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 361 records · Page 20

Exploring the interoperability of remote GPGPU virtualization using rCUDA and directive-based programming models

Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate applications by using coprocessors with little effort. These devices offer significant computing power, but their use can introduce two problems: an increase in the total cost of ownership and their underutilization because not all codes match their architecture. Remote accelerator virtualization frameworks address those problems. In particular, rCUDA provides transparent access to any graphic processor unit installed in a cluster, reducing the number of accelerators and increasing their utilization ratio. Joining these two technologies, directive-based programming models and rCUDA, is thus highly appealing. In this work, we study the integration of OmpSs and OpenACC with rCUDA, describing and analyzing several applications over three different hardware configurations that include two InfiniBand interconnections and three NVIDIA accelerators. Our evaluation reveals favorable performance results, showing low overhead and similar scaling factors when using remote accelerators instead of local devices.

97 MATHEMATICS AND COMPUTING↗

Modernization Plans for Fermilab’s Accelerator Control System

The control system, ACNET, for Fermilab’s accelerator complex has enabled the lab’s scientific mission for decades. ACNET has evolved over the years to incorporate new technologies. However, as Fermilab prepares to enter a new era with its PIP-II superconducting linear accelerator, ACNET is at a crossroads. There are several components that are either obsolete or outdated, or certainly will be over the long lifetime of PIP-II. We have begun a plan to modernize our accelerator control system. This paper discusses some of the obsolete hardware and software that needs to be replaced, and lays out options and technologies that we might adopt as part of this modernization effort.

43 PARTICLE ACCELERATORS↗

Deployment and validation of predictive 6-dimensional beam diagnostics through generative reconstruction with standard accelerator elements

Understanding the 6-dimensional phase space distribution of particle beams is essential for optimizing accelerator performance. Conventional diagnostics such as use of transverse deflecting cavities offer detailed characterization but require dedicated hardware and space. Generative phase space reconstruction (GPSR) methods have shown promise in beam diagnostics, yet prior implementations still rely on such components. Here we present the first experimental implementation and validation of the GPSR methodology, realized by the use of standard accelerator elements including accelerating cavities and dipole magnets, to achieve complete 6-dimensional phase space reconstruction. Through simulations and experiments at the Pohang Accelerator Laboratory X-ray Free Electron Laser facility, we successfully reconstruct complex, nonlinear beam structures. Furthermore, we validate the methodology by predicting independent downstream measurements excluded from training, revealing the reconstruction closely resembling ground truth. This advancement establishes a pathway for predictive diagnostics across beamline segments while reducing hardware requirements and expanding applicability to various accelerator facilities.

Kim, Seongyeol [Pohang Univ. of Science and Techno↗

Power Hardware-In-the-Loop Hydropower and Ultracapacitor Hybrid Testbed

Widespread deployment of a proof-of-concept technological solution for power system performance improvement can be accelerated through onsite demonstration and pilot projects. Digital real-time simulation with power hardware-in-the-loop in controlled lab environment is the precursor to de-risk the timely and efficient execution of field demonstration and pilot projects. However, the detailed process of development, characterization, and calibration of such high fidelity simulation testbed needs to be documented in a reproducible and publicly accessible manner to leverage across broader research and development communities. This paper presents such a laboratory testbed to study black start capability of a run-of-river hydro + ultracapacitor hybrid system. Beside the high-fidelity model of the islanded grid with hydropower unit, the testbed includes the energy storage, grid following inverter, and grid emulator hardware. Several aspects such as storage characterization, control and various parameter settings necessary to capture frequency transients during load restoration are described in a comprehensive manner, which led to an effective and timely execution of black start field demonstration with an actual hydropower plant.

13 HYDRO ENERGY↗

Accelerating Science Driven System Design With RAMP

Researchers from UC Berkeley, in collaboration with the Lawrence Berkeley National Lab, are engaged in developing an Infrastructure for Synthesis with Integrated Simulation (ISIS). The ISIS Project was a cooperative effort for “application-driven hardware design” that engages application scientists in the early parts of the hardware design process for future generation supercomputing systems. This project served to foster development of computing systems that are better tuned to the application requirements of demanding scientific applications and result in more cost-effective and efficient HPC system designs. In order to overcome long conventional design-cycle times, we leveraged reconfigurable devices to aid in the design of high-efficiency systems, including conventional multi- and many-core systems. The resulting system emulation/prototyping environment, in conjunction with the appropriate intermediate abstractions, provided both a convenient user programming experience and retained flexibility, and thus efficiency, of a reconfigurable platform. We initially targeted the Berkeley RAMP system (Research Accelerator for Multiple Processors) as that hardware emulation environment to facilitate and ultimately accelerate the iterative process of science-driven system design. Our goal was to develop and demonstrate a design methodology for domain-optimized computer system architectures. The tangible outcome is a methodology and tools for rapid prototyping and design-space exploration, leading to highly optimized and efficient HPC systems.

97 MATHEMATICS AND COMPUTING↗

ECP ST Project 2.3.1.06-STPM08-RAJA (Final Report)

Modern high-performance computing architectures are diverse, with hardware designs that feature multicore CPUs and CPUs plus accelerators, such as GPUs or FPGAs. Achieving good application performance often requires using a programming model and managing application data in ways that are best suited to a particular platform. For large codes that are used daily in production, and are under continual development, architecture-specific ports are untenable. Maintainability requires single-source code that is performance portable across a range of architectures and programming model back-ends. This report describes RAJA, Umpire, and CHAI, three software libraries that provide complementary capabilities to enable application portability for high performance computing (HPC) platforms. In particular, these libraries provide software abstractions that insulate application source code from hardware architecture and programming model-specific implementation details. These development of these libraries was motivated by the needs of multiphysics applications in the Weapons Simulation and Computing Program (WSC) at Lawrence Livermore National Laboratory (LLNL). Funding though the Exascale Computing Project (ECP) Software Technology (ST) project 2.3.1.06 RAJA has fostered outreach and collaboration with the ECP application and software technology development communities. In this report, we describe ECP adoption and integration of these tools to this point. The larger goal of the report is to describe to the ECP community what these projects offer, how they are used, and how to approach adoption and integration of them.

97 MATHEMATICS AND COMPUTING↗

10 Gbps TCP/IP streams from the FPGA for High Energy Physics

The DAQ system of the CMS experiment at CERN collects data from more than 600 custom detector Front-End Drivers (FEDs). During 2013 and 2014 the CMS DAQ system will undergo a major upgrade to address the obsolescence of current hardware and the requirements posed by the upgrade of the LHC accelerator and various detector components. For a loss-less data collection from the FEDs a new FPGA based card implementing the TCP/IP protocol suite over 10Gbps Ethernet has been developed. To limit the TCP hardware implementation complexity the DAQ group developed a simplified and unidirectional but RFC 793 compliant version of the TCP protocol. This allows to use a PC with the standard Linux TCP/IP stack as a receiver. We present the challenges and protocol modifications made to TCP in order to simplify its FPGA implementation. We also describe the interaction between the simplified TCP and Linux TCP/IP stack including the performance measurements.

Bauer, Gerry↗

Operational experience with CW high gradient and high QL cryomodules

The Continuous Electron Beam Accelerator Facility (CEBAF) energy upgrade from 6 GeV to 12 GeV includes the installation of ten new 100 MV cryomodules (80 cavities). The superconducting RF cavities are designed to operate CW at an accelerating gradient of 19.3 MV/m with a QL of 3×107. The RF system employs single cavity control using new digital LLRF controls and 13 kW klystrons. Recently, all of the new cryomodules and associated RF hardware and software have been commissioned and operated in the CEBAF accelerator. Electrons at linac currents up to 10 ?A have been successfully accelerated and used for nuclear physics experiments. This paper reports on the commissioning and operation of the cryomodules and RF system.

Hovater, J. Curt↗

High-Speed Ionic Synaptic Memory Based on 2D Titanium Carbide MXene

Synaptic devices with linear high-speed switching can accelerate learning in artificial neural networks (ANNs) embodied in hardware. Conventional resistive memories however suffer from high write noise and asymmetric conductance tuning, preventing parallel programming of ANN arrays. Electrochemical random-access memories (ECRAMs), where resistive switching occurs by ion insertion into a redox-active channel, aim to address these challenges due to their linear switching and low noise. ECRAMs using 2D materials and metal oxides however suffer from slow ion kinetics, whereas organic ECRAMs enable high-speed operation but face challenges toward on-chip integration due to poor temperature stability of polymers. Here, ECRAMs using 2D titanium carbide (Ti 3 C 2 T x ) MXene that combine the high speed of organics and the integration compatibility of inorganic materials in a single high-performance device are demonstrated. These ECRAMs combine the speed, linearity, write noise, switching energy, and endurance metrics essential for parallel acceleration of ANNs, and importantly, they are stable after heat treatment needed for back-end-of-line integration with Si electronics. The high speed and performance of these ECRAMs introduces MXenes, a large family of 2D carbides and nitrides with more than 30 stoichiometric compositions synthesized to date, as promising candidates for devices operating at the nexus of electrochemistry and electronics.

2D materials↗

Final Design of the SLAC P2 Marx Klystron Modulator

The SLAC P2 Marx has been under development for two years, and follows on the P1 Marx as an alternative to the baseline klystron modulator for the International Linear Collider. The P2 Marx utilizes a redundant architecture, air-insulation, a control system with abundant diagnostic access, and a novel nested droop correction scheme. This paper is an overview of the design of this modulator. There are several points of emphasis for the P2 Marx design. First, the modulator must be compatible with the ILC two-tunnel design. In this scheme, the modulator and klystron are located within a service tunnel with limited access and available footprint for a modulator. Access to the modulator is only practical from one side. Second, the modulator must have high availability. Robust components are not sufficient alone to achieve availability much higher than 99%. Therefore, redundant architectures are necessary. Third, the modulator must be relatively low cost. Because of the large number of stations in the ILC, the investment needed for the modulator components is significant. High-volume construction techniques which take advantage of an economy of scale must be utilized. Fourth, the modulator must be simple and efficient to maintain. If a modulator does become inoperable, the MTTR must be small. Fifth, even though the present application for the modulator is for the ILC, future accelerators can also take advantage of this development effort. The hardware, software, and concepts developed in this project should be designed such that further development time necessary for other applications is minimal.

43 PARTICLE ACCELERATORS↗

Accelerator Real-time Edge AI for Distributed Systems (READS) (Proposal)

Over the last decade, Machine Learning (ML) technologies have slowly made their way into the accelerator community. Rapid advances in recent years in deep learning, particularly reinforcement learning for control system applications and the accessibility of deep learning in embedded hardware, have generated renewed interest and spawned a number of applications. The Fermilab Accelerator Complex, shown in Fig. 1, has provided High Energy Physics (HEP) experiments with proton beams for nearly fifty years. The current focus of the laboratory is its world-class experimental program at the intensity frontier. While increasing beam intensity certainly presents its own challenges, preserving beam size while minimizing beam losses – particles lost through interactions with the beam vacuum pipe – turns out to be, in many ways, the main challenge. The accelerator is controlled via a complex system of hundreds of thousands of devices. Enabling fine tuning and real-time optimization of their parameters using ML methods and stepping beyond experience-based reasoning of human operators are key to the success of future intensity upgrades. Our objective will be to integrate ML into accelerator operations and furthermore, provide an accessible framework, which can also be used by a broad range of other accelerator systems with dynamic tuning needs.

43 PARTICLE ACCELERATORS↗

Removing Noise in BPM Measurements with Variational Autoencoders

Noise in beam measurements is an ever-present challenge in accelerator operations. In addition to the challenges presented by hardware and signal processing, new operational regimes, such as ultra-short bunches, create additional difficulties in routine beam measurements. Techniques in machine learning have been successfully applied in other domains to overcome challenges inherent in noisy data. Variational autoencoders (VAEs) are shown to be capable of removing significant leevels of noise. A VAE can be used as a pre-processing tool for noise removal before the de-noised data is analyzed via other methods, or the VAE can be directly used to make beam dynamics measurements. Here we present the use of VAEs as a tool for addressing noise in BPM measurements.

43 PARTICLE ACCELERATORS↗

PLANS FOR WARM DENSE MATTER EXPERIMENTS AND IFE TARGET EXPERIMENTS ON NDCX-II

The Heavy Ion Fusion Science Virtual National Laboratory (HIFS-VNL) is currently developing design concepts for NDCX-II, the second phase of the Neutralized Drift Compression Experiment, which will use ion beams to explore Warm Dense Matter (WDM) and Inertial Fusion Energy (IFE) target hydrodynamics. The ion induction accelerator will consist of a new short pulse injector and induction cells from the decommissioned Advanced Test Accelerator (ATA) at Lawrence Livermore National Laboratory (LLNL). To fit within an existing building and to meet the energy and temporal requirements of various target experiments, an aggressive beam compression and acceleration schedule is planned. WDM physics and ion-driven direct drive hydrodynamics will initially be explored with 30 nC of lithium ions in experiments involving ion deposition, ablation, acceleration and stability of planar targets. Other ion sources which may deliver higher charge per bunch will be explored. A test stand has been built at Lawrence Berkeley National Laboratory (LBNL) to test refurbished ATA induction cells and pulsed power hardware for voltage holding and ability to produce various compression and acceleration waveforms. Another test stand is being used to develop and characterize lithium-doped aluminosilicate ion sources. The first experiments will include heating metallic targets to 10,000 K and hydrodynamics studies with cryogenic hydrogen targets.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Institute for Sustained Performance, Energy, and Resilience (SuPER)

The University of Tennessee (UTK) and University of Texas at El Paso (UTEP) partnership supported the three main thrusts of the SUPER project---performance, energy, and resilience. The UTK-UTEP effort thus helped advance the main goal of SUPER, which was to ensure that DOE's computational scientists can successfully exploit the emerging generation of high performance computing (HPC) systems. This goal is being met by providing application scientists with strategies and tools to productively maximize performance, conserve energy, and attain resilience. The primary vehicle through which UTK provided performance measurement support to SUPER and the larger HPC community is the Performance Application Programming Interface (PAPI). PAPI is an ongoing project that provides a consistent interface and methodology for collecting hardware performance information from various hardware and software components, including most major CPUs, GPUs and accelerators, interconnects, I/O systems, and power interfaces, as well as virtual cloud environments. The PAPI software is widely used for performance modeling of scientific and engineering applications---for example, the HOMME (High Order Methods Modeling Environment) climate code, and the GAMESS and NWChem computational chemistry codes---on DOE supercomputers. PAPI is widely deployed as middleware for use by higher-level profiling, tracing, and sampling tools (e.g., CrayPat, HPCToolkit, Scalasca, Score-P, TAU, Vampir, PerfExpert), making it the de facto standard for hardware counter analysis. PAPI has established itself as fundamental software infrastructure in every application domain (spanning academia, government, and industry), where improving performance can be mission critical. Ultimately, as more application scientists migrate their applications to HPC platforms, they will benefit from the extended capabilities this grant brought to PAPI to analyze and optimize performance in these environments, whether they use PAPI directly, or via third-party performance tools. Capabilities added to PAPI through this grant include support for new architectures such as the lastest GPU and Xeon Phi accelerators, and advanced power measurement and management features. Another important topic for the UTK team was providing support for a rich ecosystem of different fault management strategies in the context of parallel computing. Our long term efforts have been oriented toward proposing flexible strategies and providing building boxes that application developers can use to build the most efficient fault management technique for their application. These efforts span across the entire software spectrum, from theoretical models of existing strategies to easily assess their performance, to algorithmic modifications to take advantage of specific mathematical properties for data redundancy and to extensions to widely used programming paradigms to empower the application developers to deal with all types of faults. We have also continued our tight collaborations with users to help them adopt these technologies to ensure their application always deliver meaningful scientific data. Large supercomputer systems are becoming more and more power and energy constrained, and future systems and applications running on them will need to be optimized to run under power caps and/or minimize energy consumption. The UTEP team contributed to the SUPER energy thrust by developing power modeling methodologies and investigating power management strategies. Scalability modeling results showed that some applications can scale better with respect to an increasing power budget than with respect to only the number of processors. Power management, in particular shifting power to processors on the critical path of an application execution, can reduce perturbation due to system noise and other sources of runtime variability, which are growing problems on large-scale power-constrained computer systems.

42 ENGINEERING↗

GPU-accelerated Tersoff potentials for massively parallel Molecular Dynamics simulations

The Tersoff potential is one of the empirical many-body potentials that has been widely used in simulation studies at atomic scales. Unlike pair-wise potentials, the Tersoff potential involves three-body terms, which require much more arithmetic operations and data dependency. In this contribution, we have implemented the GPU-accelerated version of several variants of the Tersoff potential for LAMMPS, an open-source massively parallel Molecular Dynamics code. Compared to the existing MPI implementation in LAMMPS, the GPU implementation exhibits a better scalability and offers a speedup of 2.2X when run on 1000 compute nodes on the Titan supercomputer. On a single node, the speedup ranges from 2.0 to 8.0 times, depending on the number of atoms per GPU and hardware configurations. The most notable features of our GPU-accelerated version include its design for MPI/accelerator heterogeneous parallelism, its compatibility with other functionalities in LAMMPS, its ability to give deterministic results and to support both NVIDIA CUDA- and OpenCL-enabled accelerators. Our implementation is now part of the GPU package in LAMMPS and accessible for public use.

Computer Science↗

COMET: A Domain-Specific Compilation of High-Performance Computational Chemistry

The computational power increases over the past decades have greatly enhanced the ability to simulate chemical reactions and understand ever more complex transformations. Tensor contractions are the fundamental computational building block of these simulations. These simulations have often been tied to one platform and restricted in generality by the interface provided to the user. The expanding prevalence of accelerators and researcher demands necessitate a more general approach which is not tied to specific hardware or requires contortion of algorithms to specific hardware platforms. In this paper we present COMET, a domain-specific programming language and compiler infrastructure for tensor contractions targeting heterogeneous accelerators. We present a system of progressive lowering through multiple layers of abstraction and optimization that achieves up to 1.98×speedup for 30 tensor contractions commonly used in computational chemistry and beyond.

Mutlu, Erdal↗

ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing

The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this work, we propose ARENA – an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the dataflow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9 percent). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37× speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm 2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.

97 MATHEMATICS AND COMPUTING↗

Spatially resolved degradation during startup and shutdown in polymer electrolyte membrane fuel cell operation

Polymer electrolyte membrane fuel cells have durability limitations associated with the startup and shutdown of the fuel cell, which is critical for real-world vehicle commercialization. During startup or shutdown, there exists an active region (hydrogen/air) and a passive region (air/air) between the cell inlet and outlet. Internal currents are generated in the passive region causing high-potential excursion in the cathode leading to accelerated carbon corrosion. In this study, a segmented cathode hardware is used to evaluate the effect of platinum loading on both cathode and anode, and carbon support material on degradation due to repeated series of startups or shutdowns. Here, in situ losses in the performance and electrochemical surface area were measured spatially, and ex situ analysis of the catalyst layer thickness and platinum particle size was performed to understand the effect of startup or shutdown on different membrane electrode assembly materials. Startup degrades the region near anode outlet more, while shutdown degrades the region near anode inlet more compared to the rest of the electrode. While various system mitigation strategies have been reported in the literature to limit this degradation, one materials mitigation strategy is to limit the anode's ability to reduce oxygen to water through increasing the ratio of platinum loading in the cathode to the anode, or by using a bi-functional catalyst.

25 ENERGY STORAGE↗