Matrix Convolution using Parallel Programming

Anirud Pande, Rohit Chandna

Abstract: The convolution theorem is used to multiply matrices of two different sizes i. e. matrices in which the number of rows in the first matrix is not equal to the number of columns in the second matrix. In this study, the multiplication of 3*3 and 4*4 matrices was done using MPI. A 3*3 matrix was taken as a filter which was multiplied with different matrices of sizes as big as 1000*1000 and was implemented using OpenCL. Each element of the resultant matrix was calculated both parallelly and sequentially and their performance and efficiency were compared on the basis of execution time.

Keywords: Convolution filter, Bitmap, OpenCL, Kernel

How to Cite?: Anirud Pande, Rohit Chandna, "Matrix Convolution using Parallel Programming", Volume 2 Issue 7, July 2013, International Journal of Science and Research (IJSR), Pages: 286-291, https://www.ijsr.net/getabstract.php?paperid=IJSROFF2013318, DOI: https://dx.doi.org/10.21275/IJSROFF2013318