我正在运行书籍《CUDA By Example》中的示例julia_gpu.cu
,使用的是Visual Studio Express 2012中的CUDA 6.0。以下是参考源代码:
#include <book.h>
#include <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();
}
编译上述内容时出现了一系列错误,这些错误都具有相同的形式:
Error 2 error : calling a __host__ function("cuComplex::cuComplex") from a __device__ function("julia") is not allowed
Error 4 error : calling a __host__ function("cuComplex::cuComplex") from a __device__ function("cuComplex::operator *") is not allowed
Error 5 error : calling a __host__ function("cuComplex::cuComplex") from a __device__ function("cuComplex::operator +") is not allowed
我很难理解问题所在,因为据我所知,__device__
函数(例如julia
)可以自由调用和创建struct
对象(例如cuComplex
)。这里到底是什么问题?《CUDA By Example》中提供的代码(写于2010年)是否被更近期的CUDA 6.0更新中引入的一些更改破坏了?