Downloads & Free Reading Options - Results

The House Armed Services Committee asked the GAO (General Accounting Office) to examine the HPCC (High Performance Computing and Communications) program in terms of: (1) the effectiveness of the program's management structure in setting goals and measuring progress, and (2) how extensively private industry has been involved in the planning and execution of this program. The HPCC program aims to accelerate the research and development of high performance computers and networks and promote the use of those resources in both the federal government and the private sector. The administration is now broadening the role of the HPCC program in developing new technology in support of the NII (National Information Infrastructure), and industry participation is crucial for the creation of new products and services for the NII. The GAO recommended that the HPCC program develop a detailed technical agenda as a framework for guiding the government's investment in HPCC research. The HPCC budgets are developed without formal guidelines, and a more standardized method for spending could broaden industry support for the program. Private sector participation could be promoted by inviting industry representatives to collaborate on the development of program plans. The Assistant to the President for Science and Technology (Science Advisor) concurred with the GAO's findings and also recommended that a private sector advisory board be established. (DGM)

The application of high end computing to astrophysical problems, mainly in the galactic environment, is under development since many years at the Dep. of Physics of Sapienza Univ. of Roma. The main scientific topic is the physics of self gravitating systems, whose specific subtopics are: i) celestial mechanics and interplanetary probe transfers in the solar system; ii) dynamics of globular clusters and of globular cluster systems in their parent galaxies; iii) nuclear clusters formation and evolution; iv) massive black hole formation and evolution; v) young star cluster early evolution. In this poster we describe the software and hardware computational resources available in our group and how we are developing both software and hardware to reach the scientific aims above itemized.

IRPF90 is a Fortran programming environment which helps the development of large Fortran codes. In Fortran programs, the programmer has to focus on the order of the instructions: before using a variable, the programmer has to be sure that it has already been computed in all possible situations. For large codes, it is common source of error. In IRPF90 most of the order of instructions is handled by the pre-processor, and an automatic mechanism guarantees that every entity is built before being used. This mechanism relies on the {needs/needed by} relations between the entities, which are built automatically. Codes written with IRPF90 execute often faster than Fortran programs, are faster to write and easier to maintain.

IRPF90 is a Fortran programming environment which helps the development of large Fortran codes. In Fortran programs, the programmer has to focus on the order of the instructions: before using a variable, the programmer has to be sure that it has already been computed in all possible situations. For large codes, it is common source of error. In IRPF90 most of the order of instructions is handled by the pre-processor, and an automatic mechanism guarantees that every entity is built before being used. This mechanism relies on the {needs/needed by} relations between the entities, which are built automatically. Codes written with IRPF90 execute often faster than Fortran programs, are faster to write and easier to maintain.

IRPF90 is a Fortran programming environment which helps the development of large Fortran codes. In Fortran programs, the programmer has to focus on the order of the instructions: before using a variable, the programmer has to be sure that it has already been computed in all possible situations. For large codes, it is common source of error. In IRPF90 most of the order of instructions is handled by the pre-processor, and an automatic mechanism guarantees that every entity is built before being used. This mechanism relies on the {needs/needed by} relations between the entities, which are built automatically. Codes written with IRPF90 execute often faster than Fortran programs, are faster to write and easier to maintain.

IRPF90 is a Fortran programming environment which helps the development of large Fortran codes. In Fortran programs, the programmer has to focus on the order of the instructions: before using a variable, the programmer has to be sure that it has already been computed in all possible situations. For large codes, it is common source of error. In IRPF90 most of the order of instructions is handled by the pre-processor, and an automatic mechanism guarantees that every entity is built before being used. This mechanism relies on the {needs/needed by} relations between the entities, which are built automatically. Codes written with IRPF90 execute often faster than Fortran programs, are faster to write and easier to maintain.

IRPF90 is a Fortran programming environment which helps the development of large Fortran codes. In Fortran programs, the programmer has to focus on the order of the instructions: before using a variable, the programmer has to be sure that it has already been computed in all possible situations. For large codes, it is common source of error. In IRPF90 most of the order of instructions is handled by the pre-processor, and an automatic mechanism guarantees that every entity is built before being used. This mechanism relies on the {needs/needed by} relations between the entities, which are built automatically. Codes written with IRPF90 execute often faster than Fortran programs, are faster to write and easier to maintain.

Todd Gamblin, a computer scientist at Lawrence Livermore National Laboratory, joined us to talk about Moore's Law, his work at Lawrence Livermore National Laboratory, the components of a micro-chip, and High Performance Computing.

The use and acceptance of new high-performance, parallel computing platforms will be impeded by the absence of an infrastructure capable of supporting orders-of-magnitude improvement in hierarchical storage and high-speed I/O (Input/Output). The distribution of these high-performance platforms and supporting infrastructures across a wide-area network further compounds this problem. We describe an architectural design and phased implementation plan for a distributed, Cooperative Storage Environment (CSE) to achieve the necessary performance, user transparency, site autonomy, communication, and security features needed to support the Accelerated Strategic Computing Initiative (ASCI). ASCI is a Department of Energy (DOE) program attempting to apply terascale platforms and Problem-Solving Environments (PSEs) toward real-world computational modeling and simulation problems. The ASCI mission must be carried out through a unified, multilaboratory effort, and will require highly secure, efficient access to vast amounts of data. The CSE provides a logically simple, geographically distributed, storage infrastructure of semi-autonomous cooperating sites to meet the strategic ASCI PSE goal of highperformance data storage and access at the user desktop.

The use and acceptance of new high-performance, parallel computing platforms will be impeded by the absence of an infrastructure capable of supporting orders-of-magnitude improvement in hierarchical storage and high-speed I/O (Input/Output). The distribution of these high-performance platforms and supporting infrastructures across a wide-area network further compounds this problem. We describe an architectural design and phased implementation plan for a distributed, Cooperative Storage Environment (CSE) to achieve the necessary performance, user transparency, site autonomy, communication, and security features needed to support the Accelerated Strategic Computing Initiative (ASCI). ASCI is a Department of Energy (DOE) program attempting to apply terascale platforms and Problem-Solving Environments (PSEs) toward real-world computational modeling and simulation problems. The ASCI mission must be carried out through a unified, multilaboratory effort, and will require highly secure, efficient access to vast amounts of data. The CSE provides a logically simple, geographically distributed, storage infrastructure of semi-autonomous cooperating sites to meet the strategic ASCI PSE goal of highperformance data storage and access at the user desktop.

Remote data access for data analysis in high performance computing is commonly done with specialized data access protocols and storage systems. These protocols are highly optimized for high throughput on very large datasets, multi-streams, high availability, low latency and efficient parallel I/O. The purpose of this paper is to describe how we have adapted a generic protocol, the Hyper Text Transport Protocol (HTTP) to make it a competitive alternative for high performance I/O and data analysis applications in a global computing grid: the Worldwide LHC Computing Grid. In this work, we first analyze the design differences between the HTTP protocol and the most common high performance I/O protocols, pointing out the main performance weaknesses of HTTP. Then, we describe in detail how we solved these issues. Our solutions have been implemented in a toolkit called davix, available through several recent Linux distributions. Finally, we describe the results of our benchmarks where we compare the performance of davix against a HPC specific protocol for a data analysis use case.

The computing systems used by LHC experiments has historically consisted of the federation of hundreds to thousands of distributed resources, ranging from small to mid-size resource. In spite of the impressive scale of the existing distributed computing solutions, the federation of small to mid-size resources will be insufficient to meet projected future demands. This paper is a case study of how the ATLAS experiment has embraced Titan -- a DOE leadership facility in conjunction with traditional distributed high-throughput computing to reach sustained production scales of approximately 51M core-hours a years. The three main contributions of this paper are: (i) a critical evaluation of design and operational considerations to support the sustained, scalable and production usage of Titan; (ii) a preliminary characterization of a next generation executor for PanDA to support new workloads and advanced execution modes; and (iii) early lessons for how current and future experimental and observational systems can be integrated with production supercomputers and other platforms in a general and extensible manner.

This paper presents a novel Edge Cloud collaborative computing framework designed to meet the low latency and high performance requirements of emerging IoT applications. As the demand for real time processing and efficient resource utilization continues to grow, traditional cloud centric or edge only architectures face critical limitations, such as high latency, limited computational power, and energy inefficiencies. The proposed framework dynamically allocates computational tasks between edge nodes and cloud servers based on factors such as latency sensitivity, computational complexity, and energy constraints. Utilizing machine learning algorithms for intelligent task scheduling and predictive workload management, the system achieves a balanced distribution of processing loads, enhancing responsiveness and scalability. Experimental evaluation through simulation and real world prototyping demonstrates significant improvements in latency reduction, throughput, task completion time, and energy efficiency compared to baseline models. The framework also incorporates secure communication protocols and modular architecture, ensuring adaptability, data privacy, and compatibility with heterogeneous IoT environments. These findings highlight the potential of Edge Cloud collaboration as a practical and scalable solution for enabling next generation IoT services with stringent performance and reliability demands. Shiva Kiran Lingishetty | Yuvaraj Madheswaran | Vineet Baniya "Edge-Cloud Collaboration: A Framework for Low-Latency and High-Performance Computing in IoT Applications" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-9 | Issue-3 , June 2025, URL: https://www.ijtsrd.com/papers/ijtsrd79991.pdf Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/79991/edgecloud-collaboration-a-framework-for-lowlatency-and-highperformance-computing-in-iot-applications/shiva-kiran-lingishetty

Trimester 1 - 2017/2018

This hearing explores how the High Performance Computing and Communications Program (HPCC) relates to the technology needs of industry. Testimony and prepared statements from the following witnesses on future effects of computing and networking technologies on their companies are included: (1) F. Brett Berlin, president, Brett Berlin Associates, accompanied by David R. Audley, managing director, Prudential Securities; (2) Peter R. Bridenbaugh, executive vice president, science, engineering, environment, safety and health, Aluminum Co. of America; (3) Paul E. Rubbert, unit chief, aerodynamics research, Boeing Commercial Airplane Group; (4) W. Donald Frazer, vice president, Massively Parallel Products, Oracle Corp; and (5) Marvin G. Bloomquist, manager, information technology, Mobil Exploration and Producing Technical Center. (JLB)

Knowing the future weather on the battlefield with high certainty can result in a higher advantage over the adversary. To create this advantage for the United States, the U.S. Navy utilizes the Coupled Ocean/Atmosphere Mesoscale Prediction System (COAMPS) to create high spatial resolution, regional, numerical weather prediction (NWP) forecasts. To compute a forecast, COAMPS runs on high performance computing (HPC) systems. These HPC systems are large, dedicated supercomputers with little ability to scale or move. This makes these systems vulnerable to outages without a costly, equally powerful secondary system. Recent advancements in cloud computing and virtualization technologies provide a method for high mobility and scalability without sacrificing performance. This research used standard benchmarks in order to quantitatively compare a virtual machine (VM) to a native HPC cluster. The benchmark tests showed that the VM was feasible platform for executing HPC applications. Then we ran the COAMPS NWP on a VM within a cloud infrastructure to prove the ability to run a HPC application in a virtualized environment. The VM COAMPS model run performed better than the native HPC machine model run. These results show that VM and cloud computing technologies can be used to run HPC applications for the Department of Defense

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS-national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91 percent was achieved, which is a 6 percent improvement in unmixing based classification relative to per-pixel-based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS-national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91 percent was achieved, which is a 6 percent improvement in unmixing based classification relative to per-pixel-based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS-national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91 percent was achieved, which is a 6 percent improvement in unmixing based classification relative to per-pixel-based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Includes index

Includes index

Includes bibliographical references

This report, submitted by Representative Ford, of Michigan, from the House Committee on Education and Labor, is intended to accompany H.R. 656. The bill provides for a focused and coordinated federal research program to ensure continued U.S. leadership in high-performance computing through the establishment of a national network of high-performance computers and to accelerate research in the field and broaden the application of high-performance computing throughout all spheres of society. The bill also requires the Director of the Office of Science and Technology Policy to coordinate among the various federal agencies a national network of high-speed computers, which would be known as the National Research and Education Network (NREN). In addition, the bill authorizes funding for several federal agencies to carry out high-speed computer research and application. It is noted that, during consideration of the bill by the Science, Space, and Technology Committee, a number of provisions were included that will permit the participation of libraries and education institutions at all levels in NREN. The Committee on Education and Labor received the bill as a sequential referral, and adopted three amendments to the bill to enhance the ability of educators and librarians to participate in the benefits which will be provided through NREN. This Committee reports favorably on the bill as amended and recommends that it be passed. Cost estimates of the Congressional Budget Office are included in the report. (DB)

The problem of turbulent jet sprays of n-dodecane injected into a quiescent nitrogen gas chamber was investigated as a test case for the incorporation of a multiphysics Large-Eddy Simulation solver known as LESLIE into the US Army Research Laboratorys High Performance Computing system. Preliminary simulations were performed on the Excalibur supercomputer to test the capability of the solver to simulate subcritical turbulent jet sprays. The solver was chosen for its ability to make use of alternative models that are capable of modeling multicomponent fluids such as n-dodecane. The long-term goal of this research is to incorporate these models into future simulations of turbulent jet sprays and develop a predictive theory for comparison to measurements in the laboratory of turbulent diesel sprays.

This work outlines a unified multi-threaded, multi-scale High Performance Computing (HPC) approach for the direct numerical simulation of Fluid-Solid Interaction(FSI) problems. The simulation algorithm relies on the extended Smoothed Particle Hydrodynamics (XSPH) method, which approaches the fluid flow in a Lagrangian framework consistent with the Lagrangian tracking of the solid phase. A general 3D rigid body dynamics and an Absolute Nodal Coordinate Formulation(ANCF) are implemented to model rigid and flexible multibody dynamics. The two way coupling of the fluid and solid phases is supported through use of Boundary Condition Enforcing (BCE) markers that capture the fluid-solid coupling forces by enforcing a no-slip boundary condition. The solid-solid short range interaction, which has a crucial impact on the small-scale behavior of fluid-solid mixtures, is resolved via a lubrication force model. The collective system states are integrated in time using an explicit, multi-rate scheme. To alleviate the heavy computational load, the overall algorithm leverages parallel computing on Graphics Processing Unit (GPU) cards. Performance and scaling analysis are provided for simulations scenarios involving one or multiple phases with up to tens of thousands of solid objects. The software implementation of the approach, called Chrono::Fluid, is part of the Chrono project and available as an open-source software.

This work outlines a unified multi-threaded, multi-scale High Performance Computing (HPC) approach for the direct numerical simulation of Fluid-Solid Interaction(FSI) problems. The simulation algorithm relies on the extended Smoothed Particle Hydrodynamics (XSPH) method, which approaches the fluid flow in a Lagrangian framework consistent with the Lagrangian tracking of the solid phase. A general 3D rigid body dynamics and an Absolute Nodal Coordinate Formulation(ANCF) are implemented to model rigid and flexible multibody dynamics. The two way coupling of the fluid and solid phases is supported through use of Boundary Condition Enforcing (BCE) markers that capture the fluid-solid coupling forces by enforcing a no-slip boundary condition. The solid-solid short range interaction, which has a crucial impact on the small-scale behavior of fluid-solid mixtures, is resolved via a lubrication force model. The collective system states are integrated in time using an explicit, multi-rate scheme. To alleviate the heavy computational load, the overall algorithm leverages parallel computing on Graphics Processing Unit (GPU) cards. Performance and scaling analysis are provided for simulations scenarios involving one or multiple phases with up to tens of thousands of solid objects. The software implementation of the approach, called Chrono::Fluid, is part of the Chrono project and available as an open-source software.

This report, profusely illustrated with color photographs and other graphics, elaborates on the Department of Energy (DOE) research program in High Performance Computing and Communications (HPCC). The DOE is one of seven agency programs within the Federal Research and Development Program working on HPCC. The DOE HPCC program emphasizes research in four areas: (1) HPCC Systems--evaluate advanced architectures for large-scale scientific and engineering applications; (2) Advanced Software Technology and Algorithms--research computational methods, algorithms, and tools; develop large-scale data handling techniques; establish HPCC research centers; and exploit extensive teaming among scientists and engineers, applied mathematicians, and computer scientists; (3) National Research and Education Network--research and develop high-speed computer networking technologies through a multiagency cooperative effort; and (4) Basic Research and Human Resources--encourage research partnerships between national laboratories, industry, and universities; support computational mathematics and computer science research; establish research and educational programs in computational science; and enhance K through 12 education. The stated goals of the DOE HPCC program are to support the economic competitiveness and productivity of the United States, accelerate the application of HPCC technology to the solution of scientific and engineering problems, and enhance U.S leadership in research, development, and deployment of HPCC technologies. A number of examples of DOE HPCC operations are provided, including the MatVu matrix visualization computer software package; Global Ocean Model; Molecular Dynamics Simulations; Pion Propagator; Three-Dimensional Tokamak Modeling; MediaView, a system for multimedia communication; and the CASA testbed, a wide-area, very high speed communication network that enables a number of collaborating agencies to work with geographically dispersed supercomputing resources. (DB)

This report addresses an opportunity to accelerate progress in virtually every branch of science and engineering concurrently, while also boosting the American economy as business firms also learn to exploit these new capabilities. The successful rapid advancement in both science and technology creates its own challenges, four of which are outlined here for the National Science Board. Four sets of interdependent recommendations are made in response to the challenges. The first implements a balanced pyramid of computing environments. Each element in the pyramid supports the others; whatever resources are applied to the whole, the balance in the pyramid should be sustained. The second set addresses the essential research investments and other steps to remove the obstacles to realizing the technologies in the pyramid and the barriers to the effective use of these environments. The third set addresses the institutional structure for delivery of the HPC capabilities, and consists itself of a pyramid. At the base of the institutional pyramid is the diverse array of investigators in their universities and other settings, who use all the facilities at all levels of the pyramid, followed by departments and research groups devoted to specific areas of computer science and engineering, and the National Science Foundation (NSF) high performance computing (HPC) Centers. At the apex is the national teraflop-class society, which is recommended as a multi-agency facility pushing the frontiers of high performance into the next decade. A final recommendation addresses the NSF role at the national level and its relationship with the states in HPC. Concepts are illustrated with two figures and two tables. Appendices include: a list of the membership of the Blue Ribbon Panel on High Performance Computing; information on the history and origin of this study on the NSF and HPC; a discussion of technology trends and barriers to further progress; four figures illustrating supercomputer data; and a review and prospectus of computational and computer science and engineering with personal statements by panel members. (MAS)

This report addresses an opportunity to accelerate progress in virtually every branch of science and engineering concurrently, while also boosting the American economy as business firms also learn to exploit these new capabilities. The successful rapid advancement in both science and technology creates its own challenges, four of which are outlined here for the National Science Board. Four sets of interdependent recommendations are made in response to the challenges. The first implements a balanced pyramid of computing environments. Each element in the pyramid supports the others; whatever resources are applied to the whole, the balance in the pyramid should be sustained. The second set addresses the essential research investments and other steps to remove the obstacles to realizing the technologies in the pyramid and the barriers to the effective use of these environments. The third set addresses the institutional structure for delivery of the HPC capabilities, and consists itself of a pyramid. At the base of the institutional pyramid is the diverse array of investigators in their universities and other settings, who use all the facilities at all levels of the pyramid, followed by departments and research groups devoted to specific areas of computer science and engineering, and the National Science Foundation (NSF) high performance computing (HPC) Centers. At the apex is the national teraflop-class society, which is recommended as a multi-agency facility pushing the frontiers of high performance into the next decade. A final recommendation addresses the NSF role at the national level and its relationship with the states in HPC. Concepts are illustrated with two figures and two tables. Appendices include: a list of the membership of the Blue Ribbon Panel on High Performance Computing; information on the history and origin of this study on the NSF and HPC; a discussion of technology trends and barriers to further progress; four figures illustrating supercomputer data; and a review and prospectus of computational and computer science and engineering with personal statements by panel members. (MAS)

Reliability Based Design Optimization (RBDO) is a process of optimizing under uncertainty to obtain a reliable (in the probabilistic sense) optimum for a design, which is robust under the expected variability inherent in realizing the design. In this case, we are optimizing the design of a ground vehicle to reduce weight while maintaining or improving durability. Like any optimization, it is best done on a system level. When optimizing under uncertainty, considering a large number of sources of variability makes the optimization method more robust. The objective is to improve the RBDO process, expanding from component optimization to system optimization of a ground vehicle, consider more sources of uncertainty and use a multi-physics and multi-scale approach. This requires greater computing power than has previously been applied to such optimizations.

Over the last decade, the performance capabilities of FPGAs have increased exponentially. Leading vendors such as Xilinx and Altera have improved the functionality of their reconfigurable devices through the inclusion of memory, processors, multi-gigabit transceivers, and multipliers to the basic FPGA architecture. The result is a flexible, high performance processing device able to perform low latency, parallel processing tasks with low power consumption. In order to exploit the obvious benefits of FPGA technology in embedded systems, Nallatech has developed a range of FPGA-centric COTS products based upon the company's modular DIME-II architecture capable of TeraOPS performance. Customers using Nallatech products such as the BenNUEY-PC104+ are able to harness the full capability of advanced Virtex-II and Virtex-II Pro Xilinx FPGAs. With a range of motherboard form factors including PC104plus, VME, PCI and cPCI and a catalogue of plug and play DIME-II modules, embedded system developers can quickly build a flexible, high performance processing system tailored to the requirements of a specific application.

This paper describes a novel QR decomposition algorithm that utilizes both Givens rotations and Householder reflections to give optimal performance on high performance computing architectures. Computing the matrix factorization A = QR is a mathematical step frequently encountered in many signal processing applications including adaptive nulling. Efficient algorithms for computing the QR factorization are vital to satisfying strict latency and throughput constraints in real-time implementations of these signal processing algorithms. By effectively combining the use of Givens rotations and Householder reflections on a parallel computing platform it is possible to efficiently map the computational algorithm to the available computational hardware to best make use of the memory hierarchy and to optimize performance. Furthermore by introducing adjustable software parameters that control load partitioning among the processors cache use and the number of computations done in serial fashion on one processor versus the calculations done concurrently on several processors it is possible for the user to tune the algorithm to run on different machines, without rewriting any code and still maintaining optimum performance. Results given in this abstract show that properly tuning the Hybrid QR algorithm on the SGI O3000 provided better performance than the available SCALAPACK library routine PSGEQRF for computing the QR decomposition.

A key goal of this effort is to demonstrate and develop heterogeneous and distributed computing technologies that are applicable to DoD and scientific communities, while maintaining and benefiting from industry standards that could be applied to high performance computing. High performance computing systems based on clusters of compute nodes, connected via a high speed interconnect, are becoming popular for large-scale parallel applications, forming a highly scalable infrastructure. Most large-scale scientific applications are highly I/O-centric and have a tremendous need for a similarly scalable file I/O subsystem. DAFS is a well-defined highperformance protocol for file access across a network as well as set of APIs, uDAFS, for user level OS-bypassing application programming, designed to take advantage of RDMA-based transports, such as Virtual Interface Architecture (VIA), InfiniBand Architecture1, and iWARP.

The Applied Computational Electromagnetics Society Journal is devoted to the exchange of information in computational electromagnetics, to the advancement of the state of the art, and to the promotion of related technical activities. This issue concerns the following topics: (1) integral equation methods, (2) differential equation methods, and (3) fast algorithms.

Molecular-simulation methods in conjunction with X-ray crystallography and interactive computer graphics have been employed for determining key structural and functional features of ligand-bound ricin A- chain. Particular detail has been given to analyzing the structural interactions and energetics governing the binding of two nucleotide ligands, formycin 5'- monophosphate (FMP) and adenyl-3',5'-guanosine (ApG), thought to mimic certain elements of the rRNA substrate. The studies undertaken showed the average simulation structures of the ligand-bound enzyme to be in good accord with the observed X-ray crystal structures in reproducing an overall binding mode. Complementary studies have been carried out aimed at exploring several structural motifs of FMP which would have a greater binding affinity for the active site and perhaps function as template for the development of transition- state analogs for ricin. Building on the binding motif of the adenine ring from the average simulation structures, several substituents have been appended to the base with removal of the ribose and phosphate group leading to the de novo design of ligands for ricin. Ricin, Molecular modeling, Protein structure-based design of enzyme inhibitors, BD, RAD IV.

CONTENTS: Three-Dimensional Target Visualization from Wide-Angle IFSAR Data By Randolph L. Moses, Paul Adams, Randall Hand, and Tommy Biddlecome; ERDC MSRC Installs Most Powerful Supercomputer in DoD By Jay Cliburn; solutionHPC; Technical Overview of ezHPC Architecture By Weston Monceaux, Keith Rappold, and Patti Duett; ezVIZ - An Open-Source, Cross-Platform Visualization Tool By Randall Hand and Paul Adams; About PET By Dr. Jim Pennington; Storage Monitoring and Forecasting at the ERDC MSRC By Teresa Moncrief and David Sanders; DoD Supercomputing Center at ERDC to be Featured Worldwide Once Again By Rose J. Dykes; Helping Shape the Future; ERDC MSRC Makes 11 Presentations at UGC 2005 and Brings Home Two Hero Awards By Rose J. Dykes

To impact the decision making for military ground vehicles, we are using High Performance Computing (HPC) to speed up the time for analyzing the reliability of a design in modeling and simulation. We use parallelization to get accurate results in days rather than months. We can obtain accurate reliability prediction with modeling and simulation, using uncertainties and multiple physics-of-failure, but by utilizing parallel computing we get results in much less time than conventional analysis techniques.

rfn

This report experimentally assesses the effect of the underlying network in a cluster-based computing environment. The assessment is quantified by application-level benchmarking, process-level communication, and network file input/output. Two testbeds were considered, one small cluster of Sun workstations and another large cluster composed of 32 high-end IBM RS/6000 platforms. The clusters had Ethernet, fiber distributed data interface (FDDI), Fibre Channel, and asynchronous transfer mode (ATM) network interface cards installed, providing the same processors and operating system for the entire suite of experiments. The primary goal of this report is to assess the suitability of an ATM-based, local-area network to support interprocess communication and remote file input/output systems for distributed computing.

This study is the first attempt to understand the current gender demographics of the HPC community, and identify potential reasons and ways to tackle the gender imbalance. By listening to the people who constitute the community, the study offers a guideline on what the HPC community should focus on in order to become more attractive, accessible and useful to everyone. Please see our speaker release agreement for details: https://ep2019.europython.eu/events/speaker-release-agreement/

This study is the first attempt to understand the current gender demographics of the HPC community, and identify potential reasons and ways to tackle the gender imbalance. By listening to the people who constitute the community, the study offers a guideline on what the HPC community should focus on in order to become more attractive, accessible and useful to everyone. Please see our speaker release agreement for details: https://ep2019.europython.eu/events/speaker-release-agreement/

High Performance Computing market

Power-spectrum analysis is an important tool providing critical information about a signal. The range of applications includes communication-systems to DNA-sequencing. If there is interference present on a transmitted signal, it could be due to a natural cause or superimposed forcefully. In the latter case, its early detection and analysis becomes important. In such situations having a small observation window, a quick look at power-spectrum can reveal a great deal of information, including frequency and source of interference. In this paper, we present our design of a FPGA based reconfigurable platform for high performance power-spectrum analysis. This allows for the real-time data-acquisition and processing of samples of the incoming signal in a small time frame. The processing consists of computation of power, its average and peak, over a set of input values. This platform sustains simultaneous data streams on each of the four input channels.

We present a systematic, algebraically based, design methodology for efficient implementation of computer programs optimized over multiple levels of the processor/memory and network hierarchy. Using a common formalism to describe the problem and the partitioning of data over processors and memory levels allows one to mathematically prove the efficiency and correctness of a given algorithm as measured in terms of a set of metrics (such as processor/network speeds, etc.). The approach allows the average programmer to achieve high-level optimizations similar to those used by compiler writers (e.g. the notion of "tiling"). The approach presented in this monograph makes use of A Mathematics of Arrays (MoA, Mullin 1988) and an indexing calculus (i.e. the psi-calculus) to enable the programmer to develop algorithms using high-level compiler-like optimizations through the ability to algebraically compose and reduce sequences of array operations. Extensive discussion and benchmark results are presented for the Fast Fourier Transform and other important algorithms.

The Embedded High Performance Scalable Computing Systems (EHPSCS) program is a cooperative agreement between Sanders, A Lockheed Martin Company and DARPA that ran for three years, from Apr 1995 - Apr 1998. The focus of the EHPSCS research program was on the development of a highly integrated, scalable multiprocessing architecture based on leading COTS technologies for environmentally constrained applications. The program developed an 11 GFLOPS embedded processor hardware/software testbed and software development tools to facilitate technology transfer, an advanced packaging insertion approach, and a second generation microarchitecture - the ReConfigurable Transport Engine.

The 1984/85 accomplishments of the research project High Performance Parallel Computing included bringing the prototype of the Texas Reconfigurable Array Computer (TRAC) to a configuration and to a state of stability where it could support execution of simple assembly language programs, initial development of a unified model of parallel computation which is a basis for a programming environment uniting process and data flow models of parallel computation, bringing to operational status on an alternative host one of the two parallel programming languages (the Computation Structures Language, CSL) originally intended for use on TRAC, exploration of the expressive capabilities of this programming language, initiation of development of a graphical programming language based on the unified model of parallel computation mentioned preceding, major progress on a graphically interfaced Petri Net-based performance modeling system for parallel computations and development of algorithms for scheduling of circuits to realize configurations in configurable banyan network based computer architectures.

The 1984/85 accomplishments of the research project High Performance Parallel Computing included bringing the prototype of the Texas Reconfigurable Array Computer (TRAC) to a configuration and to a state of stability where it could support execution of simple assembly language programs, initial development of a unified model of parallel computation which is a basis for a programming environment uniting process and data flow models of parallel computation, bringing to operational status on an alternative host one of the two parallel programming languages (the Computation Structures Language, CSL) originally intended for use on TRAC, exploration of the expressive capabilities of this programming language, initiation of development of a graphical programming language based on the unified model of parallel computation mentioned preceding, major progress on a graphically interfaced Petri Net-based performance modeling system for parallel computations and development of algorithms for scheduling of circuits to realize configurations in configurable banyan network based computer architectures.

The ability to visually interact with and guide a running simulation can greatly enhance understanding of both the nature of a numerical model and the characteristics of the underlying physical process. Until recently, interaction with large-scale simulations was inhibited not only by computational limitations, but by network and graphics capabilities as well. However, the increasing power of large high performance computing (HPC) systems, coupled with the advent of new network hardware and innovative techniques for displaying large data sets, has eliminated many of the barriers. It is now possible to link large computational resources with powerful remote graphics workstations to create fully interactive, distributed applications. This report discuses the development of a distributed, interactive modeling system capable of providing responsive visual feedback to user input. The system is built around a discrete element soil model being used to simulate the behavior of soil masses under large deformations. During the process of designing this system to be interactively responsive to the user for systems of several hundred thousand particles, a range of technical problems were encountered, including the computational burden of the discrete element method (DEM), real-time visualization of large particle masses, and communication of data over large distances between heterogeneous resources using a variety of networks. This report highlights bow each of those obstacles was addressed and discusses the effectiveness of the final system.

High performance computing (HPC) has historically played a major role in the ability of the United States to develop and deploy superior weapons, warfighting capabilities, and mission support systems. Under the auspices of the Director, Defense Research and Engineering (DDR&E), the Department of Defense (DoD) High Performance Computing Modernization Program (HPCMP) is the focused modernization effort within the DoD to acquire, manage, and sustain modern HPC resources in support of defense science and technology, and developmental test and evaluation. The HPCMP is rapidly evolving past its initial program development and procurement start up phase and is increasing focus on application of HPC technology and resources to priority defense requirements. This plan describes some of the accomplishments achieved by the program in Fiscal Year (FY) 1997 and outlines the major strategies and milestones we expect to achieve over the next two years. The overriding goal of the program is to exploit HPC technology for military advantage across battlespace. The strategy to achieve this goal is to acquire and sustain world class high performance computing and network capabilities for use by defense scientists and engineers.

High Performance Computing (HPC) is an enabling technology for a large class of Army needs including weapon system design, simulation and modeling, intelligence, automation, advanced manufacturing, and training. Recognizing this, in 1989 Army established the Army HPC Research Center. The Center consists of four integrated activities: interdisciplinary research into various aspects of HPC including novel solution techniques, advanced algorithms, applications, and graphics and visualization (GV); evaluation of advanced computing systems and implementation of an advanced HPC environment; infrastructure support and technology transfer to Army and other DOD activities; and, an aggressive outreach program through participation of Historically Black Colleges and Universities (HBCU) and Minority Institutions. The prime contractor for the Center is the University of Minnesota; its HBCU partners are Clark Atlanta, Florida A&M, Howard, and Jackson State Universities; and its industrial partner, the Minnesota Supercomputer Center, Inc. (MSCI), maintains and operates the supercomputing resources of the Army HPC Research Center. (KAR) P. 2