Hello everyone,
I am new to this forum, so please let me know if I am posting in the wrong place.
Recently acquired a Digits box with pre-installed software, but the command-line profiler does not seem to be working. For testing purposes, I am trying to profile the following program:
// This is the REAL "hello world" for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string "World!"
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
__global__
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = "Hello
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
// This is the REAL “hello world” for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string “World!”
// By Ingemar Ragnemalm 2010
#include <stdio.h>
const int N = 16;
const int blocksize = 1;
global
void hello(char *a, int *b)
{
a[threadIdx.x] += b[threadIdx.x];
}
int main()
{
char a[N] = “Hello \0\0\0\0\0\0”;
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
";
int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
char *ad;
int *bd;
const int csize = N*sizeof(char);
const int isize = N*sizeof(int);
printf("%s", a);
cudaMalloc( (void**)&ad, csize );
cudaMalloc( (void**)&bd, isize );
cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice );
cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice );
dim3 dimBlock( blocksize, 1 );
dim3 dimGrid( 1, 1 );
hello<<<dimGrid, dimBlock>>>(ad, bd);
cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost );
cudaFree( ad );
cudaFree( bd );
printf("%s\n", a);
return EXIT_SUCCESS;
}
Which I compile as follows:
nvcc -c hello_world.cu
nvcc hello_world.o -o hello_world
I then try to profile it as:
nvprof /home/joost/code/hello_world/hello_world
This command never returns, and after a minute or 5 I kill it, after which it gives me the following output:
^C======== Warning: No CUDA application was profiled, exiting
======== Error: Application received signal 2
When I run the visual profiler (nvvp), the program can be profiled just fine, until I try to debug individual kernels. At that point, the visual profiler seems to be calling the nvprof, and the process never completes.
nvprof gives me the following version information:
~/code/hello_world$ nvprof --version
nvprof: NVIDIA (R) Cuda command line profiler
Copyright (c) 2012 - 2015 NVIDIA Corporation
Release version 7.5.18 (21)
The machine contains 4 GeForce GTX TITAN X.
Major revision number: 5
Minor revision number: 2
Any suggestions what I may be doing wrong, or where I should look for more information?