scholarly journals Using Graphics Processors to Accelerate the Solution of Out-of-Core Linear Systems

2009 ◽  
Author(s):  
Mercedes Marques ◽  
Gregorio Quintana-Orti ◽  
Enrique S. Quintana-Orti ◽  
Robert van de Geijn
Keyword(s):  
Linear Systems ◽  
Graphics Processors

scholarly journals Accelerating Model Reduction of Large Linear Systems with Graphics Processors

2012 ◽  
pp. 88-97 ◽  
Author(s):  
Peter Benner ◽  
Pablo Ezzatti ◽  
Daniel Kressner ◽  
Enrique S. Quintana-Ortí ◽  
Alfredo Remón
Keyword(s):  
Model Reduction ◽  
Linear Systems ◽  
Graphics Processors ◽  
Large Linear Systems

scholarly journals Optimization of power consumption in the iterative solution of sparse linear systems on graphics processors

2011 ◽  
Vol 27 (4) ◽  
pp. 299-307 ◽  
Author(s):  
Hartwig Anzt ◽  
Maribel Castillo ◽  
Juan C. Fernández ◽  
Vincent Heuveline ◽  
Francisco D. Igual ◽  
...  
Keyword(s):  
Power Consumption ◽  
Linear Systems ◽  
Iterative Solution ◽  
Sparse Linear Systems ◽  
Graphics Processors

scholarly journals A parallel preconditioner based on the approximation of an inverse matrix by power series for solving sparse linear systems on graphics processors

2019 ◽  
pp. 444-456
Author(s):  
А.В. Юлдашев ◽  
Н.В. Репин ◽  
В.В. Спеле
Keyword(s):  
Power Series ◽  
Linear Systems ◽  
Numerical Experiments ◽  
Computing System ◽  
Neumann Series ◽  
Inverse Matrix ◽  
Reservoir Modeling ◽  
Sparse Linear Systems ◽  
Graphics Processors ◽  
Tridiagonal Matrices

Рассмотрена применимость метода AIPS, аппроксимирующего обратную матрицу на основе степенного разложения в ряд Неймана, в рамках двухступенчатого предобусловливателя CPR. Предложен ориентированный на архитектуру CUDA параллельный алгоритм решения линейных систем с трехдиагональной матрицей, состоящей из независимых блоков различного размера. Показано, что реализация предложенного алгоритма может более чем в 2 раза превосходить по быстродействию функции решения трехдиагональных систем из библиотеки cuSPARSE. Проведено тестирование метода BiCGStab с предобусловливателем CPRAIPS на современных GPU, в том числе на гибридной вычислительной системе с 4 GPU NVIDIA Tesla V100, показавшее приемлемую масштабируемость данного предобусловливателя, а также возможность ускорить решение линейных систем, характерных для задачи гидродинамического моделирования нефтегазовых месторождений, по сравнению с CPRAMG. The applicability of the AIPS method approximating an inverse matrix using Neumann series is considered in the framework of the CPR two stage preconditioner. A parallel CUDAoriented algorithm is proposed for solving linear systems with tridiagonal matrices consisting of independent blocks of different sizes. It is shown that the implementation of the proposed algorithm can be more than twice the speed of the similar functions from the cuSPARSE library. Experimental evaluation of the BiCGStab method with the CPRAIPS preconditioner on modern GPUs, including a hybrid computing system with 4 GPU NVIDIA Tesla V100, is performed. Numerical experiments show an adequate scalability of this preconditioner as well as the possibility (compared to the CPRAMG) to accelerate the solution of linear systems being typical for the reservoir modeling problems.

Out-of-core solution of linear systems on graphics processors

2009 ◽  
Vol 24 (6) ◽  
pp. 521-538 ◽  
Author(s):  
Maribel Castillo ◽  
Francisco D. Igual ◽  
Mercedes Marqués ◽  
Rafael Mayo ◽  
Enrique S. Quintana-Ortí ◽  
...  
Keyword(s):  
Linear Systems ◽  
Graphics Processors ◽  
Core Solution

scholarly journals Solving Dense Linear Systems on Graphics Processors

2008 ◽  
pp. 739-748 ◽  
Author(s):  
Sergio Barrachina ◽  
Maribel Castillo ◽  
Francisco D. Igual ◽  
Rafael Mayo ◽  
Enrique S. Quintana-Ortí
Keyword(s):  
Linear Systems ◽  
Graphics Processors

Well-Posed Linear Systems

2005 ◽  
Author(s):  
Olof Staffans
Keyword(s):  
Linear Systems ◽  
Well Posed

Principles of Linear Systems

1997 ◽  
Author(s):  
Philip E. Sarachik
Keyword(s):  
Linear Systems

Particularities of overdetermined linear systems arising in particle size analysis

1992 ◽  
Vol 2 (8) ◽  
pp. 1547-1555
Author(s):  
D. M. Calistru ◽  
R. Mondescu ◽  
I. Baltog
Keyword(s):  
Particle Size ◽  
Linear Systems ◽  
Particle Size Analysis ◽  
Size Analysis ◽  
Overdetermined Linear Systems
Sign in / Sign up

Export Citation Format

Share Document