Communication Optimization of Iterative Sparse Matrix-Vector Multiply on GPUs and FPGAs

• Main Authors: Rafique, Abid, Constantinides, George A., Kapre, Nachiket
• Other Authors: School of Computer Engineering
• Format: Article
• Language: English
• Published: 2015
• Subjects: Graphics processing units (GPUs); Iterative numerical methods; Spare matrix-vector multiply; Matrix powers kernel; Field programmable gate arrays (FPGAs)
• Online Access: https://hdl.handle.net/10356/81168; http://hdl.handle.net/10220/39128
• Institution: Nanyang Technological University

Trading communication with redundant computation can increase the silicon efficiency of FPGAs and GPUs in accelerating communication-bound sparse iterative solvers. While k iterations of the iterative solver can be unrolled to provide O(k) reduction in communication cost, the extent of this unrollin...