Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory device”

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 271 records · Page 15

Performance Potential of Mixed Data Management Modes for Heterogeneous Memory Systems

Many high-performance systems now include different types of memory devices within the same compute platform to meet strict performance and cost constraints. Such heterogeneous memory systems often include an upper-level tier with better performance, but limited capacity, and lower-level tiers with higher capacity, but less bandwidth and longer latencies for reads and writes. To utilize the different memory layers efficiently, current systems rely on hardware-directed, memory -side caching or they provide facilities in the operating system (OS) that allow applications to make their own data-tier assignments. Since these data management options each come with their own set of trade-offs, many systems also include mixed data management configurations that allow applications to employ hardware- and software-directed management simultaneously, but for different portions of their address space. Despite the opportunity to address limitations of stand-alone data management options, such mixed management modes are under-utilized in practice, and have not been evaluated in prior studies of complex memory hardware. In this work, we develop custom program profiling, configurations, and policies to study the potential of mixed data management modes to outperform hardware- or software-based management schemes alone. Our experiments, conducted on an Intel ® Knights Landing platform with high-bandwidth memory, demonstrate that the mixed data management mode achieves the same or better performance than the best stand-alone option for five memory intensive benchmark applications (run separately and in isolation), resulting in an average speedup compared to the best stand-alone policy of over 10 %, on average.

Effler, Chad↗

Spatiotemporal Thermal Coupling in VO 2 Device Arrays

Correlated oxides such as VO 2 exhibit an electrically driven insulator–metal transition (IMT) that underlies their promise for neuromorphic and memory devices. Yet the IMT is not a uniform bulk process but a spatiotemporal phenomenon in which local heating nucleates filaments, contracts or dissolves them with the electric field, and couples to the environment. In this work, we directly image the VO 2 IMT dynamics by mid-wave infrared, thermography synchronized with electrical transport, resolving device temperature with micrometer spatial and microsecond temporal resolution. At the single-device level, we capture the full cycle of filament nucleation, contraction, and relaxation during current/voltage-driven resistive switching. At the array level, we show that heat propagates across etched gaps with an effective length scale of ∼131 µm, enabling cooperative behaviors among electrically isolated devices. Short-range distanced devices exhibit mutual filament attraction and sequential dissolution, while long-range distanced devices differentiate into distinct roles: drivers that initiate switching, cooperative responders that undergo assisted self-oscillations, and passive reporters that record the thermal field. Furthermore, these results reframe thermal crosstalk, long regarded as parasitic, as an intrinsic coupling channel and design principle for organizing collective switching behaviors, with direct implications for emergent circuit functionality in neuromorphic and unconventional computing architectures.

coupling↗

Hod Carrier

SAND2023-06720O Hod Carrier is a simple proof-of-concept library for moving data from host to NVIDIA BlueField device memory using remote direct memory access. The Hod Carrier software also facilitates research activities related to the potential uses of NVIDIA BlueField data processing unit devices. Using well-established technologies (e.g., RDMA over Infiniband), it will move data from the host to the data processing unit’s memory. This software is a middleware utility for moving data without regard to its semantic meaning. Its operation is fundamentally unaffected by storage allocation. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

SciDAC↗

Si Doped Hafnium Oxide-A “Fragile” Ferroelectric System

Here, silicon doped hafnium oxide was the material used in the original report of ferroelectricity in hafnia in 2011. Since then, it has been subject of many further publications including the demonstration of the world's first ferroelectric field-effect transistor in the state-of-the-art 28 nm technology. Though many studies are conducted with a strong focus on application in memory devices, a comprehensive study on structural stability in these films remains to be seen. In this work, a film thickness of about 36 nm, instead of the 10 nm used in most previous studies, is utilized to carefully probe how the concentration range impacts the evolution of phases, the dopant distribution, the field cycling effects, and their interplay in the macroscopic ferroelectric response of the films. Si:HfO2 appears to be a rather fragile system: different phases seem close in energy and the system is thus rich in competing phenomena. Nonetheless, it offers ferroelectricity or field-induced ferroelectricity for elevated annealing conditions up to 1000 °C. Similar to the measures taken for conventional ferroelectrics such as lead zirconate titanate, engineering efforts to guarantee stable interfaces and stoichiometry are mandatory to achieve stable performance in applications such as ferroelectric memories, supercapacitors, or energy harvesting devices.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Algorithmic optimization of quantum optical storage in solids

Quantum memory devices with high storage efficiency and bandwidth are essential elements for future quantum networks. Solid-state quantum memories can provide broadband storage, but they primarily suffer from low storage efficiency. We use passive optimization and algorithmic optimization techniques to demonstrate nearly a sixfold enhancement in quantum memory efficiency. In this regime, we demonstrate coherent and single-photon-level storage with a high signal-to-noise ratio. The optimization technique presented here can be applied to most solid-state quantum memories to significantly improve the storage efficiency without compromising the memory bandwidth. Published by the American Physical Society 2024

Lei, Yisheng↗

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↗

Nanoprobe Based Information Processing: Nanoprobe‐Electronics

Abstract With computational architectures becoming data‐centric and with the rise of in‐memory computing, the role of memory will be ever more crucial. In turn, storing massive amount of data demands for ultra‐low power and non‐volatile types necessitating new memory technologies. Here, a controllable nanoelectromechanical (NEM) spin memory is proposed for compact nonvolatile memory arrays. It combines the advantages of both nanomechanical and spin‐transfer torque (STT) magnetic memory devices to overcome fundamental scalability roadblocks of non‐hybrid alternatives. The hybrid system paves the way to a new memory technology in the regime of sub‐10‐nm lateral size with a sub‐1‐MA cm −2 switching energy.

Yi, Bao↗

Low Power, Radiation Resilient Synchronous Edge Processing for Remote Monitoring

Next-generation space remote sensing systems may be equipped with imaging arrays that sense data at a rate that outstrips the processing capability of any computing hardware that can operate within a satellite’s power budget. This project developed novel convolutional and recurrent neural networks to detect and estimate point-like events amid clutter, and investigated their efficient and accurate implementation on analog in-memory computing systems that are 10-1000× more energy-efficient than digital processors. This project leveraged two memory devices at different levels of technological maturity: a large-scale analog computing prototype using commercial SONOS charge-trap memory, and electrochemical memory (ECRAM) with intrinsic radiation hardness. We experimentally demonstrated end-to-end analog processing of our neural networks on SONOS and characterized the radiation response of both SONOS and ECRAM. We advanced the state-of-the-art in ECRAM precision and reliability, and developed co-design methods to enable accurate long-term operation of SONOS analog accelerators in space radiation environments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Local rollback for fault-tolerance in parallel computing systems

A control logic device performs a local rollback in a parallel super computing system. The super computing system includes at least one cache memory device. The control logic device determines a local rollback interval. The control logic device runs at least one instruction in the local rollback interval. The control logic device evaluates whether an unrecoverable condition occurs while running the at least one instruction during the local rollback interval. The control logic device checks whether an error occurs during the local rollback. The control logic device restarts the local rollback interval if the error occurs and the unrecoverable condition does not occur during the local rollback interval.

97 MATHEMATICS AND COMPUTING↗

PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications

Iterative memory-bound solvers commonly occur in HPC codes. Typical GPU implementations have a loop on the host side that invokes the GPU kernel as much as time/algorithm steps there are. The termination of each kernel implicitly acts the barrier required after advancing the solution every time step. We propose an execution model for running memory-bound iterative GPU kernels: PERsistent KernelS (PERKS). In this model, the time loop is moved inside persistent kernel, and device-wide barriers are used for synchronization. We then reduce the traffic to device memory by caching subset of the output in each time step in the unused registers and shared memory. PERKS can be generalized to any iterative solver: they largely independent of the solver's implementation. We explain the design principle of PERKS and demonstrate effectiveness of PERKS for a wide range of iterative 2D/3D stencil benchmarks (geomean speedup of 2.12x for 2D stencils and 1.24x for 3D stencils over state-of-art libraries), and a Krylov subspace conjugate gradient solver (geomean speedup of 4.86x in smaller SpMV datasets from SuiteSparse and 1.43x in larger SpMV datasets over a state-of-art library). All PERKS-based implementations available at: https://github.com/neozhang307/PERKS.

Zhang, Lingqi↗

Energy and Area Efficiency in Neuromorphic Computing for Resource Constrained Devices

Resource constrained devices are the building blocks of the internet of things (IoT) era. Since the idea behind IoT is to develop an interconnected environment where the devices are tiny enough to operate with limited resources, several control systems have been built to maintain low energy and area consumption while operating as IoT edge devices. Several researchers have begun work on implementing control systems built from resource constrained devices using machine learning. However, there are many ways such devices can achieve lower power consumption and area utilization while maximizing application efficiency. Spiky neuromorphic computing (SNC) is an emerging paradigm that can be leveraged in resource constrained devices for several emerging applications. While delivering the benefits of machine learning, SNC also helps minimize power consumption. For example, low energy memory devices (memristors) are often used to achieve low power operation and also help in reducing system area. In total, we anticipate SNC will provide computational efficiency approaching that of deep learning while using low power, resource constrained devices.

Chakma, Gangotree↗

End-group-directed self-assembly of organic compounds useful for photovoltaic applications

The present invention provides for an organic compound comprising electron deficient unit covalently linked to two or more electron rich units. The present invention also provides for a device comprising the organic compound, such as a light-emitting diode, thin-film transistor, chemical biosensor, non-emissive electrochromic, memory device, photovoltaic cells, or the like.

14 SOLAR ENERGY↗

Femtosecond x-ray diffraction reveals a liquid–liquid phase transition in phase-change materials

In phase-change memory devices, a material is cycled between glassy and crystalline states. The highly temperature-dependent kinetics of its crystallization process enables application in memory technology, but the transition has not been resolved on an atomic scale. Using femtosecond x-ray diffraction and ab initio computer simulations, we determined the time-dependent pair-correlation function of phase-change materials throughout the melt-quenching and crystallization process. We found a liquid–liquid phase transition in the phase-change materials Ag 4 In 3 Sb 67 Te 26 and Ge 15 Sb 85 at 660 and 610 kelvin, respectively. The transition is predominantly caused by the onset of Peierls distortions, the amplitude of which correlates with an increase of the apparent activation energy of diffusivity. This reveals a relationship between atomic structure and kinetics, enabling a systematic optimization of the memory-switching kinetics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Static power reduction for midpoint-terminated busses

A memory system is disclosed which is comprised of a memory controller and addressable memory devices such as DRAMs. The invention provides a programmable register to control the high vs. low drive state of each bit of a memory system address and control bus during periods of bus inactivity. In this way, termination voltage supply current can be minimized, while permitting selected bus bits to be driven to a required state. This minimizes termination power dissipation while not affecting memory system performance. The technique can be extended to work for other high-speed busses as well.

97 MATHEMATICS AND COMPUTING↗

Electron-beam-induced-current and active secondary-electron voltage-contrast with aberration-corrected electron probes

The ability to map out electrostatic potentials in materials is critical for the development and the design of nanoscale electronic and spintronic devices in modern industry. Electron holography has been an important tool for revealing electric and magnetic field distributions in microelectronics and magnetic-based memory devices, however, its utility is hindered by several practical constraints, such as charging artifacts and limitations in sensitivity and in field of view. In this article, we report electron-beam-induced-current (EBIC) and secondary-electron voltage-contrast (SE-VC) with an aberration-corrected electron probe in a transmission electron microscope (TEM), as complementary techniques to electron holography, to measure electric fields and surface potentials, respectively. These two techniques were applied to ferroelectric thin films, multiferroic nanowires, and single crystals. Electrostatic potential maps obtained by off-axis electron holography were compared with EBIC and SE-VC to show that these techniques can be used as a complementary approach to validate quantitative results obtained from electron holography analysis.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Polarization-coupled tunable resistive behavior in oxide ferroelectric heterostructures

This research focuses on investigation of the physical mechanism of the electrically and mechanically tunable resistive behavior in oxide ferroelectric heterostructures with engineered interfaces realized via a strong coupling of ferroelectric polarization with tunneling electroresistance and metal-insulator (M-I) transitions. This report describes observation of electrically conductive domain walls in semiconducting ferroelectrics, voltage-free control of resistive switching and demonstration of a new mechanism of electrical control of 2D electron gas (2DEG) at oxide interfaces. The research goals are achieved by creating strong synergy between cutting-edge fabrication of epitaxial single-crystalline complex oxides, nanoscale electrical characterization by scanning probe microscopy and theoretical modeling of the observed phenomena. The concept of the ferroelectric devices with electrically and mechanically tunable nonvolatile resistance represents a new paradigm shift in realization of the next-generation of non-volatile memory devices and low-power logic switches.

36 MATERIALS SCIENCE↗

LastingNVCache: A Technique for Improving the Lifetime of Non-volatile Caches

Use of NVM (Non-volatile memory) devices such as ReRAM (resistive RAM) and STT-RAM (spin transfer torque RAM) for designing on-chip caches holds the promise of providing a high-density, low-leakage alternative to SRAM. However, low write endurance of NVMs, along with the write-variation introduced by existing cache management schemes may significantly limit the lifetime of NVM caches. We present LastingNVCache, a technique for improving lifetime of NVM caches by mitigating the intra-set write variation. LastingNVCache works on the key idea that by periodically flushing a frequently-written data-item, the next time the block can be made to load into a cold block in the set. Through this, the future writes to that data-item can be redirected from a hot block to a cold block, which leads to improvement in the cache lifetime. Microarchitectural simulations have shown that LastingNVCache provides 6.36X, 9.79X, and 10.94X improvement in lifetime for single, dual and quad-core systems. Also, its implementation overhead is small and it outperforms a recently proposed technique for improving lifetime of NVM caches.

device lifetime↗

Using DMA for copying performance counter data to memory

A device for copying performance counter data includes hardware path that connects a direct memory access (DMA) unit to a plurality of hardware performance counters and a memory device. Software prepares an injection packet for the DMA unit to perform copying, while the software can perform other tasks. In one aspect, the software that prepares the injection packet runs on a processing core other than the core that gathers the hardware performance data.

97 MATHEMATICS AND COMPUTING↗