Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parallel computer architecture”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

SIERRA Multimechanics Module: Aria Thermal Theory Manual (V.4.56)

Aria is a Galerkin finite element based program for solving coupled-physics problems described by systems of PDEs and is capable of solving nonlinear, implicit, transient and direct-to-steady state problems in two and three dimensions on parallel architectures. The suite of physics currently supported by Aria includes thermal energy transport, species transport, and electrostatics as well as generalized scalar, vector and tensor transport equations. Additionally, Aria includes support for manufacturing process flows via the incompressible Navier-Stokes equations specialized to a low Reynolds number ( Re < 1) regime. Enhanced modeling support of manufacturing processing is made possible through use of either arbitrary Lagrangian-Eulerian (ALE) and level set based free and moving boundary tracking in conjunction with quasi-static nonlinear elastic solid mechanics for mesh control. Coupled physics problems are solved in several ways including fully-coupled Newton’s method with analytic or numerical sensitivities, fully-coupled Newton-Krylov methods and a loosely-coupled nonlinear iteration about subsets of the system that are solved using combinations of the aforementioned methods. Error estimation, uniform and dynamic h -adaptivity and dynamic load balancing are some of Aria’s more advanced capabilities.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Distributed memory, GPU accelerated Fock construction for hybrid, Gaussian basis density functional theory

With the growing reliance of modern supercomputers on accelerator-based architecture such a graphics processing units (GPUs), the development and optimization of electronic structure methods to exploit these massively parallel resources has become a recent priority. While significant strides have been made in the development GPU accelerated, distributed memory algorithms for many modern electronic structure methods, the primary focus of GPU development for Gaussian basis atomic orbital methods has been for shared memory systems with only a handful of examples pursing massive parallelism. Here in this work, we present a set of distributed memory algorithms for the evaluation of the Coulomb and exact exchange matrices for hybrid Kohn–Sham DFT with Gaussian basis sets via direct density-fitted (DF-J-Engine) and seminumerical (sn-K) methods, respectively. The absolute performance and strong scalability of the developed methods are demonstrated on systems ranging from a few hundred to over one thousand atoms using up to 128 NVIDIA A100 GPUs on the Perlmutter supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

SIERRA Multimechanics Module: Aria User Manual - Version 5.8

Aria is a Galerkin finite element based program for solving coupled-physics problems described by systems of PDEs and is capable of solving nonlinear, implicit, transient and direct-to-steady state problems in two and three dimensions on parallel architectures. The suite of physics currently supported by Aria includes thermal energy transport, species transport, and electrostatics as well as generalized scalar, vector and tensor transport equations. Additionally, Aria includes support for manufacturing process flows via the incompressible Navier-Stokes equations specialized to a low Reynolds number (Re < 1) regime. Enhanced modeling support of manufacturing processing is made possible through use of either arbitrary Lagrangian-Eulerian (ALE) and level set based free and moving boundary tracking in conjunction with quasi-static nonlinear elastic solid mechanics for mesh control. Coupled physics problems are solved in several ways including fully-coupled Newton’s method with analytic or numerical sensitivities, fully-coupled Newton-Krylov methods and a loosely-coupled nonlinear iteration about subsets of the system that are solved using combinations of the aforementioned methods. Error estimation, uniform and dynamic ℎ-adaptivity and dynamic load balancing are some of Aria’s more advanced capabilities.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

SIERRA Multimechanics Module: Aria Thermal Theory Manual - Version 5.8

Aria is a Galerkin finite element based program for solving coupled-physics problems described by systems of PDEs and is capable of solving nonlinear, implicit, transient and direct-to-steady state problems in two and three dimensions on parallel architectures. The suite of physics currently supported by Aria includes thermal energy transport, species transport, and electrostatics as well as generalized scalar, vector and tensor transport equations. Additionally, Aria includes support for manufacturing process ows via the incompressible Navier-Stokes equations specialized to a low Reynolds number (Re < 1) regime. Enhanced modeling support of manufacturing processing is made possible through use of either arbitrary Lagrangian-Eulerian (ALE) and level set based free and moving boundary tracking in conjunction with quasi-static nonlinear elastic solid mechanics for mesh control. Coupled physics problems are solved in several ways including fully-coupled Newton’s method with analytic or numerical sensitivities, fully-coupled Newton-Krylov methods and a loosely-coupled nonlinear iteration about subsets of the system that are solved using combinations of the aforementioned methods. Error estimation, uniform and dynamic ℎ-adaptivity and dynamic load balancing are some of Aria’s more advanced capabilities.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Scalable molecular dynamics on CPU and GPU architectures with NAMD

NAMD is a molecular dynamics program designed for high-performance simulations of very large biological objects on CPU- and GPU-based architectures. NAMD offers scalable performance on petascale parallel supercomputers consisting of hundreds of thousands of cores, as well as on inexpensive commodity clusters commonly found in academic environments. It is written in C++ and leans on Charm++ parallel objects for optimal performance on low-latency architectures. NAMD is a versatile, multipurpose code that gathers state-of-the-art algorithms to carry out simulations in apt thermodynamic ensembles, using the widely popular CHARMM, AMBER, OPLS, and GROMOS biomolecular force fields. Here, we review the main features of NAMD that allow both equilibrium and enhanced-sampling molecular dynamics simulations with numerical efficiency. We describe the underlying concepts utilized by NAMD and their implementation, most notably for handling long-range electrostatics; controlling the temperature, pressure, and pH; applying external potentials on tailored grids; leveraging massively parallel resources in multiple-copy simulations; and hybrid quantum-mechanical/molecular-mechanical descriptions. We detail the variety of options offered by NAMD for enhanced-sampling simulations aimed at determining free-energy differences of either alchemical or geometrical transformations and outline their applicability to specific problems. Last, we discuss the roadmap for the development of NAMD and our current efforts toward achieving optimal performance on GPU-based architectures, for pushing back the limitations that have prevented biologically realistic billion-atom objects to be fruitfully simulated, and for making large-scale simulations less expensive and easier to set up, run, and analyze. NAMD is distributed free of charge with its source code at www.ks.uiuc.edu.

high-performance computing↗
DOE OSTI2020

Optimizing the hypre solver for manycore and GPU architectures

The solution of large-scale combustion problems with codes such as Uintah on modern computer architectures requires the use of multithreading and GPUs to achieve performance. Uintah uses a low-Mach number approximation that requires iteratively solving a large system of linear equations. The Hypre iterative solver has solved such systems in a scalable way for Uintah, but the use of OpenMP with Hypre leads to at least slowdown due to OpenMP overheads. The proposed solution uses the MPI Endpoints within Hypre, where each team of threads acts as a different MPI rank. This approach minimizes OpenMP synchronization overhead and performs as fast or (up to 1.44) faster than Hypre's MPI-only version, and allows the rest of Uintah to be optimized using OpenMP. The profiling of the GPU version of Hypre shows the bottleneck to be the launch overhead of thousands of micro-kernels. The GPU performance was improved by fusing these micro-kernels and was further optimized by using Cuda-aware MPI, resulting in an overall speedup of 1.16—1.44 compared to the baseline GPU implementation. The above optimization strategies were published in the International Conference on Computational Science 2020 [1]. This work extends the previously published research by carrying out the second phase of communication-centered optimizations in Hypre to improve its scalability on large-scale supercomputers. Additionally, this includes an efficient non-blocking inter-thread communication scheme, communication-reducing patch assignment, and expression of logical communication parallelism to a new version of the MPICH library that utilizes the underlying network parallelism [2]. The above optimizations avoid communication bottlenecks previously observed during strong scaling and improve performance by up to 2 on 256 nodes of Intel Knight's Landing processor.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

How the Size and Density of Charge-Transfer Excitons Depend on Heterojunction’s Architecture

We have characterized the size, intensity, density, and distribution of charge-transfer (CT) excitons as a function of the acceptor–donor architecture of prototypical organic interfaces. This characterization was done by computational analysis of 17 models of varying numbers, positions, and orientations of the donor and acceptor molecules. The models’ building blocks were phenyl-C61-butyric acid methyl ester (PCBM) fullerene acceptors and dual-band donor polymers composed of thiophene, benzothiadiazole, and benzotriazole subunits. The electronic structure of the donor–acceptor complexes was computed with the time-dependent long-range-corrected density-functional tight-binding method and analyzed with the fragment-based one-electron transition density matrix. In all models, the complexes with edge-on orientation have denser spectra of low-energy CT states lying below the absorption bands compared to the complexes with face-on orientation. This CT-state distribution in edge-on complexes provides a gate to efficiently populate cold CT excitons. Moreover, the cold CT excitons have a higher degree of charge separation in the edge-on than in the face-on complexes. The CT amount and the CT exciton size generally increase with the energy of the CT states, although the electron remains localized on a single molecule in cold CT states. Delocalization over two PCBM molecules was observed for high-energy CT states. The exciton size also depends on the orientation. Larger excitons are produced by the delocalization of the electrons perpendicularly to the interface. When the delocalization is parallel, the smaller electron–hole distances yield moderately sized CT excitons.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Demystifying asynchronous I/O Interference in HPC applications

With increasing complexity of HPC workflows, data management services need to perform expensive I/O operations asynchronously in the background, aiming to overlap the I/O with the application runtime. However, this may cause interference due to competition for resources: CPU, memory/network bandwidth. The advent of multi-core architectures has exacerbated this problem, as many I/O operations are issued concurrently, thereby competing not only with the application but also among themselves. Furthermore, the interference patterns can dynamically change as a response to variations in application behavior and I/O subsystems (e.g. multiple users sharing a parallel file system). Without a thorough understanding, I/O operations may perform suboptimally, potentially even worse than in the blocking case. To fill this gap, here we investigate the causes and consequences of interference due to asynchronous I/O on HPC systems. Specifically, we focus on multi-core CPUs and memory bandwidth, isolating the interference due to each resource. Then, we perform an in-depth study to explain the interplay and contention in a variety of resource sharing scenarios such as varying priority and number of background I/O threads and different I/O strategies: sendfile, read/write, mmap/write underlining trade-offs. The insights from this study are important both to enable guided optimizations of existing background I/O, as well as to open new opportunities to design advanced asynchronous I/O strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Scaling comb-driven resonator-based DWDM silicon photonic links to multi-Tb/s in the multi-FSR regime

The use of chip-based micro-resonator Kerr frequency combs in conjunction with dense wavelength-division multiplexing (DWDM) enables massively parallel intensity-modulated direct-detection data transmission with low energy consumption. Resonator-based modulators and filters used in such systems can limit the number of usable wavelength channels due to practical constraints on the maximum achievable free spectral range (FSR). In this work, we introduce the design of multi-Tb/s comb-driven resonator-based silicon photonic links by leveraging the multi-FSR regime. We demonstrate the viability of the link architecture with yield estimates that are supported by extensive wafer-scale measurements of 704 micro-resonators fabricated in a commercial complementary metal–oxide–semiconductor foundry. We show that a 2.80 Tb/s link is realizable with a ≥6 σ yield (∼99.999%), and that aggregate bandwidths of 3.76 Tb/s and 4.72 Tb/s are possible if yield targets are relaxed (3 σ and 1 σ , respectively). All designs represent a 1.94−3.28× boost to aggregate link bandwidth while maintaining BER≤10 −10 performance, with a theoretical bandwidth of 10.51 Tb/s being possible for sufficiently robust resonators. We use high-speed BER measurements to inform co-optimization of data rate and aggressor spacing ( λ ag ), limiting any additional loss-based power penalties to off-resonance insertion loss (IL) and routing loss. This work demonstrates that, through the multi-FSR regime, there is a clear path toward Kerr comb-driven ultra-broadband, high bandwidth silicon photonic links that can support next-generation data centers and high-performance computers.

James, Aneek (ORCID:0000000262527807)↗
DOE OSTI2022

COMPOFF: A Compiler Cost model using Machine Learning to predict the Cost of OpenMP Offloading

The HPC industry is inexorably moving towards an era of extremely heterogeneous architectures, with more devices configured on any given HPC platform and potentially more kinds of devices, some of them highly specialized. Writing a separate code suitable for each target system for a given HPC application is not practical. The better solution is to use directive-based parallel programming models such as OpenMP. OpenMP provides a number of options for offloading a piece of code to devices like GPUs. To select the best option from such options during compilation, most modern compilers use analytical models to estimate the cost of executing the original code and the different offloading code variants. Building such an analytical model for compilers is a difficult task that necessitates a lot of effort on the part of a compiler engineer. Recently, machine learning techniques have been successfully applied to build cost models for a variety of compiler optimization problems. In this paper, we present COMPOFF, a cost model which uses the multi-layer perceptrons to statically estimates the Cost of OpenMP OFFloading. We used six different transformations on a parallel code of Wilson Dslash Operator to support GPU offloading, and we predicted their cost of execution on different GPUs using COMPOFF during compile time. Our results show that this model can predict offloading costs with a root mean squared error in prediction of less than 0.5 seconds. Our preliminary findings indicate that this work will make it much easier and faster for scientists and compiler developers to port legacy HPC applications that use OpenMP to new heterogeneous computing environment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Cybersecurity for Grid Connected eXtreme Fast Charging (XFC) Station (CyberX) (Final Scientific/Technical Report)

This report summarizes the activities conducted under the DOE VTO funded project DE- EE0008451, where ABB Inc. (ABB), in collaboration with Idaho National Laboratory (INL), APS Global (APS), and XOS Trucks (XOS) pursued the development of a cyber-resilient extreme fast charging (XFC) management system. This project entitled Cybersecurity for Grid Connected eXtreme Fast Charging (XFC) Station (CyberX) focuses on a resilient architecture for smart charging EV Supply Equipment (EVSE) device control and Coordinated Anomaly Detection System (CADS) features that can be added at the charging site depot level to increase cybersecurity. The project was split into two budget periods focused first on developing the threat model and resilient control concepts and second on testing, improving, and validating those developed resilient control algorithms and features with a focus on key vulnerabilities identified during the threat assessment portion of the project. During the first budget period of the CyberX project, the ABB led team focused on activities to identify, model, and quantitatively prioritize high-impact attack scenarios with potential cyber-physical effects while also modeling and developing concepts for a resilient control system that could securely address integration of DERs and other resources with EV charging. Development of the security focused XFC management system (XMS) was accomplished first by offline simulation using a developed XFC station or depot with 480V input level and simulating measurement inputs to monitoring and control systems in concept development. A representative distribution grid model was developed supporting an EV charging site model with BESS and 6 general EV charging models. These EV charging models allowed multiple configurations of charging level, multiple connected protection and measurement devices, and simulation function to show general compromise of EV, BESS, and protection features based on parallel threat analysis. During the second budget period, the EV site and supporting systems model was developed in more detail and converted from offline model to real-time to real-time with EV charging hardware in the loop (HIL). The resilient control architecture developed as concept in the first part of the project was further tested and validated for integration of local energy resources and XFC charging station site equipment while maintaining cybersecure operating principles. The proposed resilient architecture for smart charging and cybersecurity features consists of two main concepts developed and tested within the project. The first concept is an XFC management system (XMS) consisting of a hardware gateway, software platform, and Supervisory Control and Data Acquisition (SCADA) or Distribution Management System integration components. The second concept is a Coordinated Anomaly Detection System (CADS) which forms a primarily software-related subsystem of the total CyberX solution focused on monitoring system measurements, estimation of measurement states, and predicting current at the utility point of interaction based on machine learning for anomaly detection.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

High-Fidelity Modeling of a Type-5 Wind Turbine Gearbox (Intern Poster) [Poster]

Type-5 wind turbines are unique in their use of a permanent magnet synchronous generator, as well as their use of a hydraulic torque converter. This architecture presents an opportunity to provide steady and grid-ready energy without the need for a power converter. With infrastructure continuity and reliability being an important topic amongst renewable energies, researchers have been prompted to further investigate the benefits of type-5 turbines’ unique electromechanical configuration on stable electricity generation. Researchers involved in the WindSG project, SG standing for synchronous generator, are aiming to model a type-5 turbine using Real Time Digital Simulation (RTDS) to evaluate its efficacy in the grid. RSCAD, the software run on the RTDS, comes pre-loaded with electrical and electromechanical components to help simulate electrical generation and grid conditions. However, within this repertoire there is a lack of a component to represent a gearbox with high-fidelity. Within RSCAD’s case studies, the gearbox is often represented simply by a gear ratio value. This presented the task of developing a high-fidelity gearbox model in RSCAD for use in the larger RTDS type-5 wind turbine model. This poster describes a method of developing a lumped parameter mathematical model to represent a planetary-parallel-parallel gearbox in RSCAD for use in RTDS.

17 WIND ENERGY↗
DOE OSTI2024

High-Fidelity Modeling of a Type-5 Wind Turbine Gearbox (Intern Technical Presentation) (Poster)

Type-5 wind turbines are unique in their use of a permanent magnet synchronous generator, as well as their use of a hydraulic torque converter. This architecture presents an opportunity to provide steady and grid-ready energy without the need for a power converter. With infrastructure continuity and reliability being an important topic amongst renewable energies, researchers have been prompted to further investigate the benefits of type-5 turbines’ unique electromechanical configuration on stable electricity generation. Researchers involved in the WindSG project, SG standing for synchronous generator, are aiming to model a type-5 turbine using Real Time Digital Simulation (RTDS) to evaluate its efficacy in the grid. RSCAD, the software run on the RTDS, comes pre-loaded with electrical and electromechanical components to help simulate electrical generation and grid conditions. However, within this repertoire there is a lack of a component to represent a gearbox with high-fidelity. Within RSCAD’s case studies, the gearbox is often represented simply by a gear ratio value. This presented the task of developing a high-fidelity gearbox model in RSCAD for use in the larger RTDS type-5 wind turbine model. This presentation describes a method of developing a lumped parameter mathematical model to represent a planetary-parallel-parallel gearbox in RSCAD for use in RTDS.

17 WIND ENERGY↗
DOE OSTI2020

PLEXUS: A Pattern-Oriented Runtime System Architecture for Resilient Extreme-Scale High-Performance Computing Systems

For high-performance computing (HPC) system designers and users, meeting the myriad challenges of next-generation exascale supercomputing systems requires rethinking their approach to application and system software design. Among these challenges, providing resiliency and stability to the scientific applications in the presence of high fault rates requires new approaches to software architecture and design. As HPC systems become increasingly complex, they require intricate solutions for detection and mitigation for various modes of faults and errors that occur in these large-scale systems, as well as solutions for failure recovery. These resiliency solutions often interact with and affect other system properties, including application scalability, power and energy efficiency. Therefore, resilience solutions for HPC systems must be thoughtfully engineered and deployed.In previous work, we developed the concept of resilience design patterns, which consist of templated solutions based on well-established techniques for detection, mitigation and recovery. In this paper, we use these patterns as the foundation to propose new approaches to designing runtime systems for HPC systems. The instantiation of these patterns within a runtime system enables flexible and adaptable end-to-end resiliency solutions for HPC environments. The paper describes the architecture of the runtime system, named Plexus, and the strategies for dynamically composing and adapting pattern instances under runtime control. This runtime-based approach enables actively balancing the cost-benefit trade-off between performance overhead and protection coverage of the resilience solutions. Based on a prototype implementation of PLEXUS, we demonstrate the resiliency and performance gains achieved by the pattern-based runtime system for a parallel linear solver application.

Hukerikar, Saurabh↗
DOE OSTI2025

Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multitask learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art US Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2000 GPUs on Perlmutter and 16,000 GPUs on Frontier.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A Performance Portable, Fully Implicit Landau Collision Operator with Batched Linear Solvers

Modern accelerators use hierarchical parallel programming models that enable massive multithreading within a processing element (PE), with multiple PEs per device driven by traditional processes. Batching is a technique for exposing PE-level parallelism in algorithms that have traditionally run on MPI processes or multiple threads within a single process. Opportunities for batching arise in, for example, kinetic discretizations of magnetized plasmas where collisions are advanced in velocity space at each spatial point independently. This paper builds on previous work on a high-performance, fully nonlinear, Landau collision operator by batching the linear solver, as well as batching the spatial point problems and adding new support for multiple grids for multiscale, multispecies problems. An anisotropic relaxation verification test that agrees well with previously published results and analytical models is presented. The performance results from NVIDIA A100 and AMD MI250X nodes are presented with hardware utilization analysis for each architecture. Finally, the entire implicit Landau operator time advance is implemented in Kokkos for performance portability, running entirely on the device and is available in the PETSc numerical library.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Two-Stage Gauss-Seidel Preconditioners and Smoothers for Krylov Solvers on a GPU Cluster: Preprint

Gauss-Seidel (GS) relaxation is often employed as a preconditioner for a Krylov solver or as a smoother for Algebraic Multigrid (AMG). However, the requisite sparse triangular solve is difficult to parallelize on many-core architectures such as graphics processing units (GPUs). In the present study, the performance of the sequential GS relaxation based on a triangular solve is compared with two-stage variants, replacing the direct triangular solve with a fixed number of inner Jacobi-Richardson (JR) iterations. When a small number of inner iterations is sufficient to maintain the Krylov convergence rate, the two-stage GS (GS2) often outperforms the sequential algorithm on many-core architectures. The GS2 algorithm is also compared with JR. When they perform the same number of ops for SpMV (e.g. three JR sweeps compared to two GS sweeps with one inner JR sweep), the GS2 iterations, and the Krylov solver preconditioned with GS2, may converge faster than the JR iterations. Moreover, for some problems (e.g. elasticity), it was found that JR may diverge with a damping factor of one, whereas two-stage GS may improve the convergence with more inner iterations. Finally, to study the performance of the two-stage smoother and preconditioner for a practical problem, these were applied to incompressible uid ow simulations on GPUs.

algebraic multigrid↗