Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “GPU acceleration”

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 415 records · Page 23

Performance of a geometric deep learning pipeline for HL-LHC particle tracking

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX’s tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Gyrokinetic toroidal simulations on leading multi- and manycore HPC systems

The gyrokinetic Particle-in-Cell (PIC) method is a critical computational tool enabling petascale fusion simulation re-search. In this work, we present novel multi- and manycore-centric optimizations to enhance performance of GTC, a PIC-based production code for studying plasma microtur-bulence in tokamak devices. Our optimizations encompass all six GTC sub-routines and include multi-level particle and grid decompositions designed to improve multi-node parallel scaling, particle binning for improved load balance, GPU acceleration of key subroutines, and memory-centric optimizations to improve single-node scaling and reduce memory utilization. The new hybrid MPI-OpenMP and MPI-OpenMP-CUDA GTC versions achieve up to a 2× speedup over the production Fortran code on four parallel systems - clusters based on the AMD Magny-Cours, Intel Nehalem-EP, IBM BlueGene/P, and NVIDIA Fermi architectures. Finally, strong scaling experiments provide insight into parallel scalability, memory utilization, and programmability trade-offs for large-scale gyrokinetic PIC simulations, while attaining a 1.6× speedup on 49,152 XE6 cores.

97 MATHEMATICS AND COMPUTING↗

Delayed Update Algorithms for Quantum Monte Carlo Simulation on GPU: Extended Abstract

QMCPACK is open source scientific software designed to perform Quantum Monte Carlo (QMC) simulation, a first-principles method for describing many-body systems. The evaluation of each Monte Carlo move requires finding the determinant of a dense matrix in the wave functions. This calculation forms a key computational kernel in QMCPACK. After each accepted event, the wave function matrix undergoes a rank-one update to represent a single particle move within the system. The matrix inverse is updated via the Sherman-Morrison formula; occasionally, the explicit inverse must be recomputed to maintain numerical stability.; We propose an alternate approach to this kernel that utilizes QR factorization to maintain stability without refactorization. In addition, algorithms based on a novel delayed update scheme are explored in this effort. This strategy enables probability evaluation for multiple successive Monte Carlo moves, with application of accepted moves to the wave function matrix delayed until an event is denied, or a predetermined limit on acceptances p is reached. Accepted events grouped in this manner are then applied to the matrix en bloc with enhanced arithmetic intensity and computational efficiency. Delayed update Sherman-Morrison probability evaluation algorithms with CPU and GPU-accelerated implementations are tested, profiled, and analyzed. A QR based delayed update algorithm remains in development. Results are evaluated against existing methods for numerical stability and efficiency; emphasis is placed on large systems, for which acceleration is critical.

Computer Science↗

Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs

NVIDIA has been the main provider of GPU hardware in HPC systems for over a decade. Most applications that benefit from GPUs have thus been developed and optimized for the NVIDIA software stack. Recent exascale HPC systems are, however, introducing GPUs from other vendors, e.g. with the AMD GPU-based OLCF Frontier system just becoming available. AMD GPUs cannot be directly accessed using the NVIDIA software stack, and require a porting effort by the application developers. This paper provides an overview of our experience porting and optimizing the CGYRO code, a widely-used fusion simulation tool based on FORTRAN with OpenACC-based GPU acceleration. While the porting from the NVIDIA compilers was relatively straightforward using the CRAY compilers on the AMD systems, the performance optimization required more fine-tuning. In the optimization effort, we uncovered code sections that had performed well on NVIDIA GPUs, but were unexpectedly slow on AMD GPUs. After AMD-targeted code optimizations, performance on AMD GPUs has increased to meet our expectations. Modest speed improvements were also seen on NVIDIA GPUs, which was an unexpected benefit of this exercise.

Sfiligoi, Igor↗

Revisiting Temporal Blocking Stencil Optimizations

Iterative stencils are used widely across the spectrum of High Performance Computing (HPC) applications. Many efforts have been put into optimizing stencil GPU kernels, given the prevalence of GPU-accelerated supercomputers. To improve the data locality, temporal blocking is an optimization that combines a batch of time steps to process them together. Under the observation that GPUs are evolving to resemble CPUs in some aspects, we revisit temporal blocking optimizations for GPUs. We explore how temporal blocking schemes can be adapted to the new features in the recent Nvidia GPUs, including large scratchpad memory, hardware prefetching, and device-wide synchronization. We propose a novel temporal blocking method, EBISU, which champions low device occupancy to drive aggressive deep temporal blocking on large tiles that are executed tile-by-tile. We compare EBISU with state-of-the-art temporal blocking libraries: STENCILGEN and AN5D. We also compare with state-of-the-art stencil auto-tuning tools that are equipped with temporal blocking optimizations: ARTEMIS and DRSTENCIL. Over a wide range of stencil benchmarks, EBISU achieves speedups up to 2.53x and a geometric mean speedup of 1.49x over the best state-of-the-art performance in each stencil benchmark.

Zhang, Lingqi↗

SuperNeuro: A Fast and Scalable Simulator for Neuromorphic Computing

In many neuromorphic workflows, simulators play a vital role for important tasks such as training spiking neural networks, running neuroscience simulations, and designing, implementing, and testing neuromorphic algorithms. Currently available simulators cater to either neuroscience workflows (e.g., NEST and Brian2) or deep learning workflows (e.g., BindsNET). Problematically, the neuroscience-based simulators are slow and not very scalable, and the deep learning-based simulators do not support certain functionalities that are typical of neuromorphic workloads (e.g., synaptic delay). In this paper, we address this gap in the literature and present SuperNeuro, which is a fast and scalable simulator for neuromorphic computing capable of both homogeneous and heterogeneous simulations as well as GPU acceleration. We also present preliminary results that compare SuperNeuro to widely used neuromorphic simulators such as NEST, Brian2, and BindsNET in terms of computation times. We demonstrate that SuperNeuro can be approximately 10×--300× faster than some of the other simulators for small sparse networks. On large sparse and large dense networks, SuperNeuro can be approximately 2.2×--3.4× faster than the other simulators, respectively.

Date, Prasanna↗

Optimizing Communication in 2D Grid-Based MPI Applications at Exascale

The new reality of exascale computing faces many challenges in achieving optimal performance on large numbers of nodes. A key challenge is the efficient utilization of the message-passing interface (MPI), a critical component for process communication. This paper explores communication optimization strategies to harness the GPU-accelerated architectures of these supercomputers. We focus on MPI applications where processors form a two-dimensional process grid, a common arrangement in applications involving dense matrix operations. This configuration offers a unique opportunity to implement innovative strategies to improve performance and maintain effective load distribution. We study two applications— Dist-FW (Apsp:all-pair-shortest-path) and HPL-MxP (LU factorization with Mixed precision)—on two accelerated systems: Summit (IBM Power and NVIDIA V100) and Frontier (AMD EPYC and MI250X). These supercomputers are operated by the Oak Ridge Leadership Computing Facility (OLCF) and are currently ranked #1 and #5 on the Top500 list. We show how to scale up both applications to exascale levels and tackle the MPI challenges related to implementation, synchronization, and performance. We also compare the performance of several communication strategies at an unprecedented scale. Accurately predicting application performance becomes crucial for cost reduction as the computational scale grows. To address this, we suggest a hyperbolic model as a better alternative to the traditional one-sided asymptotic model for predicting future application performance at such large scales.

Lu, Hao↗

Dax v. 1.0

The Dax Toolkit enables the fine-grained concurrency for data analysis and visualization required to drive multi-core processors, many-core GPU accelerators, and emerging architectures for exascale computing. Dax simplifies the design of finely threaded algorithms by characterizing them in per element operations, which we call worklets. Worklets simplify design because they can behave as serial processes without the complications of memory clashes or other race conditions. Yet worklets can be scheduled on a practically unlimited number of threads, thereby making effective utilization of many processing cores. Operations coordinated across elements are encapsulated in a few versatile communicative operations that are adapted to the specifics of computing devices.

SciDAC↗

HPSim, Version 1.0

HPSim is a GPU-accelerated online multi-particle beam dynamics simulation tool for ion linacs. It was originally developed for use on the Los Alamos 800-MeV proton linac. It is a “z-code” that contains typical linac beam transport elements. The linac RF-gap transformation utilizes transit-time-factors to calculate the beam acceleration therein. The space-charge effects are computed using the 2D SCHEFF (Space CHarge EFFect) algorithm, which calculates the radial and longitudinal space charge forces for cylindrically symmetric beam distributions. Other space- charge routines to be incorporated include the 3D PICNIC and a 3D Poisson solver. HPSim can simulate beam dynamics in drift tube linacs (DTLs) and coupled cavity linacs (CCLs). Elliptical superconducting cavity (SC) structures will also be incorporated into the code. The computational core of the code is written in C++ and accelerated using the NVIDIA CUDA technology. Users access the core code, which is wrapped in Python/C APIs, via Pythons scripts that enable ease-of-use and automation of the simulations. The overall linac description including the EPICS PV machine control parameters is kept in an SQLite database that also contains calibration and conversion factors required to transform the machine set points into model values used in the simulation.

Pang, Xiaoying↗

Dimensionality Reduction Library v 0.2

Dimensionality Reduction Library is a C++ library for dimensionality reduction. In the context of this library, dimensionality reduction is considered to consist of 1)estimation of the intrinsic dimensionality using sampled data, 2) Finding maps that reduce the dimensionality of data (forward map) or increase the dimensionality of data (reverse map) and 3) mapping arbitray coordinates to high and low dimensionalities. The library is intended to provide a consistent interface to multiple dimensionality reduction algorithms with an efficient C++ interface that runs efficiently on multicore architectures. A few routines have been optimized with an option for GPU acceleration or distributed computation. Currently the library offers intrinsic dimensionality estimation using point-PCA reconstruction error and/ residual variance. The following dimensionality reduction methods have been implemented: Principal Component Analysis Multidimensional Scaling Locally Linear Embedding IsoMap Autoencoder Neutral Networks An executable is also supplied that can be built to allow for command-line access to the library routines. A description for an application of the library for molecular structure analysis has been published.

BROWN, WILLIAM↗

GraphDot v0.1

GraphDot is a scikit-learn compatible library that implements GPU-accelerated graph kernels for similarity comparison between graphs.

Tang, Yu-Hang↗

DiHydrogen

DiHydrogen is the second version of the Hydrogen fork of the well-known distributed linear algebra library, Elemental. DiHydrogen is a GPU-accelerated distributed multilinear algebra interface with a particular emphasis on the needs of the scalable distributed deep learning training and inference. DiHydrogen is part of the Livermore Big Artificial Neural Network (LBANN) software stack.

Maruyama, Naoya↗

CoMet

CoMet is an application for finding epistatic and pleiotropic relationships from large quantities of genomic data. It solves these large combinatorial problems on GPU-accelerated systems with thousands of compute nodes. Its methods include the 2-way Proportional Similarity method, the Custom Correlation Coefficient and the DUO method. CoMet was developed at the Oak Ridge Leadership Computing Facility in collaboration with the Computational Biology and Bioinformatics Group at Oak Ridge National Laboratory.

Joubert, WayneD↗

Empirical Roofline Tool (ERT) v1.1.0

The Empirical Roofline Tool (ERT) empirically determines the machine characteristics (CPU or GPU-accelerated) that are needed to generate the machine characteristics for the roofline model.

Van Straalen, Brian↗

MEUMAPPS (C++ Version)

Many materials, metal alloys in particular, have features on the on micrometer or nanometer scale that have a large impact on the properties of the material. These features are known as the microstructure of the material. Understanding why and how the microstructure forms in a material is of fundamental scientific interest as well as of significant technological interest. The capability to predict microstructure evolution in a material allows the intentional design of microstructures and hence the intentional design of material properties. The phase-field method is one of the leading methods for predicting microstructure evolution. One of the most significant problems for phase-field models is their computational expense. Even limited phase-field simulations can easily require thousands of CPU core-hours to complete, which significantly limits their use. This code provides both a general framework for creating scalable, GPU-accelerated phase-field model applications as well as several applications themselves. The code is capable of using hundreds of GPUs efficiently, which greatly reduces the time required to perform simulations. The code is written with an emphasis on performance portability, that is the ability for the code to run efficiently on a number of different computing architectures without modification of the source code. The performance portability of this code is primarily enabled through the use of two libraries, Kokkos (performance portable data structures and execution patterns) and heFFTe (performance portable distributed 3D fast Fourier transforms). The code consists of a core library, applications, and tests. The core library includes shared functionality between applications. This includes interfaces with fast Fourier transform (FFT) libraries such as heFFTe, data structures based on Kokkos, file input and output capabilities, and a solver for infinitesimal strain mechanical equilibrium problems. Five applications are included in the code. The flagship application is the MEUMAPPS-SS application, which implements the Kim-Kim-Suzuki phase-field model for precipitation for an arbitrary number of phases and components in a metal alloy. Five simpler applications are also included that solve the Eshelby inclusion problem, Allen-Cahn equation, the coupled Allen-Cahn and diffusion equations, and the Cahn-Hilliard equation. The code includes two applications to solve the Cahn-Hilliard equation, one with constant-step-size first-order time integration and the second with adaptive high-order time integration.

DeWitt, Stephen [Oak Ridge National Lab. (ORNL), O↗

PeleLMeX [SWR-22-48]

PeleLMeX is a solver for high fidelity reactive flow simulations, namely direct numerical simulation (DNS) and large eddy simulation (LES). The solver combines a low Mach number approach, adaptive mesh refinement (AMR), embedded boundary (EB) geometry treatment and high performance computing (HPC) to provide a flexible tool to address research questions on platforms ranging from small workstations to the world's largest GPU-accelerated supercomputers. PeleLMeX has been used to study complex flame/turbulence interactions in RCCI engines and hydrogen combustion or the effect of sustainable aviation fuel on gas turbine combustion. PeleLMeX is part of the Pele combustion Suite (https://amrex-combustion.github.io/)

Day, Marcus↗

Swift

Swift is a fast Fourier transform based spectral solver based on the MOOSE framework. It supports GPU accelerated semi-implicit solves of partial differential equations, such as those used for phase field mesoscale microstructure evolution.

Schwen, Daniel [Idaho National Laboratory (INL), I↗

OpenFerro v0.1.0

OpenFerro is a Python package for on-lattice atomistic dynamics simulation of ferroic materials. OpenFerro is based on JAX, a high-performance linear algebra package supporting auto-differentiation and GPU acceleration. OpenFerro is designed to minimize the effort required to build on-lattice Hamiltonian models, and to perform molecular dynamics (MD) and Landau-Lifshitz-Gilbert simulations. Unlike existing codes, OpenFerro provides a unified interface to model different types of local order parameters.

Xie, Pinchen [Lawrence Berkeley National Laborator↗