Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Petascale 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2014

Final Report

The goal of this project was to create a community tool infrastructure for program development tools targeting Petascale class machines and beyond. This includes performance analysis, debugging, and correctness tools, as well as tuning and optimization frameworks. The infrastructure provides a comprehensive and extensible set of individual tool building components. Within this project we developed the basis for this infrastructure as well as set of core modules that allow a comprehensive performance analysis at scale. Further, we developed a methodology and workflow that allows others to add or replace modules, to integrate parts into their own tools, or to customize existing solutions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

Petascale Hierarchical Modeling VIA Parallel Execution

The research allows more effective model building. By allowing researchers to fit complex models to large datasets in a scalable manner, our algorithms and software enable more effective scientific research. In the new area of “big data,” it is often necessary to fit “big models” to adjust for systematic differences between sample and population. For this task, scalable and efficient model-fitting tools are needed, and these have been achieved with our new Hamiltonian Monte Carlo algorithm, the no-U-turn sampler, and our new C++ program, Stan. In layman’s terms, our research enables researchers to create improved mathematical modes for large and complex systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

First-Principles Petascale Simulations for Predicting Deflagration to Detonation Transition in Hydrogen-Oxygen Mixtures

Hydrogen has emerged as an important fuel across a range of industries as a means of achieving energy independence and to reduce emissions. DDT and the resulting detonation waves in hydrogen-oxygen can have especially catastrophic consequences in a variety of industrial and energy producing settings related to hydrogen. First-principles numerical simulations of flame acceleration and DDT are required for an in-depth understanding of the phenomena and facilitating design of safe hydrogen systems. The goals of this project were (1) to develop first-principles petascale reactive flow Navier-Stokes simulation code for predicting gaseous high-speed combustion and detonation (HSCD) phenomena and (2) demonstrate feasibility of first-principles simulations of rapid flame acceleration and deflagration-to-detonation transition (DDT) in stoichiometric hydrogen-oxygen mixture (2H 2 + O 2 ). The goals of the project have been accomplished. We have developed a novel numerical simulation code, named HSCD, for performing first-principles direct numerical simulations of high-speed hydrogen combustion. We carried out a series of validating numerical simulations of inert and reactive shock reflection experiments in shock tubes. We then performed a pilot numerical simulation of flame acceleration in a long pipe. The simulation showed the transition of the rapidly accelerating flame into a detonation. The DDT simulations were performed using BG/Q Mira at the Argonne National Laboratory, currently the fourth fastest super-computer in the world.

08 HYDROGEN↗
DOE OSTI2013

Community Petascale Project for Accelerator Science and Simulation

The UCLA Plasma Simulation Group is a major partner of the "Community Petascale Project for Accelerator Science and Simulation. This is the final technical report. We include an overall summary, a list of publications and individual progress reports for each years. During the past five years we have made tremendous progress in enhancing the capabilities of OSIRIS and QuickPIC, in developing new algorithms and data structures for PIC codes to run on GPUS and many future core architectures, and in using these codes to model experiments and in making new scientific discoveries. Here we summarize some highlights for which SciDAC was a major contributor.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2012

MOGO: Model-Oriented Global Optimization of Petascale Applications

The MOGO project was initiated under in 2008 under the DOE Program Announcement for Software Development Tools for Improved Ease-of-Use on Petascale systems (LAB 08-19). The MOGO team consisted of Oak Ridge National Lab, Argonne National Lab, and the University of Oregon. The overall goal of MOGO was to attack petascale performance analysis by developing a general framework where empirical performance data could be efficiently and accurately compared with performance expectations at various levels of abstraction. This information could then be used to automatically identify and remediate performance problems. MOGO was be based on performance models derived from application knowledge, performance experiments, and symbolic analysis. MOGO was able to make reasonable impact on existing DOE applications and systems. New tools and techniques were developed, which, in turn, were used on important DOE applications on DOE LCF systems to show significant performance improvements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

Final Report for "Community Petascale Project for Accelerator Science and Simulations"

This final report describes the work that has been accomplished over the past 5 years under the Community Petascale Project for Accelerator and Simulations (ComPASS) at Tech-X Corporation. Tech-X had been involved in the full range of ComPASS activities with simulation of laser plasma accelerator concepts, mainly in collaboration with LOASIS program at LBNL, simulation of coherent electron cooling in collaboration with BNL, modeling of electron clouds in high intensity accelerators, in collaboration with researchers at Fermilab and accurate modeling of superconducting RF cavity in collaboration with Fermilab, JLab and Cockcroft Institute in the UK.

43 PARTICLE ACCELERATORS↗
NASA NTRS2011

Using 100G Network Technology in Support of Petascale Science

NASA in collaboration with a number of partners conducted a set of individual experiments and demonstrations during SC 10 that collectively were titled "Using 100G Network Technology in Support of Petascale Science". The partners included the iCAIR, Internet2, LAC, MAX, National LambdaRail (NLR), NOAA and SCinet Research Sandbox (SRS) as well as the vendors Ciena, Cisco, ColorChip, cPacket, Extreme Networks, Fusion-io, HP and Panduit who most generously allowed some of their leading edge 40G/100G optical transport, Ethernet switch and Internet Protocol router equipment and file server technologies to be involved. The experiments and demonstrations featured different vendor-provided 40G/100G network technology solutions for full-duplex 40G and 100G LAN data flows across SRS-deployed single-node fiber-pairs among the Exhibit Booths of NASA, the National Center for Data lining, NOAA and the SCinet Network Operations Center, as well as between the NASA Exhibit Booth in New Orleans and the Starlight Communications Exchange facility in Chicago across special SC 10- only 80- and 100-Gbps wide area network links provisioned respectively by the NLR and Internet2, then on to GSFC across a 40-Gbps link. provisioned by the Mid-Atlantic Crossroads. The networks and vendor equipment were load-stressed by sets of NASA/GSFC High End Computer Network Team-built, relatively inexpensive, net-test-workstations that are capable of demonstrating greater than 100Gbps uni-directional nuttcp-enabled memory-to-memory data transfers, greater than 80-Gbps aggregate--bidirectional memory-to-memory data transfers, and near 40-Gbps uni-directional disk-to-disk file copying. This paper will summarize the background context, key accomplishments and some significances of these experiments and demonstrations.

Gary, James P.↗
DOE OSTI2019

Toward Simulating Turbulent Wall-Bounded Flows at High Reynolds Numbers on Exascale Platforms

Given that wall resolved LES (WRLES) of high Reynolds number flows will continue to be intractable on even exascale computing platforms, there is considerable effort to make hybrid RANS/LES (HRLES) methods the tool of choice for predictive simulations of high-Re separated flows. The fidelity of HRLES depends on the ability of the subgrid model to account for the effects of the filtered scales on the resolved scales, and on the numerical schemes that are used to evolve the Navier-Stokes equations. While higher-order numerical schemes, with low dissipation/dispersion errors (and higher arithmetic intensity), are commonly used for canonical flow simulations (on simpler geometries), the bulk of the high-Re flow simulations on complex geometry still employ nominally second-order accurate schemes in structured/unstructured flow solvers. Hence, there is a need for better sub-grid models that can improve the predictive capability of both the higher-order flow solvers and existing second-order accurate flow solvers, for simulating turbulent separated flows. This talk is about ongoing efforts to develop HRLES subgrid models from DNS/WRLES simulations of canonical flows over curved and sharply discontinuous surfaces and their ability to predict high-Re flows on current petascale platforms.

Balakrishnan, Ramesh↗
DOE OSTI2016

MADNESS: A Multiresolution, Adaptive Numerical Environment for Scientific Simulation

MADNESS (multiresolution adaptive numerical environment for scientific simulation) is a high-level software environment for solving integral and differential equations in many dimensions that uses adaptive and fast harmonic analysis methods with guaranteed precision based on multiresolution analysis and separated representations. Underpinning the numerical capabilities is a powerful petascale parallel programming environment that aims to increase both programmer productivity and code scalability. This paper describes the features and capabilities of MADNESS and briefly discusses some current applications in chemistry and several areas of physics.

00A72↗
DOE OSTI2013

TOPS2 - Towards Optimal Petascale Simulations

Our goal in this project was to design scalable numerical algorithms needed by SciDAC applications that adapt to use evolving hardware resources as efficiently as possible. Our primary challenge is minimizing communication costs, where communication means moving data either between levels of a memory hierarchy (L1 cache to L2 cache to main memory etc.) or between processors over a network. Floating point rates are improving exponentially faster than bandwidth, which is improving exponentially faster than latency. So our goal is to minimize communication. We describe our progress in this area, both for direct and iterative linear algebra. In both areas we have (1) identified lower bounds on the amount of communication (measured both by the number of words moved and the number of messages) required to perform these algorithms, (2) analyzed existing algorithms, which by and large do not attain these lower bounds, and (3) identified or invented new algorithms that do attain them, and evaluated their speedups, which can be quite large.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

A Petascale Non-Hydrostatic Atmospheric Dynamical Core in the HOMME Framework

The High-Order Method Modeling Environment (HOMME) is a framework for building scalable, conserva- tive atmospheric models for climate simulation and general atmospheric-modeling applications. Its spatial discretizations are based on Spectral-Element (SE) and Discontinuous Galerkin (DG) methods. These are local methods employing high-order accurate spectral basis-functions that have been shown to perform well on massively parallel supercomputers at any resolution and scale particularly well at high resolutions. HOMME provides the framework upon which the CAM-SE community atmosphere model dynamical-core is constructed. In its current incarnation, CAM-SE employs the hydrostatic primitive-equations (PE) of motion, which limits its resolution to simulations coarser than 0.1 per grid cell. The primary objective of this project is to remove this resolution limitation by providing HOMME with the capabilities needed to build nonhydrostatic models that solve the compressible Euler/Navier-Stokes equations.

58 GEOSCIENCES↗
DOE OSTI2014

Matrix Algebra for GPU and Multicore Architectures (MAGMA) for Large Petascale Systems

The goal of the MAGMA project is to create a new generation of linear algebra libraries that achieve the fastest possible time to an accurate solution on hybrid Multicore+GPU-based systems, using all the processing power that future high-end systems can make available within given energy constraints. Our efforts at the University of Tennessee achieved the goals set in all of the five areas identified in the proposal: 1. Communication optimal algorithms; 2. Autotuning for GPU and hybrid processors; 3. Scheduling and memory management techniques for heterogeneity and scale; 4. Fault tolerance and robustness for large scale systems; 5. Building energy efficiency into software foundations. The University of Tennessee’s main contributions, as proposed, were the research and software development of new algorithms for hybrid multi/many-core CPUs and GPUs, as related to two-sided factorizations and complete eigenproblem solvers, hybrid BLAS, and energy efficiency for dense, as well as sparse, operations. Furthermore, as proposed, we investigated and experimented with various techniques targeting the five main areas outlined.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

Near Real-time Data Analysis of Core-collapse Supernova Simulations with Bellerophon

We present an overview of a software system, Bellerophon, built to support a production-level HPC application called CHIMERA, which simulates core-collapse supernova events at the petascale. Developed over the last four years, Bellerophon enables CHIMERA's geographically dispersed team of collaborators to perform data analysis in near real-time. Its n-tier architecture provides an encapsulated, end-to-end software solution that enables the CHIMERA team to quickly and easily access highly customizable animated and static views of results from anywhere in the world via a web- deliverable, cross-platform desktop application. In addition, Bellerophon addresses software engineering tasks for the CHIMERA team by providing an automated mechanism for performing regression testing on a variety of supercomputing platforms. Elements of the team's workflow management needs are met with software tools that dynamically generate code repository statistics, access important online resources, and monitor the current status of several supercomputing resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

A new paradigm for petascale Monte Carlo simulation: Replica exchange Wang-Landau sampling

We introduce a generic, parallel Wang-Landau method that is naturally suited to implementation on massively parallel, petaflop supercomputers. The approach introduces a replica-exchange framework in which densities of states for overlapping sub-windows in energy space are determined iteratively by traditional Wang-Landau sampling. The advantages and general applicability of the method are demonstrated for several distinct systems that possess discrete or continuous degrees of freedom, including those with complex free energy landscapes and topological constraints.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2015

UCLA Final Technical Report for the "Community Petascale Project for Accelerator Science and Simulation”.

The UCLA Plasma Simulation Group is a major partner of the “Community Petascale Project for Accelerator Science and Simulation”. This is the final technical report. We include an overall summary, a list of publications, progress for the most recent year, and individual progress reports for each year. We have made tremendous progress during the three years. SciDAC funds have contributed to the development of a large number of skeleton codes that illustrate how to write PIC codes with a hierarchy of parallelism. These codes cover 2D and 3D as well as electrostatic solvers (which are used in beam dynamics codes and quasi-static codes) and electromagnetic solvers (which are used in plasma based accelerator codes). We also used these ideas to develop a GPU enabled version of OSIRIS. SciDAC funds were also contributed to the development of strategies to eliminate the Numerical Cerenkov Instability (NCI) which is an issue when carrying laser wakefield accelerator (LWFA) simulations in a boosted frame and when quantifying the emittance and energy spread of self-injected electron beams. This work included the development of a new code called UPIC-EMMA which is an FFT based electromagnetic PIC code and to new hybrid algorithms in OSIRIS. A new hybrid (PIC in r-z and gridless in φ) algorithm was implemented into OSIRIS. In this algorithm the fields and current are expanded into azimuthal harmonics and the complex amplitude for each harmonic is calculated separately. The contributions from each harmonic are summed and then used to push the particles. This algorithm permits modeling plasma based acceleration with some 3D effects but with the computational load of an 2D r-z PIC code. We developed a rigorously charge conserving current deposit for this algorithm. Very recently, we made progress in combining the speed up from the quasi-3D algorithm with that from the Lorentz boosted frame. SciDAC funds also contributed to the improvement and speed up of the quasi-static PIC code QuickPIC. We have also used our suite of PIC codes to make scientific discovery. Highlights include supporting FACET experiments which achieved the milestones of showing high beam loading and energy transfer efficiency from a drive electron beam to a witness electron beam and the discovery of a self-loading regime a for high gradient acceleration of a positron beam. Both of these experimental milestones were published in Nature together with supporting QuickPIC simulation results. Simulation results from QuickPIC were used on the cover of Nature in one case. We are also making progress on using highly resolved QuickPIC simulations to show that ion motion may not lead to catastrophic emittance growth for tightly focused electron bunches loaded into nonlinear wakefields. This could mean that fully self-consistent beam loading scenarios are possible. This work remains in progress. OSIRIS simulations were used to discover how 200 MeV electron rings are formed in LWFA experiments, on how to generate electrons that have a series of bunches on nanometer scale, and how to transport electron beams from (into) plasma sections into (from) conventional beam optic sections.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗
DOE OSTI2014

ACDT: Architected Composite Data Types Trading-in Unfettered Data Access for Improved Execution

With Exascale performance and its challenges in mind, one ubiquitous concern among architects is energy efficiency. Petascale systems projected to Exascale systems are unsustainable at current power consumption rates. One major contributor to system-wide power consumption is the number of memory operations leading to data movement and management techniques applied by the runtime system. To address this problem, we present the concept of the Architected Composite Data Types (ACDT) framework. The framework is made aware of data composites, assigning them a specific layout, transformations and operators. Data manipulation overhead is amortized over a larger number of elements and program performance and power efficiency can be significantly improved. We developed the fundamentals of an ACDT framework on a massively multithreaded adaptive runtime system geared towards Exascale clusters. Showcasing the capability of ACDT, we exercised the framework with two representative processing kernels - Matrix Vector Multiply and the Cholesky Decomposition – applied to sparse matrices. As transformation modules, we applied optimized compress/decompress engines and configured invariant operators for maximum energy/performance efficiency. Additionally, we explored two different approaches based on transformation opaqueness in relation to the application. Under the first approach, the application is agnostic to compression and decompression activity. Such approach entails minimal changes to the original application code, but leaves out potential applicationspecific optimizations. The second approach exposes the decompression process to the application, hereby exposing optimization opportunities that can only be exploited with application knowledge. The experimental results show that the two approaches have their strengths in HW and SW respectively, where the SW approach can yield performance and power improvements that are an order of magnitude better than ACDT-oblivious, hand-optimized implementations.We consider the ACDT runtime framework an important component of compute nodes that will lead towards power efficient Exascale clusters.

exascale↗
DOE OSTI2013

Automatic Transformation of MPI Programs to Asynchronous, Graph-Driven Form

The goals of this project are to develop new, scalable, high-fidelity algorithms for atomic-level simulations and program transformations that automatically restructure existing applications, enabling them to scale forward to Petascale systems and beyond. The techniques enable legacy MPI application code to exploit greater parallelism though increased latency hiding and improved workload assignment. The techniques were successfully demonstrated on high-end scalable systems located at DOE laboratories. Besides the automatic MPI program transformations efforts, the project also developed several new scalable algorithms for ab-initio molecular dynamics, including new massively parallel algorithms for hybrid DFT and new parallel in time algorithms for molecular dynamics and ab-initio molecular dynamics. These algorithms were shown to scale to very large number of cores, and they were designed to work in the latency hiding framework developed in this project. The effectiveness of the developments was enhanced by the direct application to real grand challenge simulation problems covering a wide range of technologically important applications, time scales and accuracies. These included the simulation of the electronic structure of mineral/fluid interfaces, the very accurate simulation of chemical reactions in microsolvated environments, and the simulation of chemical behavior in very large enzyme reactions.

97 MATHEMATICS AND COMPUTING↗