Analysis of Parallel Algorithms for Energy Conservation with GPU

GPU has recently gained considerable attention in getting significant performance, for application raging from scientific computing to database sorting and search. General-purpose computing on GPU can easily reduce the execution time but results in an associated increase in the energy consumption. This paper analyzes energy consumption of parallel algorithms executing on GPU and provide a methodology for energy scalability while satisfying performance requirements. Then parallel prefix sum are analyzed to illustrate our method for energy conservation. We experimentally evaluate Sparse Matrix-Vector Multiply using the method for energy scalability and the results show that the number of blocks, memory choice and task scheduling are the important characterizes to trade-offs the performance and the energy consumption on GPU.