when I want to debug program with nsight this message show: "Value cannot be null. Parameter name: pSrcNativeVariant". when i rebuild project this error not shown. but i must perform this action repeatedly for debug program. previously this action Not required.
this is my code:
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#include <iostream>
using namespace std;
#define COLUMNS 3
#define ROWS 2
__global__ void add(int *a, int *b, int *c)
{
*a=345678;
int x = blockIdx.x;
int y = blockIdx.y;
int i = (COLUMNS*y) + x;
c[i] = a[i] + b[i];
}
int main()
{
int a[ROWS][COLUMNS], b[ROWS][COLUMNS], c[ROWS][COLUMNS];
int *dev_a, *dev_b, *dev_c;
int *x;
int r;
x=&r;
cudaMalloc((void **) &dev_a, ROWS*COLUMNS*sizeof(int));
cudaMalloc((void **) &dev_b, ROWS*COLUMNS*sizeof(int));
cudaMalloc((void **) &dev_c, ROWS*COLUMNS*sizeof(int));
for (int y = 0; y < ROWS; y++) // Fill Arrays
for (int x = 0; x < COLUMNS; x++)
{
a[y][x] = x;
b[y][x] = y;
}
cudaMemcpy(dev_a, a, ROWS*COLUMNS*sizeof(int),
cudaMemcpyHostToDevice);
cudaMemcpy(dev_b, b, ROWS*COLUMNS*sizeof(int),
cudaMemcpyHostToDevice);
dim3 grid(COLUMNS,ROWS);
add<<<grid,1>>>(dev_a, dev_b, dev_c);
cudaMemcpy(c, dev_c, ROWS*COLUMNS*sizeof(int),
cudaMemcpyDeviceToHost);
for (int y = 0; y < ROWS; y++) // Output Arrays
{
for (int x = 0; x < COLUMNS; x++)
{
printf("[%d][%d]=%d ",y,x,c[y][x]);
}
printf("\n");
}
return 0;
}
I encountered exactly the same problem. After trying many things, I found this problem could be simply solved by just running the visual studio in the administration mode once. Under the admin mode, run the nsight debugger, then the problem is solved. Admin mode is not required later. At least this works for me, good luck to you.
Added on May 12, 2014:
This problem happened again today. This time I solved it by switching the platform from Win32 to X64 then switch back
Added on May 22, 2014:
It happens again and everything I tried before did not work this time. Finally it is solved in this way:
I fixed this by deleting the visual studio solution user options file (.suo).
NuGet Package restore failed for project Miscellaneous Files: Value cannot be null or an empty string. Parameter name: root. 0 0
It is a problem with the NuGet package.
Solution:
Update it if it is out-of-date(restart).
Uninstall and reinstall(restart).
Open the "Package Manager Console", which is under "Tools/NuGet Package Manager/Package Manager Console", type any command to make sure it works.
The problem should be solved.
Related
I am trying to run a c program using cuda the code does some math operations on an array of consecutive numbers (where every thread add elements of a row and check the last array element and return a value of the sum or zero if the conditions are met).
I don't have NVIDIA GPU so I wrote my code on google colab notebook.
The problem that I have encountered was not being able to debug the program. It outputs nothing at all no error messages and no output.
There's something wrong with the code but I cannot know where after reviewing it a few times.
Here's the code:
#include <iostream>
__global__ void matrixadd(int *l,int *result,int digits ,int possible_ids )
{
int sum=0;
int zeroflag=1;
int identicalflag=1;
int id= blockIdx .x * blockDim .x + threadIdx .x;
if(id<possible_ids)
{
if (l[(digits*id)+digits-1]==0) zeroflag=0;/*checking if the first number is zero*/
for(int i=0; i< digits-1;i++)/*edited:for(int i=0; i< digits;i++) */
{
if(l[(digits*id)+i]-l[(digits*id)+i+1]==0)
identicalflag+=1; /* checking if 2 consequitive numbers are identical*/
sum = sum + l[(digits*id)+i]; /* finding the sum*/
}
if (identicalflag!=1)identicalflag=0;
result[id]=sum*zeroflag*identicalflag;
}
}
int main()
{
int digits=6;
int possible_ids=pow(10,digits);
/*populate the array */
int* a ;
a= (int *)malloc((possible_ids * digits) * sizeof(int));
int the_id,temp=possible_ids;
for (int i = 0; i < possible_ids; i++)
{
temp--;
the_id=temp;
for (int j = 0; j < digits; j++)
{
a[i * digits + j] = the_id % 10;
if(the_id !=0) the_id /= 10;
}
}
/*the numbers will appear in reversed order */
/*allocate memory on host and device then invoke the kernel function*/
int *d_a,*d_c,*c;
int size=possible_ids * digits;
c= (int *)malloc(possible_ids * sizeof(int));/*results matrix*/
cudaMalloc((void **)&d_a,size*sizeof(int));
cudaMemcpy(d_a,a,size*sizeof(int),cudaMemcpyHostToDevice);
cudaMalloc((void **)&d_c,possible_ids*sizeof(int));
/*EDITED: cudaMalloc((void **)&d_c,digits*sizeof(int));*/
matrixadd<<<ceil(possible_ids/1024.0),1024>>>(d_a,d_c,digits,possible_ids);
cudaMemcpy(c,d_c,possible_ids*sizeof(int),cudaMemcpyDeviceToHost);
int acc=0;
for (int k=0;k<possible_ids;k++)
{
if (c[k]==7||c[k]==17||c[k]==11||c[k]==15)continue;
acc += c[k];
}
printf("The number of possible ids %d",acc);
}
You are doing invalid indexing into the l array in this line of code: if(l[(digits*id)+i]-l[(digits*id)+i+1]==0)
From comment by Robert Covella
If you are using python code, you can use 'pdb' built-in breakpoint function. put the following line of command at the top of your script.
import pdb
then before the line, you want to debug put the following command
pdb.set_trace()
you will get '(Pdb), then empty box' to insert the command. If you want to continue to the next line put 'n' or you can use 's' to see the detailed work of your current line command.
Suppose you are interested in debugging python code. Enjoy it!
I've got an error, regarding calling JacobiSVD in my cuda function.
This is the part of the code that causing the error.
Eigen::JacobiSVD<Eigen::Matrix3d> svd( cov_e, Eigen::ComputeThinU | Eigen::ComputeThinV);
And this is the error message.
CUDA_voxel_building.cu(43): error: calling a __host__
function("Eigen::JacobiSVD , (int)2> ::JacobiSVD") from a __global__
function("kernel") is not allowed
I've used the following command to compile it.
nvcc -std=c++11 -D_MWAITXINTRIN_H_INCLUDED -D__STRICT_ANSI__ -ptx CUDA_voxel_building.cu
I'm using code 8.0 with eigen3 on ubuntu 16.04.
It seems like other functions such as eigen value decomposition also gives the same error.
Anyone knows a solution? I'm enclosing my code below.
//nvcc -ptx CUDA_voxel_building.cu
#include </usr/include/eigen3/Eigen/Core>
#include </usr/include/eigen3/Eigen/SVD>
/*
#include </usr/include/eigen3/Eigen/Sparse>
#include </usr/include/eigen3/Eigen/Dense>
#include </usr/include/eigen3/Eigen/Eigenvalues>
*/
__global__ void kernel(double *p, double *breaks,double *ind, double *mu, double *cov, double *e,double *v, int *n, char *isgood, int minpts, int maxgpu){
bool debuginfo = false;
int idx = threadIdx.x + blockIdx.x * blockDim.x;
if(debuginfo)printf("Thread %d got pointer\n",idx);
if( idx < maxgpu){
int s_ind = breaks[idx];
int e_ind = breaks[idx+1];
int diff = e_ind-s_ind;
if(diff >minpts){
int cnt = 0;
Eigen::MatrixXd local_p(3,diff) ;
for(int k = s_ind;k<e_ind;k++){
int temp_ind=ind[k];
//Eigen::Matrix<double, 3, diff> local_p;
local_p(1,cnt) = p[temp_ind*3];
local_p(2,cnt) = p[temp_ind*3+1];
local_p(3,cnt) = p[temp_ind*3+2];
cnt++;
}
Eigen::Matrix3d centered = local_p.rowwise() - local_p.colwise().mean();
Eigen::Matrix3d cov_e = (centered.adjoint() * centered) / double(local_p.rows() - 1);
Eigen::JacobiSVD<Eigen::Matrix3d> svd( cov_e, Eigen::ComputeThinU | Eigen::ComputeThinV);
/* Eigen::Matrix3d Cp = svd.matrixU() * svd.singularValues().asDiagonal() * svd.matrixV().transpose();
mu[idx]=p[ind[s_ind]*3];
mu[idx+1]=p[ind[s_ind+1]*3];
mu[idx+2]=p[ind[s_ind+2]*3];
e[idx]=svd.singularValues()(0);
e[idx+1]=svd.singularValues()(1);
e[idx+2]=svd.singularValues()(2);
n[idx] = diff;
isgood[idx] = 1;
for(int x = 0; x < 3; x++)
{
for(int y = 0; y < 3; y++)
{
v[x+ 3*y +idx*9]=svd.matrixV()(x, y);
cov[x+ 3*y +idx*9]=cov_e(x, y);
//if(debuginfo)printf("%f ",R[x+ 3*y +i*9]);
if(debuginfo)printf("%f ",Rm(x, y));
}
}
*/
} else {
mu[idx]=0;
mu[idx+1]=0;
mu[idx+2]=0;
e[idx]=0;
e[idx+1]=0;
e[idx+2]=0;
n[idx] = 0;
isgood[idx] = 0;
for(int x = 0; x < 3; x++)
{
for(int y = 0; y < 3; y++)
{
v[x+ 3*y +idx*9]=0;
cov[x+ 3*y +idx*9]=0;
}
}
}
}
}
First of all, Ubuntu 16.04 provides Eigen 3.3-beta1, which is not really recommended to be used. I would suggest upgrading to a more recent version. Furthermore, to include Eigen, write (e.g.):
#include <Eigen/Eigenvalues>
and compile with -I /usr/include/eigen3 (if you use the version provided by the OS), or better -I /path/to/local/eigen-version.
Then, as talonmies noted, you can't call host-functions from kernels, (I'm not sure at the moment, why JacobiSVD is not marked as device function), but in your case it would make much more sense to use Eigen::SelfAdjointEigenSolver, anyway. Since the matrix you are decomposing is fixed-size 3x3 you should actually use the optimized computeDirect method:
Eigen::SelfAdjointEigenSolver<Eigen::Matrix3d> eig; // default constructor
eig.computeDirect(cov_e); // works for 2x2 and 3x3 matrices, does not require loops
It seems the computeDirect even works on the beta version provided by Ubuntu (I'd still recommend to update).
Some unrelated notes:
The following is wrong, since you should start with index 0:
local_p(1,cnt) = p[temp_ind*3];
local_p(2,cnt) = p[temp_ind*3+1];
local_p(3,cnt) = p[temp_ind*3+2];
Also, you can write this in one line:
local_p.col(cnt) = Eigen::Vector3d::Map(p+temp_ind*3);
This line will not fit (unless diff==3):
Eigen::Matrix3d centered = local_p.rowwise() - local_p.colwise().mean();
What you probably mean is (local_p is actually 3xn not nx3)
Eigen::Matrix<double, 3, Eigen::Dynamic> centered = local_p.colwise() - local_p.rowwise().mean();
And when computing cov_e you need to .adjoint() the second factor, not the first.
You can avoid both 'big' matrices local_p and centered, by directly accumulating Eigen::Matrix3d sum2 and Eigen::Vector3d sum with sum2 += v*v.adjoint() and sum +=v and computing
Eigen::Vector3d mu = sum / diff;
Eigen::Matrix3d cov_e = (sum2 - mu*mu.adjoint()*diff)/(diff-1);
I want to compile an easy openacc sample (it was attached) , it was correctly compiled but when i run it got an error :
compile with : gcc-5 -fopenacc accVetAdd.c -lm
run with : ./a.out
got error in runtime
error: libgomp: while loading libgomp-plugin-host_nonshm.so.1: libgomp-plugin-host_nonshm.so.1: cannot open shared object file: No such file or directory
I google it and find only one page! then i ask how to fix this problem?
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
int main(int argc, char* argv[])
{
// Size of vectors
int n = 10000;
// Input vectors
double *restrict a;
double *restrict b;
// Output vector
double *restrict c;
// Size, in bytes, of each vector
size_t bytes = n*sizeof(double);
// Allocate memory for each vector
a = (double*)malloc(bytes);
b = (double*)malloc(bytes);
c = (double*)malloc(bytes);
// Initialize content of input vectors, vector a[i] = sin(i)^2 vector b[i] = cos(i)^2
int i;
for (i = 0; i<n; i++) {
a[i] = sin(i)*sin(i);
b[i] = cos(i)*cos(i);
}
// sum component wise and save result into vector c
#pragma acc kernels copyin(a[0:n],b[0:n]), copyout(c[0:n])
for (i = 0; i<n; i++) {
c[i] = a[i] + b[i];
}
// Sum up vector c and print result divided by n, this should equal 1 within error
double sum = 0.0;
for (i = 0; i<n; i++) {
sum += c[i];
}
sum = sum / n;
printf("final result: %f\n", sum);
// Release memory
free(a);
free(b);
free(c);
return 0;
}
libgomp dynamically loads shared object files for the plugins it supports, such as the one implementing the host_nonshm device. If they're installed in a non-standard directory (that is, not in the system's default search path), you need to tell the dynamic linker where to look for these shared object files: either compile with -Wl,-rpath,[...], or set the LD_LIBRARY_PATH environment variable.
Using visual studios 2010. Win 7. Nsight 2.1
#include "cuda.h"
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
// incrementArray.cu
#include <stdio.h>
#include <assert.h>
void incrementArrayOnHost(float *a, int N)
{
int i;
for (i=0; i < N; i++) a[i] = a[i]+1.f;
}
__global__ void incrementArrayOnDevice(float *a, int N)
{
int idx = blockIdx.x*blockDim.x + threadIdx.x;
int j = idx;
int i = 2;
i = i+j; //->breakpoint here
if (idx<N) a[idx] = a[idx]+1.f; //->breakpoint here
}
int main(void)
{
float *a_h, *b_h; // pointers to host memory
float *a_d; // pointer to device memory
int i, N = 10;
size_t size = N*sizeof(float);
// allocate arrays on host
a_h = (float *)malloc(size);
b_h = (float *)malloc(size);
// allocate array on device
cudaMalloc((void **) &a_d, size);
// initialization of host data
for (i=0; i<N; i++) a_h[i] = (float)i;
// copy data from host to device
cudaMemcpy(a_d, a_h, sizeof(float)*N, cudaMemcpyHostToDevice);
// do calculation on host
incrementArrayOnHost(a_h, N);
// do calculation on device:
// Part 1 of 2. Compute execution configuration
int blockSize = 4;
int nBlocks = N/blockSize + (N%blockSize == 0?0:1);
// Part 2 of 2. Call incrementArrayOnDevice kernel
incrementArrayOnDevice <<< nBlocks, blockSize >>> (a_d, N);
// Retrieve result from device and store in b_h
cudaMemcpy(b_h, a_d, sizeof(float)*N, cudaMemcpyDeviceToHost);
// check results
for (i=0; i<N; i++) assert(a_h[i] == b_h[i]);
// cleanup
free(a_h); free(b_h); cudaFree(a_d);
return 0;
}
I've tried inserting breakpoints as listed above inside my global void incrementArrayOnDevice(float *a, int N) but they're not hitting.
When I run debug (f5) in visual studios, I tried to step into incrementArrayOnDevice <<< nBlocks, blockSize >>> (a_d, N); but they would skip the entire kernel code section.
tried to add a watch on the variables i and j but there was an error "CXX0017: Error: symbol "i" not found."
Is this issue normal? Can someone please try on their pc and let me know if they can hit the breakpoints? If you can, what possible problem could mine be? Please help! :(
Nsight debugging is different from VS debugging . You need to use Nsight debugging to hit the kernel breakpoints. However, for this you need 2 GPU cards. Do you have 2 cards in the first place? Please check
You can debug on a single GPU but on the following conditions:
You have to be using 5.0 toolkit
You have to be programming on a GPU that suports 303.xx NForceWare or higher
Need Help.I'm stuck at a problem when running a C++ code on Windows- Visual Studio.
When I run that code in Linux environment, there is no restriction on the memory I am able to allocate dynamically(till the size available in RAM).
But on VS Compiler, it does not let me create an array beyond a limited size.
I've tried /F option and 20-25 of google links to increase memory size but they dont seem to help much.
I am currently able to assign only around 100mb out of 3gb available.
If there is a solution for this in Windows and not in Visual Studio's compiler, I will be glad to hear that as I have a CUDA TeslaC2070 card which is proving to be pretty useless on Windows as I wanted to run my CUDA/C++ code on Windows environment.
Here's my code. it fails when LENGTH>128(no of images 640x480pngs. less than 0.5mb each. I've also calculated the approximate memory size it takes by counting data structures and types used in OpenCV and by me but still it is very less than 2gb). stackoverflow exception. Same with dynamic allocation. I've already maximized the heap and stack sizes.
#include "stdafx.h"
#include <cv.h>
#include <cxcore.h>
#include <highgui.h>
#include <cuda.h>
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#define LENGTH 100
#define SIZE1 640
#define SIZE2 480
#include <iostream>
using namespace std;
__global__ void square_array(double *img1_d, long N)
{
int idx = blockIdx.x * blockDim.x + threadIdx.x;
img1_d[idx]= 255.0-img1_d[idx];
}
int _tmain(int argc, _TCHAR* argv[])
{
IplImage *img1[LENGTH];
// Open the file.
for(int i=0;i<LENGTH;i++)
{ img1[i] = cvLoadImage("abstract3.jpg");}
CvMat *mat1[LENGTH];
for(int i=0;i<LENGTH;i++)
{
mat1[i] = cvCreateMat(img1[i]->height,img1[i]->width,CV_32FC3 );
cvConvert( img1[i], mat1[i] );
}
double a[LENGTH][2*SIZE1][SIZE2][3];
for(int m=0;m<LENGTH;m++)
{
for(int i=0;i<SIZE1;i++)
{
for(int j=0;j<SIZE2;j++)
{
CvScalar scal = cvGet2D( mat1[m],j,i);
a[m][i][j][0] = scal.val[0];
a[m][i][j][1] = scal.val[1];
a[m][i][j][2] = scal.val[2];
a[m][i+SIZE1][j][0] = scal.val[0];
a[m][i+SIZE1][j][1] = scal.val[1];
a[m][i+SIZE1][j][2] = scal.val[2];
}
} }
//cuda
double *a_d;
int N=LENGTH*2*SIZE1*SIZE2*3;
cudaMalloc((void **) &a_d, N*sizeof(double));
cudaMemcpy(a_d, a, N*sizeof(double), cudaMemcpyHostToDevice);
int block_size = 370;
int n_blocks = N/block_size + (N%block_size == 0 ? 0:1);
cout<<n_blocks<<block_size;
square_array <<< n_blocks, block_size >>> (a_d, N);
cudaMemcpy(a, a_d, N*sizeof(double), cudaMemcpyDeviceToHost);
//cuda end
char name[]= "Image: 00000";
name[12]='\0';
int x=0,y=0;
for(int m=0;m<LENGTH;m++)
{
for (int i = 0; i < img1[m]->width*img1[m]->height*3; i+=3)
{
img1[m]->imageData[i]= a[m][x][y][0];
img1[m]->imageData[i+1]= a[m][x][y][1];
img1[m]->imageData[i+2]= a[m][x][y][2];
if(x==SIZE1)
{
x=0;
y++;
}
x++;
}
switch(name[11])
{
case '9': switch(name[10])
{
case '9':
switch(name[9])
{
case '9': name[11]='0';name[10]='0';name[9]='0';name[8]++;
break;
default : name[11]='0';
name[10]='0';
name[9]++;
}break;
default : name[11]='0'; name[10]++;break;
}
break;
default : name[11]++;break;
}
// Display the image.
cvNamedWindow(name, CV_WINDOW_AUTOSIZE);
cvShowImage(name,img1);
//cvSaveImage(name ,img1);
}
// Wait for the user to press a key in the GUI window.
cvWaitKey(0);
// Free the resources.
//cvDestroyWindow(x);
//cvReleaseImage(&img1);
//cvDestroyWindow("Image:");
//cvReleaseImage(&img2);
return 0;
}
The problem is that you are allocating a huge multidimensional array on the stack in your main function (double a[..][..][..]). Do not allocate this much memory on the stack. Use malloc/new to allocate on the heap.