HPCwire: HPC@Intel: The New Intel Xeon Architecture

The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing

HPCwire >> Topic >> Processors

April 15, 2009

HPC@Intel: The New Intel Xeon Architecture

by Richard Dracott and Thor Sewell, Intel's Server Platform Group

Sponsored Content

What do HPC users need?

Whether they work in manufacturing, energy, life sciences, financial services, weather, digital content creation, or other fields, many users have similar requirements in selecting HPC solutions. First and foremost, they need outstanding total application performance so they can simulate, analyze, and visualize larger, more complex models in less time. And they need to achieve that performance without increasing data center power or real estate.

In addition, HPC users want those performance gains immediately, with little to no software development. If they do invest time and resources to parallelize or optimize applications for a new architecture, they want to be sure that the work they do today will continue to benefit them in the future.

Finally, HPC users want to simplify the process of choosing, configuring, and operating clusters. Small research labs and departmental groups need solutions that do not require extensive IT expertise. Large organizations want to focus on innovation, not server management.

The new Intel® Xeon® processor 5500 series (code named "Nehalem") will play a key role in helping HPC users meet these requirements. This new microarchitecture enables HPC users to experience groundbreaking, intelligent, and energy-efficient performance quickly and easily. The Intel® Cluster Ready program makes it even simpler for organizations of all sizes to select, deploy, and operate HPC clusters with the new microarchitecture. At the same time, Intel provides software development tools that can help users scale performance forward, so the work they invest in parallelizing or optimizing their applications for this multi-core architecture will benefit them when they migrate to the many-core architectures of the future.

Immediate improvements in total application performance

Many HPC users moving from previous-generation Intel® architectures or competing architectures will experience significant and immediate gains in total application performance with the new microarchitecture. Users will be able to experience those gains with little or no software development. Internal Intel total application benchmarking shows that key applications in manufacturing, reservoir modeling, and seismic modeling, for example, have achieved more than three times greater performance with this microarchitecture compared with the previous quad-core Intel architecture.

New "intelligent" features help to deliver those performance gains. For example, dynamic management of cores, threads, cache, interfaces, and power provides energy-efficient performance on demand. In addition, Intel® Turbo Boost Technology automatically increases processor frequency to boost application performance. Meanwhile, Intel® Hyper-Threading Technology enables users to run multiple threads on each processing core to increase total application performance while requiring only a fraction of the power that would be necessary to support additional cores.

Memory-bound applications will also benefit right away from the dramatic increase in available memory bandwidth. The new microarchitecture provides three channels of directly connected, native DDR3 memory through an Integrated Memory Controller. In addition, the Intel® QuickPath Architecture facilitates high-speed, direct connections among microprocessors and the I/O hub to provide each microprocessor with fast, coherent access to the memory attached to the other microprocessor. Together, these changes provide more than three times the memory bandwidth per node compared with the previous-generation dual-socket architecture.

By increasing memory bandwidth along with processor performance, the new microarchitecture helps to deliver a balanced platform. HPC users can incorporate new Intel® solid-state drives and Intel® Ethernet server cluster adapters to improve I/O speeds as well. The end result is not just acceleration of one part of the code, but real, sustainable improvements in total HPC application performance.

Performance without more watts or square feet

The new microarchitecture can deliver these performance benefits while helping to conserve energy and real estate. By running more instructions per clock cycle, the processors can complete more work, faster than before. The microarchitecture also provides more power states, faster transitions between states, and lower idle power than the previous-generation architectures so the processors can conserve energy between tasks. As a result, this new microarchitecture delivers the highest system-level performance per watt of any Intel® microarchitecture.

At the same time, the new microarchitecture helps to increase the density of HPC clusters. By packing more performance into servers with the same form factor, the new microarchitecture will help HPC users who are refreshing their data centers see tremendous gains without having to expand the HPC physical footprint.

Scaling performance forward

The Intel Xeon processor 5500 series can help many HPC users experience immediate results without any software development. But for those users (or software developers) who are ready to parallelize or optimize applications for this and future microarchitectures, Intel provides a full range of software development tools. Intel® software development tools can help improve application programmability, reducing the time to develop, operate, and maintain HPC application solutions. The tools can also increase application portability, allowing users to port code between clusters easily.

In addition, Intel software development tools can help programmers scale performance forward. By using the tools to parallelize an application correctly, programmers will be able to drop in a new runtime optimized for a future platform and achieve immediate performance improvements. The work that programmers do today will continue to deliver benefits in the future.

Making HPC simpler with Intel Cluster Ready

The Intel Cluster Ready program can help organizations of any size simplify the path to the benefits of the new microarchitecture. The Intel Cluster Ready program helps to ensure application and hardware platform interoperability at time of purchase and throughout the lifetime of the cluster. By running a registered Intel Cluster Ready application on any certified Intel Cluster Ready cluster equipped with the new microarchitecture, users can achieve performance improvements and gain the confidence that everything will work together from the first project through the life of the cluster.

HPC challenges drive Intel forward

The new Intel Xeon processor 5500 series, Intel software development tools, and the Intel Cluster Ready program are important examples of Intel's ongoing efforts to meet the requirements of HPC users. Intel is driven to create these products by the complex problems that HPC users are trying to solve. As long as organizations want to increase the detail of crash test simulations, find new sources of energy, enhance genomic analysis, accelerate business analytics, predict larger weather patterns, or create better 3D animation, Intel will be working to deliver the products to achieve those goals.

Richard Dracott is the General Manager of High Performance Computing in Intel's Server Platform Group. He is responsible for driving a cross organizational team to grow Intel's overall business in this fast growing market segment including silicon, platforms and software products, in addition to industry initiatives and collaboration.

Thor Sewell is the Director of Technical Computing Marketing in Intel's Server Platform Group. He is responsible for driving Intel's marketing strategy for High Performance Computing and Workstations, and working with the industry to incorporate Intel's products and platforms for these fast growing segments.

Article Tools

Share Options

(Digg, Technorati, more)

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

You must be a registered user in order to comment on HPCwire stories.

Members enjoy:

	Access to Special Content, including Podcasts, Webcasts, and Whitepapers and more!
	Ability to take an active role in the discussions that are shaping the HPC technology discipline!
	Special offers available only to HPCwire members!

Become a Registered User Today!

Registered Users Log in Here to Comment

Email Address:	Password (case sensitive)

Remember me	Forgot Password?

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Feature Articles

The Week in Review

C-DAC announces plans for a petaflop system; IBM researchers are working on vertical integration techniques to extend Moore's Law another 15 years. We recap those stories and more in our weekly wrapup.
Read More...

Moscow State University Supercomputer Has Petaflop Aspirations

The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...

Intel Ups Performance Ante with Westmere Server Chips

Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...

Read more HPCwire features...

Top Headlines

Australia Commissions Cray Supercomputer

Mar 19 | OfficialWire | New super to support intelligence work Down Under. Read more...

Intel Partners See 'Easy' Upgrade Path With Xeon 5600 Chips

Mar 18 | ChannelWeb | Westmere parts already showing up in HPC machines. Read more...

AMD: OEMs primed for Opteron 6100s

Mar 17 | The Register | But what about the tier ones? Read more...

Arrival of the Desktop Supercomputer

Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...

Scheduling HPC In The Cloud

Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...

Read more headlines...

Featured Whitepapers

Virtualization for Aggregation And The vSMP Architecture™

Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.

Copper Cable Technologies for High Performance Computing

Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.

View the White Paper Library

Multimedia

Webcast: Virtualized Data Center Roundtable

Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.

Webcast: Watch SC09 Birds of a Feather Video: Scalable Fault-Tolerant HPC Supercomputers

Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.

Webcast: High Performance Computing for a Smarter Planet

LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html