大规模并行处理机
- 网络MPP;Massively Parallel Processor
-
最后通过该算法在PC机和分布式存储的大规模并行处理机曙光1000上的实验数据对比验证了该算法的性能较雅可比算法优越。
By comparing the new method with Jacobi algorithm on both personal computer and MPP Dawn-1000 , it is proved that the method is much superior .
-
路由算法在大规模并行处理机(MPP)系统中对互连网络通信性能和系统性能的发挥起着关键作用。
In a massively parallel processors ( MPP ) system , the routing algorithm constitutes the primary factor influencing the performance of the interconnect network and MPP system .
-
大规模并行处理机(massivelyparallelprocessor,MPP)一般都具有极高的理论峰值速度,但用户在实际应用中的有效速度却往往与之大相径庭。
Generally , the Massively Parallel Processor ( MPP ) has very high peak speed in theory , but the user 's effective speed in use is far from it .
-
讨论了松弛迭代算法在大规模并行处理机(massivelyparallelprocessor,MPP)计算模型上的并行化,给出了在MPP上的并行算法。
Based on the computational model of MPP ( massively parellel processor ), parallelization of relaxation iteration method is discussed and a parallel relaxation iteration algorithm on MPP is given .
-
本文在工作站群机及大规模并行处理机(MPP)上进行了超燃发动机内氢气/空气的混合与燃烧流场的并行计算。
The parallel simulation of the H 2 / Air mixing and combustion flows in the scramjet have been implemented on both NOWs and MPP .
-
适合于大规模并行处理机(MPP)的中国科学院大气物理研究所新一代九层大气环流模式(IAP9LAGCM)被发展成功。
A new version of the Institute of Atmospheric Physics ( IAP ) 9-Layer ( 9L ) atmospheric general circula - tion model ( AGCM ) suitable for Massively Parallel Processor ( MPP ) has been developed .
-
大规模并行处理机三维叠前深度偏移
3-D prestack depth migration on massive parallel processing system
-
三维叠前深度偏移能对复杂构造准确成像,可以减小钻井风险。大规模并行处理机的并行高效率为短周期完成三维叠前深度偏移成像奠定了基础。
D pre stack depth migration can accurately image a complex structure and make the drilling risk be reduced .
-
介绍了互连网络在大规模并行处理机中的重要地位、发展特点,分析了各种互连网络的性能,最后提出了互连网络有待开发的问题。
This paper presents the important position of interconnection network in massively parallel processing , and the characteristic of development of interconnection network , then analyses the function of various interconnection networks , and finally puts forward some questions which should be developed .