Gain Critical Insight into the Parallel I/O Ecosystem Parallel I/O is an integral component of modern high performance computing (HPC), especially in storing and processing very large datasets to facilitate scientific discovery. Revealing the state of the art in this field, High Performance Parallel I/O draws on insights from leading practitioners, researchers, software architects, developers, and scientists who shed light on the parallel I/O ecosystem. The first part of the book explains how large-scale HPC facilities scope, configure, and operate systems, with an emphasis on choices of I/O hardware, middleware, and applications. The book then traverses up the I/O software stack. The second part covers the file system layer and the third part discusses middleware (such as MPIIO and PLFS) and user-facing libraries (such as Parallel-NetCDF, HDF5, ADIOS, and GLEAN). Delving into real-world scientific applications that use the parallel I/O infrastructure, the fourth part presents case studies from particle-in-cell, stochastic, finite volume, and direct numerical simulations. The fifth part gives an overview of various profiling and benchmarking tools used by practitioners. The final part of the book addresses the implications of current trends in HPC on parallel I/O in the exascale world.

Making the most ef?cient use of computer systems has rapidly become a leading topic of interest for the computer industry and its customers alike. However, the focus of these discussions is often on single, isolated, and speci?c architectural and technological improvements for power reduction and conservation, while ignoring the fact that power ef?ciency as a ratio of performance to power consumption is equally in?uenced by performance improvements and architectural power red- tion. Furthermore, ef?ciency can be in?uenced on all levels of today's system hi- archies from single cores all the way to distributed Grid environments. To improve execution and power ef?ciency requires progress in such diverse ?elds as program optimization, optimization of program scheduling, and power reduction of idling system components for all levels of the system hierarchy. Improving computer system ef?ciency requires improving system performance and reducing system power consumption. To research and reach reasonable conc- sions about system performance we need to not only understand the architectures of our computer systems and the available array of code transformations for p- formance optimizations, but we also need to be able to express this understanding in performance models good enough to guide decisions about code optimizations for speci?c systems. This understanding is necessary on all levels of the system hierarchy from single cores to nodes to full high performance computing (HPC) systems, and eventually to Grid environments with multiple systems and resources.

This book constitutes the refereed joint post-conference proceedings of the 6th International Symposium on High-Performance Computing, ISHPC 2005, held in, Japan, in 2005. It also includes the refereed post-proceedings of the First International Workshop on Advanced Low Power Systems 2006, ALPS2006, and some from the Workshop on Applications for PetaFLOPS Computing, APC 2005. A total of 42 papers were carefully selected from 76 submissions, covering a huge range of topics.

For the fourth time, the Leibniz Supercomputing Centre (LRZ) and the Com- tence Network for Technical, Scienti c High Performance Computing in Bavaria (KONWIHR) publishes the results from scienti c projects conducted on the c- puter systems HLRB I and II (High Performance Computer in Bavaria). This book reports the research carried out on the HLRB systems within the last three years and compiles the proceedings of the Third Joint HLRB and KONWIHR Result and Reviewing Workshop (3rd and 4th December 2007) in Garching. In 2000, HLRB I was the rst system in Europe that was capable of performing more than one Tera op/s or one billion oating point operations per second. In 2006 it was replaced by HLRB II. After a substantial upgrade it now achieves a peak performance of more than 62 Tera op/s. To install and operate this powerful system, LRZ had to move to its new facilities in Garching. However, the situation regarding the need for more computation cycles has not changed much since 2000. The demand for higher performance is still present, a trend that is likely to continue for the foreseeable future. Other resources like memory and disk space are currently in suf cient abundance on this new system.

This book constitutes the refereed proceedings of the 14th International Conference on High-Performance Computing, HiPC 2007, held in Goa, India, in December 2007.

The 53 revised full papers presented together with the abstracts of 5 keynote talks were carefully reviewed and selected from 253 submissions. The papers are organized in topical sections on applications on I/O and FPGAs, microarchitecture and multiprocessor architecture, applications of novel architectures, system software, scheduling, energy-aware computing, P2P and internet applications, communication and routing, cluster and grid applications, as well as mobile computing.

This volume is published as the proceedings of the third Russian-German - vanced Research Workshop on Computational Science and High Performance Computing in Novosibirsk, Russia, in July 2007. The contributions of these proceedings were provided and edited by the - thors, chosen after a careful selection and reviewing. The workshop was organized by the High Performance Computing Center Stuttgart(Stuttgart,Germany)andtheInstituteofComputationalTechnologies SBRAS(Novosibirsk,Russia)intheframeworkofactivitiesoftheGerman-Russian CenterforComputationalTechnologiesandHighPerformanceComputing. Thee event is held biannually and has already become a good tradition for German and Russian scientists. The ?rst Workshop took place in September 2003 in Novosibirskand the second Workshopwas hosted by Stuttgart in March 2005. Both workshops gave the possibility of sharing and discussing the latest results and developing further scienti?c contacts in the ?eld of computational science and high performance computing. The topics of the current workshop include software and hardware for high performancecomputation,numericalmodellingingeophysicsandcomputational ?uid dynamics, mathematical modelling of tsunami waves, simulation of fuel cellsandmodern? breopticsdevices,numericalmodellingincryptographypr- lems andaeroacoustics,interval analysis,toolsfor Gridapplications,researchon service-oriented architecture (SOA) and telemedicine technologies. Theparticipationofrepresentativesofmajorresearchorganizationsengagedin the solution of the most complex problems of mathematical modelling, devel- ment of new algorithms,programsandkey elementsof informationtechnologies, elaboration and implementation of software and hardware for high performance computing systems,provideda highlevelof competenceofthe workshop. Among the German participants were the heads and leading specialists of the HighPerformanceComputingCenterStuttgart(HLRS)(UniversityofStuttgart), NECHighPerformanceComputingEuropeGmbH,SectionofAppliedMathem- ics(UniversityofFreiburgi.Br.),InstituteofAerodynamics(RWTHAachen),- gionalComputingCenterErlangen(RRZE(UniversityofErlangen-Nuremberg), Center for High Performance Computing (ZHR) (Dresden University of Technology).

This book presents the state-of-the-art in simulation on supercomputers. Leading researchers present results achieved on systems of the Stuttgart High Performance Computing Center in 2007. The reports cover all fields of computational science and engineering, with emphasis on industrially relevant applications. Presenting results for both vector-based and microprocessor-based systems, the book allows comparison between performance levels and usability of various architectures.

This book constitutes the refereed proceedings of the 13th International Conference on High-Performance Computing, HiPC 2006, held in Bangalore, India in December 2006.

The 52 revised full papers presented together with the abstracts of 7 invited talks were carefully reviewed and selected from 335 submissions. The papers are organized in topical sections on scheduling and load balancing, architectures, network and distributed algorithms, application software, network services, applications, ad-hoc networks, systems software, sensor networks and performance evaluation, as well as routing and data management algorithms.

The SUPERMEN "After a rare speech at the National Center for Atmospheric Research in Boulder, Colorado, in 1976, programmers in the audience had suddenly fallen silent when Cray offered to answer questions. He stood there for several minutes, waiting for their queries, but none came. When he left, the head of NCAR's computing division chided the programmers. 'Why didn't someone raise a hand?' After a tense moment, one programmer replied, 'How do you talk to God?'" -from The SUPERMEN The Story of Seymour Cray and the Technical Wizards behind the Supercomputer "They were building revolutionary, not evolutionary, machines...They were blazing a trail-molding science into a product...The freedom to create was extraordinary." -from The Supermen In 1951, a soft-spoken, skinny young man fresh from the University of Minnesota took a job in an old glider factory in St. Paul. Computer technology would never be the same, for the glider factory was the home of Engineering Research Associates and the recent college grad was Seymour R. Cray. During his extraordinary career, Cray would be alternately hailed as "the Albert Einstein," "the Thomas Edison," and "the Evel Knievel" of supercomputing. At various times, he was all three-a master craftsman, inventor, and visionary whose disdain for the rigors of corporate life became legendary, and whose achievements remain unsurpassed. The Supermen is award-winning writer Charles J. Murray's exhilarating account of how the brilliant-some would say eccentric-Cray and his gifted colleagues blazed the trail that led to the Information Age. This is a thrilling, real-life scientific adventure, deftly capturing the daring, seat-of-the-pants spirit of the early days of computer development, as well as an audacious, modern-day David and Goliath battle, in which a group of maverick engineers beat out IBM to become the runaway industry leaders. Murray's briskly paced narrative begins during the final months of the Second World War, when men such as William Norris and Howard Engstrom began researching commercial applications for the code-breaking machines of wartime, and charts the rise of technological research in response to the Cold War. In those days computers were huge, cumbersome machines with names like Demon and Atlas. When Cray came on board, things quickly changed. Drawing on in-depth interviews-including the last interview Cray completed before his untimely and tragic death-Murray provides rare insight into Cray's often controversial approach to his work. Cray could spend exhausting hours in single-minded pursuit of a particular goal, and Murray takes us behind the scenes to witness late-night brainstorming sessions and miraculous eleventh-hour fixes. Cray's casual, often hostile attitude toward management, although alienating to some, was more than a passionate need for independence; he simply thought differently than others. Seymour Cray saw farther and faster, and trusted his vision with an unassailable confidence. Yet he inspired great loyalty as well, making it possible for his own start-up company, Cray Research, to bring the 54,000-employee conglomerate of Control Data to its knees. Ultimately, The Supermen is a story of genius, and how a unique set of circumstances-a small-team approach, corporate detachment, and a government-backed marketplace-enabled that genius to flourish. In an atmosphere of unparalleled freedom and creativity, Seymour Cray's vision and drive fueled a technological revolution from which America would emerge as the world's leader in supercomputing.

The book presents the state-of-the-art in high performance computing and simulation on modern supercomputer architectures. It covers trends in high performance application software development in general and specifically for parallel vector architectures. The contributions cover among others the field of computational fluid dynamics, physics, chemistry, and meteorology. Innovative application fields like reactive flow simulations and nano technology are presented.

This book presents the state-of-the-art in simulation on supercomputers. Leading researchers present results achieved on systems of the High Performance Computing Center Stuttgart (HLRS) for the year 2006. The reports cover all fields of computational science and engineering ranging from CFD via computational physics and chemistry to computer science with a special emphasis on industrially relevant applications. The book comes with illustrations and tables.

to acknowledge the dedicated effort put forth by the Vice-Chairs: Michael A. Bender (Algorithms), Zhiwei Xu (Applications), Jose Duato (Architecture), M. Cristina Pinotti (Communication Networks), and Satoshi Matsuoka (System Software). Without their help and timely work, the quality of this program would not be as high nor would the process have run so smoothly. I thank the other organizers who have contributed to assembling this program, - cludingthose who organizedthe keynotes, tutorials, workshops, awards, poster session, industry exhibits, and those who performed the administrative functions that have been essential to the success of this conference. The work of Sushil K. Prasad in putting - gethertheconferenceproceedingsisalsoacknowledged, aswell asthesupportprovided by Kamesh Madduri and Vaddadi Chandu, Ph.D. students at Georgia Institute of Te- nology, and Vipin Sachdeva, M.S. student at the Universityof New Mexico, in assisting with the EDAS online paper submission and evaluation software. Last, but certainly not least, I express heart-felt thanks to our General Co-chairs, Manish Parashar and V. Sridhar; Steering Chair, Viktor Prasanna; and to the Vice-General Chair, Rajendra V. Boppana; for all their useful advice. Lastly, I thank the Conference General Co-chairs for allowing me to serve our c- munity as the Program Chair of this high-quality international conference. It has been my pleasure to correspond with so many of you, and I personally welcome you to Go

A bold, visionary, and mind-bending exploration of how the geometry of chaos can explain our uncertain world - from weather and pandemics to quantum physics and free will Covering a breathtaking range of topics - from climate change to the foundations of quantum physics, from economic modelling to conflict prediction, from free will to consciousness and spirituality - The Primacy of Doubt takes us on a unique journey through the science of uncertainty. A key theme that unifies these seemingly unconnected topics is the geometry of chaos: the beautiful and profound fractal structures that lie at the heart of much of modern mathematics. Royal Society Research Professor Tim Palmer shows us how the geometry of chaos not only provides the means to predict the world around us, it suggests new insights into some of the most astonishing aspects of our universe and ourselves. This important and timely book helps the reader makes sense of uncertainty in a rapidly changing world.

This volume contains 27 contributions to the Second Russian-German Advanced Research Workshop on Computational Science and High Performance Computing presented in March 2005 at Stuttgart, Germany. Contributions range from computer science, mathematics and high performance computing to applications in mechanical and aerospace engineering.

High-Performance Computing (HPC) delivers higher computational performance to solve problems in science, engineering and finance. There are various HPC resources available for different needs, ranging from cloud computing- that can be used without much expertise and expense - to more tailored hardware, such as Field-Programmable Gate Arrays (FPGAs) or D-Wave's quantum computer systems. High-Performance Computing in Finance is the first book that provides a state-of-the-art introduction to HPC for finance, capturing both academically and practically relevant problems.

VECPAR is a series of international conferences dedicated to the promotion and advancement of all aspects of high-performance computing for computational science, as an industrial technique and academic discipline, extending the fr- tier of both the state of the art and the state of practice. The audience for and participants in VECPAR are seen as researchers in academic departments, g- ernment laboratories and industrial organizations. There is now a permanent website for the series, http: //vecpar.fe.up.pt, where the history of the conf- ences is described. ThesixtheditionofVECPARwasthe?rsttimetheconferencewascelebrated outside Porto at the Universitad Politecnica de Valencia (Spain), June 28 30, 2004. The whole conference programme consisted of 6 invited talks, 61 papers and26posters, outof130contributionsthatwereinitiallysubmitted.Themajor themes were divided into large-scale numerical and non-numerical simulations, parallel and grid computing, biosciences, numerical algorithms, data mining and visualization. This postconference book includes the best 48 papers and 5 invited talks presented during the three days of the conference. The book is organized into 6 chapters, with a prominent position reserved for the invited talks and the Best Student Paper. As a whole it appeals to a wide research community, from those involved in the engineering applications to those interested in the actual details of the hardware or software implementations, in line with what, in these days, tends to be considered as computational science and engineering (CSE)."

Proceedings of the International Symposium on High Performance Computational Science and Engineering 2004 (IFIP World Computer Congress) is an essential reference for both academic and professional researchers in the field of computational science and engineering.

Computational Science and Engineering is increasingly becoming an emerging and promising discipline in shaping future research and development activities in academia and industry ranging from engineering, science, finance, economics, arts and humanitarian fields. New challenges are in modeling of complex systems, sophisticated algorithms, advanced scientific and engineering computing, and associated (multi-disciplinary) problem solving environments. The papers presented in this volume are specially selected to address the most up-to-date ideas, results, work-in-progress and research experience in the area of high performance computational techniques for science and engineering applications.

This state-of-the-are volume presents the proceedings of the International Symposium on High Performance Computational Science and Engineering, held in conjunction with the IFIP World Computer Congress, August 2004, in Toulouse, France.

The collection will be important not only for computational science and engineering experts and researchers but for all teachers and administrators interested in high performance computational techniques.

Message from the Steering Chair It was my pleasure to welcome attendees to the 10th International Conference on High-Performance Computing and to Hyderabad, an emerging center of IT activities in India. We are indebted to Timothy Pinkston for his superb e?orts as program chair in organizing an excellent technical program. We received a record number of submissions this year. Over the past year, I discussed the meeting details with Timothy. I am grateful to him for his thoughtful inputs. Many volunteers helped to organize the meeting. In addition, I was glad to welcome Rajesh Gupta as Keynote Chair, Atul Negi as Student Scholarships Chair, and Sushil Prasad as Proceedings Chair. I look forward to their cont- butions for the continued success of the meeting series. Sushil Prasad did an excellent job in bringing out these proceedings. Kamal Karlapalem assisted us with local arrangements at IIIT, Hyderabad. Dheeraj Sanghi took on the r- ponsibility of focussed publicity for the meeting within India. Vijay Keshav of Intel India, though not listed as a volunteer, provided me with many pointers for bringing the India-based high-performance computing vendors to the meeting. I would like to thank M. Vidyasagar for agreeing to host the meeting in Hyderabad and for his assistance with the local arrangements. Continuing the tradition set at last year's meeting, several workshops were organized by volunteers. These workshops were coordinated by C.P. Ravikumar. Healsovolunteeredtoputtogethertheworkshopproceedings, andSushilPrasad assisted him in this.

The 5th International Symposium on High Performance Computing (ISHPC-V) was held in Odaiba, Tokyo, Japan, October 20-22, 2003. The symposium was thoughtfully planned, organized, and supported by the ISHPC Organizing C- mittee and its collaborating organizations. The ISHPC-V program included two keynote speeches, several invited talks, two panel discussions, and technical sessions covering theoretical and applied research topics in high-performance computing and representing both academia and industry. One of the regular sessions highlighted the research results of the ITBL project (IT-based research laboratory, http://www.itbl.riken.go.jp/). ITBL is a Japanese national project started in 2001 with the objective of re- izing a virtual joint research environment using information technology. ITBL aims to connect 100 supercomputers located in main Japanese scienti?c research laboratories via high-speed networks. A total of 58 technical contributions from 11 countries were submitted to ISHPC-V. Each paper received at least three peer reviews. After a thorough evaluation process, the program committee selected 14 regular (12-page) papers for presentation at the symposium. In addition, several other papers with fav- able reviews were recommended for a poster session presentation. They are also included in the proceedings as short (8-page) papers. Theprogramcommitteegaveadistinguishedpaperawardandabeststudent paper award to two of the regular papers. The distinguished paper award was given for "Code and Data Transformations for Improving Shared Cache P- formance on SMT Processors" by Dimitrios S. Nikolopoulos. The best student paper award was given for "Improving Memory Latency Aware Fetch Policies for SMT Processors" by Francisco J. Cazorla.

This book constitutes the thoroughly refereed post-proceedings of the 5th International Conference on High Performance Computing for Computational Science, VECPAR 2002, held in Porto, Portugal in June 2002. The 45 revised full papers presented together with 4 invited papers were carefully selected during two rounds of reviewing and improvement. The papers are organized in topical sections on fluids and structures, data mining, computing in chemistry and biology, problem solving environments, computational linear and non-linear algebra, cluster computing, imaging, and software tools and environments.

This book constitutes the refereed proceedings of the 9th International Conference on High Performance Computing, HiPC 2002, held in Bangalore, India in December 2002. The 57 revised full contributed papers and 9 invited papers presented together with various keynote abstracts were carefully reviewed and selected from 145 submissions. The papers are organized in topical sections on algorithms, architecture, systems software, networks, mobile computing and databases, applications, scientific computation, embedded systems, and biocomputing.

This book constitutes the refereed proceedings of the 4th International Symposium on High Performance Computing, ISHPC 2002, held in Kansai Science City, Japan, in May 2002 together with the two workshops WOMPEI 2002 and HPF/HiWEP 2002.The 51 revised papers presented were carefully reviewed and selected for inclusion in the proceedings. The book is organized in topical sections on networks, architectures, HPC systems, Earth Simulator, OpenMP-WOMPEI 2002, and HPF-HiWEP 2002.

This book constitutes the refereed proceedings of the 8th International Conference on High Performance Computing, HiPC 2001, held in Hyderabad, India, in December 2001.The 29 revised full papers presented together with 5 keynote papers and 3 invited papers were carefully reviewed and selected from 108 submissions. The papers are organized in topical sections on algorithms, applications, architecture, systems software, communications networks, and challenges in networking.

The International Symposium on Supercomputing - New Horizon of Computational Science was held on September 1-3, 1997 at the Science MuseuminTokyo,tocelebrate60-yearbirthdayofProfessorDaiichiroSug- imoto,who hasbeenleadingtheoreticalandnumericalastrophysicsfor 30 years. The conference coveredexceptionally wide range ofsubjects, to follow Sugimoto'saccomplishmentsinmanyfields.Onthefirstdaywehadthree talksonstellarevolutionandsixtalksonstellardynamics. Onthesecond day, six talks on special-purpose computingand four talks on large-scale computing in MolecularDynamicswere given. Onthethirdandthelast day,threetalks on dedicatedcomputerson LatticeQCDcalculationsand sixtalksonpresentandfutureofgeneral-purposeHPCsystemsweregiven. Inaddition,some30posterswerepresentedonvarioussubjectsincompu- tationalscience. Instellarevolution, D.Arnett (Univ. ofArizona) gaveanexcellenttalk on the recent development in three-dimensionalsimulation ofSupernova, inparticularonquantitativecomparisonbetweendifferenttechniquessuch asgrid-basedmethodsandSPH (SmoothedParticleHydrodynamics). Y. Kondo (NASA) discussedresentadvanceinthemodelingoftheevolution ofbinarystars,and1.Hachisu(Univ. ofTokyo)discussedRayleigh-Taylor instabilitiesinsupernovae(contributionnotincluded). Instellardynamics, P.Hut(lAS)gaveasuperbreviewonthelong-term evolution ofstellarsystem, J. Makino (Univ. ofTokyo) described briefly theresultsobtainedonGRAPE-4special-purposecomputerandthefollow- up project,GRAPE-6,whichisapprovedas ofJune 1997. GRAPE-6will be completed by year 2001 with the peak speed around 200 Tflops. R. Spurzem (Rechen-Inst.) and D. Heggie (Univ. of Edinburgh) talked on recentadvanceinthestudyofstarclusters,andE.Athanassoula(Marseille Observatory) describedthe work doneusingtheirGRAPE-3 systems. S. Ida (TokyoInst. ofTechnology) describedthe result ofthe simulationof theformationofMoon. Thefirst talkoftheseconddaywas given by F-H. Hsu oftheIBMT.J. Watson Research center, on "Deep Blue", the special-purpose computer for Chess,which, forthefirst timeinthehistory, wonthematchwiththe besthumanplayer,Mr. GaryKasparov(unfortunately,Hsu'scontribution isnot included in this volume). Then A. Bakker of Delft Inst. of Tech- nology looked back his 20 years ofdevelopingspecial-purpose computers formoleculardynamicsandsimulationofspinsystems. J.Arnoldgavean overviewoftheemergingnewfieldofreconfigurablecomputing,whichfalls inbetweentraditionalgeneral-purposecomputersandspecial-purposecom- puters. S.Okumura(NAO)describedthehistoryofultra-high-performance digital signalprocessors for radio astronomy. They havebuilt a machine with 20GaPS performance in early 80s, and keep improvingthe speed. M. Taiji (ISM) told on general aspects of GRAPE-type systems, and T. Narumi (Univ. of Tokyo) the 100-Tflops GRAPE-type machine for MD calculations,whichwillbefinished by 1999.

This book constitutes the refereed proceedings of the 7th International Conference on High Performance Computing, HiPC 2000, held in Bangalore, India in December 2000. The 46 revised papers presented together with five invited contributions were carefully reviewed and selected from a total of 127 submissions. The papers are organized in topical sections on system software, algorithms, high-performance middleware, applications, cluster computing, architecture, applied parallel processing, networks, wireless and mobile communication systems, and large scale data mining.