好的,这就是问题所在:使用 CUDA 1.1 计算 gpu,我试图为每个线程维护一组(可能数量不同,这里固定为 4 个)索引,这是我作为 struct var 成员保留的引用。我的问题是在访问成员数组时获取对结构的引用会导致不正确的结果:我用 0 初始化成员数组值,当我使用原始结构 var 读取数组 vals 时,我得到正确的值 (0) ,但是当我使用对 struct var 的引用阅读它时,我得到了垃圾(-8193)。即使使用类而不是结构也会发生这种情况。
为什么tmp低于!= 0 ??
c++ 不是我的主要语言,所以这可能是一个概念问题,或者它可能是在 cuda 中工作的一个怪癖
struct DataIdx {
int numFeats;
int* featIdx;
};
extern __shared__ int sharedData[];
__global__ void myFn(){
int tidx = blockIdx.x * blockDim.x + threadIdx.x;
DataIdx myIdx; //instantiate the struct var in the context of the current thread
myIdx.numFeats = 4;
size_t idxArraySize = sizeof(int)*4;
//get a reference to my array for this thread. Parallel Nsight debugger shows myIdx.featIdx address = 0x0000000000000000e0
myIdx.featIdx = (int*)(&sharedData[tidx*idxArraySize]);
myIdx.featIdx[0] = 0x0; //set first value to 0
int tmp = myIdx.featIdx[0]; // tmp is correctly eq to 0 in Nsight debugger -- As Expected!!
tmp = 2*tmp; antIdx.featIdx[0] = tmp; //ensure compiler doesn't elide out tmp
DataIdx *tmpIdx = &myIdx; //create a reference to my struct var
tmp = tmpIdx.featIdx[0]; // expected 0, but tmp = -8193 in debugger !! why? debugger shows address of tmpIdx.featIdx = __devicea__ address=8
tmpIdx.featIdx[0] = 0x0;
tmp = tmpIdx.featIdx[0]; // tmp = -1; cant even read what we just set
//forcing the same reference as myIdx.featIdx, still gives a problem! debugger shows address of tmpIdx.featIdx = __devicea__ address=8
tmpIdx->featIdx = (int*)(&sharedData[tidx*idxArraySize]);
tmp = tmpIdx.featIdx[0]; //tmp = -8193!! why != 0?
DataIdx tmpIdxAlias = myIdx;
tmp = tmpIdx.featIdx[0]; //aliasing the original var gives correct results, tmp=0
myIdx.featIdx[0] = 0x0;
mySubfn(&myIdx); //this is a problem because it happens when passing the struct by reference to subfns
mySubfn2(myIdx);
}
__device__ mySubfn(struct DataIdx *myIdx){
int tmp = myIdx->featIdx[0]; //tmp == -8193!! should be 0
}
__device__ mySubfn2(struct DataIdx &myIdx){
int tmp = myIdx.featIdx[0]; //tmp == -8193!! should be 0
}