Efficient Parallel Scan Algorithms for GPUs

Scan and segmented scan algorithms are crucial building blocks for a great many data-parallel algorithms. Segmented scan and related primitives also provide the necessary support for the attening transform, which allows for nested data-parallel programs to be compiled into at data-parallel languages. In this paper, we describe the design of ecient scan and segmented scan parallel primitives in CUDA for execution on GPUs. Our algorithms are designed using a divide-and-conquer approach that builds all scan primitives on top of a set of primitive intra-warp scan routines. We demonstrate that this design methodology results in routines that are simple, highly ecient, and free of irregular access patterns that lead to memory bank conicts. These algorithms form the basis for current and upcoming releases of the widely used CUDPP library.