i am new to cuda…i am working in WINDOWS XP…i dont have graphic card…the following program i complie in the emulation mode…
example1:
#include “stdafx.h”
#include <stdio.h>
#include <cuda.h>
// Kernel that executes on the CUDA device
global void square_array(float *a, int N)
{
int idx = blockIdx.x * blockDim.x + threadIdx.x;
if (idx<N) a[idx] = a[idx] * a[idx];
}
// main routine that executes on the host
int main(void)
{
float *a_h, *a_d; // Pointer to host & device arrays
const int N = 10; // Number of elements in arrays
size_t size = N * sizeof(float);
a_h = (float *)malloc(size); // Allocate array on host
cudaMalloc((void **) &a_d, size); // Allocate array on device
// Initialize host array and copy it to CUDA device
for (int i=0; i<N; i++) a_h[i] = (float)i;
cudaMemcpy(a_d, a_h, size, cudaMemcpyHostToDevice);
// Do calculation on device:
int block_size = 4;
int n_blocks = N/block_size + (N%block_size == 0 ? 0:1);
square_array <<< n_blocks, block_size >>> (a_d, N);
// Retrieve result from device and store it in host array
cudaMemcpy(a_h, a_d, sizeof(float)*N, cudaMemcpyDeviceToHost);
// Print results
for (int i=0; i<N; i++) printf("%d %f\n", i, a_h[i]);
// Cleanup
free(a_h); cudaFree(a_d);
}
After compling program. I have the following problem:
------ Build started: Project: example1, Configuration: Debug Win32 ------
Linking…
LINK : fatal error LNK1181: cannot open input file ‘cutil32D.lib’
Build log was saved at “file://c:\Documents and Settings\srividhya.y\My Documents\example\example1\example1\Debug\BuildLog.htm”
example1 - 1 error(s), 0 warning(s)
========== Build: 0 succeeded, 1 failed, 0 up-to-date, 0 skipped ==========
What else do I need to do… please suggest me quickly…