GPU Accelerated Parallel Cholesky Factorization
One of the fundamental problems in scientific computing is to find solutions for linear equation systems. For finite element problem, Cholesky factorization is often used to solve symmetric positive definite matrices. In this paper, Cholesky factorization is massively parallelized and three different optimization methods - highly parallel factorization, tile strategy and memory scheduling are used to accelerate Cholesky factorization effectively. A novel algorithm using OpenCL is implemented. Testing on GPU shows that performance of the algorithm increases with the dimension of matrix, reaching 785.41GFlops, about 50x times speedup. Cholesky factorization is remarkably improved with OpenCL on GPU.
GPU Accelerators Cholesky Parallel Computing OpenCL Matrix Factorization.
Liang Wang Visheng Zhang Bin Zhu Chi Xu Xiaowei Tian Chao Wang Mo Jianhua Jian Li
State Key Laboratory of Material Processing and Die and Mould Technology, Huazhong University of Sci Huazhong University of Science and Technology, School of Mechanical Science and Technology, Wuhan, H
国际会议
大连
英文
1370-1373
2011-10-19（万方平台首次上网日期，不代表论文的发表时间）