Search NASA⌕ Search

SEARCH · Search NASA

Results for “MEMORY DEVICES”

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 955 records · Page 53

Phase-change heterostructure enables ultralow noise and drift for memory operation

Artificial intelligence and other data-intensive applications have escalated the demand for data storage and processing. New computing devices, such as phase-change random access memory (PCRAM)–based neuro-inspired devices, are promising options for breaking the von Neumann barrier by unifying storage with computing in memory cells. However, current PCRAM devices have considerable noise and drift in electrical resistance that erodes the precision and consistency of these devices. We designed a phase-change heterostructure (PCH) that consists of alternately stacked phase-change and confinement nanolayers to suppress the noise and drift, allowing reliable iterative RESET and cumulative SET operations for high-performance neuro-inspired computing. Our PCH architecture is amenable to industrial production as an intrinsic materials solution, without complex manufacturing procedure or much increased fabrication cost.

Science & Technology - Other Topics↗

Ferromagnetic (Ga,Mn)As nanostructures for spintronic applications

Magneto-resistive, cross-like nanostructures have been designed and fabricated by electron-beam lithography patterning and chemical etching from thin epitaxial layers of the ferromagnetic semiconductor (Ga,Mn)As. The nanostructures, composed of two perpendicular nanostripes crossing in the middle of their length, represent four-terminal devices, in which an electric current can be driven through any of the two nanostripes. In these devices, a novel magneto-resistive memory effect, related to a rearrangement of magnetic domain walls in the central part of the device, has been demonstrated. It consists in that the zero-field resistance of a nanostripe depends on the direction of previously applied magnetic field. The nanostructures can thus work as two-state devices providing basic elements of nonvolatile memory cells.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Data storage technology comparisons

The role of data storage and data storage technology is an integral, though conceptually often underestimated, portion of data processing technology. Data storage is important in the mass storage mode in which generated data is buffered for later use. But data storage technology is also important in the data flow mode when data are manipulated and hence required to flow between databases, datasets and processors. This latter mode is commonly associated with memory hierarchies which support computation. VLSI devices can reasonably be defined as electronic circuit devices such as channel and control electronics as well as highly integrated, solid-state devices that are fabricated using thin film deposition technology. VLSI devices in both capacities play an important role in data storage technology. In addition to random access memories (RAM), read-only memories (ROM), and other silicon-based variations such as PROM's, EPROM's, and EEPROM's, integrated devices find their way into a variety of memory technologies which offer significant performance advantages. These memory technologies include magnetic tape, magnetic disk, magneto-optic disk, and vertical Bloch line memory. In this paper, some comparison between selected technologies will be made to demonstrate why more than one memory technology exists today, based for example on access time and storage density at the active bit and system levels.

Katti, Romney R.↗

CG-Kit: Code Generation Toolkit for performant and maintainable variants of source code applied to Flash-X hydrodynamics simulations

CG-Kit is a new Code Generation tool-Kit that we have developed as a part of the solution for portability and maintainability for multiphysics computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of high-performance computing platforms and the algorithmic complexities of a particular large-scale multiphysics application: Flash-X. To efficiently use computing resources on a heterogeneous node, an application must have a map of computation to resources and a mechanism to move the data and computation to the resources according to the map. Most existing performance portability solutions are focussed on abstracting the expression of computations so that a unified source code can be specialized to run on different resources. However, such an approach is insufficient for a code like Flash-X, which has a multitude of code components that can be assembled in various permutations and combinations to form different instances of applications. Similar challenges apply to any code that has composability, where a single specified way of apportioning work among devices may not be optimal. Additionally, use cases arise where the optimal control flow of computation may differ for different devices while the underlying numerics remain identical. This combination leads to unique challenges including handling an existing large code base in Fortran and/or C/C++, subdivision of code into a great variety of units supporting a wide range of physics and numerical methods, different parallelization techniques for distributed and shared memory systems and accelerator devices, and heterogeneity of computing platforms requiring coexisting variants of parallel algorithms. All of these challenges demand that scientific software developers apply existing knowledge about domain applications, algorithms, and computing platforms to determine custom abstractions and granularity for code generation. There is a critical lack of tools to tackle those problems. CG-Kit is designed to fill this gap by providing a user with the ability to express their desired control flow and computation-to-resource map in the form a pseudocode-like recipe. It consists of standalone tools that can be combined into highly specific and, we argue, highly effective portability and maintainability toolchains. Here we present the design of our new tools: parametrized source trees, control flow graphs, and recipes. The tools are implemented in Python. They are agnostic to the programming language of the source code targeted for code generation. In conclusion, we demonstrate the capabilities of the toolkit with two examples, first, multithreaded variants of the basic AXPY operation, and second, variants of parallel algorithms within a hydrodynamics solver, called Spark, from Flash-X that operates on block-structured adaptive meshes.

Algorithmic portability↗

Recent Advances in Commercial Memories and Potential Contribution to GN&C Miniaturation

The last few years have seen a surge in technology, device, and architecture introductions in commercial memories such as SDRAM and NAND driven by the explosion of handheld and portable electronics. Some of the resultant devices provide high density in very small and light packages, which may be possible to leverage for the miniaturization of future GN&C systems in addition to providing considerable memory capacity to enable advanced capabilities such as image-based navigation or adaptive/autonomous operations. We will show that these advanced SDRAM and NAND technologies are worth serious consideration for the next generation of GN&C needs by highlighting reliability and radiation effects results from some of these devices.

Yang-Scharlotta, Jean Y.↗

Content-addressable memory based enforcement of configurable policies

A monitoring device for monitoring transactions on a bus includes content-addressable memory ("CAM") and a response policy unit. The CAM includes an input coupled to receive a bus transaction tag based on bus traffic on the bus. The CAM stores data tags associated with rules of a security policy to compare the bus transaction tag to the data tags. The CAM generates an output signal indicating whether one or more matches occurred. The response policy unit is coupled to the CAM to receive the output signal from the CAM and to execute a policy action in response to the output signal.

97 MATHEMATICS AND COMPUTING↗

Field-induced domain wall motion of amorphous [CoSiB/Pt]{sub N} multilayers with perpendicular anisotropy

Amorphous CoSiB/Pt multilayer is a perpendicular magnetic anisotropy material to achieve high squareness, low coercivity, strong anisotropy, and smooth domain wall (DW) motion, because of the smoother interface compared with crystalline multilayers. For [CoSiB(6 Å)/Pt (14 Å)]{sub N} multilayers with N = 3, 6, and 9, we studied the field-induced DW dynamics. The effective anisotropy constant K{sub 1}{sup eff} is 1.5 × 10{sup 6} erg/cm{sup 3} for all the N values, and the linear increment of coercive field H{sub c} with N gives constant exchange coupling J. By analyzing the field dependence of DW images at room temperature, a clear creep motion with the exponent μ = 1/4 could be observed. Even though the pinning field H{sub dep} slightly increases with N, the pinning potential energy U{sub c} is constant (=35 k{sub B}T) for all the N values. These results imply that the amorphous [CoSiB/Pt]{sub N} multilayers are inherently homogeneous compared to crystalline multilayers. For N ≤ 6, the pinning site density ρ{sub pin} is less than 1000/μm{sup 2}, which is about 1 pinning site per the typical device junction size of 30 × 30 nm{sup 2}. Also, the exchange stiffness constant A{sub ex} is obtained to be 0.48 × 10{sup −6} erg/cm, and the domain wall width is expected to be smaller than 5.5 nm. These results may be applicable for spin-transfer-torque magnetic random access memory and DW logic device applications.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗

Radiation Effects on Current Field Programmable Technologies

Manufacturers of field programmable gate arrays (FPGAS) take different technological and architectural approaches that directly affect radiation performance. Similar y technological and architectural features are used in related technologies such as programmable substrates and quick-turn application specific integrated circuits (ASICs). After analyzing current technologies and architectures and their radiation-effects implications, this paper includes extensive test data quantifying various devices total dose and single event susceptibilities, including performance degradation effects and temporary or permanent re-configuration faults. Test results will concentrate on recent technologies being used in space flight electronic systems and those being developed for use in the near term. This paper will provide the first extensive study of various configuration memories used in programmable devices. Radiation performance limits and their impacts will be discussed for each design. In addition, the interplay between device scaling, process, bias voltage, design, and architecture will be explored. Lastly, areas of ongoing research will be discussed.

Katz, R.↗

Domain walls riding the wave.

Recent years have witnessed a rapid proliferation of electronic gadgets around the world. These devices are used for both communication and entertainment, and it is a fact that they account for a growing portion of household energy consumption and overall world consumption of electricity. Increasing the energy efficiency of these devices could have a far greater and immediate impact than a gradual switch to renewable energy sources. The advances in the area of spintronics are therefore very important, as gadgets are mostly comprised of memory and logic elements. Recent developments in controlled manipulation of magnetic domains in ferromagnet nanostructures have opened opportunities for novel device architectures. This new class of memories and logic gates could soon power millions of consumer electronic devices. The attractiveness of using domain-wall motion in electronics is due to its inherent reliability (no mechanical moving parts), scalability (3D scalable architectures such as in racetrack memory), and nonvolatility (retains information in the absence of power). The remaining obstacles in widespread use of 'racetrack-type' elements are the speed and the energy dissipation during the manipulation of domain walls. In their recent contribution to Physical Review Letters, Oleg Tretiakov, Yang Liu, and Artem Abanov from Texas A&M University in College Station, provide a theoretical description of domain-wall motion in nanoscale ferromagnets due to the spin-polarized currents. They find exact conditions for time-dependent resonant domain-wall movement, which could speed up the motion of domain walls while minimizing Ohmic losses. Movement of domain walls in ferromagnetic nanowires can be achieved by application of external magnetic fields or by passing a spin-polarized current through the nanowire itself. On the other hand, the readout of the domain state is done by measuring the resistance of the wire. Therefore, passing current through the ferromagnetic wire is the preferred method, as it combines manipulation and readout of the domain-wall state. The electrons that take part in the process of readout and manipulation of the domain-wall structure in the nanowire do so through the so-called spin transfer torque: When spin-polarized electrons in the ferromagnet nanowire pass through the domain wall they experience a nonuniform magnetization, and they try to align their spins with the local magnetic moments. The force that the electrons experience has a reaction force counterpart that 'pushes' the local magnetic moments, resulting in movement of the domain wall in the direction of the electron flow through the spin-transfer torque. The forces between the electrons and the local magnetic moments in the ferromagnet also create additional electrical resistance for the electrons passing through the domain wall. By measuring resistance across a segment of the nanowire, one determines if a domain wall is present; i.e., one can read the stored information. The interaction of the spin-polarized electrons with the domain wall in the ferromagnetic nanowire is not very efficient. Even for materials achieving high polarization of the free electrons, it is very difficult to move the magnetic domain wall. Several factors contribute to this problem, with imperfections of the ferromagnetic nanowire that cause domain-wall pinning being the dominant one. Permalloy nanowires, one of the best candidates for domain-wall-based memory and logic devices, require current densities of the order of 10{sup 8} A/cm{sup 2} in order to move a domain wall from a pinning well. Considering that this current has to pass through a relatively long wire, it is not very difficult to imagine that most of the energy will go to Joule heating. The efficiency of the process - the ratio of the energy converted to domain-wall motion to the total energy consumed - is comparable to that of an incandescent light bulb converting electricity to light. A step towards more efficient domain-wall-based memory devices is the advance of using alternating currents or current pulses to drive the domain walls. Injection of a spin-polarized current below the threshold value necessary to move the domain wall only causes oscillation of the domain wall inside the pinning potential. Exploiting the effect of resonance, one can apply a specific current waveform to drive the oscillations of the domain wall into resonance. Resonant amplification of domain-wall oscillations will free the domain wall from the pinning well at current levels that are a fraction of the dc threshold. Currents of an order of magnitude lower than before were shown to be sufficient to manipulate domain walls, thus reducing Joule heating 100 times. In their current paper, Tretiakov et al. provide a theoretical basis for the mechanism of resonant domain-wall motion in ferromagnetic nanowires.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Stable Metallic Enrichment in Conductive Filaments in TaO x –Based Resistive Switches Arising from Competing Diffusive Fluxes

Oxide–based resistive–switching devices hold promise for solid–state memory technology. Information encoding is accomplished by electrically switching the device between two nonvolatile states with low and high resistance states (LRS/HRS). It is generally accepted that the change between these states is due to the motion of oxygen vacancies forming a continuous (LRS) or gapped (HRS) filament between the electrodes. Direct assessments of filaments are rare due to their small size and the difficulty of locating the filament. Electron microscopy experiments reveal the filament structure and chemistry in TaO 2.0 ± 0.2 –based 150 × 150 nm 2 devices with cross–sectional geometry after forming with power dissipation lower than 1 mW. The filaments appear to be roughly hourglass–shaped with a diameter of less than 10 nm and are composed of Ta–rich and O–poor mostly amorphous material with local compositions as Ta–rich as TaO 0.4 . The as–formed HRS has a gap up to 10 nm wide located next to the anode and composed of nearly stoichiometric TaO 2.5 . The tantalum and oxygen distribution is consistent with filaments formed by the motion of both Ta and O driven by temperature gradients (Soret effect) and an electric field. As a result, this interpretation points towards a new compact model of resistive–switching devices.

36 MATERIALS SCIENCE↗

Non-Volatile Ferroelectric Switching of Ferromagnetic Resonance in NiFe/PLZT Multiferroic Thin Film Heterostructures

Magnetoelectric effect, arising from the interfacial coupling between magnetic and electrical order parameters, has recently emerged as a robust means to electrically manipulate the magnetic properties in multiferroic heterostructures. Challenge remains as finding an energy efficient way to modify the distinct magnetic states in a reliable, reversible and non-volatile manner. Here we report ferroelectric switching of ferromagnetic resonance in multiferroic bilayers consisting of ultrathin ferromagnetic NiFe and ferroelectric Pb 0.92 La 0.08 Zr 0.52 Ti 0.48 O 3 (PLZT) films, where the magnetic anisotropy of NiFe can be electrically modified by low voltages. Ferromagnetic resonance measurements confirm that the interfacial charge-mediated magnetoelectric effect is dominant in NiFe/PLZT heterostructures. Non-volatile modification of ferromagnetic resonance field is demonstrated by applying voltage pulses. The ferroelectric switching of magnetic anisotropy exhibits extensive applications in energy-efficient electronic devices such as magnetoelectric random access memories, magnetic field sensors and tunable radio frequency (RF)/microwave devices.

42 ENGINEERING↗

Finite Element Analysis of Adaptive-Stiffening and Shape-Control SMA Hybrid Composites

The usage of shape memory materials has extended rapidly to many fields, including medical devices, actuators, composites, structures and MEMS devices. For these various applications, shape memory alloys (SMAs) are available in various forms: bulk, wire, ribbon, thin film, and porous. In this work, the focus is on SMA hybrid composites with adaptive-stiffening or morphing functions. These composites are created by using SMA ribbons or wires embedded in a polymeric based composite panel/beam. Adaptive stiffening or morphing is activated via selective resistance heating or uniform thermal loads. To simulate the thermomechanical behavior of these composites, a SMA model was implemented using ABAQUS user element interface and finite element simulations of the systems were studied. Several examples are presented which show that the implemented model can be a very useful design and simulation tool for SMA hybrid composites.

Gao, Xiu-Jie↗

Radiation effects assessment of MRAM devices

The Magneto-resistive Random Access Memory (MRAM) from Freescale Semiconductor, MR2A16A, was subjected to heavy ion single event testing. Test results show that this device is sensitive to Single Event Latchup (SEL). The sensitivity of the MRAM was attributed to the complementary metal oxide semiconductor (CMOS) process in which the active portion of this device is constructed. Therefore, the device must be used with caution and may require mitigation techniques if used in a space environment. There was no indication that the MRAM technology itself, the memory element construction, is subject to damage from heavy ions.

McClure, Steve↗

Nonvolatile Memories in Spiking Neural Network Architectures: Current and Emerging Trends

A sustainable computing scenario demands more energy-efficient processors. Neuromorphic systems mimic biological functions by employing spiking neural networks for achieving brain-like efficiency, speed, adaptability, and intelligence. Current trends in neuromorphic technologies address the challenges of investigating novel materials, systems, and architectures for enabling high-integration and extreme low-power brain-inspired computing. This review collects the most recent trends in exploiting the physical properties of nonvolatile memory technologies for implementing efficient in-memory and in-device computing with spike-based neuromorphic architectures.

42 ENGINEERING↗

Achieving perpendicular anisotropy in half-metallic Heusler alloys for spin device applications

Various full Heusler alloys are interfaced with MgO and the magnetic properties of the Heusler-MgO junctions are studied. Next to MgO, the cubic Heusler system distorts to a tetragonal one, thereby inducing an anisotropy. The half-metallicity and nature of anisotropy (in-plane or perpendicular) in the Heusler-MgO system is governed mostly by the interface Heusler layers. There is a trend that Mn-O bonding near the MgO-Heusler junction results in perpendicular anisotropy. The ability to remain half-metallic and have perpendicular anisotropy makes some of these alloys potential candidates as free-layers in Spin Transfer Torque Random Access Memory (STT-RAM) devices, particularly, Cr{sub 2}MnAs-MgO system with MnAs interface layers and Co{sub 2}MnSi-MgO system with Mn{sub 2} interface layers.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Localized strain profile in surface electrode array for programmable composite multiferroic devices

In this work, we investigate localized in-plane strains on the microscale, induced by arrays of biased surface electrodes patterned on piezoelectrics. Particular focus is given to the influence that adjacent electrode pairs have on one another to study the impact of densely packed electrode arrays. We present a series of X-ray microdiffraction studies to reveal the spatially resolved micrometer-scale strain distribution. The strain maps with micrometer-scale resolution highlight how the local strain profile in square regions up to 250 x 250 lm 2 in size is affected by the surface electrodes that are patterned on ferroelectric single-crystal [Pb(Mg 1/3 Nb 2/3 )O 3 ] x -[PbTiO 3 ] 1-x . The experimental measurements and simulation results show the influence of electrode pair distance, positioning of the electrode pair, including the angle of placement, and neighboring electrode pair arrangements on the strength and direction of the regional strain. Our findings are relevant to the development of microarchitected strain-mediated multiferroic devices. The electrode arrays could provide array-addressable localized strain control for applications including straintronic memory, probabilistic computing platforms, microwave devices, and magnetic-activated cell sorting platforms.

42 ENGINEERING↗

The Global File System

The global file system (GFS) is a prototype design for a distributed file system in which cluster nodes physically share storage devices connected via a network-like fiber channel. Networks and network-attached storage devices have advanced to a level of performance and extensibility so that the previous disadvantages of shared disk architectures are no longer valid. This shared storage architecture attempts to exploit the sophistication of storage device technologies whereas a server architecture diminishes a device's role to that of a simple component. GFS distributes the file system responsibilities across processing nodes, storage across the devices, and file system resources across the entire storage pool. GFS caches data on the storage devices instead of the main memories of the machines. Consistency is established by using a locking mechanism maintained by the storage devices to facilitate atomic read-modify-write operations. The locking mechanism is being prototyped in the Silicon Graphics IRIX operating system and is accessed using standard Unix commands and modules.

Soltis, Steven R.↗