【摘要】 MPI Alltoall是一种重要的集合通信.在多核机群中,一个节点内的多个进程同时参与Alltoall通信.一方面,这些进程可以利用共享内存优化通信性能.虽然当前基于首进程的方法利用共享内存提高了Alltoall小消息通信的性能,但由于采用固定数目的首进程,这些方法不能使所有不同长度的小消息都获得最优性能.另一方面,这些进程需要竞争节点内有限的网络资源.在Alltoall大消息的通信中存在许多个同步消息.然而竞争导致同步消息的延迟增大了数十倍,同步开销不可忽略.针对这些问题,提出了两种不同的优化方法.对于Alltoall小消息通信,PLP方法根据小消息的长度采用不同数目的首进程;对于Alltoall大消息通信,LSS方法将同步消息的总数从3N减少到2N(1/2).相关实验结果验证了这两种方法.对于小消息,PLP方法总是可以获得最优的性能.对于大消息,LSS方法获得的性能提升比例几乎为常数,并且与系统的规模无关;其中32KB和64KB消息的性能提高了25%.更多还原

【Abstract】 MPI Alltoall is an important collective operation.In multicore clusters , many processes run in a node.On the one hand , shared memory can be adopted to optimize Alltoall communications of small messages by leader-based schemes.However , as these schemes adopt a fixed number of leader processes , the optimal performance can’t be obtained for all small messages.On the other hand , processes within a node contend for the same network resource.In Alltoall communications of large messages , many synchronization messages are used.Nevertheless , the contention makes their latency increase many times and the synchronization overhead cant be ingored.To solve these problems , two optimizations are presented.For small messages , the PLP method adopts changeable numbers of leader processes.For large messages , the LSS method reduces the number of synchronization messages from 3N to 2N(1/2).The evaluations prove two methods.For small messages , the PLP method always obtains optimal performance.For large messages , the LSS method brings almost constant improvement percentage.The performance is improved by 25% for 32KB and 64KB messages.更多还原