C++ CUDA和C++；链接/编译，Cudamaloc上的程序崩溃
我有两个问题想向你们提出 (一) 我有一个C++ CUDA和C++；链接/编译，Cudamaloc上的程序崩溃,c++,memory,cuda,C++,Memory,Cuda,我有两个问题想向你们提出 (一) 我有一个.cpp文件，其中是main（），为了调用内核（在cu文件中），我使用extern函数调用调用内核的.cu文件launch（）。这两个文件分别是.cu和.cpp，正在成功编译。为了将它们结合在一起，由于我是CUDA的初学者，我尝试了两件事： 1） nvcc-Wno不推荐使用的gpu目标-o final file1.cpp file2.cu，它不会出现错误并成功编译最终程序，并且 (二) 在第二种情况下，由于无法识别-l参数（只有-lcuda是），我猜是因
.cppmain（）cuextern.culaunch（）.cu.cppCUDAnvcc-Wno不推荐使用的gpu目标-o final file1.cpp file2.cu-l-lcuda-l$ g++ -o final backpropalgorithm_CUDA_kernel_copy.o backpropalgorithm_CUDA_main_copy.o -lcuda
backpropalgorithm_CUDA_kernel_copy.o: In function `launch':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x185): undefined reference to `cudaConfigureCall'
backpropalgorithm_CUDA_kernel_copy.o: In function `__cudaUnregisterBinaryUtil()':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x259): undefined reference to `__cudaUnregisterFatBinary'
backpropalgorithm_CUDA_kernel_copy.o: In function `__nv_init_managed_rt_with_module(void**)':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x274): undefined reference to `__cudaInitModule'
backpropalgorithm_CUDA_kernel_copy.o: In function `__device_stub__Z21neural_network_kernelPfPiS0_PdS1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_S1_(float*, int*, int*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*, double*)':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x2ac): undefined reference to `cudaSetupArgument'
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x2cf): undefined reference to `cudaSetupArgument'
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x2f2): undefined reference to `cudaSetupArgument'
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x315): undefined reference to `cudaSetupArgument'
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x338): undefined reference to `cudaSetupArgument'
backpropalgorithm_CUDA_kernel_copy.o:tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x35b): more undefined references to `cudaSetupArgument' follow
backpropalgorithm_CUDA_kernel_copy.o: In function `__nv_cudaEntityRegisterCallback(void**)':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x663): undefined reference to `__cudaRegisterFunction'
backpropalgorithm_CUDA_kernel_copy.o: In function `__sti____cudaRegisterAll_69_tmpxft_0000717b_00000000_7_backpropalgorithm_CUDA_kernel_copy_cpp1_ii_43082cd7()':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x67c): undefined reference to `__cudaRegisterFatBinary'
backpropalgorithm_CUDA_kernel_copy.o: In function `cudaError cudaLaunch<char>(char*)':
tmpxft_0000717b_00000000-4_backpropalgorithm_CUDA_kernel_copy.cudafe1.cpp:(.text+0x6c0): undefined reference to `cudaLaunch'
backpropalgorithm_CUDA_main_copy.o: In function `main':
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x92): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0xf8): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x118): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x12c): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x14c): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x160): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x180): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x194): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x1b4): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x1c8): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x1e8): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x1ff): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x21f): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x236): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x256): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x26a): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x28a): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x2a1): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x2c1): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x2d5): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x2f5): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x309): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x329): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x33d): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x35d): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x371): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x391): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x3a5): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x3c5): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x3dc): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x3fc): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x413): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x433): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x44a): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x46a): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x481): undefined reference to `cudaMalloc'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x4a1): undefined reference to `cudaMemcpy'
backpropalgorithm_CUDA_main_copy.cpp:(.text+0x5bf): undefined reference to `cudaDeviceSynchronize'
collect2: error: ld returned 1 exit status
.cppprintf（）file1.cpp#include <stdio.h>
#include <math.h>
#include <stdlib.h>
#include <string>
#include "/home/user/include_files/cuda-8.0/include/cuda.h"
#include "/home/user/include_files/cuda-8.0/include/cuda_runtime.h"
#include "/home/user/include_files/cuda-8.0/include/cuda_runtime_api.h"
#define datanum 4 // number of training samples
#define InputN 16 // number of neurons in the input layer
#define hn 64 // number of neurons in the hidden layer
#define OutN 1 // number of neurons in the output layer
#define threads_per_block 256
using namespace std;
extern "C"
void launch(float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp);
__global__ void neural_network_kernel (float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp);
int main(int argc, char *argv[]){
printf("welcome1\n");
int times = 100000;
double sigmoid(double);
//string result = "";
char buffer[200];
printf("welcome2\n");
double x_out[InputN]; // input layer
printf("welcome3\n");
double hn_out[hn]; // hidden layer
printf("welcome4\n");
double y_out[OutN]; // output layer
printf("welcome5\n");
double y[OutN]; // expected output layer
printf("welcome6\n");
double w[InputN][hn]; // weights from input layer to hidden layer
double v[hn][OutN]; // weights from hidden layer to output layer
double deltaw[InputN][hn];
double deltav[hn][OutN];
printf("welcome7\n");
double hn_delta[hn]; // delta of hidden layer
double y_delta[OutN]; // delta of output layer
//double errlimit = 0.001;
double alpha = 0.1, beta = 0.1;
int i, j, m;
double sumtemp;
double errtemp;
/*cudaPrintfInit();
cudaPrintfDisplay(stdout, true);
cudaPrintfEnd();*/
printf("Line : main\n");
// Training
/*struct{
double input[InputN];
double teach[OutN];
}data[datanum];
for(m=0; m<datanum; m++){
for(i=0; i<InputN; i++)
data[m].input[i] = (double)rand()/32767.0;
for(i=0;i<OutN;i++)
data[m].teach[i] = (double)rand()/32767.0;
}
// Initialization
for(i=0; i<InputN; i++){
for(j=0; j<hn; j++){
w[i][j] = ((double)rand()/32767.0)*2-1;
deltaw[i][j] = 0;
}
}
for(i=0; i<hn; i++){
for(j=0; j<OutN; j++){
v[i][j] = ((double)rand()/32767.0)*2-1;
deltav[i][j] = 0;
}
}*/
//curandGenerator_t gen;
srand (time(NULL));
float randData[threads_per_block];
printf("welcome8\n");
for (int i=0; i<threads_per_block; i++)
{
randData[i] = rand()%100; //Else, without %100, it returns some billions for number!
}
printf("welcome9\n");
/*curandCreateGenerator(&gen, CURAND_RNG_PSEUDO_DEFAULT);
curandSetPseudoRandomGeneratorSeed(gen, 1234ULL);
curandGenerateUniform(gen, randData, threads_per_block);*/
int loop = 0;
double error;
double max, min;
double *max_p_GPU, *min_p_GPU, *error_p_GPU;
float *randData_p_GPU;
int *times_p_GPU, *loop_p_GPU, *InputN_p_GPU, *hn_p_GPU, *OutN_p_GPU;
double *x_out_p_GPU, *hn_out_p_GPU, *y_out_p_GPU, *y_p_GPU, *w_p_GPU, *v_p_GPU, *deltaw_p_GPU, *deltav_p_GPU, *hn_delta_p_GPU;
double *y_delta_p_GPU, *alpha_p_GPU, *beta_p_GPU, *sumtemp_p_GPU, *errtemp_p_GPU;
//int blocks = times/threads_per_block;
printf("welcome10\n");
cudaMalloc((void **)&randData_p_GPU, threads_per_block*sizeof(float));
printf("DEBUG1\n");
cudaMemcpy(randData_p_GPU, randData, threads_per_block*sizeof(float), cudaMemcpyHostToDevice);
printf("welcome11\n");
cudaMalloc((void **)×_p_GPU, sizeof(int));
printf("welcome12\n");
cudaMemcpy(times_p_GPU, ×, sizeof(int), cudaMemcpyHostToDevice);
printf("welcome13\n");
cudaMalloc((void **)&loop_p_GPU, sizeof(int));
printf("welcome14\n");
cudaMemcpy(loop_p_GPU, &loop, sizeof(int), cudaMemcpyHostToDevice);
printf("welcome15\n");
cudaMalloc((void **)&error_p_GPU, sizeof(double));
printf("welcome16\n");
cudaMemcpy(error_p_GPU, &error, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome17\n");
cudaMalloc((void **)&max_p_GPU, sizeof(double));
printf("welcome18\n");
cudaMemcpy(max_p_GPU, &max, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome19\n");
cudaMalloc((void **)&min_p_GPU, sizeof(double));
printf("welcome20\n");
cudaMemcpy(min_p_GPU, &min, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome21\n");
/* cudaMalloc((void **)&InputN_p_GPU, sizeof(int));
cudaMemcpy(InputN_p_GPU, &InputN, sizeof(int), cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_p_GPU, sizeof(int));
cudaMemcpy(hn_p_GPU, &hn, sizeof(int), cudaMemcpyHostToDevice);
cudaMalloc((void **)&OutN_p_GPU, sizeof(int));
cudaMemcpy(OutN_p_GPU, &OutN, sizeof(int), cudaMemcpyHostToDevice); */
/*cudaMalloc((void **)&x_out_p_GPU, sizeof(double)*(threads_per_block*InputN));
cudaMemcpy(x_out_p_GPU, &x_out, sizeof(double)*InputN, cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_out_p_GPU, sizeof(double)*(threads_per_block*hn));
cudaMemcpy(hn_out_p_GPU, &hn_out, sizeof(double)*hn, cudaMemcpyHostToDevice);
cudaMalloc((void **)&y_out_p_GPU, sizeof(double)*(threads_per_block*OutN));
cudaMemcpy(y_out_p_GPU, &y_out, sizeof(double)*OutN, cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_delta_p_GPU, sizeof(double)*(threads_per_block*hn));
cudaMemcpy(hn_delta_p_GPU, &hn_delta, sizeof(double)*hn, cudaMemcpyHostToDevice);
cudaMalloc((void **)&y_delta_p_GPU, sizeof(double)*(threads_per_block*OutN));
cudaMemcpy(y_delta_p_GPU, &y_delta, sizeof(double)*OutN, cudaMemcpyHostToDevice);*/
cudaMalloc((void **)&x_out_p_GPU, sizeof(double)*InputN);
printf("welcome22\n");
cudaMemcpy(x_out_p_GPU, &x_out, sizeof(double)*InputN, cudaMemcpyHostToDevice);
printf("welcome23\n");
cudaMalloc((void **)&hn_out_p_GPU, sizeof(double)*hn);
printf("welcome24\n");
cudaMemcpy(hn_out_p_GPU, &hn_out, sizeof(double)*hn, cudaMemcpyHostToDevice);
printf("welcome25\n");
cudaMalloc((void **)&y_out_p_GPU, sizeof(double)*OutN);
printf("welcome26\n");
cudaMemcpy(y_out_p_GPU, &y_out, sizeof(double)*OutN, cudaMemcpyHostToDevice);
printf("welcome27\n");
cudaMalloc((void **)&hn_delta_p_GPU, sizeof(double)*hn);
printf("welcome28\n");
cudaMemcpy(hn_delta_p_GPU, &hn_delta, sizeof(double)*hn, cudaMemcpyHostToDevice);
printf("welcome29\n");
cudaMalloc((void **)&y_delta_p_GPU, sizeof(double)*OutN);
printf("welcome30\n");
cudaMemcpy(y_delta_p_GPU, &y_delta, sizeof(double)*OutN, cudaMemcpyHostToDevice);
printf("welcome31\n");
cudaMalloc((void **)&alpha_p_GPU, sizeof(double));
cudaMemcpy(alpha_p_GPU, &alpha, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&beta_p_GPU, sizeof(double));
cudaMemcpy(beta_p_GPU, &beta, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&sumtemp_p_GPU, sizeof(double));
cudaMemcpy(sumtemp_p_GPU, &sumtemp, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&errtemp_p_GPU, sizeof(double));
cudaMemcpy(errtemp_p_GPU, &errtemp, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&w_p_GPU, sizeof(double)*InputN*hn);
cudaMemcpy(w_p_GPU, &w, sizeof(double)*(InputN*hn), cudaMemcpyHostToDevice);
cudaMalloc((void **)&v_p_GPU, sizeof(double)*hn*OutN);
cudaMemcpy(v_p_GPU, &v, sizeof(double)*(hn*OutN), cudaMemcpyHostToDevice);
cudaMalloc((void **)&deltaw_p_GPU, sizeof(double)*InputN*hn);
cudaMemcpy(deltaw_p_GPU, &deltaw, sizeof(double)*(InputN*hn), cudaMemcpyHostToDevice);
cudaMalloc((void **)&deltav_p_GPU, sizeof(double)*hn*OutN);
cudaMemcpy(deltav_p_GPU, &deltav, sizeof(double)*(hn*OutN), cudaMemcpyHostToDevice);
printf("welcome40\n");
launch(randData, times_p_GPU, loop_p_GPU, error_p_GPU, max_p_GPU, min_p_GPU, x_out_p_GPU, hn_out_p_GPU, y_out_p_GPU, y_p_GPU, w_p_GPU, v_p_GPU, deltaw_p_GPU, deltav_p_GPU, hn_delta_p_GPU, y_delta_p_GPU, alpha_p_GPU, beta_p_GPU, sumtemp_p_GPU, errtemp_p_GPU);
printf("welcome41\n");
cudaDeviceSynchronize();
printf("welcome_after_kernel\n");
}
cudamaloc（）但一开始它会永远挂起，为什么？在这里寻求帮助之前，最好使用正确的cuda错误检查并使用
cuda memcheck运行代码。如果不这样做，您可能会忽略有用的错误信息，浪费您的时间以及其他试图帮助您的人的时间
在第二种情况下，由于无法识别-l参数（只有-lcuda可以识别），我想是因为我不知道这些文件存储在哪里，所以没有指定它们的路径
你不想跳过这些nvcc
将自动为您链接其中一些库，并自动知道在哪里可以找到它们。当使用g++时，您必须告诉它在哪里查找以及您需要的特定库。对于显示的代码，您不需要所有链接所针对的库，因此以下内容就足够了：
g++ -o program file1.o file2.o -L/usr/local/cuda/lib64 -lcudart
用于CUDA的标准linux安装。如果您没有标准安装，您可以执行哪个nvcc
来查找nvcc
的位置，然后使用它来查找库可能位于的位置（将路径中的bin
更改为lib64
）
如果您确实需要其他一些库，那么像cutil
和cudpp
这样的库将不可用，除非您执行特殊步骤安装它们，并且在这种情况下，您需要确定它们的路径
关于cuPrintf
，如果您是在cc2.0或更高版本的GPU上编译和运行（这是CUDA 8支持的最低计算能力），您应该不需要它。普通的printf
应该在设备代码中工作，如果它不工作（因为您有设备代码错误-使用正确的错误检查和cuda memcheck
），那么cuPrintf
就不会工作得更好。因此，与其绞尽脑汁让它工作，不如将代码还原为使用printf
（并包括stdio.h
）
关于你的程序和为什么它不工作，我认为你可能有一些错误。您可能想学习如何使用调试器。在bat右侧的主机代码中，您试图从主机代码初始化randData
是非法的
现在我看到你已经多次改变了这个问题，把它变成了一个移动的目标，我将停止
如果需要帮助，请停止移动目标
使用正确的cuda错误检查
#include <stdio.h>
#include <math.h>
#include <stdlib.h>
#include <string>
#include "/home/user/include_files/cuda-8.0/include/cuda.h"
#include "/home/user/include_files/cuda-8.0/include/cuda_runtime.h"
#include "/home/user/include_files/cuda-8.0/include/cuda_runtime_api.h"
#define datanum 4 // number of training samples
#define InputN 16 // number of neurons in the input layer
#define hn 64 // number of neurons in the hidden layer
#define OutN 1 // number of neurons in the output layer
#define threads_per_block 256
using namespace std;
extern "C"
void launch(float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp);
__global__ void neural_network_kernel (float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp);
int main(int argc, char *argv[]){
printf("welcome1\n");
int times = 100000;
double sigmoid(double);
//string result = "";
char buffer[200];
printf("welcome2\n");
double x_out[InputN]; // input layer
printf("welcome3\n");
double hn_out[hn]; // hidden layer
printf("welcome4\n");
double y_out[OutN]; // output layer
printf("welcome5\n");
double y[OutN]; // expected output layer
printf("welcome6\n");
double w[InputN][hn]; // weights from input layer to hidden layer
double v[hn][OutN]; // weights from hidden layer to output layer
double deltaw[InputN][hn];
double deltav[hn][OutN];
printf("welcome7\n");
double hn_delta[hn]; // delta of hidden layer
double y_delta[OutN]; // delta of output layer
//double errlimit = 0.001;
double alpha = 0.1, beta = 0.1;
int i, j, m;
double sumtemp;
double errtemp;
/*cudaPrintfInit();
cudaPrintfDisplay(stdout, true);
cudaPrintfEnd();*/
printf("Line : main\n");
// Training
/*struct{
double input[InputN];
double teach[OutN];
}data[datanum];
for(m=0; m<datanum; m++){
for(i=0; i<InputN; i++)
data[m].input[i] = (double)rand()/32767.0;
for(i=0;i<OutN;i++)
data[m].teach[i] = (double)rand()/32767.0;
}
// Initialization
for(i=0; i<InputN; i++){
for(j=0; j<hn; j++){
w[i][j] = ((double)rand()/32767.0)*2-1;
deltaw[i][j] = 0;
}
}
for(i=0; i<hn; i++){
for(j=0; j<OutN; j++){
v[i][j] = ((double)rand()/32767.0)*2-1;
deltav[i][j] = 0;
}
}*/
//curandGenerator_t gen;
srand (time(NULL));
float randData[threads_per_block];
printf("welcome8\n");
for (int i=0; i<threads_per_block; i++)
{
randData[i] = rand()%100; //Else, without %100, it returns some billions for number!
}
printf("welcome9\n");
/*curandCreateGenerator(&gen, CURAND_RNG_PSEUDO_DEFAULT);
curandSetPseudoRandomGeneratorSeed(gen, 1234ULL);
curandGenerateUniform(gen, randData, threads_per_block);*/
int loop = 0;
double error;
double max, min;
double *max_p_GPU, *min_p_GPU, *error_p_GPU;
float *randData_p_GPU;
int *times_p_GPU, *loop_p_GPU, *InputN_p_GPU, *hn_p_GPU, *OutN_p_GPU;
double *x_out_p_GPU, *hn_out_p_GPU, *y_out_p_GPU, *y_p_GPU, *w_p_GPU, *v_p_GPU, *deltaw_p_GPU, *deltav_p_GPU, *hn_delta_p_GPU;
double *y_delta_p_GPU, *alpha_p_GPU, *beta_p_GPU, *sumtemp_p_GPU, *errtemp_p_GPU;
//int blocks = times/threads_per_block;
printf("welcome10\n");
cudaMalloc((void **)&randData_p_GPU, threads_per_block*sizeof(float));
printf("DEBUG1\n");
cudaMemcpy(randData_p_GPU, randData, threads_per_block*sizeof(float), cudaMemcpyHostToDevice);
printf("welcome11\n");
cudaMalloc((void **)×_p_GPU, sizeof(int));
printf("welcome12\n");
cudaMemcpy(times_p_GPU, ×, sizeof(int), cudaMemcpyHostToDevice);
printf("welcome13\n");
cudaMalloc((void **)&loop_p_GPU, sizeof(int));
printf("welcome14\n");
cudaMemcpy(loop_p_GPU, &loop, sizeof(int), cudaMemcpyHostToDevice);
printf("welcome15\n");
cudaMalloc((void **)&error_p_GPU, sizeof(double));
printf("welcome16\n");
cudaMemcpy(error_p_GPU, &error, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome17\n");
cudaMalloc((void **)&max_p_GPU, sizeof(double));
printf("welcome18\n");
cudaMemcpy(max_p_GPU, &max, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome19\n");
cudaMalloc((void **)&min_p_GPU, sizeof(double));
printf("welcome20\n");
cudaMemcpy(min_p_GPU, &min, sizeof(double), cudaMemcpyHostToDevice);
printf("welcome21\n");
/* cudaMalloc((void **)&InputN_p_GPU, sizeof(int));
cudaMemcpy(InputN_p_GPU, &InputN, sizeof(int), cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_p_GPU, sizeof(int));
cudaMemcpy(hn_p_GPU, &hn, sizeof(int), cudaMemcpyHostToDevice);
cudaMalloc((void **)&OutN_p_GPU, sizeof(int));
cudaMemcpy(OutN_p_GPU, &OutN, sizeof(int), cudaMemcpyHostToDevice); */
/*cudaMalloc((void **)&x_out_p_GPU, sizeof(double)*(threads_per_block*InputN));
cudaMemcpy(x_out_p_GPU, &x_out, sizeof(double)*InputN, cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_out_p_GPU, sizeof(double)*(threads_per_block*hn));
cudaMemcpy(hn_out_p_GPU, &hn_out, sizeof(double)*hn, cudaMemcpyHostToDevice);
cudaMalloc((void **)&y_out_p_GPU, sizeof(double)*(threads_per_block*OutN));
cudaMemcpy(y_out_p_GPU, &y_out, sizeof(double)*OutN, cudaMemcpyHostToDevice);
cudaMalloc((void **)&hn_delta_p_GPU, sizeof(double)*(threads_per_block*hn));
cudaMemcpy(hn_delta_p_GPU, &hn_delta, sizeof(double)*hn, cudaMemcpyHostToDevice);
cudaMalloc((void **)&y_delta_p_GPU, sizeof(double)*(threads_per_block*OutN));
cudaMemcpy(y_delta_p_GPU, &y_delta, sizeof(double)*OutN, cudaMemcpyHostToDevice);*/
cudaMalloc((void **)&x_out_p_GPU, sizeof(double)*InputN);
printf("welcome22\n");
cudaMemcpy(x_out_p_GPU, &x_out, sizeof(double)*InputN, cudaMemcpyHostToDevice);
printf("welcome23\n");
cudaMalloc((void **)&hn_out_p_GPU, sizeof(double)*hn);
printf("welcome24\n");
cudaMemcpy(hn_out_p_GPU, &hn_out, sizeof(double)*hn, cudaMemcpyHostToDevice);
printf("welcome25\n");
cudaMalloc((void **)&y_out_p_GPU, sizeof(double)*OutN);
printf("welcome26\n");
cudaMemcpy(y_out_p_GPU, &y_out, sizeof(double)*OutN, cudaMemcpyHostToDevice);
printf("welcome27\n");
cudaMalloc((void **)&hn_delta_p_GPU, sizeof(double)*hn);
printf("welcome28\n");
cudaMemcpy(hn_delta_p_GPU, &hn_delta, sizeof(double)*hn, cudaMemcpyHostToDevice);
printf("welcome29\n");
cudaMalloc((void **)&y_delta_p_GPU, sizeof(double)*OutN);
printf("welcome30\n");
cudaMemcpy(y_delta_p_GPU, &y_delta, sizeof(double)*OutN, cudaMemcpyHostToDevice);
printf("welcome31\n");
cudaMalloc((void **)&alpha_p_GPU, sizeof(double));
cudaMemcpy(alpha_p_GPU, &alpha, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&beta_p_GPU, sizeof(double));
cudaMemcpy(beta_p_GPU, &beta, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&sumtemp_p_GPU, sizeof(double));
cudaMemcpy(sumtemp_p_GPU, &sumtemp, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&errtemp_p_GPU, sizeof(double));
cudaMemcpy(errtemp_p_GPU, &errtemp, sizeof(double), cudaMemcpyHostToDevice);
cudaMalloc((void **)&w_p_GPU, sizeof(double)*InputN*hn);
cudaMemcpy(w_p_GPU, &w, sizeof(double)*(InputN*hn), cudaMemcpyHostToDevice);
cudaMalloc((void **)&v_p_GPU, sizeof(double)*hn*OutN);
cudaMemcpy(v_p_GPU, &v, sizeof(double)*(hn*OutN), cudaMemcpyHostToDevice);
cudaMalloc((void **)&deltaw_p_GPU, sizeof(double)*InputN*hn);
cudaMemcpy(deltaw_p_GPU, &deltaw, sizeof(double)*(InputN*hn), cudaMemcpyHostToDevice);
cudaMalloc((void **)&deltav_p_GPU, sizeof(double)*hn*OutN);
cudaMemcpy(deltav_p_GPU, &deltav, sizeof(double)*(hn*OutN), cudaMemcpyHostToDevice);
printf("welcome40\n");
launch(randData, times_p_GPU, loop_p_GPU, error_p_GPU, max_p_GPU, min_p_GPU, x_out_p_GPU, hn_out_p_GPU, y_out_p_GPU, y_p_GPU, w_p_GPU, v_p_GPU, deltaw_p_GPU, deltav_p_GPU, hn_delta_p_GPU, y_delta_p_GPU, alpha_p_GPU, beta_p_GPU, sumtemp_p_GPU, errtemp_p_GPU);
printf("welcome41\n");
cudaDeviceSynchronize();
printf("welcome_after_kernel\n");
}
#define w(i,j) w[(i)*(InputN*hn) + (j)]
#define v(i,j) v[(i)*(hn*OutN) + (j)]
#define x_out(i,j) x_out[(i)*(InputN) + (j)]
#define y(i,j) y[(i)*(OutN) + (j)]
#define hn_out(i,j) hn_out[(i)*(hn) + (j)]
#define y_out(i,j) y_out[(i)*(OutN) + (j)]
#define y_delta(i,j) y_delta[(i)*(OutN) + (j)]
#define hn_delta(i,j) hn_delta[(i)*(hn) + (j)]
#define deltav(i,j) deltav[(i)*(hn*OutN) + (j)]
#define deltaw(i,j) deltaw[(i)*(InputN*hn) + (j)]
#define datanum 4 // number of training samples
#define InputN 16 // number of neurons in the input layer
#define hn 64 // number of neurons in the hidden layer
#define OutN 1 // number of neurons in the output layer
#define threads_per_block 256
#define MAX_RAND 100
#define MIN_RAND 10
#include <stdio.h>
#include <math.h> //for truncf()
// sigmoid serves as avtivation function
__device__ double sigmoid(double x){
return(1.0 / (1.0 + exp(-x)));
}
__device__ int rand_kernel(int index, float *randData){
float myrandf = randData[index];
myrandf *= (MAX_RAND - MIN_RAND + 0.999999);
myrandf += MIN_RAND;
int myrand = (int)truncf(myrandf);
return myrand;
}
__global__ void neural_network_kernel (float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp)
{
//int i = blockIdx.x;
//int idx = threadIdx.x;
//int idy = threadIdx.y
int index = blockIdx.x * blockDim.x + threadIdx.x;
// training set
struct{
double input_kernel[InputN];
double teach_kernel[OutN];
}data_kernel[threads_per_block + datanum];
if (index==0)
{
for(int m=0; m<datanum; m++){
for(int i=0; i<InputN; i++)
data_kernel[threads_per_block + m].input_kernel[i] = (double)rand_kernel(index, randData)/32767.0;
for(int i=0;i<OutN;i++)
data_kernel[threads_per_block + m].teach_kernel[i] = (double)rand_kernel(index, randData)/32767.0;
}
}
// Initialization
for(int i=0; i<InputN; i++){
for(int j=0; j<hn; j++){
w(i,j) = ((double)rand_kernel(index, randData)/32767.0)*2-1;
deltaw(i,j) = 0;
}
}
for(int i=0; i<hn; i++){
for(int j=0; j<OutN; j++){
v(i,j) = ((double)rand_kernel(index, randData)/32767.0)*2-1;
deltav(i,j) = 0;
}
}
while(loop[index] < *times){
loop[index]++;
error[index] = 0.0;
for(int m=0; m<datanum ; m++){
// Feedforward
max[index] = 0.0;
min[index] = 0.0;
for(int i=0; i<InputN; i++){
x_out(index,i) = data_kernel[threads_per_block + m].input_kernel[i];
if(max[index] < x_out(index,i))
max[index] = x_out(index,i);
if(min[index] > x_out(index,i))
min[index] = x_out(index,i);
}
for(int i=0; i<InputN; i++){
x_out(index,i) = (x_out(index,i) - min[index]) / (max[index] - min[index]);
}
for(int i=0; i<OutN ; i++){
y(index,i) = data_kernel[threads_per_block + m].teach_kernel[i];
}
for(int i=0; i<hn; i++){
sumtemp[index] = 0.0;
for(int j=0; j<InputN; j++)
sumtemp[index] += w(j,i) * x_out(index,j);
hn_out(index,i) = sigmoid(sumtemp[index]); // sigmoid serves as the activation function
}
for(int i=0; i<OutN; i++){
sumtemp[index] = 0.0;
for(int j=0; j<hn; j++)
sumtemp[index] += v(j,i) * hn_out(index,j);
y_out(index,i) = sigmoid(sumtemp[index]);
}
// Backpropagation
for(int i=0; i<OutN; i++){
errtemp[index] = y(index,i) - y_out(index,i);
y_delta(index,i) = -errtemp[index] * sigmoid(y_out(index,i)) * (1.0 - sigmoid(y_out(index,i)));
error[index] += errtemp[index] * errtemp[index];
}
for(int i=0; i<hn; i++){
errtemp[index] = 0.0;
for(int j=0; j<OutN; j++)
errtemp[index] += y_delta(index,j) * v(i,j);
hn_delta(index,i) = errtemp[index] * (1.0 + hn_out(index,i)) * (1.0 - hn_out(index,i));
}
// Stochastic gradient descent
for(int i=0; i<OutN; i++){
for(int j=0; j<hn; j++){
deltav(j,i) = (*alpha) * deltav(j,i) + (*beta) * y_delta(index,i) * hn_out(index,j);
v(j,i) -= deltav(j,i);
}
}
for(int i=0; i<hn; i++){
for(int j=0; j<InputN; j++){
deltaw(j,i) = (*alpha) * deltaw(j,i) + (*beta) * hn_delta(index,i) * x_out(index,j);
w(j,i) -= deltaw(j,i);
}
}
}
// Global error
error[index] = error[index] / 2;
/*if(loop%1000==0){
result = "Global Error = ";
sprintf(buffer, "%f", error);
result += buffer;
result += "\r\n";
}
if(error < errlimit)
break;*/
printf("The %d th training, error: %0.100f\n", loop[index], error[index]);
}
}
extern "C"
void launch(float *randData, int *times, int *loop, double *error, double *max, double *min, double *x_out, double *hn_out, double *y_out, double *y, double *w, double *v, double *deltaw, double *deltav, double *hn_delta, double *y_delta, double *alpha, double *beta, double *sumtemp, double *errtemp)
{
int blocks = *times/threads_per_block;
neural_network_kernel<<<blocks, threads_per_block>>>(randData, times, loop, error, max, min, x_out, hn_out, y_out, y, w, v, deltaw, deltav, hn_delta, y_delta, alpha, beta, sumtemp, errtemp);
}
g++ -o program file1.o file2.o -L/usr/local/cuda/lib64 -lcudart