摘要
针对GPU并行计算领域缺少精确的性能分析模型和有针对性的性能优化方法,提出一种基于GPU的并行计算性能定量分析模型,其通过对指令流水线、共享存储器访存、全局存储器访存的性能建模,来定量分析并行程序,帮助程序员找到程序运行瓶颈,进行有效的性能优化。实验部分通过3个具有代表性的实际应用(稠密矩阵乘法、三对角线性方程组求解、稀疏矩阵矢量乘法)的性能分析证明了该模型的实用性,并有效地实现了算法的优化。
In order to solve the problem of lacking accurate performance analysis model in parallel computation field based on GPU,we proposed a quantitative performance model which can simulate the performance of three major com- ponents of GPU including instruction pipeline, shared memory access time, and global memory access time. It is designed to build a performance model that helps programmer find the performance bottlenecks and improve the system's per-formance efficiently. To demonstrate the usefulness of the model and to optimize the algorithms performance, we ana- lyzed three representative real-world programs: dense matrix multiplication, tridiagonal systems solver, and sparse ma- trix vector multiplication.
出处
《计算机科学》
CSCD
北大核心
2014年第1期31-38,共8页
Computer Science
基金
广州市科技项目(2012Y2-0031)
博士后基金(2013M531825)
国家自然科学基金(U1201251)资助
关键词
GPU
性能定量分析模型
指令流水线
共享存储器访存
全局存储器访存
GPU, Quantitative performance model, Instruction pipeline, Shared memory access time, Global memory ac- cess time