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 487 records · Page 27

Scaling Linear Algebra Kernels using Remote Memory Access

This paper describes the scalability of linear algebra kernels based on remote memory access approach. The current approach differs from the other linear algebra algorithms by the explicit use of shared memory and remote memory access (RMA) communication rather than message passing. It is suitable for clusters and scalable shared memory systems. The experimental results on large scale systems (Linux-Infiniband cluster, Cray XT) demonstrate consistent performance advantages over ScaLAPACK suite, the leading implementation of parallel linear algebra algorithms used today. For example, on a Cray XT4 for a matrix size of 102400, our RMA-based matrix multiplication achieved over 55 teraflops while ScaLAPACK’s pdgemm measured close to 42 teraflops on 10000 processes.

99 GENERAL AND MISCELLANEOUS↗

Unraveling Network-induced Memory Contention: Deeper Insights with Machine Learning

Remote Direct Memory Access (RDMA) is expected to be an integral communication mechanism for future exascale systems enabling asynchronous data transfers, so that applications may fully utilize CPU resources while simultaneously sharing data amongst remote nodes. We examine Network-induced Memory Contention (NiMC) on Infiniband networks. We expose the interactions between RDMA, main-memory and cache, when applications and out-of-band services compete for memory resources. We then explore NiMCs resulting impact on application-level performance. For a range of hardware technologies and HPC workloads, we quantify NiMC and show that NiMCs impact grows with scale resulting in up to 3X performance degradation at scales as small as 8K processes even in applications that previously have been shown to be performance resilient in the presence of noise. In addition, this work examines the problem of predicting NiMC's impact on applications by leveraging machine learning and easily accessible performance counters. This approach provides additional insights about the root cause of NiMC and facilitates dynamic selection of potential solutions. Finally, we evaluated three potential techniques to reduce NiMCs impact, namely hardware offloading, core reservation and network throttling.

97 MATHEMATICS AND COMPUTING↗

Distributed-memory lattice H-matrix factorization

We parallelize the LU factorization of a hierarchical low-rank matrix (H-matrix) on a distributed-memory computer. This is much more difficult than the H-matrix-vector multiplication due to the dataflow of the factorization, and it is much harder than the parallelization of a dense matrix factorization due to the irregular hierarchical block structure of the matrix. Block low-rank (BLR) format gets rid of the hierarchy and simplifies the parallelization, often increasing concurrency. However, this comes at a price of losing the near-linear complexity of the H-matrix factorization. In this work, we propose to factorize the matrix using a “lattice H-matrix” format that generalizes the BLR format by storing each of the blocks (both diagonals and off-diagonals) in the H-matrix format. These blocks stored in the H-matrix format are referred to as lattices. Thus, this lattice format aims to combine the parallel scalability of BLR factorization with the near-linear complexity of H-matrix factorization. We first compare factorization performances using the H-matrix, BLR, and lattice H-matrix formats under various conditions on a shared-memory computer. Our performance results show that the lattice format has storage and computational complexities similar to those of the H-matrix format, and hence a much lower cost of factorization than BLR. In conclusion, we then compare the BLR and lattice H-matrix factorization on distributed-memory computers. Our performance results demonstrate that compared with BLR, the lattice format with the lower cost of factorization may lead to faster factorization on the distributed-memory computer.

97 MATHEMATICS AND COMPUTING↗

Collective Memory Transfers for Multi-Core Chips

Future performance improvements for microprocessors have shifted from clock frequency scaling towards increases in on-chip parallelism. Performance improvements for a wide variety of parallel applications require domain-decomposition of data arrays from a contiguous arrangement in memory to a tiled layout for on-chip L1 data caches and scratchpads. How- ever, DRAM performance suffers under the non-streaming access patterns generated by many independent cores. We propose collective memory scheduling (CMS) that actively takes control of collective memory transfers such that requests arrive in a sequential and predictable fashion to the memory controller. CMS uses the hierarchically tiled arrays formal- ism to compactly express collective operations, which greatly improves programmability over conventional prefetch or list- DMA approaches. CMS reduces application execution time by up to 32% and DRAM read power by 2.2×, compared to a baseline DMA architecture such as STI Cell.

97 MATHEMATICS AND COMPUTING↗

Deformation and Failure Mechanisms of Shape Memory Alloys

The goal of this research was to understand the fundamental mechanics that drive the deformation and failure of shape memory alloys (SMAs). SMAs are difficult materials to characterize because of the complex phase transformations that give rise to their unique properties, including shape memory and superelasticity. These phase transformations occur across multiple length scales (one example being the martensite-austenite twinning that underlies macroscopic strain localization) and result in a large hysteresis. In order to optimize the use of this hysteretic behavior in energy storage and damping applications, we must first have a quantitative understanding of this transformation behavior. Prior results on shape memory alloys have been largely qualitative (i.e., mapping phase transformations through cracked oxide coatings or surface morphology). The PI developed and utilized new approaches to provide a quantitative, full-field characterization of phase transformation, conducting a comprehensive suite of experiments across multiple length scales and tying these results to theoretical and computational analysis. The research funded by this award utilized new combinations of scanning electron microscopy, diffraction, digital image correlation, and custom testing equipment and procedures to study phase transformation processes at a wide range of length scales, with a focus at small length scales with spatial resolution on the order of 1 nanometer. These experiments probe the basic connections between length scales during phase transformation. In addition to the insights gained on the fundamental mechanisms driving transformations in shape memory alloys, the unique experimental methodologies developed under this award are applicable to a wide range of solid-to-solid phase transformations and other strain localization mechanisms.

36 MATERIALS SCIENCE↗

Parallel Asynchronous Distributed-Memory Maximal Independent Set Algorithm with Work Ordering

The maximal independent set (MIS) graph problem arises in many applications such as computer vision, information theory, molecular biology, and process scheduling. The growing scale of graph data suggests the use of distributed memory hardware as a cost-effective approach to providing necessary compute and memory resources. Existing distributed memory parallel MIS algorithms rely on synchronous communication and use techniques such as subgraph computations. In this paper, we present an asynchronous distributed-memory parallel graph algorithm that relies on a virtual directed acyclic graph (DAG) that is created during the algorithm execution. We introduce two additional algorithms that save computations by ordering generated work. The first algorithm applies ordering globally to reduce computations, and the second algorithm applies ordering locally at the level of threads to minimize the synchronization overhead. We use two different implementations of Luby’s algorithm variants as baseline to compare the performance of the presented algorithms: (1) vertex-centric Luby A and Luby B implementations, and (2) the CombBLAS linear-algebra Luby A implementation. Results show that proposed algorithms outperform both implementations of Luby algorithms, especially in distributed execution. Furthermore, we show that for low-diameter graphs the algorithm that applies global ordering scales better than other algorithms and for high diameter graphs the original asynchronous algorithm and thread-level ordering algorithm show better performance.

maximal independent set (MIS), distributed memory ↗

UNITY: Unified Memory and Storage Space

UNITY is a 36-month project focused on providing design and evaluate a new distributed storage paradigm that unifies the traditionally distinct application views of memory- and file-based data storage into a single scalable and resilient environment. The project is a collaboration among Oak Ridge National Laboratory (ORNL, Lead institution), Los Alamos National Labs (LANL), and Georgia Tech (GT). The main contributions of the GT team have been around development of low level systems software for best leveraging the capabilities of new types of persistent memory technologies, and for development of methods for intelligent data management across memory/storage substrates with heterogeneous components. GT contributed the Phoenix library for optimized checkpoint/restart for HPC I/O for systems with non-volatile memory (NVM), the NVStream library for NVM-specialized streaming I/O for HPC workflows, the CoMerge, Mnemo and Kleio solutions for intelligent data management on NVM-based systems. These contributions result in significant improvements in both application performance and system efficiency.

97 MATHEMATICS AND COMPUTING↗

Memorial Pools Energy Efficiency Retrofits

The National September 11 Memorial & Museum completed a retrofit of the submergible LED lighting fixtures in its North and South Memorial Pools, located at the World Trade Center site in New York City. The two one-acre pools are illuminated nightly by custom LED fixtures set into their base, and the original lights — in place since 2011 — had begun reaching the end of their useful life, leaving sections of the pools dim or dark. Rather than fully replacing the fixtures, the project team worked with the original manufacturer, Acuity Brands, to retrofit and reuse existing components across all eight pool walls (34 fixtures per wall), reducing cost and waste. Fixtures were shipped in custom crates to Minnesota for retrofitting, then reinstalled onsite by Memorial & Museum staff and contractor ABM. The team addressed two key technical challenges during the project: early leakage in retrofitted fixtures, resolved by introducing vacuum-sealing and nitrogen-fill testing before shipment; and chord damage during transit, resolved with custom-designed shipping crates. All eight pool walls were successfully retrofitted and reinstalled by August 27, 2025, ahead of the 25th anniversary of the September 11, 2001 attacks. Sitewide electrical consumption in September 2025 reflected an approximate 7% reduction, contributing to the institution's broader net-zero and LEED Gold sustainability goals.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Total-Ionizing-Dose Effects on Long-term Data Retention Characteristics of Commercial 3-D NAND Memories

This article evaluates the data retention characteristics of irradiated multi-level cell (MLC) 3-D NAND flash memories. We irradiate the memory chips by a Co-60 gamma-ray source for up to 50 krad(Si) and then write a random data pattern on the irradiated chip to find its retention characteristics. The experimental results show that the data retention property of the irradiated chips is significantly degraded compared to the un-irradiated ones. We evaluate two independent strategies to improve the data retention characteristics of the irradiated chips. Furthermore, the first method involves high-temperature annealing of the irradiated chip while the second method suggests pre-programming the memory modules before deploying them in radiation-prone environments.

3-D NAND flash↗

Optical Memory, Switching, and Neuromorphic Functionality in Metal Halide Perovskite Materials and Devices

Metal halide perovskite-based materials have emerged over the past few decades as remarkable solution-processable opto-electronic materials with many intriguing properties and potential applications. Notably, these emerging materials have recently been considered for their promise in low-energy memory and information processing applications. In particular, their large optical cross-sections, high photoconductance contrast, large carrier diffusion lengths, and mixed electronic/ionic transport mechanisms are attractive for enabling memory elements and neuromorphic devices that are written and/or read in the optical domain. Here, we review recent progress towards memory and neuromorphic functionality in metal halide perovskite materials and devices where photons are used as a critical degree of freedom for switching, memory, and neuromorphic functionality.

14 SOLAR ENERGY↗

Nonvolatile Electrochemical Random‐Access Memory under Short Circuit

Abstract Electrochemical random‐access memory (ECRAM) is a recently developed and highly promising analog resistive memory element for in‐memory computing. One longstanding challenge of ECRAM is attaining retention time beyond a few hours. This short retention has precluded ECRAM from being considered for inference classification in deep neural networks, which is likely the largest opportunity for in‐memory computing. In this work, an ECRAM cell with orders of magnitude longer retention than previously achieved is developed, and which is anticipated to exceed ten years at 85 °C. This study hypothesizes that the origin of this exceptional retention is phase separation, which enables the formation of multiple effectively equilibrium resistance states. This work highlights the promises and opportunities to use phase separation to yield ECRAM cells with exceptionally long, and potentially permanent, retention times.

Kim, Diana S.↗

From shockwaves to the gravitational memory effect

We study the relationship between shockwave geometries and the gravitational memory effect in four-dimensional asymptotically flat spacetime. In particular, we show the ’t Hooft commutation relations of shockwave operators are equivalent to the commutation relation between soft and Goldstone modes parametrizing a sector of the gravitational phase space. We demonstrate this equivalence via a diffeomorphism that takes a shockwave metric to a metric whose transverse traceless component is the gravitational memory. The shockwave momentum in ’t Hooft’s analysis is related to the soft graviton mode, which is responsible for the memory effect, while the shift in the shockwave position is related to the Goldstone mode. This equivalence opens new directions to utilize the gravitational memory effect to explore the observational implications of shockwave geometries in flat space.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Disrupting nNOS-PSD-95 coupling in the hippocampal dentate gyrus promotes extinction memory retrieval

Granule cells in the dentate gyrus regenerate constantly in adult hippocampus and then integrate into neural circuits in the hippocampus thereby providing the neural basis for learning and memory. Promoting the neurogenesis in the hippocampus facilitates learning and memory such as spatial learning, object identification, and extinction learning. The interaction between neuronal nitric oxide synthase (nNOS) and postsynaptic density protein-95 (PSD-95) is reported to negatively regulate neurogenesis in brain, so we hypothesized that disrupting this interaction might facilitate the neurogenesis in the dentate gyrus (DG) and thus enhance the extinction memory retrieval of fear learning. We found that uncoupling the nNOS-PSD-95 complex in remote contextual fear condition promoted both neuronal proliferation and survival in the DG, contributing to an enhanced retrieval of the extinction memory. Moreover, the nNOS-PSD-95 uncoupling-induced neurogenesis may be mediated by the extracellular signal-regulated kinase (ERK) as the phosphorylation level of ERK1/2 was increased after uncoupling. These findings suggest that the nNOS-PSD-95 complex may serve as a novel target for the treatment of post-traumatic stress disorder (PTSD). - Highlights: • nNOS-PSD-95 disruption promoted neurogenesis in the DG. • Delayed disruption of nNOS-PSD-95 still enhanced remote contextual fear extinction. • The enhancement of fear extinction relied on neuronal proliferation. • nNOS-PSD-95 disruption increased ERK1/2 phosphorylation.

60 APPLIED LIFE SCIENCES↗

Sirtuin 7 is involved in the consolidation of fear memory in mice

Highlights: • SIRT7 is involved in many biological processes. • The functional role of SIRT7 in the brain is unknown. • We demonstrate that SIRT7 is expressed in the amygdala and hippocampus. • Fear memory consolidation was impaired in Sirt7 knockout mice. • SIRT7 is involved in the consolidation of fear memory. Sirtuin 7 (SIRT7) is an NAD{sup +}-dependent deacetylase/deacylase, and is involved in a variety of biological processes relevant to the transcription of rRNA, the DNA damage response, tumorigenesis, and metabolism. SIRT7 mRNA is expressed ubiquitously, including in the brain, but there is no detailed information about the anatomical distribution and functional role of SIRT7 in the brain. Here, we demonstrated that SIRT7 is widely expressed in the mouse brain, including in the cortex, striatum, thalamus, hippocampus, and amygdala. Behavioral examinations revealed that Sirt7 knockout (KO) and control mice showed similar levels of freezing behavior immediately after a fear response, but a significant decrease of freezing behavior at 24 h after fear conditioning was observed in Sirt7 KO mice. Histological analysis revealed that there is no apparent structural abnormality of the amygdala and hippocampus, which are regions involved in fear memory consolidation, in Sirt7 KO mice. Our results indicate that SIRT7 is involved in the consolidation of fear memory.

60 APPLIED LIFE SCIENCES↗

Attenuation of zinc-enhanced inflammatory M1 phenotype of microglia by peridinin protects against short-term spatial-memory impairment following cerebral ischemia in mice

Highlights: • Peridinin suppressed zinc-enhanced inflammatory M1 phenotype of microglia. • Zinc-increased microglial ROS level was abolished by peridinin. • Peridinin protected mice from ischemia-induced deficits in short-term spatial memory. Activated microglia exhibit two opposite activation states, the inflammatory M1 and the anti-inflammatory M2 activation states. In the mammalian brain, ischemia elicits a massive release of zinc from hippocampal neurons, and the extracellular zinc primes M1 microglia—by inducing reactive oxygen species (ROS) generation—to enhance their production of proinflammatory cytokines, which ultimately results in short-term spatial memory impairment. Here, we examined how peridinin, a carotenoid in dinoflagellates, affects the zinc-enhanced inflammatory M1 phenotype of microglia. Treatment of microglia with 30–300 ng/mL peridinin caused a dose-dependent attenuation of zinc-enhanced interleukin (IL)-1β, IL-6, and tumor necrosis factor-α (TNFα) secretion when M1 activation was induced by lipopolysaccharide exposure. Moreover, peridinin inhibited the increase in ROS levels in zinc-treated microglia without directly interacting with zinc. Notably, when mice were administrated peridinin (20–200 ng/animal) intracerebroventricularly 5 min before cerebral ischemia-reperfusion, the peridinin treatment not only suppressed the increase in expression of IL-1β, IL-6, TNFα, and the microglial M1 surface marker CD16/32, but also protected the mice against ischemia-induced short-term spatial-memory impairment. Our findings suggest that peridinin prevents extracellular zinc-enhanced proinflammatory cytokine secretion from M1 microglia by inhibiting the increase in microglial ROS levels, and that this anti-inflammatory effect of peridinin might result in protection against deficits in short-term spatial memory.

60 APPLIED LIFE SCIENCES↗

Speeding up and reducing memory usage for scientific machine learning via mixed precision

Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems. Within this field, physics-informed neural networks (PINNs) and deep operator networks (DeepONets) stand out as the leading techniques for solving partial differential equations by incorporating both physical equations and experimental data. However, training PINNs and DeepONets require significant computational resources, including long computational times and large amounts of memory. In search of computational efficiency, training neural networks using half precision (float16) rather than the conventional single (float32) or double (float64) precision has gained substantial interest, given the inherent benefits of reduced computational time and memory consumed. However, we find that float16 cannot be applied to SciML methods, because of gradient divergence at the start of training, weight updates going to zero, and the inability to converge to a local minima. To overcome these limitations, we explore mixed precision, which is an approach that combines the float16 and float32 numerical formats to reduce memory usage and increase computational speed. Our experiments showcase that mixed precision training not only substantially decreases training times and memory demands but also maintains model accuracy. Here, we also reinforce our empirical observations with a theoretical analysis. The research has broad implications for SciML in various computational applications.

97 MATHEMATICS AND COMPUTING↗

Kokkos: Enabling manycore performance portability through polymorphic memory access patterns

The manycore revolution can be characterized by increasing thread counts, decreasing memory per thread, and diversity of continually evolving manycore architectures. High performance computing (HPC) applications and libraries must exploit increasingly finer levels of parallelism within their codes to sustain scalability on these devices. We found that a major obstacle to performance portability is the diverse and conflicting set of constraints on memory access patterns across devices. Contemporary portable programming models address manycore parallelism (e.g., OpenMP, OpenACC, OpenCL) but fail to address memory access patterns. The Kokkos C++ library enables applications and domain libraries to achieve performance portability on diverse manycore architectures by unifying abstractions for both fine-grain data parallelism and memory access patterns. In this paper we describe Kokkos’ abstractions, summarize its application programmer interface (API), present performance results for unit-test kernels and mini-applications, and outline an incremental strategy for migrating legacy C++ codes to Kokkos. Furthermore, the Kokkos library is under active research and development to incorporate capabilities from new generations of manycore architectures, and to address a growing list of applications and domain libraries.

97 MATHEMATICS AND COMPUTING↗

FLAMES─Fast, Low-Storage, Accurate, and Memory-Efficient Adaptive Sampling─Approach to Resolve Spatially Dependent Dynamics of Molecular Liquids

Many critical phenomena in soft matter occur at large length scales, necessitating the resolution of their structure and dynamics at low wavenumbers. However, resolving wavenumber-dependent dynamics computationally via molecular dynamics simulations presents significant challenges, as these phenomena span several orders of magnitude in both time and length scales, resulting in high computational costs and memory demands. Here, this work highlights the computational and memory challenges associated with analyzing molecular trajectories in reciprocal space and demonstrates a method to address them. We introduce FLAMESFast, Low-storage, Accurate, and Memory-Efficient adaptive Sampling, which is a direct method for calculation of structure factors, allowing us to select only the required number of wavevectors for binning. We also use wavenumber-dependent time steps to extract dynamics. Our FLAMES approach effectively mitigates computational and memory/storage bottlenecks. We demonstrate the method using simulations of a model system, liquid octane, at various temperatures. Comparisons with experimental data and real space computation show that the FLAMES technique achieves high accuracy in resolving temperature- and spatially dependent dynamics while being significantly more computationally efficient and requiring less memory and storage than methods based on a uniform wavevector grid and fixed temporal spacing.

Chen, Guang [Argonne National Laboratory (ANL), Ar↗