While trying to learn dynamic assignment in C++, every time I use the "new" operator, the code fails to compile.
I have already tried to use malloc and the other functions. They worked for a time, but now I need to dynamically declare an object and I can't seem to get malloc to work with that. (Also, I should be able to use new so...)
#include <stdio.h>
#include <stdlib.h>
int main(){
int * x = new int[10];
for(int i = 0; i < 10; i++){
x[i] = i;
}
for(int i = 0; i < 10; i++){
printf("%d\n", x[i]);
}
}
When I try to compile with "gcc main.cpp -o main.exe"
it always gives me the same error:
[temporary file name]cc8cDkmk.o:main.cpp:(.text+0x13): undefined reference to `operator new[](unsigned long long)'
Related
I am currently porting some code over to OpenMP at my place of work. One of the tasks I am doing is figuring out how to speed up matrix multiplication for one of our applications.
The matrices are stored in row-major format, so A[i*cols +j] gives the A_i_j element of the matrix A.
The code looks like this (uncommenting the pragma parallelises the code):
#include <omp.h>
#include <iostream>
#include <iomanip>
#include <stdio.h>
#define NUM_THREADS 8
#define size 500
#define num_iter 10
int main (int argc, char *argv[])
{
// omp_set_num_threads(NUM_THREADS);
int *A = new int [size*size];
int *B = new int [size*size];
int *C = new int [size*size];
for (int i=0; i<size; i++)
{
for (int j=0; j<size; j++)
{
A[i*size+j] = j*1;
B[i*size+j] = i*j+2;
C[i*size+j] = 0;
}
}
double total_time = 0;
double start = 0;
for (int t=0; t<num_iter; t++)
{
start = omp_get_wtime();
int i, k;
// #pragma omp parallel for num_threads(10) private(i, k) collapse(2) schedule(dynamic)
for (int j=0; j<size; j++)
{
for (i=0; i<size; i++)
{
for (k=0; k<size; k++)
{
C[i*size+j] += A[i*size+k] * B[k*size+j];
}
}
}
total_time += omp_get_wtime() - start;
}
std::setprecision(5);
std::cout << total_time/num_iter << std::endl;
delete[] A;
delete[] B;
delete[] C;
return 0;
}
What is confusing me is the following: why is dynamic scheduling faster than static scheduling for this task? Timing the runs and taking an average shows that static scheduling is slower, which to me is a bit counterintuitive since each thread is doing the same amount of work.
Also, am I correctly speeding up my matrix multiplication code?
Parallel matrix multiplication is non-trivial (have you even considered cache-blocking?). Your best bet is likely to be to use a BLAS Library for this, rather than writing it yourself. (Remember, "The best code is the code I do not have to write").
Wikipedia: Basic Linear Algebra Subprograms points to many implementations, a lot of which (including Intel Math Kernel Library) have free licenses.
When i try to run this code, it compiles without any error, but i wanted that it should display the string and int array that it takes as input. Instead, after giving one input, I am presented with a list of zeroes and program terminates.
however,when i removed the line containing k[j] from both for loops, it worked.
What am I doing wrong? Pardon if asked something stupid as I'm a novice, please help...
#include <iostream>
#include <string>
using namespace std;
int main ()
{
int t,count = 0;
string state[t];
int k[t];
cin>>t;
for (int j=0; j<t; j++)
{
getline(cin, state[j]);
cin>>k[j];
}
for (int j=0; j<t; j++)
{ cout<< state [j]<<'\t'<<k[j];
cout<<endl;
}
return 0
}
You declare both arrays k[] and state[] with t wich is undefined at this moment.
t should be initiated with a valid value beforehand!
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.
I am trying to use lapack functions from C.
Here is some test code, copied from this question
#include <stdlib.h>
#include <stdio.h>
#include <time.h>
#include "clapack.h"
#include "cblas.h"
void invertMatrix(float *a, unsigned int height){
int info, ipiv[height];
info = clapack_sgetrf(CblasColMajor, height, height, a, height, ipiv);
info = clapack_sgetri(CblasColMajor, height, a, height, ipiv);
}
void displayMatrix(float *a, unsigned int height, unsigned int width)
{
int i, j;
for(i = 0; i < height; i++){
for(j = 0; j < width; j++)
{
printf("%1.3f ", a[height*j + i]);
}
printf("\n");
}
printf("\n");
}
int main(int argc, char *argv[])
{
int i;
float a[9], b[9], c[9];
srand(time(NULL));
for(i = 0; i < 9; i++)
{
a[i] = 1.0f*rand()/RAND_MAX;
b[i] = a[i];
}
displayMatrix(a, 3, 3);
return 0;
}
I compile this with gcc:
gcc -o test test.c \
-lblas -llapack -lf2c
n.b.: I've tried those libraries in various orders, I've also tried others libs like latlas, lcblas, lgfortran, etc.
The error message is:
/tmp//cc8JMnRT.o: In function `invertMatrix':
test.c:(.text+0x94): undefined reference to `clapack_sgetrf'
test.c:(.text+0xb4): undefined reference to `clapack_sgetri'
collect2: error: ld returned 1 exit status
clapack.h is found and included (installed as part of atlas). clapack.h includes the offending functions --- so how can they not be found?
The symbols are actually in the library libalapack (found using strings). However, adding -lalapack to the gcc command seems to require adding -lcblas (lots of undefined cblas_* references). Installing cblas automatically uninstalls atlas, which removes clapack.h.
So, this feels like some kind of dependency hell.
I am on FreeBSD 10 amd64, all the relevant libraries seem to be installed and on the right paths.
Any help much appreciated.
Thanks
Ivan
I uninstalled everything remotely relevant --- blas, cblas, lapack, atlas, etc. --- then reinstalled atlas (from ports) alone, and then the lapack and blas packages.
This time around, /usr/local/lib contained a new lib file: libcblas.so --- previous random installations must have deleted it.
The gcc line that compiles is now:
gcc -o test test.c \
-llapack -lblas -lalapack -lcblas
Changing the order of the -l arguments doesn't seem to make any difference.
I have a CUDA C code, when I try to compile it, nvcc gives me an error with an undefined identifier error: identifier "cudamalloc" is undefined, identifier "cudamemcpy" is undefined.
I'm running Windows 7 with Visual Studio 10 and CUDA Toolkit 4.0
I have installed Cuda on drive "C" and Visual Studio on drive "E" but im not sure that it is the problem.
I use this command to compile:
nvcc -o ej1b ej1b.cu
and this is my program:
#include <cuda.h>
#include <cstdio>
#include <cuda_runtime_api.h>
#include <device_functions.h>
#include "device_launch_parameters.h"
#include <stdio.h>
#include <stdlib.h>
const int N = 512;
const int C = 5;
void init_CPU_array(int vec[],const int N){
unsigned int i;
for(i = 0; i < N; i++) {
vec[i] = i;
}
}
__global__ void kernel(int vec[],const int N, const int C){
int id = blockIdx.x * blockDim.x + threadIdx.x;
if(id<N)
vec[id] = vec[id] * C;
}
int main(){
int vec[N];
int vecRES[N];
int *vecGPU;
unsigned int cantaloc=N*sizeof(int);
init_CPU_array(vec,N);
cudamalloc((void**)&vecGPU,cantaloc);
cudamemcpy(vecGPU,vec,cantaloc,cudaMemcpyHostToDevice);
dim3 dimBlock(64);
dim3 dimGrid((N + dimBlock.x - 1) / dimBlock.x);
printf("-> Variable dimBlock.x = %d\n",dimBlock.x);
kernel<<<dimGrid, dimBlock>>>(vecGPU, N, C);
cudaThreadSynchronize();
cudamemcpy(vecRES,vecGPU,cantaloc,cudaMemcpyDeviceToHost);
cudaFree(vecGPU);
printf("%s \n","-> Resultados");
int i;
for(i=0;i<10;i++){
printf("%d ",vecRES[i]);
printf("%d \n",vec[i]);
}
return 0;
I used all those #include because I don't know where the problem is.
If you read the documentation, you will find the API calls are cudaMalloc and cudaMemcpy. C and C++ are case sensitive languages and you have the names incorrect.