Question

I have copied a hello world program in cuda using this site http://code.google.com/p/stanford-cs193g-sp2010/wiki/TutorialHelloWorld

The code is

#include "util/cuPrintf.cu"
#include <stdio.h>

__global__ void device_greetings(void)
{
  cuPrintf("Hello, world from the device!\n");
}

int main(void)
{
  // greet from the host
  printf("Hello, world from the host!\n");

  // initialize cuPrintf
  cudaPrintfInit();

  // launch a kernel with a single thread to greet from the device
  device_greetings<<<1,1>>>();

  // display the device's greeting
  cudaPrintfDisplay();

  // clean up after cuPrintf
  cudaPrintfEnd();

  return 0;
}

Then compiled using nvcc hello_world.cu -o hello_world however I only see the hello fom host and not the device.

I even tried

printf("{CudaPrintfInt => %s}\n",cudaGetErrorString(cudaPrintfInit()));
printf("{cudaPrintfDisplay => %s}\n",cudaGetErrorString(cudaPrintfDisplay(stdout, true)));

and compiled with nvcc -arch=sm_11 hello_world.cu -o hello_world, However I get:

$ ./hello_world
Hello, world from the host!
{CudaPrintfInt => initialization error}
{cudaPrintfDisplay => __global__ function call is not configured}
$

The graphic model is :

$/sbin/lspci -v | grep VGA
07:01.0 VGA compatible controller: Matrox Graphics, Inc. MGA G200eW WPCM450 (rev 0a) (prog-if 00 [VGA controller])

and the cuda version is 4:

$ ls /usr/local/cuda/lib/
libcublas.so         libcudart.so.4.0.17  libcurand.so.4         libnpp.so
libcublas.so.4       libcufft.so          libcurand.so.4.0.17    libnpp.so.4
libcublas.so.4.0.17  libcufft.so.4        libcusparse.so         libnpp.so.4.0.17
libcudart.so         libcufft.so.4.0.17   libcusparse.so.4
libcudart.so.4       libcurand.so         libcusparse.so.4.0.17

Answer 1

“If you are on a CC 2.0 GPU, you don’t need cuPrintf at all — CUDA has printf built-in for CC-2.0 and higher GPUs. So just replace your call to cuPrintf for the actual prinft” (source)

Put you code this way just to check what is causing this problem.

#include <cuda_runtime.h>
#include "util/cuPrintf.cu"
#include <stdio.h>
__global__ void device_greetings(void)
{
  cuPrintf("Hello, world from the device!\n");
}

  int main(void)
  {
  // greet from the host
  printf("Hello, world from the host!\n");

  // initialize cuPrintf
  printf("{CudaPrintfInt => %s}\n",cudaGetErrorString(cudaPrintfInit()));

  // launch a kernel with a single thread to greet from the device
  device_greetings<<<1,1>>>();

  // display the device's greeting
  printf("{cudaPrintfDisplay => %s}\n",cudaGetErrorString(cudaPrintfDisplay()));

  // clean up after cuPrintf
  cudaPrintfEnd();

  return 0;
}

Here say that happen because :
“The device function being invoked (usually via cudaLaunch()) was not previously configured via the cudaConfigureCall() function.”