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 1,063 records · Page 59

Multi-Line Superconducting Waveguides Based on YBCO-on-Kapton Technology

Coplanar (with the ground) and stripline 25 cm long waveguides are manufactured from the YBCO-Kapton material. The waveguides are intended as the key components of a scalable signal delivery for large quantum computing systems and detectors. The waveguide is coupled with an integrated power divider that replaces the standard attenuator. The divider is designed to return most of the power to the previous thermalization stage. The method is projected to reduce the active dissipation by ≈10. We investigate the effect of internal strain in YBCO layer on the device's mechanical stability. Here, we show that adhesives with high stiffness are essential for the reliability of YBCO-Kapton devices.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

7X performance results - final report : ASCI Red vs Red Storm.

The goal of the 7X performance testing was to assure Sandia National Laboratories, Cray Inc., and the Department of Energy that Red Storm would achieve its performance requirements which were defined as a comparison between ASCI Red and Red Storm. Our approach was to identify one or more problems for each application in the 7X suite, run those problems at multiple processor sizes in the capability computing range, and compare the results between ASCI Red and Red Storm. The first part of this report describes the two computer systems, the applications in the 7X suite, the test problems, and the results of the performance tests on ASCI Red and Red Storm. During the course of the testing on Red Storm, we had the opportunity to run the test problems in both single-core mode and dual-core mode and the second part of this report describes those results. Finally, we reflect on lessons learned in undertaking a major head-to-head benchmark comparison.

99 GENERAL AND MISCELLANEOUS↗

Phase II Nevada Water Resources Data, Modeling, and Visualization (DMV) Center (Final Report)

Water is unquestionably a critical resource throughout the United States. In the semi-arid west -- an area stressed by increase in human population and sprawl of the built environment -- water is the most important limiting resource. Crucially, science must understand factors that affect availability and distribution of water. To sustain growing consumptive demand, science needs to translate understanding into reliable and robust predictions of availability under weather conditions that could be average but might be extreme. These predictions are needed to support current and long-term planning. Similar to the role of weather forecast and climate prediction, water prediction over short and long temporal scales can contribute to resource strategy, governmental policy and municipal infrastructure decisions, which are arguably tied to the natural variability and unnatural change to climate. Change in seasonal and annual temperature, precipitation, snowmelt, and runoff affect the distribution of water over large temporal and spatial scales, which impact the risk of flooding and the groundwater recharge. Anthropogenic influences and impacts increase the complexity and urgency of the challenge. The goal of this project has been to develop a decision support framework of data acquisition, digital modeling, and 3D visualization. This integrated framework consists of tools for compiling, discovering and projecting our understanding of processes that control the availability and distribution of water. The framework is intended to support the analysis of the complex interactions between processes that affect water supply, from controlled availability to either scarcity or deluge. The developed framework enables DRI to promote excellence in water resource management, particularly within the Lake Tahoe basin. In principle, this framework could be replicated for other watersheds throughout the United States. Phase II of this project builds upon the research conducted during Phase I, in which the hydrologic framework was investigated and the development initiated. Phase II concentrates on practical implementation of the earlier work but emphasizes applications to the hydrology of the Lake Tahoe basin. Phase 1 efforts have been refined and extended by creating a toolset for geographic information systems (GIS) that is usable for disparate types of geospatial and geo-referenced data. The toolset is intended to serve multiple users for a variety of applications. The web portal for internet access to hydrologic and remotely sensed product data, prototyped in Phase I, has been significantly enhanced. The portal provides high performance access to LANDSAT-derived data using techniques developed during the course of the project. The portal is interactive, and supports the geo-referenced display of hydrologic information derived from remotely sensed data, such as various vegetative indices used to calculate water consumption. The platform can serve both internal and external constituencies using inter-operating infrastructure that spans both sides of the DRI firewall. The platform is intended grow its supported data assets and to serve as a template for replication to other geographic areas. An unanticipated development during the project was the use of ArcGIS software on a new computer system, called the IBM PureSytems, and the parallel use of the systems for faster, more efficient image processing. Additional data, independent of the portal, was collected within the Sagehen basin and provides detailed information regarding the processes that control hydrologic responses within mountain watersheds. The newly collected data include elevation, evapotranspiration, energy balance and remotely sensed snow-pack data. A Lake Tahoe basin hydrologic model has been developed, in part to help predict the hydrologic impacts of climate change. The model couples both the surface and subsurface hydrology, with the two components having been independently calibrated. Results from the coupled simulations involving both surface water and groundwater processes show that it is possible to fairly accurately simulate lake effects and water budget variables over a wide range of dry and wet cycles in the historical record. The Lake Tahoe basin is representative of the hydrology, topography and climate throughout the Sierra Nevada Range, and the entire model development is prototypical of the efforts required to replicate the decision support framework to other locales. The Lake Tahoe model in particular, could allow water managers to evaluate more accurately components of the water budget (ET, runoff, groundwater, etc) and to answer important questions regarding water resources in northern Nevada. This report discusses the geographic scale and the hydrologic complexity of the calibrated model developed as part of this project, as well as simulation results for historical and future climate projects To enable human-driven data exploration and discovery, de novo software for a globalized rendering module that extends the capability of our evolving custom visualization engine from Phase I (called SMEngine) has been developed. The new rendering component, called Horizon, supports terrain rendering capable of displaying and interrogating both remotely sensed and modeled data. The development of Horizon necessitated adaptation of the visualization engine to allow extensible integration of components such as the global rendering module and support for associated features. The resulting software is general in its GIS capability, but a specific Lake Tahoe visualization application suitable for immersive decision support in the DRIVE6 virtual reality facility has been developed. During the development, various features to enhance the value of the visualization experience were explored, including the use of hyperspectral image overlays. An over-arching goal of the visualization aspect of the project has been to develop and demonstrate the CAVE (CAVE Automatic Virtual Environment) as a practical tool for hydrologic research.

54 ENVIRONMENTAL SCIENCES↗

The Portals 4.2 Network Programming Interface

This report presents a specification for the Portals 4 network programming interface. Portals 4 is intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Portals 4 is well suited to massively parallel processing and embedded systems. Portals 4 represents an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Sandia's Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4 is targeted to the next generation of machines employing advanced network interface architectures that support enhanced offload capabilities.

97 MATHEMATICS AND COMPUTING↗

The Portals 4.0.2 Networking Programming Interface

This report presents a specification for the Portals 4 network programming interface. Portals 4 is intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Portals 4 is well suited to massively parallel processing and embedded systems. Portals 4 represents an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Sandia's Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4 is targeted to the next generation of machines employing advanced network interface architectures that support enhanced offload capabilities.

97 MATHEMATICS AND COMPUTING↗

List based prefetch

A list prefetch engine improves a performance of a parallel computing system. The list prefetch engine receives a current cache miss address. The list prefetch engine evaluates whether the current cache miss address is valid. If the current cache miss address is valid, the list prefetch engine compares the current cache miss address and a list address. A list address represents an address in a list. A list describes an arbitrary sequence of prior cache miss addresses. The prefetch engine prefetches data according to the list, if there is a match between the current cache miss address and the list address.

97 MATHEMATICS AND COMPUTING↗

List based prefetch

A list prefetch engine improves a performance of a parallel computing system. The list prefetch engine receives a current cache miss address. The list prefetch engine evaluates whether the current cache miss address is valid. If the current cache miss address is valid, the list prefetch engine compares the current cache miss address and a list address. A list address represents an address in a list. A list describes an arbitrary sequence of prior cache miss addresses. The prefetch engine prefetches data according to the list, if there is a match between the current cache miss address and the list address.

97 MATHEMATICS AND COMPUTING↗

H5hut: A High-Performance I/O Library for Particle-based Simulations

Particle-based simulations running on large high-performance computing systems over many time steps can generate an enormous amount of particle- and field-based data for post-processing and analysis. Achieving high-performance I/O for this data, effectively managing it on disk, and interfacing it with analysis and visualization tools can be challenging, especially for domain scientists who do not have I/O and data management expertise. We present the H5hut library, an implementation of several data models for particle-based simulations that encapsulates the complexity of HDF5 and is simple to use, yet does not compromise performance.

97 MATHEMATICS AND COMPUTING↗

NLO QCD corrections to Drell-Yan processes in the SANC framework

NLO QCD corrections to charged and neutral current Drell-Yan processes are computed with help of the computer system SANC. At the partonic level both quark-antiquark and quark-gluon scattering channels are taken into account. Subtraction of collinear singularities in the massive quark scheme is compared with the one in the MS-bar scheme. Numerical results at the hadronic level are received for the LHC conditions with help of Monte-Carlo integrators and event generator programs based on the standard SANC modules. Comparison with analogous results of the MCFM package is shown.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Case Study of Truncated Electrostatics for Simulation of Polyelectrolyte Brushes on GPU Accelerators

Numerous issues have disrupted the trend for increasing computational performance with faster CPU clock frequencies. In order to exploit the potential performance of new computers, it is becoming increasingly desirable to re-evaluate computational physics methods and models with an eye towards towards approaches that allow for increased concurrency and data locality. The evaluation of long-range Coulombic interactions is a common bottleneck for molecular dynamics simulations. Enhanced truncation approaches have been proposed as an alternative method and are particularly well suited for many-core architectures and GPUs due to the inherent fine-grain parallelism that can be exploited. In this paper, we compare efficient truncation-based approximations to evaluation of electrostatic forces with the more traditional particle-particle particle-mesh (P3M) method for molecular dynamics simulation of polyelectrolyte brush layers. We show that with the use of GPU accelerators, large parallel simulations using P3M can be greater than 3 times faster due to a reduction in the mesh-size required. Alternatively, using a truncation-based scheme can improve performance even further. This approach can be up to 3.9 times faster than GPU-accelerated P3M for many polymer systems and results in accurate calculation of shear velocities and disjoining pressures for brush layers. For configurations with highly non-uniform charge distributions, however, we find that it is more efficient to use P3M; for these systems, computationally efficient parameterizations of the truncation-based approach do not produce accurate counterion density profiles or brush morphologies.

Nguyen, Trung D↗

The Portals 4.3 Network Programming Interface

This report presents a specification for the Portals 4 network programming interface. Portals 4 is intended to allow scalable, high-performance network communication between nodes of a parallel computing system. Portals 4 is well suited to massively parallel processing and embedded systems. Portals 4 represents an adaption of the data movement layer developed for massively parallel processing platforms, such as the 4500-node Intel TeraFLOPS machine. Sandia's Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4 is targeted to the next generation of machines employing advanced network interface architectures that support enhanced offload capabilities.

97 MATHEMATICS AND COMPUTING↗

ASA-FTL: An adaptive separation aware flash translation layer for solid state drives

Here, the flash-memory based Solid State Drive (SSD) presents a promising storage solution for increasingly critical data-intensive applications due to its low latency (high throughput), high bandwidth, and low power consumption. Within an SSD, its Flash Translation Layer (FTL) is responsible for exposing the SSD’s flash memory storage to the computer system as a simple block device. The FTL design is one of the dominant factors determining an SSD’s lifespan and performance. To reduce the garbage collection overhead and deliver better performance, we propose a new, low-cost, adaptive separation-aware flash translation layer (ASA-FTL) that combines sampling, data clustering and selective caching of recency information to accurately identify and separate hot/cold data while incurring minimal overhead. We use sampling for light-weight identification of separation criteria, and our dedicated selective caching mechanism is designed to save the limited RAM resource in contemporary SSDs. Using simulations of ASA-FTL with both real-world and synthetic workloads, we have shown that our proposed approach reduces the garbage collection overhead by up to 28% and the overall response time by 15% compared to one of the most advanced existing FTLs. We find that the data clustering using a small sample size provides significant performance benefit while only incurring a very small computation and memory cost. In addition, our evaluation shows that ASA-FTL is able to adapt to the changes in the access pattern of workloads, which is a major advantage comparing to existing fixed data separation methods.

97 MATHEMATICS AND COMPUTING↗

Validation of a method for in vivo 3D dose reconstruction for IMRT and VMAT treatments using on-treatment EPID images and a model-based forward-calculation algorithm

Purpose: Radiation treatments are trending toward delivering higher doses per fraction under stereotactic radiosurgery and hypofractionated treatment regimens. There is a need for accurate 3D in vivo patient dose verification using electronic portal imaging device (EPID) measurements. This work presents a model-based technique to compute full three-dimensional patient dose reconstructed from on-treatment EPID portal images (i.e., transmission images). Methods: EPID dose is converted to incident fluence entering the patient using a series of steps which include converting measured EPID dose to fluence at the detector plane and then back-projecting the primary source component of the EPID fluence upstream of the patient. Incident fluence is then recombined with predicted extra-focal fluence and used to calculate 3D patient dose via a collapsed-cone convolution method. This method is implemented in an iterative manner, although in practice it provides accurate results in a single iteration. The robustness of the dose reconstruction technique is demonstrated with several simple slab phantom and nine anthropomorphic phantom cases. Prostate, head and neck, and lung treatments are all included as well as a range of delivery techniques including VMAT and dynamic intensity modulated radiation therapy (IMRT). Results: Results indicate that the patient dose reconstruction algorithm compares well with treatment planning system computed doses for controlled test situations. For simple phantom and square field tests, agreement was excellent with a 2%/2 mm 3D chi pass rate ≥98.9%. On anthropomorphic phantoms, the 2%/2 mm 3D chi pass rates ranged from 79.9% to 99.9% in the planning target volume (PTV) region and 96.5% to 100% in the low dose region (>20% of prescription, excluding PTV and skin build-up region). Conclusions: An algorithm to reconstruct delivered patient 3D doses from EPID exit dosimetry measurements was presented. The method was applied to phantom and patient data sets, as well as for dynamic IMRT and VMAT delivery techniques. Results indicate that the EPID dose reconstruction algorithm presented in this work is suitable for clinical implementation.

60 APPLIED LIFE SCIENCES↗

Release Notes for Whisper-1.1

Whisper is a statistical analysis package developed in 2014 to support nuclear criticality safety (NCS) validation [1-3]. It uses the sensitivity profile data for an application as computed by MCNP6 [4-6] along with covariance files [7,8] for the nuclear data to determine a baseline upper-subcritical-limit (USL) for the application. Whisper version 1.0 was first developed and used at LANL in 2014 [3]. During 2015-2016, Whisper was updated to version 1.1 [9] and is to be included with the upcoming release of MCNP6.2. This document describes the Whisper-1.1 package that will be included with the MCNP6.2 release during 2017. Specific details are provided on the computer systems supported, the software quality assurance (SQA) procedures, installation, and testing. This document does not address other important topics, such as the importance of sensitivity-uncertainty (SU) methods to NCS validation, the theory underlying SU methodology, tutorials on the usage of MCNP-Whisper, practical approaches to using SU methodology to support and extend traditional validation, etc. There are over 50 documents included with Whisper-1.1 and available in the MCNP Reference Collection on the MCNP website (mcnp.lanl.gov) that address all of those topics and more. In this document, however, a complete bibliography of relevant MCNP-Whisper references is provided.

97 MATHEMATICS AND COMPUTING↗

The Portals 4.1 Network Programming Interface

This report presents a specification for the Portals 4 networ k programming interface. Portals 4 is intended to allow scalable, high-performance network communication betwee n nodes of a parallel computing system. Portals 4 is well suited to massively parallel processing and embedded syste ms. Portals 4 represents an adaption of the data movement layer developed for massively parallel processing platfor ms, such as the 4500-node Intel TeraFLOPS machine. Sandia's Cplant cluster project motivated the development of Version 3.0, which was later extended to Version 3.3 as part of the Cray Red Storm machine and XT line. Version 4 is tar geted to the next generation of machines employing advanced network interface architectures that support enh anced offload capabilities.

97 MATHEMATICS AND COMPUTING↗

Scalable data management, analysis and visualization (SDAV) Institute. Final Scientific/Technical Report

The purpose of the SDAV institute is to provide tools and expertise in scientific data management, analysis, and visualization to DOE’s application scientists. Our goal is to actively work with application teams to assist them in achieving breakthrough science, and to provide technical solutions in the data management, analysis, and visualization regimes that are broadly used by the computational science community. Over the last 5 years members of our institute worked directly with application scientists and DOE leadership-class facilities to assist them by applying the best tools and technologies at our disposal. We also enhanced our tools based on input from scientists on their needs. Many of the applications we have been working with are based on connections with scientists established in previous years. However, we contacted additional scientists though our outreach activities, as well as engaging application teams running on leading DOE computing systems. Our approach is to employ an evolutionary development and deployment process: first considering the application of existing tools, followed by the customization necessary for each particular application, and then the deployment in real frameworks and infrastructures. The institute is organized into three areas, each with area leaders, who keep track of progress, engagement of application scientists, and results. The areas are: (1) Data Management, (2) Data Analysis, and (3) Visualization. Kitware has been involved in the Visualization area. This report covers Kitware’s contributions over the last 5 years (February 2012 – February 2017). For details on the work performed by the SDAV institute as a whole, please see the SDAV final report.

97 MATHEMATICS AND COMPUTING↗

Global Arrays Parallel Programming Toolkit

The two predominant classes of programming models for parallel computing are distributed memory and shared memory. Both shared memory and distributed memory models have advantages and shortcomings. Shared memory model is much easier to use but it ignores data locality/placement. Given the hierarchical nature of the memory subsystems in modern computers this characteristic can have a negative impact on performance and scalability. Careful code restructuring to increase data reuse and replacing fine grain load/stores with block access to shared data can address the problem and yield performance for shared memory that is competitive with message-passing. However, this performance comes at the cost of compromising the ease of use that the shared memory model advertises. Distributed memory models, such as message-passing or one-sided communication, offer performance and scalability but they are difficult to program. The Global Arrays toolkit attempts to offer the best features of both models. It implements a shared-memory programming model in which data locality is managed by the programmer. This management is achieved by calls to functions that transfer data between a global address space (a distributed array) and local storage. In this respect, the GA model has similarities to the distributed shared-memory models that provide an explicit acquire/release protocol. However, the GA model acknowledges that remote data is slower to access than local data and allows data locality to be specified by the programmer and hence managed. GA is related to the global address space languages such as UPC, Titanium, and, to a lesser extent, Co-Array Fortran. In addition, by providing a set of data-parallel operations, GA is also related to data-parallel languages such as HPF, ZPL, and Data Parallel C. However, the Global Array programming model is implemented as a library that works with most languages used for technical computing and does not rely on compiler technology for achieving parallel efficiency. It also supports a combination of task- and data-parallelism and is available as an extension of the message passing (MPI) model. The GA model exposes to the programmer the hierarchical memory of modern high-performance computer systems, and by recognizing the communication overhead for remote data transfer, it promotes data reuse and locality of reference. Virtually all the scalable architectures possess non-uniform memory access characteristics that reflect their multi-level memory hierarchies. These hierarchies typically comprise processor registers, multiple levels of cache, local memory, and remote memory. Over time, both the number of levels and the cost (in processor cycles) of accessing deeper levels has been increasing. It is important for any scalable programming model to address memory hierarchy since it is critical to the efficient execution of scalable applications.

ARMCI↗

High-bandwidth density silicon photonic resonators for energy-efficient optical interconnects

The growth of artificial intelligence applications demands ever larger and more complex deep learning models, dominating today's—and tomorrow's—data center and high-performance computing systems. While traditional electronics are failing to keep pace with application demands, silicon photonic (SiPh) interconnects have emerged as a necessary technology to support these systems. SiPh-driven wavelength-division multiplexing (WDM) offers a particularly promising path toward supporting incredibly high-aggregate link bandwidth in a compact and efficient form factor. One of the basic building blocks of these integrated WDM interconnects is the SiPh resonator. Their inherent wavelength selectivity and compact footprint allow for efficient data transmission multiplexed across dozens of carrier wavelengths. Used as add-drop (AD) filters, SiPh resonators are critical to constructing integrated tunable wavelength-selective optical circuit switches as well as for demultiplexing the different carrier wavelengths toward independent wavelength-insensitive photodiodes in a dense wavelength-division multiplexing receiver. Resonators in the all-pass (AP) configuration are widespread as well, allowing for wavelength-selective modulation to drive aggregate link bandwidths far beyond the individual channel data rate. Unlike SiPh Mach–Zehnder modulators (MZM), resonant modulators can be driven using low, complementary metal-oxide-semiconductor drive voltages, allowing for tight co-integration between photonic integrated circuits, fabricated with larger process node technologies, and electronic integrated circuits, designed to exploit the advantages of the latest node. To push toward practical peta-scale interconnects, a comprehensive review of SiPh resonators is required, addressing bottlenecks and design constraints at both the architecture and device levels. We first describe the predominant integrated link architectures and identify their limits. We then discuss the device-level design considerations that can be made for both AD and AP configuration resonators to overcome the system level limits with novel resonator device designs. Analytical models and numerical simulation of resonators are validated by experimental measurement of devices fabricated in a commercial 300-mm foundry, showing a clear path toward volume manufacturing. The demonstrated resonant modulators and filters support the feasibility of increasing the aggregate bandwidth of resonator-driven SiPh interconnects into the peta-scale regime.

42 ENGINEERING↗