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.
Related
I tried to call an OpenBlas function from an OpenMP thread while the Blas parallelisation is set to a value unequal to one. I am using OpenBlas 0.3.9, after downloading the source I untared it and called
make USE_OPENMP=1
make PREFIX=/someFolder/ install
However I always get the following error message from my executeable
OpenBLAS Warning : Detect OpenMP Loop and this application may hang. Please rebuild the library with USE_OPENMP=1 option.
Does anyone know, why this is the case and how I can change it? Here is a minimal example of my code:
#include <complex>
#include <vector>
#include <random>
#include <iostream>
#include <algorithm>
#include <omp.h>
#include <cblas.h>
#include <lapacke.h>
int main(int, char**) {
int const blas_threads = 2,
omp_threads = 2,
matrix_size = 100;
openblas_set_num_threads(blas_threads);
omp_set_max_active_levels(2);
double alpha = 1.,
beta = 0.;
std::vector<std::vector<double>> as(omp_threads,
std::vector<double>(matrix_size*matrix_size));
std::vector<std::vector<double>> bs(omp_threads,
std::vector<double>(matrix_size*matrix_size));
std::vector<std::vector<double>> cs(omp_threads,
std::vector<double>(matrix_size*matrix_size));
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_real_distribution<double> dis;
for(int i = 0; i < omp_threads; ++i) {
std::generate(as[i].begin(),
as[i].end(),
[&dis,&gen]() { return dis(gen); });
std::generate(bs[i].begin(),
bs[i].end(),
[&dis,&gen]() { return dis(gen); });
}
// for(int i = 0; i < matrix_size*matrix_size; ++i) {
// std::cout << as[0][i] << " " << bs[0][i] << std::endl;
// }
#pragma omp parallel for num_threads(omp_threads), schedule(static, 1)
for(int i = 0; i < omp_threads; ++i) {
cblas_dgemm(CblasColMajor,
CblasNoTrans,
CblasNoTrans,
matrix_size,
matrix_size,
matrix_size,
alpha,
as[i].data(),
matrix_size,
bs[i].data(),
matrix_size,
beta,
cs[i].data(),
matrix_size);
}
// for(int i = 0; i < matrix_size*matrix_size; ++i) {
// std::cout << cs[0][i] << std::endl;
// }
return 0;
}
#include <cstdint>
#include <cstring>
template<typename T>
T oph_(const char *s){
constexpr std::size_t MAX = sizeof(T);
const std::size_t size = strnlen(s, MAX);
T r = 0;
for(auto it = s; it - s < size; ++it)
r = r << 8 | *it;
return r;
}
inline uint64_t oph(const char *s){
return oph_<uint64_t>(s);
}
int main(){
uint64_t const a = oph("New York City");
uint64_t const b = oph("Boston International");
return a > b;
}
I want to convert first 8 characters from const char * to uint64_t so I can easily compare if two strings are greater / lesser.
I am aware that equals will semi-work.
However I am not sure if this is most efficient implementation.
I want the implementation to work on both little and big endian machines.
This is a C implementation, that should be faster that your implementation, but I still need to use strncpy which should be the bottleneck
#include <string.h>
#include <stdio.h>
#include <stdint.h>
#include <byteswap.h>
union small_str {
uint64_t v;
char buf[8];
};
static uint64_t fill_small_str(const char *str)
{
union small_str ss = { 0 };
strncpy(ss.buf, str, 8);
#if defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
return ss.v;
#else
return bswap_64(ss.v);
#endif
}
int main(void)
{
uint64_t const a = fill_small_str("Aew York City");
uint64_t const b = fill_small_str("Boston International");
printf("%lu ; %lu ; %d\n", a, b, (a < b));
return 0;
}
I'm trying to add a custom system call into the linux kernel. Here is a simple code:
#include <linux/mysyscall.h>
#include <linux/kernel.h>
#include <asm/uaccess.h>
#include <asm/system.h>
asmlinkage int sys_mysyscall(int *data){
int a = 3;
cli();
copy_to_user(data, &a, 1);
sti();
printk(KERN_EMERG "Called with %d\n", a);
return a;
}
I can compile a kernel with mysyscall added and when I try to access it with a user program like:
#include <linux/mysyscall.h>
int main(void){
int *data;
int r;
int a = 0;
data = &a;
r = mysyscall(data);
printf("r is %d and data is %d", r, *data);
}
*data does not equal to 3 it equals to 0.
How should I use copy_to_user to fix it?
The copy to user line of code copies only one byte from 'a'. In case of little endian systems it is going to be 0. Copy all the 4 bytes to get the correct result.
good afternoon.
I got the code below on a book. I'm trying to execute it, but I don't know what is the "first" and "last" parameters on the MakeCodeWritable function, or where I can find them. Someone can help? This code is about C obfuscation method. I'm using Xcode program and LLVM GCC 4.2 compiler.
#include <stdio.h>
#include <sys/mman.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
typedef unsigned int uint32;
typedef char* caddr_t;
typedef uint32* waddr_t;
#define Tam_celula 64
#define ALIGN __attribute__((aligned(Tam_celula)))
void makeCodeWritable(char* first, char* last) {
char* firstpage = first - ((int)first % getpagesize());
char* lastpage = last - ((int)last % getpagesize());
int pages = (lastpage-firstpage)/getpagesize()+1;
if (mprotect(firstpage,pages*getpagesize(), PROT_READ|PROT_EXEC|PROT_WRITE)==-1) perror("mprotect");
}
void xor(caddr_t from, caddr_t to, int len){
int i;
for(i=0;i<len;i++){
*to ^= *from; from++; to++;
} }
void swap(caddr_t from, caddr_t to, int len){
int i;
for(i=0;i<len;i++){
char t = *from; *from = *to; *to = t; from++; to++;
} }
#define CELLSIZE 64
#define ALIGN asm volatile (".align 64\n");
void P() {
static int firsttime=1; if (firsttime) {
xor(&&cell5,&&cell2,CELLSIZE);
xor(&&cell0,&&cell3,CELLSIZE);
swap(&&cell1,&&cell4,CELLSIZE);
firsttime = 0; }
char* a[] = {&&align0,&&align1,&&align2,&&align3,&&align4,&&align5};
char*next[] ={&&cell0,&&cell1,&&cell2,&&cell3, &&cell4,&&cell5};
goto *next[0];
align0: ALIGN
cell0: printf("SPGM0\n");
xor(&&cell0,&&cell3,3*CELLSIZE);
goto *next[3];
align1: ALIGN
cell1: printf("SPGM2\n"); xor(&&cell0,&&cell3,3*CELLSIZE);
goto *next[4];
align2: ALIGN
cell2: printf("SPGM4\n"); xor(&&cell0,&&cell3,3*CELLSIZE);
goto *next[5];
align3: ALIGN
cell3: printf("SPGM1\n"); xor(&&cell3,&&cell0,3*CELLSIZE);
goto *next[1];
align4: ALIGN
cell4: printf("SPGM3\n"); xor(&&cell3,&&cell0,3*CELLSIZE);
goto *next[2];
align5: ALIGN
cell5: printf("SPGM5\n");
xor(&&cell3,&&cell0,3*CELLSIZE);
}
int main (int argc, char *argv[]) {
makeCodeWritable(...);
P(); P();
}
The first argument should be (char *)P, because it looks like you want to modify code inside function P. The second argument is the ending address of function P. You can first compile the code, and using objdump -d to see the address of beginning and end of P, then calculate the size of the function, SIZE, then manually specify in the makeCodeWritable( (char *)P, ((char *)P) + SIZE.
The second way is utilizing the as to get the size of function P, but it depends on the assembler language on your platform. This is code snipe I modified from your code, it should be able to compile and run in x86, x86_64 in GCC 4.x on Linux platform.
align5: ALIGN
cell5: printf("SPGM5\n");
xor(&&cell3,&&cell0,3*CELLSIZE);
// adding an label to the end of function P to assembly code
asm ("END_P: \n");
;
}
extern char __sizeof__myfunc[];
int main (int argc, char *argv[]) {
// calculate the code size, ending - starting address of P
asm (" __sizeof__myfunc = END_P-P \n");
// you can see the code size of P
printf("code size is %d\n", (unsigned)__sizeof__myfunc);
makeCodeWritable( (char*)P, ((char *)P) + (unsigned)__sizeof__myfunc);
P(); P();
}
With some modification to support LLVM GCC and as in Mac OS X
int main (int argc, char *argv[]) {
size_t sizeof__myfunc = 0;
asm volatile ("movq $(_END_P - _P),%0;"
: "=r" (sizeof__myfunc)
: );
printf("%d\n", sizeof__myfunc);
#include <windows.h>
#include <stdio.h>
#include <conio.h>
#include <stdlib.h>
#include <iostream.h>
#include <string.h>
void Thread1( LPVOID param)
{
int a;
a = *((int *)param);
for (int i= 0; i <10; i++)
printf("%d\n", a);
}
int main()
{
int a =4;
int ThreadId;
CreateThread( 0, 0x0100, Thread1, &a, 0, &ThreadId);
for( int i = 0; i <11; i++)
Sleep( 1);
return( 1);
}
This is a simple code but I am not able to figure it out why visual studio is giving me error:
error C2664: 'CreateThread' : cannot convert parameter 3 from 'void (void *)' to 'unsigned long (__stdcall *)(void *)'
None of the functions with this name in scope match the target type
Error executing cl.exe.
define as following
DWORD WINAPI MyThreadProc(LPVOID lpParameter)
CreateThread() require __stdcall calling convention.