Scribd
Upload
6 views4 pages

Cuda4 1

The document contains a CUDA C program that performs vector addition of two arrays A and B, storing the result in array C. It allocates memory on the GPU, copies the input arrays to the device, executes the vector addition kernel, and retrieves the result back to the host. Finally, it prints the resulting vector and frees the allocated GPU memory.

Uploaded by

tryhackkme123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views4 pages

Cuda4 1

The document contains a CUDA C program that performs vector addition of two arrays A and B, storing the result in array C. It allocates memory on the GPU, copies the input arrays to the device, executes the vector addition kernel, and retrieves the result back to the host. Finally, it prints the resulting vector and frees the allocated GPU memory.

Uploaded by

tryhackkme123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

// vector_add.

cu

#include <stdio.h>

__global__ void vecAdd(float *A, float *B, float *C, int N) {

int i = blockIdx.x * blockDim.x + threadIdx.x;

if (i < N)

C[i] = A[i] + B[i];

int main() {

int N = 5;
size_t size = N * sizeof(float);

float A[] = {1, 2, 3, 4, 5};

float B[] = {10, 20, 30, 40, 50};

float C[5];

float *d_A, *d_B, *d_C;

cudaMalloc(&d_A, size);

cudaMalloc(&d_B, size);

cudaMalloc(&d_C, size);

cudaMemcpy(d_A, A, size, cudaMemcpyHostToDevice);


cudaMemcpy(d_B, B, size, cudaMemcpyHostToDevice);

vecAdd<<<1, N>>>(d_A, d_B, d_C, N);

cudaMemcpy(C, d_C, size, cudaMemcpyDeviceToHost);

printf("Result Vector C:\n");

for (int i = 0; i < N; i++)

printf("%f ", C[i]);

printf("\n");
cudaFree(d_A);

cudaFree(d_B);

cudaFree(d_C);

return 0;

You might also like