Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware accelerators”

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 883 records · Page 49

Accelerator and Particle Physics Research for the Next Generation Muon to Electron Conversion Experiment - the PRISM Task Force

The next generation of lepton flavour violation experiments will use high intensity and high quality muon beams. Such beams can be produced by sending a short proton pulse to the pion production target, capturing pions and performing RF phase rotation on the resulting muon beam in an FFAG ring, which was proposed for the PRISM project. A PRISM task force was created to address the accelerator and detector issues that need to be solved in order to realise the PRISM experiment. The parameters of the initial proton beam required and the PRISM experiment are reviewed. Alternative designs of the PRISM FFAG ring are presented and compared with the reference design. The ring injection/extraction system, matching with the solenoid channel and progress on the ring’s main hardware systems like RF and kicker magnet are discussed. The progress and future directions of the study are presented in this paper.

43 PARTICLE ACCELERATORS↗

Interactive Quantum Chemistry Enabled by Machine Learning, Graphical Processing Units, and Cloud Computing

Modern quantum chemistry algorithms are increasingly able to accurately predict molecular properties that are useful for chemists in research and education. Despite this progress, performing such calculations is currently unattainable to the wider chemistry community, as they often require domain expertise, computer programming skills, and powerful computer hardware. In this review, we outline methods to eliminate these barriers using cutting-edge technologies. We discuss the ingredients needed to create accessible platforms that can compute quantum chemistry properties in real time, including graphical processing units–accelerated quantum chemistry in the cloud, artificial intelligence–driven natural molecule input methods, and extended reality visualization. We end by highlighting a series of exciting applications that assemble these components to create uniquely interactive platforms for computing and visualizing spectra, 3D structures, molecular orbitals, and many other chemical properties.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A performance model for the communication in fast multipole methods on high-performance computing platforms

Exascale systems are predicted to have approximately 1 billion cores, assuming gigahertz cores. Limitations on affordable network topologies for distributed memory systems of such massive scale bring new challenges to the currently dominant parallel programing model. Currently, there are many efforts to evaluate the hardware and software bottlenecks of exascale designs. It is therefore of interest to model application performance and to understand what changes need to be made to ensure extrapolated scalability. The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics but has recently been extended to a wider range of problems. Its high arithmetic intensity combined with its linear complexity and asynchronous communication patterns make it a promising algorithm for exascale systems. In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on internode communication. We focus on the communication part only; the efficiency of the computational kernels are beyond the scope of the present study. We develop a performance model that considers the communication patterns of the FMM and observe a good match between our model and the actual communication time on four high-performance computing (HPC) systems, when latency, bandwidth, network topology, and multicore penalties are all taken into account. To our knowledge, this is the first formal characterization of internode communication in FMM that validates the model against actual measurements of communication time. The ultimate communication model is predictive in an absolute sense; however, on complex systems, this objective is often out of reach or of a difficulty out of proportion to its benefit when there exists a simpler model that is inexpensive and sufficient to guide coding decisions leading to improved scaling. The current model provides such guidance.

Computer Science↗

Understanding the Design Space of Sparse/Dense Multiphase Dataflows for Mapping Graph Neural Networks on Spatial Accelerators

Graph Neural Networks (GNNs) have garnered a lot of recent interest because of their success in learning representations from graph-structured data across several critical applications in cloud and HPC. Owing to their unique compute and memory characteristics that come from an interplay between dense and sparse phases of computations, the emergence of reconfigurable dataflow (aka spatial) accelerators offers promise for acceleration by mapping optimized dataflows (i.e., computation order and parallelism) for both phases. The goal of this work is to characterize and understand the design-space of dataflow choices for running GNNs on spatial accelerators in order for the compilers to optimize the dataflow based on the workload. Specifically, we propose a taxonomy to describe all possible choices for mapping the dense and sparse phases of GNNs spatially and temporally over a spatial accelerator, capturing both the intra-phase dataflow and the inter-phase (pipelined) dataflow. Using this taxonomy, we do deep-dives into the cost and benefits of several dataflows and perform case studies on implications of hardware parameters for dataflows and value of flexibility to support pipelined execution.

97 MATHEMATICS AND COMPUTING↗

Interactive real time flow simulations

An interactive real time flow simulation technique is developed for an unsteady channel flow. A finite-volume algorithm in conjunction with a Runge-Kutta time stepping scheme was developed for two-dimensional Euler equations. A global time step was used to accelerate convergence of steady-state calculations. A raster image generation routine was developed for high speed image transmission which allows the user to have direct interaction with the solution development. In addition to theory and results, the hardware and software requirements are discussed.

Sadrehaghighi, I.↗

Hypervelocity Impact Test Facility: A gun for hire

An affordable technique has been developed to duplicate the types of impacts observed on spacecraft, including the Shuttle, by use of a certified Hypervelocity Impact Facility (HIF) which propels particulates using capacitor driven electric gun techniques. The fully operational facility provides a flux of particles in the 10-100 micron diameter range with a velocity distribution covering the space debris and interplanetary dust particle environment. HIF measurements of particle size, composition, impact angle and velocity distribution indicate that such parameters can be controlled in a specified, tailored test designed for or by the user. Unique diagnostics enable researchers to fully describe the impact for evaluating the 'targets' under full power or load. Users regularly evaluate space hardware, including solar cells, coatings, and materials, exposing selected portions of space-qualified items to a wide range of impact events and environmental conditions. Benefits include corroboration of data obtained from impact events, flight simulation of designs, accelerated aging of systems, and development of manufacturing techniques.

Johnson, Calvin R.↗

Phaeton Mast Dynamics: On-Orbit Characterization of Deployable Masts

The PMD instrument is a set of three custom-designed triaxial accelerometer systems designed specifically to detect and characterize the modal dynamics of deployable masts in orbit. The instrument was designed and built as a payload for the NuSTAR spacecraft, but it is now sponsored by the Air Force Research Laboratory's DSX project. It can detect acceleration levels from 1 micro gram to 0.12g over a frequency range of 0.1Hz to 30Hz, the results of which can support future modeling and designing of deployable mast structures for space. This paper details the hardware architecture and design, calibration test and results, and current status of the PMD instrument.

Phaeton Mast Dynamics (PMD)↗

The state of Monte Carlo neutron transport on GPU accelerators - A review - 25609

A review of the current state of Monte Carlo neutron transport of Graphical Processing Units (GPUs) has been performed. Up-to-date data has been solicited from researchers in the field and combined with data available in literature to provide the current state of Monte Carlo neutron transport on GPU hardware. Nine implementations of neutron transport on GPUs have been summarized and the performance results have been presented to allow the reader to compare performance. A comparison of the results has shown that researchers obtained similar performance when scaled to the performance of NVIDIA Tesla K40 GPUs. A strong scaling equation will be presented that can be used to describe the GPU performance against different numbers of CPU cores. One implementation of a production Monte Carlo code on GPU hardware, the code Shift, showed that newer NVIDIA Pascal and Volta based GPUs provide a significant performance improvement. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

Co-design of Advanced Architectures for Graph Analytics using Machine Learning

A graph is an excellent way of representing relationships among entities. We can use graph analytics to synthesize and analyze such relational data, and extract relevant features that are useful for various tasks such as machine learning. Considering the crucial role of graph analytics in various domains, it is important and timely to investigate the right hardware configurations that can achieve optimal performance for graph workloads on future high-performance computing systems. Design space exploration studies facilitate the selection of appropriate configurations (e.g. memory) to achieve a desired system performance. Recently, the approach of accelerating graph analytics using persistent non-volatile memory has gained a lot of attention. Traditional system simulators such as Gem5 and NVMain can be used to explore the design space of these advanced memory architectures for graph workloads. However, these simulators are slow in execution thus limiting the efficiency of design space exploration studies. To overcome this challenge, we proposed a machine learning based approach to co-design advanced memory architectures for graph workloads. We tested our approach with DRAM, non-volatile memory, and hybrid memory (DRAM+NVM) using a breadth first search benchmark algorithm. Our results showed the applicability of the proposed machine learning based approach to the co-design of the advanced memory architectures. In this paper, we provide recommendations on selecting advanced memory architectures to achieve desired performance for graph workloads. We also discuss the performances of different machine learning models that were considered in this study.

Kurte, Kuldeep↗

OpenSNAPI: Toward a Unified API for SmartNICs

The end of Moore’s Law and Dennard Scaling has produced a renaissance in the field of computer architecture. Unable to continue leveraging silicon-level processor improvements to further enhance performance and scalability, system architects have been forced to explore other options. In this new era of heterogeneous architectures and hardware/software codesign, a new class of devices known as “accelerators” has emerged. Independently designed for optimized execution of distinct workloads, these devices have proven critical to the continued advancement of application performance. SmartNICs, accelerator devices integrated with a network controller, have conventionally been utilized to offload low-level networking functionality. However, newer SmartNIC variants, which incorporate a system-on-chip (SoC) with traditional designs, are challenging this precedent. Leveraging significantly augmented resources, these new devices offer increased versatility and the potential to more effectively complement a given architecture’s CPU. In this talk, we introduce the motivation underlying acceleration, explore the fundamentals of SmartNICs, and discuss traditional use cases. We also detail our initial efforts to investigate the feasibility and benefits of SmartNICs as general-purpose accelerators. We present the OpenSNAPI project created to define a uniform application programming interface (API) for this emerging class of devices. Finally, we provide a brief tutorial regarding development of SmartNIC-accelerated applications on Los Alamos National Laboratory’s SmartNIC-enabled platforms.

97 MATHEMATICS AND COMPUTING↗

Neurovestibular and Sensorimotor Studies in Space and Earth Benefits

This review summarizes what has been learned from studies of human neurovestibular system in weightless conditions, including balance and locomotion, gaze control, vestibular-autonomic function and spatial orientation, and gives some examples of the potential Earth benefits of this research. Results show that when astronauts and cosmonauts return from space flight, both the peripheral and central neural processes are physiologically and functionally altered. There are clear distinctions between the virtually immediate adaptive compensations to weightlessness and those that require longer periods of time to adapt. However, little is known to date about the adaptation of sensory-motor functions to long-duration space missions in weightlessness and to the transitions between various reduced gravitational levels, such as on the Moon and Mars. Results from neurovestibular research in space have substantially enhanced our understanding of the mechanisms and characteristics of postural, gaze, and spatial orientation deficits, analogous to clinical cases of labyrinthine-defective function. Also, space neurosciences research has participated in the development and application of significant new technologies, such as video recording and processing of three-dimensional eye movements and posture, hardware for the unencumbered measurement of head and body movement, and procedures for investigating otolith function on Earth. In particular, devices such as centrifugation or off-vertical axis rotation could enhance clinical neurological testing because it provides linear acceleration which specifically stimulates the otolith organs in a frequency range close to natural head and body movement.

Clement, Gilles↗

Force Limited Vibration Testing

This slide presentation reviews the concept and applications of Force Limited Vibration Testing. The goal of vibration testing of aerospace hardware is to identify problems that would result in flight failures. The commonly used aerospace vibration tests uses artificially high shaker forces and responses at the resonance frequencies of the test item. It has become common to limit the acceleration responses in the test to those predicted for the flight. This requires an analysis of the acceleration response, and requires placing accelerometers on the test item. With the advent of piezoelectric gages it has become possible to improve vibration testing. The basic equations have are reviewed. Force limits are analogous and complementary to the acceleration specifications used in conventional vibration testing. Just as the acceleration specification is the frequency spectrum envelope of the in-flight acceleration at the interface between the test item and flight mounting structure, the force limit is the envelope of the in-flight force at the interface . In force limited vibration tests, both the acceleration and force specifications are needed, and the force specification is generally based on and proportional to the acceleration specification. Therefore, force limiting does not compensate for errors in the development of the acceleration specification, e.g., too much conservatism or the lack thereof. These errors will carry over into the force specification. Since in-flight vibratory force data are scarce, force limits are often derived from coupled system analyses and impedance information obtained from measurements or finite element models (FEM). Fortunately, data on the interface forces between systems and components are now available from system acoustic and vibration tests of development test models and from a few flight experiments. Semi-empirical methods of predicting force limits are currently being developed on the basis of the limited flight and system test data. A simple two degree of freedom system is shown and the governing equations for basic force limiting results for this system are reviewed. The design and results of the shuttle vibration forces (SVF) experiments are reviewed. The Advanced Composition Explorer (ACE) also was used to validate force limiting. Test instrumentation and supporting equipment are reviewed including piezo-electric force transducers, signal processing and conditioning systems, test fixtures, and vibration controller systems. Several examples of force limited vibration testing are presented with some results.

random vibration testing↗

Change in Mouse Bone Turnover in Response to Microgravity on RR-1

Mechanical unloading during spaceflight is known to adversely affect mammalian physiology. Our previous studies using the Animal Enclosure Module on short duration Shuttle missions enabled us to identify a deficit in stem cell based-tissue regeneration as being a significant concern for long-duration spaceflight. Specifically, we found that mechanical unloading in microgravity resulted in inhibition of differentiation of mesenchymal and hematopoietic stem cells in the bone marrow compartment. Also, we observed overexpression of a cell cycle arrest molecule, CDKN1ap21, in osteoprecursor cells on the bone surface, chondroprogenitors in the articular cartilage, and in myofibers attached to bone tissue. Specifically in bone tissue during both short (15-day) and long (30-day) microgravity experiments, we observed significant loss of bone tissue and structure in both the pelvis and the femur. After 15-days of microgravity on STS-131, pelvic ischium displayed a 6.23 decrease in bone fraction (p0.005) and 11.91 decrease in bone thickness (p0.002). Furthermore, during long-duration spaceflight we observed onset of an accelerated aging-like phenotype and osteoarthritic disease state indicating that stem cells within the bone tissue fail to repair and regenerate tissues in a normal manner, leading to drastic tissue alterations in response to microgravity. The Rodent Research Hardware System provides the capability to investigate these effects during long-duration experiments on the International Space Station. During the Rodent Research-1 mission 10 16-week-old female C57Bl6J mice were exposed to 37-days of microgravity. All flight animals were euthanized and frozen on orbit for future dissection. Ground (n10) and vivarium controls (n10) were housed and processed to match the flight animal timeline. During this study we collected pelvis, femur, and tibia from all animal groups to test the hypothesis that stem cell-based tissue regeneration is significantly altered after 37-days of spaceflight. To do this, we will analyze differences in bone morphometric parameters using MicroCT. The pelvis, femur, and tibia are key in supporting and distributing weight under normal conditions. Therefore, we expect to see altered remodeling in flight animals in response to microgravity with respect to ground controls. In combination with histomorphometry, these results will help elucidate the complex mechanisms underlying bone tissue maintenance and stem cell regeneration.

bone↗

Changes in Mouse Bone Turnover in Response to Microgravity

Mechanical unloading during spaceflight is known to adversely affect mammalian physiology. Our previous studies using the Animal Enclosure Module on short duration Shuttle missions enabled us to identify a deficit in stem cell based-tissue regeneration as being a significant concern for long-duration spaceflight. Specifically, we found that mechanical unloading in microgravity resulted in inhibition of differentiation of mesenchymal and hematopoietic stem cells in the bone marrow compartment. Also, we observed overexpression of a cell cycle arrest molecule, CDKN1a/p21, in osteoprecursor cells on the bone surface, chondroprogenitors in the articular cartilage, and in myofibers attached to bone tissue. Specifically in bone tissue during both short (15-day) and long (30-day) microgravity experiments, we observed significant loss of bone tissue and structure in both the pelvis and the femur. After 15-days of microgravity on STS-131, pelvic ischium displayed a 6.23% decrease in bone fraction (p=0.005) and 11.91% decrease in bone thickness (p=0.002). Furthermore, during long-duration spaceflight we observed onset of an accelerated aging-like phenotype and osteoarthritic disease state indicating that stem cells within the bone tissue fail to repair and regenerate tissues in a normal manner, leading to drastic tissue alterations in response to microgravity. The Rodent Research Hardware System provides the capability to investigate these effects during long-duration experiments on the International Space Station. During the Rodent Research-1 mission 10 16-week-old female C57Bl/6J mice were exposed to 37-days of microgravity. All flight animals were euthanized and frozen on orbit for future dissection. Ground (n=10) and vivarium controls (n=10) were housed and processed to match the flight animal timeline. During this study we collected pelvis, femur, and tibia from all animal groups to test the hypothesis that stem cell-based tissue regeneration is significantly altered after 37-days of spaceflight. To do this, we will analyze differences in bone morphometric parameters using MicroCT. The pelvis, femur, and tibia are key in supporting and distributing weight under normal conditions. Therefore, we expect to see altered remodeling in flight animals in response to microgravity with respect to ground controls. In combination with histomorphometry, these results will help elucidate the complex mechanisms underlying bone tissue maintenance and stem cell regeneration.

microgravity↗

Smart sensors using artificial intelligence for on-detector electronics and ASICs

Cutting edge detectors push sensing technology by further improving spatial and temporal resolution, increasing detector area and volume, and generally reducing backgrounds and noise. This has led to a explosion of more and more data being generated in next-generation experiments. Therefore, the need for near-sensor, at the data source, processing with more powerful algorithms is becoming increasingly important to more efficiently capture the right experimental data, reduce downstream system complexity, and enable faster and lower-power feedback loops. In this paper, we discuss the motivations and potential applications for on-detector AI. Furthermore, the unique requirements of particle physics can uniquely drive the development of novel AI hardware and design tools. We describe existing modern work for particle physics in this area. Finally, we outline a number of areas of opportunity where we can advance machine learning techniques, codesign workflows, and future microelectronics technologies which will accelerate design, performance, and implementations for next generation experiments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Record acceleration of the two-dimensional Ising model using a high-performance wafer-scale engine

The versatility and wide-ranging applicability of the Ising model, originally introduced to study phase transitions in magnetic materials, have made it a cornerstone in statistical physics and a valuable tool for evaluating the performance of emerging computer hardware. Here, we present a novel implementation of the two-dimensional Ising model on Cerebras Wafer-Scale Engine (WSE) – a revolutionary processor that is opening new frontiers in computing. In our deployment of the checkerboard algorithm, we optimized the Ising model to take advantage of the unique WSE architecture. Specifically, we employed a compressed bit representation storing 16 spins on each int16 word, and efficiently distributed the spins over the processing units enabling seamless weak scaling and limiting communications to only immediate neighboring units. Our implementation can handle up to 754 simulations in parallel, achieving an aggregate of over 61.8 trillion flip attempts per second for Ising models with up to 200 million spins. This represents a gain of up to 148 times over previously reported single-devices with a highly optimized implementation on NVIDIA V100 and up to 88 times in productivity compared to NVIDIA H100. Our findings highlight the significant potential of the WSE in scientific computing, particularly in the field of materials modeling.

Ising model↗

Fluids flight hardware

The following are discussed in this viewgraph presentation: Glovebox-2 investigations, study of oscillatory thermocapillary flows and validate physical models on the second U.S. Microgravity Laboratory Mission (USML-2), pool boiling experiment, critical fluid viscosity measurement experiment, Hitchhiker-G typical structural configuration, ZENO-critical fluid light scattering experiment, isothermal dendritic growth experiment, microgravity acceleration environment support, and the space acceleration measurement system (SAMS).

Shaw, Nancy↗

Experimental and Numerical Studies on the Proposed Application of Hollow Electron Beam Collimation for the LHC at CERN

This thesis work was carried out in the framework of the U.S. LHC Accelerator Research Program (USLARP), a collaboration between the European Organization for Nuclear Research (CERN) and the U.S. Department of Energy. The first half of the work was completed at Fermilab (USA), the location of the Tevatron, a proton-antiproton collider and the second largest particle collider in the world. The second half was completed at CERN (Switzerland), the location of the largest proton collider in the world (Large Hadron Collider (LHC)). This thesis characterizes a Hollow Electron Beam (HEB) for possible usage at the LHC to enhance its collimation through Hollow Electron Beam Lenses (HEBLs). Collimation is a long established principle in high energy particle accelerators. Hollow Electron Beam Collimation (HEBC) aims to enhance current collimation systems by controlling diffusion of primary halo particles into the limiting aperture. It works on the principle of a transverse radial electric field that kicks the primary halo particles outwards upon each pass in a multi-pass system. The transverse field is produced by a HEB that is coaxially aligned with the accelerator beam, producing a negligible electric field in the center and a strong transverse electric field at amplitudes higher than the inner radius of the electron beam. Ideally, halo particles are affected without perturbation of the beam core. One of the main advantages of this system is to decrease the dependence on instantaneous loss spikes and beam jitter. A solid experimental basis of HEBC was accumulated at the Tevatron. The application of this technique at the LHC is now under investigation. The aim of this thesis is to present a preliminary report to support a future optimal conceptual design report. It characterizes the available hardware in order to facilitate the design of a Hollow Electron Gun (HEG) for the LHC, characterizes the effect on beam diffusion by determining the transverse electric fields of the electron beam and initiates 3D simulations in order to determine the effect of the HEBL on the beam core. Experiments were conducted in the Tevatron Electron Lens Test Stand (TELTS) at Fermi National Accelerator Lab (Fermilab) (USA) in the lower Linear Accelerator (LINAC) gallery.

43 PARTICLE ACCELERATORS↗