@article{(Open Science Index):https://publications.waset.org/pdf/2362, title = {Accelerating Sparse Matrix Vector Multiplication on Many-Core GPUs}, author = {Weizhi Xu and Zhiyong Liu and Dongrui Fan and Shuai Jiao and Xiaochun Ye and Fenglong Song and Chenggang Yan}, country = {}, institution = {}, abstract = {Many-core GPUs provide high computing ability and substantial bandwidth; however, optimizing irregular applications like SpMV on GPUs becomes a difficult but meaningful task. In this paper, we propose a novel method to improve the performance of SpMV on GPUs. A new storage format called HYB-R is proposed to exploit GPU architecture more efficiently. The COO portion of the matrix is partitioned recursively into a ELL portion and a COO portion in the process of creating HYB-R format to ensure that there are as many non-zeros as possible in ELL format. The method of partitioning the matrix is an important problem for HYB-R kernel, so we also try to tune the parameters to partition the matrix for higher performance. Experimental results show that our method can get better performance than the fastest kernel (HYB) in NVIDIA-s SpMV library with as high as 17% speedup.}, journal = {International Journal of Computer and Information Engineering}, volume = {6}, number = {1}, year = {2012}, pages = {11 - 18}, ee = {https://publications.waset.org/pdf/2362}, url = {https://publications.waset.org/vol/61}, bibsource = {https://publications.waset.org/}, issn = {eISSN: 1307-6892}, publisher = {World Academy of Science, Engineering and Technology}, index = {Open Science Index 61, 2012}, }