{"id":312357,"date":"2020-10-31T15:00:31","date_gmt":"2020-10-31T15:00:31","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=312357"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=312357","title":{"rendered":"\u0421\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u0435 \u0432\u0440\u0435\u043c\u0435\u043d\u0438 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u043d\u0430 CPU \u0438 GPU"},"content":{"rendered":"\n
\n

\u0418\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 CUDA Runtime API \u0434\u043b\u044f \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439. \u0421\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u0435 CPU \u0438 GPU \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439<\/h2>\n

\u0412 \u0434\u0430\u043d\u043d\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u044f \u0440\u0435\u0448\u0438\u043b \u043f\u0440\u043e\u0432\u0435\u0441\u0442\u0438 \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u0435 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u043d\u043e\u0433\u043e \u043d\u0430 C++ \u043d\u0430 \u0446\u0435\u043d\u0442\u0440\u0430\u043b\u044c\u043d\u043e\u043c \u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u043e\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0435(\u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435 \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e Nvidia CUDA Runtime API \u043d\u0430 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u043c\u043e\u043c GPU Nvidia). CUDA API \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439 \u043d\u0430 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u043e\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0435. \u0424\u0430\u0439\u043b c++ \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0449\u0438\u0439 cuda, \u0431\u0443\u0434\u0435\u0442 \u0438\u043c\u0435\u0442\u044c \u0440\u0430\u0441\u0448\u0438\u0440\u0435\u043d\u0438\u0435 .cu<\/b>.
\u0421\u0445\u0435\u043c\u0430 \u0440\u0430\u0431\u043e\u0442\u044b \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u043f\u0440\u0438\u0432\u0435\u0434\u0435\u043d\u0430 \u043d\u0438\u0436\u0435. <\/p>\n

<\/p>\n

\u0417\u0430\u0434\u0430\u0447\u0430 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u0441\u043e\u0441\u0442\u043e\u0438\u0442 \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e \u043d\u0430\u0439\u0442\u0438 \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u044b\u0435 \u0447\u0438\u0441\u043b\u0430 X, \u043f\u0440\u0438 \u0432\u043e\u0437\u0432\u0435\u0434\u0435\u043d\u0438\u0438 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0432 \u0441\u0442\u0435\u043f\u0435\u043d\u044c degree_of, \u0431\u0443\u0434\u0435\u0442 \u043f\u043e\u043b\u0443\u0447\u0430\u0442\u0441\u044f \u0438\u0441\u0445\u043e\u0434\u043d\u043e\u0435 \u0447\u0438\u0441\u043b\u043e max_number. \u0421\u0440\u0430\u0437\u0443 \u043e\u0442\u043c\u0435\u0447\u0443, \u0447\u0442\u043e \u0432\u0441\u0435 \u0447\u0438\u0441\u043b\u0430 \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0431\u0443\u0434\u0443\u0442 \u043f\u0435\u0440\u0435\u0434\u0430\u0432\u0430\u0442\u044c\u0441\u044f GPU, \u0431\u0443\u0434\u0443\u0442 \u0445\u0440\u0430\u043d\u0438\u0442\u0441\u044f \u0432 \u043c\u0430\u0441\u0441\u0438\u0432\u0430\u0445. \u0410\u043b\u0433\u043e\u0440\u0438\u0442\u043c, \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0439 \u043a\u0430\u0436\u0434\u044b\u043c \u043f\u043e\u0442\u043e\u043a\u043e\u043c, \u0438\u043c\u0435\u0435\u0442 \u043f\u0440\u0438\u0431\u043b\u0438\u0437\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0439 \u0432\u0438\u0434:
<\/a> <\/p>\n

int\u00a0degree_of=2; int\u00a0degree_of_max=Number_degree_of_max[0];\/\/\u041c\u0430\u0441\u0441\u0438\u0432\u00a0\u0445\u0440\u0430\u043d\u044f\u0449\u0438\u0439\u00a0\u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435\u00a0\u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0439\u00a0\u0441\u0442\u0435\u043f\u0435\u043d\u0438\u00a0\u0447\u0438\u0441\u043b\u0430 int\u00a0x=thread;\/\/\u043d\u043e\u043c\u0435\u0440\u00a0\u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u043e\u0433\u043e\u00a0\u043f\u043e\u0442\u043e\u043a\u0430 int\u00a0max_number=INPUT[0];\/\/\u041c\u0430\u0441\u0441\u0438\u0432\u00a0\u0445\u0440\u0430\u043d\u044f\u0449\u0438\u0439\u00a0\u0447\u0438\u0441\u043b\u043e,\u00a0\u043a\u043e\u0442\u043e\u0440\u043e\u0435\u00a0\u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u00a0\u043f\u043e\u043b\u0443\u0447\u0438\u0442\u044c int\u00a0Number=1; int\u00a0Degree; bool\u00a0BREAK=false;\/\/\u041f\u0435\u0440\u0435\u043c\u0435\u043d\u043d\u0430\u044f\u00a0\u0434\u043b\u044f\u00a0\u0437\u0430\u0432\u0435\u0440\u0448\u0435\u043d\u0438\u044f\u00a0while while(degree_of<=degree_of_max&&!BREAK){ \u00a0\u00a0\u00a0\u00a0Number=1; \u00a0\u00a0\u00a0\u00a0for(int\u00a0i=0;i<degree_of;i++){ \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Number*=x; \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Degree=degree_of; \u00a0\u00a0\u00a0\u00a0} \u00a0\u00a0\u00a0\u00a0if(Number==max_number){ \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0OUT_NUMBER[thread]=X;\/\/OUT_NUMBER\u00a0\u041c\u0430\u0441\u0441\u0438\u0432\u00a0\u0445\u0440\u0430\u043d\u044f\u0449\u0438\u0439\u00a0\u0447\u0438\u0441\u043b\u0430\u00a0\u043a\u043e\u0442\u043e\u0440\u044b\u0435\u00a0\u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u00a0\u0432\u043e\u0437\u0432\u0435\u0441\u0442\u0438\u00a0\u0432\u00a0\u0441\u0442\u0435\u043f\u0435\u043d\u044c\u00a0Degree\u00a0\u0434\u043b\u044f\u00a0\u043f\u043e\u043b\u0443\u0447\u0435\u043d\u0438\u044f\u00a0\u0438\u0441\u0445\u043e\u0434\u043d\u043e\u0433\u043e\u00a0\u0447\u0438\u0441\u043b\u0430 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0OUT_DEGREE[thread]=Degree;\/\/\u00a0OUT_DEGREE\u00a0\u041c\u0430\u0441\u0441\u0438\u0432\u00a0\u0445\u0440\u0430\u043d\u044f\u0449\u0438\u0439\u00a0\u0441\u0442\u0435\u043f\u0435\u043d\u044c\u00a0\u0432\u00a0\u043a\u043e\u0442\u043e\u0440\u0443\u044e\u00a0\u043d\u0443\u0436\u043d\u043e\u00a0\u0432\u043e\u0437\u0432\u0435\u0441\u0442\u0438\u00a0\u0447\u0438\u0441\u043b\u043e\u00a0X\u00a0\u0434\u043b\u044f\u00a0\u043f\u043e\u043b\u0443\u0447\u0435\u043d\u0438\u044f\u00a0\u0438\u0441\u0445\u043e\u0434\u043d\u043e\u0433\u043e\u00a0\u0447\u0438\u0441\u043b\u0430 \u00a0\u00a0\u00a0\u00a0} \u00a0\u00a0\u00a0degree_of++; \u00a0\u00a0\u00a0\/\/\u0412\u00a0\u0441\u043b\u0443\u0447\u0430\u0435\u00a0\u0432\u044b\u0445\u043e\u0434\u0430\u00a0\u0437\u0430\u00a0\u043f\u0440\u0435\u0434\u0435\u043b\u00a0: if(degree_of>degree_of_max||Number>max_number){ \u00a0\u00a0\u00a0\u00a0BREAK=true; } }  <\/code><\/pre>\n
  <\/p>\n
                         \u041a\u043e\u0434 \u0434\u043b\u044f \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u043d\u0430 CPU<\/b>                         <\/p>\n
\n
#include <iostream> #include<vector> #include<string>\/\/\u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u0434\u043b\u044f getline #include<thread> #include<fstream> using namespace std; int Running_thread_counter = 0; void Upload_to_CPU(unsigned long long  *Number, unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT, unsigned long long  *max, int THREAD); void Upload_to_CPU(unsigned long long  *Number, unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT, unsigned long long  *max, int THREAD) { \tint thread = THREAD; \tRunning_thread_counter++; \tunsigned long long  MAX_DEGREE_OF = max[0]; \tint X = thread; \tunsigned long long  Calculated_number = 1; \tunsigned long long  DEGREE_OF = 2; \tunsigned long long   INP = INPUT[0]; \tStop[thread] = false; \tbool BREAK = false; \tif (X != 0 && X != 1) { \t\twhile (!BREAK) { \t\t\tif (DEGREE_OF <= MAX_DEGREE_OF) { \t\t\t\tCalculated_number = 1; \t\t\t\tfor (int counter = 0; counter < DEGREE_OF; counter++) { \t\t\t\t\tCalculated_number *= X; \t\t\t\t} \t\t\t\tif (Calculated_number == INP) { \t\t\t\t\tStepn[thread] = DEGREE_OF; \t\t\t\t\tNumber[thread] = X; \t\t\t\t\tStop[thread] = true; \t\t\t\t\tBREAK = true; \t\t\t\t} \t\t\t\tDEGREE_OF++; \t\t\t} \t\t\telse { BREAK = true; } \t\t} \t} } void Parallelize_to_threads(unsigned long long  *Number, unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT, unsigned long long  *max, int size); int main() { \tint size = 1000; \tunsigned long long  *Number = new unsigned long long[size], *Degree_of = new unsigned long long[size]; \tunsigned long long  *Max_Degree_of = new unsigned long long[1]; \tunsigned long long  *INPUT_NUMBER = new unsigned long long[1]; \tMax_Degree_of[0] = 7900;  \tINPUT_NUMBER[0] = 216 * 216 * 216; \tifstream inp("input.txt"); \tif (inp.is_open()) { \t\tstring t; \t\tvector<unsigned long long>IN; \t\twhile (getline(inp, t)) { \t\t\tIN.push_back(stol(t));  \t\t} \t\tINPUT_NUMBER[0] = IN[0];\/\/\u0438\u0441\u0445\u043e\u0434\u043d\u043e\u0435 \u0447\u0438\u0441\u043b\u043e \t\tMax_Degree_of[0] = IN[1];\/\/\u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0439 \u0441\u0442\u0435\u043f\u0435\u043d\u0438 \t} \telse { \t\tofstream error("error.txt"); \t\tif (error.is_open()) { \t\t\terror << "No file " << '"' << "input.txt" << '"' << endl; \t\t\terror << "Please , create a file" << '"' << "input.txt" << '"' << endl; \t\t\terror << "One read:input number" << endl; \t\t\terror << "Two read:input max stepen" << endl; \t\t\terror << "." << endl; \t\t\terror.close(); \t\t\tINPUT_NUMBER[0] = 1; \t\t\tMax_Degree_of[0] = 1; \t\t} \t} \t\/\/\u0440\u0430\u0441\u0441\u043a\u043e\u043c\u0435\u0442\u0440\u0438\u0440\u0443\u0439\u0442\u0435 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0439 \u043a\u043e\u0434 , \u0435\u0441\u043b\u0438 \u0445\u043e\u0442\u0438\u0442\u0435 \u0432\u0438\u0434\u0435\u0442\u044c \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f \u0432 \u043e\u043a\u043d\u0435 \u043a\u043e\u043d\u0441\u043e\u043b\u0438  \t\/\/cout << INPUT[0] << endl; \tbool *Elements_that_need_to_stop = new bool[size]; \tParallelize_to_threads(Number, Degree_of, Elements_that_need_to_stop, INPUT_NUMBER, Max_Degree_of, size); \tvector<unsigned long long>NUMBER, DEGREEOF; \tfor (int i = 0; i < size; i++) { \t\tif (Elements_that_need_to_stop[i]) { \t\t\tif (Degree_of[i] < INPUT_NUMBER[0] && Number[i] < INPUT_NUMBER[0]) {\/\/\u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u043d\u0430 \u043e\u0448\u0438\u0431\u043a\u0438  \t\t\t\tNUMBER.push_back(Number[i]); \t\t\t\tDEGREEOF.push_back(Degree_of[i]); \t\t\t} \t\t} \t} \t\/\/\u0440\u0430\u0441\u0441\u043a\u043e\u043c\u0435\u0442\u0440\u0438\u0440\u0443\u0439\u0442\u0435 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0439 \u043a\u043e\u0434 , \u0435\u0441\u043b\u0438 \u0445\u043e\u0442\u0438\u0442\u0435 \u0432\u044b\u0432\u0435\u0441\u0442\u0438 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u0432 \u043a\u043e\u043d\u0441\u043e\u043b\u044c \t\/\/\u044d\u0442\u043e \u043c\u043e\u0436\u0435\u0442 \u0437\u0430\u043c\u0435\u0434\u043b\u0438\u0442\u044c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443  \t\/* \tfor (int f = 0; f < NUMBER.size(); f++) { \t\t\tcout << NUMBER[f] << "^" << DEGREEOF[f] << "=" << INPUT_NUMBER[0] << endl; \t\t} \t\t*\/ \tofstream out("out.txt"); \tif (out.is_open()) { \t\tfor (int f = 0; f < NUMBER.size(); f++) { \t\t\tout << NUMBER[f] << "^" << DEGREEOF[f] << "=" << INPUT_NUMBER[0] << endl; \t\t} \t\tout.close(); \t} } void Parallelize_to_threads(unsigned long long  *Number, unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT, unsigned long long  *max, int size) { \tthread *T = new thread[size]; \tRunning_thread_counter = 0; \tfor (int i = 0; i < size; i++) { \t\tT[i] = thread(Upload_to_CPU, Number, Stepn, Stop, INPUT, max, i); \t\tT[i].detach(); \t} \twhile (Running_thread_counter < size - 1);\/\/\u0434\u043e\u0436\u0434\u0430\u0442\u044c\u0441\u044f \u0437\u0430\u0432\u0435\u0440\u0448\u0435\u043d\u0438\u044f \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0432\u0441\u0435\u0445 \u043f\u043e\u0442\u043e\u043a\u043e\u0432  } <\/code><\/pre>\n
  <\/div>\n<\/p><\/div>\n
  \u0414\u043b\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u0430\u0439\u043b \u0441 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u043c \u0447\u0438\u0441\u043b\u043e\u043c \u0438 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0439 \u0441\u0442\u0435\u043f\u0435\u043d\u044c\u044e. <\/p>\n
                         \u041a\u043e\u0434 \u0434\u043b\u044f  \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439  \u043d\u0430 GPU<\/b>                         <\/p>\n
\n
\/\/\u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 cuda_runtime.h \u0438 device_launch_parameters.h \/\/\u0434\u043b\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u0441 cyda #include "cuda_runtime.h" #include "device_launch_parameters.h" #include<vector> #include<string>\/\/\u0434\u043b\u044f getline #include <stdio.h> #include<fstream> using namespace std; __global__ void Upload_to_GPU(unsigned long long  *Number,unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT,unsigned long long  *max) { \tint thread = threadIdx.x; \tunsigned long long  MAX_DEGREE_OF = max[0];     int X = thread; \tunsigned long long  Calculated_number = 1; \tunsigned long long  Current_degree_of_number = 2;     unsigned long long   Original_numberP = INPUT[0]; \tStop[thread] = false; \tbool BREAK = false; \tif (X!=0&&X!=1) { \t\twhile (!BREAK) { \t\t\tif (Current_degree_of_number <= MAX_DEGREE_OF) { \t\t\t\tCalculated_number = 1; \t\t\t\tfor (int counter = 0; counter < Current_degree_of_number; counter++) { \t\t\t\t Calculated_number\t*=X; \t\t\t\t} \t\t\t\tif (Calculated_number == Original_numberP) { \t\t\t\t\tStepn[thread] = Current_degree_of_number; \t\t\t\t\tNumber[thread] = X; \t\t\t\t\tStop[thread] = true; \t\t\t\t\tBREAK = true; \t\t\t\t} \t\t\t\tCurrent_degree_of_number++; \t\t\t} \t\t\telse { BREAK = true; } \t\t} \t} } cudaError_t Configure_cuda(unsigned long long *Number, unsigned long long  *Stepn, bool *Stop,unsigned long long  *INPUT, unsigned long long  *max,unsigned int size); int main() { \tint size = 1000;     unsigned long long  *Number=new unsigned long long [size], *Degree_of=new unsigned long long [size]; \tunsigned long long  *Max_degree_of = new unsigned long long [1]; \tunsigned long long  *INPUT_NUMBER = new unsigned long long [1];    Max_degree_of[0] = 7900; \t \t \tifstream inp("input.txt"); \tif (inp.is_open()) { \t\tstring text; \t\tvector<unsigned long long>IN; \t\twhile (getline(inp, text)) { \t\t\tIN.push_back( stol(text)); \t\t\t\t \t\t} \t\tINPUT_NUMBER[0] = IN[0]; \t\tMax_degree_of[0] = IN[1]; \t} \telse { \t\tofstream error("error.txt"); \t\tif (error.is_open()) { \t\t\terror<<"No file "<<'"'<<"input.txt"<<'"'<<endl; \t\t\terror<<"Please , create a file" << '"' << "input.txt" << '"' << endl; \t\t\terror << "One read:input number" << endl; \t\t\terror << "Two read:input max stepen" << endl; \t\t\terror << "." << endl; \t\t\terror.close(); \t\t\tINPUT_NUMBER[0] = 1; \t\t\tMax_degree_of[0] = 1; \t\t} \t} \t \t \tbool *Elements_that_need_to_stop = new bool[size];     \/\/ \u0417\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u043c\u0430\u0441\u0441\u0438\u0432\u043e\u0432 \u0432 cuda \tcudaError_t cudaStatus =  Configure_cuda(Number, Degree_of, Elements_that_need_to_stop, INPUT_NUMBER, Max_degree_of, size);     if (cudaStatus != cudaSuccess) {         fprintf(stderr, "addWithCuda failed!");         return 1;     } \tvector<unsigned long long>NUMBER, DEGREEOF; \tfor (int i = 0; i < size; i++) { \t\tif (Elements_that_need_to_stop[i]) { \t\t\tNUMBER.push_back(Number[i]);\/\/\u0437\u0430\u043d\u0435\u0441\u0442\u0438 \u0432 \u0432\u0435\u043a\u0442\u043e\u0440 \u0447\u0438\u0441\u043b\u043e \t\t\tDEGREEOF.push_back(Degree_of[i]);\/\/\u0437\u0430\u043d\u0435\u0441\u0442\u0438 \u0432 \u0432\u0435\u043a\u0442\u043e\u0440 \u0441\u0442\u0435\u043f\u0435\u043d\u044c \u0447\u0438\u0441\u043b\u0430 \t\t} \t} \t\/\/\u0440\u0430\u0441\u043a\u043e\u043c\u0435\u043d\u0442\u0438\u0440\u0443\u0439\u0442\u0435 \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0439 \u043a\u043e\u0434 , \u0447\u0442\u043e\u0431\u044b \u0432\u044b\u0432\u0435\u0441\u0442\u0438 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u0432 \u043a\u043e\u043d\u0441\u043e\u043b\u044c \t\/* \tfor (int f = 0; f < NUMBER.size(); f++) { \t\tcout << NUMBER[f] << "^" << DEGREEOF[f] << "=" << INPUT_NUMBER[0] << endl; \t}*\/ \tofstream out("out.txt"); \tif (out.is_open()) { \t\tfor (int f = 0; f < NUMBER.size(); f++) { \t\t\tout << NUMBER[f] << "^" << DEGREEOF[f] << "=" << INPUT_NUMBER[0] << endl; \t\t} \t\tout.close(); \t} \t     \/\/\u041e\u0447\u0438\u0441\u0442\u0438\u0442\u044c \u0440\u0435\u0441\u0443\u0440\u0441\u044b \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u043e\u043c     cudaStatus = cudaDeviceReset();     if (cudaStatus != cudaSuccess) {         fprintf(stderr, "cudaDeviceReset failed!");         return 1;     }      return 0; }   cudaError_t  Configure_cuda(unsigned long long  *Number, unsigned long long *Degree_of, bool *Stop,unsigned long long *INPUT, unsigned long long *max,unsigned int size) { \tunsigned long long *dev_Number = 0; \tunsigned long long *dev_Degree_of = 0; \tunsigned long long *dev_INPUT = 0; \tunsigned long long *dev_Max = 0; \tbool *dev_Elements_that_need_to_stop;  \tcudaError_t cudaStatus;  \t\/\/ \u0423\u0421\u0422\u0410\u041d\u041e\u0412\u041a\u0410 \u0418\u0421\u041f\u041e\u041b\u042c\u0417\u0423\u0415\u041c\u041e\u0413\u041e GPU  \tcudaStatus = cudaSetDevice(0); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?"); \t\tgoto Error; \t}  \t\/\/ \u0420\u0415\u0417\u0415\u0420\u0412\u0418\u0420\u041e\u0412\u0410\u041d\u0418\u0415 \u041c\u0415\u0421\u0422\u0410 \u0412 \u041f\u0410\u041c\u042f\u0422\u0418 \u041f\u041e\u0414 \u0414\u0410\u041d\u041d\u042b\u0415 \tcudaStatus = cudaMalloc((void**)&dev_Number, size * sizeof(unsigned long long)); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMalloc failed!dev_Number"); \t\tgoto Error; \t} \tcudaStatus = cudaMalloc((void**)&dev_Degree_of, size * sizeof(unsigned long long)); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMalloc failed!dev_Degree_of"); \t\tgoto Error; \t} \tcudaStatus = cudaMalloc((void**)&dev_Max, size * sizeof(unsigned long long int)); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMalloc failed!dev_Max"); \t\tgoto Error; \t} \tcudaStatus = cudaMalloc((void**)&dev_INPUT, size * sizeof(unsigned long long)); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMalloc failed!dev_INPUT"); \t\tgoto Error; \t} \tcudaStatus = cudaMalloc((void**)&dev_Elements_that_need_to_stop, size * sizeof(bool)); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMalloc failed!dev_Stop"); \t\tgoto Error; \t} \t\/\/ \u041f\u0415\u0420\u0415\u041c\u0415\u0429\u0415\u041d\u0418\u0415 \u0414\u0410\u041d\u041d\u042b\u0425 \u0412 \u041f\u0410\u041c\u042f\u0422\u042c GPU \tcudaStatus = cudaMemcpy(dev_Max, max, size * sizeof(unsigned long long), cudaMemcpyHostToDevice); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMemcpy failed!"); \t\tgoto Error; \t} \tcudaStatus = cudaMemcpy(dev_INPUT, INPUT, size * sizeof(unsigned long long), cudaMemcpyHostToDevice); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMemcpy failed!"); \t\tgoto Error; \t} \tUpload_to_GPU<<<1, size>>>(dev_Number, dev_Degree_of, dev_Elements_that_need_to_stop, dev_INPUT, dev_Max); \t\/\/ \u041f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u0441\u0431\u043e\u0435\u0432 \u044f\u0434\u0440\u0430 \tcudaStatus = cudaGetLastError(); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "addKernel launch failed: %s\\n", cudaGetErrorString(cudaStatus)); \t\tgoto Error; \t}  \t\/\/ \u041e\u0436\u0438\u0434\u0430\u043d\u0438\u0435 \u0437\u0430\u0432\u0435\u0440\u0448\u0435\u043d\u0438\u044f \u043e\u043f\u0435\u0440\u0430\u0446\u0438\u0439 , \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0445 \u044f\u0434\u0440\u043e\u043c  \tcudaStatus = cudaDeviceSynchronize(); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\\n", cudaStatus); \t\tgoto Error; \t}  \t\/\/ \u041f\u0435\u0440\u0435\u043c\u0435\u0449\u0435\u043d\u0438\u0435 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438\u0437 \u043f\u0430\u043c\u044f\u0442\u0438 GPU \u0432 \u0441\u0438\u0441\u0442\u0435\u043c\u043d\u0443\u044e \u043f\u0430\u043c\u044f\u0442\u044c \tcudaStatus = cudaMemcpy(Number, dev_Number, size * sizeof(unsigned long long), cudaMemcpyDeviceToHost); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMemcpy failed!"); \t\tgoto Error; \t} \tcudaStatus = cudaMemcpy(Degree_of, dev_Degree_of, size * sizeof(unsigned long long), cudaMemcpyDeviceToHost); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMemcpy failed!"); \t\tgoto Error; \t} \tcudaStatus = cudaMemcpy(Stop, dev_Elements_that_need_to_stop, size * sizeof(bool), cudaMemcpyDeviceToHost); \tif (cudaStatus != cudaSuccess) { \t\tfprintf(stderr, "cudaMemcpy failed!"); \t\tgoto Error; \t} Error:\/\/\u041e\u0441\u0432\u043e\u0431\u043e\u0436\u0434\u0435\u043d\u0438\u0435 \u043f\u0430\u043c\u044f\u0442\u0438 GPU \u043e\u0442 \u0434\u0430\u043d\u043d\u044b\u0445 \tcudaFree(dev_INPUT); \tcudaFree(dev_Degree_of); \tcudaFree(dev_Max); \tcudaFree(dev_Elements_that_need_to_stop); \tcudaFree(dev_Number);  \treturn cudaStatus; } <\/code><\/pre>\n
  <\/div>\n<\/p><\/div>\n
   \u0418\u0434\u0435\u043d\u0442\u0438\u0444\u0438\u043a\u0430\u0442\u043e\u0440 <\/p>\n
__global__  <\/code><\/pre>\n
 \u0432 .cu \u0444\u0430\u0439\u043b\u0435<\/i> \u0443\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442, \u0447\u0442\u043e \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u0442\u0441\u044f \u043d\u0430 \u0443\u0440\u043e\u0432\u043d\u0435 \u044f\u0434\u0440\u0430 GPU. <\/p>\n
  \u0414\u043b\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u0441 cyda, \u043f\u0435\u0440\u0435\u0434 \u0432\u044b\u0437\u043e\u0432\u043e\u043c \u0444\u0443\u043d\u043a\u0446\u0438\u0438, \u043d\u0443\u0436\u043d\u043e \u0437\u0430\u0440\u0435\u0437\u0435\u0440\u0432\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043f\u0430\u043c\u044f\u0442\u044c \u043f\u043e\u0434 \u043c\u0430\u0441\u0441\u0438\u0432 \u0438 \u043f\u0435\u0440\u0435\u043d\u0435\u0441\u0442\u0438 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u044b \u0432 \u043f\u0430\u043c\u044f\u0442\u044c GPU. \u042d\u0442\u043e \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0432\u0430\u0435\u0442 \u043e\u0431\u044a\u0435\u043c \u043a\u043e\u0434\u0430, \u043d\u043e \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 \u0440\u0430\u0437\u0433\u0440\u0443\u0437\u0438\u0442\u044c CPU, \u0442\u0430\u043a \u043a\u0430\u043a \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u044f\u0442\u0441\u044f \u043d\u0430 GPU.\u041f\u043e\u044d\u0442\u043e\u043c\u0443 ,cuda, \u0434\u0430\u0435\u0442 \u043a\u0430\u043a \u043c\u0438\u043d\u0438\u043c\u0443\u043c \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0441\u0442\u044c \u0440\u0430\u0437\u0433\u0440\u0443\u0437\u0438\u0442\u044c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u0434\u043b\u044f \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0434\u0440\u0443\u0433\u0438\u0445 \u043d\u0430\u0433\u0440\u0443\u0437\u043e\u043a, \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0449\u0438\u0445 cuda.<\/p>\n
  \u0412 \u0441\u043b\u0443\u0447\u0430\u0435 \u043f\u0440\u0438\u043c\u0435\u0440\u0430 \u043d\u0430 cuda, \u0437\u0430\u0434\u0430\u0447\u0430 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430 \u0437\u0430\u043a\u043b\u044e\u0447\u0430\u0435\u0442\u0441\u044f \u043b\u0438\u0448\u044c \u0432 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439 \u043d\u0430 GPU \u0438 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u043e\u0432 \u043f\u0440\u0438\u0448\u0435\u0434\u0448\u0438\u0445 \u0441 GPU; \u0412 \u0442\u043e \u0432\u0440\u0435\u043c\u044f \u043a\u0430\u043a \u0432 \u043a\u043e\u0434\u0435 \u0434\u043b\u044f CPU, \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u043e\u0431\u0440\u0430\u0431\u0430\u0442\u044b\u0432\u0430\u0435\u0442 \u043a\u0430\u0436\u0434\u044b\u0439 \u043f\u043e\u0442\u043e\u043a. \u0421\u0442\u043e\u0438\u0442 \u043e\u0442\u043c\u0435\u0442\u0438\u0442\u044c, \u0447\u0442\u043e cyda \u0438\u043c\u0435\u0435\u0442 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u0438\u044f \u043f\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0443 \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0435\u043c\u044b\u0445 \u043f\u043e\u0442\u043e\u043a\u043e\u0432, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0432 \u043e\u0431\u043e\u0438\u0445 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430\u0445 \u044f \u0432\u0437\u044f\u043b \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u043e\u0435 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u043f\u043e\u0442\u043e\u043a\u043e\u0432, \u0440\u0430\u0432\u043d\u043e\u0435 1000. \u0422\u0430\u043a\u0436\u0435, \u0432 \u0441\u043b\u0443\u0447\u0430\u0435 \u0441 CPU \u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b \u043f\u0435\u0440\u0435\u043c\u0435\u043d\u043d\u0443\u044e <\/p>\n
int\u00a0Running_thread_counter\u00a0=\u00a00;<\/code><\/pre>\n
  \u0447\u0442\u043e\u0431\u044b \u0441\u0447\u0438\u0442\u0430\u0442\u044c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0443\u0436\u0435 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u043d\u044b\u0445 \u043f\u043e\u0442\u043e\u043a\u043e\u0432 \u0438 \u0434\u043e\u0436\u0438\u0434\u0430\u0442\u044c\u0441\u044f, \u043f\u043e\u043a\u0430 \u0432\u0441\u0435 \u043f\u043e\u0442\u043e\u043a\u0438 \u043d\u0435 \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0442\u0441\u044f. <\/p>\n
                         \u0422\u0435\u0441\u0442\u0438\u0440\u0443\u0435\u043c\u0430\u044f \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u044f<\/b>                         <\/p>\n
\n