Saratov State University Developing Curriculum on Sun HPC Software

Grid Dynamics, the global leader in scaling mission-critical systems, today announced it is working with Sun Microsystems and Saratov State University (SSU), to develop a new course of study in high-performance computing (HPC) at SSU, which is one of Russia’s oldest and most respected universities. Full Story

Benchmark: Sun Ultra 27 Single Frame Buffer SPECviewperf 10 Results

Yes, Sun still makes high performance workstations. The BestPerf blog describes how a Sun Ultra 27 workstation configured with an nVidia FX5800 graphics card delivered outstanding performance running the SPECviewperf® 10 benchmark. Full Story

Sun Benchmarks Reverse Time Migration

Just in time for SEG comes news of Sun's outstanding performance on Reverse Time Migration:

"A Sun Blade 6048 Modular System with 12 Sun Blade X6275 server modules were clustered together with QDR InfiniBand and using a Lustre File System with QDR InfiniBand to show performance improvements over an NFS file system for reading in Velocity, Epsilon, and Delta Slices and imaging 800 samples of various various grid sizes using the Reverse Time Migration. Full Story

and

"A prominent Seismic Processing algorithm, Reverse Time Migration with Optimal Checkpointing, in SMP "THREADS" Mode, was testing using a Sun Fire X4270 server configured with four high performance 15K SAS hard disk drives (HDDs) and a Sun Storage F5100 Flash Array. This benchmark compares I/O devices for checkpointing wave state information while processing a production seismic migration. Full Story

New Software Could Smooth HPC Speed Bumps

With all the buzz on GPUs these days, programming these devices remains a big issue:

"Now, this is changing as AMD, NVIDIA and their customers (primarily computer- and game system–makers) throw their support behind a standard way of writing software called the Open Computing Language (OpenCL), which works across both GPU brands. A longer-term goal behind OpenCL is to create a common programming interface that will even let software writers create applications that run both GPUs and CPUs with few modifications, cutting the time and effort required to harness supercomputing power for scientific endeavors." Full Story

Sun and Voltaire Accelerate Clemson Computational Center

This Desktop Engineering article describes the HPC cluster at CU-CMS. Sun Microsystems delivered and installed a 35 teraflop system based on 43 Sun Blade 6000 Modular Systems, Sun Fire servers and Sun StorageTek systems.

"To help attract leading companies from the automotive industry as well as other industries such as energy, aviation, and aerospace, Clemson University selected Voltaire’s scaleout computing fabric solutions as the interconnect for the high-performance computing (HPC) system operated by the Clemson University Computational Center for Mobility Systems (CU-CCMS). The system enables the university to provide simulation test research to automotive and transportation companies that need to reduce overall design cycle times to develop better products faster and at a lower cost. Full Story

HPC Customers Weigh in on Sun Storage F5100 Flash Array

HPC Wire cites some glowing customer quotes from Sun HPC customers on the performance of the Sun Storage F5100 Flash Array. Don Thorp, Operations Manager at SDSC had this to say:

"San Diego Supercomputer Center (SDSC) has been evaluating the F5100 Flash Storage array as a high performance SamQFS metadata target, which sits at the core of our archiving services and hosts well over one hundred million files. Performance improvement of 2.5 to four times was demonstrated for file creation and metadata scans, such as listing and backups. Further testing will be done using the Sun Storage F5100 as a Lustre metadata target, high speed storage pool in Lustre 2.0 for user checkpoint data, Oracle database storage device and out-of-core storage device on an HPC cluster." Full Story

Vote: HPC Community Leadership Awards

Democracy reigns in the HPC community. Here is your chance to recognize the leaders that drive high performance computing:

insideHPC’s HPC Community Leadership Awards. The award recognizes the people and organizations who have persevered through technology, budget or organizational challenges to place innovative HPC solutions in the hands of users in business, engineering, technology, and science.

Not to be left out, the HPCwire Reader's Choice Awards allow the HPC community to recognize some of the most outstanding organizations and individuals in the industry. This year, two new categories were added: "Best Use of HPC in the Cloud" and "Best Application of Green Computing in HPC" in recognition of the tremendous amount of innovation happening in the industry. The Readers' Choice Awards are determined by a poll of HPCwire readers, and the Editors' Choice Awards are determined by a panel of recognized HPC luminaries and contributing editors from industry. All winners will be announced at the SC09 in Portland, Oregon. Vote Here

Sun Rocks HPC Benchmarks

Sun just rolled out an impressive set of HPC Benchmarks:

Oct 13, 2009 Halliburton ProMAX Oil & Gas Appl on Sun 6048/X6275 Cluster and Oracle Database
Oct 13, 2009 MCAE ABAQUS faster on Sun F5100 and Sun X4270 - Single Node World Record
Oct 12, 2009 MCAE ANSYS faster on Sun F5100 and Sun X4270
Oct 12, 2009 MCAE MCS/NASTRAN faster on Sun F5100 and Fire X4270
Oct 13, 2009 CP2K Life Sciences, Ab-initio Chem - Sun C48 with Sun Blade X6275 - QDR InfiniBand
Oct 09, 2009 X6275 Cluster Demonstrates Performance and Scalability on WRF 2.5km CONUS Dataset

Sun Blades: Outstanding Performance on WRF Weather Code

Sun continues to set new performance levels with Intel Nehalem processors. The BestPerf Blog presents exciting results for the Weather Research and Forecasting (WRF) code running on twelve Sun Blade X6275 server modules, housed in the Sun Blade 6048 chassis, using the 2.5 km CONUS benchmark dataset.

* The Sun Blade X6275 cluster was able to achieve 373 GFLOP/s on the CONUS 2.5-KM Dataset.
* The results demonstrate an 91% speedup efficiency, or 11x speedup, from 1 to 12 blades.
* The current results results were run with turbo on.

Read the Full Story.

Sneak Preview Video: Featured Speakers at SC09

Here's a recap of featured speakers at SC09:

TUESDAY, NOVEMBER 17TH

Opening Address: The Rise of the 3D Internet: Advancements in Collaborative and Immersive Sciences

Speaker: Justin Rattner, Intel Corporation
Time: 08:30AM - 10:00AM
Room: PB253-254-257-258

WEDNESDAY, NOVEMBER 18TH

Plenary Speaker: Systems Medicine, Transformational Technologies and the Emergence of Predictive, Personalized, Preventive and Participatory (P4) Medicine

Speaker: Leroy Hood, Institute for Systems Biology
Time: 08:30AM - 9:15AM
Room: PB253-254-257-258

THURSDAY, NOVEMBER 19TH

Keynote Address:Building Solutions: Energy, Climate and Computing for a Changing World

Speaker: Former U.S. Vice President, Al Gore
Time: 08:30AM - 10:00AM
Room: PB253-254-257-258

Get the Full Story.

New Details on Al Gore Keynote at SC09

The SC09 folks have announced the title of Al Gore's Keynote Presentation for Thursday, November 19th. The SC09 Keynote will be titled, "Building Solutions - Energy, Climate and Computing for a Changing World."

Gore will deliver the keynote presentation on Thursday, November 19th for the anticipated crowd of 11,000 attendees made up of leading computational scientists, researchers, and supercomputing experts from around the globe, many of whom work on HPC platforms and supercomputers researching life-changing issues such as disease understanding, drug discovery, renewable energy, and global climate change. Full Story

Interview with Intel CTO Justin Rattner

Inside HPC has a nice piece on Justin Rattner of Intel, keynote speaker for the opening address at SC09 in November:

“When I started out with this idea in 1984, Cray and vector supercomputing was dominant,” Rattner says. “In 1984 or 1985 I gave a talk on the idea that very large ensembles of microprocessors would eventually replace complicated vector processors in supercomputers. I think 9 out of 10 people in the audience thought I had lost my mind.” Full Story

Dude is not getting a Dell

Contrary to what you might be reading elsewhere, Sun customers are a loyal bunch. Case in point: Karl Katzke blogs on why he is sticking with Sun hardware:

"Simply put, the Sun option was the fastest, most scalable option. The hardware is put together well, with the same sort of build quality you’ve come to expect from HP… far superior to Dell or IBM. And the management and tuning options are awesome." Full Story

Latest Sun HPC News Published

The latest edition of the Sun HPC News is out. Don't miss an issue--Subscribe today!

Register Now: Sun HPC Consortium - Portland, Nov. 14-15

Save the dates: November 14-15 for the upcoming Sun HPC Consortium to be held in Portland, Oregon for Sun's customers and partners. This special Sun HPC customer event is taking place just before the SC09 Conference. For further information, please see the registration site.

Sun HPC Consortium participants represent a broad range of computing applications and environments. The meeting format is designed to give participants the opportunity to present HPC developments, discuss applications and needs with their peers, and to hear and provide feedback on Sun's engineering plans.

Who should attend: All Sun scientific, engineering, or research computing customers or anyone interested in high-performance computing on Sun technologies. Each meeting is designed to address a wide range of interests from application developers to CIOs and VPs of Research.

Hurry! Early Bird Registration rate (20% discount) is valid only until October 23rd. Registration site.

Get HPC for Dummies

Do all those high performance acronyms get you confused? Download your copy of this special edition eBook from Sun and AMD today! Get the book

Bechtolsheim: 10 Gig Ethernet going mainstream

The Register interviews Andy Bechtolsheim and discovers that he is bullish on 10Gig Ethernet:

"What has Bechtolsheim fired up about 10GE is that it is starting to go mainstream. Even with the generic networking business expected to see an annual revenue decline on the order of 20 per cent in 2009, according to Bechtolsheim, the number of 10GE ports attached to servers are expected to grow from about 400,000 in 2008 (against new server shipments of around 8 million globally). Bechtolsheim predicts that the number will more than double each year over the three years so that by 2011, over 4 million 10GE server ports will ship in that year and, if you do the math, with about 7.5 million 10GE server ports installed by 2011. About 2 per cent of all servers in the installed base had 10GE ports in 2008, which will rise to about 5 per cent this year, hit maybe 10 per cent in 2010 and to about 25 per cent or more in 2011.

"It is easier to forecast 10GE ports than revenues," says Bechtolsheim. "This is one of the few areas in IT with predictable growth." Full Story

September Sun HPC Newsletter

The September edition of the Sun HPC Newsletter is out. Don't miss an issue--Subscribe today!

Sun Rolls Out Business Ready HPC

Sun's industry solutions are optimized for maximum application performance, efficiency, and scale with reliability built-in. With Sun Business Ready HPC, you can shorten your product development cycles, enable you to make better decisions, faster. The result? You can boost your ROI and gain major competitive advantage. Full Story

New whitepaper: Storage for Cloud Computing

Sun's Mark Carlson and Gary Mazzaferro have written a new whitepaper on Storage for Cloud Computing. To learn more about SNIA's Cloud Data Management Interface (CDMI) standard, and how it works with Cloud Computing standards such as the OGF Open Cloud Computing Interface (OCCI) please download the whitepaper.

Java Fast Sockets for HPC

Does Java have what it takes as a programming environment for HPC? Inside HPC points us to this paper on Java Fast Sockets:

"This paper presents Java Fast Sockets (JFS), an optimized Java socket implementation on clusters for high performance computing. Current socket libraries do not efficiently support high-speed cluster interconnects and impose substantial communication overhead. JFS overcomes these performance constraints by: (1) enabling high-speed communication on cluster networks such as Scalable Coherent Interface (SCI), Myrinet and Gigabit Ethernet; (2) avoiding the need of primitive data type array serialization; (3) reducing buffering and unnecessary copies; and (4) reimplementing the protocol for boosting shared memory (intra-node) communication. Its interoperability and user and application transparency allow for immediate applicability on a wide range of parallel and distributed target applications. A performance evaluation conducted on a dual-core cluster has shown experimental evidence of throughput increase on SCI, Myrinet, Gigabit Ethernet and shared memory communication. It has also been analyzed the impact of this improvement on the overall application performance of representative parallel codes." Full Story

Sun HPC Newsletter for August

The August edition of the Sun HPC Newsletter is out. Don't miss an issue--Subscribe today!

Hedge Funds And HPC

As we approach the annual High Performance on Wall Street event, this excerpt from Business Knowledge for IT in Hedge Funds sheds some light on how HPC is used in the financial sector:

"Currently, there is intensive competition among hedge funds and with other financial markets for a slice of the credit derivatives market. To achieve this, a great deal of consideration should be given to scalability across business processes, which may provide a competitive edge. HPC is a veritable technology that is an enabler for scalability and faster pricing of existing and new types of exotic derivatives." Full Story

Posted by Rich Brueckner [HPC Article of the Day] ( August 30, 2009 05:00 AM ) Permalink | Comments [0]

Iowa State Replaces IBM with Sun HPC

Iowa State University has replaced their IBM Blue Gene/L system with "Cystorm," a Sun HPC Cluster with 3200 processor cores:

""Cystorm is going to be very good for data-intensive research projects," Aluru said. "The capabilities of Cystorm will help Iowa State researchers do new, pioneering research in their fields." Full Story

Posted by Rich Brueckner [HPC Article of the Day] ( August 25, 2009 05:00 AM ) Permalink | Comments [0]

Comparing MPI and OpenMP

Douglas Eadline writes in Cluster Connection that the hardware environment may determine the best parallel programming tool to use:

"Another method to express parallelism is OpenMP. Unlike MPI, OpenMP is not an API, but an extension to a compiler. To use OpenMP, the programmer adds “pragmas” (comments) to the program that are used as hints by the compiler. The resulting program uses operating system threads to run in parallel. Operating system threads can be thought of as separate subroutines running at the same time that share the same memory space. In addition to the fact that “MP” is in both the names of these methods, there is often some confusion about how each of these parallel paradigms works and where/when they should be applied. This article will explain the differences and provide a better understanding of these two powerful technologies." Full Story