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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Evaluation of Performance Variables to Accelerate the Deployment of Sustainable Aviation Fuels at a Regional Scale

An increase in jet fuel consumption and its associated emissions across the world have led to the need for alternative technologies to produce sustainable aviation fuels (SAF). One option to produce SAFs is to utilize waste or biomass-based feedstocks that has the potential to reduce greenhouse gas emissions by 50% or more compared to conventional jet fuel. However, there is a lack of understanding of how the synergistic effects of key performance variables could hinder or help the deployment of aviation fuels on a regional scale. Here, we assess the implications of key variables-including type and quantity of waste/biomass feedstock availability near the airport, cost of SAF production, life cycle greenhouse gas (GHG) emissions, policies, and fuel/infrastructure logistics-on the deployment of SAF at Chicago's O'Hare International Airport. We consider three ASTM International-approved SAF technologies (Hydroprocessed Esters and Fatty Acids, Fischer-Tropsch, and Alcohol to Jet) that can be blended up to 50% with petroleum-based jet fuel. Results from our analysis show that woody biomass-based Fischer-Tropsch technology has the lowest fuel production costs ($2.31-$2.81/gallon gasoline equivalent) of all pathways, and it reduces life cycle GHG emissions by 86% compared to conventional jet fuel despite the higher availability of crop residues compared to either woody biomass or fats, oils, and greases. Also, infrastructure is available at O'Hare International Airport to blend SAF with Jet A fuel through three terminals directly connected to the airport via pipelines. Our sensitivity analysis shows renewable fuel incentives and feedstock price to be key performance variables affecting the production cost and deployment of SAF.

alcohol-to-jet↗
DOE OSTI2023

Performance-Portable GPU Acceleration of the EFIT Tokamak Plasma Equilibrium Reconstruction Code

This paper presents the steps followed to GPU-offload parts of the core solver of EFIT-AI, an equilibrium reconstruction code suitable for tokamak experiments and burning plasmas. For this work, we will focus on the fitting procedure that consists of a Grad–Shafranov (GS) equation inverse solver that calculates equilibrium reconstructions on a grid. We will show profiling results of the original code (CPU-baseline), as well as the directives used to GPU-offload the most time-consuming function, initially to compare OpenACC and OpenMP on NVIDIA and AMD GPUs and later on to assess OpenMP performance portability on NVIDIA, AMD and Intel GPUs. We will make a performance comparison for different spatial grid sizes and show the speedup achieved on NVIDIA A100 (Perlmutter-NERSC), AMD MI250X (Frontier-OLCF) and Intel PVC GPUs (Sunspot-ALCF). Finally, we will draw some conclusions and recommendations to achieve high-performance portability for an equilibrium reconstruction code on the new HPC architectures

GPU↗
DOE OSTI2023

CHARM-SYCL: New Unified Programming Environment for Multiple Accelerator Types

Addressing performance portability across diverse accelerator architectures has emerged as a major challenge in the development of application and programming systems for high-performance computing environments. Although recent programming systems that focus on performance portability have significantly improved productivity in an effort to meet this challenge, the problem becomes notably more complex when compute nodes are equipped with multiple accelerator types—each with unique performance attributes, optimal data layout, and binary formats. To navigate the intricacies of multi-accelerator programming, we propose CHARM-SYCL as an extension of our CHARM multi-accelerator execution environment [27]. This environment will combine our SYCL-based performance-portability programming front end with a back end for extremely heterogeneous architectures as implemented with the IRIS runtime from Oak Ridge National Laboratory. Our preliminary evaluation indicates potential productivity boost and reasonable performance compared to vendor-specific programming system and runtimes.

Fujita, Norihisa↗
DOE OSTI2024

LibERI—A portable and performant multi-GPU accelerated library for electron repulsion integrals via OpenMP offloading and standard language parallelism

A portable and performant graphics processing unit (GPU)-accelerated library for electron repulsion integral (ERI) evaluation, named LibERI, has been developed and implemented via directive-based (e.g., OpenMP and OpenACC) and standard language parallelism (e.g., Fortran DO CONCURRENT). Offloaded ERIs consist of integrals over low and high contraction s, p, and d functions using the rotated-axis and Rys quadrature methods. GPU codes are factorized based on previous developments with two layers of integral screening and quartet presorting. In this work, the density screening is moved to the GPU to enhance the computational efficacy for large molecular systems. Here, the L-shells in the Pople basis set are also separated into pure S and P shells to increase the ERI homogeneity and reduce atomic operations and the memory footprint. LibERI is compatible with any quantum chemistry drivers supporting the MolSSI Driver Interface. Benchmark calculations of LibERI interfaced with the GAMESS software package were carried out on various GPU architectures and molecular systems. The results show that the LibERI performance is comparable to other state-of-the-art GPU-accelerated codes (e.g., TeraChem and GMSHPC) and, in some cases, outperforms conventionally developed ERI CUDA kernels (e.g., QUICK) while fully maintaining portability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Diesel Particulate Filter Durability Performance Comparison Using Metals Doped B20 vs. Conventional Diesel Part I: Accelerated Ash Loading and DPF Performance Evaluation

The project objective was to generate experimental data to evaluate the impact of metals doped B20 on DPF ash loading and performance compared to that of conventional petrodiesel. Accelerated ash loading was conducted on two DPFs - one exposed to regular diesel fuel and the other to B20 containing metal dopants equivalent to 4 ppm B100 total metals (currently total metals are limited to 10 ppm in ASTM D6751, the standard for B100). Periodic performance evaluations were conducted on the DPFs at 10 g/L ash loading intervals. After the evaluations at 30 g/L, the DPF was cleaned with a commercial DPF cleaning machine and another round of DPF evaluations were conducted. A comparison of the effect of ash loading with the two fuels and DPF cleaning is presented. The metals doped B20 fuel resulted in ash that was similar to that deposited when exposed to ULSD (lube oil ash) and exhibited similar ash cleaning removal efficiency. Metals doped B20 resulted in faster ash accumulation within the DPF, as expected, but did not appear to have a negative effect on DPF pressure drop or regeneration rates (up to 30 g/L of ash) or exhibit deleterious physical effects on the DPF substrate.

ADVANCED PROPULSION SYSTEMS,BIOMASS FUELS↗
DOE OSTI2024

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↗
DOE OSTI2024

Regional-scale fault-to-structure earthquake simulations with the EQSIM framework: Workflow maturation and computational performance on GPU-accelerated exascale platforms

Continuous advancements in scientific and engineering understanding of earthquake phenomena, combined with the associated development of representative physics-based models, is providing a foundation for high-performance, fault-to-structure earthquake simulations. However, regional-scale applications of high-performance models have been challenged by the computational requirements at the resolutions required for engineering risk assessments. The EarthQuake SIMulation (EQSIM) framework, a software application development under the US Department of Energy (DOE) Exascale Computing Project, is focused on overcoming the existing computational barriers and enabling routine regional-scale simulations at resolutions relevant to a breadth of engineered systems. This multidisciplinary software development—drawing upon expertise in geophysics, engineering, applied math and computer science—is preparing the advanced computational workflow necessary to fully exploit the DOE’s exaflop computer platforms coming online in the 2023 to 2024 timeframe. Achievement of the computational performance required for high-resolution regional models containing upward of hundreds of billions to trillions of model grid points requires numerical efficiency in every phase of a regional simulation. This includes run time start-up and regional model generation, effective distribution of the computational workload across thousands of computer nodes, efficient coupling of regional geophysics and local engineering models, and application-tailored highly efficient transfer, storage, and interrogation of very large volumes of simulation data. This article summarizes the most recent advancements and refinements incorporated in the workflow design for the EQSIM integrated fault-to-structure framework, which are based on extensive numerical testing across multiple graphics processing unit (GPU)-accelerated platforms, and demonstrates the computational performance achieved on the world’s first exaflop computer platform through representative regional-scale earthquake simulations for the San Francisco Bay Area in California, USA.

58 GEOSCIENCES↗
DOE OSTI2022

3rd harmonic magnetometry assessment of NbTiN-based SIS structures

In the quest for alternative superconducting materials to bring accelerator cavity performance beyond the bulk niobium (Nb) intrinsic limits, a promising concept proposes that superconductor-insulator-superconductor (SIS) thin film structures can delay magnetic flux penetration in accelerator cavities to higher fields [1]. NbTiN is a candidate superconductor for such structures. We have demonstrated high quality NbTiN and AlN deposited by reactive direct current magnetron sputtering (DCMS), both for individual layers and multilayers. Interface quality has been assessed for bi-layer stacks with various NbTiN and AlN thicknesses from 500 and 30 nm down to 3 and 1 nm. These SIS structures show continued sharp interfaces. The Hfp enhancement of the films was examined with 3rd harmonic magnetometry. The system was designed and built in an ongoing collaboration with CEA Saclay. It can measure 1? to 2? samples on a temperature controlled stage. This contribution presents the assessment of the first penetration field enhancement with 3rd harmonic magnetometry for standalone films and multilayer nanostructures.

Valente, Anne-Marie↗
DOE OSTI2021

Performance of concrete under accelerated physical salt attack and carbonation

Conventional testing of physical salt attack (PSA) on concrete does not consider concomitant factors that may exist in service and alter the mechanisms and kinetics of PSA. This study adopted a combined testing approach where concrete was concurrently investigated under accelerated PSA and carbonation, simulating elements serving in heavy traffic and industrial zones, while implementing ambient conditions similar to that in geographic locations with previous cases of PSA. Based on the tested mixture design parameters [water-to-binder ratio, cement type, and supplementary cementitious materials], potential performance improvement and risks were identified. Thermal, mineralogical, and microscopy analyses elucidated the co-occurrence of complex degradation processes in concrete subjected to accelerated PSA and carbonation, which were distinctive from that induced by the single-factor PSA exposure. The synoptic results from this study may informatively improve guidance on mixture design of concrete when dual exposure to PSA and carbonation is expected in the field.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Parallelizing autotuning for HPC applications: Unveiling the potential of the speculation strategy in Bayesian optimization

In the exascale computing era, tuning High-Performance Computing (HPC) applications has become a significant computational challenge. Although Bayesian optimization (BO) has emerged as a promising tool for HPC performance tuning, the BO workflow is inherently sequential (i.e., one function evaluation at a time) and cannot leverage the huge amount of parallel resources present in modern supercomputers, resulting in a considerable underutilization of their computational capabilities. This paper explores the trade-off between search quality and parallelism in BO, investigating a diverse set of methods. Building upon both previous approaches from the literature and novel methodologies introduced in this work, our study provides a deep analysis to accelerate BO performance tuning. By examining a set of synthetic functions and practical HPC applications, our exploration analyzes the interaction among various BO methods for parallelization, the quantity of parallel resources, the runtime distribution of target HPC applications, and the costs associated with different search orchestration mechanisms that have been overlooked in previous studies. Compared to sequential BO, our novel methodology achieves comparable quality while demonstrating robust scalability in search time as the amount of parallel resources increases; it also outperforms a state-of-the-art tuner, which supports parallelization, achieving up to 3.67x faster search time. We provide high-value insights for practitioners seeking to leverage the power of parallel computing for efficient HPC application tuning. Additionally, to further assist researchers in accelerating the performance tuning of their HPC applications, we provide an extension of an existing open-source tuning framework that incorporates our methods.

Bayesian optimization↗
DOE OSTI2021

FPGA-based HPC accelerators: An evaluation on performance and energy efficiency

Hardware specialization is a promising direction for the future of digital computing. Reconfigurable technologies enable hardware specialization with modest non-recurring engineering cost, but their performance and energy efficiency compared to state-of-the-art processor architectures remain an open question. In this article, we use FPGAs to evaluate the benefits of building specialized hardware for numerical kernels found in scientific applications. In order to properly evaluate performance, we not only compare Intel Arria 10 and Xilinx U280 performance against Intel Xeon, Intel Xeon Phi, and NVIDIA V100 GPUs, but we also extend the Empirical Roofline Toolkit (ERT) to FPGAs in order to assess our results in terms of the Roofline model. We show design optimization and tuning techniques for peak FPGA performance at reasonable hardware usage and power consumption. As FPGA peak performance is known to be far less than that of a GPU, we also benchmark the energy efficiency of each platform for the scientific kernels comparing against microbenchmark and technological limits. Results show that while FPGAs struggle to compete in absolute terms with GPUs on memory- and compute-intensive kernels, they require far less power and can deliver nearly the same energy efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

High-gradient performance of a prototype accelerator cavity for a 3 GeV proton radiography booster

This paper reports the design, fabrication, and results of the high-gradient conditioning and testing for a two-cell, π -mode, standing wave normal-conducting prototype booster cavity for the proposed 3 GeV proton linac upgrade at Los Alamos Neutron Science Center. Increasing the energy of proton beam from the existing 800 MeV to 3 GeV will improve resolution of the proton radiography by up to 10 times. The proposed energy boost can be achieved with a compact normal-conducting high-gradient radio-frequency (rf) linac section. The C-band section of the booster linac was designed with optimized-shaped copper accelerator cavities with distributed rf coupling. A short two-cell test prototype structure was designed for the frequency of 5.712 GHz, fabricated, and tested at the C-band Engineering Research Test Facility in New Mexico (CERF-NM) at Los Alamos National Laboratory. The maximum klystron power coupled into the test structure was 8.3 MW with 1 μ s pulse length and 100 Hz repetition rate. The breakdown probabilities were recorded as functions of the accelerating gradient and peak surface fields. Operation of the test cavity at accelerating gradients of up to 100 MV / m was demonstrated. Published by the American Physical Society 2024

43 PARTICLE ACCELERATORS↗