Issue link: http://osercommunicationsgroup.uberflip.com/i/247471
12 Mo n d a y, N o ve m b e r 1 8 , 2 0 1 3 VISUALIZE AT EXASCALE WITH KITWARE Advances in high-performance computing and data acquisition technologies are allowing researchers to contemplate more complex problems than ever before in many scientific, engineering and medical fields. The research community is facing the challenge of how to manage, analyze and visualize data of such unprecedented size in a meaningful way. With expertise in high-performance, distributed visualization and data processing, Kitware is addressing these issues. As a leader in scientific visualization, Kitware is developing the next-generation infrastructure that will power visualization at the exascale. Visualization and analysis are critical to understanding complex data, but current approaches require a paradigm shift in order to scale with advances in high-performance computing. To tackle this challenge, Kitware is further developing the Visualization Toolkit (VTK) and ParaView, the leading open-source tools for scientific visualization and analysis. VTK is the industry standard, an open-source, freely available software system for 3D visualization and data processing. A true cross-platform solution designed to scale from mobile devices up to supercomputers, VTK supports scientific visualization, information visualization and medical image processing. ParaView is an open-source application that leverages the robust visualization algorithms of VTK to provide data ASROCK INC. PRESENTS ASROCK RACK ASRock Inc. was established in 2002, specializing in the field of motherboards. ASRock strives to build up its own brand. With 3C design concepts (creativity, consideration and cost-effectiveness), the company explores the limits of motherboards manufacturing while paying attention to environmental issues at the same time, developing products with the consideration of being eco-friendly. ASRock has been growing fast, and has become one of the three largest motherboard brands, with headquarters in Taipei and Taiwan as well as branches in Cognimem (Cont'd. from p. 1) programmed with instructions. Rather, our memory is merged together with processing and is taught. Like us, this hardware chip technology is massively parallel, operates at low wattage and can scale to provide very efficient performance per watt. SCSD: You talk about creating chips that can be "taught" versus being programmed. What does this mean? BM: You teach the chips much in the same way you teach a young student how to read, speak or recognize one object versus another. Once taught, you can Silicon Mechanics (Cont'd. from p. 1) EC: We have a broad range of academic and research, government and public sector, and business and industry clients. Our impressive client list includes Duke University, Massachusetts Institute of Technology, Lawrence Livermore National Laboratories and the National Oceanic and Atmospheric Administration. SCSD: What will you be showcasing at SC13? EC: We have a really full program here at SC13. We'll be launching our 3rd Annual Research Grant Program, exhibiting the research successes Europe and the U.S. Since 2012, the manufacturer has been positioned as a leader in this segment in Korea. It's also the second largest ASRock motherboard manufacturer in Japan. The young and vibrant company targets the mainstream segment of the motherboard business, earning a reputation around the world market with its reliability and proficiency. In 2013, ASRock is throwing its enthusiasm into server product lines, and within six months the ASRock team will be offering the following creative server mother- replicate it for many users. For instance, if you wanted the chip to recognize my face versus yours, you present several examples of your face and mine to the inputs of the device. As you show it examples, it will store these as models and will automatically learn what is unique that differentiates you versus me. When it is given an example it hasn't seen before, it compares it to all the patterns it learned in parallel and gives a decision. The chip learns as fast as it recognizes and it doesn't matter if it is images, video, voice or data from a spreadsheet, as long as it is converted to digital information. achieved by prior awardee Saint Louis University, sponsoring a team in the SC13 Student Cluster Competition, as well as underwriting Indiana University's booth. We will also be demonstrating our zStax StorCore unified storage appliance, an enterpriselevel software-defined storage platform based on open-source ZFS technology and powered by NexentaStor™. SCSD: You have an interesting personal history that influences your leadership style and philosophy. Can you share some of this with us? EC: I have had much luck in my life and career, and most importantly, I have to thank the many great people that Su p e r C o m p u te r Sh o w D a ily analysis and visualization in an end-user environment. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques, and explore data interactively in 3D. ParaView was developed to analyze extremely large datasets using memory computing distributed resources, but it is also a powerful tool on a standard desktop or laptop computer. To augment these products, Kitware is contributing to the collaborative efforts on the Data Analysis at Extreme (DAX) toolkit and Portable Data-Parallel Visualization and Analysis Library (PISTON). Both of these efforts are targeted to delivering extremely scalable data analysis functionality using current and next generation processors including multi- and many-core architectures. With the architectures of DAX and PISTON, researchers will be able to leverage boards and barebones: 1U cold storage barebone, 2U SSD cache barebone, 3U GPGPU card barebone, 4U 60 3.5 inch HDD barebone, Mini ITX Intel Avoton board, and Half Width Intel Denlow board. Seeing the growth potential of this industry segment, ASRock decided to fund a new subsidiary, ASRock Rack Inc. ASRock Rack Inc. aims to bring the market a fast, flexible, efficient product design and distribute business model, which should have the ability to rock the industry. "Like Zara or UniQlo in the clothing business, we want to bring a similar fast response product design and distribution model to the server industry. We believe it is where the industry is going, and can SCSD: What potential applications will this technology enable? BM: As I mentioned, this pattern recognition hardware is based on very simple, but highly scalable memory processing elements. You can just use a few of them – or a lot – depending on the application needs, with no change in latency for a decision. So applications can range from using a small number of them to monitor a set of signals or control a motor, to using more for doing gesture recognition locally on a handheld to large arrays handling searching through a data base to detect malicious viruses or find that scene in a video that you are looking for. We are helped me along the way. Having grown up in the former East Germany, I saw the effects of a general disregard for an individual's personal growth and achievement. I have come to believe and experience that enduring success requires leadership that shows an unwavering ambition for the organization to thrive, and a passion for building teams that enjoy working together towards a common goal. SCSD: Tell us more about how you put this into practice. EC: First, attracting the right people to join our team is critical. I firmly believe that people drive company objectives, not the other way around. Second, we VTK and ParaView to move their work to the exascale. To support its visualization and analysis products, Kitware provides customers with a variety of advanced software development services. As a flexible and agile organization, Kitware has experience both in leading large-scale collaborative teams to tackle some of today's toughest research challenges, and in developing custom, proprietary software solutions for commercial customers. Representatives are available at booth 4207 to demonstrate how Kitware's highperformance computing and visualization services can be tailored to the needs of both research organizations and commercial product companies. Visit Kitware at booth 4207 during SC13. For more information, visit www .kitware.com, call 518-371-3971 or email kitware@kitware.com. bring enormous value to our customers and the whole market," said LL Shiu, Chief Operating Officer of ASRock and Chief Executive Officer of ASRock Rack. View the exciting video of the ASRock extreme computing server at www.youtube.com/watch?v=LIYDuJV5D0&list=UUK2t9Vtqq7AYKXCShevGcmA &index=2. For more product information, please visit www.asrock.com/news/ show/CeBit2013. During SC13, visit ASRock at booth 4322. For more information, visit www.asrock.com, call +886-2-55599600 or email ASRockRack_sales@ asrockrack.com. very good at looking at unstructured data in parallel and making fuzzy decisions based on incomplete data. So applications like machine vision for parts assembly or product inspection, finding a fingerprint match against millions instantaneously for crime scene investigation or gesture control to get rid of all those remotes are just a few examples. There are many practical examples that can utilize the technology long before truly autonomous machines become an everyday reality. During SC13, visit Cognimem at booth 3609. For more information, visit www.cognimem.com, call 916-358-9483 or email info@cognimem.com. grow the company based on our core competencies. It's easy to get distracted and reach for new emerging technologies and markets, but unless it builds on what we can do best, we won't do it. Lastly, good decision making is based on accurate data. To obtain accurate data we need to report and review all facts, whether they are good or bad. A culture of honest communication and transparency, internal and external to our organization, is core to the success of our business. Visit Silicon Mechanics and meet Eva Cherry at booth 3126 during SC13. For more information, visit www.siliconmechanics.com, call 425-424-0000, or email info@siliconmechanics.com.