CUDA_BIN_PATH　　%CUDA_PATH%\bin
CUDA_LIB_PATH　　%CUDA_PATH%\lib\Win32
CUDA_SDK_BIN　　%CUDA_SDK_PATH%\bin\Win32
CUDA_SDK_LIB　　%CUDA_SDK_PATH%\common\lib\Win32
CUDA_SDK_PATH　　C:\cuda\cudasdk\common

#include "cuda_runtime.h"
#include "device_launch_parameters.h"#include <stdio.h>cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);__global__ void addKernel(int *c, const int *a, const int *b)
{int i = threadIdx.x;c[i] = a[i] + b[i];
}int main()
{const int arraySize = 5;const int a[arraySize] = { 1, 2, 3, 4, 5 };const int b[arraySize] = { 10, 20, 30, 40, 50 };int c[arraySize] = { 0 };// Add vectors in parallel.cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);if (cudaStatus != cudaSuccess) {fprintf(stderr, "addWithCuda failed!");return 1;}printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",c[0], c[1], c[2], c[3], c[4]);// cudaDeviceReset must be called before exiting in order for profiling and// tracing tools such as Nsight and Visual Profiler to show complete traces.cudaStatus = cudaDeviceReset();if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaDeviceReset failed!");return 1;}getchar();return 0;
}// Helper function for using CUDA to add vectors in parallel.
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{int *dev_a = 0;int *dev_b = 0;int *dev_c = 0;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?");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;}cudaStatus = cudaMalloc((void**)&dev_b, 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;}cudaStatus = cudaMemcpy(dev_b, b, 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<<<1, size>>>(dev_c, dev_a, dev_b);// Check for any errors launching the kernelcudaStatus = cudaGetLastError();if (cudaStatus != cudaSuccess) {fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));goto Error;}// cudaDeviceSynchronize waits for the kernel to finish, and returns// any errors encountered during the launch.cudaStatus = cudaDeviceSynchronize();if (cudaStatus != cudaSuccess) {fprintf(stderr, "cudaDeviceSynchronize 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);cudaFree(dev_b);return cudaStatus;
}

#include <stdio.h>
#include <stdlib.h>
#include <cuda_runtime.h> #define DATA_SIZE 1024
#define checkCudaErrors(err)  __checkCudaErrors (err, __FILE__, __LINE__)
#define getLastCudaError(msg)  __getLastCudaError (msg, __FILE__, __LINE__)int data[DATA_SIZE];////
// These are CUDA Helper functions// This will output the proper CUDA error strings in the event that a CUDA host call returns an error
inline void __checkCudaErrors(cudaError err, const char *file, const int line )
{if(cudaSuccess != err){fprintf(stderr, "%s(%i) : CUDA Runtime API error %d: %s.\n",file, line, (int)err, cudaGetErrorString( err ) );return ;        }
}// This will output the proper error string when calling cudaGetLastError
inline void __getLastCudaError(const char *errorMessage, const char *file, const int line )
{cudaError_t err = cudaGetLastError();if (cudaSuccess != err){fprintf(stderr, "%s(%i) : getLastCudaError() CUDA error : %s : (%d) %s.\n",file, line, errorMessage, (int)err, cudaGetErrorString( err ) );return ;}
}// end of CUDA Helper Functions

__global__ static void sumOfSquares(int *num, int * result){int sum=0;int i;for(i=0;i<DATA_SIZE;i++) {sum += num[i]*num[i];}*result = sum;
}
void GenerateNumbers(int *number, int size){for(int i = 0; i < size; i++) {number[i] = rand() % 10;printf("number[%d] is %d\n",i,number[i]);}}int main(){cudaSetDevice(0);cudaDeviceSynchronize();cudaThreadSynchronize();GenerateNumbers(data, DATA_SIZE);int * gpudata, * result;int sum;checkCudaErrors( cudaMalloc((void**) &gpudata, sizeof(int)*DATA_SIZE));checkCudaErrors(cudaMalloc((void**) &result, sizeof(int)));checkCudaErrors(cudaMemcpy(gpudata, data, sizeof(int)*DATA_SIZE,cudaMemcpyHostToDevice));sumOfSquares<<<1, 1, 0>>>(gpudata, result);checkCudaErrors(cudaMemcpy(&sum, result, sizeof(int), cudaMemcpyDeviceToHost));cudaFree(gpudata);cudaFree(result);printf("-----------sum: %d\n",sum);sum = 0;for(int i = 0; i < DATA_SIZE; i++) {sum += data[i] * data[i];}printf("sum (CPU): %d\n", sum);getchar();return 0;
}