Search NASA⌕ Search

SEARCH · Search NASA

Results for “near memory computing”

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 109 records · Page 6

Electrode and Microstructure Dependence of Oxygen Diffusion in Ferroelectric Hafnium Zirconium Oxide Thin Films

Hafnia-based ferroelectrics hold promise to reduce energy demand for computing by enabling compute-in-memory and as non-volatile memories. The ferroelectric phase in this material system is, in part, stabilized by oxygen vacancies. While oxygen vacancies may be a necessity for phase stability, they limit device endurance through diffusion and accumulation into conducting channels. Herein, it is shown that oxygen diffusion is spatially variable within individual grains of ferroelectric hafnium zirconium oxide (HZO). Using 18 O tracers and finite difference modeling, it is shown that grain boundaries and regions near electrode interfaces allow for relatively rapid oxygen diffusion, with values as much as 10 4 larger than the grain cores. Further, the selection of electrode material affects the diffusion coefficients across all microstructural regions. HZO films in contact with TiN electrodes result in more oxygen-deficient HZO films and higher oxygen diffusion coefficients. Tungsten electrodes result in fewer vacancies and lower diffusion coefficients. Diffusion activation energy differences between the HZO with the two electrodes is reconciled by differing populations of charged and uncharged oxygen vacancies. This insight into the local vacancy populations and diffusion pathways provides a platform for designing hafnia-based films, deposition processes, and integration strategies to reduce vacancy gradients and improve performance.

36 MATERIALS SCIENCE↗

Sage: parallel semi-asymmtric graph algorithms for NVRAMs

Non-volatile main memory (NVRAM) technologies provide an attractive set of features for large-scale graph analytics, including byte-addressability, low idle power, and improved memory-density. NVRAM systems today have an order of magnitude more NVRAM than traditional memory (DRAM). NVRAM systems could therefore potentially allow very large graph problems to be solved on a single machine, at a modest cost. However, a significant challenge in achieving high performance is in accounting for the fact that NVRAM writes can be much more expensive than NVRAM reads. In this paper, we propose an approach to parallel graph analytics using the Parallel Semi-Asymmetric Model (PSAM), in which the graph is stored as a read-only data structure (in NVRAM), and the amount of mutable memory is kept proportional to the number of vertices. Similar to the popular semi-external and semi-streaming models for graph analytics, the PSAM approach assumes that the vertices of the graph fit in a fast read-write memory (DRAM), but the edges do not. In NVRAM systems, our approach eliminates writes to the NVRAM, among other benefits. To experimentally study this new setting, we develop Sage, a parallel semi-asymmetric graph engine with which we implement provably-efficient (and often work-optimal) PSAM algorithms for over a dozen fundamental graph problems. We experimentally study Sage using a 48--core machine on the largest publicly-available real-world graph (the Hyperlink Web graph with over 3.5 billion vertices and 128 billion edges) equipped with Optane DC Persistent Memory, and show that Sage outperforms the fastest prior systems designed for NVRAM. Importantly, we also show that Sage nearly matches the fastest prior systems running solely in DRAM, by effectively hiding the costs of repeatedly accessing NVRAM versus DRAM.

97 MATHEMATICS AND COMPUTING↗

Running SW4 On New Commodity Technology Systems (CTS-1) Platform

We have recently been running earthquake ground motion simulations with SW4 on the new capacity computing systems, called the Commodity Technology Systems - 1 (CTS-1) at Lawrence Livermore National Laboratory (LLNL). SW4 is a fourth order time domain finite difference code developed by LLNL and distributed by the Computational Infrastructure for Geodynamics (CIG). SW4 simulates seismic wave propagation in complex three-dimensional Earth models including anelasticity and surface topography. We are modeling near-fault earthquake strong ground motions for the purposes of evaluating the response of engineered structures, such as nuclear power plants and other critical infrastructure. Engineering analysis of structures requires the inclusion of high frequencies which can cause damage, but are often difficult to include in simulations because of the need for large memory to model fine grid spacing on large domains.

58 GEOSCIENCES↗

Accelerating String Set Matching in FPGA Hardware for Bioinformatics Research

Background: This paper describes techniques for accelerating the performance of the string set matching problem with particular emphasis on applications in computational proteomics. The process of matching peptide sequences against a genome translated in six reading frames is part of a proteogenomic mapping pipeline that is used as a case-study. The Aho-Corasick algorithm is adapted for execution in field programmable gate array (FPGA) devices in a manner that optimizes space and performance. In this approach, the traditional Aho-Corasick finite state machine (FSM) is split into smaller FSMs, operating in parallel, each of which matches up to 20 peptides in the input translated genome. Each of the smaller FSMs is further divided into five simpler FSMs such that each simple FSM operates on a single bit position in the input (five bits are sufficient for representing all amino acids and special symbols in protein sequences). Results: This bit-split organization of the Aho-Corasick implementation enables efficient utilization of the limited random access memory (RAM) resources available in typical FPGAs. The use of onchip RAM as opposed to FPGA logic resources for FSM implementation also enables rapid reconfiguration of the FPGA without the place and routing delays associated with complex digital designs. Conclusion: Experimental results show storage efficiencies of over 80% for several data sets. Furthermore, the FPGA implementation executing at 100 MHz is nearly 20 times faster than an implementation of the traditional Aho-Corasick algorithm executing on a 2.67 GHz workstation.

59 BASIC BIOLOGICAL SCIENCES↗

Randomized Projection for Rank-Revealing Matrix Factorizations and Low-Rank Approximations

Rank-revealing matrix decompositions provide an essential tool in spectral analysis of matrices, including the Singular Value Decomposition (SVD) and related low-rank approximation techniques. QR with Column Pivoting (QRCP) is usually suitable for these purposes, but it can be much slower than the unpivoted QR algorithm. For large matrices, the difference in performance is due to increased communication between the processor and slow memory, which QRCP needs in order to choose pivots during decomposition. Our main algorithm, Randomized QR with Column Pivoting (RQRCP), uses randomized projection to make pivot decisions from a much smaller sample matrix, which we can construct to reside in a faster level of memory than the original matrix. This technique may be understood as trading vastly reduced communication for a controlled increase in uncertainty during the decision process. Furthermore, for rank-revealing purposes, the selection mechanism in RQRCP produces results that are the same quality as the standard algorithm, but with performance near that of unpivoted QR (often an order of magnitude faster for large matrices). Additionally, we also propose two formulas that facilitate further performance improvements. The first efficiently updates sample matrices to avoid computing new randomized projections. The second avoids large trailing updates during the decomposition in truncated low-rank approximations. Our truncated version of RQRCP also provides a key initial step in our truncated SVD approximation, TUXV. These advances open up a new performance domain for large matrix factorizations that will support efficient problem-solving techniques for challenging applications in science, engineering, and data analysis.

97 MATHEMATICS AND COMPUTING↗

Simulating many-engine spacecraft: Exceeding 1 quadrillion degrees of freedom via information geometric regularization

We present an optimized implementation of the recently proposed information geometric regularization (IGR) for unprecedented scale simulation of compressible fluid flows applied to multi-engine spacecraft boosters. We improve upon state-of-the-art computational fluid dynamics (CFD) techniques in terms of computational cost, memory footprint, and energy-to-solution metrics. Unified memory on coupled CPU–GPU or APU platforms increases problem size with negligible overhead. Mixed half/single-precision storage and computation are used on well-conditioned numerics. We simulate flow at 200 trillion grid points and 1 quadrillion degrees of freedom, exceeding the current record by a factor of 20. A factor of 4 wall-time speedup is achieved over optimized baselines. Ideal weak scaling is observed on OLCF Frontier, LLNL El Capitan, and CSCS Alps using the full systems. Strong scaling is near ideal at extreme conditions, including 80% efficiency on CSCS Alps with an 8 node baseline and stretching to the full system.

Wilfong, Benjamin [Georgia Institute of Technology↗

An efficient hybrid MLFMA-FFT solver for the volume integral equation in case of sparse 3D inhomogeneous dielectric scatterers

Electromagnetic scattering problems involving inhomogeneous objects can be numerically solved by applying a Method of Moments discretization to the volume integral equation. For electrically large problems, the iterative solution of the resulting linear system is expensive, both computationally and in memory use. In this paper, a hybrid MLFMA-FFT method is presented, which combines the fast Fourier transform (FFT) method and the High Frequency Multilevel Fast Multipole Algorithm (MLFMA) in order to reduce the cost of the matrix-vector multiplications needed in the iterative solver. The method represents the scatterers within a set of possibly disjoint identical cubic subdomains, which are meshed using a uniform cubic grid. This specific mesh allows for the application of FFTs to calculate the near interactions in the MLFMA and reduces the memory cost considerably, since the aggregation and disaggregation matrices of the MLFMA can be reused. Additional improvements to the general MLFMA framework, such as an extention of the FFT interpolation scheme of Sarvas et al. from the scalar to the vectorial case in combination with a more economical representation of the radiation patterns on the lowest level in vector spherical harmonics, are proposed and the choice of the subdomain size is discussed. The hybrid method performs better in terms of speed and memory use on large sparse configurations than both the FFT method and the HF MLFMA separately and it has lower memory requirements on general large problems. This is illustrated on a number of representative numerical test cases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Scalable, In-situ Data Clustering Data Analysis for Extreme Scale Scientific Computing (Final Report)

The objective of this project is to address challenges in the design and development of scalable in-situ data clustering and analytics algorithms and software. Our goal is to develop parallel software consisting of a set of spatio-temporal data clustering and anomaly detection functions, both of which are very important for large-scale analysis and have wide applicability for in-situ runs as well as post-processing analysis. Our design principles for in-situ analysis consider the following: (1) identify parts of the computation can be done close to the data within the nodes, while it is still in memory; (2) extract analysis components can (and should) be performed in remote staging and analysis nodes; (3) develop error-bound approximation methods for applications tolerable for small errors; (4) identify the type of derived distributions and statistics, for spatio-temporal data, that can be kept locally in order to both accelerate computations and meet energy constraints in subsequent iterations and phases; (5) use a self-describing data format so that data can be consistent and understood among local storage (memory and SSDs) and at staging and analysis nodes, thereby providing portability and flexibility; (6) develop service-oriented functions that can schedule in-situ and post-hoc analysis tasks based on the dynamic requirements of applications. Our development focus is to produce the parallel data analysis software/library that will be scalable, reusable, extensible, and generic for applications in different disciplines. The software will be able to run in-situ with the simulations as well as post-hoc analysis. This approach will satisfy many synergistic requirements for data intensive applications executed on data coming from instruments and experiments. In particular, the proposed multilevel approach is directly applicable to perform design tradeoffs for running part of the algorithms near the instruments and the rest on remote (analysis) systems.

97 MATHEMATICS AND COMPUTING↗

Sparsity-Independent Lyapunov Exponent in the Sachdev-Ye-Kitaev Model

The saturation of a recently proposed universal bound on the Lyapunov exponent has been conjectured to signal the existence of a gravity dual. This saturation occurs in the low-temperature limit of the dense Sachdev-Ye-Kitaev (SYK) model, N Majorana fermions with q body ( q > 2 ) infinite-range interactions. We calculate certain out-of-time-order correlators (OTOCs) for N ≤ 64 fermions for a highly sparse SYK model and find no significant dependence of the Lyapunov exponent on sparsity up to near the percolation limit where the Hamiltonian breaks up into blocks. This provides strong support to the saturation of the Lyapunov exponent in the low-temperature limit of the sparse SYK. A key ingredient to reaching N = 64 is the development of a novel quantum spin model simulation library that implements highly optimized matrix-free Krylov subspace methods on graphical processing units. This leads to a significantly lower simulation time as well as vastly reduced memory usage over previous approaches, while using modest computational resources. Strong sparsity-driven statistical fluctuations require both the use of a much larger number of disorder realizations with respect to the dense limit and a careful finite size scaling analysis. The saturation of the bound in the sparse SYK points to the existence of a gravity analog that would enlarge substantially the number of field theories with this feature. Published by the American Physical Society 2024

Physics↗

Efficient Management of Complex Striped Files in Active Storage

Active Storage provides an opportunity for reducing the band- width requirements between the storage and compute elements of cur- rent supercomputing systems, and leveraging the processing power of the storage nodes used by some modern file systems. To achieve both objec- tives, Active Storage allows certain processing tasks to be performed directly on the storage nodes, near the data they manage. However, Active Storage must also support key requirements of scientific applications. In particular, Active Storage must be able to support striped files and files with complex formats (e.g., netCDF). In this paper, we describe how these important requirements can be addressed. The experimental results on a Lustre file system not only show that our proposal can re- duce the network traffic to near zero and scale the performance with the number of storage nodes, but also that it provides an efficient treatment of striped files and can manage files with complex data structures.

97 MATHEMATICS AND COMPUTING↗

Comparison of machine learning systems trained to detect Alfvén eigenmodes using the CO 2 interferometer on DIII-D

Abstract A Machine-Learning (ML) based detection scheme that automatically detects Alfvén Eigenmodes (AE) in a labelled DIII-D database is presented here. Controlling AEs is important for the success of planned burning plasma devices such as ITER, since resonant fast ions can drive AEs unstable and degrade the performance of the plasma or damage the first walls of the machine vessel. Artificial Intelligence could be useful for real-time detection and control of AEs in steady-state plasma scenarios by implementing ML-based models into control algorithms that drive actuators for mitigation of AE impacts. Thus, the objective is to compare differences in performance between using two different recurrent neural network systems (Reservoir Computing Network and Long Short Term Memory Network) and two different representations of the C O 2 phase data (simple and crosspower spectrograms). All C O 2 interferometer chords are used to train both models, but only one is processed during each training step. The results from the model and data comparison show higher performance for the RCN model (True Positive Rate = 90% and False Positive Rate = 14%), and that using simple magnitude spectrograms is sufficient to detect AEs. Also, the vertical C O 2 interferometer chord passing near the center is better for ML-based detection of AEs.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Tracer particle transport dynamics in the diffusive sandpile cellular automaton

The confinement properties of the diffusive running sandpile are characterized by tracking the motion of a population of marked grains of sand. It is found that, as the relative strength of the avalanching to the diffusive transport channel is varied, a point is reached at which the particle global confinement time and the probability density functions of the jump-sizes and waiting-times of the tracked grains experience a sudden change, thus revealing a dynamical transition, that is consistent with previous studies (Newman DE et al., Phys Rev Lett 2002;88(20):204304). Across this transition, the sandpile moves from a regime characterized by self-similarity and memory, where avalanches of all possible sizes dominate transport across the system, to another regime where transport is taken over by near system-size, quasi-periodic avalanches. Values for the fractional transport exponents that quantify effective transport across the sandpile prior to the transition are also obtained.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Supramolecular Control of Ionic Retention in Electrolyte-Gated Synaptic Transistors

Electrolyte-gated transistors with ion-trapping layers offer a promising platform for artificial synapses in neuromorphic computing, yet molecular mechanisms governing ionic retention remain poorly understood. Here, in this study, we present a supramolecular approach to modulate ion retention by incorporating a crown ether derivative-based polymer network as an ion-trapping layer on top of a semiconducting monolayer. We show that the balance between ion–host binding and ion–solvent interactions dictates the kinetics of ion capture and release, which in turn controls the memory characteristics of the device. By varying the solvent dielectric constant, we tune the ionic retention time from nearly permanent trapping to rapid relaxation. Intermediate solvent polarity enables programmable short- and long-term synaptic behaviors, including excitatory postsynaptic current, paired-pulse facilitation, and long-term potentiation and depression. These findings establish a direct link between supramolecular ion recognition and synaptic plasticity and provide a generalizable design strategy for ionic–electronic neuromorphic devices.

36 MATERIALS SCIENCE↗

SORA: Scalable Overlap-graph Reduction Algorithms for Genome Assembly using Apache Spark in the Cloud

The advent of high-throughput DNA sequencing techniques has permitted very high quality de novo assemblies of genomes, but raise an issue of requiring large amounts of computer memory to resolve the large genome graphs generated by most overlap graph de novo assemblers. To address these limitations, we present a novel algorithmic approach; Scalable Overlap-graph Reduction Algorithms (SORA). SORA adapts string graph reduction algorithms for the genome assembly using a distributed computing platform. To efficiently compute coverage for enormous paths in the graphs, SORA uses Apache Spark which is a cluster-based engine designed on top of Hadoop to handle very large datasets in the cloud. The experimental results show that SORA can process a nearly one billion edge graph in a distributed cloud cluster as well as smaller graphs on a local cluster with a short turnaround time. Moreover, our algorithms scale almost linearly with increasing numbers of virtual instances in the cloud. SORA is freely available for download at https://github.com/BioHPC/SORA/.

Paul, Alexander↗

pGraph: Efficient Parallel Construction of Large-Scale Protein Sequence Homology Graphs

Detecting sequence homology between protein sequences is a fundamental problem in computational molecular biology, with a pervasive application in nearly all analyses that aim to structurally and functionally characterize protein molecules. While detecting the homology between two protein sequences is relatively inexpensive, detecting pairwise homology for a large number of protein sequences can become computationally prohibitive for modern inputs, often requiring millions of CPU hours. Yet, there is currently no robust support to parallelize this kernel. In this paper, we identify the key characteristics that make this problemparticularly hard to parallelize, and then propose a new parallel algorithm that is suited for detecting homology on large data sets using distributed memory parallel computers. Our method, called pGraph, is a novel hybrid between the hierarchical multiple-master/worker model and producer-consumer model, and is designed to break the irregularities imposed by alignment computation and work generation. Experimental results show that pGraph achieves linear scaling on a 2,048 processor distributed memory cluster for a wide range of inputs ranging from as small as 20,000 sequences to 2,560,000 sequences. In addition to demonstrating strong scaling, we present an extensive report on the performance of the various system components and related parametric studies.

Environmental Molecular Sciences Laboratory↗

Timely Reporting of Heavy Hitters Using External Memory

Given an input stream S of size N, a Φ-heavy hitter is an item that occurs at least ΦN times in S. The problem of finding heavy-hitters is extensively studied in the database literature. In this work, we study a real-time heavy-hitters variant in which an element must be reported shortly after we see its T = Φ N-th occurrence (and hence it becomes a heavy hitter). We call this the Timely Event Detection (TED) Problem. The TED problem models the needs of many real-world monitoring systems, which demand accurate (i.e., no false negatives) and timely reporting of all events from large, high-speed streams with a low reporting threshold (high sensitivity). Like the classic heavy-hitters problem, solving the TED problem without false-positives requires large space (Ω (N) words). Thus in-RAM heavy-hitters algorithms typically sacrifice accuracy (i.e., allow false positives), sensitivity, or timeliness (i.e., use multiple passes). We show how to adapt heavy-hitters algorithms to external memory to solve the TED problem on large high-speed streams while guaranteeing accuracy, sensitivity, and timeliness. Our data structures are limited only by I/O-bandwidth (not latency) and support a tunable tradeoff between reporting delay and I/O overhead. With a small bounded reporting delay, our algorithms incur only a logarithmic I/O overhead. We implement and validate our data structures empirically using the Firehose streaming benchmark. Multi-threaded versions of our structures can scale to process 11M observations per second before becoming CPU bound. In comparison, a naive adaptation of the standard heavy-hitters algorithm to external memory would be limited by the storage device’s random I/O throughput, i.e., ≈100K observations per second.

97 MATHEMATICS AND COMPUTING↗

Traleika Glacier: A hardware-software co-designed approach to exascale computing

The move from current petascale machines to future exascale machines will need both hardware improvements and software changes. Hardware will need to evolve to focus primarily on features that lower energy consumption: near-threshold voltage operation, fine-grained power and clock management and heterogeneity. Software will also need to evolve and be able to express more parallelism, become more dynamic and adaptable in order to be able to operate on a much more variable hardware. Here, we present Traleika Glacier, an effort that seeks to evaluate radical design changes to meet the constraints, both in terms of power and cost, of exascale computing. The salient features of the hardware design presented in the work include a) a use of heterogeneous cores, b) a redesign of the memory system that centers around hierarchical scratchpads and a global address space, c) the hardware acceleration of certain memory and network operations through specialized engines and, d) very fine-grained control and monitoring capabilities. On the software side, we describe a task-based runtime system, the Open Community Runtime (OCR) which aims to express a wide range of higher-level programming models with a very limited set of core concepts: event-driven tasks for computation, events for synchronization and relocatable data-blocks for data management.

97 MATHEMATICS AND COMPUTING↗

A Scalable Gaussian Process Analysis Algorithm for Biomass Monitoring

Biomass monitoring is vital for studying the carbon cycle of earth's ecosystem and has several significant implications, especially in the context of understanding climate change and its impacts. Recently, several change detection methods have been proposed to identify land cover changes in temporal profiles (time series) of vegetation collected using remote sensing instruments, but do not satisfy one or both of the two requirements of the biomass monitoring problem, i.e., {\em operating in online mode} and {\em handling periodic time series}. In this paper, we adapt Gaussian process regression to detect changes in such time series in an online fashion. While Gaussian process (GP) have been widely used as a kernel based learning method for regression and classification, their applicability to massive spatio-temporal data sets, such as remote sensing data, has been limited owing to the high computational costs involved. We focus on addressing the scalability issues associated with the proposed GP based change detection algorithm. This paper makes several significant contributions. First, we propose a GP based online time series change detection algorithm and demonstrate its effectiveness in detecting different types of changes in {\em Normalized Difference Vegetation Index} (NDVI) data obtained from a study area in Iowa, USA. Second, we propose an efficient Toeplitz matrix based solution which significantly improves the computational complexity and memory requirements of the proposed GP based method. Specifically, the proposed solution can analyze a time series of length $t$ in $O(t^2)$ time while maintaining a $O(t)$ memory footprint, compared to the $O(t^3)$ time and $O(t^2)$ memory requirement of standard matrix manipulation based methods. Third, we describe a parallel version of the proposed solution which can be used to simultaneously analyze a large number of time series. We study three different parallel implementations: using threads, MPI, and a hybrid implementation using threads and MPI. Experimental results show that the hybrid implementation scales better than the multi-threaded and MPI based implementations. The application of the proposed scalable algorithm is demonstrated in analyzing massive remote sensing observation data. The hybrid implementation, using 1536 computing cores, can analyze an NDVI data set for the Iowa study area in nearly 5 seconds, while a serial algorithm, using standard Cholesky decomposition based routines, takes several days to process the same data set.

09 BIOMASS FUELS↗