Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory 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 757 records · Page 42

Compiler-generated memory mapping hints

According to one embodiment, a method of creating compiler-generated memory mapping hints in a computer system includes analyzing code, by a compiler of the computer system, to identify data access patterns in the code. System configuration information defining data processing system characteristics of a target system for the code is accessed. The data processing system characteristics include a plurality of processing resources and memory domain characteristics relative to the processing resources. A preferred allocation of data in memory domains of the target system is determined based on mapping the code to one or more selected processing resources and mapping the data to one or more of the memory domains based on the memory domain characteristics relative to the one or more selected processing resources. The preferred allocation is stored as compiler-generated memory mapping hints in a format accessible by a physical memory mapping resource of the target system.

97 MATHEMATICS AND COMPUTING↗

Reverse Computation for Rollback-based Fault Tolerance in Large Parallel Systems

Reverse computation is presented here as an important future direction in addressing the challenge of fault tolerant execution on very large cluster platforms for parallel computing. As the scale of parallel jobs increases, traditional checkpointing approaches suffer scalability problems ranging from computational slowdowns to high congestion at the persistent stores for checkpoints. Reverse computation can overcome such problems and is also better suited for parallel computing on newer architectures with smaller, cheaper or energy-efficient memories and file systems. Initial evidence for the feasibility of reverse computation in large systems is presented with detailed performance data from a particle simulation scaling to 65,536 processor cores and 950 accelerators (GPUs). Reverse computation is observed to deliver very large gains relative to checkpointing schemes when nodes rely on their host processors/memory to tolerate faults at their accelerators. A comparison between reverse computation and checkpointing with measurements such as cache miss ratios, TLB misses and memory usage indicates that reverse computation is hard to ignore as a future alternative to be pursued in emerging architectures.

Perumalla, Kalyan S↗

Energy scaling advantages of resistive memory crossbar based computation and its application to sparse coding

In this study, the exponential increase in data over the last decade presents a significant challenge to analytics efforts that seek to process and interpret such data for various applications. Neural-inspired computing approaches are being developed in order to leverage the computational properties of the analog, low-power data processing observed in biological systems. Analog resistive memory crossbars can perform a parallel read or a vector-matrix multiplication as well as a parallel write or a rank-1 update with high computational efficiency. For an N × N crossbar, these two kernels can be O(N) more energy efficient than a conventional digital memory-based architecture. If the read operation is noise limited, the energy to read a column can be independent of the crossbar size (O(1)). These two kernels form the basis of many neuromorphic algorithms such as image, text, and speech recognition. For instance, these kernels can be applied to a neural sparse coding algorithm to give an O(N) reduction in energy for the entire algorithm when run with finite precision. Sparse coding is a rich problem with a host of applications including computer vision, object tracking, and more generally unsupervised learning.

97 MATHEMATICS AND COMPUTING↗

Pseudomodes as an effective description of memory: Non-Markovian dynamics of two-state systems in structured reservoirs

We investigate the non-Markovian dynamics of two-state systems in structured reservoirs. We establish a connection between two theoretical quantum approaches, the pseudomodes [B. M. Garraway, Phys. Rev. A 55, 2290 (1997)] and the recently developed non-Markovian quantum jump method [J. Piilo et al., Phys. Rev. Lett. 100, 180402 (2008)]. This connection provides a clear physical picture of how the structured reservoir affects the system dynamics, suggesting the role of the pseudomodes as effective description of environmental memory.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Implementation of a partitioned algorithm for simulation of large CSI problems

The implementation of a partitioned numerical algorithm for determining the dynamic response of coupled structure/controller/estimator finite-dimensional systems is reviewed. The partitioned approach leads to a set of coupled first and second-order linear differential equations which are numerically integrated with extrapolation and implicit step methods. The present software implementation, ACSIS, utilizes parallel processing techniques at various levels to optimize performance on a shared-memory concurrent/vector processing system. A general procedure for the design of controller and filter gains is also implemented, which utilizes the vibration characteristics of the structure to be solved. Also presented are: example problems; a user's guide to the software; the procedures and algorithm scripts; a stability analysis for the algorithm; and the source code for the parallel implementation.

Alvin, Kenneth F.↗

Ergodicity, lack thereof, and the performance of reservoir computing with memristive networks and nanowire

Networks composed of nanoscale memristive components, such as nanowire and nanoparticle networks, have recently received considerable attention because of their potential use as neuromorphic devices. In this study, we explore ergodicity in memristive networks, showing that the performance on machine leaning tasks improves when these networks are tuned to operate at the edge between two global stability points. We find this lack of ergodicity is associated with the emergence of memory in the system. We measure the level of ergodicity using the Thirumalai-Mountain metric, and we show that in the absence of ergodicity, two different memristive network systems show improved performance when utilized as reservoir computers (RC). We highlight that it is also important to let the system synchronize to the input signal in order for the performance of the RC to exhibit improvements over the baseline.

97 MATHEMATICS AND COMPUTING↗

GPU Direct I/O with HDF5

Exascale HPC systems are being designed with accelerators, such as GPUs, to accelerate parts of applications. In machine learning workloads as well as large-scale simulations that use GPUs as accelerators, the CPU (or host) memory is currently used as a buffer for data transfers between GPU (or device) memory and the file system. If the CPU does not need to operate on the data, then this is sub-optimal because it wastes host memory by reserving space for duplicated data. Furthermore, this “bounce buffer” approach wastes CPU cycles spent on transferring data. A new technique, NVIDIA GPUDirect Storage (GDS), can eliminate the need to use the host memory as a bounce buffer. Thereby, it becomes possible to transfer data directly between the device memory and the file system. This direct data path shortens latency by omitting the extra copy and enables higher-bandwidth. To take full advantage of GDS in existing applications, it is necessary to provide support with existing I/O libraries, such as HDF5 and MPI-IO, which are heavily used in applications. In this paper, we describe our effort of integrating GDS with HDF5, the top I/O library at NERSC and at DOE leadership computing facilities. We design and implement this integration using a HDF5 Virtual File Driver (VFD). The GDS VFD provides a file system abstraction to the application that allows HDF5 applications to perform I/O without the need to move data between CPUs and GPUs explicitly. We compare performance of the HDF5 GDS VFD with explicit data movement approaches and demonstrate superior performance with the GDS method.

Ravi, J↗

Micromechanics of composites with shape memory alloy fibers in uniform thermal fields

Analytical procedures are developed for a composite system consisting of shape memory alloy fibers within an elastic matrix subject to uniform temperature fluctuations. Micromechanics for the calculation of the equivalent properties of the composite are presented by extending the multi-cell model to incorporate shape memory alloy fibers. A three phase concentric cylinder model is developed for the analysis of local stresses which includes the fiber, the matrix, and the surrounding homogenized composite. The solution addresses the complexities induced by the nonlinear dependence of the in-situ martensite fraction of the fibers to the local stresses and temperature, and the local stresses developed from interactions between the fibers and matrix during the martensitic and reverse phase transformations. Results are presented for a nitinol/epoxy composite. The applications illustrate the response of the composite in isothermal longitudinal loading and unloading, and in temperature induced actuation. The local stresses developed in the composite under various stages of the martensitic and reverse phase transformation are also shown.

Birman, Victor↗

Error detection and correction utilizing locally stored parity information

A processing system includes a memory coupled to a processor. The memory stores data blocks, with each data block having a separate associated checksum value stored along with the data block in the memory. The processor has a storage location that stores parity information for the data blocks, with the parity information having a plurality of parity blocks. Each parity block represents a parity of a corresponding set of data blocks. The parity blocks can be accessed for use in error detection and correction schemes used by the processing system.

97 MATHEMATICS AND COMPUTING↗

Quantum formalism for classical statistics

In static classical statistical systems the problem of information transport from a boundary to the bulk finds a simple description in terms of wave functions or density matrices. While the transfer matrix formalism is a type of Heisenberg picture for this problem, we develop here the associated Schrödinger picture that keeps track of the local probabilistic information. The transport of the probabilistic information between neighboring hypersurfaces obeys a linear evolution equation, and therefore the superposition principle for the possible solutions. Operators are associated to local observables, with rules for the computation of expectation values similar to quantum mechanics. We discuss how non-commutativity naturally arises in this setting. Also other features characteristic of quantum mechanics, such as complex structure, change of basis or symmetry transformations, can be found in classical statistics once formulated in terms of wave functions or density matrices. We construct for every quantum system an equivalent classical statistical system, such that time in quantum mechanics corresponds to the location of hypersurfaces in the classical probabilistic ensemble. For suitable choices of local observables in the classical statistical system one can, in principle, compute all expectation values and correlations of observables in the quantum system from the local probabilistic information of the associated classical statistical system. Realizing a static memory material as a quantum simulator for a given quantum system is not a matter of principle, but rather of practical simplicity.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Freeing Space for NASA: Incorporating a Lossless Compression Algorithm into NASA's FOSS System

NASA's Fiber Optic Strain Sensing (FOSS) system can gather and store up to 1,536,000 bytes (1.46 megabytes) per second. Since the FOSS system typically acquires hours - or even days - of data, the system can gather hundreds of gigabytes of data for a given test event. To store such large quantities of data more effectively, NASA is modifying a Lempel-Ziv-Oberhumer (LZO) lossless data compression program to compress data as it is being acquired in real time. After proving that the algorithm is capable of compressing the data from the FOSS system, the LZO program will be modified and incorporated into the FOSS system. Implementing an LZO compression algorithm will instantly free up memory space without compromising any data obtained. With the availability of memory space, the FOSS system can be used more efficiently on test specimens, such as Unmanned Aerial Vehicles (UAVs) that can be in flight for days. By integrating the compression algorithm, the FOSS system can continue gathering data, even on longer flights.

Fiechtner, Kaitlyn↗

Study on fault-tolerant processors for advanced launch system

Issues related to the reliability of a redundant system with large main memory are addressed. The Fault-Tolerant Processor (FTP) for the Advanced Launch System (ALS) is used as a basis for the presentation. When the system is free of latent faults, the probability of system crash due to multiple channel faults is shown to be insignificant even when voting on the outputs of computing channels is infrequent. Using channel error maskers (CEMs) is shown to improve reliability more effectively than increasing redundancy or the number of channels for applications with long mission times. Even without using a voter, most memory errors can be immediately corrected by those CEMs implemented with conventional coding techniques. In addition to their ability to enhance system reliability, CEMs (with a very low hardware overhead) can be used to dramatically reduce not only the need of memory realignment, but also the time required to realign channel memories in case, albeit rare, such a need arises. Using CEMs, two different schemes were developed to solve the memory realignment problem. In both schemes, most errors are corrected by CEMs, and the remaining errors are masked by a voter.

Shin, Kang G.↗

Ergodicity, lack thereof, and the performance of reservoir computing with memristive networks

Abstract Networks composed of nanoscale memristive components, such as nanowire and nanoparticle networks, have recently received considerable attention because of their potential use as neuromorphic devices. In this study, we explore ergodicity in memristive networks, showing that the performance on machine leaning tasks improves when these networks are tuned to operate at the edge between two global stability points. We find this lack of ergodicity is associated with the emergence of memory in the system. We measure the level of ergodicity using the Thirumalai-Mountain metric, and we show that in the absence of ergodicity, two different memristive network systems show improved performance when utilized as reservoir computers (RC). We highlight that it is also important to let the system synchronize to the input signal in order for the performance of the RC to exhibit improvements over the baseline.

97 MATHEMATICS AND COMPUTING↗

Dynamic Load-Balancing for Distributed Heterogeneous Computing of Parallel CFD Problems

The developed methodology is aimed at improving the efficiency of executing block-structured algorithms on parallel, distributed, heterogeneous computers. The basic approach of these algorithms is to divide the flow domain into many sub- domains called blocks, and solve the governing equations over these blocks. Dynamic load balancing problem is defined as the efficient distribution of the blocks among the available processors over a period of several hours of computations. In environments with computers of different architecture, operating systems, CPU speed, memory size, load, and network speed, balancing the loads and managing the communication between processors becomes crucial. Load balancing software tools for mutually dependent parallel processes have been created to efficiently utilize an advanced computation environment and algorithms. These tools are dynamic in nature because of the chances in the computer environment during execution time. More recently, these tools were extended to a second operating system: NT. In this paper, the problems associated with this application will be discussed. Also, the developed algorithms were combined with the load sharing capability of LSF to efficiently utilize workstation clusters for parallel computing. Finally, results will be presented on running a NASA based code ADPAC to demonstrate the developed tools for dynamic load balancing.

Ecer, A.↗

Quantifying ecological memory in plant and ecosystem processes

Abstract The role of time in ecology has a long history of investigation, but ecologists have largely restricted their attention to the influence of concurrent abiotic conditions on rates and magnitudes of important ecological processes. Recently, however, ecologists have improved their understanding of ecological processes by explicitly considering the effects of antecedent conditions. To broadly help in studying the role of time, we evaluate the length, temporal pattern, and strength of memory with respect to the influence of antecedent conditions on current ecological dynamics. We developed the stochastic antecedent modelling ( SAM ) framework as a flexible analytic approach for evaluating exogenous and endogenous process components of memory in a system of interest. We designed SAM to be useful in revealing novel insights promoting further study, illustrated in four examples with different degrees of complexity and varying time scales: stomatal conductance, soil respiration, ecosystem productivity, and tree growth. Models with antecedent effects explained an additional 18–28% of response variation compared to models without antecedent effects. Moreover, SAM also enabled identification of potential mechanisms that underlie components of memory, thus revealing temporal properties that are not apparent from traditional treatments of ecological time‐series data and facilitating new hypothesis generation and additional research.

Ogle, Kiona↗

Spark and HPC for High Energy Physics Data Analyses

A full High Energy Physics (HEP) data analysis is divided into multiple data reduction phases. Processing within these phases is extremely time consuming, therefore intermediate results are stored in files held in mass storage systems and referenced as part of large datasets. This processing model limits what can be done with interactive data analytics. Growth in size and complexity of experimental datasets, along with emerging big data tools are beginning to cause changes to the traditional ways of doing data analyses. Use of big data tools for HEP analysis looks promising, mainly because extremely large HEP datasets can be represented and held in memory across a system, and accessed interactively by encoding an analysis using highlevel programming abstractions. The mainstream tools, however, are not designed for scientific computing or for exploiting the available HPC platform features. We use an example from the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) in Geneva, Switzerland. The LHC is the highest energy particle collider in the world. Our use case focuses on searching for new types of elementary particles explaining Dark Matter in the universe. We use HDF5 as our input data format, and Spark to implement the use case. We show the benefits and limitations of using Spark with HDF5 on Edison at NERSC.

Sehrish, Saba↗

Trinity Benchmarks on the Intel Xeon Phi (Knights Corner)

This report documents the early experiences with porting and performance analysis of the Tri-Lab Trinity benchmark applications on Intel Xeon Phi (Knights Corner) (KNC) processor. KNC, the second generation of the Intel Many Integrated Core (MIC) architectures, uses a large number of small P54C-x86 cores with wide vector units and is deployed as PCI bus attached process accelerators. Sandia has experimental test beds of small InifiniBand clusters and workstations to investigate the performance of the MIC architecture. On these experimental test beds the programming models that may be investigated are "offload", "symmetric" and "native". Among these program usage models our primary interest is in the so called "native" mode, because the planned Trinity system to be deployed in 2016 using the next generation MIC processor architecture called Knights Landing would be self-hosted. Trinity / NERSC-8 benchmark programs cover a variety of scientific disciplines and they were used to guide the procurement of these systems. Architectures such as the Intel MIC are well suited to study evolving processor architectures and a usage model commonly referred to as MPI + X that facilitates migration of our applications to use both coarse grain and fine grain parallelism. Our focus with the applications selected is on the efficacy of algorithms in these applications to take advantage of features like: large number of cores, wide vector units, higher-bandwidth and deeper memory sub-system. This is a first step towards understanding applications, algorithms and programming environments for Trinity and future exascale computing systems.

97 MATHEMATICS AND COMPUTING↗

Shared memory for a fault-tolerant computer

A system is described for sharing a memory in a fault-tolerant computer. The memory is under the direct control and monitoring of error detecting and error diagnostic units in the fault-tolerant computer. This computer verifies that data to and from the memory is legally encoded and verifies that words read from the memory at a desired address are, in fact, actually delivered from that desired address. The means are provided for a second processor, which is independent of the direct control and monitoring of the error checking and diagnostic units of the fault-tolerant computer, and to share the memory of the fault-tolerant computer. Circuitry is included to verify that: (1) the processor has properly accessed a desired memory location in the memory; (2) a data word read-out from the memory is properly coded; and (3) no inactive memory was erroneously outputting data onto the shared memory bus.

Gilley, G. C.↗