Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed memory”

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 883 records · Page 49

A Portable MPI-Based Parallel Vector Template Library

This paper discusses the design and implementation of a polymorphic collection library for distributed address-space parallel computers. The library provides a data-parallel programming model for C + + by providing three main components: a single generic collection class, generic algorithms over collections, and generic algebraic combining functions. Collection elements are the fourth component of a program written using the library and may be either of the built-in types of c or of user-defined types. Many ideas are borrowed from the Standard Template Library (STL) of C++, although a restricted programming model is proposed because of the distributed address-space memory model assumed. Whereas the STL provides standard collections and implementations of algorithms for uniprocessors, this paper advocates standardizing interfaces that may be customized for different parallel computers. Just as the STL attempts to increase programmer productivity through code reuse, a similar standard for parallel computers could provide programmers with a standard set of algorithms portable across many different architectures. The efficacy of this approach is verified by examining performance data collected from an initial implementation of the library running on an IBM SP-2 and an Intel Paragon.

Sheffler, Thomas J.↗

Position Paper - pFLogger: The Parallel Fortran Logging framework for HPC Applications

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or logger) similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Fortran↗

POSITION PAPER - pFLogger: The Parallel Fortran Logging Framework for HPC Applications

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or 'logger') similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger - a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Clune, Thomas L.↗

pFlogger: The Parallel Fortran Logging Utility

In the context of high performance computing (HPC), software investments in support of text-based diagnostics, which monitor a running application, are typically limited compared to those for other types of IO. Examples of such diagnostics include reiteration of configuration parameters, progress indicators, simple metrics (e.g., mass conservation, convergence of solvers, etc.), and timers. To some degree, this difference in priority is justifiable as other forms of output are the primary products of a scientific model and, due to their large data volume, much more likely to be a significant performance concern. In contrast, text-based diagnostic content is generally not shared beyond the individual or group running an application and is most often used to troubleshoot when something goes wrong. We suggest that a more systematic approach enabled by a logging facility (or 'logger)' similar to those routinely used by many communities would provide significant value to complex scientific applications. In the context of high-performance computing, an appropriate logger would provide specialized support for distributed and shared-memory parallelism and have low performance overhead. In this paper, we present our prototype implementation of pFlogger - a parallel Fortran-based logging framework, and assess its suitability for use in a complex scientific application.

Clune, Tom↗

Locating node of named data elements in coordination namespace

An approach is disclosed that locates a named data element by a local node. A name corresponding to the named data element is received, the named data element exists in a Coordination Namespace allocated in a memory area that is distributed amongst a set of nodes that include the local node and remote nodes. A predicted node identifier is received and then the named data element is requested from the predicted node based on the predicted node identifier.

97 MATHEMATICS AND COMPUTING↗

A method to compute SEU fault probabilities in memory arrays with error correction

With the increasing packing densities in VLSI technology, Single Event Upsets (SEU) due to cosmic radiations are becoming more of a critical issue in the design of space avionics systems. In this paper, a method is introduced to compute the fault (mishap) probability for a computer memory of size M words. It is assumed that a Hamming code is used for each word to provide single error correction. It is also assumed that every time a memory location is read, single errors are corrected. Memory is read randomly whose distribution is assumed to be known. In such a scenario, a mishap is defined as two SEU's corrupting the same memory location prior to a read. The paper introduces a method to compute the overall mishap probability for the entire memory for a mission duration of T hours.

Gercek, Gokhan↗

Fast entanglement distribution with atomic ensembles and fluorescent detection

Quantum repeaters based on atomic ensemble quantum memories are promising candidates for achieving scalable distribution of entanglement over long distances. Recently, important experimental progress has been made toward their implementation. However, the entanglement rates and scalability of current approaches are limited by relatively low retrieval and single-photon detector efficiencies. We propose a scheme which makes use of fluorescent detection of stored excitations to significantly increase the efficiency of connection and hence the rate. Practical performance and possible experimental realizations of the new protocol are discussed.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Fault-tolerant computer study

A set of building block circuits is described which can be used with commercially available microprocessors and memories to implement fault tolerant distributed computer systems. Each building block circuit is intended for VLSI implementation as a single chip. Several building blocks and associated processor and memory chips form a self checking computer module with self contained input output and interfaces to redundant communications buses. Fault tolerance is achieved by connecting self checking computer modules into a redundant network in which backup buses and computer modules are provided to circumvent failures. The requirements and design methodology which led to the definition of the building block circuits are discussed.

Rennels, D. A.↗

NUMA-Aware Thread Scheduling for Big Data Transfers over Terabits Network Infrastructure

The evergrowing trend of big data has led scientists to share and transfer the simulation and analytical data across the geodistributed research and computing facilities. However, the existing data transfer frameworks used for data sharing lack the capability to adopt the attributes of the underlying parallel file systems (PFS). LADS (Layout-Aware Data Scheduling) is an end-to-end data transfer tool optimized for terabit network using a layout-aware data scheduling via PFS. However, it does not consider the NUMA (Nonuniform Memory Access) architecture. In this paper, we propose a NUMA-aware thread and resource scheduling for optimized data transfer in terabit network. First, we propose distributed RMA buffers to reduce memory controller contention in CPU sockets and then schedule the threads based on CPU socket and NUMA nodes inside CPU socket to reduce memory access latency. We design and implement the proposed resource and thread scheduling in the existing LADS framework. Experimental results showed from 21.7% to 44% improvement with memory-level optimizations in the LADS framework as compared to the baseline without any optimization.

97 MATHEMATICS AND COMPUTING↗

On the memory attribution problem: A solution and case study using MPI

As parallel applications running on large–scale computing systems become increasingly memory constrained, the ability to attribute memory usage to the various components of the application is becoming increasingly important. We present the design and implementation of memnesia, a novel memory usage profiler for parallel and distributed message–passing applications. Our approach captures both application– and message–passing library–specific memory usage statistics from unmodified binaries dynamically linked to a message–passing communication library. Using microbenchmarks and proxy applications, we evaluated our profiler across three Message Passing Interface (MPI) implementations and two hardware platforms. Furthermore, the results show that our approach and the corresponding implementation can accurately quantify memory resource usage as a function of time, scale, communication workload, and software or hardware system architecture, clearly distinguishing between application and MPI library memory usage at a per–process level. With this new capability, we show that job size, communication workload, and hardware/software architecture influence peak runtime memory usage. In practice, this tool provides a potentially valuable source of information for application developers seeking to measure and optimize memory usage.

97 MATHEMATICS AND COMPUTING↗

Cosmic string loop distribution on all length scales and at any redshift

We analytically derive the expected number density distribution of Nambu-Goto cosmic string loops at any redshift soon after the time of string formation to today. Our approach is based on the Polchinski-Rocha model of loop formation from long strings which we adjust to fit numerical simulations and complement by a phenomenological modelling of gravitational backreaction. Cosmological evolution drives the loop distribution towards scaling on all length scales in both the radiation and matter era. Memory of any reasonable initial loop distribution in the radiation era is shown to be erased well before Big Bang Nucleosynthesis. In the matter era, the loop distribution reaches full scaling, up to some residual loops from the radiation era which may be present for extremely low string tension. Finally, the number density of loops below the gravitational cutoff is shown to be scale independent, proportional to a negative power of the string tension and insensitive to the details of the backreaction modelling. As an application, we show that the energy density parameter of loops today cannot exceed 10{sup −5} for currently allowed string tension values, while the loop number density cannot be less than 10{sup −6} per Mpc{sup 3}. Our result should provide a more robust basis for studying the cosmological consequences of cosmic string loops.

79 ASTRONOMY AND ASTROPHYSICS↗

ac Stark gradient echo memory in cold atoms

The burgeoning fields of quantum computing and quantum key distribution have created a demand for a quantum memory. The gradient echo memory scheme is a quantum memory candidate for light storage that can boast efficiencies approaching unity, as well as the flexibility to work with either two- or three-level atoms. The key to this scheme is the frequency gradient that is placed across the memory. Currently, the three-level implementation uses a Zeeman gradient and warm atoms. In this article we model an alternate gradient-creation mechanism--the ac Stark effect--to provide an improvement in the flexibility of gradient-creation and field-switching times. We propose this scheme in concert with a move to cold atoms ({approx_equal}1 mK). These temperatures would increase the storage times possible, and the small ensemble volumes would enable large ac Stark shifts with reasonable laser power. We find that memory bandwidths on the order of MHz can be produced with experimentally achievable laser powers and trapping volumes, with high precision in gradient creation and switching times on the order of nanoseconds possible. By looking at the different decoherence mechanisms present in this system, we determine that coherence times on the order of tens of milliseconds are possible, as are delay-bandwidth products of approximately 50 and efficiencies over 90%.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Cometary memory of interstellar aluminum

It is shown that the distribution of refractory metals in a comet-nucleus drill core carries a chemical memory quite distinct from that of volatiles. Using aluminum as an example, it is demonstrated that very refractory structures, either grain cores or refractory aggregates of cores, must be much older than the volatile component. It is argued that isotopic anomalies are specifically associated with aluminum. An evolutionary model capable of rationalizing the interstellar gas depletions of Al and Mg is advocated. The distribution of Al in comets is shown to be crucial to understanding the origin of comets and of the solar system.

Clayton, Donald D.↗

Effect of local surface potential distribution on its relaxation in polycrystalline ferroelectric films.

We have studied the effect of local surface potential distribution on its relaxation in the polycrystalline ferroelectric thin films. A lower surface potential region, i.e., potential pit, is generated near a grain boundary. The deep potential pit has a faster relaxation than the area far away from the potential pit due to the acceleration of the screen charge draining near the grain boundary and the domains formed by applying higher voltage have a faster relaxation due to the larger gradient of screen charge distribution. In addition, the surface potential and its relaxation depend on the sign of applying voltage. The result shows that the surface potential distribution may influence significantly to the reliability of bit signal on the memory devices.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Multiple-stable anisotropic magnetoresistance memory in antiferromagnetic MnTe

Commercial magnetic memories rely on the bistability of ordered spins in ferromagnetic materials. Recently, experimental bistable memories have been realized using fully compensated antiferromagnetic metals. Here we demonstrate a multiple-stable memory device in epitaxial MnTe, an antiferromagnetic counterpart of common II–VI semiconductors. Favourable micromagnetic characteristics of MnTe allow us to demonstrate a smoothly varying zero-field antiferromagnetic anisotropic magnetoresistance (AMR) with a harmonic angular dependence on the writing magnetic field angle, analogous to ferromagnets. The continuously varying AMR provides means for the electrical read-out of multiple-stable antiferromagnetic memory states, which we set by heat-assisted magneto-recording and by changing the writing field direction. The multiple stability in our memory is ascribed to different distributions of domains with the Ne´el vector aligned along one of the three magnetic easy axes. The robustness against strong magnetic field perturbations combined with the multiple stability of the magnetic memory states are unique properties of antiferromagnets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

High Level Synthesis of RDF Queries for Graph Analytics

In this paper we present a set of techniques that enable the synthesis of efficient custom accelerators for memory intensive, irregular applications. To address irregular applications challenges (large memory footprints, unpredictable fine- grained data accesses, and high synchronization intensity), and exploit their opportunities (thread level parallelism, memory level parallelism), we propose a novel accelerator design which take advantage of an adaptive and Distributed Controller (DC) architecture, and a Memory Interface (MI) that supports parallel memory subsystems. Among the multitude of algorithms that may benefit from our solution, we focus on the acceleration of graph analytics applications, and in particular, on the syn- thesis of SPARQL queries on Resource Description Framework (RDF) databases. We achieve this objective by incorporating the synthesis techniques into Bambu, an Open Source high- level synthesis tools, and interfacing the system with GEMS, the Graph database Engine for Multithreaded Systems. The front- end of GEMS generates optimized C implementations of the input queries, modeled as pattern matching routines, which are then automatically synthesized by Bambu. We validate our approach synthesizing several SPARQL queries from the Lehigh University Benchmark (LUBM).

HLS, FPGA, Convey, RDF, GEMS, Memory-intensive,↗

Ambipolar organic thin-film transistor-based nano-floating-gate nonvolatile memory

An ambipolar organic thin-film transistor-based nano-floating-gate nonvolatile memory was demonstrated, with discrete distributed gold nanoparticles, tetratetracontane (TTC), pentacene as the floating-gate layer, tunneling layer, and active layer, respectively. The electron traps at the TTC/pentacene interface were significantly suppressed, which resulted in an ambipolar operation in present memory. As both electrons and holes were supplied in the channel and trapped in the floating-gate by programming/erasing operations, respectively, i.e., one type of charge carriers was used to overwrite the other, trapped, one, a large memory window, extending on both sides of the initial threshold voltage, was realized.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Inferring Soil Moisture Memory from Streamflow Observations Using a Simple Water Balance Model

Soil moisture is known for its integrative behavior and resulting memory characteristics. Soil moisture anomalies can persist for weeks or even months into the future, making initial soil moisture a potentially important contributor to skill in weather forecasting. A major difficulty when investigating soil moisture and its memory using observations is the sparse availability of long-term measurements and their limited spatial representativeness. In contrast, there is an abundance of long-term streamflow measurements for catchments of various sizes across the world. We investigate in this study whether such streamflow measurements can be used to infer and characterize soil moisture memory in respective catchments. Our approach uses a simple water balance model in which evapotranspiration and runoff ratios are expressed as simple functions of soil moisture; optimized functions for the model are determined using streamflow observations, and the optimized model in turn provides information on soil moisture memory on the catchment scale. The validity of the approach is demonstrated with data from three heavily monitored catchments. The approach is then applied to streamflow data in several small catchments across Switzerland to obtain a spatially distributed description of soil moisture memory and to show how memory varies, for example, with altitude and topography.

Soil Moisture↗