Description: 基于图模型的图像分割并行算法研究与实现,该方案通过网格划分来实现相似度矩阵的并行计算同时考虑到相似度矩阵的稀疏性和矩阵向量乘运算的内在并行性, 在该方案中本文设计并行算法来求解特征值问题在环境下的实验结果表明, 该并行方案是提高图模型分割方法实时性的有效途径.-Image segmentation based on graph model of parallel algorithm and implementation of the program through the mesh to achieve similarity matrix of parallel computing the similarity matrix, taking into account the sparsity of matrix vector multiplication He' s inherent parallelism in the program in this article Design of parallel algorithms to solve the eigenvalue problem in the environment under the experimental results show that, 该 parallel programs is Tigao graph model segmentation in real time to Xing' s Youxiao way. Platform: |
Size: 575488 |
Author:郭事业 |
Hits:
Description: 稀疏矩阵的DIA/ELLPACK/COO/CSR/HYB表示形式,以及各表示形式下的稀疏矩阵乘法(稀疏大矩阵*矢量)的CUDA实现。对于矩阵中每一行稀疏元素个数较统一的情况,ELLPACK表示最佳,其次是HYB(ELL+COO)。
CUDA™ 是一种由NVIDIA推出的通用并行计算架构,该架构使GPU能够解决复杂的计算问题。 它包含了CUDA指令集架构(ISA)以及GPU内部的并行计算引擎。 开发人员现在可以使用C语言来为CUDA™ 架构编写程序-Sparse matrix DIA/ELLPACK/COO/CSR/HYB representation, as well as the representation of the sparse matrix multiplication (large sparse matrix* vector)' s CUDA implementation. For each row of the sparse matrix representing the number of elements the case of unification, ELLPACK that the best, followed by HYB (ELL+COO). NVIDIA CUDA ™ is introduced by a general purpose parallel computing architecture that makes the GPU to solve complex computational problems. It contains the CUDA Instruction Set Architecture (ISA) and the GPU parallel computing engine. Developers can now use the C language to write programs for the CUDA ™ architecture Platform: |
Size: 3282944 |
Author:lipeng |
Hits:
Description: mpi和openmp混合编程,实现矩阵向量相乘的并行计算,主要是并行开启和终止的示例,适合初学者-mpi and openmp mixed programming, parallel computing matrix-vector multiplication, is an example of a parallel main opening and termination for beginners Platform: |
Size: 4096 |
Author:王耀侦 |
Hits:
Description: 《MPI与OpenMP并行程序设计(C语言版)》是美国Oregon州立大学的Michael J.Quinn教授在多年讲授“并行程序设计”课程的基础上编写而成的,主要介绍用C语言,并结合使用MPI和OpenMP进行并行程序设计,内容包括并行体系结构、并行算法设计、消息传递编程、Eratosthenes 筛法、Floyd 算法、性能分析、矩阵向量乘法、文档分类、蒙特卡洛法、矩阵乘法、线性方程组求解、有限差分方法、排序、快速傅立叶变换、组合搜索、共享存储编程、融合OpenMP和MPI以及5个附录。-" MPI and OpenMP parallel programming (C language version)" is Michael J.Quinn Professor Oregon State University in the years written in a lecture on " parallel programming" course, based on the C language introduces, and in conjunction with MPI and OpenMP parallel programming, including parallel architectures, parallel algorithm design, message passing programming, Eratosthenes sieve method, Floyd algorithm, performance analysis, matrix-vector multiplication, document classification, Monte Carlo method, matrix multiplication, linear equations solving finite difference method, sorting, fast Fourier transform, a combination of search, shared memory programming, integration OpenMP and MPI and five appendices. Platform: |
Size: 48901120 |
Author:艾艾 |
Hits: