Downloads & Free Reading Options - Results

Motivated by the computational demands of our research and budgetary constraints which are common to many research institutions, we built a ``poor man's supercomputer'', a cluster of PC nodes which together can perform parallel calculations at a fraction of the price of a commercial supercomputer. We describe the construction, cost, and performance of our cluster.

Motivated by the computational demands of our research and budgetary constraints which are common to many research institutions, we built a ``poor man's supercomputer'', a cluster of PC nodes which together can perform parallel calculations at a fraction of the price of a commercial supercomputer. We describe the construction, cost, and performance of our cluster.

Motivated by the computational demands of our research and budgetary constraints which are common to many research institutions, we built a ``poor man's supercomputer'', a cluster of PC nodes which together can perform parallel calculations at a fraction of the price of a commercial supercomputer. We describe the construction, cost, and performance of our cluster.

Aeroshark computing cluster

Using workstation clusters for distributed computing has become popular with the proliferation of inexpensive, powerful workstations. Workstation clusters offer both a cost effective alternative to batch processing and an easy entry into parallel computing. However, a number of workstations on a network does not constitute a cluster. Cluster management software is necessary to harness the collective computing power. A variety of cluster management and queuing systems are compared: Distributed Queueing Systems (DQS), Condor, Load Leveler, Load Balancer, Load Sharing Facility (LSF - formerly Utopia), Distributed Job Manager (DJM), Computing in Distributed Networked Environments (CODINE), and NQS/Exec. The systems differ in their design philosophy and implementation. Based on published reports on the different systems and conversations with the system's developers and vendors, a comparison of the systems are made on the integral issues of clustered computing.

We establish bounds to the necessary resource consumption when building up cluster states for one-way computing using probabilistic gates. Emphasis is put on state preparation with linear optical gates, as the probabilistic character is unavoidable here. We identify rigorous general bounds to the necessary consumption of initially available maximally entangled pairs when building up one-dimensional cluster states with individually acting linear optical quantum gates, entangled pairs and vacuum modes. As the known linear optics gates have a limited maximum success probability, as we show, this amounts to finding the optimal classical strategy of fusing pieces of linear cluster states. A formal notion of classical configurations and strategies is introduced for probabilistic non-faulty gates. We study the asymptotic performance of strategies that can be simply described, and prove ultimate bounds to the performance of the globally optimal strategy. The arguments employ methods of random walks and convex optimization. This optimal strategy is also the one that requires the shortest storage time, and necessitates the fewest invocations of probabilistic gates. For two-dimensional cluster states, we find, for any elementary success probability, an essentially deterministic preparation of a cluster state with quadratic, hence optimal, asymptotic scaling in the use of entangled pairs. We also identify a percolation effect in state preparation, in that from a threshold probability on, almost all preparations will be either successful or fail. We outline the implications on linear optical architectures and fault-tolerant computations.

Computer hardware costs are the limiting factor in producing highly accurate radiation dose calculations on convenient time scales. Because of this, large-scale, full Monte Carlo simulations and other resource intensive algorithms are often considered infeasible for clinical settings. The emerging cloud computing paradigm promises to fundamentally alter the economics of such calculations by providing relatively cheap, on-demand, pay-as-you-go computing resources over the Internet. We believe that cloud computing will usher in a new era, in which very large scale calculations will be routinely performed by clinics and researchers using cloud-based resources. In this research, several proof-of-concept radiation therapy calculations were successfully performed on a cloud-based virtual Monte Carlo cluster. Performance evaluations were made of a distributed processing framework developed specifically for this project. The expected 1/n performance was observed with some caveats. The economics of cloud-based virtual computing clusters versus traditional in-house hardware is also discussed. For most situations, cloud computing can provide a substantial cost savings for distributed calculations.

Recent advances in low-end processor and network technology have made it possible to build a "supercomputer" out of commodity components. We develop simple models of the NAS Parallel Benchmarks version 2 (NPB 2) to explore the cost/performance trade-offs involved in building a balanced parallel computer supporting a scientific workload. We develop closed form expressions detailing the number and size of messages sent by each benchmark. Coupling these with measured single processor performance, network latency, and network bandwidth, our models predict benchmark performance to within 30%. A comparison based on total system cost reveals that current commodity technology (200 MHz Pentium Pros with 100baseT Ethernet) is well balanced for the NPBs up to a total system cost of around $1,000,000.

We discuss the potential and limitations of Gaussian cluster states for measurement-based quantum computing. Using a framework of Gaussian projected entangled pair states (GPEPS), we show that no matter what Gaussian local measurements are performed on systems distributed on a general graph, transport and processing of quantum information is not possible beyond a certain influence region, except for exponentially suppressed corrections. We also demonstrate that even under arbitrary non-Gaussian local measurements, slabs of Gaussian cluster states of a finite width cannot carry logical quantum information, even if sophisticated encodings of qubits in continuous-variable (CV) systems are allowed for. This is proven by suitably contracting tensor networks representing infinite-dimensional quantum systems. The result can be seen as sharpening the requirements for quantum error correction and fault tolerance for Gaussian cluster states, and points towards the necessity of non-Gaussian resource states for measurement-based quantum computing. The results can equally be viewed as referring to Gaussian quantum repeater networks.

We discuss the potential and limitations of Gaussian cluster states for measurement-based quantum computing. Using a framework of Gaussian projected entangled pair states (GPEPS), we show that no matter what Gaussian local measurements are performed on systems distributed on a general graph, transport and processing of quantum information is not possible beyond a certain influence region, except for exponentially suppressed corrections. We also demonstrate that even under arbitrary non-Gaussian local measurements, slabs of Gaussian cluster states of a finite width cannot carry logical quantum information, even if sophisticated encodings of qubits in continuous-variable (CV) systems are allowed for. This is proven by suitably contracting tensor networks representing infinite-dimensional quantum systems. The result can be seen as sharpening the requirements for quantum error correction and fault tolerance for Gaussian cluster states, and points towards the necessity of non-Gaussian resource states for measurement-based quantum computing. The results can equally be viewed as referring to Gaussian quantum repeater networks.

We discuss the potential and limitations of Gaussian cluster states for measurement-based quantum computing. Using a framework of Gaussian projected entangled pair states (GPEPS), we show that no matter what Gaussian local measurements are performed on systems distributed on a general graph, transport and processing of quantum information is not possible beyond a certain influence region, except for exponentially suppressed corrections. We also demonstrate that even under arbitrary non-Gaussian local measurements, slabs of Gaussian cluster states of a finite width cannot carry logical quantum information, even if sophisticated encodings of qubits in continuous-variable (CV) systems are allowed for. This is proven by suitably contracting tensor networks representing infinite-dimensional quantum systems. The result can be seen as sharpening the requirements for quantum error correction and fault tolerance for Gaussian cluster states, and points towards the necessity of non-Gaussian resource states for measurement-based quantum computing. The results can equally be viewed as referring to Gaussian quantum repeater networks.

We present sample CUDA programs for the GPU computing of the Swendsen-Wang multi-cluster spin flip algorithm. We deal with the classical spin models; the Ising model, the $q$-state Potts model, and the classical XY model. As for the lattice, both the 2D (square) lattice and the 3D (simple cubic) lattice are treated. We already reported the idea of the GPU implementation for 2D models [Comput. Phys. Commun. 183 (2012) 1155-1161]. We here explain the details of sample programs, and discuss the performance of the present GPU implementation for the 3D Ising and XY models. We also show the calculated results of the moment ratio for these models, and discuss phase transitions.

We report an experimental realization of one-way quantum computing on a two-photon four-qubit cluster state. This is accomplished by developing a two-photon cluster state source entangled both in polarization and spatial modes. With this special source, we implemented a highly efficient Grover's search algorithm and high-fidelity two qubits quantum gates. Our experiment demonstrates that such cluster states could serve as an ideal source and a building block for rapid and precise optical quantum computation.

This thesis focused on creating an object-oriented software architecture around which tools can be created to increase the usability of stochastic simulations such as IWARS and Pythagoras on high performance computing clusters. The objective of the architecture was to enable the user to design and execute simulation experiments using a platformindependent client and server to create a common interface for various simulations. The interface input is used to select the experimental factors of interest to the research analyst and then to create the scenario files for each simulation run with minimal human intervention. To develop the architecture the current state of the art was explored, a proposed process flow was developed. This process flow was then vetted by operations researchers from several organizations. A prototype application was developed based on the software architecture. The prototype revealed great benefit in this type of tool.

We have updated the Atmospheric Boundary Layer Environment (ABLE) model to use multicore/multinode parallelization via the Message Passing Interface (MPI). The model source code has been rewritten to use the Battlefield Environment Division Modeling Framework (BMF), an object-oriented framework developed to facilitate implementation of new technologies and algorithms. BMF is documented in this report.

Given the recent progress in the evolution of high-performance computing (HPC) technologies, the research in computational intelligence has entered a new era. In this paper, we present an HPC-based context-aware intelligent text recognition system (ITRS) that serves as the physical layer of machine reading. A parallel computing architecture is adopted that incorporates the HPC technologies with advances in neuromorphic computing models. The algorithm learns from what has been read and, based on the obtained knowledge, it forms anticipations of the word and sentence level context. The information processing flow of the ITRS imitates the function of the neocortex system. It incorporates large number of simple pattern detection modules with advanced information association layer to achieve perception and recognition. Such architecture provides robust performance to images with large noise. The implemented ITRS software is able to process about 16 to 20 scanned pages per second on the 500 trillion floating point operations per second (TFLOPS) Air Force Research Laboratory (AFRL)/Information Directorate (RI) Condor HPC after performance optimization.

The quantum computing scheme described in Phys. Rev. Lett. 98, 190504 (2007), when viewed as a cluster state computation, features a 3-D cluster state, novel adjustable strength error correction capable of correcting general errors through the correction of Z errors only, a threshold error rate approaching 1% and low overhead arbitrarily long-range logical gates. In this work, we review the scheme in detail framing discussion solely in terms of the required 3-D cluster state and its stabilizers.

Topological quantum computing is a way of allowing precise quantum computations to run on noisy and imperfect hardware. One implementation uses surface codes created by forming defects in a highly-entangled cluster state. Such a method of computing is a leading candidate for large-scale quantum computing. However, there has been a lack of sufficiently powerful high-level languages to describe computing in this form without resorting to single-qubit operations, which quickly become prohibitively complex as the system size increases. In this paper we apply the category-theoretic work of Abramsky and Coecke to the topological cluster-state model of quantum computing to give a high-level graphical language that enables direct translation between quantum processes and physical patterns of measurement in a computer - a "compiler language". We give the equivalence between the graphical and topological information flows, and show the applicable rewrite algebra for this computing model. We show that this gives us a native graphical language for the design and analysis of topological quantum algorithms, and finish by discussing the possibilities for automating this process on a large scale.

Different departments of a large organization often run dedicated cluster systems for different computing loads, like HPC (high performance computing) jobs or Web service applications. In this paper, we have designed and implemented a cloud management system software Phoenix Cloud to consolidate heterogeneous workloads from different departments affiliated to the same organization on the shared cluster system. We have also proposed cooperative resource provisioning and management policies for a large organization and its affiliated departments, running HPC jobs and Web service applications, to share the consolidated cluster system. The experiments show that in comparison with the case that each department operates its dedicated cluster system, Phoenix Cloud significantly decreases the scale of the required cluster system for a large organization, improves the benefit of the scientific computing department, and at the same time provisions enough resources to the other department running Web services with varying loads.

The surface code cannot be used when qubits vanish during computation; instead, a variant known as the topological cluster state is necessary. It has a gate error threshold of $0.75% and only requires nearest-neighbor interactions on a 2D array of qubits. Previous work on loss tolerance using this code only considered qubits vanishing during measurement. We begin by also including qubit loss during two-qubit gates and initialization, and then additionally consider interaction errors that occur when neighbors attempt to entangle with a qubit that isn't there. In doing so, we show that even our best case scenario requires a loss rate below 1% in order to avoid considerable space-time overhead.

We introduce and implement a technique to extend the quantum computational power of cluster states by replacing some projective measurements with generalized quantum measurements (POVMs). As an experimental demonstration we fully realize an arbitrary three-qubit cluster computation by implementing a tunable linear-optical POVM, as well as fast active feedforward, on a two-qubit photonic cluster state. Over 206 diferent computations, the average output fidelity is 0.9832 +/- 0.0002; furthermore the error contribution from our POVM device and feedforward is only of order 10e-3, less than some recent thresholds for fault-tolerant cluster computing.

We experimentally demonstrate a simple scheme for generating a four-photon entangled cluster state with fidelity over 0.860 $\pm$ 0.015. We show that the fidelity is high enough to guarantee that the produced state is distinguished from Greenberger-Horne-Zeilinger, W, and Dicke types of genuine four-qubit entanglement. We also demonstrate basic operations of one-way quantum computing using the produced state and show that the output state fidelities surpass classical bounds, which indicates that the entanglement in the produced state essentially contributes to the quantum operation.

Lockheed Martin Space Operations - Stennis Programs (LMSO) at the John C Stennis Space Center (NASA/SSC) has designed and built a Beowulf computer cluster which is owned by NASA/SSC and operated by LMSO. The design and construction of the cluster are detailed in this paper. The cluster is currently used for Computational Fluid Dynamics (CFD) simulations. The CFD codes in use and their applications are discussed. Examples of some of the work are also presented. Performance benchmark studies have been conducted for the CFD codes being run on the cluster. The results of two of the studies are presented and discussed. The cluster is not currently being utilized to its full potential; therefore, plans are underway to add more capabilities. These include the addition of structural, thermal, fluid, and acoustic Finite Element Analysis codes as well as real-time data acquisition and processing during test operations at NASA/SSC. These plans are discussed as well.

We study the low energy states of finite spin chains with isotropic (Heisenberg) and anisotropic (XY and Ising-like) exchange interaction with uniform and non-uniform coupling constants. We show that for an odd number of sites a spin cluster qubit can be defined in terms of the ground state doublet. This qubit is remarkably insensitive to the placement and coupling anisotropy of spins within the cluster. One- and two-qubit quantum gates can be generated by magnetic fields and inter-cluster exchange, and leakage during quantum gate operation is small. Spin cluster qubits inherit the long decoherence times and short gate operation times of single spins. Control of single spins is hence not necessary for the realization of universal quantum gates.

The performance of cluster computing depends on how concurrent jobs share multiple data center resource types like CPU, RAM and disk storage. Recent research has discussed efficiency and fairness requirements and identified a number of desirable scheduling objectives including so-called dominant resource fairness (DRF). We argue here that proportional fairness (PF), long recognized as a desirable objective in sharing network bandwidth between ongoing flows, is preferable to DRF. The superiority of PF is manifest under the realistic modelling assumption that the population of jobs in progress is a stochastic process. In random traffic the strategy-proof property of DRF proves unimportant while PF is shown by analysis and simulation to offer a significantly better efficiency-fairness tradeoff.

The aggregate power use of computing hardware is an important cost factor in scientific cluster and distributed computing systems. The Worldwide LHC Computing Grid (WLCG) is a major example of such a distributed computing system, used primarily for high throughput computing (HTC) applications. It has a computing capacity and power consumption rivaling that of the largest supercomputers. The computing capacity required from this system is also expected to grow over the next decade. Optimizing the power utilization and cost of such systems is thus of great interest. A number of trends currently underway will provide new opportunities for power-aware optimizations. We discuss how power-aware software applications and scheduling might be used to reduce power consumption, both as autonomous entities and as part of a (globally) distributed system. As concrete examples of computing centers we provide information on the large HEP-focused Tier-1 at FNAL, and the Tigress High Performance Computing Center at Princeton University, which provides HPC resources in a university context.

The tremendous advance in computer technology in the past decade has made it possible to achieve the performance of a supercomputer on a very small budget. We have built a multi-CPU cluster of Pentium PC capable of parallel computations using the Message Passing Interface (MPI). We will discuss the configuration, performance, and application of the cluster to our work in physics.

Aeroshark computing cluster

Aeroshark computing cluster

Models of quantum computation are important because they change the physical requirements for achieving universal quantum computation (QC). For example, one-way QC requires the preparation of an entangled "cluster" state followed by adaptive measurement on this state, a set of requirements which is different from the standard quantum circuit model. Here we introduce a model based on one-way QC but without measurements (except for the final readout), instead using adiabatic deformation of a Hamiltonian whose initial ground state is the cluster state. This opens the possibility to use the copious results from one-way QC to build more feasible adiabatic schemes.

We study the robustness--the invariance under definition changes--of the cluster class CL#P [HHKW05]. This class contains each #P function that is computed by a balanced Turing machine whose accepting paths always form a cluster with respect to some length-respecting total order with efficient adjacency checks. The definition of CL#P is heavily influenced by the defining paper's focus on (global) orders. In contrast, we define a cluster class, CLU#P, to capture what seems to us a more natural model of cluster computing. We prove that the naturalness is costless: CL#P = CLU#P. Then we exploit the more natural, flexible features of CLU#P to prove new robustness results for CL#P and to expand what is known about the closure properties of CL#P. The complexity of recognizing edges--of an ordered collection of computation paths or of a cluster of accepting computation paths--is central to this study. Most particularly, our proofs exploit the power of unique discovery of edges--the ability of nondeterministic functions to, in certain settings, discover on exactly one (in some cases, on at most one) computation path a critical piece of information regarding edges of orderings or clusters.

We study the robustness--the invariance under definition changes--of the cluster class CL#P [HHKW05]. This class contains each #P function that is computed by a balanced Turing machine whose accepting paths always form a cluster with respect to some length-respecting total order with efficient adjacency checks. The definition of CL#P is heavily influenced by the defining paper's focus on (global) orders. In contrast, we define a cluster class, CLU#P, to capture what seems to us a more natural model of cluster computing. We prove that the naturalness is costless: CL#P = CLU#P. Then we exploit the more natural, flexible features of CLU#P to prove new robustness results for CL#P and to expand what is known about the closure properties of CL#P. The complexity of recognizing edges--of an ordered collection of computation paths or of a cluster of accepting computation paths--is central to this study. Most particularly, our proofs exploit the power of unique discovery of edges--the ability of nondeterministic functions to, in certain settings, discover on exactly one (in some cases, on at most one) computation path a critical piece of information regarding edges of orderings or clusters.

We study the robustness--the invariance under definition changes--of the cluster class CL#P [HHKW05]. This class contains each #P function that is computed by a balanced Turing machine whose accepting paths always form a cluster with respect to some length-respecting total order with efficient adjacency checks. The definition of CL#P is heavily influenced by the defining paper's focus on (global) orders. In contrast, we define a cluster class, CLU#P, to capture what seems to us a more natural model of cluster computing. We prove that the naturalness is costless: CL#P = CLU#P. Then we exploit the more natural, flexible features of CLU#P to prove new robustness results for CL#P and to expand what is known about the closure properties of CL#P. The complexity of recognizing edges--of an ordered collection of computation paths or of a cluster of accepting computation paths--is central to this study. Most particularly, our proofs exploit the power of unique discovery of edges--the ability of nondeterministic functions to, in certain settings, discover on exactly one (in some cases, on at most one) computation path a critical piece of information regarding edges of orderings or clusters.

Aeroshark computing cluster

Aeroshark computing cluster

A scheme for the implementation of the cluster state model of quantum computing in optical fibers, which enables the feedforward feature, is proposed. This scheme uses the time-bin encoding of qubits. Following previously suggested methods of applying arbitrary one-qubit gates in optical fibers, two different ways for the realization of fusion gate types I and II for cluster production are proposed: a fully time-bin based encoding scheme and a combination of time-bin and polarization based encoding scheme. Also the methods of measurement in any desired bases for the purpose of the processing of cluster state computing for both these encodings are explained.

Monitoring large clusters is a challenging problem. It is necessary to observe a large quantity of devices with a reasonably short delay between consecutive observations. The set of monitored devices may include PCs, network switches, tape libraries and other equipments. The monitoring activity should not impact the performances of the system. In this paper we present PerfMC, a monitoring system for large clusters. PerfMC is driven by an XML configuration file, and uses the Simple Network Management Protocol (SNMP) for data collection. SNMP is a standard protocol implemented by many networked equipments, so the tool can be used to monitor a wide range of devices. System administrators can display informations on the status of each device by connecting to a WEB server embedded in PerfMC. The WEB server can produce graphs showing the value of different monitored quantities as a function of time; it can also produce arbitrary XML pages by applying XSL Transformations to an internal XML representation of the cluster's status. XSL Transformations may be used to produce HTML pages which can be displayed by ordinary WEB browsers. PerfMC aims at being relatively easy to configure and operate, and highly efficient. It is currently being used to monitor the Italian Reprocessing farm for the BaBar experiment, which is made of about 200 dual-CPU Linux machines.

Monitoring large clusters is a challenging problem. It is necessary to observe a large quantity of devices with a reasonably short delay between consecutive observations. The set of monitored devices may include PCs, network switches, tape libraries and other equipments. The monitoring activity should not impact the performances of the system. In this paper we present PerfMC, a monitoring system for large clusters. PerfMC is driven by an XML configuration file, and uses the Simple Network Management Protocol (SNMP) for data collection. SNMP is a standard protocol implemented by many networked equipments, so the tool can be used to monitor a wide range of devices. System administrators can display informations on the status of each device by connecting to a WEB server embedded in PerfMC. The WEB server can produce graphs showing the value of different monitored quantities as a function of time; it can also produce arbitrary XML pages by applying XSL Transformations to an internal XML representation of the cluster's status. XSL Transformations may be used to produce HTML pages which can be displayed by ordinary WEB browsers. PerfMC aims at being relatively easy to configure and operate, and highly efficient. It is currently being used to monitor the Italian Reprocessing farm for the BaBar experiment, which is made of about 200 dual-CPU Linux machines.

Tachyon is a distributed file system enabling reliable data sharing at memory speed across cluster computing frameworks. While caching today improves read workloads, writes are either network or disk bound, as replication is used for fault-tolerance. Tachyon eliminates this bottleneck by pushing lineage, a well-known technique borrowed from application frameworks, into the storage layer. The key challenge in making a long-lived lineage-based storage system is timely data recovery in case of failures. Tachyon addresses this issue by introducing a checkpointing algorithm that guarantees bounded recovery cost and resource allocation strategies for recomputation under common resource schedulers. Our evaluation shows that Tachyon outperforms in-memory HDFS by 110x for writes. It also improves the end-to-end latency of a realistic workflow by 4x. Tachyon is open source and is deployed at multiple companies.

The use of a heterogeneous cluster comprised of host processors and Field Programmable Gate Arrays (FPGAs) was investigated for accelerating the performance of parallel fine-grained applications using a direct FPGA to FPGA communication channel. The communication channel is implemented with an all-to-all board that attaches directly to the FPGA boards via their I/O interface. Test scripts were written to test the all-to-all board. The necessary communication support was designed, tested, and implemented to allow message exchange over the all-to-all board. The all-to-all support provides a low latency, low-bandwidth, communication channel for the FPGAs that can considerably extend the range of parallel applications. The Parallel Discrete Event Simulation was used to demonstrate that this computing model can accelerate the performance of parallel applications.

Lockheed Martin Space Operations - Stennis Programs (LMSO) at the John C Stennis Space Center (NASA/SSC) has designed and built a Beowulf computer cluster which is owned by NASA/SSC and operated by LMSO. The design and construction of the cluster are detailed in this paper. The cluster is currently used for Computational Fluid Dynamics (CFD) simulations. The CFD codes in use and their applications are discussed. Examples of some of the work are also presented. Performance benchmark studies have been conducted for the CFD codes being run on the cluster. The results of two of the studies are presented and discussed. The cluster is not currently being utilized to its full potential; therefore, plans are underway to add more capabilities. These include the addition of structural, thermal, fluid, and acoustic Finite Element Analysis codes as well as real-time data acquisition and processing during test operations at NASA/SSC. These plans are discussed as well.

Lockheed Martin Space Operations - Stennis Programs (LMSO) at the John C Stennis Space Center (NASA/SSC) has designed and built a Beowulf computer cluster which is owned by NASA/SSC and operated by LMSO. The design and construction of the cluster are detailed in this paper. The cluster is currently used for Computational Fluid Dynamics (CFD) simulations. The CFD codes in use and their applications are discussed. Examples of some of the work are also presented. Performance benchmark studies have been conducted for the CFD codes being run on the cluster. The results of two of the studies are presented and discussed. The cluster is not currently being utilized to its full potential; therefore, plans are underway to add more capabilities. These include the addition of structural, thermal, fluid, and acoustic Finite Element Analysis codes as well as real-time data acquisition and processing during test operations at NASA/SSC. These plans are discussed as well.

Lockheed Martin Space Operations - Stennis Programs (LMSO) at the John C Stennis Space Center (NASA/SSC) has designed and built a Beowulf computer cluster which is owned by NASA/SSC and operated by LMSO. The design and construction of the cluster are detailed in this paper. The cluster is currently used for Computational Fluid Dynamics (CFD) simulations. The CFD codes in use and their applications are discussed. Examples of some of the work are also presented. Performance benchmark studies have been conducted for the CFD codes being run on the cluster. The results of two of the studies are presented and discussed. The cluster is not currently being utilized to its full potential; therefore, plans are underway to add more capabilities. These include the addition of structural, thermal, fluid, and acoustic Finite Element Analysis codes as well as real-time data acquisition and processing during test operations at NASA/SSC. These plans are discussed as well.

Conventional single node packet analyzers are unable to monitor network traffic at scale. In this thesis, elements of the Apache Hadoop ecosystem, including HBase, Spark, and MapReduce, are employed to conduct network traffic analysis on a large collection of network traffic. Limited analysis is conducted directly on packet capture next generation (pcapng) files on the Hadoop Distributed File System (HDFS) using MapReduce. Next, to allow for repeated analysis on the same dataset without reading all source files in their entirety for every calculation, pcapng files are parsed and relevant meta-data is bulk loaded into HBase, a Not Only Structured Query Language (NoSQL) database employing the HDFS for parallelization. This NoSQL database is then accessed via Apache Spark where pertinent data is loaded into DataFrames and additional analysis on the network traffic takes place. This research demonstrates the viability of custom, modular, automated analytics, employing open-source software to enable parallelization, to conduct traffic analysis at scale.

One-way quantum computing is experimentally appealing because it requires only local measurements on an entangled resource called a cluster state. Record-size, but non-universal, continuous-variable cluster states were recently demonstrated separately in the time and frequency domains. We propose to combine these approaches into a scalable architecture in which a single optical parametric oscillator and simple interferometer entangle up to ($3\times 10^3$ frequencies) $\times$ (unlimited number of temporal modes) into a new and computationally universal continuous-variable cluster state. We introduce a generalized measurement protocol to enable improved computational performance on this new entanglement resource.

One-way quantum computing is experimentally appealing because it requires only local measurements on an entangled resource called a cluster state. Record-size, but non-universal, continuous-variable cluster states were recently demonstrated separately in the time and frequency domains. We propose to combine these approaches into a scalable architecture in which a single optical parametric oscillator and simple interferometer entangle up to ($3\times 10^3$ frequencies) $\times$ (unlimited number of temporal modes) into a new and computationally universal continuous-variable cluster state. We introduce a generalized measurement protocol to enable improved computational performance on this new entanglement resource.

In this paper I describe some results on the use of virtual processors technology for parallelize some SPMD computational programs in a cluster environment. The tested technology is the INTEL Hyper Threading on real processors, and the programs are MATLAB 6.5 Release 13 scripts for floating points computation. By the use of this technology, I tested that a cluster can run with benefit a number of concurrent processes double the amount of physical processors. The conclusions of the work concern on the utility and limits of the used approach. The main result is that using virtual processors is a good technique for improving parallel programs not only for memory-based computations, but in the case of massive disk-storage operations too.

Funds were received in April 2001 under the Department of Defense DURIP program for construction of a 48 processor high performance computing cluster. This report details the hardware which was purchased and how it has been used to enable and enhance research activities directly supported by, and of interest to, the Air Force Office of Scientific Research and the Department of Defense. The report is divided into two major sections. The first section after this summary describes the computer cluster, its setup, and some cluster performance benchmark results. The second section explains ongoing research efforts which have benefited from the cluster hardware, and presents highlights of those efforts since installation of the cluster.

A computer cluster could be a group of joined computers, operating along closely so in several respects they type one laptop. The parts of a cluster area unit ordinarily, however not forever, connected to every different through quick native space networks. Clusters area unit typically deployed to enhance performance and or handiness over that provided by one laptop, whereas usually being far more cost efficient than single computers of comparable speed or accessibility.The major objective within the cluster is utilizing a bunch of process nodes therefore on complete the assigned job in an exceedingly minimum quantity of your time by operating hand in glove. the most and necessary strategy to realize such objective is by transferring the additional hundreds from busy nodes to idle nodes.In this paper weve presented style and of a cluster based framework . The cluster implementation involves the planning of a server named MCLUSTER that manages the configuring, resetting of cluster. Framework handles the generation of application mobile code and its distribution to appropriate client nodes. The consumer node receives and executes the mobile code that defines the distributed job submitted by MCLUSTER server and replies the results back. Trupti Bhor | Yogeshchandra Puranik "An Introduction to Cluster Computing" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42561.pdf Paper URL: https://www.ijtsrd.comengineering/computer-engineering/42561/an-introduction-to-cluster-computing/trupti-bhor

The acquired computing cluster is used in the development of novel techniques for computational fluid dynamics and continuum mechanics, with a focus on large Eulerian or Lagrangian discretizations. Applications that receive particular emphasis include the following: (1) simulation of discontinuous flows resulting from the interaction of several immiscible or chemically reacting phases; (2) adaptive discretizations of large fluid volumes that can resolve turbulent flows and the effects of highly variable bottom topography; (3) coupling of Lagrangian deformable or rigid objects to Eulerian discretizations of fluid volumes; and (4) simulation of nonlinear and anisotropic elastic continua under extreme deformation, severe impact, and fracture scenarios. This report provides a summary of the applications and algorithms whose development was enabled by the acquisition of the equipment allowed by the grant. The author also outlines the impact of this parallel computing resource on their future research roadmap.