搜索资源列表
zihanshu
- 实现小波变换的CUDA子函数源代码，能够大幅度提高小波变换的速度-Wavelet transform CUDA Functions, can greatly improve the speed of image wavelet transform
dot_product
- 使用CUDA语言实现向量的点乘，可以大幅度提高点乘的速度，是CUDA语言的入门程序-Using CUDA language vector dot product, can greatly improve the speed of the dot is CUDA language entry program
shebeisheding
- CUDA语言实现设备设定，是CUDA语言的初始化程序，是CUDA的入门程序-CUDA language setting device is initialized program CUDA language is CUDA entry procedures
Gauss_Adjust_GPU
- 该算法基于opencv的自适应高斯滤波，并且使用CUDA（GPU）架构进行算法加速-The algorithm is based opencv adaptive Gaussian filter, and use CUDA (GPU) architecture to accelerate the algorithm
MeanFilter_GPU
- 该程序是基于CUDA架构的均值滤波程序，GPU加速，并且使用了opencv函数库-The program is based on the CUDA architecture mean filtering program, GPU acceleration, and use the opencv library
MedianFilter_GPU
- 该VC++程序是基于CUDA架构的中值滤波程序，GPU加速，并且使用了opencv函数库-The VC++ program is based on the CUDA architecture median filtering program, GPU acceleration, and use the opencv library
Sobel_GPU
- 该VC++ 程序是基于CUDA架构的sobel边缘检测程序，GPU加速，并且使用了opencv函数库-The program is based on VC++ CUDA architecture sobel edge detection procedures, GPU acceleration, and use the opencv library
Roberts_GPU
- 该VC++ 程序是基于CUDA架构的Robert边缘检测程序，GPU加速，并且使用了opencv函数库-The VC++ program is based on the CUDA architecture, Robert edge detection procedures, GPU acceleration, and use the opencv library
LoG_GPU-log
- 该VC++ 程序是基于CUDA架构的LOG边缘检测程序，GPU加速，并且使用了opencv函数库-The program is based on VC++ CUDA architecture LOG edge detection procedures, GPU acceleration, and use the opencv library
cuda
- We might want to consider using g4 like sparc64 to shave a few cycles. -We might want to consider using g4 like sparc64 to shave a few cycles.
Simrank
- 结合mex编程实现的一个基于cuda的simrank计算程序-An implementation of Simrank algorithm on Cuda with Mex
cudamarix-mul
- 用cuda写的矩阵相乘，包含分块和共享内存的核函数，请大家参照-Written by cuda matrix multiplication, and shared memory block containing the kernel function, please reference
CUDAreductionMatrix
- cuda reduction matix stu-cuda reduction matix stuff
turbodecode
- 应用于3G，4G 通信系统中的 turbo 解码。应用环境为C，可嵌套CUDA。-Applies to 3G, turbo decoding 4G communication system. Application environment for C, can be nested CUDA.
runge-kutta-master
- RungeKutta法的并行实现。对于想用CUDA实现RungeKutta并行的人有一定的帮助。-Parallel RungeKutta law implementation. For those who want to achieve with CUDA parallel RungeKutta people have some help.
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
Matrix_add
- 此程序使用CUDA并行语言完成矩阵的加法。矩阵维数为3×3矩阵。矩阵维数可以更改。但是同时矩阵的处置也要手动设置。-This program uses the CUDA parallel language to complete the addition matrix. 33 matrix matrix dimensions. You can change the dimension of the matrix. However, while the disposal of the matrix
Face-Recognition-2.4.9
- 使用emcv C#进行人脸定位与识别对比,各位要自己下载libemgucv-windows-universal-cuda-2.9.0.1922-beta.exe文件-Use emcv C# for face location and recognition contrast, you have to download their libemgucv-windows-universal-cuda-2.9.0.1922-beta.exe file
cuda_by_example
- 该代码是GPU高性能编程cuda实战中所有代码的合集，包含了书中所有的代码，对于初学GPU编程者来说是一本非常好的人们书-GPU programming by cuda codes
VS2010-CUDAdeploy
- VS2010 CUDA 5.5 Win7 64位配置以及项目创建配置-VS2010 CUDA 5.5 Win7 64bit system deploy and new project deploy