The Itanium Solutions Blog

It’s a little known fact that the same uniquely scalable shared memory architecture that enables SGI Altix® 4700 with Intel® Itanium® processors to power technical and scientific breakthroughs also excels at high-performance reasoning on ontologies for enterprise data analytics applications. Ontologies are knowledge models or formal representations of a set of relevant concepts within a domain and the relationship between these concepts.

A major advantage of ontologies for data analytics is the ability to share the meaning (semantics) of information in a knowledge model, capture complex relationships and integrate heterogeneous data sources. These characteristics can only be achieved if the ontology run-time is able to scale with a growing number of facts.

Silicon Graphics and Ontoprise GmbH have demonstrated that OntoBroker® inference engine can load and process large ontologies in main memory. The SGI Altix 4700 platform has a unique configuration elasticity that allows adding processors and memory independent of each other, and thus easily accommodating user growth and securing hardware investment with a lower TCO. Here are some benchmark examples using the OntoBroker inference engine on a SGI Altix 4700 server:

–Complex graph traversal. Finding the possible traversable paths between the nodes in a graph comprising of 1 million nodes takes only 15.7 seconds, thus making complex reasoning possible

–Semantic retrieval and query processing with 104 facts. Five classes of 195 queries with varying complexity run in less than 18 milliseconds on the SGI Altix® 4700

–SmartWeb®. The longest queries for multimedia web content with 95 queries and 60 rules takes an average of 17 seconds from a disk-based database but only an average of 73 milliseconds from a non-materialized in-memory model.

–Wikipedia® knowledge base search. The most complex query with average result sets from Wikipedia® knowledge base takes less than 35 ms with a trade-off of load time of 48 million wiki facts in 138 minutes

–Automotive test. A large ontology comprising of 1.4 million facts takes only 133 seconds for in-memory load while queries over the indexed database model, and the database load took 381 seconds. The query times showed that large result sets benefit most from an in-memory model

So with a professional reasoning engine like OntoBroker, and scalable servers like SGI Altix 4700, users of many applications can find required information much more quickly and easily.

As a leader in computationally intensive computing, SGI tends to set the pace for the large memory systems often required to crunch the numbers in massive data sets. In a recent press release, we announced that our Altix systems have now achieved 21 Terabytes of globally addressable memory at customer sites. I’d like to explain what this means in more depth and offer examples.

The Altix 450/4700 (Itanium) systems can accommodate 128 terabytes of globally shared memory under the control of a single instance of the Linux operating system. The system may also be partitioned among multiple instances of Linux and provide globally addressable shared memory among OS instances via SGI’s unique NUMAlink® interconnect technology. What this means to the customer is essentially saving time: time-to-results, time-to-solution and time-to-innovation. It significantly simplifies application development and debugging for all parallel programming models be it OpenMP, pthreads, MPI or SHMEM.

In addition, it offers an integrated platform for application fusion, which enables running a mix of different applications and workloads. As workloads usually change during the project life-cycle, a global shared memory platform lowers TCO compared to clusters that require node reconfiguration.

We have seen great success for memory-resident database applications with uses in Internet data centers and transaction processing; as well as those based on “graph theory,” an important area of mathematics with uses in defense and homeland security applications, multi-disciplinary science, and data assimilation. Some customers who are already seeing the advantages of the SGI Altix product line are:

Wright-Patterson Air Force Base: the laboratory here uses an SGI Altix 4700 system with 4,608 Intel Itanium processors in a single supercomputer equipped with 20 TB of globally addressable memory and 440 TB of usable disk space. Globally addressable memory means applications can be shared across various operating systems via SGI NUMAlink. One of the largest computers in the Department of Defense, the SGI resource helps DoD researchers to design faster, reduce risk by increasing the quality of modeling and simulation, and support an intensifying effort to develop “game-changing” computational science and engineering applications.

The Leibniz Supercomputing Centre Munich (LRZ): This facility operates a 4,864 Intel Itanium processor system with slightly over 39 TB of globally addressable memory that is hard at work solving increasingly complex simulations in physics and astrophysics, materials research, fluid dynamics, chemistry, geosciences and biological sciences.

Click here for more information about SGI® Altix® Itanium globally addressable memory capabilities, or click here for the press release.

In these tough economic times, we are all witness to the profound and unrelenting change and disruption in global economies and markets. Dealing with disruptive change is not easy — it requires careful planning, the proper assessment of risk, and the avoidance of short-term fixes to the detriment of long-term strategies. Companies are looking hard at necessary cost improvements to their IT infrastructure and doing more with less; which has become the mantra of many organizations on the path from surviving to thriving again.

Fortunately, the Itanium Solutions Alliance was formed with a common vision for a new era of mission-critical computing that includes delivering a cost effective, open standards-based infrastructure for businesses and large enterprises who need to ensure their data is protected and always available.

This year the Itanium platform will move from dual-core to a more powerful and more reliable quad-core foundation, assuring users that performance gains are keeping up with the demands of their data infrastructure.

In this video, Kirk Skaugen, VP of Intel’s Digital Enterprise Group and General Manager of Intel’s Server Platforms Group explains how a group of competitors in the mission-critical computing segment got together to form the Alliance, what that means for today’s customers, and how it helps address the requirements of tomorrow.

In these days of economic turmoil, it’s tempting for industry observers to paint with a pessimistic brush. Cynicism is in vogue, and the computer business is certainly not immune. When things look the darkest and negativity prevails, it’s easy to overlook the positive. Take the Itanium architecture, for example. From its rather rocky start in the early 2000’s, Itanium has made great gains across a number of critical markets. While not the Swiss Army knife that it once hoped to provide, the architecture has earned considerable success as a foundation for powerful servers that carry the industry’s toughest workloads — as validated by the ecosystem’s growth to more than 13,000 applications, broad availability of OS environments and host of system manufacturers that offer Itanium-based solutions.

Today, more than 224,000 Itanium systems have shipped worldwide to customers who have demanded the type of mission critical performance and reliability Itanium is known for. And while not all customers require the robustness of an Itanium solution, there are countless users who rely on these solutions to power their mission critical businesses, provide critical support to their customers, and enable state of the art research that benefits the world. The Alliance is committed to recognize and share the stories of these customers and the often dramatic results they have achieved. Through our annual Innovation Awards program we seek to focus the spotlight on remarkable successes that Itanium users have created using Itanium-based systems. These stories come from around the world and from a variety of industries and research institutions.

Whether saving an enterprise a bundle in operating costs as a mainframe or RISC system replacement, helping researchers unlock the human genome or delivering complex visualization systems that protect our troops overseas, Itanium-based platforms form the backbone of projects that typify the continuing innovation in our industry — the sort of innovation that has driven and will continue to drive the industry to new levels of achievement and success.

And in today’s economic climate, it’s not enough to deliver dramatic results; those results must be reached in the most cost effective manner possible. In 2008, IDC called the Itanium platform the “fastest growing computing platform in the world.” We like to think that’s because of the real value Itanium-based solutions have to offer — value that perhaps means even more in times like these.

For the electricity industry in India, managing customers is all about power and availability.

Yes, handling the ever-increasing energy production and distribution demands in a rapidly growing economy is a challenge, indeed. Along with that, however, comes a sometimes less discussed but no less critical problem: how to handle the explosive growth in IT infrastructure to manage the growing volume and complexity of its customer base.

In Maharashtra, the country’s third largest state in area and home of its largest city (Mumbai), this problem is massive. The good news is that business is booming, with over 15% of the India’s industrial output produced in this region and the state boasting India’s highest per capital income as well.

Power consumption itself is putting major strains on the region in many ways, as demand currently exceeds supply on a regular basis, and management of customer issues is also growing at a staggering rate. But thanks to Itanium and HP, Maharashtra Electricity State Distribution Company Ltd. (MESDCL) has found a way to handle both current IT demands more effectively and to establish a system with built-in capacity for expansion.

Every month MESDCL handles 15 million customers and the expected growth rate is at least 500,000 new customers to be added every year. Its annual revenues are currently just under $5 billion (U.S.), and the company itself has over 75,000 employees. To support its substantial client base MESDCL had originally written its billing system in Cobol, a workable system for a time but with significant limitations on managing large data arrays.

As capacity demands began to build significantly in the 1990s, MESDC realized it needed to replace its older software solution with a more modern one based on Oracle, which it completed in 2000. Although that helped, as customer growth continued MESDC quickly realized the hardware part of the solution also badly needed upgrading.

As just one example, MESDCL’s existing PA-RISC system, even with the power of Oracle behind it, took as much as 24 hours just to process 10,000 bills. There were other issues as well, including the need to handle a unique photo-based approach to recording electrical meter readings, something that added even more data management problems and was completely unmanageable within the existing IT environment.

MESDCL needed a system with much faster overall response times, lower IT costs that would scale even more efficiently as customer demand grew, and dramatically improved productivity on a grand scale.

Their final solution, which involved a complete re-engineering of their IT infrastructure (including a new picture-processing capability for the photo-based meter readings), used 12 HP Integrity rx3600 servers and 10 HP Integrity rx6600 servers, all driven by dual-core Itanium microprocessors.

With this solution in place, MESDCL has seen its billing processing time for those 10,000 bills drop from 24 hours to only one hour. In addition, because of the increased processing speed, MESDCL was able to roll out its new photo-based meter reading systems for approximately half of its 15 million customers – in the first six months of system deployment.

The solution also offers a far more energy-efficient hardware environment than before, along with a less costly IT support environment as well. Both will provide MESDCL with the “power” to scale their mission-critical computing needs for many years to come.