搜索资源列表
parallel-dijkstra 并行化思路实现dijkstra算法
- 并行化思路实现dijkstra算法。假设有p个处理器，N个顶点。给每个处理器分配N/p个顶点，求出局部的最小值，复杂度为O (N/p)。然后后一半的处理器将自己的最小值发送给第前p/2个处理器。前一半处理器接收到传来的值后，与局部的最小值比较，作为新值。继续循环，直到剩下一个处理器为止。-Parallelized dijkstra algorithm. Suppose there is p a processor, N vertex. Give each processor distributi
paralall_sort
- mpi实现并行排序算法，可以设置处理器节点个数并比较不同节点数目时的计算时间-mpi parallel sorting algorithm, you can set the number of processor nodes and compare the different number of nodes at the time of computing time
CompQsortToMsort
- 分治算法与快速排序时间比较,根据运行时间比较其算法的优越性。-compare quicksort to mergesort
hw2
- cuda compare using shared memory and unshared memory to computer the matrix
openmp
- 用OpenMp实现矩阵转置，输出转置结果和串行及并行的时间，进行比较-With OpenMp realization matrix transpose, transpose output serial and parallel results and time to compare
Matrix_mulitiple
- 使用CUDA并行语言编写的矩阵乘法，与串行语句的对比试验，主要检测出CPU与GPU运行的时间，通过比较时间，达到比较效果。另外此程序可以随意更改矩阵的维数，增强程序的移植性。-CUDA parallel language use matrix multiplication, and serial statement comparison test, the main test of CPU and GPU to run time, by comparing the time, to compar
different_multiplier
- 比较了不同设计方法下的乘法器性能，给出了计算公式-Compare the performance of different design methods multiplier under the given formulas
hanshu2
- 使用c++编写的函数模板，主要是用来比较数字的大小-Use c++ write function template is mainly used to compare the size of the digital