您的位置:首页 > 编程语言

并行计算02-《cuda by examples》代码配置及julia例子

2017-11-19 13:19 531 查看


摘要:回忆VS的使用,把《cuda by examples》书的代码配置一下,使julian在CPU及GPU都跑起来, 对比GPU与CPU的编程的区别。

VS很久没用,用起有些不熟悉了,今天复习了一下VS的使用,练习一下把一些例子使用起来,记录一下。感觉一个技术如果不用,一段时间就可以忘记得一点印象都没有,这时就得回忆了,一边做一边回忆。

1. h文件

包的存放问题,本想创建一个文件夹来存放头文件的,把所有的头文件都copy过来了。可是后来发现这个只是把这个文件只是把它的路径引用来的,那个显示像文件夹的东西是一个过滤器来的。后在在目录下创建相关目录,把头文件放入去就可以。



这样:



这个是相对于项目demo_cuda的目录,引用时像例子所给的那样就可以用了。

#include "../common/book.h"
#include "../common/cpu_bitmap.h"


头文件配置好之后,编译就不会有问题了:

1>CUDACOMPILE : nvcc warning : The 'compute_20', 'sm_20', and 'sm_21' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
1>CUDACOMPILE : nvcc warning : nvcc support for Microsoft Visual Studio 2010 and earlier has been deprecated and is no longer being maintained
1>  demo_julia.cu
1>  support for Microsoft Visual Studio 2010 has been deprecated!
1>
1>生成成功。
1>
1>已用时间 00:00:02.47
========== 生成: 成功 1 个,失败 0 个,最新 0 个,跳过 0 个 ==========


2. lib配置

当头文件解决了,到lib了,如果不配置会出现如下问题:

1>LINK : fatal error LNK1104: 无法打开文件“glut32.lib”

配置附加库目录



配置附加依赖项



注意了,如果glut32.lib少了后缀,再编译一下,再生成,会出现问题2:

1>LINK : fatal error LNK1104: 无法打开文件“glut32.obj”

问题3:1>LINK : fatal error LNK1123: 转换到 COFF 期间失败: 文件无效或损坏



3. julia例子

3.1 CPU

#include "../common/book.h"
#include "../common/cpu_bitmap.h"

#define DIM 1000

struct cuComplex {
float r;
float i;
cuComplex( float a, float b ) : r(a), i(b) {}
float magnitude2( void ) { return r * r + i * i; }
cuComplex operator*(const cuComplex& a) {
return cuComplex(r*a.r - i*a.i, i*a.r + r*a.i);
}
cuComplex operator+(const cuComplex& a) {
return cuComplex(r+a.r, i+a.i);
}
};

int julia( int x, int y ) {
const float scale = 1.5;
float jx = scale * (float)(DIM/2 - x)/(DIM/2);
float jy = scale * (float)(DIM/2 - y)/(DIM/2);

cuComplex c(-0.8, 0.156);
cuComplex a(jx, jy);

int i = 0;
for (i=0; i<200; i++) {
a = a * a + c;
if (a.magnitude2() > 1000)
return 0;
}

return 1;
}

void kernel( unsigned char *ptr ){
for (int y=0; y<DIM; y++) {
for (int x=0; x<DIM; x++) {
int offset = x + y * DIM;

int juliaValue = julia( x, y );
ptr[offset*4 + 0] = 255 * juliaValue;
ptr[offset*4 + 1] = 0;
ptr[offset*4 + 2] = 0;
ptr[offset*4 + 3] = 255;
}
}
}

int main( void ) {
CPUBitmap bitmap( DIM, DIM );
unsigned char *ptr = bitmap.get_ptr();

kernel( ptr );

bitmap.display_and_exit();
}



3.2 GPU

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>

#include "../common/book.h" #include "../common/cpu_bitmap.h"

#define DIM 1000

struct cuComplex {
float r;
float i;
__device__ cuComplex( float a, float b ) : r(a), i(b) {}
__device__ float magnitude2( void ) {
return r * r + i * i;
}
__device__ cuComplex operator*(const cuComplex& a) {
return cuComplex(r*a.r - i*a.i, i*a.r + r*a.i);
}
__device__ cuComplex operator+(const cuComplex& a) {
return cuComplex(r+a.r, i+a.i);
}
};

__device__ int julia( int x, int y ) {
const float scale = 1.5;
float jx = scale * (float)(DIM/2 - x)/(DIM/2);
float jy = scale * (float)(DIM/2 - y)/(DIM/2);

cuComplex c(-0.8, 0.156);
cuComplex a(jx, jy);

int i = 0;
for (i=0; i<200; i++) {
a = a * a + c;
if (a.magnitude2() > 1000)
return 0;
}

return 1;
}

__global__ void kernel( unsigned char *ptr ) {
// map from blockIdx to pixel position
int x = blockIdx.x;
int y = blockIdx.y;
int offset = x + y * gridDim.x;

// now calculate the value at that position
int juliaValue = julia( x, y );
ptr[offset*4 + 0] = 255 * juliaValue;
ptr[offset*4 + 1] = 0;
ptr[offset*4 + 2] = 0;
ptr[offset*4 + 3] = 255;
}

// globals needed by the update routine
struct DataBlock {
unsigned char *dev_bitmap;
};

int main( void ) {
DataBlock data;
CPUBitmap bitmap( DIM, DIM, &data );
unsigned char *dev_bitmap;

HANDLE_ERROR( cudaMalloc( (void**)&dev_bitmap, bitmap.image_size() ) );
data.dev_bitmap = dev_bitmap;

dim3 grid(DIM,DIM);
kernel<<<grid,1>>>( dev_bitmap );

HANDLE_ERROR( cudaMemcpy( bitmap.get_ptr(), dev_bitmap,
bitmap.image_size(),
cudaMemcpyDeviceToHost ) );

HANDLE_ERROR( cudaFree( dev_bitmap ) );

bitmap.display_and_exit();
}


注意,GPU的代码下载包里的代码有些问题,要在cuComplex构造函数前加上device ,上面已经加上了。详细修改参见《CUDA BY EXAMPLES第4章代码错误解决方法》;

http://blog.csdn.net/chevroletss/article/details/48130953

对julia这个东西是什么,参见《再谈Julia集与Mandelbrot集》

http://www.matrix67.com/blog/archives/4570

4. 运行结果



【作者:happyprince, http://blog.csdn.net/ld326/article/details/78573914
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签:  cuda 并行计算 julia