Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed 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 757 records · Page 42

Scalable measurement error mitigation via iterative bayesian unfolding

Measurement errors are a significant obstacle to achieving scalable quantum computation. To counteract systematic readout errors, researchers have developed postprocessing techniques known as measurement error mitigation methods. However, these methods face a tradeoff between scalability and returning nonnegative probabilities. In this paper, we present a solution to overcome this challenge. Our approach focuses on iterative Bayesian unfolding, a standard mitigation technique used in high-energy physics experiments, and implements it in a scalable way. We demonstrate our method on experimental Greenberger-Horne-Zeilinger state preparation on up to 127 qubits and on the Bernstein-Vazirani algorithm on up to 26 qubits. Compared to state-of-the-art methods (such as M3), our implementation guarantees valid probability distributions, returns comparable or better-mitigated results, and does so without a noticeable time and memory overhead. Published by the American Physical Society 2024

Pokharel, Bibek (ORCID:0000000342841353)↗

Axom

Axom is an open-source library of "building block" software components that provide core infrastructure capabilities for HPC applications. Such capabilities include: input file parsing and verification for various file formats, format specification for material shape input to multi-material simulations and tools for placing those shapes on meshes, parallel distributed coordination of diagnostic messages, geometric primitives, spatial queries and spatial search acceleration data structures, in memory key-value data store for managing simulation data and parallel file I/O. Axom components are used widely across LLNL Advanced Simulation and Computing program applications. It is also part of the LLNL institutionally-supported RADIUSS project, which promotes and funds its adoption by projects across LLNL.

Zagaris, George↗

On Data Transfers Over Wide-Area Dedicated Connections

Dedicated wide-area network connections are employed in big data and high-performance computing scenarios, since the absence of cross-traffic promises to make it easier to analyze and optimize data transfers over them. However, nonlinear transport dynamics and end-system complexity due to multi-core hosts and distributed file systems make these tasks surprisingly challenging. We present an overview of methods to analyze memory and disk file transfers using extensive measurements over 10 Gbps physical and emulated connections with 0–366 ms round trip times (RTTs). For memory transfers, we derive performance profiles of TCP and UDT throughput as a function of RTT, which show concave regions in contrast to entirely convex regions predicted by previous models. These highly desirable concave regions can be expanded by utilizing large buffers and more parallel flows. We also present Poincar´e maps and Lyapunov exponents of TCP and UDT throughputtraces that indicate complex throughput dynamics. For disk file transfers, we show that throughput can be optimized using a combination of parallel I/O and network threads under direct I/O mode. Our initial throughput measurements of Lustre filesystems mounted over long-haul connections using LNet routers show convex profiles indicative of I/O limits.

Rao, Nageswara S.↗

Scalable PGAS Metadata Management on Extreme Scale Systems

Programming models intended to run on exascale systems have a number of challenges to overcome, specially the sheer size of the system as measured by the number of concurrent software entities created and managed by the underlying runtime. It is clear from the size of these systems that any state maintained by the programming model has to be strictly sub-linear in size, in order not to overwhelm memory usage with pure overhead. A principal feature of Partitioned Global Address Space (PGAS) models is providing easy access to global-view distributed data structures. In order to provide efficient access to these distributed data structures, PGAS models must keep track of metadata such as where array sections are located with respect to processes/threads running on the HPC system. As PGAS models and applications become ubiquitous on very large transpetascale systems, a key component to their performance and scalability will be efficient and judicious use of memory for model overhead (metadata) compared to application data. We present an evaluation of several strategies to manage PGAS metadata that exhibit different space/time tradeoffs. We use two real-world PGAS applications to capture metadata usage patterns and gain insight into their communication behavior.

Global Arrays↗

Perovskite neural trees

Trees are used by animals, humans and machines to classify information and make decisions. Natural tree structures displayed by synapses of the brain involves potentiation and depression capable of branching and is essential for survival and learning. Demonstration of such features in synthetic matter is challenging due to the need to host a complex energy landscape capable of learning, memory and electrical interrogation. We report experimental realization of tree-like conductance states at room temperature in strongly correlated perovskite nickelates by modulating proton distribution under high speed electric pulses. This demonstration represents physical realization of ultrametric trees, a concept from number theory applied to the study of spin glasses in physics that inspired early neural network theory dating almost forty years ago. We apply the tree-like memory features in spiking neural networks to demonstrate high fidelity object recognition, and in future can open new directions for neuromorphic computing and artificial intelligence.

36 MATERIALS SCIENCE↗

Distributed caching for processing raw arrays

As applications continue to generate multi-dimensional data at exponentially increasing rates, fast analytics to extract meaningful results is becoming extremely important. The database community has developed array databases that alleviate this problem through a series of techniques. In-situ mechanisms provide direct access to raw data in the original format---without loading and partitioning. Parallel processing scales to the largest datasets. In-memory caching reduces latency when the same data are accessed across a workload of queries. However, we are not aware of any work on distributed caching of multi-dimensional raw arrays. In this paper, we introduce a distributed framework for cost-based caching of multi-dimensional arrays in native format. Given a set of files that contain portions of an array and an online query workload, the framework computes an effective caching plan in two stages. First, the plan identifies the cells to be cached locally from each of the input files by continuously refining an evolving R-tree index. In the second stage, an optimal assignment of cells to nodes that collocates dependent cells in order to minimize the overall data transfer is determined. We design cache eviction and placement heuristic algorithms that consider the historical query workload. A thorough experimental evaluation over two real datasets in three file formats confirms the superiority -- by as much as two orders of magnitude -- of the proposed framework over existing techniques in terms of cache overhead and workload execution time.

Zhao, Weijie↗

Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints

Subsurface nuclear magnetic resonance (NMR) logs acquired in the wellbore environment are sensitive to fluid-filled pore size distribution, fluid mobility, permeability, and porosity in the near-wellbore reservoir volume. NMR response of a formation layer is processed to extract the T2 distribution, which approximates the fluid-filled pore size distribution. NMR logs are acquired in limited number of wells due to financial and operational challenges, which adversely affects reservoir characterization. We developed here two neural-network-based machine learning techniques, long short-term memory (LSTM) network and variational autoencoder with a convolutional layer (VAEc) network, to process the ‘easy-to-acquire’ formation mineral and fluid saturation logs to generate synthetic NMR T2 distributions in the absence of ‘hard-to-acquire’ NMR T2 distribution log. Both the predictive models are trained and tested on limited wireline log measurements randomly selected from a 300-ft depth interval of the Bakken shale formation. Synthesis performances of LSTM and VAEc models in terms of R 2 are 0.78 and 0.75, respectively. Noise is inevitable in logging data due to the complex wellbore and formation conditions. Notably, both the predictive models robustly synthesize the fluid-filled pore size distributions in the presence of 50% noise in input logs and 30% noise in training T2 data. The performance of the proposed methodology improves with access to larger volume of training data from other formation types. The proposed method is critical to the synthesis of in situ fluid-filled pore size distributions in shale formations under data constraints due to financial and operational challenges.

58 GEOSCIENCES↗

Multi-fault Tolerance for Cartesian Data Distributions

Faults are expected to play an increasingly important role in how algorithms and applications are designed to run on future extreme-scale sys- tems. Algorithm-based fault tolerance (ABFT) is a promising approach that involves modications to the algorithm to recover from faults with lower over- heads than replicated storage and a signicant reduction in lost work compared to checkpoint-restart techniques. Fault-tolerant linear algebra (FTLA) algo- rithms employ additional processors that store parities along the dimensions of a matrix to tolerate multiple, simultaneous faults. Existing approaches as- sume regular data distributions (blocked or block-cyclic) with the failures of each data block being independent. To match the characteristics of failures on parallel computers, we extend these approaches to mapping parity blocks in several important ways. First, we handle parity computation for generalized Cartesian data distributions with each processor holding arbitrary subsets of blocks in a Cartesian-distributed array. Second, techniques to handle corre- lated failures, i.e., multiple processors that can be expected to fail together, are presented. Third, we handle the colocation of parity blocks with the data blocks and do not require them to be on additional processors. Several al- ternative approaches, based on graph matching, are presented that attempt to balance the memory overhead on processors while guaranteeing the same fault tolerance properties as existing approaches that assume independent fail- ures on regular blocked data distributions. The evaluation of these algorithms demonstrates that the additional desirable properties are provided by the pro- posed approach with minimal overhead.

Ali, Nawab↗

A scalable approach to solving dense linear algebra problems on hybrid CPU-GPU systems

Aiming to fully exploit the computing power of all CPUs and all graphics processing units (GPUs) on hybrid CPU-GPU systems to solve dense linear algebra problems, in this paper we design a class of heterogeneous tile algorithms to maximize the degree of parallelism, to minimize the communication volume, and to accommodate the heterogeneity between CPUs and GPUs. The new heterogeneous tile algorithms are executed upon our decentralized dynamic scheduling runtime system, which schedules a task graph dynamically and transfers data between compute nodes automatically. The runtime system uses a new distributed task assignment protocol to solve data dependencies between tasks without any coordination between processing units. By overlapping computation and communication through dynamic scheduling, we are able to attain scalable performance for the double-precision Cholesky factorization and QR factorization. Finally, our approach demonstrates a performance comparable to Intel MKL on shared-memory multicore systems and better performance than both vendor (e.g., Intel MKL) and open source libraries (e.g., StarPU) in the following three environments: heterogeneous clusters with GPUs, conventional clusters without GPUs, and shared-memory systems with multiple GPUs.

97 MATHEMATICS AND COMPUTING↗

Results of the Grid Friendly Appliance Project

As part of the Pacific Northwest GridWise™ Testbed Demonstration funded by the U.S. Department of Energy and others, Pacific Northwest National Laboratory (PNNL) collaborated with Whirlpool Corporation, Invensys Controls, the Bonneville Power Administration, PacifiCorp, Portland General Electric and several smaller utilities to install 150 new Sears Kenmore clothes dryers and to retrofit 50 existing electric water heaters in homes in Washington and Oregon. Each dryer and water heater was configured to respond to the Grid Friendly™ appliance controller, a small electronic circuit that sensed underfrequency grid conditions and requested that electric load be shed by the appliances. These controllers and appliances were observed for over a year in residences spread over a wide geographic area. The controllers were found to respond predictably and reliably despite their geographic separation. Over 350 minor underfrequency events were observed during the experiment. This paper presents the distributions of these events by season and by time of day. Based on measured load profiles for the dryers and water heaters, the average electrical load that can be shed by each of the two appliance types was estimated by time of day and by season. Battelle Memorial Institute and PNNL have been assembling a suite of grid-responsive functions and benefits that can be achieved through the control of relatively small, distributed loads and resources on a power grid. These controllers should eventually receive acceptance for the opportunities they offer for circuit protection, regulation services, facilitation of demand responsiveness, and even power quality.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A wireless sensor tag platform for container security and integrity

Cargo containers onboard ships are widely used in the global supply chain. The need for container security is evidenced by the Container Security Initiative launched by the U.S. Bureau of Customs and Border Protection (CBP). One method of monitoring cargo containers is using low power wireless sensor tags. The wireless sensor tags are used to set up a network that is comprised of tags internal to the container and a central device. The sensor network reports alarms and other anomalies to a central device, which then relays the message to an outside network upon arrival at the destination port. This allows the port authorities to have knowledge of potential security or integrity issues before physically examining the container. Challenges of using wireless sensor tag networks for container security include battery life, size, environmental conditions, information security, and cost among others. PNNL developed an active wireless sensor tag platform capable of reporting data wirelessly to a central node as well as logging data to nonvolatile memory. The tags, operate at 2.4 GHz over an IEEE 802.15.4 protocol, and were designed to be distributed throughout the inside of a shipping container in the upper support frame. The tags are mounted in a housing that allows for simple and efficient installation or removal prior to, during, or after shipment. The distributed tags monitor the entire container volume. The sensor tag platform utilizes low power electronics and provides an extensible sensor interface for incorporating a wide range of sensors including chemical, biological, and environmental sensors.

36 MATERIALS SCIENCE↗

Persistent photoconductivity in two-dimensional Mo 1-x W x Se 2 –MoSe 2 van der Waals heterojunctions

Van der Waals (vdW) heterojunctions consisting of vertically-stacked individual or multiple layers of two-dimensional (2D) layered semiconductors, especially the transition metal dichalcogenides (TMDs), are fascinating new artificial solids just nanometers-thin that promise novel optoelectronic functionalities due to the sensitivity of their electronic and optical properties to strong quantum confinement and interfacial interactions. Here, monolayers of n-type MoSe 2 and p-type Mo 1-x W x Se 2 –MoSe 2 are grown by vapor transport methods, then transferred and stamped to form artificial vdW heterostructures with different interlayer orientations. Atomic-resolution Z-contrast electron microscopy and electron diffraction are used to characterize both the individual monolayers and the atomic registry between layers in the bilayer vdW heterostructures. These measurements are compared with photoluminescence and low-frequency Raman spectroscopy, which indicates strong interlayer coupling in heterostructures. Remarkably, the heterojunctions exhibit an unprecedented photoconductivity effect that persists at room temperature for several days. This persistent photoconductivity is shown to be tunable by applying a gate bias that equilibrates the charge distribution. Furthermore, these measurements indicate that such ultrathin vdW heterojunctions can function as rewritable optoelectronic switches or memory elements under time-dependent photo-illumination, an effect which appears promising for new monolayer TMDs-based optoelectronic devices applications.

36 MATERIALS SCIENCE↗

Extreme-bandwidth scalable performance-per-watt GPU architecture

A technique for accessing memory in an accelerated processing device coupled to stacked memory dies is provided herein. The technique includes receiving a memory access request from an execution unit and identifying whether the memory access request corresponds to memory cells of the stacked dies that are considered local to the execution unit or non-local. For local accesses, the access is made “directly”, that is, without using a bus. A control die coordinates operations for such local accesses, activating particular through-silicon-vias associated with the memory cells that include the data for the access. Non-local accesses are made via a distributed cache fabric and an interconnect bus in the control die. Various other features and details are provided below.

97 MATHEMATICS AND COMPUTING↗

Nanometer-scale temperature imaging for independent observation of Joule and Peltier effects in phase change memory devices

This paper reports a technique for independent observation of nanometer-scale Joule heating and thermoelectric effects, using atomic force microscopy (AFM) based measurements of nanometer-scale temperature fields. When electrical current flows through nanoscale devices and contacts the temperature distribution is governed by both Joule and thermoelectric effects. When the device is driven by an electrical current that is both periodic and bipolar, the temperature rise due to the Joule effect is at a different harmonic than the temperature rise due to the Peltier effect. An AFM tip scanning over the device can simultaneously measure all of the relevant harmonic responses, such that the Joule effect and the Peltier effect can be independently measured. Here we demonstrate the efficacy of the technique by measuring Joule and Peltier effects in phase change memory devices. By comparing the observed temperature responses of these working devices, we measure the device thermopower, which is in the range of 30 ± 3 to 250 ± 10 μV K{sup −1}. This technique could facilitate improved measurements of thermoelectric phenomena and properties at the nanometer-scale.

42 ENGINEERING↗

In situ investigation of stress-induced martensitic transformation in granular shape memory ceramic packings

Stress-induced martensitic transformation can occur in granular shape memory materials when individual particles experience high stresses and transform from a high-symmetry austenite phase to a low-symmetry martensite phase. This involves a highly heterogeneous distribution of the driving force and very low mechanical constraint for martensite nucleation, so the transformation behavior can be dramatically different from the well-documented case of monolithic solids. In this work, we investigate the stress-induced martensitic transformation in granular shape memory ceramic packings, which consist of single-crystal micro-particles of ZrO 2 -12 at%CeO 2 and ZrO 2 -15 at%CeO 2 . Using in situ neutron diffraction, we study how the phase fraction, lattice strain, and integral peak broadness evolve during external loading, unloading, and subsequent heating. Several peculiar features are discovered, including (i) a continuous mode of transformation with a wide range of transformation loads, (ii) co-evolution of the packing structure, contact deformation, and martensitic transformation, and (iii) a strong correlation between the peak broadening and the transformed phase fraction. In addition, we show the first direct evidence of reversible stress-induced martensitic transformation in granular materials. We additionally discuss the mechanism for martensite nucleation and growth in granular packings and show how that leads to the observed transformation characteristics.

36 MATERIALS SCIENCE↗

Loss circulation prevention in geothermal drilling by shape memory polymer

Geothermal formations are naturally fractured with large fracture openings and networks. This can often lead to frequent drilling fluid loss events which is a major contributor to the cost and non-productive time in geothermal drilling. Development of smarter technologies and methods to tackle problem lost circulation is vital for geothermal drilling cost reduction required for geothermal energy to be recognized as a competitive alternative energy source. Mitigation of this problem and other drilling problems such as stuck pipe can minimize overall project cost. In this report, a thermoset shape memory polymer that can be activated by formation natural heat was assessed to seal near wellbore fractures in geothermal wells. The performance of the shape memory polymer (SMP) was evaluated using artificial fractures created in aluminum discs and cylindrical granite cores. Rheology and particle size distribution were considered. A novel testing setup was built for this work, which allows testing of sealing efficiency under dynamic conditions at high temperature. Analysis showed that the SMP has efficiently succeeded in forming a strong plug inside the fractures and stopped fluid loss at high sealing pressure. This smart loss circulation material can expand within the fractures to reduces non-drilling time and strengthen the wellbore in high-temperature drilling operations.

58 GEOSCIENCES↗

An Accurate, Error-Tolerant, and Energy-Efficient Neural Network Inference Engine Based on SONOS Analog Memory

In this work, we demonstrate SONOS (silicon-oxide-nitrideoxide- silicon) analog memory arrays that are optimized for neural network inference. The devices are fabricated in a 40nm process and operated in the subthreshold regime for in-memory matrix multiplication. Subthreshold operation enables low conductances to be implemented with low error, which matches the typical weight distribution of neural networks, which is heavily skewed toward near-zero values. This leads to high accuracy in the presence of programming errors and process variations. We simulate the end-to-end neural network inference accuracy, accounting for the measured programming error, read noise, and retention loss in a fabricated SONOS array. Evaluated on the ImageNet dataset using ResNet50, the accuracy using a SONOS system is within 2.16% of floating-point accuracy without any retraining. The unique error properties and high On/Off ratio of the SONOS device allow scaling to large arrays without bit slicing, and enable an inference architecture that achieves 20 TOPS/W on ResNet50, a >10× gain in energy efficiency over state-of-the-art digital and analog inference accelerators.

97 MATHEMATICS AND COMPUTING↗

Advanced Data Structures for Improved Cyber Resilience and Awareness in Untrusted Environments: LDRD Report

This report summarizes the work performed under the project "Advanced Data Structures for Improved Cyber Resilience and Awareness in Untrusted Environments." The goal of the project was to design, analyze, and test new data structures for cybersecurity applications. We had two major thrusts: 1) using new/improved write-optimized data structures and/or algorithms to better man- age and analyze high-speed massive-volume cyberstreams, and 2) adding security features to data structures at minimum cost. Write optimization allows data structures to better use secondary memory to store and search a larger amount of useful information. Secondary memory is large compared to main memory, but data movement to and from secondary memory must be carefully managed to run quickly enough to keep up with fast streams. The first thrust included managing cyberstreams in parallel, both multi-threaded and distributed, and improving the benchmarking infrastructure for testing new streaming data structures. We considered both (near) real-time discovery of particular patterns, and improved logging for improved forensics. We considered two kinds of security-feature problem. The first was high-performance history- independent external-memory data structures. These provide certain protections to data if a disk is stolen. We also prove some trade-offs between speed and security in this setting. The second data-security problem is more secure data look-up in secret-shared data bases. This report summarizes the project's major accomplishments, with the background to under- stand these accomplishments. It gathers the abstracts and references for the six refereed publications that have appeared as part of this work. We summarize several accomplishments that will be submitted for publication. We then archive one piece of partial work that is not likely to be published in the near future: validation of history-independent data structure implementations.

97 MATHEMATICS AND COMPUTING↗