Collective communication functions including the broadcast in cluster computers usually take O(m log P) time in propagating the size-m message to P processors. We have devised a new O(m) broadcast algorithm, independent of the number of processors involved, by using divided-and-conquer algorithm. Details are given below.
Paolo CignoniC. MontaniRiccardo Scopigno
Woong-Kee LohYang‐Sae MoonWookey Lee
Fan MinLijun XieQihe LiuHongbin Cai