Irregular Problems on Multi-core Architectures

Irregular problems exhibit random and unpredictable memory access patterns, poor spatial locality and input dependent control flow. Heterogeneous multi-core processors vary in: clock frequency, power dissipation, programming model (MIMD vs. SIMD), memory design and computing units, scalar versus vector units. The heterogeneity of the processors makes designing efficient parallel algorithms for irregular problems on heterogeneous multi-core processors challenging. This book exploits parallelism of irregular problems on heterogeneous multi-core architectures and proposes an analytical performance prediction model that considers the multitude architectural features of heterogeneous multi-cores (such as DMA transfers, number of instructions and operations, the processor frequency and DMA bandwidth).

Autorentext

Dr. Meilian Xu received her Ph.D. from The University of Manitoba in Canada. She obtained her M.Sc from Peking University and B.E. from East China Normal University, China. She is a distinguished expert at Chengdu University, China. Her research interests include parallel algorithms for interdisciplinary applications, big data & cloud computing.