Desktop

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

在Isight环境中集成UG/ANSYS，将UG的prt文件先储存文x_t格式文件，然后再导入ANSYS计算，将实现一个ugupdate.exe，功能除了更新prt文件文还将prt文件另存为x_t文件，以供ANSYS调用。(The Isight environment integrated the UG/ANSYS, the UG prt files first to store text x_t format file, and then import the ANSYS calculation will achieve a ugupdate.exe, functions in addition to updated prt files text will prt files saved as files x_t, for ANSYS invoked.)

calculate the circle surface using parallel mpi

CUDA代码，主要是要实现一个具体ADD操作，并且可以高速在GPU上运行(An Algorithm based on UKF)

说明：  主要是自己学习时做的习题，希望对你有帮助(Mainly to their own learning exercises to do, want to help you)

mpi的源码，示例程序等，主要用于对mpi并行编程程序的研究。(mpi source code, sample programs, mainly for mpi parallel programming procedures.)

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)

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.)

多核编程，比 OPENCL 简单 可以通过类似 OPENMP 的方式，简洁的实现异构编程，使用 GPU 计算(Multicore programming than simple OPENCL)

进行相关运算时必须要是用的一些步骤,可以解决相关算法的一些问题(Related operations must be used in a number of steps can be solved a number of issues related to algorithm)