我有一个很简单的问题,但我不明白。我正在使用4.2 cuda。
我有以下代码:
在我的cudaClass.h中:
unsigned char *dev_trimapExpanded;
在我的cudaClass.cpp中:
void cudaClass::expansionTrimap() {
printf("dev_trimapExpanded %d before function \n", dev_trimapExpanded);
//Call cuda function
cudaError_t cudaStatus = expansionTrimapCuda(dev_trimapExpanded, width, height);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "expansionTrimapCuda failed!\n");
}
printf("dev_trimapExpanded %d after function \n", dev_trimapExpanded);
}
在我的文件kernel.cu中,我有:
cudaError_t expansionTrimapCuda(unsigned char *dev_trimapExpanded, size_t width, size_t height)
{
size_t size = width*height;
cudaError_t cudaStatus;
// Choose which GPU to run on, change this on a multi-GPU system.
cudaStatus = cudaSetDevice(0);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaSetDevice failed! Do you have a CUDA-capable GPU installed?");
return cudaStatus;
}
printf("dev_trimapExpanded %d before cudaMalloc \n", dev_trimapExpanded);
cudaStatus = cudaMalloc((void**)&dev_trimapExpanded, size);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc dev_trimapExpanded failed!");
return cudaStatus;
}
printf("dev_trimapExpanded %d after cudaMalloc \n", dev_trimapExpanded);
return cudaStatus;
}
输出为:
dev_trimapExpanded 0 before function
dev_trimapExpanded 0 before cudaMalloc
dev_trimapExpanded 93323264 after cudaMalloc
dev_trimapExpanded 0 after function
我的指针的地址在cudaMalloc调用之前是0,这是正常的,但是我不明白为什么在函数之后地址是0。指针dev_trimapExpanded的地址不应更改。 cudaMalloc的作用域仅在函数中吗?内存也不是免费的。如何跟踪不同内核调用之间的全局内存?
最佳答案
这种行为是绝对正确的,您的问题是,在调用函数时,您是按“按值”传递指针,而不是按“按引用”传递指针。所以现在发生的是,当函数被称为youre指针被复制时,副本的值在函数内部被更改,但是当函数完成后,旧指针完全不受影响(因为所有更改仅发生在副本)。
尝试使用此方法代替函数头:
cudaError_t expansionTrimapCuda(unsigned char *& dev_trimapExpanded, ... )
另请参阅:Pointer to Pointer / Reference to Pointer
关于c++ - cuda内存分配cudaMalloc,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/12738711/