Search NASA⌕ Search

SEARCH · Search NASA

Results for “High Bandwidth Network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

Extravehicular Activity Operations Concepts Under Communication Latency and Bandwidth Constraints

The Biologic Analog Science Associated with Lava Terrains (BASALT) project is a multi-year program dedicated to iteratively develop, implement, and evaluate concepts of operations (ConOps) and supporting capabilities intended to enable and enhance human scientific exploration of Mars. This pa-per describes the planning, execution, and initial results from the first field deployment, referred to as BASALT-1, which consisted of a series of 10 simulated extravehicular activities (EVAs) on volcanic flows in Idaho's Craters of the Moon (COTM) National Monument. The ConOps and capabilities deployed and tested during BASALT-1 were based on previous NASA trade studies and analog testing. Our primary research question was whether those ConOps and capabilities work acceptably when performing real (non-simulated) biological and geological scientific exploration under 4 different Mars-to-Earth communication conditions: 5 and 15 min one-way light time (OWLT) communication latencies and low (0.512 Mb/s uplink, 1.54 Mb/s downlink) and high (5.0 Mb/s uplink, 10.0 Mb/s downlink) bandwidth conditions representing the lower and higher limits of technical communication capabilities currently proposed for future human exploration missions. The synthesized results of BASALT-1 with respect to the ConOps and capabilities assessment were derived from a variety of sources, including EVA task timing data, network analytic data, and subjective ratings and comments regarding the scientific and operational acceptability of the ConOp and the extent to which specific capabilities were enabling and enhancing, and are presented here. BASALT-1 established preliminary findings that baseline ConOp, software systems, and communication protocols were scientifically and operationally acceptable with minor improvements desired by the "Mars" extravehicular (EV) and intravehicular (IV) crewmembers, but unacceptable with improvements required by the "Earth" Mission Support Center. These data will provide a basis for guiding and prioritizing capability development for future BASALT deployments and, ultimately, future human exploration missions.

Beaton, Kara H.↗

Effectiveness and predictability of in-network storage cache for Scientific Workflows

Large scientific collaborations often have multiple scientists accessing the same set of files while doing different analyses, which create repeated accesses to the large amounts of shared data located far away. These data accesses have long latency due to distance and occupy the limited bandwidth available over the wide-area network. To reduce the wide-area network traffic and the data access latency, regional data storage caches have been installed as a new networking service. To study the effectiveness of such a cache system in scientific applications, we examine the Southern California Petabyte Scale Cache for a high-energy physics experiment. By examining about 3TB of operational logs, we show that this cache removed 67.6% of file requests from the wide-area network and reduced the traffic volume on wide-area network by 12. 3TB (or 35.4%) an average day. The reduction in the traffic volume (35.4%) is less than the reduction in file counts (67.6%) because the larger files are less likely to be reused. Due to this difference in data access patterns, the cache system has implemented a policy to avoid evicting smaller files when processing larger files. We also build a machine learning model to study the predictability of the cache behavior. Tests show that this model is able to accurately predict the cache accesses, cache misses, and network throughput, making the model useful for future studies on resource provisioning and planning.

Sim, Caitlin↗

Intelligent neuroprocessors for in-situ launch vehicle propulsion systems health management

Efficacy of existing on-board propulsion systems health management systems (HMS) are severely impacted by computational limitations (e.g., low sampling rates); paradigmatic limitations (e.g., low-fidelity logic/parameter redlining only, false alarms due to noisy/corrupted sensor signatures, preprogrammed diagnostics only); and telemetry bandwidth limitations on space/ground interactions. Ultra-compact/light, adaptive neural networks with massively parallel, asynchronous, fast reconfigurable and fault-tolerant information processing properties have already demonstrated significant potential for inflight diagnostic analyses and resource allocation with reduced ground dependence. In particular, they can automatically exploit correlation effects across multiple sensor streams (plume analyzer, flow meters, vibration detectors, etc.) so as to detect anomaly signatures that cannot be determined from the exploitation of single sensor. Furthermore, neural networks have already demonstrated the potential for impacting real-time fault recovery in vehicle subsystems by adaptively regulating combustion mixture/power subsystems and optimizing resource utilization under degraded conditions. A class of high-performance neuroprocessors, developed at JPL, that have demonstrated potential for next-generation HMS for a family of space transportation vehicles envisioned for the next few decades, including HLLV, NLS, and space shuttle is presented. Of fundamental interest are intelligent neuroprocessors for real-time plume analysis, optimizing combustion mixture-ratio, and feedback to hydraulic, pneumatic control systems. This class includes concurrently asynchronous reprogrammable, nonvolatile, analog neural processors with high speed, high bandwidth electronic/optical I/O interfaced, with special emphasis on NASA's unique requirements in terms of performance, reliability, ultra-high density ultra-compactness, ultra-light weight devices, radiation hardened devices, power stringency, and long life terms.

Gulati, S.↗

Data Movement Dominates: Advanced Memory Technology to Address the Real Exascale Power Problem

Energy is the fundamental barrier to Exascale supercomputing and is dominated by the cost of moving data from one point to another, not computation. Similarly, performance is dominated by data movement, not computation. The solution to this problem requires three critical technologies: 3D integration, optical chip-to-chip communication, and a new communication model. The central goal of the Sandia led "Data Movement Dominates" project aimed to develop memory systems and new architectures based on these technologies that have the potential to lower the cost of local memory accesses by orders of magnitude and provide substantially more bandwidth. Only through these transformational advances can future systems reach the goals of Exascale computing with a manageable power budgets. The Sandia led team included co-PIs from Columbia University, Lawrence Berkeley Lab, and the University of Maryland. The Columbia effort of Data Movement Dominates focused on developing a physically accurate simulation environment and experimental verification for optically-connected memory (OCM) systems that can enable continued performance scaling through high-bandwidth capacity, energy-efficient bit-rate transparency, and time-of-flight latency. With OCM, memory device parallelism and total capacity can scale to match future high-performance computing requirements without sacrificing data-movement efficiency. When we consider systems with integrated photonics, links to memory can be seamlessly integrated with the interconnection network-in a sense, memory becomes a primary aspect of the interconnection network. At the core of the Columbia effort, toward expanding our understanding of OCM enabled computing we have created an integrated modeling and simulation environment that uniquely integrates the physical behavior of the optical layer. The PhoenxSim suite of design and software tools developed under this effort has enabled the co-design of and performance evaluation photonics-enabled OCM architectures on Exascale computing systems.

97 MATHEMATICS AND COMPUTING↗

ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers

Deep neural networks (DNNs) have heavily relied on traditional computational units, such as CPUs and GPUs. However, this conventional approach brings significant computational burden, latency issues, and high power consumption, limiting their effectiveness. This has sparked the need for lightweight networks such as ExtremeC3Net. Meanwhile, there have been notable advancements in optical computational units, particularly with metamaterials, offering the exciting prospect of energy-efficient neural networks operating at the speed of light. Yet, the digital design of metamaterial neural networks (MNNs) faces precision, noise, and bandwidth challenges, limiting their application to intuitive tasks and low-resolution images. In this study, we proposed a large kernel lightweight segmentation model, ExtremeMETA. Based on ExtremeC3Net, our proposed model, ExtremeMETA maximized the ability of the first convolution layer by exploring a larger convolution kernel and multiple processing paths. With the large kernel convolution model, we extended the optic neural network application boundary to the segmentation task. To further lighten the computation burden of the digital processing part, a set of model compression methods was applied to improve model efficiency in the inference stage. The experimental results on three publicly available datasets demonstrated that the optimized efficient design improved segmentation performance from 92.45 to 95.97 on mIoU while reducing computational FLOPs from 461.07 MMacs to 166.03 MMacs. The large kernel lightweight model ExtremeMETA showcased the hybrid design’s ability on complex tasks.

large convolution kernel↗

High-speed digital fiber optic links for satellite traffic

Large aperture phased array antennas operating at millimeter wave frequencies are designed for space-based communications and imaging platforms. Array elements are comprised of active T/R modules which are linked to the central processing unit through high-speed fiber-optic networks. The system architecture satisfying system requirements at millimeter wave frequency is T/R level data mixing where data and frequency reference signals are distributed independently before mixing at the T/R modules. This paper demonstrates design procedures of a low loss high-speed fiber-optic link used for transmission of data signals over 600-900 MHz bandwidth inside satellite. The fiber-optic link is characterized for transmission of analog and digital data. A dynamic range of 79 dB/MHz was measured for analog data over the bandwidth. On the other hand, for bursted SMSK satellite traffic at 220 Mbps rates, BER of 2 x 10 to the -7th was measured for E(b)/N(o) of 14.3 dB.

Daryoush, A. S.↗

Ka-Band Waveguide Two-Way Hybrid Combiner for MMIC Amplifiers

The design, simulation, and characterization of a novel Ka-band (32.05 0.25 GHz) rectangular waveguide two-way branch-line hybrid unequal power combiner (with port impedances matched to that of a standard WR-28 waveguide) has been created to combine input signals, which are in phase and with an amplitude ratio of two. The measured return loss and isolation of the branch-line hybrid are better than 22 and 27 dB, respectively. The measured combining efficiency is 92.9 percent at the center frequency of 32.05 GHz. This circuit is efficacious in combining the unequal output power from two Ka-band GaAs pseudomorphic high electron mobility transistor (pHEMT) monolithic microwave integrated circuit (MMIC) power amplifiers (PAs) with high efficiency. The component parts include the branch-line hybrid-based power combiner and the MMIC-based PAs. A two-way branch-line hybrid is a four-port device with all ports matched; power entering port 1 is divided in phase, and into the ratio 2:1 between ports 3 and 4. No power is coupled to port 2. MMICs are a type of integrated circuit fabricated on GaAs that operates at microwave frequencies, and performs the function of signal amplification. The power combiner is designed to operate over the frequency band of 31.8 to 32.3 GHz, which is NASA's deep space frequency band. The power combiner would have an output return loss better than 20 dB. Isolation between the output port and the isolated port is greater than 25 dB. Isolation between the two input ports is greater than 25 dB. The combining efficiency would be greater than 90 percent when the ratio of the two input power levels is two. The power combiner is machined from aluminum with E-plane split-block arrangement, and has excellent reliability. The flexibility of this design allows the combiner to be customized for combining the power from MMIC PAs with an arbitrary power output ratio. In addition, it allows combining a low-power GaAs MMIC with a high-power GaN MMIC. The arbitrary port impedance allows matching the output impedance of the MMIC PA directly to the waveguide impedance without transitioning first into a transmission line with characteristic impedance of 50 ohms. Thus, by eliminating the losses associated with a transition, the overall SSPA efficiency is enhanced. For reducing the cost and weight when required in very large quantities, such as in the beam-forming networks of phased-array antenna systems, the combiner can be manufactured using metal-plated plastic. Two hybrid unequal power combiners can be cascaded to realize a non-binary combiner (for e.g., a three-way) and can be synergistically optimized for low VSWR (voltage standing wave ratio), low insertion loss, high isolation, and wide bandwidth using commercial off-the-shelf electromagnetic software design tools.

Simons, Rainee N.↗

Extending Parsimonious Bayesian Inference

Parsimonious Bayesian inference is a theoretical framework for efficient data assimilation that seeks to balance increased consistency between predictions and training data against corresponding increases in model complexity. Within this framework, over-training is understood as optimization that encodes excessive information within model parameters while only achieving small improvements between predictions and training data. This project aims to develop practical methods of limiting excess model information during optimization. One key observation is that practical heuristics for parsimonious learning in high-dimensions must balance expressivity, i.e. the ability of the model to capture diverse predictions with only a few non-zero parameters, against discoverability, i.e. the ability to train the model with gradient-based optimization and drive parameters to low information states. As such, we developed logical activation functions that are able to adaptively approximate arbitrary truth tables that define Boolean logic operations within a probabilistic framework. These functions have demonstrated the ability to learn exclusive disjunction (XOR) and conditioned disjunction (if [condition] then [result_if_true] else [result_if_false]) within a single layer of a neural network. To efficiently exploit these activation functions to drive parsimonious learning required several other advances within the domain of variational inference. The most efficient form of complexity suppression is structured sparsification, driving most model parameters to zero while achieving the structural coherence among nonzeros needed for bandwidth reduction. Such models are not only far more efficient at suppressing information-theoretic complexity, they also reduce the other forms of complexity (computations, communication, storage, and the number of dependencies needed to evaluate predictions). Aiming to support enhanced sparsification, this project examined new approaches to high-dimensional variational inference that allow us to calibrate and control parameter uncertainty during optimization. By identifying which parameters can sustain sparsifying perturbations with little impact on prediction quality, we can develop better pruning strategies by framing them as approximate Bayesian inference. These advances also open paths to mitigate concerns with deploying advanced learning methods in resource-constrained environments, such as running models on power-limited or communication-limited devices.

97 MATHEMATICS AND COMPUTING↗

HEP Science Network Requirements--Final Report

The Energy Sciences Network (ESnet) is the primary provider of network connectivity for the US Department of Energy Office of Science, the single largest supporter of basic research in the physical sciences in the United States. In support of the Office of Science programs, ESnet regularly updates and refreshes its understanding of the networking requirements of the instruments, facilities, scientists, and science programs that it serves. This focus has helped ESnet to be a highly successful enabler of scientific discovery for over 20 years. In August 2009 ESnet and the Office of High Energy Physics (HEP), of the DOE Office of Science, organized a workshop to characterize the networking requirements of the programs funded by HEP. The International HEP community has been a leader in data intensive science from the beginning. HEP data sets have historically been the largest of all scientific data sets, and the communty of interest the most distributed. The HEP community was also the first to embrace Grid technologies. The requirements identified at the workshop are summarized below, and described in more detail in the case studies and the Findings section: (1) There will be more LHC Tier-3 sites than orginally thought, and likely more Tier-2 to Tier-2 traffic than was envisioned. It it not yet known what the impact of this will be on ESnet, but we will need to keep an eye on this traffic. (2) The LHC Tier-1 sites (BNL and FNAL) predict the need for 40-50 Gbps of data movement capacity in 2-5 years, and 100-200 Gbps in 5-10 years for HEP program related traffic. Other key HEP sites include LHC Tier-2 and Tier-3 sites, many of which are located at universities. To support the LHC, ESnet must continue its collaborations with university and international networks. (3) While in all cases the deployed 'raw' network bandwidth must exceed the user requirements in order to meet the data transfer and reliability requirements, network engineering for trans-Atlantic connectivity is more complex than network engineering for intra-US connectivity. This is because transoceanic circuits have lower reliability and longer repair times when compared with land-based circuits. Therefore, trans-Atlantic connectivity requires greater deployed bandwidth and diversity to ensure reliability and service continuity of the user-level required data transfer rates. (4) Trans-Atlantic traffic load and patterns must be monitored, and projections adjusted if necessary. There is currently a shutdown planned for the LHC in 2012 that may affect projections of trans-Atlantic bandwidth requirements. (5) There is a significant need for network tuning and troubleshooting during the establishment of new LHC Tier-2 and Tier-3 facilities. ESnet will work with the HEP community to help new sites effectively use the network. (6) SLAC is building the CCD camera for the LSST. This project will require significant bandwidth (up to 30Gbps) to NCSA over the next few years. (7) The accelerator modeling program at SLAC could require the movement of 1PB simulation data sets from the Leadership Computing Facilities at Argonne and Oak Ridge to SLAC. The data sets would need to be moved overnight, and moving 1PB in eight hours requires more than 300Gbps of throughput. This requirement is dependent on the deployment of analysis capabilities at SLAC, and is about five years away. (8) It is difficult to achieve high data transfer throughput to sites in China. Projects that need to transfer data in or out of China are encouraged to deploy test and measurement infrastructure (e.g. perfSONAR) and allow time for performance tuning.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Overcoming the fundamental limit of quantum transduction via intraband entanglement

A quantum transducer converts an input signal to an output probe at a distant frequency band while maintaining the quantum information with high fidelity, which is crucial for quantum networking and distributed quantum sensing and computing. In terms of microwave–optical quantum transduction, the state-of-the-art quantum transducers suffer low transduction efficiency from weak nonlinear coupling, wherein increasing pump power to enhance efficiency inevitably leads to thermal noise from heating. Moreover, we reveal that the efficiency-bandwidth product of a cavity electro-optical or electro-optomechanical transducer is fundamentally limited by pump power and nonlinear coupling coefficient, irrespective of cavity engineering efforts. To overcome this fundamental limit, we propose to noiselessly boost the transduction efficiency by consuming intraband entanglement (e.g., microwave–microwave or optical–optical entanglement in the case of microwave–optical transduction). Via a squeezer–coupler–antisqueezer sandwich structure, the protocol enhances the transduction efficiency to unity in the ideal lossless case, given an arbitrarily weak pump and nonlinear coupling. In practical cavity systems, our entanglement-assisted protocol surpasses the non-assisted fundamental limit of the efficiency-bandwidth product and reduces the threshold cooperativity for positive quantum capacity by a factor proportional to two-mode squeezing gain. Given a fixed cooperativity, our approach increases the broadband quantum capacity by orders of magnitude. The entanglement-assisted advantage is robust to ancilla loss and cavity detuning.

Shi, Haowei [Southern California U.] (ORCID:000000↗

Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications

With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters stored on-chip. In many of these applications, there is not enough time to go off-chip and retrieve weights. Even more so, off-chip memory such as DRAM does not have the bandwidth required to process these NNs as fast as the data is being produced (e.g., every 25 ns). As such, these extreme latency and bandwidth requirements have architectural implications for the hardware intended to run these NNs: 1) all NN parameters must fit on-chip, and 2) codesigning custom/reconfigurable logic is often required to meet these latency and bandwidth constraints. In our work, we show that many scientific NN applications must run fully on chip, in the extreme case requiring a custom chip to meet such stringent constraints.

Weng, Olivia↗

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗

The Open High Throughput Computing Content Delivery Network

LHC experiments make extensive use of web proxy caches, especially for software distribution via the CernVM File System and for conditions data via the Frontier Distributed Database Caching system. Since many jobs read the same data, cache hit rates are high and hence most of the traffic flows efficiently over Local Area Networks. However, it is not always possible to have local web caches, particularly for opportunistic cases whereexperiments have little control over site services. The Open High Throughput Computing (HTC) Content Delivery Network (CDN), openhtc.io, aims to address this by using web proxy caches from a commercial CDN provider. Cloudflare provides a simple interface for registering DNS aliases of any web server and does reverse proxy web caching on those aliases. The openhtc.io domain is hosted on Cloudflare's free tier CDN which has no bandwidth limit and makes use of data centers throughout the world, so the average performance for clients is much improved compared to reading from CERN or a Tier 1. The load on WLCG servers is also significantly reduced. WLCG Web Proxy Auto Discovery is used to select local web caches when they are available and otherwise select openhtc.io caching. This paper describes the Open HTC CDN in detail and provides initial results from its use for LHC@Home and USCMS opportunistic computing.

97 MATHEMATICS AND COMPUTING↗

Evaluating Trade-offs in Potential Exascale Interconnect Topologies

This study looks at the high-level trade-offs for interconnect architectures that are likely to be available in HPC machines in the 2021-2022 timeframe. The study uses multiple simulation models to look at the effects of varying machine size, injection bandwidth and topology for a selected set of benchmark communication patterns. The studies show the sensitivity of various applications to these network parameters. This study can help inform decisions on node size versus number of nodes, which topology is most efficient for our applications, how much injection bandwidth to provision, etc. These simulations only look at interconnects with maximally configured global bandwidth, and studies of networks configured with less will be the subject of future milestones.

97 MATHEMATICS AND COMPUTING↗

Low-sensitivity, frequency-selective amplifier circuits for hybrid and bipolar fabrication.

A network is described which is suitable for realizing a low-sensitivity high-Q second-order frequency-selective amplifier for high-frequency operation. Circuits are obtained from this network which are well suited for realizing monolithic integrated circuits and which do not require any process steps more critical than those used for conventional monolithic operational and video amplifiers. A single chip version using compatible thin-film techniques for the frequency determination elements is then feasible. Center frequency and bandwidth can be set independently by trimming two resistors. The frequency selective circuits have a low sensitivity to the process variables, and the sensitivity of the center frequency and bandwidth to changes in temperature is very low.

Pi, C.↗

Mobile satellite communications technology - A summary of NASA activities

Studies in recent years indicate that future high-capacity mobile satellite systems are viable only if certain high-risk enabling technologies are developed. Accordingly, NASA has structured an advanced technology development program aimed at efficient utilization of orbit, spectrum, and power. Over the last two years, studies have concentrated on developing concepts and identifying cost drivers and other issues associated with the major technical areas of emphasis: vehicle antennas, speech compression, bandwidth-efficient digital modems, network architecture, mobile satellite channel characterization, and selected space segment technology. The program is now entering the next phase - breadboarding, development, and field experimentation.

Dutzi, E. J.↗

High-Performance, Multi-Node File Copies and Checksums for Clustered File Systems

Modern parallel file systems achieve high performance using a variety of techniques, such as striping files across multiple disks to increase aggregate I/O bandwidth and spreading disks across multiple servers to increase aggregate interconnect bandwidth. To achieve peak performance from such systems, it is typically necessary to utilize multiple concurrent readers/writers from multiple systems to overcome various singlesystem limitations, such as number of processors and network bandwidth. The standard cp and md5sum tools of GNU coreutils found on every modern Unix/Linux system, however, utilize a single execution thread on a single CPU core of a single system, and hence cannot take full advantage of the increased performance of clustered file systems. Mcp and msum are drop-in replacements for the standard cp and md5sum programs that utilize multiple types of parallelism and other optimizations to achieve maximum copy and checksum performance on clustered file systems. Multi-threading is used to ensure that nodes are kept as busy as possible. Read/write parallelism allows individual operations of a single copy to be overlapped using asynchronous I/O. Multinode cooperation allows different nodes to take part in the same copy/checksum. Split-file processing allows multiple threads to operate concurrently on the same file. Finally, hash trees allow inherently serial checksums to be performed in parallel. Mcp and msum provide significant performance improvements over standard cp and md5sum using multiple types of parallelism and other optimizations. The total speed-ups from all improvements are significant. Mcp improves cp performance over 27x, msum improves md5sum performance almost 19x, and the combination of mcp and msum improves verified copies via cp and md5sum by almost 22x. These improvements come in the form of drop-in replacements for cp and md5sum, so are easily used and are available for download as open source software at http://mutil.sourceforge.net.

Kolano, Paul Z.↗

Nuclear Physics Science Network Requirements Workshop, May 2008 - Final Report

The Energy Sciences Network (ESnet) is the primary provider of network connectivity for the US Department of Energy Office of Science, the single largest supporter of basic research in the physical sciences in the United States of America. In support of the Office of Science programs, ESnet regularly updates and refreshes its understanding of the networking requirements of the instruments, facilities, scientists, and science programs that it serves. This focus has helped ESnet to be a highly successful enabler of scientific discovery for over 20 years. In May 2008, ESnet and the Nuclear Physics (NP) Program Office of the DOE Office of Science organized a workshop to characterize the networking requirements of the science programs funded by the NP Program Office. Most of the key DOE sites for NP related work will require significant increases in network bandwidth in the 5 year time frame. This includes roughly 40 Gbps for BNL, and 20 Gbps for NERSC. Total transatlantic requirements are on the order of 40 Gbps, and transpacific requirements are on the order of 30 Gbps. Other key sites are Vanderbilt University and MIT, which will need on the order of 20 Gbps bandwidth to support data transfers for the CMS Heavy Ion program. In addition to bandwidth requirements, the workshop emphasized several points in regard to science process and collaboration. One key point is the heavy reliance on Grid tools and infrastructure (both PKI and tools such as GridFTP) by the NP community. The reliance on Grid software is expected to increase in the future. Therefore, continued development and support of Grid software is very important to the NP science community. Another key finding is that scientific productivity is greatly enhanced by easy researcher-local access to instrument data. This is driving the creation of distributed repositories for instrument data at collaborating institutions, along with a corresponding increase in demand for network-based data transfers and the tools to manage those transfers effectively. Network reliability is also becoming more important as there is often a narrow window between data collection and data archiving when transfer and analysis can be done. The instruments do not stop producing data, so extended network outages can result in data loss due to analysis pipeline stalls. Finally, as the scope of collaboration continues to increase, collaboration tools such as audio and video conferencing are becoming ever more critical to the productivity of scientific collaborations.

97 MATHEMATICS AND COMPUTING↗