cuda多线程间通信

 #include "cuda_runtime.h"
 #include "device_launch_parameters.h"

 #include <stdio.h>
 #include <time.h>
 #include <stdlib.h>

 #define MAX 120
 #define MIN 0
 cudaError_t addWithCuda(int *c, const int *a, size_t size);

 __global__ void addKernel(int *c, const int *a) {
     int i = threadIdx.x;
     extern __shared__ int smem[];
     smem[i] = a[i];
     __syncthreads();
     if (i == )  // 0号线程做平方和
             {
         c[] = ;
         for (int d = ; d < ; d++) {
             c[] += smem[d] * smem[d];
         }
     }
     if (i == )  //1号线程做累加
             {
         c[] = ;
         for (int d = ; d < ; d++) {
             c[] += smem[d];
         }
     }
     if (i == )  //2号线程做累乘
             {
         c[] = ;
         for (int d = ; d < ; d++) {
             c[] = smem[d];
         }

     }

     if (i == )  //3号线程做异或
                 {
             c[] = ;
             for (int d = ; d < ; d++) {
                 c[] ^= smem[d];
             }

         }
 }

 int main() {
     const int arraySize = ;
     srand((unsigned) time(NULL));
     const int a[arraySize] = { rand() % (MAX +  - MIN) + MIN, rand()
             % (MAX +  - MIN) + MIN, rand() % (MAX +  - MIN) + MIN, rand()
             % (MAX +  - MIN) + MIN, rand() % (MAX +  - MIN) + MIN };
     int c[arraySize] = {  };
     // Add vectors in parallel.
     cudaError_t cudaStatus = addWithCuda(c, a, arraySize);
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "addWithCuda failed!");
         return ;
     }
     printf(
             "\t%d+%d+%d+%d+%d = %d\n\t%d^2+%d^2+%d^2+%d^2+%d^2 = %d\n\t%d*%d*%d*%d*%d = %d\n\t%d^%d^%d^%d^%d = %d\n\n\n\n\n",
             a[], a[], a[], a[], a[], c[], a[], a[], a[], a[], a[],
             c[], a[], a[], a[], a[], a[], c[],a[], a[], a[], a[], a[], c[]);
     // cudaThreadExit must be called before exiting in order for profiling and
     // tracing tools such as Nsight and Visual Profiler to show complete traces.
     cudaStatus = cudaThreadExit();
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "cudaThreadExit failed!");
         return ;
     }
     return ;
 }

 // Helper function for using CUDA to add vectors in parallel.
 cudaError_t addWithCuda(int *c, const int *a, size_t size) {
     int *dev_a = ;
     int *dev_c = ;
     cudaError_t cudaStatus;

     // Choose which GPU to run on, change this on a multi-GPU system.
     cudaStatus = cudaSetDevice();
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr,
                 "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");
         goto Error;
     }

     // Allocate GPU buffers for three vectors (two input, one output)    .
     cudaStatus = cudaMalloc((void**) &dev_c, size * sizeof(int));
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "cudaMalloc failed!");
         goto Error;
     }

     cudaStatus = cudaMalloc((void**) &dev_a, size * sizeof(int));
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "cudaMalloc failed!");
         goto Error;
     }
     // Copy input vectors from host memory to GPU buffers.
     cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int),
             cudaMemcpyHostToDevice);
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "cudaMemcpy failed!");
         goto Error;
     }
     // Launch a kernel on the GPU with one thread for each element.
     addKernel<<<, size, size * sizeof(int), >>>(dev_c, dev_a);

     // cudaThreadSynchronize waits for the kernel to finish, and returns
     // any errors encountered during the launch.
     cudaStatus = cudaThreadSynchronize();
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr,
                 "cudaThreadSynchronize returned error code %d after launching addKernel!\n",
                 cudaStatus);
         goto Error;
     }

     // Copy output vector from GPU buffer to host memory.
     cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int),
             cudaMemcpyDeviceToHost);
     if (cudaStatus != cudaSuccess) {
         fprintf(stderr, "cudaMemcpy failed!");
         goto Error;
     }

     Error: cudaFree(dev_c);
     cudaFree(dev_a);
     return cudaStatus;
 }

22+103+61+63+17 = 266
22^2+103^2+61^2+63^2+17^2 = 19072
22*103*61*63*17 = 17
22^103^61^63^17 = 98