• A novel parallel algorithm for computing the scan operations on x86 multicore processors. • This design of the algorithm presents the rate of cache misses is reduced and the cost of thread synchronization and management are minimized. • A novel approach to sparse matrix multiplication (SpMV), unlike the existing ones that make use of backward segmented operations, uses forward ones for more efficient caching. • Seemingly serial though, parallel solutions to the scan problem have long been developed. • The concerns for designing algorithms on multicore processors are very different from those when working with super computers. • Parallezation is achieved through concurrent running threads. • The current best known parallel scan algorithm for the same platform.