Abstract
Abstract
This paper addresses the performance analysis of sparse matrix-vector multiplication through hypergraph partitioning techniques using CUDA GPU-based parallel computing. Quadro K4200 is the GPU that is used in this paper. On the implementation of matrix-vector multiplication, various sizes and types of matrices are attempted. Our results show that on the average scenarios with 2 partitions, 4 partitions, 8 partitions, 16 partitions and 32 partitions in 1024 threads, CUDA performs up to 700 × better than sequential programming.
Reference16 articles.
1. Performance Evaluation of Fast Smith-Waterman Algorithm for Sequence Database Searches using CUDA GPU-based Parallel Computing;Bustamam;Journal of Next Generation Information Technology,2014
2. Decomposing Irregularly Sparse Matrices for Parallel Matrix-Vector Multiplication;Catalyurek;Parallel Algorithms for Irregularly Structured Problems, Irregular’96, In Lecture Notes in Computer Science,1996
3. Hypergraph-Partitioning-Based Decomposition for Parallel Sparse-Matrix Vector Multiplication;Catalyurek;IEEE Transactions on Parallel and Distributed Systems,1999
4. Simplicity Versus Accuracy in a Model of Cache Coherency Overhead;Eggers;IEEE Transactions on Computer,1991