Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 703 records · Page 39

Myrmics Memory Allocator

MMA is a stand-alone memory management system for MPI clusters. It implements a shared Partitioned Global Address Space, where multiple MPI processes request objects from the allocator and the latter provides them with system-wide unique memory addresses for each object. It provides applications with an intuitive way of managing the memory system in a unified way, thus enabling easier writing of irregular application code.

Lymperis, S.↗

A memory-driven mapping algorithm for heterogeneous systems

mpibind is a memory-driven algorithm to map parallel hybrid applications to the underlying hardware resources transparently, efficiently, and portably. There are two fundamental aspects of this algorithm. First, unlike existing mappings, its primary design point is the memory system. Compute elements are selected based on the identified memory components and not vice versa. Second, it embodies a global awareness of hybrid programming abstractions as well as heterogeneous devices.

Leon Borja, EdgarA↗

LDRD final report : managing shared memory data distribution in hybrid HPC applications.

MPI is the dominant programming model for distributed memory parallel computers, and is often used as the intra-node programming model on multi-core compute nodes. However, application developers are increasingly turning to hybrid models that use threading within a node and MPI between nodes. In contrast to MPI, most current threaded models do not require application developers to deal explicitly with data locality. With increasing core counts and deeper NUMA hierarchies seen in the upcoming LANL/SNL 'Cielo' capability supercomputer, data distribution poses an upper boundary on intra-node scalability within threaded applications. Data locality therefore has to be identified at runtime using static memory allocation policies such as first-touch or next-touch, or specified by the application user at launch time. We evaluate several existing techniques for managing data distribution using micro-benchmarks on an AMD 'Magny-Cours' system with 24 cores among 4 NUMA domains and argue for the adoption of a dynamic runtime system implemented at the kernel level, employing a novel page table replication scheme to gather per-NUMA domain memory access traces.

99 GENERAL AND MISCELLANEOUS↗

Nanopatterned ferroelectrics for ultrahigh density rad-hard nonvolatile memories.

Radiation hard nonvolatile random access memory (NVRAM) is a crucial component for DOE and DOD surveillance and defense applications. NVRAMs based upon ferroelectric materials (also known as FERAMs) are proven to work in radiation-rich environments and inherently require less power than many other NVRAM technologies. However, fabrication and integration challenges have led to state-of-the-art FERAMs still being fabricated using a 130nm process while competing phase-change memory (PRAM) has been demonstrated with a 20nm process. Use of block copolymer lithography is a promising approach to patterning at the sub-32nm scale, but is currently limited to self-assembly directly on Si or SiO{sub 2} layers. Successful integration of ferroelectrics with discrete and addressable features of {approx}15-20nm would represent a 100-fold improvement in areal memory density and would enable more highly integrated electronic devices required for systems advances. Towards this end, we have developed a technique that allows us to carry out block copolymer self-assembly directly on a huge variety of different materials and have investigated the fabrication, integration, and characterization of electroceramic materials - primarily focused on solution-derived ferroelectrics - with discrete features of {approx}20nm and below. Significant challenges remain before such techniques will be capable of fabricating fully integrated NVRAM devices, but the tools developed for this effort are already finding broader use. This report introduces the nanopatterned NVRAM device concept as a mechanism for motivating the subsequent studies, but the bulk of the document will focus on the platform and technology development.

36 MATERIALS SCIENCE↗

Limited-memory adaptive snapshot selection for proper orthogonal decomposition

Reduced order models are useful for accelerating simulations in many-query contexts, such as optimization, uncertainty quantification, and sensitivity analysis. However, offline training of reduced order models can have prohibitively expensive memory and floating-point operation costs in high-performance computing applications, where memory per core is limited. To overcome this limitation for proper orthogonal decomposition, we propose a novel adaptive selection method for snapshots in time that limits offline training costs by selecting snapshots according an error control mechanism similar to that found in adaptive time-stepping ordinary differential equation solvers. The error estimator used in this work is related to theory bounding the approximation error in time of proper orthogonal decomposition-based reduced order models, and memory usage is minimized by computing the singular value decomposition using a single-pass incremental algorithm. Results for a viscous Burgers’ test problem demonstrate convergence in the limit as the algorithm error tolerances go to zero; in this limit, the full order model is recovered to within discretization error. The resulting method can be used on supercomputers to generate proper orthogonal decomposition-based reduced order models, or as a subroutine within hyperreduction algorithms that require taking snapshots in time, or within greedy algorithms for sampling parameter space.

97 MATHEMATICS AND COMPUTING↗

zorder-lib: Library API for Z-Order Memory Layout

This document describes the motivation for, elements of, and use of the zorder-lib, a library API that implements organization of and access to data in memory using either a-order (also known as "row-major" order) or z-order memory layouts. The primary motivation for this work is to improve the performance of many types of data- intensive codes by increasing both spatial and temporal locality of memory accesses. The basic idea is that the cost associated with accessing a datum is less when it is nearby in either space or time.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

zorder-lib: Library API for Z-Order Memory Layout

This document describes the motivation for, elements of, and use of the zorder-lib, a library API that implements organization of and access to data in memory using either a-order (also known as “row-major” order) or z-order memory layouts. The primary motivation for this work is to improve the performance of many types of data-intensive codes by increasing both spatial and temporal locality of memory accesses. The basic idea is that the cost associated with accessing a datum is less when it is nearby in either space or time.

97 MATHEMATICS AND COMPUTING↗

GentenMPI: Distributed Memory Sparse Tensor Decomposition

GentenMPl is a toolkit of sparse canonical polyadic (CP) tensor decomposition algorithms that is designed to run effectively on distributed-memory high-performance computers. Its use of distributed-memory parallelism enables it to efficiently decompose tensors that are too large for a single compute node's memory. GentenMPl leverages Sandia's decades-long investment in the Trilinos solver framework for much of its parallel-computation capability. Trilinos contains numerical algorithms and linear algebra classes that have been optimized for parallel simulation of complex physical phenomena. This work applies these tools to the data science problem of sparse tensor decomposition. In this report, we describe the use of Trilinos in GentenMPl, extensions needed for sparse tensor decomposition, and implementations of the CP-ALS (CP via alternating least squares) and GCP-SGD (generalized CP via stochastic gradient descent) sparse tensor decomposition algorithms. We show that GentenMPl can decompose sparse tensors of extreme size, e.g., a 12.6-terabyte tensor on 8192 computer cores. We demonstrate that the Trilinos backbone provides good strong and weak scaling of the tensor decomposition algorithms.

97 MATHEMATICS AND COMPUTING↗

Probabilistic Nanomagnetic Memories for Uncertain and Robust Machine Learning

This project evaluated the use of emerging spintronic memory devices for robust and efficient variational inference schemes. Variational inference (VI) schemes, which constrain the distribution for each weight to be a Gaussian distribution with a mean and standard deviation, are a tractable method for calculating posterior distributions of weights in a Bayesian neural network such that this neural network can also be trained using the powerful backpropagation algorithm. Our project focuses on domain-wall magnetic tunnel junctions (DW-MTJs), a powerful multi-functional spintronic synapse design that can achieve low power switching while also opening the pathway towards repeatable, analog operation using fabricated notches. Our initial efforts to employ DW-MTJs as an all-in-one stochastic synapse with both a mean and standard deviation didn’t end up meeting the quality metrics for hardware-friendly VI. In the future, new device stacks and methods for expressive anisotropy modification may make this idea still possible. However, as a fall back that immediately satisfies our requirements, we invented and detailed how the combination of a DW-MTJ synapse encoding the mean and a probabilistic Bayes-MTJ device, programmed via a ferroelectric or ionically modifiable layer, can robustly and expressively implement VI. This design includes a physics-informed small circuit model, that was scaled up to perform and demonstrate rigorous uncertainty quantification applications, up to and including small convolutional networks on a grayscale image classification task, and larger (Residual) networks implementing multi-channel image classification. Lastly, as these results and ideas all depend upon the idea of an inference application where weights (spintronic memory states) remain non-volatile, the retention of these synapses for the notched case was further interrogated. These investigations revealed and emphasized the importance of both notch geometry and anisotropy modification in order to further enhance the endurance of written spintronic states. In the near future, these results will be mapped to effective predictions for room temperature and elevated operation DW-MTJ memory retention, and experimentally verified when devices become available.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

New Results on Communication- and Memory-Aware Load Balancing Model and Algorithms

While load balancing in distributed-memory computing has been well-studied, we present an innovative approach to this problem: a unified, reduced-order model that combines three key components to describe “work” in a distributed system: computation, communication, and memory. Our model enables an optimizer to explore complex tradeoffs in task placement, such as augmented parallelism, at the expense of data replication increasing memory usage. We propose a fully distributed, heuristic-based load balancing optimization algorithm, and demonstrate that it quickly finds close-to-optimal solutions. We formalize the complex optimization problem as a mixed-integer linear program, and compare it to our strategy. Finally, we show that when applied to an electromagnetics code, our approach obtains up to 2.3x speedups for the imbalanced execution.

97 MATHEMATICS AND COMPUTING↗

Loss of Mitochondrial Tusc2/Fus1 Triggers a Brain Pro-Inflammatory Microenvironment and Early Spatial Memory Impairment

Brain pathological changes impair cognition early in disease etiology. There is an urgent need to understand aging-linked mechanisms of early memory loss to develop therapeutic strategies and prevent the development of cognitive impairment. Tusc2 is a mitochondrial-resident protein regulating Ca 2+ fluxes to and from mitochondria impacting overall health. We previously reported that Tusc2 –/– female mice develop chronic inflammation and age prematurely, causing age- and sex-dependent spatial memory deficits at 5 months old. Therefore, we investigated Tusc2-dependent mechanisms of memory impairment in 4-month-old mice, comparing changes in resident and brain-infiltrating immune cells. Interestingly, Tusc2 –/– female mice demonstrated a pro-inflammatory increase in astrocytes, expression of IFN-γ in CD4 + T cells and Granzyme-B in CD8 + T cells. We also found fewer FOXP3 + T-regulatory cells and Ly49G + NK and Ly49G + NKT cells in female Tusc2 –/– brains, suggesting a dampened anti-inflammatory response. Moreover, Tusc2 –/– hippocampi exhibited Tusc2- and sex-specific protein changes associated with brain plasticity, including mTOR activation, and Calbindin and CamKII dysregulation affecting intracellular Ca2 + dynamics. Overall, the data suggest that dysregulation of Ca 2+ -dependent processes and a heightened pro-inflammatory brain microenvironment in Tusc2 –/– mice could underlie cognitive impairment. Thus, strategies to modulate the mitochondrial Tusc2- and Ca 2+ - signaling pathways in the brain should be explored to improve cognitive health.

59 BASIC BIOLOGICAL SCIENCES↗

CENTRAL ENGINE MEMORY OF GAMMA-RAY BURSTS AND SOFT GAMMA-RAY REPEATERS

Gamma-ray bursts (GRBs) are bursts of γ-rays generated from relativistic jets launched from catastrophic events such as massive star core collapse or binary compact star coalescence. Previous studies suggested that GRB emission is erratic, with no noticeable memory in the central engine. Here we report a discovery that similar light curve patterns exist within individual bursts for at least some GRBs. Applying the Dynamic Time Warping method, we show that similarity of light curve patterns between pulses of a single burst or between the light curves of a GRB and its X-ray flare can be identified. This suggests that the central engine of at least some GRBs carries “memory” of its activities. We also show that the same technique can identify memory-like emission episodes in the flaring emission in soft gamma-ray repeaters (SGRs), which are believed to be Galactic, highly magnetized neutron stars named magnetars. Such a phenomenon challenges the standard black hole central engine models for GRBs, and suggest a common physical mechanism behind GRBs and SGRs, which points toward a magnetar central engine of GRBs.

79 ASTRONOMY AND ASTROPHYSICS↗

Performance Characterization of a Hierarchical MPI Implementations on Large-scale Distributed-memory Platforms

The building blocks of emerging Petascale massively parallel processing (MPP) systems are multi-core processors with four or more cores as a single processing element and a customized network interface. The resulting memory and communication hierarchy of these platforms are now exposed to application developers and end users by creating a hierarchical or multi-core aware message-passing (MPI) programming interface and by providing a handful of runtime, tunable parameters that allows mapping and control of MPI tasks and message handling. We characterize performance of MPI communication patterns and present strategies for optimizing applications performance on Cray XT series systems that are composed of contemporary AMD processors and a proprietary network infrastructure. We highlight dependencies in its memory and network subsystems, which could influence production-level applications performance. We demonstrate that MPI micro-benchmarks could mislead an application developer or end user since these benchmarks often do not expose the interplay between memory allocation and usage in the user space, which depends on the number of tasks or cores and workload characteristics. Our studies show performance improvements compared to the default options for our target scientific benchmarks and production-level applications.

99 GENERAL AND MISCELLANEOUS↗

Towards scalable parellelism in Monte Carlo particle transport codes using remote memory access

One forthcoming challenge in the area of high-performance computing is having the ability to run large-scale problems while coping with less memory per compute node. In this work, they investigate a novel data decomposition method that would allow Monte Carlo transport calculations to be performed on systems with limited memory per compute node. In this method, each compute node remotely retrieves a small set of geometry and cross-section data as needed and remotely accumulates local tallies when crossing the boundary of the local spatial domain. initial results demonstrate that while the method does allow large problems to be run in a memory-limited environment, achieving scalability may be difficult due to inefficiencies in the current implementation of RMA operations.

97 MATHEMATICS AND COMPUTING↗

Shape memory polymer foams for endovascular therapies

A system for occluding a physical anomaly. One embodiment comprises a shape memory material body wherein the shape memory material body fits within the physical anomaly occluding the physical anomaly. The shape memory material body has a primary shape for occluding the physical anomaly and a secondary shape for being positioned in the physical anomaly.

60 APPLIED LIFE SCIENCES↗

Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

97 MATHEMATICS AND COMPUTING↗

Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

97 MATHEMATICS AND COMPUTING↗

Securing non-volatile memory regions

Methods, apparatus and articles of manufacture to secure non-volatile memory regions are disclosed. An example method disclosed herein comprises associating a first key pair and a second key pair different than the first key pair with a process, using the first key pair to secure a first region of a non-volatile memory for the process, and using the second key pair to secure a second region of the non-volatile memory for the same process, the second region being different than the first region.

97 MATHEMATICS AND COMPUTING↗