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 865 records · Page 48

Adaptive Mesh Refinement in the Fastlane

Adaptive Mesh Refinement (AMR) allows us to dramatically reduce memory usage by dynamically distributing resources to areas of physical significance.

97 MATHEMATICS AND COMPUTING↗

Optimizing the Energy Usage and Cognitive Value of Extreme-Scale Data-Analysis Approaches (Final Report)

This report serves as a record that we have successfully completed work on the proposal Optimizing the Energy Usage and Cognitive Value of Extreme Scale Analysis Approaches, or, more succinctly, ECX. This includes successful completion of all three phases of the project, findings as summarized below, strong publications across the fields represented in the proposal, and a set of artifacts (code, websites, and other documentation) available to the public. In total, the results of this project represent significant findings in each domain, and a toolkit that will allow the community to engage with this work, advancing it and contributing to it in the years ahead. They also form the basis for a successfully funded follow-on project. This executive summary presents findings, tools and publications resulting from the ECX project. The balance of the report then provides more detail on these results.

97 MATHEMATICS AND COMPUTING↗

Balancing Loads Among Parallel Data Processors

Heuristic algorithm minimizes amount of memory used by multiprocessor system. Distributes load of many identical, short computations among multiple parallel digital data processors, each of which has its own (local) memory. Each processor operates on distinct and independent set of data in larger shared memory. As integral part of load-balancing scheme, total amount of space used in shared memory minimized. Possible applications include artificial neural networks or image processors for which "pipeline" and vector methods of load balancing inappropriate.

Baffes, Paul Thomas↗

Concurrent Finite-Element Analysis On Hypercube Computers

Improved approach to execution of finite-element codes on hypercube and similar concurrent data processors increases efficiency of computation for many different types of problems. Based on flexible general model of computation on, and communication among, large-node parallel processors. Hybrid combining direct methods within subdomains and preconditioned-conjugate-gradient (PCG) iteration on remaining boundary system to obtain method of solution both robust and efficient. Preserves general structure and function of conventional sequential finite-element-method software. Generalized to both distributed- and shared-memory multicomputers, eliminating degree of machine specificity restricting general usefulness.

Lyzenga, G. A.↗

Portable programming on parallel/networked computers using the Application Portable Parallel Library (APPL)

The Application Portable Parallel Library (APPL) is a subroutine-based library of communication primitives that is callable from applications written in FORTRAN or C. APPL provides a consistent programmer interface to a variety of distributed and shared-memory multiprocessor MIMD machines. The objective of APPL is to minimize the effort required to move parallel applications from one machine to another, or to a network of homogeneous machines. APPL encompasses many of the message-passing primitives that are currently available on commercial multiprocessor systems. This paper describes APPL (version 2.3.1) and its usage, reports the status of the APPL project, and indicates possible directions for the future. Several applications using APPL are discussed, as well as performance and overhead results.

Quealy, Angela↗

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.↗

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↗