On the Factor Refinement Principle and its Implementation on Multicore Architectures

Md Mohsin Ali, Marc Moreno Maza, Yuzhen Xie
2012 Journal of Physics, Conference Series  
We propose a divide and conquer adaptation of the factor refinement algorithm of Bach, Driscoll and Shallit. For an ideal cache of Z words, with L words per block, the original approach suffers from O(n 2 /L) cache misses, meanwhile our adaptation incurs O(n 2 /ZL) cache misses only. We have realized a multithreaded implementation of the latter using Cilk++ targeting multicores. Our code achieves linear speedup on 16 cores for sufficiently large input data.
doi:10.1088/1742-6596/385/1/012015 fatcat:4k2nezl3h5hwbkqfsntig3btki