scholarly journals Achieving Efficient Strong Scaling with PETSc Using Hybrid MPI/OpenMP Optimisation

2013 ◽  
pp. 97-108 ◽  
Author(s):  
Michael Lange ◽  
Gerard Gorman ◽  
Michèle Weiland ◽  
Lawrence Mitchell ◽  
James Southern
Keyword(s):  
Strong Scaling

Lattice QCD on GPU clusters, using the QUDA library and the Chroma software system

2012 ◽  
Vol 26 (4) ◽  
pp. 386-398 ◽  
Author(s):  
Bálint Joó ◽  
Mike A. Clark
Keyword(s):  
Quantum Chromodynamics ◽  
Graphics Processing Units ◽  
Lawrence Livermore National Laboratory ◽  
National Laboratory ◽  
Application Framework ◽  
Software System ◽  
Nuclear Forces ◽  
Lattice Quantum Chromodynamics ◽  
Lattice Quantum ◽  
Strong Scaling

The QUDA library for optimized lattice quantum chromodynamics using GPUs, combined with a high-level application framework such as the Chroma software system, provides a powerful tool for computing quark propagators, a key step in current calculations of hadron spectroscopy, nuclear structure, and nuclear forces. In this contribution we discuss our experiences, including performance and strong scaling of the QUDA library and Chroma on the Edge Cluster at Lawrence Livermore National Laboratory and on various clusters at Jefferson Lab. We highlight some scientific successes and consider future directions for graphics processing units in lattice quantum chromodynamics calculations.

scholarly journals On Strong Scaling Open Source Tools for Mining Atom Probe Tomography Data

2019 ◽  
Vol 25 (S2) ◽  
pp. 298-299 ◽  
Author(s):  
Markus Kühbach ◽  
Priyanshu Bajaj ◽  
Andrew Breen ◽  
Eric A. Jägle ◽  
Baptiste Gault
Keyword(s):  
Open Source ◽  
Atom Probe Tomography ◽  
Atom Probe ◽  
Strong Scaling ◽  
Tomography Data

scholarly journals Strong Scaling of OpenACC enabled Nek5000 on several GPU based HPC systems

2022 ◽  
Author(s):  
Jonathan Vincent ◽  
Jing Gong ◽  
Martin Karp ◽  
Adam Peplinski ◽  
Niclas Jansson ◽  
...  
Keyword(s):  
Strong Scaling

scholarly journals Blue Matter: Strong Scaling of Molecular Dynamics on Blue Gene/L

2006 ◽  
pp. 846-854 ◽  
Author(s):  
Blake G. Fitch ◽  
Aleksandr Rayshubskiy ◽  
Maria Eleftheriou ◽  
T. J. Christopher Ward ◽  
Mark Giampapa ◽  
...  
Keyword(s):  
Molecular Dynamics ◽  
Strong Scaling ◽  
Blue Gene

Spin Glass Simulations on the Janus Architecture: A Desperate Quest for Strong Scaling

2013 ◽  
pp. 528-537 ◽  
Author(s):  
M. Baity-Jesi ◽  
R. A. Baños ◽  
A. Cruz ◽  
L. A. Fernandez ◽  
J. M. Gil-Narvion ◽  
...  
Keyword(s):  
Spin Glass ◽  
Strong Scaling

scholarly journals High resolution parameter study of the vertical shear instability

2020 ◽  
Vol 499 (2) ◽  
pp. 1841-1853
Author(s):  
Natascha Manger ◽  
Hubert Klahr ◽  
Wilhelm Kley ◽  
Mario Flock
Keyword(s):  
Aspect Ratio ◽  
Large Scale ◽  
Dead Zone ◽  
Pressure Ratio ◽  
Theoretical Models ◽  
Shear Instability ◽  
Vertical Shear ◽  
Parameter Study ◽  
Aspect Ratios ◽  
Strong Scaling

ABSTRACT Theoretical models of protoplanetary discs have shown the vertical shear instability (VSI) to be a prime candidate to explain turbulence in the dead zone of the disc. However, simulations of the VSI have yet to show consistent levels of key disc turbulence parameters like the stress-to-pressure ratio α. We aim to reconcile these different values by performing a parameter study on the VSI with focus on the disc density gradient p and aspect ratio h = H/R. We use full 2π 3D simulations of the disc for chosen set of both parameters. All simulations are evolved for 1000 reference orbits, at a resolution of 18 cells per h. We find that the saturated stress-to-pressure ratio in our simulations is dependent on the disc aspect ratio with a strong scaling of α∝h2.6, in contrast to the traditional α model, where viscosity scales as ν∝αh2 with a constant α. We also observe consistent formation of large scale vortices across all investigated parameters. The vortices show uniformly aspect ratios of χ ≈ 10 and radial widths of approximately 1.5H. With our findings we can reconcile the different values reported for the stress-to-pressure ratio from both isothermal and full radiation hydrodynamics models, and show long-term evolution effects of the VSI that could aide in the formation of planetesimals.

scholarly journals Unified memory in HOOMD-blue improves node-level strong scaling

2020 ◽  
Vol 173 ◽  
pp. 109359 ◽  
Author(s):  
Jens Glaser ◽  
Peter S. Schwendeman ◽  
Joshua A. Anderson ◽  
Sharon C. Glotzer
Keyword(s):  
Node Level ◽  
Strong Scaling

scholarly journals Reducing communication in algebraic multigrid with multi-step node aware communication

2020 ◽  
Vol 34 (5) ◽  
pp. 547-561
Author(s):  
Amanda Bienz ◽  
William D Gropp ◽  
Luke N Olson
Keyword(s):  
Message Passing ◽  
Message Passing Interface ◽  
Parallel Implementation ◽  
Algebraic Multigrid ◽  
Sparse Linear Systems ◽  
Parallel Scalability ◽  
Strong Scaling ◽  
The Cost ◽  
Communication Schedule ◽  
Inter Process Communication

Algebraic multigrid (AMG) is often viewed as a scalable [Formula: see text] solver for sparse linear systems. Yet, AMG lacks parallel scalability due to increasingly large costs associated with communication, both in the initial construction of a multigrid hierarchy and in the iterative solve phase. This work introduces a parallel implementation of AMG that reduces the cost of communication, yielding improved parallel scalability. It is common in Message Passing Interface (MPI), particularly in the MPI-everywhere approach, to arrange inter-process communication, so that communication is transported regardless of the location of the send and receive processes. Performance tests show notable differences in the cost of intra- and internode communication, motivating a restructuring of communication. In this case, the communication schedule takes advantage of the less costly intra-node communication, reducing both the number and the size of internode messages. Node-centric communication extends to the range of components in both the setup and solve phase of AMG, yielding an increase in the weak and strong scaling of the entire method.

scholarly journals 3-D radiative transfer in large-eddy simulations – experiences coupling the TenStream solver to the UCLA-LES

2016 ◽  
Vol 9 (4) ◽  
pp. 1413-1422 ◽  
Author(s):  
Fabian Jakub ◽  
Bernhard Mayer
Keyword(s):  
Monte Carlo ◽  
Los Angeles ◽  
Radiative Transfer ◽  
Algebraic Multigrid ◽  
Eddy Simulation ◽  
Spectral Integration ◽  
Large Eddy ◽  
Cloud Resolving Model ◽  
Strong Scaling ◽  
The University

Abstract. The recently developed 3-D TenStream radiative transfer solver was integrated into the University of California, Los Angeles large-eddy simulation (UCLA-LES) cloud-resolving model. This work documents the overall performance of the TenStream solver as well as the technical challenges of migrating from 1-D schemes to 3-D schemes. In particular the employed Monte Carlo spectral integration needed to be reexamined in conjunction with 3-D radiative transfer. Despite the fact that the spectral sampling has to be performed uniformly over the whole domain, we find that the Monte Carlo spectral integration remains valid. To understand the performance characteristics of the coupled TenStream solver, we conducted weak as well as strong-scaling experiments. In this context, we investigate two matrix preconditioner: geometric algebraic multigrid preconditioning (GAMG) and block Jacobi incomplete LU (ILU) factorization and find that algebraic multigrid preconditioning performs well for complex scenes and highly parallelized simulations. The TenStream solver is tested for up to 4096 cores and shows a parallel scaling efficiency of 80–90 % on various supercomputers. Compared to the widely employed 1-D delta-Eddington two-stream solver, the computational costs for the radiative transfer solver alone increases by a factor of 5–10.

Sign in / Sign up

Export Citation Format

Share Document