搜索资源列表
cuda-memcheck-handbook-4.0cn
- CUDA调试工具cuda-gdb，包含一个可以在CUDA中检测和调试内存错误的内存检查特性。该文档描述了这个名为cuda-memcheck的工具与它的功能。 NVIDIA用它强大的cuda-gdb硬件调试器简化了CUDA程序错误的调试。然而，每个程序员总会遇到难以检测到的内存相关错误，并花大量时间去调试。当处理上千条线程时，内存相关的错误的数量会明显增加。cuda-memcheck就是设计用来检测你的CUDA程序中这种内存存取错误的工具。-CUDA debugging tool cud
pi
- 使用pthread多线程计算圆周率，直接在linux环境下编译运行，线程数通过代码中N进行修改-Use pthread multi-threaded computing pi, directly in the linux environment, compile run threads through the code to modify N
China
- 国家联邦：两个线程交互，互相获取各自人口信息并实时显示。-National Federation: two threads interact with each other to get each demographic information and real-time display.
procon
- 生产者消费者同步问题，用于模拟都线程的并行与互斥-Producer consumer synchronization, threads are used to simulate parallel and mutually exclusive
openmp
- 基于OPENMP的并行算法，通过设置不同的线程数来验证多线程对并行计算速度提高的贡献-OPENMP-based parallel algorithm, by setting a different number of threads to validate the multi-threaded parallel computing speed of the contribution of
2006_book-TransactionalMemory
- 电子书，综述了事务存储，事务存储是一种很有前途的并行编程模型-ABSTRACT The advent of multicore processors has renewed interest in the idea of incorporating transactions into the programming model used to write parallel programs. This approach, known as transactional memory,
Prime
- JAVA多线程找质数。 输入为你想要创建的线程数和质数上限。 例： java PrimeSieve 10 3会利用三个线程输出10以下所有的质数-JAVA multi-threading to find prime numbers. Enter the number of threads you want to create the maximum number and quality. Example: java PrimeSieve 10 3 will make use of
ques_3_bonus
- hybrid program for column-wise matrix multiplication with following: N=2048 && number of nodes=4 && #threads/process=16
a
- OpenMP简单的应用 输入计算线程数 重复循环执行一定数量的代码 记录起始时间和结束时间 时间相减求出代码执行时间-A simple OpenMP applications enter the calculation of the number of threads that repeat loop executes a certain amount of code to record the start time and end time subtraction to find the co
Pi
- 一个简单的计算Pi的Pthread多线程程序，提供给用户输入想开的线程数和N计算pi值。-A simple calculation of Pi Pthread multi-threaded program, available to user input like to open the number of threads and N calculate the value of pi.
Ripple
- 在GPU上使用线程实现波纹效果，CUDA C编程，使用VS及CUDA平台才能运行成功-The use of threads on the GPU to achieve ripple effect, CUDA C programming, the successful use of VS and CUDA platform to run
pi
- pthread多线程实现π的计算，可以设置线程数与计算量-pthread multithreading π calculation, you can set the number of threads and computation
bingxing
- openMP与MPI混合编程，实现矩阵与矩阵相乘。 并且矩阵阶数可调整，进程数与线程数可调整。-OpenMP and MPI mixed programming, matrix and matrix multiplication. And the matrix order can be adjusted, the number of processes and threads can be adjusted.
mpi
- 搭建MPI集群，实现矩阵运算，对比不同线程不同规模允许时间，对比加速比。-MPI cluster structures, implement matrix operations, comparison of different threads of different sizes to allow time, compared to speedup.
OMP_TEST
- OpenMV小程序，在vs2013中采用OMP编程实现读取一个文件中的数据，文件中数据的第一行为数据个数，第二行为实际数据，数据间以空格隔开。判断第二行的数据中有多少个水仙花数。判断过程利用MPI采用多个线程进行。-Using OMP program implemented in vs2013 read data in a file, the first acts of the number of data files in the data, and the second actual beh
omp_pi
- Estimate the pi value in multiple threads system OpenMP.
Colfax-HOW-Day-04
- 引入了线程并行，OpenMP并行框架。讨论的主题包括：使用线程来利用多个处理器内核，线程和数据并行，协调使用OpenMP线程的创建和团队他们处理循环和树木的任务。OpenMP的讨论提到控制线程的数量，控制变量条款和范围的共享，循环调度模式，使用互斥锁来保护竞争的条件，并与线程私有变量减少并行可扩展的方法。讲座部分的结论与讨论的一般方法来实现在计算应用中的并行的机会。动手部分演示了使用OpenMP并行串行计算和论证了循环变量共享，在一个应用实例进行数值积分的互斥和并行还原。-Session 4 i
mpich2-1.4.1p1.tar
- MPI简介多线程是一种便捷的模型,其中每个线程都可以访问其它线程的存储空间。因此,这种模型只能在共享存储系统之间移植。(MPI introduction to multithreading is a convenient model in which each thread can access the storage space of other threads. Therefore, this model can only be transplanted between shared sto