CUDA:如何从主机复制一个三维阵列设备? [英] CUDA : How to copy a 3D array from host to device?

查看:219
本文介绍了CUDA:如何从主机复制一个三维阵列设备?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我想学习如何从主机内存复制一个3维数组到设备内存中。 可以说我有一个三维数组,它包含的数据。例如 INT HOST_DATA [256] [256] [256]; 我要复制的数据到dev_data(一个元件阵列)以这样的方式,以便 HOST_DATA [X] [Y] [Z] = dev_data [X] [Y] [Z]。 我怎样才能做到这一点?而我怎么来访问设备的dev_data阵列? 一个简单的例子是非常有益的。

I want to learn how can i copy a 3 dimensional array from host memory to device memory. Lets say i have a 3d array which contains data. For example int host_data[256][256][256]; I want to copy that data to dev_data (a device array) in such a way so host_data[x][y][z]=dev_data[x][y][z]; How can i do it? and how am i supposed to access the dev_data array in the device? A simple example would be very helpfull.

推荐答案

的常用方法是变平的阵列(使其一维)。然后,你就必须做一些计算,从地图(X,Y,Z)三到一个数字 - 在一个扁平的一维数组的位置。

The common way is to flatten an array (make it one-dimensional). Then you'll have to make some calculations to map from (x,y,z) triple to one number - a position in a flattened one-dimensional array.

例2D:

int data[256][256];
int *flattened = data;
data[x][y] == fattened[x * 256 + y];

例如3D:

int data[256][256][256];
int *flattened = data;
data[x][y][z] == flattened[x * 256 * 256 + y * 256 + z];

或使用包装:

or use a wrapper:

__host__ __device___ inline int index(const int x, const int y, const int z) {
     return x * 256 * 256 + y * 256 + z;
}

知道了,你可以分配一个与cudaMalloc线性阵列,像往常一样,然后用首页函数访问设备code对应的元素。

Knowing that, you can allocate a linear array with cudaMalloc, as usual, then use an index function to access corresponding element in device code.

更新: 的作者<一href="http://stackoverflow.com/questions/15799086/cuda-how-to-copy-a-3d-array-from-host-to-device">this问题声称已经找到了更好的解决方案(至少在2D),你可能想看看。

Update: The author of this question claims to have found a better solution (at least for 2D), you might want to have a look.

这篇关于CUDA:如何从主机复制一个三维阵列设备?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆