Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “computing systems”

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 973 records · Page 54

A Survey Of Architectural Approaches for Managing Embedded DRAM and Non-volatile On-chip Caches

Recent trends of CMOS scaling and increasing number of on-chip cores have led to a large increase in the size of on-chip caches. Since SRAM has low density and consumes large amount of leakage power, its use in designing on-chip caches has become more challenging. To address this issue, researchers are exploring the use of several emerging memory technologies, such as embedded DRAM, spin transfer torque RAM, resistive RAM, phase change RAM and domain wall memory. In this paper, we survey the architectural approaches proposed for designing memory systems and, specifically, caches with these emerging memory technologies. To highlight their similarities and differences, we present a classification of these technologies and architectural approaches based on their key characteristics. We also briefly summarize the challenges in using these technologies for architecting caches. We believe that this survey will help the readers gain insights into the emerging memory device technologies, and their potential use in designing future computing systems.

classification↗

The Approximability of Partial Vertex Covers in Trees.

Motivated by applications in risk management of computational systems, we focus our attention on a special case of the partial vertex cover problem, where the underlying graph is assumed to be a tree. Here, we consider four possible versions of this setting, depending on whether vertices and edges are weighted or not. Two of these versions, where edges are assumed to be unweighted, are known to be polynomial-time solvable (Gandhi, Khuller, and Srinivasan, 2004). However, the computational complexity of this problem with weighted edges, and possibly with weighted vertices, has not been determined yet. The main contribution of this paper is to resolve these questions, by fully characterizing which variants of partial vertex cover remain intractable in trees, and which can be efficiently solved. In particular, we propose a pseudo-polynomial DP-based algorithm for the most general case of having weights on both edges and vertices, which is proven to be NPhard. This algorithm provides a polynomial-time solution method when weights are limited to edges, and combined with additional scaling ideas, leads to an FPTAS for the general case. A secondary contribution of this work is to propose a novel way of using centroid decompositions in trees, which could be useful in other settings as well.

97 MATHEMATICS AND COMPUTING↗

Extreme-scale workflows: A perspective from the JLESC international community

The Joint Laboratory for Extreme-Scale Computing (JLESC) focuses on software challenges in high-performance computing systems to meet the needs of today’s science campaigns, which often require large resources, consist of multiple tasks, and generate vast amounts of data. In this context, extreme-scale workflows have been the key factor in enabling scientific discoveries by helping scientists automate the dependencies and data exchanges between workflow tasks, instead of managing those manually. Here, in this paper, we present representative extreme-scale workflows and feature workflow systems developed by JLESC participating institutions. We present lessons learned while developing these tools, alongside with the open challenges and future research directions in the field of extreme-scale workflows.

97 MATHEMATICS AND COMPUTING↗

SciDAC3 SUPER Performance Institute, University of Oregon Contributions (Final Report)

The SciDAC-3 Institute for Sustained Performance, Energy, and Resilience (SUPER) focused on developing technology and leveraging expertise towards ensuring that computational scientists could successfully exploit existing and emerging DOE high performance computing systems. To achieve this goal, SUPER was organized into research thrusts focusing on performance engineering, auto-tuning, performance tools, energy efficiency, resilience and multi-objective optimization, with a target of facilitating effective utilization of near term HPC systems. As described in this summary document, our teams’ significant insights into both application- and architecture-awareness drove numerous innovations across our stated research areas, while significantly improving the performance, portability, and functionality of numerous SciDAC partnership applications, enabling scientific simulation at unprecedented scale. Additionally, the tools, methodologies, and collaborations developed under this project will continue paying dividends as we face the challenges of forthcoming multi-petascale and exascale computing technologies.

97 MATHEMATICS AND COMPUTING↗

OpenMP Target Task: Tasking and Target Offloading on Heterogeneous Systems

This work evaluated the use of OpenMP tasking with target GPU offloading as a potential solution for programming productivity and performance on heterogeneous systems. Also, it is proposed a new OpenMP specification to make the implementation of heterogeneous codes simpler by using OpenMP target task, which integrates both OpenMP tasking and target GPU offloading in a single OpenMP pragma. As a test case, the authors used one of the most popular and widely used Basic Linear Algebra Subprogram Level-3 routines: triangular solver (TRSM). To benefit from the heterogeneity of the current high-performance computing systems, the authors propose a different parallelization of the algorithm by using a nonuniform decomposition of the problem. This work used target GPU offloading inside OpenMP tasks to address the heterogeneity found in the hardware. This new approach can outperform the state-of-the-art algorithms, which use a uniform decomposition of the data, on both the CPU-only and hybrid CPU-GPU systems, reaching speedups of up to one order of magnitude. The performance that this approach achieves is faster than the IBM ESSL math library on CPU and competitive relative to a highly optimized heterogeneous CUDA version. One node of Oak Ridge National Laboratory’s supercomputer, Summit, was used for performance analysis.

Valero Lara, Pedro↗

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗

Event triggering in the IceCube data acquisition system

In order to detect cosmic ray air showers and neutrinos, the software data acquisition (DAQ) system of the IceCube Neutrino Observatory forms triggers on patterns of Cherenkov light deposition in the detector based on temporal and/or spatial coincidences. Here we describe the algorithms used for triggering, as well as the fast merging algorithm used to combine the time-ordered hit streams from the optical modules. We also present recently implemented and planned modifications of the DAQ that take advantage of our newly upgraded multi-core computer systems at the South Pole.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Large-Scale Calculations for Material Sciences Using Accelerators to Improve Time- and Energy-to-Solution

A major impediment to deploying next-generation high-performance computational systems is the required electrical power, often measured in units of megawatts. The solution to this problem is driving the introduction of novel machine architectures, such as those employing many-core processors and specialized accelerators. In this article, we describe the use of a hybrid accelerated architecture to achieve both reduced time to solution and the associated reduction in the electrical cost for a state-of-the-art materials science computation.

36 MATERIALS SCIENCE↗

Foundational Report Series: Advanced Distribution Management Systems for Grid Modernization, Implementation Strategy for a Distribution Management System

Electric distribution utilities encounter many challenges to successful deployment of Distribution Management Systems (DMSs). The key challenges are documented in this report, along with suggestions for overcoming them. This report offers a recommended list of activities for implementing a DMS. It takes a strategic approach to implementing DMS from a project management perspective. The project management strategy covers DMS planning, procurement, design, building, testing, Installation, commissioning, and system integration issues and solutions. It identifies the risks that are associated with implementation and suggests strategies for utilities to use to mitigate them or avoid them altogether. Attention is given to common barriers to successful DMS implementation. This report begins with an overview of the implementation strategy for a DMS and proceeds to put forward a basic approach for procuring hardware and software for a DMS; designing the interfaces with external corporate computing systems such as EMS, GIS, OMS, and AMI; and implementing a complete solution.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Misleading Performance Claims in Parallel Computations

In a previous humorous note entitled 'Twelve Ways to Fool the Masses,' I outlined twelve common ways in which performance figures for technical computer systems can be distorted. In this paper and accompanying conference talk, I give a reprise of these twelve 'methods' and give some actual examples that have appeared in peer-reviewed literature in years past. I then propose guidelines for reporting performance, the adoption of which would raise the level of professionalism and reduce the level of confusion, not only in the world of device simulation but also in the larger arena of technical computing.

97 MATHEMATICS AND COMPUTING↗

Cybersecurity Assessment Methodology for International Safeguards

International nuclear safeguards are technical measures implemented by the International Atomic Energy Agency (IAEA) to verify the correctness and completeness of declarations made by States about their nuclear activities. The systems used to verify such activities include electronic and digital hardware and software components capable of data collection, processing, analysis, storage and transmission. Despite increasing efforts to protect digital systems against unauthorized access or attack through cybersecurity measures, these systems are not immune to cyber exploitation that could compromise their integrity or reliability. Previous versions of these systems did not include capabilities that exist today, such as BluetoothTM and GPS. The inclusion of these new capabilities, as well as new data processing and storage mechanisms, adds new attack vectors and opportunities for adversaries to exploit the devices that did not previously exist. As mentioned in the above referenced Cybersecurity for Safeguards study, cyber-domain vulnerabilities present risks to the equipment used to perform the international nuclear safeguards mission. The IAEA has produced guidance on the protection of nuclear facilities and their computer systems against cyber threats, but these documents do not specifically address the risks to safeguards or safeguards equipment. In response, the U.S. Department of Energy National Nuclear Security Administration (DOE/NNSA) Office of International Nuclear Safeguards/Safeguards Technology Development (NA-241) sponsored Sandia National Laboratories (Sandia, SNL) and the Idaho National Laboratory (Idaho, INL) to conduct a one-year study to evaluate cyber related vulnerabilities in safeguards equipment and develop recommendations for the mitigation of any identified risks.

97 MATHEMATICS AND COMPUTING↗

The Trinity Center of Excellence Co-Design Best Practices

Co-design between application developers and the vendors providing high-performance computing systems is essential to efficiently using current-generation HPC systems and shaping next-generation architectures. Application developers are faced with the challenge of effectively orchestrating many hardware threads and exploiting vector instructions, which can require code modifications. Will refactoring applications for current-generation systems apply to future-generation systems? Is there help available for this enormous task? Over the past 10 years, a partnership has evolved to address these issues. Centers of Excellence are mutually beneficial collaborations between application developers and vendors; vendors receive a better understanding of the needs of their users, and users receive a better understanding of the characteristics of the hardware, system software, and tools available to address their challenges. Lastly, this article describes the partnership between two vendors, Cray and Intel, and the application teams working together in the Trinity Center of Excellence.

97 MATHEMATICS AND COMPUTING↗

Thermodynamic properties and phase stability of the Ba-Bi system: A combined computational and experimental study

The thermodynamic properties and phase stability of the Ba-Bi system are investigated computationally and experimentally in the present work. The enthalpies of formation and the finite temperature thermodynamic properties of seven compounds are predicted by first-principles calculations based on density functional theory (DFT), indicating five compounds (BaBi 3 , Ba 11 Bi 10 , Ba 4 Bi 3 , Ba 5 Bi 3 , and Ba 2 Bi) to be stable. Phase relations at 773 K and 858 K with composition x Ba = 0.90 are established by isothermal annealing and powder X-ray diffraction (XRD) to clarify the previously observed phase transition at 796 K. The extremely low chemical activity of Ba in liquid for a wide range of temperatures and compositions indicates very strong short-range ordering in the liquid phase which is modeled in the present work by introducing the Ba 4 Bi 3 and BaBi 3 associates in the liquid phase. Both thermodynamic and phase equilibrium data are then used to evaluate the model parameters in Gibbs energy functions of the five stable compounds and three solution phases of liquid, bcc, and rhombohedral phases by the CALPHAD (CALculation of PHAse Diagram) technique. Here the present work shows that the Ba-Bi system consists of three eutectic reactions, two peritectic reactions, one peritectoid reaction, and two congruent reactions, as well as that the concentrations of associates are very high in the liquid phase with very low concentration of atomic Ba, which provides the fundamental understanding as to why Bi can be used to remove Ba ions from molten salt solutions.

36 MATERIALS SCIENCE↗

System and method for optimizing hydrocarbon production from subsurface reservoirs

A method is described for subsurface hydrocarbon reservoir characterization including receiving a time-lapse electromagnetic (EM) dataset and a flow dataset; inverting the time-lapse EM dataset using a parametric inversion that models steel well casings to determine a volume of fluid-changed reservoir; inverting the time-lapse EM dataset and the flow dataset using a joint inversion that honors the volume of the fluid-changed reservoir to determine relative permeability and capillary pressure; and characterizing flow characteristics in the volume of the fluid-changed reservoir. The method may be executed by a computer system.

Hoversten, Gary Michael↗

System and method for the direct calorimetric measurement of laser absorptivity of materials

A method and system for calorimetrically measuring the temperature-dependent absorptivity of a homogeneous material dimensioned to be thin and flat with a predetermined uniform thickness and a predetermined porosity. The system includes a material holder adapted to support and thermally isolate the material to be measured, an irradiation source adapted to uniformly irradiate the material with a beam of electromagnetic radiation, and an irradiation source controller adapted to control the irradiation source to uniformly heat the material during a heating period, followed by a cooling period when the material is not irradiated. A thermal sensor measures temperature of the material during the heating and cooling periods, and a computing system first calculates temperature-dependent convective and radiative thermal losses of the material based on the measured temperature of the material during the cooling period when beam intensity is zero, followed by calculation of the temperature-dependent absorptivity of the material based on the temperature-dependent convective and radiative thermal losses determined from the cooling period.

Rubenchik, Alexander↗

Towards an Abstraction-Friendly Programming Model for High Productivity and High Performance Computing

General purpose languages, such as C++, permit the construction of various high-level abstractions to hide redundant, low-level details and accelerate programming productivity. Example abstractions include functions, data structures, classes, templates and so on. However, the use of abstractions significantly impedes static code analyses and optimizations, including parallelization, applied to the abstraction's complex implementations. As a result, there is a common perception that performance is inversely proportional to the level of abstraction. On the other hand, programming large scale, possibly heterogeneous high-performance computing systems is notoriously difficult, and programmers are less likely to abandon the help from high level abstractions when solving real-world, complex problems. Therefore, the need for programming models balancing both programming productivity and execution performance has reached a new level of criticality.

97 MATHEMATICS AND COMPUTING↗

Sensitivities and Uncertainties Related to Numerics and Building Features in Urban Modeling

Oak Ridge National Laboratory (ORNL) has been engaged in the development and testing of a computational system that would use a grid of activation foil detectors to provide postdetonation forensic information from a nuclear device detonation. ORNL has developed a high-performance, three-dimensional (3-D) deterministic radiation transport code called Denovo. Denovo solves the multigroup discrete ordinates (SN) equations and can output 3-D data in a platform-independent format that can be efficiently analyzed using parallel, high-performance visualization tools. To evaluate the sensitivities and uncertainties associated with the deterministic computational method numerics, a numerical study on the New York City Times Square model was conducted using Denovo. In particular, the sensitivities and uncertainties associated with various components of the calculational method were systematically investigated, including (a) the Legendre polynomial expansion order of the scattering cross sections, (b) the angular quadrature, (c) multigroup energy binning, (d) spatial mesh sizes, (e) the material compositions of the building models, (f) the composition of the foundations upon which the buildings rest (e.g., ground, concrete, or asphalt), and (g) the amount of detail included in the building models. Although Denovo may calculate the idealized model well, there may be uncertainty in the results because of slight departures of the above-named parameters from those used in the idealized calculations. Fluxes and activities at selected locations from perturbed calculations are compared with corresponding values from the idealized or base case to determine the sensitivities associated with specified parameter changes. Results indicate that uncertainties related to numerics can be controlled by using higher fidelity models, but more work is needed to control the uncertainties related to the model.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗