Progeniq

New BoostServe™ Extreme Provides 1000x Acceleration for Selected Bioinformatics Applications

Progeniq — Thu, 02 Oct 2008 13:00:00 GMT

...Acceleration solution also offers cost savings of more than 10x, energy savings of 600x...

Redwood City, CA & Singapore - October 2, 2008 - Progeniq Pte Ltd, a leader in providing accelerated computing solutions, today launched the BoostServe™ Extreme for the Bioinformatics industry. The product gives servers and desktops processing power equivalent to over one thousand CPU cores in less than one tenth the space of a server rack.

“The BoostServe™ Extreme launch is a major milestone in Progeniq’s aggressive R&D effort, delivering high-end, accelerated solutions for mid-sized research institutes at an unbeatable space and power footprint” said Progeniq's VP Business Development, Mr. Teck Hiong Chua. “Other solutions in the market require at least one rack (42U) of server space to deliver 1,024 CPU cores of performance. The BoostServe™ Extreme provides a 1,000 CPU equivalent performance in just a tenth of that space. By installing 10 chained BoostServe™ units, the overall solution can scale linearly by ten times to 10,000 CPU core performance in each rack of datacenter space, presenting unprecedented scalability.”

BoostServe™ Extreme accelerates computationally intensive Bioinformatics applications like Smith-Waterman, ClustalW, HMMsearch, and HMMpfam, over one thousand times faster than a single CPU core. It consumes six hundred times less power, and slashes equivalent performance acquisition cost by 90%. Annual maintenance cost is estimated to be 80% lower than if the same performance had been achieved by CPUs alone.

More details on the BoostServe™ Extreme is available at:
http://www.progeniq.com/BoostServeExtreme/

For information about Progeniq, visit http://www.progeniq.com

Progeniq BioBoost™ White Paper

Progeniq — Thu, 25 Sep 2008 13:00:00 GMT

The Bioinformatics Data Overload

Life Sciences education and research requires high performance computing infrastructure, such as clusters. With the large and increasing size of Bioinformatics databases, applications often require months of processing time per data set.

As an example, the GenBank database has been growing at a rate of a doubling every 12 months. There is a corresponding need for an increasing amount of computational power to analyze all that data.

Introducing BioBoost

The Progeniq BioBoost turbo-charges applications such as Pairwise and Multiple Sequence Alignment with performance of over 20 equivalent 2.4GHz CPU cores from a single accelerator.

This is done by leveraging on a reconfigurable hardware processor that can 'rewire' itself on the fly according to whichever application needs to be accelerated. Such processors are technically known as Field Programmable Gate Arrays (FPGAs).

Removing Bottlenecks to Increase Workflow Throughput

The BioBoost accelerator can speed up specific applications, depending on how well such applications lend themselves to parallelization on FPGAs.

To maximize the use of such hardware accelerators as well as computational clusters, there is a balance that should be achieved in terms of leveraging on the BioBoost accelerators to remove computational bottlenecks so as to maximize throughput with the rest of the cluster.

SGI Whitepaper features Progeniq and FPGA technology - Supercharging Proteomics Discovery

Progeniq — Wed, 25 Jun 2008 01:23:00 GMT

Many of today’s research problems rely on huge volumes of data, the analysis of which can lead to computing bottlenecks. Systems biology approaches are even more complicated because researchers want to drill down to the minutest level of details, even as they maintain cross-referencing to investigate relationships between proteins. These computational problems become large enough that the traditional approach — assembling more CPU power in an ever-expanding cluster — begins to generate limiting returns. Numerous CPUs sending and receiving large amounts of data create an I/O bottleneck. Those processors also eat up power and space, and management of such clusters become unwieldy.

Computational limits can also prevent researchers from asking really big questions. In an ideal world, researchers would like to incorporate many lines of inquiry into a single series of experiments. For example, an experiment to investigate the genetic basis of mental retardation in fruit flies — pursued as a model of Fragile X syndrome and other forms of human mental retardation — might also include an analysis of the fly metabolites (its metabolome) as well as its proteins. Determining associations and performing cross-correlations, perhaps across multiple species of fly, would quickly overwhelm any traditional computing cluster.

Typically, researchers respond to such limitations by simplifying the experiment so that computational resources can handle the burden, but that limits the power of the experiment and analysis. The kind of in-depth analysis that can really push forward the boundaries of science requires a totally different approach, such as marrying traditional clusters with Field Programmable Gate Array (FPGA) devices that can eliminate computational bottlenecks.

The Proteomics Appliance

To respond to these needs, SGI has developed the Proteomics Appliance. It is based on the SGI® RASC™ (Reconfigurable Application Specific Computing) system using Intel® Itanium® and Quad-Core Intel ® Xeon ® Processors. SGI’s technology partner, Singapore-based Progeniq, has already loaded the Proteomics Appliance with the proteomics applications Smith-Waterman and ClustalW, and it is expected that by the end of March it will also be loaded with HMMer. BLASTp will follow soon after.

Preliminary test runs with the SGI Proteomics Appliance show a 20 to 30-fold speedup over a

2.4GHz Intel Core 2 Quad Q6600 when using Smith-Waterman to search the SWISS-PROT database with query sequences ranging from 500 to 1,000 amino acids. The performance of Clustal W shows an approximate 7-fold speedup over the same 2.4GHz Intel Core 2 Quad Q6600 when aligning a set of 124 sequences. These already impressive boosts will be improvedfurther as the researchers at SGI and Progeniq further optimize the system. Combined with the SGI® Altix® system, the Proteomics Appliance can run analyses as much as hundreds of times faster than traditional solutions, with only a minimal increase in power consumption. The Appliance’s reconfigurable hardware processor can ‘rewire’ itself on the fly according to whichever application needs to be accelerated.

Progeniq Opens Office in California, USA

Progeniq — Tue, 24 Jun 2008 13:00:00 GMT

...Continues Growth and Global Expansion Drive...

Singapore and Redwood City, CA — June 24, 2008 — Progeniq Pte Ltd, a leader in reconfigurable computing applications headquartered in Singapore, today announced the opening of its first overseas office location in Redwood City, California.

“Progeniq has been on a rapid expansion ramp-up over the past months,” said Darran Nathan, Progeniq’s Chief Executive Officer. “Establishing our US operations as the first of our overseas offices reflects our strong commitment to provide our global clients and partners with timely support in an efficient manner.”

Progeniq’s products accelerate bioinformatics applications for the Life Sciences industry and 3D CGI / Visual Effects rendering for the Animations industry. The BioBoost^TM and RenderBoost^TM product lines run accelerated applications on Field Programmable Gate Array (FPGA) processors, offering over 100x better performance per unit space, and over 1000x better performance per watt, over ordinary CPUs.

“Progeniq's accelerated applications help businesses unlock their revenue earlier, by drastically shortening their computational time requirements from days to hours and minutes,” added Nathan. “We've had very good traction in the market over the past years, and are actively continuing to hire top minds to further grow the company and maintain our leading position in the accelerated applications space.”

For additional information visit Progeniq’s website at http://www.progeniq.com

CONTACT INFORMATION

Progeniq Pte Ltd

USA

3, Twin Dolphin Drive, Suite 150

Redwood City, CA 94065

Singapore

277 Bukit Batok East Ave 3 #02-371

Singapore 650277

Tel: (65) 6899 2396 Fax: (65) 6899 2396

Bio-IT World: Add-On Speed for Bioinformatics

Progeniq — Sat, 01 Mar 2008 15:00:00 GMT

March 1, 2008 | Today’s pharmaceutical simulations eat up computer run time faster than CPU-makers can churn out more-powerful chips. “Some calculations performed in molecular dynamics, for example, can easily take a month, and many problems are not even feasible,” says Nathan Woods, chief scientist at XtremeData in Schaumburg, Illinois. As a result, researchers and hardware designers often opt to speed up simulations with hardware accelerators instead of adding CPUs.

Even without taking on new territory, such as molecule-level simulations, researchers in bioinformatics still face a data-CPU divide. “NIH’s GenBank is approximately doubling in size year after year,” says Teck Hiong Chua, vice president of business development at Progeniq in Singapore. Consequently, researchers need more computing power to search through those data. “The 400 next-generation sequencing instruments already deployed have the capacity to generate 41 terabases in a year,” says Martin Gollery, senior bioinformatics scientist for Active Motif in Carlsbad, California. “That’s over 550 times more data than is currently stored in GenBank.” So even if Moore’s Law stayed on pace, the growth in data would easily overwhelm hardware advances. This imbalance, though, gives add-on accelerators an edge.

Instead of running algorithms through programs that get interpreted and carried out by a CPU, developers essentially hard wire algorithms into the add-on accelerators. These devices work like a chip that was designed to do a specific task. As a result, they run faster than a CPU for many algorithms. Progeniq, for example, developed its BioBoost 4.0 around USB 2.0. “It can fit into an existing PCI slot or sit on the desk plugged into a workstation or laptop,” says Chua. When running Progeniq’s recent Hidden Markov Model (HMM) sequence analysis on the BioBoost 4.0, says Chua, “this gives an average speed up of 25 to 85 times — depending on the sequence length and database — versus a normal workstation.” He adds that Progeniq will soon release applications for Smith-Waterman and ClustalW algorithms. The base model of BioBoost 4.0, to just run say the HMM, costs about $7,500. To get the BioBoost 4.0 with a complete suite of applications, a researcher will pay an additional $5,000–10,000

Adding Algorithms

CLC bio in Aarhus, Denmark, makes a variety of accelerators for bioinformatics, including its Bioinformatics Cube. This FPGA (fieldprogrammable gate array)-based device can be connected to a computer via a USB port, and works with various operating systems, including Linux, Mac OS X, and Windows. “It can be programmed with any of our workbenches or command lines,” says Bjarne Knudsen, CLC bio’s chief scientific officer. He adds that the Cube can speed up Smith-Waterman algorithms by as much as 100 times. The Cube also runs a variety of BLAST algorithms. “We are continually developing new algorithms,” Knudsen says, such as the forthcoming HMM algorithm. Depending on the algorithms desired, the Cube costs about $10,000. In addition, CLC bio will build custom Cube solutions when requested.

Meanwhile, other companies keep extending their add-on options. In March 2008, for example, Active Motif’s TimeLogic division releases its NextEngine accelerator for Linux-based servers. Each of these FPGA-based PCIe cards can process HMM comparisons at the speed of 550 2.6-gigahertz Xeon CPU cores, according to Christopher Hoover, TimeLogic marketing manager. Even previous Active Motif accelerators attracted attention. For example, Terry Gaasterland, director of the Scripps Genome Center at the Scripps Institution of Oceanography of the University of California, San Diego, says, “I have four TimeLogic boards and the associated software to perform DNA- and protein-sequence alignment as well as software for protein-pattern searching by HMM.” Gaasterland describes their performance as simply, “Excellent.”

“Many researchers new to sequence analysis need to analyze Solexa, 454, or SOLiD data,” Hoover says. “These groups are finding out that mapping shorter reads accurately to reference genomes can pose significant computational challenges.” Consequently, some research groups might want more than just an accelerator. They might prefer a complete computing package, such as the Code-Quest Biocomputing Workstation, which accelerates BLAST, Smith-Waterman, HMM analysis, and gene modeling. The CodeQuest can also simplify the development of analyses. It includes a drag-and-drop interface called PipeWorks that lets users stitch together search tools and filters. “Researchers that wouldn’t attempt to code workflows in Perl can annotate genomic data without interfacing with a bioinformatics expert,” says Hoover. Even at a cost of $25,000, he says that CodeQuest can pay for itself in 1–2 years by offsetting the power, cooling, and server-room rack-space costs required by clusters.

Researchers who prefer to crank up the capabilities of their current computers might choose XtremeData’s in-socket accelerators. These plug into extra-CPU slots on a computer’s motherboard. “By plugging into a socket, our device is a peer with a CPU,” says Woods, “and that opens up a host of acceleration benefits.” This FPGA-based device serves a very specific need in a highly parallel way. For example, XtremeData’s most recent XD2000i is designed as an accelerator for Intel’s Bensley Enterprise Platform that runs on the Xeon processor. “Our device sits on the same bus as the processor,” says Woods, “and that gives us a large bandwidth to main memory.” He adds that this is crucial for speeding up calculations on large data sets, such as those used in molecular dynamics or to sequence genes.

The acceleration provided by the XD2000i depends on the application. If a program includes a loop of integer calculations — common in genomics — then “the XD2000i could speed up those operations by 10 to 100 times,” says Woods. “We have direct experience on computer tomography, and there one FPGA replaces about 10 CPUs on integer calculations.”

Hardware accelerators already speed up research in many fields, including agricultural genomics. “Handling comparative assembly techniques for large genomes — plus the downstream annotation required to understand all the genes identified — places a huge demand on IT infrastructure,” Gollery says. “Forty percent of the TimeLogic customers are engaged in plant genomics because it addresses these burdens.”

Progeniq launches fourth generation accelerators

Progeniq — Tue, 12 Feb 2008 14:00:00 GMT

...Delivers 50x CPU speedup over multi-core CPUs...

SINGAPORE — February 12, 2008 — Progeniq Pte Ltd, a leader in reconfigurable computing applications headquartered in Singapore, today launched the BioBoost™ v4.0 Accelerator for Bioinformatics. The BioBoost v4.0 turbo charges new generation multi-core CPU processors that are available on the market.

The BioBoost provides hardware accelerated processing for the most computationally intensive applications in Bioinformatics – NCBI BLAST, Smith Waterman, HMMer and ClustalW. Processing these protein searches will be cut from months to days, and weeks to hours and minutes.

By utilizing improved Field Programmable Gate Array (FPGA) technology, the fourth generation BioBoost is able to accelerate the applications by up to 50 times, and consumes little energy compared with a CPU cluster. This results in energy savings from running and cooling costs, as well as space savings in the ever-expanding data centres of today.

“Progeniq has and will continue to push the hardware accelerator technology forefront for Bioinformatics, with our BioBoost accelerator product line”, said the Chief Executive Officer of Progeniq, Mr Darran Nathan. “It remains our goal to see that hybrid computing architectures involving both FPGAs and CPUs continue the strong growth in market adoption. With the BioBoost v4.0, we’re tracking the improvements in CPU technology by offering an accelerator that provides speedups over the latest multi-core CPUs.”

The BioBoost v4.0 is available for demo upon request, and immediate shipment. Visit http://www.progeniq.com/products/offer.htm for details.

############

About Progeniq Pte Ltd, Singapore

Progeniq is a leader in reconfigurable computing applications for High Performance Computing (HPC) industries, with its BioBoost line of products for the life sciences industry already adopted by institutes worldwide. Today Progeniq continues to reinvent the way computing is done by leveraging on the Boost Platform to introduce reconfigurable computing into new computeintensive industries, increasing the efficiency of computing systems, boosting up performance and slashing cost.

Progeniq joins Microsoft in Bio IT Alliance

Progeniq — Wed, 26 Sep 2007 13:00:00 GMT

Progeniq joins Microsoft in Bio IT Alliance

... Empowers Life Sciences Community with accelerated BioInformatics...

SINGAPORE — September 26, 2007 — Microsoft Corp., announced the initiation of Progeniq Pte Ltd, a leader in reconfigurable computing applications headquartered in Singapore, into the BioIT Alliance today. The BioIT Alliance is a cross-industry group working to integrate science and technology to accelerate the pace of drug discovery and realize the potential of personalized medicine. The early focus of the Alliance has been to address the data-capture and data-integration challenges that face the industry. Additional information about the BioIT Alliance can be found on its Web site at http://www.bioitalliance.org.

The Progeniq BioBoost provides hardware accelerated processing for the most computationally intensive applications in Bioinformatics – NCBI BLAST, Smith Waterman, HMMer and ClustalW. Processing these protein searches will be cut from months to days, and weeks to hours and minutes.

“The life sciences offer one of the best opportunities for information technology to accelerate the pace of drug discovery and development,” said Rudy Potenzone, Bio IT Alliance Manager at Microsoft. “Progeniq’s collaboration in the Alliance will be a tremendous boost in Bioinformatics data-processing and discoveries in the life science industry.”

By utilizing Field Programmable Gate Array (FPGA) technology, the processor is able to 'rewire' itself on the fly according to the application that needs to be accelerated. This results in further energy savings, as the FPGA consumes as little as 5 watts of power from the USB, as compared to the racks of servers and cooling required that it replaces.

“Progeniq is delighted to collaborate with Microsoft and Life Science companies in the Bio IT Alliance,” said Darran Nathan, Progeniq’s Chief Executive Officer. “We are confident that more users will benefit from the speedups from the BioBoost, and more in the life science industry can enjoy its benefits.”

The BioBoost Accelerated suite for Bioinformatics is available for immediate shipment at USD3,000 for first time buyers. Visit http://www.progeniq.com/products/offer.htm for details.

############

About Progeniq Pte Ltd

Progeniq is a leader in reconfigurable computing applications for High Performance Computing (HPC) industries, with its BioBoost line of products for the life sciences industry already adopted by institutes worldwide. Today Progeniq continues to reinvent the way computing is done by leveraging on the Boost Platform to introduce reconfigurable computing into new compute-intensive industries, increasing the efficiency of computing systems, boosting up performance and slashing cost.

About the BioIT Alliance

Formed in 2006, the BioIT Alliance is a cross-industry group working to integrate science and technology in order to accelerate the pace of drug discovery and realize the potential of personalized medicine. Founding members include Accelrys Software Inc., Affymetrix, Inc., Agilent Technologies Inc., Amylin Pharmaceuticals, Inc., Applied Biosystems, The BioTeam Inc., Digipede Technologies LLC, Discovery Biosciences Corporation, Geospiza Inc., Hewlett-Packard Development Company, L.P., Illumina Inc., InterKnowlogy, Microsoft Corporation, Sun Microsystems Inc., The Scripps Research Institute, VizX Labs LLC and other key companies in the pharmaceutical, biotech, hardware and software industries. Additional information about the BioIT Alliance can be found on the BioIT Alliance Web site at http://www.bioitalliance.org.

About Microsoft Corp.

Founded in 1975, Microsoft (Nasdaq “MSFT”) is the worldwide leader in software, services and solutions that help people and businesses realize their full potential.

CONTACT INFORMATION

Progeniq Pte Ltd

7 Prince George’s Park Singapore 118406

Tel: (65) 6779 0930 Fax: (65) 6872 4860

KUMAR Senthil senthil@progeniq.com

CHUA Teck Hiong teckhiong@progeniq.com

AMD White Paper features Progeniq - The Need for Acceleration Technologies to Achieve Cost-effective Supercomputing Performance for Advanced Applications

Progeniq — Wed, 25 Apr 2007 04:00:00 GMT

Supercomputing has become an essential tool for many users, including those working in the scientific,engineering, biomedical, and financial disciplines. Although processing capabilities continue to advance, in many cases demand is increasing at an even faster rate. Simulation and analysis problems — once intractable due to computational limitations — have become possible.

Supercomputing technology has evolved from highly specialized and custom circuitry to commodity circuits based largely upon x86 instruction-compatible processing hardware. Leveraging economies of scale lowers costs of production, amortizes research and development, and simplifies software development, as more programmers are familiar with the technologies. Indeed, many supercomputers listed on the TOP500 supercomputers site (http://www.top500.org) are aggregations of commodity processing units and parts. Programs may be easily ported from desktop Linux® machines — which are popular platforms in development and scientific and engineering — to Linuxbased supercomputing systems.

Aggregating large numbers of processors into huge clusters and cluster-like machines, while useful, has a variety of limitations. Overcoming these limitations in order to extract the maximum performance from these systems requires extensive application of acceleration technologies. In order to understand the limitations and how acceleration technology addresses them, this paper will examine why clusters are built, and a brief history of supercomputing technology will provide context for the need for acceleration technologies.