Question

下面是一些在C / CUDA中完成的代码，但由于某些原因，某些错误似乎阻止了该程序的编译和运行。不确定如何修复这些错误，尝试更改转换，并多次校对整个代码。在C中编码并不是很好，并且看起来这个错误在通过在线搜索问题是非常具体的。任何见解或帮助将不胜感激。

#include <cstdlib>
#include <stdio.h>
#include <limits.h>

using namespace std;

const int NUMTHREADS = 1024; 

// Number of vertices in the graph
#define V 9

// A utility function to find the vertex with minimum distance value, from
// the set of vertices not yet included in shortest path tree
int minDistance(int dist[], bool sptSet[]) {
// Initialize min value
int min = INT_MAX, min_index;

for (int v = 0; v < V; v++)
 if (sptSet[v] == false && dist[v] <= min)
     min = dist[v], min_index = v;

return min_index;
}

// A utility function to print the constructed distance array
int printSolution(int dist[], int n) {
printf("Vertex   Distance from Source\n");
for (int i = 0; i < V; i++)
printf("%d \t\t %d\n", i, dist[i]);
}//end of method

// Funtion that implements Dijkstra's single source shortest path algorithm
// for a graph represented using adjacency matrix representation

__global__ void updateDistance(bool* sptSet[],int* graph[],int* dist[],int u,int V){

Int i = threadIdx.x

if(i<V){
if((!sptSet[i] && *graph[u*V+i] && dist[u] != INT_MAX && *dist[u]+graph[u*V+i] <   *dist[i]))
*dist[i] = *dist[u] + *graph[u*V+i];
}
}//end of method

long* generateAdjMatrix(int count){

long* randoMatrix = (long*)malloc(count*count*sizeof(long));
int i,j;

srand(time(NULL));

for(i=0;i<count;i++){
for(j=0;j<count;j++){
if(i != j){
Long randomResult = rand()%2;
randoMatrix[(i*count)+j] = randomResult;
randoMatrix[(j*count)+i] = randomResult;
}
 }
}   
Return randoMatrix;
}//end of method

// driver program to test above function
int main() {

//gpu
int *d_dist[V];
int *d_graph[V];
bool *d_sptSet[V];


int src = 0;
long* matrix;

 int *dist[V];     // The output array.  dist[i] will hold the shortest
                  // distance from src to i

 bool* sptSet = (bool)malloc(V*sizeof(bool));
int* graph = (int *)malloc(V*sizeof(int));
int* dist = (int *)malloc(V*sizeof(int));

Matrix = generateAdjMatrix(V); 

 // Initialize all distances as INFINITE and stpSet[] as false
 for (int i = 0; i < V; i++)
    dist[i] = INT_MAX, sptSet[i] = false;

 // Distance of source vertex from itself is always 0
 dist[src] = 0;


//allocate GPU variables in memory
cudaMalloc(&d_sptSet,(V*sizeof(bool)));
cudaMalloc(&d_dist,(V*sizeof(int)));
cudaMalloc(&d_graph,(V*sizeof(int)));

 // Find shortest path for all vertices
 for (int count = 0; count < V-1; count++) {
   // Pick the minimum distance vertex from the set of vertices not
   // yet processed. u is always equal to src in first iteration.
   int u = minDistance(dist, sptSet);

   // Mark the picked vertex as processed
   sptSet[u] = true;


//after updating distance, copy the updates to GPU
cudaMemcpy(d_sptSet,sptSet,V*sizeof(bool),cudaMemcpyHostToDevice);
cudaMemcpy(d_dist,dist,V*sizeof(int),cudaMemcpyHostToDevice);
cudaMemcpy(d_graph,graph,V*sizeof(int),cudaMemcpyHostToDevice);

  //call updatedistance
updateDistance<<<V,NUMTHREADS>>>(d_sptSet,d_graph,d_dist,u,V);

cudaMemcpy(dist,d_dist,V*sizeof(int),cudaMemcpyDeviceToHost);
cudaMemcpy(sptSet,d_sptSet,V*sizeof(int),cudaMemcpyDeviceToHost);
 }//end of for

 // print the constructed distance array
 printSolution(dist, V);


return 0;
}//end of main

我得到的错误是：

-expected a＆＃34;）＆＃34;第39行

- 没有重载函数的实例＆＃34; cudaMalloc＆＃34;匹配参数（第119行）（120行和121行相同）

- 从第119-121行开始，它还说＆＃34;参数类型是：int（）[9，unsigned long＆＃34;

Answer 1

同意Talonmies和Regis。

此外，除了这个错字之外，您还有其他类型的错误行40，并且您的updateDistance与多个块的工作分布不一定表现良好，因为您所有的块都处理相同的数据。

最后，您没有为缓冲区分配足够的内存（V条目，在您的情况下，在合并位置的所有1024个线程都可以访问9条）。

我相信您可能希望深入了解编程指南，也许是一个全面的教程。

没有重载函数错误的实例

1 个答案: