Results for “high performance parallel computing” — Page 41

DOE OSTI2020

Neuromorphic scaling advantages for energy-efficient random walk computations

Computing stands to be radically improved by neuromorphic computing (NMC) approaches inspired by the brain's incredible efficiency and capabilities. Most NMC research, which aims to replicate the brain's computational structure and architecture in man-made hardware, has focused on artificial intelligence; however, less explored is whether this brain-inspired hardware can provide value beyond cognitive tasks. We demonstrate that high-degree parallelism and configurability of spiking neuromorphic architectures makes them well-suited to implement random walks via discrete time Markov chains. Such random walks are useful in Monte Carlo methods, which represent a fundamental computational tool for solving a wide range of numerical computing tasks. Additionally, we show how the mathematical basis for a probabilistic solution involving a class of stochastic differential equations can leverage those simulations to provide solutions for a range of broadly applicable computational tasks. Despite being in an early development stage, we find that NMC platforms, at a sufficient scale, can drastically reduce the energy demands of high-performance computing platforms.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2019

Implementation of a Particle Accelerator Beam Dynamics Code on Multi-Node GPUs

Particle accelerators play an important role in a wide range of scientific discoveries and industrial applications. The self-consistent multi-particle simulation based on the particle-in-cell (PIC) method has been used to study charged particle beam dynamics inside those accelerators. However, the PIC simulation is time-consuming and needs to use modern parallel computers for high-resolution applications. In this paper, we implemented a parallel beam dynamics PIC code on multi-node hybrid architecture computers with multiple Graphics Processing Units (GPUs). We used two methods to parallelize the PIC code on multiple GPUs and observed that the replication method is a better choice for moderate problem size and current computer hardware while the domain decomposition method might be a better choice for large problem size and more advanced computer hardware that allows direct communications among multiple GPUs. Using the multi-node hybrid architectures at Oak Ridge Leadership Computing Facility (OLCF), the optimized GPU PIC code achieves a reasonable parallel performance and scales up to 64 GPUs with 16 million particles.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Automation and optimization of stopping and range of ions in matter simulation runtime

Prior to every ion implantation experiment a simulation of the ion range and other relevant parameters is performed using Monte-Carlo based codes. Although increasing computing power has improved the speed of these calculations, the demands on Monte-Carlo codes are also increasing, requiring evaluation of the optimal number of simulations while ensuring accuracy within threshold bounds. We evaluate the “Stopping and Range of Ions in Matter” (SRIM) code due to its widespread usage. We show how dividing simulations into multiple parallel simulations with different random seeds can lead to calculation speedup and find lower bounds for the required number of ion traces simulated based on an exemplar system of a Ga focused ion beam and a high energy C beam as used in high linear energy transfer testing. Here our results indicate simulations can yield results within the underlying data accuracy of SRIM at 10X and 100X shorter simulation time than the SRIM default values.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2017

On Analytics of File Transfer Rates over Dedicated Wide-Area Connections

File transfers between the decentralized storage sites over dedicated wide-area connections are becoming increasingly important in high-performance computing and big data scenarios. Designing such scientific workflows for large file transfers is extremely challenging as they depend on the file, I/O, host, and local- and wide-area network subsystems, and their interactions. To gain insights into file-transfer rate profiles, we develop polynomial, bagging, and boosting regression models for Lustre and XFS file transfer measurements, which are collected using XDD over a suite of 10 Gbps connections with 0-366 ms round trip times (RTTs). In addition to overall trends and analytics, these regressions also provide file-transfer rate estimates for RTTs and number of parallel flows at which measurements might not have been collected. They show that bagging and boosting techniques provide closer data fits than the polynomial regression. We develop probabilistic bounds on the generalization error of these methods, which combined with the cross-validation error establish that former two are more accurate estimators than the polynomial regression. In addition, we present a method to efficiently determine the number of parallel flows to achieve a peak file-transfer rate using fewer than full sweep measurements; in our measurements, the peak is achieved in 96% of cases with 15-25% of measurements of a full sweep.

Sen, Satyabrata↗

DOE OSTI2023

Fast tree-based algorithms for DBSCAN for low-dimensional data on GPUs

DBSCAN is a well-known density-based clustering algorithm to discover arbitrary shape clusters. While conceptually simple in serial, the algorithm is challenging to efficiently parallelize on manycore GPU architectures. Common pitfalls, such as asynchronous range query calls, result in high thread execution divergence in many implementations. In this paper, we propose a new framework for GPU-accelerated DBSCAN, and describe two tree-based algorithms within that framework. Both algorithms fuse the search for neighbors with updating cluster information, but differ in their treatment of dense regions of the data. We show that the time taken to compute clusters is at most twice that of determination of the neighbors. We compare the proposed algorithms with existing CPU and GPU implementations, and demonstrate their competitiveness and performance using a fast traversal structure (bounding volume hierarchy) for low dimensional data. We also show that the memory usage can be reduced by processing object neighbors dynamically without storing them.

Prokopenko, Andrey↗

DOE OSTI2022

User-oriented Improvements in the MOOSE Framework in Support of Multiphysics Simulation

The Multiphysics Object-Oriented Simulation Environment (MOOSE) framework is a foundational capability used by the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program to create over 15 different simulation tools for advanced nuclear reactors. Due to this ubiquity, improvements to the framework in support of modeling and simulation goals are critical to the program. These improvements can take many forms, including optimization, improved user experience, streamlined application programming interfaces (APIs), parallelism, and new capabilities. The work transcribed in this report was conducted in direct support of the simulation tools and has already been deployed or will be deployed in the coming months. The capabilities were implemented in the same order as they are covered in this report: chainable execution objects or executors, support for transfers between same-level applications in a coupling scheme, support for boundary/subdomain restricted transfers, support for transfers between applications with different coordinate or unit systems, support for MOOSE applications in the NEAMS Workbench, deployment of the MOOSE application of the Idaho National Laboratory (INL) high-performance computing (HPC) OnDemand platform, the addition of a triangular meshing library in libMesh, and increased support of face variables.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limit

Turbulence plays a crucial role in multiphysics applications, including aerodynamics, fusion, and combustion. Accurately capturing turbulence's multiscale characteristics is essential for reliable predictions of multiphysics interactions, but remains a grand challenge even for exascale supercomputers and advanced deep learning models. The extreme-resolution data required to represent turbulence, ranging from billions to trillions of grid points, pose prohibitive computational costs for models based on architectures like vision transformers. To address this challenge, we introduce a multiscale hierarchical Turbulence Transformer that reduces sequence length from billions to a few millions and a novel RingX sequence parallelism approach that enables scalable long-context learning. We perform scaling and science runs on the Frontier supercomputer. Our approach demonstrates excellent performance up to 1.1 EFLOPS on 32,768 AMD GPUs, with a scaling efficiency of 94\%. To our knowledge, this is the first AI model for turbulence that can capture small-scale eddies down to the dissipative range in three-dimensional turbulence at high Reynolds numbers.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗

DOE OSTI2020

Model Exploration of an Information-Based Healthcare Intervention Using Parallelization and Active Learning

This paper describes the application of a large-scale active learning method to characterize the parameter space of a computational agent-based model developed to investigate the impact of CommunityRx, a clinical information-based health intervention that provides patients with personalized information about local community resources to meet basic and self-care needs. Additionally, the diffusion of information about community resources and their use is modeled via networked interactions and their subsequent effect on agents' use of community resources across an urban population. A random forest model is iteratively fitted to model evaluations to characterize the model parameter space with respect to observed empirical data. We demonstrate the feasibility of using high-performance computing and active learning model exploration techniques to characterize large parameter spaces; by partitioning the parameter space into potentially viable and non-viable regions, we rule out regions of space where simulation output is implausible to observed empirical data. We argue that such methods are necessary to enable model exploration in complex computational models that incorporate increasingly available micro-level behavior data. We provide public access to the model and high-performance computing experimentation code.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2018

Scalable Distributed Memory Community Detection Using Vite

Graph clustering, popularly known as community detection, is a fundamental graph operation used in several applications of relevance for network analysis and cybersecurity. Community detection is an operation of partitioning a network into an arbitrary number of “communities” such that each com munity represents a tightly-knit group of nodes with relatively sparser connections to the rest of the nodes in the network. The need to compute clustering on large-scale networks necessitates the development of efficient parallel algorithms capable of exploiting modern parallel architectures. However, due to their irregular and inherently sequential nature, many of the current algorithms for community detection are challenging to parallelize. In response to the 2018 Graph Challenge, we present Vite which is a distributed-memory parallel community detection method. Vite is a parallelization of the algorithmic template provided by a widely-used serial method (Louvain). Alongside, it uses several heuristics aimed at significantly improving parallelism and performance, while preserving output quality. Using the inputs from the 2018 Graph Challenge (static and streaming), we demonstrate superior performance and high quality solutions based on four parallelization heuristics.

community detection↗

DOE OSTI2020

Lagrangian simulations of spray interaction with a surface using a stochastic multi-regime impingement model

Modeling of spray impingement upon the piston or cylinder surface is important for hydrocarbon emission and soot predictions in high-fidelity simulation of internal combustion engines with direct injections. Due to the complexity of the physical process of spray impingement, current computational models heavily rely on the empirical studies which involve large uncertainties. A computational model is presented for spray impingement on solid walls in general computational fluid dynamics (CFD) simulations. The model adopts the Marmanis-Thoroddsen theory for determining the number of secondary droplets and a stochastic method for calculating the velocities of the secondary droplets. The numerical methods and parallel implementation of the impingement model are presented in detail. The model is implemented in Grit, which is a recently developed CPU/GPU performance-portable Lagrangian particle library, for accelerating spray simulations. The model and its implementation are tested for examples of spray impingements on flat and smooth surfaces with different impingement angles.

Ge, Wenjun↗

DOE OSTI2019

Computational Strategies for Scalable Genomics Analysis

The revolution in next-generation DNA sequencing technologies is leading to explosive data growth in genomics, posing a significant challenge to the computing infrastructure and software algorithms for genomics analysis. Various big data technologies have been explored to scale up/out current bioinformatics solutions to mine the big genomics data. In this review, we survey some of these exciting developments in the applications of parallel distributed computing and special hardware to genomics. We comment on the pros and cons of each strategy in the context of ease of development, robustness, scalability, and efficiency. Although this review is written for an audience from the genomics and bioinformatics fields, it may also be informative for the audience of computer science with interests in genomics applications.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

Towards Superior Software Portability with SHAD and HPX C++ Libraries

As hardware architectures and software stacks complexity grows, development productivity, performance and software portability, quickly evolve from desirable features to actual needs. SHAD, the Scalable High-performance Algorithms and Data-structures C++ library is designed to mitigate these issues: it provides general purpose building blocks as well as high-level custom utilities, and offers a shared-memory programming abstraction which facilitates the programming of complex systems, scaling up to High Performance Computing clusters. SHAD’s portability is achieved through an abstract runtime interface, which decouples the upper layers of the library and hides the low level details of the underlying architecture. This layer enables SHAD to interface with different runtime/threading systems, e.g. Intel TBB and Global Memory and Threading (GMT). However, current backends targeting distributed systems, rely on a centralized controller which may possibly limit scalability up to hundreds of nodes and creates a network hot spot due to all to one communication for synchronization, and possibly resulting in degraded performance at high process counts. In this research, we explore HPX, the C++ standard library for parallelism and concurrency, as an additional backend in support of the SHAD library, and present the methodologies in support of local and remote task executions in SHAD with respect to HPX. Finally, we evaluate the proposed system by comparing against existing backends of SHAD and analyzing their performance on C++ Standard Template Library algorithms.

Wu, Nanmiao↗

DOE OSTI2025

ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem

ChatHPC democratizes large language models for the high-performance computing (HPC) community by providing the infrastructure, ecosystem, and knowledge needed to apply modern generative AI technologies to rapidly create specific capabilities for critical HPC components while using relatively modest computational resources. Our divide-and-conquer approach focuses on creating a collection of reliable, highly specialized, and optimized AI assistants for HPC based on the cost-effective and fast Code Llama fine-tuning processes and expert supervision. We target major components of the HPC software stack, including programming models, runtimes, I/O, tooling, and math libraries. Thanks to AI, ChatHPC provides a more productive HPC ecosystem by boosting important tasks related to portability, parallelization, optimization, scalability, and instrumentation, among others. With relatively small datasets (on the order of KB), the AI assistants, which are created in a few minutes by using one node with two NVIDIA H100 GPUs and the ChatHPC library, can create new capabilities with Meta’s 7-billion parameter Code Llama base model to produce high-quality software with a level of trustworthiness of up to 90% higher than the 1.8-trillion parameter OpenAI ChatGPT-4o model for critical programming tasks in the HPC software stack.

Young, Aaron [ORNL] (ORCID:0000000254484667)↗

DOE OSTI2023

UPC++ v1.0 Programmer’s Guide (Rev. 2023.9.0)

UPC++ is a C++ library that supports Partitioned Global Address Space (PGAS) programming. It is designed for writing efficient, scalable parallel programs on distributed-memory parallel computers. The key communication facilities in UPC++ are one-sided Remote Memory Access (RMA) and Remote Procedure Call (RPC). The UPC++ control model is single program, multiple-data (SPMD), with each separate constituent process having access to local memory as it would in C++. The PGAS memory model additionally provides one-sided RMA communication to a global address space, which is allocated in shared segments that are distributed over the processes. UPC++ also features Remote Procedure Call (RPC) communication, making it easy to move computation to operate on data that resides on remote processes. UPC++ was designed to support exascale high-performance computing, and the library interfaces and implementation are focused on maximizing scalability. In UPC++, all communication operations are syntactically explicit, which encourages programmers to consider the costs associated with communication and data movement. Moreover, all communication operations are asynchronous by default, encouraging programmers to seek opportunities for overlapping communication latencies with other useful work. UPC++ provides expressive and composable abstractions designed for efficiently managing aggressive use of asynchrony in programs. Together, these design principles are intended to enable programmers to write applications using UPC++ that perform well even on hundreds of thousands of cores.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

UPC++ v1.0 Programmer’s Guide (Revision 2022.3.0)

UPC++ is a C++ library that supports Partitioned Global Address Space (PGAS) programming. It is designed for writing efficient, scalable parallel programs on distributed-memory parallel computers. The key communication facilities in UPC++ are one-sided Remote Memory Access (RMA) and Remote Procedure Call (RPC). The UPC++ control model is single program, multiple-data (SPMD), with each separate constituent process having access to local memory as it would in C++. The PGAS memory model additionally provides one-sided RMA communication to a global address space, which is allocated in shared segments that are distributed over the processes. UPC++ also features Remote Procedure Call (RPC) communication, making it easy to move computation to operate on data that resides on remote processes. UPC++ was designed to support exascale high-performance computing, and the library interfaces and implementation are focused on maximizing scalability. In UPC++, all communication operations are syntactically explicit, which encourages programmers to consider the costs associated with communication and data movement. Moreover, all communication operations are asynchronous by default, encouraging programmers to seek opportunities for overlapping communication latencies with other useful work. UPC++ provides expressive and composable abstractions designed for efficiently managing aggressive use of asynchrony in programs. Together, these design principles are intended to enable programmers to write applications using UPC++ that perform well even on hundreds of thousands of cores.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

UPC++ v1.0 Programmer’s Guide, Revision 2023.3.0

UPC++ is a C++ library that supports Partitioned Global Address Space (PGAS) programming. It is designed for writing efficient, scalable parallel programs on distributed-memory parallel computers. The key communication facilities in UPC++ are one-sided Remote Memory Access (RMA) and Remote Procedure Call (RPC). The UPC++ control model is single program, multiple-data (SPMD), with each separate constituent process having access to local memory as it would in C++. The PGAS memory model additionally provides one-sided RMA communication to a global address space, which is allocated in shared segments that are distributed over the processes. UPC++ also features Remote Procedure Call (RPC) communication, making it easy to move computation to operate on data that resides on remote processes. UPC++ was designed to support exascale high-performance computing, and the library interfaces and implementation are focused on maximizing scalability. In UPC++, all communication operations are syntactically explicit, which encourages programmers to consider the costs associated with communication and data movement. Moreover, all communication operations are asynchronous by default, encouraging programmers to seek opportunities for overlapping communication latencies with other useful work. UPC++ provides expressive and composable abstractions designed for efficiently managing aggressive use of asynchrony in programs. Together, these design principles are intended to enable programmers to write applications using UPC++ that perform well even on hundreds of thousands of cores.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

UPC++ v1.0 Programmer’s Guide, Revision 2022.9.0

UPC++ is a C++ library that supports Partitioned Global Address Space (PGAS) programming. It is designed for writing efficient, scalable parallel programs on distributed-memory parallel computers. The key communication facilities in UPC++ are one-sided Remote Memory Access (RMA) and Remote Procedure Call (RPC). The UPC++ control model is single program, multiple-data (SPMD), with each separate constituent process having access to local memory as it would in C++. The PGAS memory model additionally provides one-sided RMA communication to a global address space, which is allocated in shared segments that are distributed over the processes. UPC++ also features Remote Procedure Call (RPC) communication, making it easy to move computation to operate on data that resides on remote processes. UPC++ was designed to support exascale high-performance computing, and the library interfaces and implementation are focused on maximizing scalability. In UPC++, all communication operations are syntactically explicit, which encourages programmers to consider the costs associated with communication and data movement. Moreover, all communication operations are asynchronous by default, encouraging programmers to seek opportunities for overlapping communication latencies with other useful work. UPC++ provides expressive and composable abstractions designed for efficiently managing aggressive use of asynchrony in programs. Together, these design principles are intended to enable programmers to write applications using UPC++ that perform well even on hundreds of thousands of cores.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Moment representation in the lattice Boltzmann method on massively parallel hardware

The widely-used lattice Boltzmann method (LBM) for computational fluid dynamics is highly scalable, but also significantly memory bandwidth-bound on current architectures. This paper presents a new regularized LBM implementation that reduces the memory footprint by only storing macroscopic, moment-based data. We show that the amount of data that must be stored in memory during a simulation is reduced by up to 47%. We also present a technique for cache-aware data re-utilization and show that optimizing cache utilization to limit data motion results in a similar improvement in time to solution. These new algorithms are implemented in the hemodynamics solver HARVEY and demonstrated using both idealized and realistic biological geometries. We develop a performance model for the moment representation algorithm and evaluate the performance on Summit.

Vardhan, Madhurima↗