Search NASA⌕ Search

SEARCH · Search NASA

Results for “accelerator performance”

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 1,279 records · Page 71

DRAGON: breaking GPU memory capacity limits with direct NVM access

Heterogeneous computing with accelerators is growing in importance in high performance computing (HPC). Recently, application datasets have expanded beyond the memory capacity of these accelerators, and often beyond the capacity of their hosts. Meanwhile, nonvolatile memory (NVM) storage has emerged as a pervasive component in HPC systems because NVM provides massive amounts of memory capacity at affordable cost. Currently, for accelerator applications to use NVM, they must manually orchestrate data movement across multiple memories and this approach only performs well for applications with simple access behaviors. To address this issue, we developed DRAGON, a solution that enables all classes of GP-GPU applications to transparently compute on terabyte datasets residing in NVM. DRAGON leverages the page-faulting mechanism on the recent NVIDIA GPUs by extending capabilities of CUDA Unified Memory (UM). Our experimental results show that DRAGON transparently expands memory capacity and obtain additional speedups via automated I/O and data transfer overlapping.

Markthub, Pak↗

Web-based, GPU-accelerated, Monte Carlo simulation and visualization of indirect radiation imaging detector performance

Purpose: Monte Carlo simulations play a vital role in the understanding of the fundamental limitations, design, and optimization of existing and emerging medical imaging systems. Efforts in this area have resulted in the development of a wide variety of open-source software packages. One such package, hybridMANTIS, uses a novel hybrid concept to model indirect scintillator detectors by balancing the computational load using dual CPU and graphics processing unit (GPU) processors, obtaining computational efficiency with reasonable accuracy. In this work, the authors describe two open-source visualization interfaces, webMANTIS and visualMANTIS to facilitate the setup of computational experiments via hybridMANTIS. Methods: The visualization tools visualMANTIS and webMANTIS enable the user to control simulation properties through a user interface. In the case of webMANTIS, control via a web browser allows access through mobile devices such as smartphones or tablets. webMANTIS acts as a server back-end and communicates with an NVIDIA GPU computing cluster that can support multiuser environments where users can execute different experiments in parallel. Results: The output consists of point response and pulse-height spectrum, and optical transport statistics generated by hybridMANTIS. The users can download the output images and statistics through a zip file for future reference. In addition, webMANTIS provides a visualization window that displays a few selected optical photon path as they get transported through the detector columns and allows the user to trace the history of the optical photons. Conclusions: The visualization tools visualMANTIS and webMANTIS provide features such as on the fly generation of pulse-height spectra and response functions for microcolumnar x-ray imagers while allowing users to save simulation parameters and results from prior experiments. The graphical interfaces simplify the simulation setup and allow the user to go directly from specifying input parameters to receiving visual feedback for the model predictions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing

Abstract We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Comparisons of time explicit hybrid kinetic-fluid code Architect for Plasma Wakefield Acceleration with a full PIC code

Architect, a time explicit hybrid code designed to perform quick simulations for electron driven plasma wakefield acceleration, is described. In order to obtain beam quality acceptable for applications, control of the beam-plasma-dynamics is necessary. Particle in Cell (PIC) codes represent the state-of-the-art technique to investigate the underlying physics and possible experimental scenarios; however PIC codes demand the necessity of heavy computational resources. Architect code substantially reduces the need for computational resources by using a hybrid approach: relativistic electron bunches are treated kinetically as in a PIC code and the background plasma as a fluid. Cylindrical symmetry is assumed for the solution of the electromagnetic fields and fluid equations. In this paper both the underlying algorithms as well as a comparison with a fully three dimensional particle in cell code are reported. The comparison highlights the good agreement between the two models up to the weakly non-linear regimes. In highly non-linear regimes the two models only disagree in a localized region, where the plasma electrons expelled by the bunch close up at the end of the first plasma oscillation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Effect of Low Temperature Nitrogen Baking on Superconducting Radio Frequency Cavities With Different Frequency

We report the rf performance of several single-cell superconducting radiofrequency cavities frequency ranging from 1.3-3.0 GHz after low temperature baking in nitrogen environment The cavities are treated at different temperature in the range of (120-160oC) for extended period of time (~24-48 hours) with nitrogen gas injection in the furnace. The improvement in Q0 with Q-rise in some case was observed when nitrogen gas was injected at elevated temperature (~250-290 oC) and held at the temperature range 120-200 oC without any degradation in accelerating gradient over the baseline performance. The temperature and time of baking play significant role in dependence of quality factor on accelerating gradient.

Khanal, B.↗

Fixing Amdahl's Law within the Limits of Accelerated Systems: FALLACY

Closeout report for FALLACY project. The performance of Data Model Convergence Initiative (DMC) applications on parallel machines is far below the limit set by Amdahl’s law. Whether the machine is based on many-core, GPUs, FPGAs, or a heterogeneous combination, usually the most significant bottleneck is accessing data from the memory system. Aligning with DMC’s HW/architecture thrust, this project developed a set of memory-centric tools called ‘MemGaze’ that inform the HW/SW stack about an application’s memory behavior, including data access latency and diagnosing poor data layout and data composition. Our approach uses architectural modeling and analysis of workload data accesses.

97 MATHEMATICS AND COMPUTING↗

Improving vacuum performance in the warm linac of the Spallation Neutron Source

The Spallation Neutron Source is an accelerator-based neutron source built and operated by the U.S. Department of Energy in Oak Ridge, Tennessee. With over 10 years of operation at 1 MW of power and above, shortcomings have been identified in the original vacuum pumping scheme for the drift tube and the coupled cavity linear accelerator sections. In this article, the vacuum performance for these systems is reviewed and the major areas of concern are discussed. The changes to the vacuum system are examined and the final design is described. Finally, the performance impact of these changes after a year of operation with the new vacuum system is presented.

47 OTHER INSTRUMENTATION↗

An Evaluation of Molecular Dynamics Performance on the Hybrid Cray XK6 Supercomputer

For many years, the drive towards computational physics studies that match the size and time-scales of experiment has been fueled by increases in processor and interconnect performance that could be exploited with relatively little modification to existing codes. Engineering and electrical power constraints have disrupted this trend, requiring more drastic changes to both hardware and software solutions. Here, we present details of the Cray XK6 architecture that achieves increased performance with the use of GPU accelerators. We review software development efforts in the LAMMPS molecular dynamics package that have been implemented in order to utilize hybrid high performance computers. We present benchmark results for solid-state, biological, and mesoscopic systems and discuss some challenges for utilizing hybrid systems. We present some early work in improving application performance on the XK6 and performance results for the simulation of liquid copper nanostructures with the embedded atom method.

43 PARTICLE ACCELERATORS↗

Intermittency and geometrical statistics of three-dimensional homogeneous magnetohydrodynamic turbulence: A wavelet viewpoint

Scale-dependent and geometrical statistics of three-dimensional incompressible homogeneous magnetohydrodynamic turbulence without mean magnetic field are examined by means of the orthogonal wavelet decomposition. The flow is computed by direct numerical simulation with a Fourier spectral method at resolution 512{sup 3} and a unit magnetic Prandtl number. Scale-dependent second and higher order statistics of the velocity and magnetic fields allow to quantify their intermittency in terms of spatial fluctuations of the energy spectra, the flatness, and the probability distribution functions at different scales. Different scale-dependent relative helicities, e.g., kinetic, cross, and magnetic relative helicities, yield geometrical information on alignment between the different scale-dependent fields. At each scale, the alignment between the velocity and magnetic field is found to be more pronounced than the other alignments considered here, i.e., the scale-dependent alignment between the velocity and vorticity, the scale-dependent alignment between the magnetic field and its vector potential, and the scale-dependent alignment between the magnetic field and the current density. Finally, statistical scale-dependent analyses of both Eulerian and Lagrangian accelerations and the corresponding time-derivatives of the magnetic field are performed. It is found that the Lagrangian acceleration does not exhibit substantially stronger intermittency compared to the Eulerian acceleration, in contrast to hydrodynamic turbulence where the Lagrangian acceleration shows much stronger intermittency than the Eulerian acceleration. The Eulerian time-derivative of the magnetic field is more intermittent than the Lagrangian time-derivative of the magnetic field.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Towards Efficient Alternating Current Optimal Power Flow Analysis on Graphical Processing Units

We present a solution of sparse ACOPF analysis on GPU. In particular, we discuss the performance bottlenecks and detail our efforts to accelerate the linear solver, a core component of ACOPF that dominates the computational time. ACOPF solutions of two large-scale systems, synthetic Northeast (25,000 buses) and Eastern (70,000 buses) \cite{birchfield2017tamu-cases} on GPU show promising speed-up compared to CPU based solution using a state-of-the-art solver. To our knowledge, this is the first result demonstrating acceleration of sparse ACOPF on GPUs.

Power grid analysis, GPU↗