#include "cuda.h"
#include "../common/book.h"
#include "../common/image.h"

#define DIM 1024

#define rnd( x ) (x * rand() / RAND_MAX)
#define INF     2e10f

struct Sphere {
    float   r,b,g;
    float   radius;
    float   x,y,z;//球心相对于图像中心的坐标
    __device__ float hit( float ox, float oy, float *n ) {
        float dx = ox - x;
        float dy = oy - y;
        //计算来自于(ox,oy)处像素的光线（垂直于图像平面），计算光线是否与球面相交
        //然后计算相机到光线命中球面出的距离
        if (dx*dx + dy*dy < radius*radius) {
            float dz = sqrtf( radius*radius - dx*dx - dy*dy );
            *n = dz / sqrtf( radius * radius );
            return dz + z;
        }
        return -INF;
    }
};
#define SPHERES 20

__constant__ Sphere s[SPHERES];

__global__ void kernel( unsigned char *ptr ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;
    float   ox = (x - DIM/2);//(ox, oy)=(x, y)相对于图像中心点（DIM / 2，DIM / 2）位置或者说将图像移到中心
    float   oy = (y - DIM/2);

    float   r=0, g=0, b=0;
    float   maxz = -INF;
    for(int i=0; i<SPHERES; i++) {
        float   n;
        float   t = s[i].hit( ox, oy, &n );
        if (t > maxz) {
            float fscale = n;
            r = s[i].r * fscale;
            g = s[i].g * fscale;
            b = s[i].b * fscale;
            maxz = t;
        }
    } 

    ptr[offset*4 + 0] = (int)(r * 255);
    ptr[offset*4 + 1] = (int)(g * 255);
    ptr[offset*4 + 2] = (int)(b * 255);
    ptr[offset*4 + 3] = 255;
}

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

int main( void ) {
    DataBlock   data;
    // capture the start time
    cudaEvent_t     start, stop;
    HANDLE_ERROR( cudaEventCreate( &start ) );
    HANDLE_ERROR( cudaEventCreate( &stop ) );
    HANDLE_ERROR( cudaEventRecord( start, 0 ) );

    IMAGE bitmap( DIM, DIM );
    unsigned char   *dev_bitmap;

    // 在GPU上分配内存以计算输出位图
    HANDLE_ERROR( cudaMalloc( (void**)&dev_bitmap,
                              bitmap.image_size() ) );

    // 分配临时内存，对其初始化，并复制到GPU上的常量内存，然后释放临时内存
    Sphere *temp_s = (Sphere*)malloc( sizeof(Sphere) * SPHERES );
    for (int i=0; i<SPHERES; i++) {
        temp_s[i].r = rnd( 1.0f );
        temp_s[i].g = rnd( 1.0f );
        temp_s[i].b = rnd( 1.0f );
        temp_s[i].x = rnd( 1000.0f ) - 500;
        temp_s[i].y = rnd( 1000.0f ) - 500;
        temp_s[i].z = rnd( 1000.0f ) - 500;
        temp_s[i].radius = rnd( 100.0f ) + 20;
    }
    HANDLE_ERROR( cudaMemcpyToSymbol( s, temp_s, 
                                sizeof(Sphere) * SPHERES) );
    free( temp_s );

    // generate a bitmap from our sphere data
    dim3    grids(DIM/16,DIM/16);
    dim3    threads(16,16);
    kernel<<<grids,threads>>>( dev_bitmap );

    // copy our bitmap back from the GPU for display
    HANDLE_ERROR( cudaMemcpy( bitmap.get_ptr(), dev_bitmap,
                              bitmap.image_size(),
                              cudaMemcpyDeviceToHost ) );

    // get stop time, and display the timing results
    HANDLE_ERROR( cudaEventRecord( stop, 0 ) );
    HANDLE_ERROR( cudaEventSynchronize( stop ) );
    float   elapsedTime;
    HANDLE_ERROR( cudaEventElapsedTime( &elapsedTime,
                                        start, stop ) );
    printf( "Time to generate:  %3.1f ms\n", elapsedTime );

    HANDLE_ERROR( cudaEventDestroy( start ) );
    HANDLE_ERROR( cudaEventDestroy( stop ) );

    HANDLE_ERROR( cudaFree( dev_bitmap ) );

    // display
    bitmap.show_image();
}

cudaEvent_t     start, stop;
cudaEventCreate( &start );
cudaEventCreate( &stop );
cudaEventRecord( start, 0 );

// 在GPU上执行一些工作

cudaEventRecord( stop, 0 );
cudaEventSynchronize( stop );
float   elapsedTime;
cudaEventElapsedTime( &elapsedTime,start, stop );
printf( "Time to generate:  %3.1f ms\n", elapsedTime );
cudaEventDestroy( start );
cudaEventDestroy( stop );