Search NASA⌕ Search

SEARCH · Search NASA

Results for “Accelerators, Computing”

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 991 records · Page 55

Balar: A SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of massive amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

SST-GPU: A Scalable SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of unprecedented amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

Integrating Asynchronous Task Parallelism with OpenSHMEM, In: OpenSHMEM 2016: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments

Partitioned Global Address Space (PGAS) programming models combine shared and distributed memory features, and provide a foundation for high-productivity parallel programming using lightweight one-sided communications. The OpenSHMEM programming interface has recently begun gaining popularity as a lightweight library-based approach for developing PGAS applications, in part through its use of a symmetric heap to realize more efficient implementations of global pointers than in other PGAS systems. However, current approaches to hybrid inter-node and intra-node parallel programming in OpenSHMEM rely on the use of multithreaded programming models (e.g., pthreads, OpenMP) that harness intra-node parallelism but are opaque to the OpenSHMEM runtime. This OpenSHMEM+X approach can encounter performance challenges such as bottlenecks on shared resources, long pause times due to load imbalances, and poor data locality. Furthermore, OpenSHMEM+X requires the expertise of hero-level programmers, compared to the use of just OpenSHMEM. All of these are hard challenges to mitigate with incremental changes. This situation will worsen as computing nodes increase their use of accelerators and heterogeneous memories.

Computer Science↗

2015 Neuro-Inspired Computational Elements Workshop: Information Processing and Computation Systems beyond von Neumann/Turing Architecture and Moore’s Law Limits

The third Neuro-Inspired Computational Elements (NICE) Workshop was held February 23-25, 2015 in Albuquerque, New Mexico. The goal of the Workshop was to bring together researchers from different scientific disciplines and application areas to provide a common point from which to develop the next generation of information processing/computing architectures that go beyond stored program architecture and Moore’s Law limits. Conventional, stored program architecture systems are designed for algorithmic and exact calculations. Many high impact problems, however, involve large, noisy, incomplete, “natural” data sets that do not lend themselves to convenient solutions from current systems. This Workshop series has focused on addressing these problems by building upon the convergence among neuroscience, microelectronics, and computational systems to develop new architectures designed to handle these natural data sets. An international group of nearly 100 registered attendees with a wide range of expertise and experience (e.g., neuroscience, systems, microelectronics, applications, and potential funding agencies) participated in this year’s event by offering knowledgeable insight regarding: Applications that look for solutions beyond the capabilities of current computational systems; Technical approaches that are at the early to middle stages of development for new computational systems; Pathways and resources to accelerate the development of these new systems.

97 MATHEMATICS AND COMPUTING↗

The ray-tracing code Zgoubi - latest developments

The reader is referred to the ICFA-BD-NL No.43, and to a more recent status article in NIMA, regarding the technical details of the Zgoubi tracking engine and its accuracy, which make it "near-symplectic" - sufficiently so to model millions of turns in large hadron colliders, - and its potential for pushing particles in complex accelerator structures and accelerator optical elements or their field maps. Extended documentation can be found in the regular FFA workshops as well as in the SourceForge code development site where in particular many examples of beam lines, FFAs and other ring simulations are maintained. There is also a comprehensive user's guide. Further documentation, including an attempt to demonstrate 6D simulation in all possible types of particle accelerators, can be found in the "Computer Laboratory" Stony Brook University "PHY689" semester series.

43 PARTICLE ACCELERATORS↗

E3SM: Improved Climate Prediction with Exascale Capability

The Energy Exascale Earth System Model (E3SM) project is an ongoing, state-of-the-science earth system modeling, simulation, and prediction effort that optimizes Department of Energy (DOE) computing resources to meet the science needs of the nation and the agency’s mission objectives. Climate simulation has become a proven tool for identifying and quantifying the impacts of climate change, but even greater accuracy is required at all levels to improve forecast precision. Understanding the impact of climate change on global and regional water cycles is one of the highest priorities and most difficult challenges in climate change prediction. As part of a subproject of DOE’s Exascale Computing Project, a multidisciplinary team including geophysical and computational scientists developed a multiscale modeling framework (MMF) to refine cloud representation in E3SM climate simulation on GPU accelerated supercomputers, making higher resolution, more computationally efficient predictions possible.

54 ENVIRONMENTAL SCIENCES↗

Numerical eigen-spectrum slicing, accurate orthogonal eigen-basis, and mixed-precision eigenvalue refinement using OpenMP data-dependent tasks and accelerator offload

Performing a variety of numerical computations efficiently and, at the same time, in a portable fashion requires both an overarching design followed by a number of implementation strategies. All of these are exemplified below as we present transitioning the PLASMA numerical library from relying on dependence-driven large tasks to achieving utilization of fine grain tasking and offload to hardware accelerators while keeping its core dependence sets: OpenMP source code pragmas and runtime for most system-level functionality and basic low-level numerical kernels provided directly by hardware vendors or open source projects with vendor contributions. We also present new algorithmic methods and their efficient parallel implementations including fine grained tasking for eigen-spectrum slicing and offload for mixed-precision eigenvalue refinement. We provide performance, scaling, and numerical results showing sizable gains over the available solutions from either the open source and vendor-provided packages.

Luszczek, Piotr↗

Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks

Here we propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope-based slope recovery term is added in the loss function, which further accelerates convergence, thereby reducing the training cost. On the theoretical side, we prove that in the proposed method, the gradient descent algorithms are not attracted to sub-optimal critical points or local minima under practical conditions on the initialization and learning rate, and that the gradient dynamics of the proposed method is not achievable by base methods with any (adaptive) learning rates. We further show that the adaptive activation methods accelerate the convergence by implicitly multiplying conditioning matrices to the gradient of the base method without any explicit computation of the conditioning matrix and the matrix–vector product. The different adaptive activation functions are shown to induce different implicit conditioning matrices. Furthermore, the proposed methods with the slope recovery are shown to accelerate the training process.

97 MATHEMATICS AND COMPUTING↗

A Task Based Approach for Co-Scheduling Ensemble Workloads on Heterogeneous Nodes

Scientific workflows consist of multiple, connected applications, with data and results flowing from one to another in a pipeline. Traditionally, such workflows are executed in sequential order, storing intermediate data in storage disks. Co-scheduling application workflows concurrently on the same compute nodes would greatly reduce the cost of moving data to/from storage and allow real-time analysis of intermediate results. Nevertheless, most parallel programming runtimes do not allow seamless integration of various applications in a scientific workflow, in part due to the complexity of managing data and resources. The situation is even more complicated for heterogeneous systems. In this work we extend the Minos Computing Library (MCL) runtime to accelerate pipe-lined and parallel workloads where multiple applications are running in the same system. MCL’s asynchronous task library and runtime dynamically manages resources to allow co-scheduling of multiple processes sharing heterogeneous resources. In addition, we design a custom ex- tension of the Open Compute Language (OpenCL) to enable multiple processes to share device memory. We enable MCL to coordinate these shared buffers to allow for easy, fast data sharing between applications. Using malleable micro-benchmarks and two application workflows that combine scientific simulation and AI-based analysis, we show that our method outperforms traditional approaches.

Index Terms—Parallel systems, Scheduling and Task ↗

Density-fitted singles and doubles coupled cluster on graphics processing units

We adapt an algorithm for singles and doubles coupled cluster (CCSD) that uses density fitting (DF) or Cholesky decomposition (CD) in the construction and contraction of all electron repulsion integrals (ERI s) for use on heterogeneous compute nodes consisting of a multicore CPU and at least one graphics processing unit (GPU). The use of approximate 3-index ERI s ameliorates two of the major difficulties in designing scientific algorithms for GPU s: (i) the extremely limited global memory on the devices and (ii) the overhead associated with data motion across the PCI bus. For the benzene trimer described by an aug-cc-pVDZ basis set, the use of a single NVIDIA Tesla C2070 (Fermi) GPU accelerates a CD-CCSD computation by a factor of 2.1, relative to the multicore CPU-only algorithm that uses 6 highly efficient Intel core i7-3930K CPU cores. The use of two Fermis provides an acceleration of 2.89, which is comparable to that observed when using a single NVIDIA Kepler K20c GPU (2.73).

Sherrill, David↗

Two new SciDAC institutes promote mathematical tools and software technology for high-performance computing

Bigger is often said to be better, and the newest extreme-scale computers certainly are bigger, with millions of processing units. Moreover, the breadth of science performed on the U.S. Department of Energy (DOE) computing facilities is expanding, with new technology such as artificial intelligence emerging. These advances are exciting, creating new opportunities for scientific discovery; however, they also raise new questions for scientists who want to exploit these advances for tackling more complex problems. Will my simulation code be able to utilize the accelerators in extreme-scale computing systems? Can I take advantage of the deepening memory hierarchy in heterogeneous processors? Is there a way around bottlenecks caused by the widening ratio of peak floating-point operations per second to I/0 bandwidth? How can I manage my huge amounts of data effectively? Can I analyze data in situ, or must I transfer it to offline storage for later analysis? To address such questions, DOE announced that it is providing $57.5 million over the next five years for two multidisciplinary teams — FASTMath and RAPIDS2 — to develop new tools and techniques to harness supercomputers for scientific discovery. The teams, called SciDAC Institutes, are part of the Scientific Discovery through Advanced Computing program.

97 MATHEMATICS AND COMPUTING↗

The Italian Summer Students Program at Fermilab and other US Laboratories: 40 years of education in particle physics and technology

Since 1983 the Italian groups collaborating with Fermilab (US) have been running a 2-month summer training program for Master students. While in the first year the program involved only 4 physics students, in the following years it was extended to engineering students. Many students have extended their collaboration with Fermilab with their Master Thesis and PhD. The program has involved more than 600 Italian students from more than 20 Italian universities. Each intern is supervised by a Fermilab Mentor responsible for the training program. Training programs spanned from Tevatron, CMS, Muon (g-2), Mu2e and SBN (MicroBooNE, Icarus, and SBND) and DUNE design and data analysis, development of particle detectors, design of electronic and accelerator components, development of infrastructures and software for tera-data handling, quantum computing and research on superconductive elements and accelerating cavities. In 2015 the University of Pisa included the program within its own educational programs. Summer Students are enrolled at the University of Pisa for the duration of the internship and at the end of the internship they write summary reports on their achievements. After positive evaluation by a University of Pisa Examining Board, interns are acknowledged 6 ECTS credits for their Diploma Supplement. The program was paused in 2020 and 2021 due to the COVID-19 pandemic, but it resumed in 2022. From 2022 to 2024, a total of 60 students participated in the nine-week training at Fermilab. We are currently organizing the 2025 program. This paper provides an overview of the program, which can serve as a model for other interested laboratories.

Barzi, Emanuela [Ohio State U.]↗

The Italian Summer Students Program at Fermilab and other US Laboratories: 40 years of education in particle physics and technology

Since 1983 the Italian groups collaborating with Fermilab (US) have been running a 2-month summer training program for Master students. While in the first year the program involved only 4 physics students, in the following years it was extended to engineering students. Many students have extended their collaboration with Fermilab with their Master Thesis and PhD. The program has involved almost 600 Italian students from more than 20 Italian universities. Each intern is supervised by a Fermilab Mentor responsible for the training program. Training programs spanned from Tevatron, CMS, Muon (g-2), Mu2e and SBN and DUNE design and data analysis, development of particle detectors, design of electronic and accelerator components, development of infrastructures and software for tera-data handling, quantum computing and research on superconductive elements and accelerating cavities. In 2015 the University of Pisa included the program within its own educational programs. Summer Students are enrolled at the University of Pisa for the duration of the internship and at the end of the internship they write summary reports on their achievements. After positive evaluation by a University of Pisa Examining Board, interns are acknowledged 6 ECTS credits for their Diploma Supplement. In the years 2020 and 2021 the program was canceled due to the sanitary emergency but in 2022 it was restarted and allowed a cohort of 21 students in 2022, and a cohort of 27 students in 2023 to be trained for nine weeks at Fermilab. We are now organizing the 2024 program.

Barzi, Emanuela↗

On a Simplified Approach to Achieve Parallel Performance and Portability Across CPU and GPU Architectures

This paper presents software advances to easily exploit computer architectures consisting of a multi-core CPU and CPU+GPU to accelerate diverse types of high-performance computing (HPC) applications using a single code implementation. The paper describes and demonstrates the performance of the open-source C++ matrix and array (MATAR) library that uniquely offers: (1) a straightforward syntax for programming productivity, (2) usable data structures for data-oriented programming (DOP) for performance, and (3) a simple interface to the open-source C++ Kokkos library for portability and memory management across CPUs and GPUs. The portability across architectures with a single code implementation is achieved by automatically switching between diverse fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. The MATAR library solves many longstanding challenges associated with easily writing software that can run in parallel on any computer architecture. This work benefits projects seeking to write new C++ codes while also addressing the challenges of quickly making existing Fortran codes performant and portable over modern computer architectures with minimal syntactical changes from Fortran to C++. We demonstrate the feasibility of readily writing new C++ codes and modernizing existing codes with MATAR to be performant, parallel, and portable across diverse computer architectures.

97 MATHEMATICS AND COMPUTING↗

THE DISSIPATION OF SOLAR WIND TURBULENT FLUCTUATIONS AT ELECTRON SCALES

We present two-dimensional fully kinetic particle-in-cell simulations of decaying electromagnetic fluctuations. The computational box is such that wavelengths ranging from electron to ion gyroradii are resolved. The parameters used are realistic for the solar wind, and the ion-to-electron mass ratio is physical. The dissipation of turbulent fluctuations at small scales is thought to be a crucial mechanism for solar wind acceleration and coronal heating. The computational results suggest that a power-law cascade of magnetic fluctuations could be sustained up to scales of the electron Larmor radius and smaller. We analyze the simulation results in light of the Vlasov linear theory, and we comment on the particle heating. The dispersion curves of lightly damped modes in this regime suggest that a linear mechanism could be responsible for the observed steepening of power spectra at electron scales, but a straightforward identification of turbulent fluctuations as an ensemble of linear modes is not possible.

79 ASTRONOMY AND ASTROPHYSICS↗

Advances in Parallel Electromagnetic Codes for Accelerator Science and Development

Over a decade of concerted effort in code development for accelerator applications has resulted in a new set of electromagnetic codes which are based on higher-order finite elements for superior geometry fidelity and better solution accuracy. SLAC's ACE3P code suite is designed to harness the power of massively parallel computers to tackle large complex problems with the increased memory and solve them at greater speed. The US DOE supports the computational science R&D under the SciDAC project to improve the scalability of ACE3P, and provides the high performance computing resources needed for the applications. This paper summarizes the advances in the ACE3P set of codes, explains the capabilities of the modules, and presents results from selected applications covering a range of problems in accelerator science and development important to the Office of Science.

43 PARTICLE ACCELERATORS↗

GPU COMPUTING FOR PARTICLE TRACKING

This is a feasibility study of using a modern Graphics Processing Unit (GPU) to parallelize the accelerator particle tracking code. To demonstrate the massive parallelization features provided by GPU computing, a simplified TracyGPU program is developed for dynamic aperture calculation. Performances, issues, and challenges from introducing GPU are also discussed. General purpose Computation on Graphics Processing Units (GPGPU) bring massive parallel computing capabilities to numerical calculation. However, the unique architecture of GPU requires a comprehensive understanding of the hardware and programming model to be able to well optimize existing applications. In the field of accelerator physics, the dynamic aperture calculation of a storage ring, which is often the most time consuming part of the accelerator modeling and simulation, can benefit from GPU due to its embarrassingly parallel feature, which fits well with the GPU programming model. In this paper, we use the Tesla C2050 GPU which consists of 14 multi-processois (MP) with 32 cores on each MP, therefore a total of 448 cores, to host thousands ot threads dynamically. Thread is a logical execution unit of the program on GPU. In the GPU programming model, threads are grouped into a collection of blocks Within each block, multiple threads share the same code, and up to 48 KB of shared memory. Multiple thread blocks form a grid, which is executed as a GPU kernel. A simplified code that is a subset of Tracy++ [2] is developed to demonstrate the possibility of using GPU to speed up the dynamic aperture calculation by having each thread track a particle.

42 ENGINEERING↗

Global adjoint tomography: first-generation model

We present the first-generation global tomographic model constructed based on adjoint tomography, an iterative full-waveform inversion technique. Synthetic seismograms were calculated using GPU-accelerated spectral-element simulations of global seismic wave propagation, accommodating effects due to 3-D anelastic crust & mantle structure, topography & bathymetry, the ocean load, ellipticity, rotation, and self-gravitation. Fréchet derivatives were calculated in 3-D anelastic models based on an adjoint-state method. The simulations were performed on the Cray XK7 named ‘Titan’, a computer with 18 688 GPU accelerators housed at Oak Ridge National Laboratory. The transversely isotropic global model is the result of 15 tomographic iterations, which systematically reduced differences between observed and simulated three-component seismograms. Our starting model combined 3-D mantle model S362ANI with 3-D crustal model Crust2.0. We simultaneously inverted for structure in the crust and mantle, thereby eliminating the need for widely used ‘crustal corrections’. We used data from 253 earthquakes in the magnitude range 5.8 ≤ M w ≤ 7.0. We started inversions by combining ~30 s body-wave data with ~60 s surface-wave data. The shortest period of the surface waves was gradually decreased, and in the last three iterations we combined ~17 s body waves with ~45 s surface waves. We started using 180 min long seismograms after the 12th iteration and assimilated minor- and major-arc body and surface waves. The 15th iteration model features enhancements of well-known slabs, an enhanced image of the Samoa/Tahiti plume, as well as various other plumes and hotspots, such as Caroline, Galapagos, Yellowstone and Erebus. Furthermore, we see clear improvements in slab resolution along the Hellenic and Japan Arcs, as well as subduction along the East of Scotia Plate, which does not exist in the starting model. Point-spread function tests demonstrate that we are approaching the resolution of continental-scale studies in some areas, for example, underneath Yellowstone. Here, this is a consequence of our multiscale smoothing strategy in which we define our smoothing operator as a function of the approximate Hessian kernel, thereby smoothing gradients less wherever we have good ray coverage, such as underneath North America.

58 GEOSCIENCES↗