Security standards:As a member of the Cloud Security Alliance (CSA), Intel is helping to drive best practice recommendations and provide better mapping of CSA recommendations into Intel’s silicon capabilities. Storage and networking standards:As a contributor and reviewer to the IEEE 802.1 and 802.3 standards, Intel is helping to shape a study group focused on cloud computing networking standards. Within the PCI-SIG, Intel was a major contributor to the Single Root I/O Virtualization (SR-IOV) specification. Regarding storage standards, Intel is a member of the Storage Networking Industry Association (SNIA) and a contributor to on the STORM (STORage Maintenance) task force, providing inputs into iSER and iSCSI specifications.Virtualization Standards: As one of the largest contributors to virtualization standards in the technology industryIntel participates actively in the Xen Open Source Hypervisor community, SpecVirt Benchmarking committee, and multiple industry forums for the advancement of virtualization technologies.   ASHRAE is mentioned in the speaker notes on slide 11 in The Realization of Cloud 2015 powerpoint To help address key barriers associated with building cloud datacenters, Intel is actively engaged in multiple industry forums to enable cloud standards that provide for improved interoperability and cross platform manageability, better security, and multi-vendor choice.    Interoperability: This is key to provide a more seamless integration among public and private clouds and across vendors.  Intel is contributing to industry forums that are driving for improved interoperability via common APIs.  Intel is co-chair of the Open Cloud Incubator within the Datacenter Manageability Task Force (DMTF), which is defining standards for interoperable cloud interfaces and portable workloads and also standards for power management integrated with Building Mgmt Systems.  Intel is also actively involved with the OGF (Open Grid Forum) which is defining the Open Cloud Computing Interface, a practical solution to interface with cloud infrastructures exposed as a service (IaaS), focused on provisioning, monitoring and definition of cloud Infrastructure services.   Security:  As companies build out their private clouds that have multi-tenant support and consider public or hybrid clouds, security is key consideration.  Intel is involved in the Cloud Security Alliance (CSA) which is focusing on delivering industry best practices to support improved security.  In addition, Intel works with industry forums as they define best practices to comprehend advanced security features embedded in Intel Architecture, such as Intel Trusted Execution Technology (TXT), which provides for improved security in virtualized environments.   Multi-vendor choice: Enabling cross platform manageability, hardware standards, and standards for networking and storage is important to help enable choice.   Intel was a leader in defining with the industry the Datacenter Manageability Interface (DCMI) spec, a subset of the IPMI spec providing low cost, non-proprietary server manageability tailored to the specific needs of the large scale datacenters.   Intel is also a major contributor to the Server System Infrastructure (SSI) standards body, which has created hardware standards that are well suited to cloud, including half width motherboards, blade form factors, and is working on standards for the emerging low end, entry server category of micro servers.   Lastly, Intel is also actively contributing to, IEEE, PCI-SIG and Internet Engineering Task Force (IETF) to define networking and storage standards that provide for consistent hardware standards within and across platforms.  A recent example that Intel contributed to is Single Root IO Virtualization (SR-IOV) spec, which improves IO virtualization by allowing multiple operating systems running simultaneously within a single computer to natively share PCI Express® devices. 

Transcript

  • 1. A PERSPECTIVE ON CLOUD COMPUTING
    Gordon Graylish
    Vice President & General Manager
    Enterprise Solution Sales
    Sales and Marketing Group, Intel Corp
  • 2. If the Internet were a movie we’d still be in the opening credits…
    1 Billion videos served up by YouTube everyday.
    30 Billion Videos Viewed each month
    182 – number of online videos avg internet user watches per month
    25% of the world is connected
    > 250 Million Websites
    45B Web Searches per Month
    The Internetis BIG &GROWING
    500M Active Users on Facebook
    50% of Active Facebook users login every day
    >30Bn pieces of content shared of Facebook each month
    100,000 Blogs Created Daily
    $750B Dollars Online Sales Worldwide
    50 Million Tweets a day 600 Tweets per second
    Source: Forrester, ABI, Facebook statistics
  • 3. Sensors
    Home
    Storage
    Point of Sale
    IP Cameras
    Power Lines
    IP Phones
    In-Vehicle
    Infotainment
    Net book
    Security
    IPTV/IMS
    Military/Aero
    Learning
    Home Auto
    Digital Signage
    Portable
    Medical
    Net top
    Factory
    Automation
    Gaming
    Industrial PC
    Printers
    Medical
    Transport
    Robotics
    MID
    From Genomic research to Connecting Cars
    …it’s Only the Beginning
    Genomics Research
    Medical Imaging
    Financial Analysis
    Weather Prediction
    Oil Exploration
    Design Simulation
    Cloud Computing
    Data Center Refresh
  • 4. The Internet Underpins the Next Wave of Enterprise Computing…
    Business Trend & Technology Response
    Customers
    Faster Business Clock Speed
    Real-time biz intelligence; data explosion;
    Utility infrastructure; rapid re-provisioning
    Mobile Consumer
    Digital
    Offices
    Innovation Beyond the Firewall
    “Everything” as a Service (SOA, Cloud),
    Consumerization, ,Embedded Clients
    Data Center
    Mobile Workforce
    The World is Flat
    Mobile device as std biz client, secure connectivity Anytime/anywhere. Unified communications. Web 2.0
    ISP / Telco
    Factory / Warehouse
    The World is Green
    Low power clients (HUGI)
    Data center utilization tunable consumption
    Efficient IT
    Consolidation & re-platforming. Dynamic resource management. Automation. Outsourcing. Cloud computing
    Supplier
    Outsourcer
  • 5. …eCommerce to Enterprise Cloud…
    The corporate boundariesare blurring.
    The cloud is emerging.
  • 6. Cloud computing is not so much a definition of a single term but a trend in Service Delivery.
    CEO = Growth Opportunity
    CIO = IT impacts business value
    IT Director = Effective IT Utilisation
    Enabled by a set of new technologies where Services and data reside in shared, dynamically scalable resource pools
  • 7. Power and Cooling Costs
    Server Management and Administration Costs
    New Server Spending
    Why is a new Service Delivery Model is Needed ?
    Installed Base
    Spending
    (US$B)
    (M Units)
    US$300
    50
    US$250
    40
    Install base cumulative
    US$200
    30
    US$150
    20
    US$100
    10
    US$50
    0
    US$0
    ‘96
    ‘97
    ‘98
    ‘99
    ‘00
    ‘01
    ‘02
    ‘03
    ‘04
    ‘05
    ‘06
    ‘07
    ‘08
    ‘09
    ‘10
    Worldwide IT Spending on Servers, Power and Cooling, and Management/Administration
    ...to regain OpEx control and meet financial expectations
    Source: IDC, “Virtualization and Multicore Innovations Disrupt the Worldwide Server Market,” Document 206035,Publish date: March 2007
  • 8. IT Budgetary Perspective –Balance Strategic with Tactical
    Drive Transformation
    • A Service Oriented Utility infrastructure
    Innovate
    (private cloud)
    Maintain
    (Keep the lights on)
    Enhance
    (near term wins)
    Remove Barriers, Lower TCO
    • Accelerate infrastructure refresh
    • 9. Secure information & assets
    • 10. Standardize & optimize
    • 11. Virtualization : utilization
    • 12. Virtualization : flexibility
    • 13. Datacenter Power Efficiencies
    Source: Gartner IT Key Metrics Data 2008
  • 14. Considering Cloud Deployment Today
    Private Clouds
    Public Clouds
    Virtual Private and Hybrid clouds
    Cloud Brokers
    Behind the Firewall
    Multi-tenant
    • Security
    • 15. Compliance and Governance
    • 16. Interoperability
    • 17. Rapid Deployment
    • 18. Reduced Capital Expenditure
    • 19. External vendor expertise
    Intel IT Strategy: develop private clouds while adopting best of breed public cloud services
  • 20. What is Holding Back the Cloud Today?
    Technology Maturation
    Security
    Lack of automation
    DC Power Constraints
    Standards
    Acceptance of Risk
    IP protection
    Interoperability and lock in Compliance and audit
    Guaranteed quality of service
    A cultural shift and technology advancement is needed
  • 21. The Cloud Drives New expectations of the Data Center
    AutomatedDynamically allocates resources to manage service level and optimize power
    FederatedData and services seamlessly and securely span clouds
    Client AwareSecure access and optimal experience across the client continuum
    Laptops
    Personal Devices
    Desktops
    Embedded
    Smartphones
    Netbooks
    Smart TVs
  • 22. Architectural Principles for Next Generation Data Centers
    SimplifiedSimplify data centre operations to reduce cables, complexity and cost
    Efficient Optimizing technologies to decrease energy, human and physical asset consumption
    SecureReduce the risk, increase the compliance and manage hybrid usage models
    Optimizing energy consumption, simplifying and securing your Data centre infrastructure
  • 23. Moore’s Law Drives Energy Efficiency
    Core Integer Performance Over Time*
    Power reduction Over Time*
    10000
    1.E+00
    Core™ 2 Duo Extreme QX6700
    Core™ 2 Duo Processor X6800
    1.E-01
    Pentium® -D Processor
    1000
    Pentium® 4 Processor EE
    1.E-02
    Pentium® 4 Processor
    1.E-03
    Pentium® -IIi Processor
    Pentium® -II Processor
    100
    1.E-04
    Pentium® Pro Processor
    Pentium® Processor
    1.E-05
    10
    i486DX2
    1.E-06
    i486
    1.E-07
    1
    386
    1970
    1980
    1990
    2000
    2005
    2010
    1986
    2008
    1988
    1990
    1992
    1994
    1996
    1998
    2000
    2002
    2004
    2006
    Single Core Moore’s Law
    • ~1 million factor reduction in energy/transistor over 30+ years
    • 24. Delivering great performance within power envelope
    • 25. Compute energy efficiency  Positive impact on environment
    Efficient
    Source: Intel Corporate Technology Group
  • 26. Datacenter Investment Alternatives
    Technology
    Efficient Alternatives
    Investment Goals
    Airside Economizers, Water Chilled Cabinets, Warm Datacenters
    Minimize Cost/kwUse, Optimize Cooling Capacity
    CoolingHVAC, Water Chillers
    DC Power (New Facilities Only)
    Optimize Power Delivery to Racks
    Power(UPC, etc.)
    Overhead
    Maximize Performance Density and Performance EfficiencyMinimize Cooling Load/Rack
    Efficient Servers (SpecPower*), Refresh, Instrumentation
    ComputeServers, Storage, Communications
    Efficient
    Optimize Investment on Productivity Drivers
  • 27. EfficientDrive Efficiency Across the Breadth of the Data Center
    • Up to 5x efficiency improvement in 5 years15
    • 28. Near linear power scaling between idle & max
    • 29. Near native virtualized performance
    • 30. Data center level power management drives 40% utilization improvement16
    • 31. Solid state data center for 100X bandwidth, 80% lower power17
    • 32. Driving PUE below 1.25
    Platform capabilities:Energy efficient Intel® Xeon® processors & Intel® Data Center Manager & Node Manager
    Efficient
  • 33. Secure Secure Execution and Data Protection at Rest and In Flight
    • Pervasive use of data encryption
    • 34. Protected and locked down virtual machines in multi-tenancy environments
    • 35. Hardware enforced audit and compliance
    • 36. Resiliency built in for defense and recovery from faults
    VM
    VM
    VM
    VM
    Cloud Software Infrastructure
    Platform Capabilities:Intel ® Virtualization Technologies & Encryption Capabilities Available Today Eco System Enabling of Trusted Execution Technologies for 2011
    Secure
  • 37. SimplifiedReduce the Avalanche of Data Center Complexity
    • Flexible infrastructure across compute, storage and network
    • 38. Unified network & storage fabric
    • 39. Scalable management for 1M+ nodes
    • 40. Resources exposed to enable optimized services across a range of clients
    Mgmt
    Unified Fabric
    Storage Arrays
    Servers
    Adopt 10GbE for unified storage and network traffic
    Design with Intel® Xeon® processors for compute & storage flexibility
    Simplified
  • 41. Tick
    Tock
    Tick
    Tock
    Tick
    Tock
    Tick
    Tock
    Sandy
    Bridge
    Merom
    Penryn
    Nehalem
    Future
    Processor
    Tick-Tock Development ModelSustained Microprocessor Leadership
    65nm
    45nm
    32nm
    22nm
    Intel® Core™
    Microarchitecture
    Nehalem
    Microarchitecture
    Sandy Bridge
    Microarchitecture
    2010
    onwards
    Westmere
  • 42. Intel ®Xeon ® Processor 5600
    Better Energy Efficiency
    Same performance as X5570 and up to 30% lower power1
    Westmere-EP
    Westmere-EP
    Intel® 5520 Chipset
    Performance Leadership
    Up to 60% performance boost25-month refresh ROI3
    Secure Virtualization
    Encrypt todayMeasure & Enforce tomorrow
    PCI Express* 2.0
    Boost Performance, Lower IT Costs, Enhance Security
    Intel® X25-ESSDs
    Intel® 82599 10GbE Controller
    1 Source: Fujitsu Performance measurements comparing Xeon L5650 vs X5570 SKUs using SPECint_rate_base2006. See http://docs.ts.fujitsu.com/dl.aspx?id=0140b19d-56e3-4b24-a01e-26b8a80cfe53 and http://docs.ts.fujitsu.com/dl.aspx?id=4af74e10-24b1-4cf8-bb3b-9c4f5f1773892 Source: Internal Intel measurements for Xeon® X5680 vs. Xeon® X5570 on BlackScholes*.3 Source: Intel measurements as of Feb 2010. Performance comparison using server side java bops (business operations per second). Results have been estimated based on internal Intel analysis and are provided for informational purposes only.
    For notes and disclaimers, see performance and legal information slides at end of this presentation.
    ICH 9/10
  • 43. Intel Architecture - a Transformational PathWhere Will You Invest Tomorrow?
    The
    “economic platform”
    for building an enterprise
    A Common Foundation with Server Choices to balance Standardization with Optimization
  • 44. Standardization Vs. Optimization
    Standardization
    Simpler automation process
    Highest modularity and expandability
    Optimization
    The best HW for every application instance
    Maximize utilization of space and power
    How do you do both ?
  • 45. Server RefreshSingle Core  Xeon® 5600
    2010
    Up to 15x Performance
    Performance Refresh
    1:1
    2005
    15 racks of Intel® Xeon® Single Core Servers
    8% Annual Energy Costs Estimated Reduction (estimated)
    15 racks of Intel® Xeon® 5600 Based Servers
    95%Annual Energy Cost Reduction (estimated)
    – OR –
    Efficiency Refresh
    15:1
    As Low as 5 MonthPayback
    1 rack of Intel® Xeon® 5600 Based Servers
    Source: Intel measurements as of Feb 2010. Performance comparison using server side java bops (business operations per second). Results have been estimated based on internal Intel analysis and are provided for informational purposes only.  Any difference in system hardware or software design or configuration may affect actual performance. For detailed calculations, configurations and assumptions refer to the legal information slide in backup.
  • 46. Server Refresh ROI : Intel Can Help You Make the Case
    • Rapid Payback
    • 47. Dramatic Savings
    • 48. Unique Opportunity
    www.intel.com/go/xeonestimator
  • 49. Intel® Cloud Builders Program:Facilitating cloud development and deployment
    Cloud Reference Architectures, & Tools
    Open Cirrus™ & Research Universities
    Intel Cloud Test Bed & POCs
    Deployment Best Practices
    Building Optimized Clouds
    Advanced Cloud Research
    Leading the ecosystem to help organizations build the Cloud
    www.intel.com/cloudbuilder
  • 50. Summary
    • Know where you’re going – don’t lose sight of your vision
    • 51. Balance tactical projects with strategic direction
    • 52. How much could you save whilst transforming your business with Information Technology ?
    • 53. Check out the demo’s on the Intel booth
    • 54. www.intel.com/cloudbuilder
  • Thank You
  • 55.
  • 56. Sources
    IDC “Server Workloads Forecast” 2009
    IDC “The Internet Reaches Late Adolescence” Dec 2009, extrapolation by Intel for 2015
    ECG “Worldwide Device Estimates Year 2020 - Intel One Smart Network Work” forecast
    http://www.facebook.com/press/info.php?statistics
    http://www.comscore.com/Press_Events/Press_Releases/2010/1/November_Sees_Number_of_U.S._Videos_Viewed_Online_Surpass_30_Billion_for_First_Time_on_Record
    http://googleblog.blogspot.com/2008/07/we-knew-web-was-big.html
    8x Network: 800 Terabytes / second of IP traffic estimated on Internal Intel analysis “Network Supply/Demand 2010-2020” forecast . 16x Storage: 60 Exabytes of data stored from Barclays Capital “Storage Bits” Sept 2009, extrapolation by Intel for 2015; 20x Compute: Intel Internal LRP forecast. Extrapolated to 1 billion virtual servers using 1 vm/core
    http://open.blogs.nytimes.com/2007/11/01/self-service-prorated-super-computing-fun/
    http://www.datacenterknowledge.com/archives/2009/10/13/facebook-now-has-30000-servers/
    http://www.globalfoundationservices.com/documents/MSFTTop10BusinessPracticesforESDataCentersApril09.pdf/
    Jonathan Kooney, 6/09. http://www.nytimes.com/2009/06/14/magazine/14search-t.html?_r=3&ref=magazine&pagewanted=all
    Data Center Knowledge, 4/09 http://www.datacenterknowledge.com/archives/2009/04/08/fbi-defends-dallas-equipment-seizures/
    Summary of spending between 2010 and 2014. Intel commission analysis with Bain Consulting based on: IDC “Server Workloads Forecast” 2009, AMI US SB/MB Overview and Market Opportunity Assessment 2006 Gartner “WW IT Services Forecast” 2009; Cowen & Co “VMware” (July 2009); IDC 2009 “Optimizing Infrastructure and Service Management in Tough Economic Times”, analyst reports, IDC storage & networking reports, Gartner 2009 WW IT Services Forecast, BLS, Computer Economics, PrincipledTechnology, expert interviews, Bain analysis
    Winston Bumpus, DMTF 6/09 http://cloudcomputing.sys-con.com/node/936264
    Intel, 2010 review of performance and performance efficiency benchmarks - SPECint and SPECpower - across multiple server generations and forecast for future improvement of future generation products
    Baidu whitepaper, 2009 posted at intel.com
    http://www.embedded.com/products/oem/212001590?_requestid=19579
  • 57. Investing for the Future
    2009 R&D Spending
    25%IN NEW AREAS
    CORE
    Includes: Handhelds, Consumer Electronics, Embedded, Graphics, WiMAX
    Total Spending in New Businesses
    25% CAGR for 2006-2009
  • 58. Spending
    Capital Additions to Property,Plant and Equipment(Dollars in Billions)
    Research and Development(Dollars in Billions)
    7.3
    5.9
    5.8
    5.7
    5.7
    6.7
    5.1
    5.9
    5.9
    4.8
    4.4
    5.2
    5.0
    4.0
    3.9
    4.7
    3.8
    4.5
    3.8
    3.7
    2009
    2009
    2008
    2000
    2001
    2002
    2003
    2004
    2005
    2006
    2007
    2008
    2000
    2001
    2002
    2003
    2004
    2005
    2006
    2007
  • 59. OpenMulti-vendor innovation with compatibility of solutions
    • Workload portability across clouds
    • 60. Data Center Mgmt taskforce (co-chair)
    • 61. OGF’s Open Cloud computing Interface (OCCI)
    • 62. Multiple virtualization forums
    • 63. Multi-vendor choice and integration
    • 64. Common APIs, protocols and interfaces
    • 65. Server Systems Infrastructure (SSI) standards
    • 66. IEEE, PCI-SIG & IETF
    • 67. Trust and transparency with security policy, best practices and technologies
    • 68. Cloud Security Alliance (CSA)
    Cloud
    Infrastructure
    Security
    Network
    Storage
    Compute
    Datacenter facilities (e.g. cooling, power)
    Adopt solutions and support standards that have the greatest levels of compatibility and interoperability
  • 69. Intel IT Cloud Computing Strategy
    • Current: Grow internal cloud
    • 70. Interim: Transform existing environment to internal cloud
    • 71. Future: Move between internal and external cloud
    Grow the Cloud from the inside out
  • 72. Xeon 5600 Performance Claim Backup60% Performance, 40% Perf/Watt, and 30% Lower Power
    Up to 1.6x performance compared to Xeon 5500 series claim supported by a CPU intensive benchmark (Blackscholes). Intel internal measurement. (Feb 25, 2010)
    Configuration details: - Blackscholes*
    Baseline Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5570 (2.93 GHz, 8 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat* EL 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 18.74 seconds.
    New Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5680 (3.33 GHz, 12 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat* EL 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 11.51 seconds.
    Up to 40% higher performance/watt compared to Intel® Xeon® Processor 5500 Series claim supported by performance results on a server side java benchmark in conjunction with power consumption across a load line. Intel internal measurement (Jan 15, 2010)
    Baseline platform: Intel preproduction server platform with two Quad-Core Intel® Xeon® processor X5570, 2.93 GHz, 8MB L3 cache, 6.4QPI, 8GB memory (4x2GB DDR3-1333), 1 PSU, Microsoft Windows Server 2008 Enterprise SP2. Intel internal measurement as of January 15,2010.
    New platform: Intel preproduction server platform with two six-Core Intel® Xeon® processor X5670, 2.93 GHz, 12MB L3 cache, 6.4QPI, 8GB memory (4x2GB DDR3-1333), 1 PSU, Microsoft Windows Server 2008 Enterprise SP2. Intel internal measurement as of January 15, 2010.
    Intel® Xeon® processor 5600 series with Intel microarchitecture Nehalem delivers similar performance as previous-generation servers but uses up to 30 percent less power
    Baseline Configuration and Score on Benchmark: - Fujitsu PRIMERGY RX300 S5 system with two Intel® Xeon® processor sX5570 (2.93 GHz, 8MB L3, 6.4 GT/s, Quad-core, 95W TDP), BIOS rev. R1.09 , Turbo Enabled, HT Enabled, NUMA Enabled, 5 x Fans, 24 GB (6x4GB DDR3-1333 DR registered ECC), 1 x Fujitsu MBD2147RC 147GB 10K RPM 2.5” SAS HDD, 1x800W PSU, SLES 11 (X86_64) Kernel 2.6.27.19-5-default. Source: Fujitsu Performance Lab testing as of Mar 2010. SPECint_rate_base2006 score: 250. http://docs.ts.fujitsu.com/dl.aspx?id=0140b19d-56e3-4b24-a01e-26b8a80cfe53
    New Configuration and Score on Benchmark:- Fujitsu PRIMERGY RX300 S6 system with two Intel® Xeon® processors L5640 (2.26 GHz, 12MB L3, 5.86 GT/s, Hex-core, 60W TDP), BIOS rev R1.00A , Turbo Enabled, HT Enabled, NUMA Enabled, 5 x Fans, 24 GB (6x4GB DDR3-1333 LV DR registered ECC), 1 x Fujitsu MBD2147RC 147GB 10K RPM 2.5” SAS HDD, 1x800W PSU, SLES 11 (X86_64) Kernel 2.6.27.19-5-default. Source: Fujitsu Performance Lab testing as of Mar 2010. SPECint_rate_base2006 score: 250 http://docs.ts.fujitsu.com/dl.aspx?id=4af74e10-24b1-4cf8-bb3b-9c4f5f177389
  • 73. Xeon 5600 Performance Summary BackupMainstream Server Benchmarks
    42% gain on Single Node server SPECpower*_ssj2008 at similar power level over previous generation processors supported by the following:
    Baseline Configuration and Score: Referenced as published at 2053 overall ssj_ops/watt http://www.spec.org/power_ssj2008/results/res2009q4/power_ssj2008-20091023-00205.html
    New Configuration and Score: IBM x3650 M3 was configured with the Intel Xeon Processor X5670 (2.93GHz, 256KB L2 cache per core, 12MB L3 cache per processor—12 cores/2 chips/6 cores per chip) and 12GB of PC3L-10600R(6 x 2GB) memory and ran IBM Java™6 Runtime Environment and Microsoft® Windows® Server 2008 R2 Enterprise x64 Edition. Score: 2,927 overall ssj_ops/watt. Submitted and in review at www.spec.org
    46% gain on SPECjbb2005 supported by the following:
    Baseline Configuration and Score: 632,425 bops, SPECjbb2005 bops/JVM = 158106 http://www.spec.org/osg/jbb2005/results/res2010q1/jbb2005-20100210-00803.html
    New Configuration and Score: Fujitsu PRIMERGY RX300 S6 system with two Intel® Xeon® processors X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, Hex-core, 130W TDP), Turbo Enabled, HT Enabled, NUMA Enabled, Data Reuse Optimization disabled, all prefetchers disabled, 48 GB (12x4GB DDR3-1333 DR registered ECC), 1 x Seagate 73GB 10K RPM 2.5” SAS HDD, Microsoft Windows Server 2008 R2 Enterprise, IBM J9 VM (build 2.4, JRE 1.6.0 IBM J9 2.4 Windows Server 2008 amd64-64 jvmwa6460sr6-20090923_42924). Source: Fujitsu Performance Lab testing as of Mar 2010. SPECjbb2005 score: bops= 928393, bops/JVM= 154732 http://docs.ts.fujitsu.com/dl.aspx?id=71488796-7a53-46b8-9163-61373214c2ef
    27% boost on SAP ERP 6.0 Unicode over previous generation supported by the following:
    Baseline Configuration and Score: 3800 Number of SAP SD benchmark users http://download.sap.com/download.epd?context=40E2D9D5E00EEF7C259FFE6AB54898440C838DED66684AFD7D58B23A917F4C0D
    New Configuration and Score : Fujitsu PRIMERGY RX300 S6 system with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, Hex-core, 130W TDP), 88 GB main memory, Windows Server 2008 Enterprise Edition, SQL Server 2008, SAP ERP 6.0 (Unicode). Source: www.sap.com Score: 4860 Number of SAP SD benchmark users
    40% gain on SPECint_rate_2006 over previous generation supported by the following:
    Baseline Configuration and Score: Score: 253
    http://www.spec.org/cpu2006/results/res2010q1/cpu2006-20100202-09561.html
    New Configuration and Score: Dell PowerEdge R710 system with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, six-core, 130W TDP), Maximum Performance Power Management mode, Data Reuse Disabled, C1E Enabled, Turbo Enabled, HT Enabled, 48 GB (12x4GB DDR3-1333 registered ECC), 1x146GB 15K RPM SAS HDD, SUSE Linux Enterprise Server 11 (2.6.27.19-5-smp).  Source: Submitted to www.spec.org for publication as of March 15 2010.  Geomean Score of 12 workloads: 355
    42% gain on VMMark* over previous generation supported by the following:
    Baseline Configuration and Score: Cisco result referenced as published at 25.06 at 17 tiles. For more information see www.vmware.com/files/pdf/vmmark/VMmark-Cisco-2010-01-12-B200M1.pdf
    New Configuration and Score on Benchmark:- Cisco UCS B250 M2 platform with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, 6-core, 130W TDP), Turbo Enabled, HT Enabled, 192GB memory (48x4GB DDR3 1333), EMC CLARiiON CX4-240 storage system with 25x73GB SSD, 20 x 450GB 15K RPM, 5 x 300GB 15K RPM, VMware vSphere 4,0 U1 Source: www.cisco.com. Score of 35.83@26 tiles. For more information see: www.cisco.com/en/US/prod/ps10265/at_work_promo.html#~industry_benchmarks.
  • 74. Xeon 5600 Performance Summary BackupTechnical Computing Benchmarks
    STREAM: Baseline Configuration and Score on Stream-MP Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5570 (2.93 GHz, 12MB L3, 6.4 GT/s, Quad-core, 130W TDP), C3 Disabled, C6 Enabled, Turbo Disabled, HT Disabled, NUMA Enabled, 24 GB (6x4GB DDR3-1333 DR registered ECC), 1x150GB 10K RPM SATA HDD, Red Hat EL5-U4 kernel 2.6.18-164.el5 experimental.8). Source: Intel internal testing TR1012. Score of workloads: 36588.0 MB/s
    New Configuration and Score on Stream-MP Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, Hex-core, 130W TDP), C3 Disabled, C6 Enabled, Turbo Disabled, HT Disabled, NUMA Enabled, 24 GB (6x4GB DDR3-1333 DR registered ECC), 1x150GB 10K RPM SATA HDD, Red Hat EL5-U4 kernel 2.6.18-164.el5 experimental.8). Source: Intel internal testing as of Feb 2010. Score of workloads: MB/s.
    CAE: Baseline Configuration and Score on CAE Vertical: 2-socket server with Intel® Xeon® processor X5570 (2.93 GHz, 8MB LLC, 6.4 GT/S QPI, 95W TDP), Turbo Enabled, HT Enabled or Disabled for best performance on each application, 24 GB memory (6x4GB DDR3-1333 registered ECC), 4x150GB 10K RPM SATA HDD RAID0 for scratch, Red Hat* EL 5.4 64-bit OS (2.6.18-164-el5). Source: Intel internal testing as of January 2010. Geometric mean score for nine applications
    New Configuration and Score on CAE Vertical: Intel pre-production 2-socket server with Intel® Xeon® processor X5680 (3.33 GHz, 12MB LLC, 6.4 GT/S QPI, 130W TDP), Turbo Enabled, HT Enabled or Disabled for best performance on each application, 24 GB memory (6x4GB DDR3-1333 registered ECC), 4x150GB 10K RPM SATA HDD RAID0 for scratch, Red Hat 5.4 64-bit OS (2.6.18-164-el5). Source: Intel internal testing as of January 2010. Geometric mean score for nine applications
    SPECfp_rate: 25% gain on SPECfp_rate_base2006 over previous generation supported by the following:
    Baseline Configuration and Score: Score 197, Referenced as published at http://www.spec.org/cpu2006/results/res2009q2/cpu2006-20090511-07354.html
    New Configuration and Score: Dell PowerEdge R710 system with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, six-core, 130W TDP), Maximum Performance Power Management mode, Data Reuse Disabled, C1E Enabled, Turbo Enabled, HT Enabled, 48 GB (12x4GB DDR3-1333 registered ECC), 1x146GB 15K RPM SAS HDD, SUSE Linux Enterprise Server 11 (2.6.27.19-5-smp).  Source: Submitted to www.spec.org for publication as of March 15 2010.  Geomean Score of 17 workloads: 248.
    LIFE SCIENCES: Baseline Configuration and Score on Life Sciences Vertical: 2-socket server with Intel® Xeon® processor X5570 (2.93 GHz, 8MB LLC, 6.4 GT/S QPI, 95W TDP), Turbo Enabled, HT Enabled or Disabled for best performance on each application, 24 GB memory (6x4GB DDR3-1333 registered ECC), 4x150GB 10K RPM SATA HDD RAID0 for scratch, Red Hat* EL 5.4 64-bit OS (2.6.18-164-el5). Source: Intel internal testing as of January 2010. Geometric mean score for ten applications
    New Configuration and Score on Life Sciences Vertical: Intel pre-production 2-socket server with Intel® Xeon® processor X5680 (3.33 GHz, 12MB LLC, 6.4 GT/S QPI, 130W TDP), Turbo Enabled, HT Enabled or Disabled for best performance on each application, 24 GB memory (6x4GB DDR3-1333 registered ECC), 4x150GB 10K RPM SATA HDD RAID0 for scratch, Red Hat 5.4 64-bit OS (2.6.18-164-el5). Source: Intel internal testing as of January 2010. Geometric mean score for ten applications
    LINPACK: Baseline Configuration and Score on Linpack Benchmark:- Supermicro* pre-production system with two Intel® Xeon® processor X5570 (2.93 GHz, 8MB L3, 6.4 GT/s, Quad-core, 95W TDP), BIOS rev 02/23/2009, C3 Disabled, C6 Enabled, Turbo Enabled, HT Disabled, NUMA Enabled, 24 GB (6x4GB DDR3-1333 DR registered ECC), 1x150GB 10K RPM SATA HDD, Red Hat EL5-U3 kernel2.6.18-128.el5 for x86_64). Source: Intel internal testing TR1011A. Score of workloads: 91 GFlops.
    New Configuration and Score on LinpackBenchmark:- Supermicro* pre-production system with two Intel® Xeon® processor X5680 (3.33 GHz, 12MB L3, 6.4 GT/s, Hex-core, 130W TDP), BIOS rev 01/06/2010, C3 Disabled, C6 Enabled, Turbo Enabled, HT Disabled, NUMA Enabled, 24 GB (6x4GB DDR3-1333 DR registered ECC), 1x150GB 10K RPM SATA HDD, Red Hat EL5-U4 kernel 2.6.18-164.el5 experimental.8). Source: Intel internal testing as of Feb 2010. Score of workloads: 146 GFlops.
    BLACKSCHOLES*: Baseline Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5570 (2.93 GHz, 8 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat* EL 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 18.74 seconds.
    New Configuration and Score on Benchmark:- Intel pre-production system with two Intel® Xeon® processor X5680 (3.33 GHz, 12 MB last level cache, 6.4 GT/sec QPI), 24GB memory (6x4GB DDR3-1333), 4 x 150GB 10K RPM SATA RAID0 for scratch, Red Hat* EL 5 Update 4 64-bit OS. Source: Intel internal testing as of February 2010. SunGard v3.0 source code compiled with Intel v11.0 compiler. Elapsed time to run benchmark: 11.51 seconds.
  • 75. Xeon 5600 5 Month Single Core Refresh ROI Claim – Back Up
    5 month ROI claim estimated based on comparison between 2S Single Core Intel® Xeon® 3.80 with 2M L2 Cache and 2S Intel® Xeon® X5680 based servers. Calculation includes analysis based on performance, power, cooling, electricity rates, operating system annual license costs and estimated server costs. This assumes 8kW racks, $0.10 per kWh, cooling costs are 2x the server power consumption costs, operating system license cost of $900/year per server, per server cost of $7200 based on estimated list prices and estimated server utilization rates. All dollar figures are approximate. Performance and power comparisons are based on measured server side java benchmark results (Intel Corporation Feb 2010). Platform power was measured during the steady state window of the benchmark run and at idle. Performance gain compared to baseline was 15x.
    Baseline platform: Intel server platform with two 64-bit Intel Xeon Processor 3.80Ghz with 2M L2 Cache, 800 FSB, 8x1GB DDR2-400 memory, 1 hard drive, 1 power supply, Microsoft* Windows* Server 2003 Ent. SP1, Oracle* JRockit* build P27.4.0-windows-x86_64 run with 2 JVM instances
    New platform: Intel server platform with two Intel® Xeon® Processor X5680 (12M Cache, 3.33 GHz, 6.40 GT/s Intel® QPI), 24 GB memory (6x4GB DDR3-1333), 1 SATA 10krpm 150GB hard drive, 1 800w power supply, Microsoft Windows Server 2008 64 bit SP2, Oracle* JRockit* build P28.0.0-29 run with 4 JVM instances
    Performance tests and ratings are measured using specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. Buyers should consult other sources of information to evaluate the performance of systems or components they are considering purchasing. For more information on performance tests and on the performance of Intel products, visit Intel Performance Benchmark Limitations.
  • 76. IT Reality : The 2010 Dilemma
    Business Spending Forecasted to Improve…
    …but this won’t translate into a blank check for IT…
    “IT spending will rebound in 2010 as the industry leaves behind the worst year ever”
    —GartnerOctober 19, 2009
    “For more than 50% of CIOs the IT budget will be 0% or less in growth terms”
    —GartnerOctober 19, 2009
    IT Investments Must Save Money or Help Grow the Business
    Source: Gartner press release http://www.gartner.com/it/page.jsp?id=1209913