Skip to content

Instantly share code, notes, and snippets.

/-
Created Sep 7, 2016

Embed
What would you like to do?
#include <iostream>
__global__ void axpy(float a, float* x, float* y) {
y[threadIdx.x] = a * x[threadIdx.x];
}
int main(int argc, char* argv[]) {
const int kDataLen = 4;
float a = 2.0f;
float host_x[kDataLen] = {1.0f, 2.0f, 3.0f, 4.0f};
float host_y[kDataLen];
// Copy input data to device.
float* device_x;
float* device_y;
cudaMalloc(&device_x, kDataLen * sizeof(float));
cudaMalloc(&device_y, kDataLen * sizeof(float));
cudaMemcpy(device_x, host_x, kDataLen * sizeof(float),
cudaMemcpyHostToDevice);
// Launch the kernel.
axpy<<<1, kDataLen>>>(a, device_x, device_y);
// Copy output data to host.
cudaDeviceSynchronize();
cudaMemcpy(host_y, device_y, kDataLen * sizeof(float),
cudaMemcpyDeviceToHost);
// Print the results.
for (int i = 0; i < kDataLen; ++i) {
std::cout << "y[" << i << "] = " << host_y[i] << "\n";
}
cudaDeviceReset();
return 0;
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.