《GPU高性能编程CUDA实战中文》中第四章的julia实验

在整个过程中出现了各种问题，我先将我调试好的真个项目打包，提供下载。

 /*
 * Copyright 1993-2010 NVIDIA Corporation.  All rights reserved.
 *
 * NVIDIA Corporation and its licensors retain all intellectual property and
 * proprietary rights in and to this software and related documentation.
 * Any use, reproduction, disclosure, or distribution of this software
 * and related documentation without an express license agreement from
 * NVIDIA Corporation is strictly prohibited.
 *
 * Please refer to the applicable NVIDIA end user license agreement (EULA)
 * associated with this source code for terms and conditions that govern
 * your use of this NVIDIA software.
 *
 */

 #include <GL\glut.h>
 #include "cuda.h"
 #include "cuda_runtime.h"
 #include "device_launch_parameters.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 /  - x) / (DIM / );
     float jy = scale * (float)(DIM /  - y) / (DIM / );

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

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

     return ;
 }

 __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 *  + ] =  * juliaValue;
     ptr[offset *  + ] = ;
     ptr[offset *  + ] = ;
     ptr[offset *  + ] = ;
 }

 // 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,  >> >(dev_bitmap);

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

     HANDLE_ERROR(cudaFree(dev_bitmap));

     bitmap.display_and_exit();
 }

期间出现的问题：

问题一

calling a host function("cuComplex::cuComplex") from a __device__/__global__ function("julia") is not allowed
calling a host function("cuComplex::cuComplex") from a __device__/__global__ function("julia") is not allowed
calling a host function("cuComplex::cuComplex") from a __device__/__global__ function("cuComplex::operator *") is not allowed
calling a host function("cuComplex::cuComplex") from a __device__/__global__ function("cuComplex::operator +") is not allowed

这个原因是在原著中提供的代码有问题，原著中结构体中的代码为

cuComplex(float a, float b) : r(a), i(b)  {}

将其修改如下即可：

 __device__ cuComplex(float a, float b) : r(a), i(b)  {}

问题二

error LNK2019: 无法解析的外部符号 ___glutInitWithExit@12，该符号在函数 _glutInit_ATEXIT_HACK@8 中被引用 1>GEARS.obj : error LNK2019: 无法解析的外部符号 ___gl

这个原因是我的OpenGL文件没有引对

#include <GL\glut.h>

其中glut.h文件要在下面的路径下

C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\include\GL

如果GL文件夹不在，要手动创建，结构如下图所示：

注意：

为了运行示例代码，需要抽取可运行的部分，同时为了减少手动修改的麻烦，也要注意各各个文件目录的层次关系，我的截图如下：

千辛万苦走下来就为了下面这张图：

确实挺好看的。赞一个！