CUDA by examples 第四章纠错

最新推荐文章于 2024-10-14 16:42:21 发布

原创最新推荐文章于 2024-10-14 16:42:21 发布 · 387 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#cuda

cuda 专栏收录该内容

1 篇文章

订阅专栏

本文针对CUDA by Example一书中第四章的代码示例出现的问题进行了详细分析，并提供了有效的解决方案。包括如何修正构造函数的调用限制及调整参数以获得正确的运行结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

本书给出的第四章代码如下：

#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)  {}
    __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();
}