To avoid memory access conflict, the algorithms are based on a parallel merge algorithm.
为了避免存储访问冲突,算法采用了基于并行归并的并行排序方法。
Merge-sort is not an inherently parallel algorithm, as it can be done sequentially, and is popular when the data set is too large to fit in memory and must be sorted in pieces.
合并排序本身并非并行算法,因为它可以顺序执行。 当数据集太大,内存无法容纳,必须分片保存的时候,经常使用合并排序。
Emad Omara's parallel merge sort algorithm assumes that you will have full access to the machine's CPUs for the duration of the sorting operation.
Emad Omara的并行合并排序算法假设了在排序操作的过程中(操作者)对计算机的所有CPU具有完全的访问权限。
应用推荐