Developing a High Performance Software Library with MPI and CUDA for Matrix Computations
Journal Title: Computational Methods in Social Sciences - Year 2013, Vol 1, Issue 2
Abstract
Nowadays, the paradigm of parallel computing is changing. CUDA is now a popular programming model for general purpose computations on GPUs and a great number of applications were ported to CUDA obtaining speedups of orders of magnitude comparing to optimized CPU implementations. Hybrid approaches that combine the message passing model with the shared memory model for parallel computing area solution for very large applications. We considered a heterogeneouscluster that combines the CPU and GPU computations using MPI and CUDA for developing a high performance linear algebra library. Our library deals with large linear systems solvers because they are a common problem in the fields of science and engineering. Direct methods for computing the solution of such systems can be very expensive due to high memory requirements and computational cost. An efficient alternative are iterative methods which computes only an approximation of the solution. In this paper we present an implementation of a library that uses a hybrid model of computation using MPI and CUDA implementing both direct and iterative linear systems solvers. Our library implements LU and Cholesky factorization based solvers and some of the non-stationary iterative methods using the MPI/CUDA combination. We compared the performance of our MPI/CUDA implementation with classic programs written to be run on a single CPU.
Authors and Affiliations
Bogdan Oancea, Andrei Tudorel
Keywords
Related Articles
- EP ID EP88071
- DOI -
- Views 200
- Downloads 0
Corporate environmental responsibility – a key determinant of corporate reputation
This paper aims to determine the trend of the relationship between corporate environmental responsibility and corporate reputation by focusing on a study of the European automotive sector. The starting point of our resea...
Evolution of the regional unemployment in Romania
Unemployment is a social and economic phenomenon, with numerous implications at the individual level and at the level of an entire population. At the macroeconomic level, unemployment may be e...
Quantitative methods applied in the analysis of teenagers problems
The theme of the article is the study of teenagers problems based on quantitative methods, the scientific approach is divided into two parts: the part of knowledge and the practical approach. During the...
M1 and M2 indicators- new proposed measures for the global accuracy of forecast intervals
This is an original scientific paper that proposes the introduction in literature of two new accuracy indicators for assessing the global accuracy of the forecast intervals. Taking into account that there are not specifi...
Modelling loans and deposits during electoral years in Romania
This paper analyzes the effect of electoral years on loans and deposits for population in Romania. Using monthly data regarding the total loans and deposits, we identify the significance of the electoral tim...