CUDA_Matrix

compilateur de code source

GPU实现的MapReduce framework,对于学习并行编程和cuda平台的编程方面有着极好的参考价值，里面附带论文。用户要求有NViDIA显卡，并且安装cuda编程环境。(We design and implement Mars, a MapReduce framework, on graphics processors (GPUs). MapReduce is a distributed programming framework originally proposed by Google for the ease of development of web search applications on a large number of commodity CPUs. Compared with CPUs, GPUs have an order of magnitude higher computation power and memory bandwidth, but are harder to program since their architectures are designed as a special-purpose co-processor and their programming interfaces are typically for graphics applications.)

CUDA平行的優化，以矩陣乘法為基礎。透過ShareMemory做加速(CUDA ShareMem)

用此程序可以方便的查讯日期和星期几，还可以查当天和未来几天的．(This procedure can be used to facilitate inquiry date and day of the week, you can check the same day and the next few days.)

基于C语言的MPICH程序，实现矩阵相乘(C-based MPICH program, to achieve matrix multiplication)

说明：  计算π值 C++ 并行算法 分别使用方法左矩形分解、中矩形分解以及梯形分解(π C++ MPI π C++ MPI π C++ MPI π C++ MPI)

LU算法的MPI串行实现，矩阵维数无要求，可在曙光4000A并行机运行(The LU algorithm MPI serial implementation matrix dimension requirements Dawning 4000A parallel machine running)

MPI编程－Nbody问题并行程序（计算1000个天体的移动，天体数据由文件sample_input.in读入，结果输出到文件result1000.data）(MPI Programming-Nbody Parallel (1000 calculated the movement of celestial bodies, Objects sample_input.in data from the document read into, Results output to a file result1000.data))

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 compare results. Also this program can change the dimension of the matrix, and enhanced portability of the program.)

CUDA平行的優化，以矩陣乘法為基礎。透過ShareMemory做加速(CUDA ShareMem)