GPUBLQMR: GPU-Accelerated Sparse Block Quasi-Minimum Residual Linear Solver

R Lacouture - 2021 - search.proquest.com
… using the block Lanczos algorithm [2] to solve multiple solutions … this method accelerates the
convergence behavior based on … In this thesis work, the parallel implementation of the block

Parallel shift-invert spectrum slicing on distributed architectures with GPU accelerators

DB Williams-Young, C Yang - … 49th International Conference on Parallel …, 2020 - dl.acm.org
… or sparse linear equation solvers for GPU architectures to carry … indicate that GPU acceleration
of sparse symmetric solvers would … A shifted block Lanczos algorithm for solving sparse …

A Study on Optimization of Sparse and Dense Linear System Solver Over GF (2) on GPUs

P Verma, K Sharma - Innovations in Computer Science and Engineering …, 2021 - Springer
Nvidia introduces series of accelerating cards for researchers to make their application
parallel and solve … system and Block Lanczos for sparse systems leverages parallel hardware …

Parallel interior-point solver for block-structured nonlinear programs on SIMD/GPU architectures

F Pacaud, M Schanen, S Shin… - Optimization Methods …, 2024 - Taylor & Francis
… Our method accelerates both operations using two levels of … Second, each process uses
SIMD/GPU accelerators locally to … Each node is equipped with four GPUs, a setup amenable to …

Parallelism and Iterative bi-Lanczos Solvers

J Bašić, B Blagojević, M Bašić… - 2021 6th International …, 2021 - ieeexplore.ieee.org
… deciding on using a parallel iterative solver, more specifically… [14] provide abstract models
for parallel execution of custom … devices (CPUs, GPUs, and other acceleration devices) in an …

[HTML][HTML] Accelerating an iterative eigensolver for nuclear structure configuration interaction calculations on GPUs using OpenACC

P Maris, C Yang, D Oryspayev, B Cook - Journal of Computational Science, 2022 - Elsevier
… on multiple GPUs and perform distributed-memory parallel … Because each GPU on Cori
GPU has 16 GB high bandwidth … of GPUs (and an appropriate number of nodes) to solve the …

A GPU implementation of the PCG method for large-scale image-based finite element analysis in heterogeneous periodic media

PCF Lopes, AMB Pereira, EWG Clua… - Computer Methods in …, 2022 - Elsevier
… massively parallel PCG solver applied to finite element analyses of heat conduction and linear
elasticity on image-based … of personal-use GPUs for large-scale simulations. The resulting …

An overview of dense eigenvalue solvers for distributed memory systems

D Davidović - 2021 44th International Convention on …, 2021 - ieeexplore.ieee.org
… packages that implement parallel eigenvalue solvers for dense … The shared-memory solutions
are commonly based on the … GPU-specific models (CUDA, OpenCL) for GPU acceleration. …

ChASE: a distributed hybrid CPU-GPU eigensolver for large-scale hermitian eigenvalue problems

X Wu, D Davidović, S Achilles, E Di Napoli - Proceedings of the Platform …, 2022 - dl.acm.org
… with the acceleration of a filter based on Chebyshev … To our knowledge, though numerous
solvers for dense eigen… algebra operation in the Filter, Lanczos and Resid is HEMM. …

A mixed precision, multi-GPU design for large-scale Top-K sparse eigenproblems

F Sgherzi, A Parravicini… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
… In this work, we introduce a novel Top-K GPU eigensolver for … Lanczos vector becomes the
input of the SpMV. We prevent … “Accelerating the explicitly restarted arnoldi method with gpus