remove openmp dependency

time may not be accurate (now using processor time instead of real time)

Makefile

@@ -27,8 +27,8 @@ TESTS_SRC_CU += $(wildcard $(TEST_SRCDIR)/*.cu)
 TESTS_OBJ     = $(TESTS_SRC:$(TEST_SRCDIR)/%.c=$(BUILDDIR)/$(TEST_SRCDIR)-%) $(TESTS_SRC_CU:$(TEST_SRCDIR)/%.cu=$(BUILDDIR)/$(TEST_SRCDIR)-%)
 
 # Linker only flags
-LD_CFLAGS    =  -lm -lpthread -ljpeg -fopenmp
+LD_CFLAGS    =  -lm -lpthread -ljpeg
-LD_NVCCFLAGS = -ljpeg -Xcompiler -fopenmp
+LD_NVCCFLAGS = -ljpeg
 
 # Compilation flag
 CFLAGS    = -Wall -Wextra -std=gnu99 -g -O3

src/cnn/train.c

@@ -5,7 +5,7 @@
 #include <float.h>
 #include <math.h>
 #include <time.h>
-#include <omp.h>
+#include <time.h>
 
 #include "../common/include/memory_management.h"
 #include "../common/include/colors.h"
@@ -64,7 +64,7 @@ void* train_thread(void* parameters) {
     float loss = 0.;
 
     #ifdef DETAILED_TRAIN_TIMINGS
-        double start_time;
+        clock_t start_time;
     #endif
 
     pthread_t tid;
@@ -81,16 +81,16 @@ void* train_thread(void* parameters) {
             write_image_in_network_32(images[index[i]], height, width, network->input[0][0], param->offset);
 
             #ifdef DETAILED_TRAIN_TIMINGS
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
             forward_propagation(network);
 
             #ifdef DETAILED_TRAIN_TIMINGS
                 printf("Temps de forward: ");
-                printf_time(omp_get_wtime() - start_time);
+                printf_time(clock() - start_time);
                 printf("\n");
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
             maxi = indice_max(network->input[network->size-1][0][0], 10);
@@ -108,9 +108,9 @@ void* train_thread(void* parameters) {
 
             #ifdef DETAILED_TRAIN_TIMINGS
                 printf("Temps de backward: ");
-                printf_time(omp_get_wtime() - start_time);
+                printf_time(clock() - start_time);
                 printf("\n");
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
             if (maxi == labels[index[i]]) {
@@ -131,16 +131,16 @@ void* train_thread(void* parameters) {
             write_256_image_in_network(param->dataset->images[index[i]], width, height, param->dataset->numComponents, network->width[0], network->input[0]);
 
             #ifdef DETAILED_TRAIN_TIMINGS
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
             forward_propagation(network);
 
             #ifdef DETAILED_TRAIN_TIMINGS
                 printf("Temps de forward: ");
-                printf_time(omp_get_wtime() - start_time);
+                printf_time(clock() - start_time);
                 printf("\n");
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
             maxi = indice_max(network->input[network->size-1][0][0], param->dataset->numCategories);
@@ -148,9 +148,9 @@ void* train_thread(void* parameters) {
             
             #ifdef DETAILED_TRAIN_TIMINGS
                 printf("Temps de backward: ");
-                printf_time(omp_get_wtime() - start_time);
+                printf_time(clock() - start_time);
                 printf("\n");
-                start_time = omp_get_wtime();
+                start_time = clock();
             #endif
 
 
@@ -179,7 +179,7 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
         exit(1);
     }
     #endif
-    srand(time(NULL));
+    srand(clock());
     float loss;
     float batch_loss; // May be redundant with loss, but gives more informations
     float test_accuracy = 0.; // Used to decrease Learning rate
@@ -190,12 +190,12 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
 
 
     //* Différents timers pour mesurer les performance en terme de vitesse
-    double start_time, end_time;
+    clock_t start_time, end_time;
-    double elapsed_time;
+    clock_t elapsed_time;
 
-    double algo_start = omp_get_wtime();
+    clock_t algo_start = clock();
 
-    start_time = omp_get_wtime();
+    start_time = clock();
 
 
     //* Chargement du dataset
@@ -320,7 +320,7 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
         train_params->finetuning = finetuning;
     #endif
 
-    end_time = omp_get_wtime();
+    end_time = clock();
 
     elapsed_time = end_time - start_time;
     printf("Taux d'apprentissage initial: %0.2e\n", network->learning_rate);
@@ -331,7 +331,7 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
     //* Boucle d'apprentissage
     for (int i=0; i < epochs; i++) {
 
-        start_time = omp_get_wtime();
+        start_time = clock();
         // La variable accuracy permet d'avoir une ESTIMATION
         // du taux de réussite et de l'entraînement du réseau,
         // mais n'est en aucun cas une valeur réelle dans le cas
@@ -423,7 +423,7 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
             #endif
         }
         //* Fin d'une époque: affichage des résultats et sauvegarde du réseau
-        end_time = omp_get_wtime();
+        end_time = clock();
         elapsed_time = end_time - start_time;
         #ifdef USE_MULTITHREADING
         printf("\rThreads [%d]\tÉpoque [%d/%d]\tImage [%d/%d]\tAccuracy: " GREEN "%0.4f%%" RESET " \tLoss: %lf\tTemps: ", nb_threads, i, epochs, nb_images_total, nb_images_total, accuracy*100, loss);
@@ -483,7 +483,7 @@ void train(int dataset_type, char* images_file, char* labels_file, char* data_di
         free_dataset(dataset);
     }
 
-    end_time = omp_get_wtime();
+    end_time = clock();
     elapsed_time = end_time - algo_start;
     printf("\nTemps total: ");
     printf_time(elapsed_time);

src/common/colors.c

@@ -1,5 +1,6 @@
 #include <stdio.h>
 #include <stdbool.h>
+#include <time.h>
 
 #include "include/colors.h"
 
@@ -15,11 +16,13 @@ void printf_info(char* string) {
     printf(BOLDBLUE "[ INFO  ]" RESET " %s", string);
 }
 
-void printf_time(float time) {
+void printf_time(clock_t time) {
-    int hours = time/3600;
+    double real_time = (double) time / CLOCKS_PER_SEC;
-    int minutes = ((int)time %3600)/60;
+
-    int seconds = ((int)time) %60;
+    int hours = real_time/3600;
-    int milliseconds = (time - (int)time)*1000;
+    int minutes = ((int)real_time %3600)/60;
+    int seconds = ((int)real_time) %60;
+    int milliseconds = (real_time - (int)real_time)*1000;
 
     if (hours != 0) {
         printf("%dh %dmn", hours, minutes);

src/common/include/colors.h

@@ -1,4 +1,5 @@
 #include <stdio.h>
+#include <time.h>
 
 #ifndef DEF_COLORS_H
 #define DEF_COLORS_H
@@ -51,7 +52,7 @@ extern "C"
 /*
 * Affiche un timing en heures minutes secondes millisecondes en limitant la précision aux deux unités les plus significatives
 */
-void printf_time(float time);
+void printf_time(clock_t time);
 
 #ifdef __CUDACC__
 extern "C"

test/cnn_convolution.cu

@@ -4,7 +4,7 @@
 #include <assert.h>
 #include <math.h>
 #include <time.h>
-#include <omp.h>
+#include <time.h>
 
 #include "../src/common/include/memory_management.h"
 #include "../src/cnn/include/convolution.h"
@@ -136,21 +136,21 @@ void run_convolution_test(int input_width, int output_width, int rows, int colum
 
 
     // Lancement des calculs
-    double start_time, end_time;
+    clock_t start_time, end_time;
-    double cpu_time_used, gpu_time_used;
+    clock_t cpu_time_used, gpu_time_used;
 
-    start_time = omp_get_wtime();
+    start_time = clock();
     make_convolution_device(kernel, input, output_gpu, output_width, 1, 0);
-    end_time = omp_get_wtime();
+    end_time = clock();
 
 
     gpu_time_used = end_time - start_time;
     printf("(%d, %d, %d, %d) Time used for GPU: %lf seconds\n", rows, columns, input_width, output_width, gpu_time_used);
 
 
-    start_time = omp_get_wtime();
+    start_time = clock();
     make_convolution_cpu(kernel, input, output_cpu, output_width, 1, 0);
-    end_time = omp_get_wtime();
+    end_time = clock();
 
     cpu_time_used = end_time - start_time;
     printf("(%d, %d, %d, %d) Time used for CPU: %lf seconds\n", rows, columns, input_width, output_width, cpu_time_used);    
@@ -199,7 +199,7 @@ int main() {
     }
     printf(GREEN "OK\n" RESET);
     
-    srand(time(NULL));
+    srand(clock());
 
     run_convolution_test(20, 15, 30, 40);
     run_convolution_test(30, 25, 40, 50);

test/cnn_jpeg.c

@@ -1,6 +1,6 @@
 #include <stdlib.h>
 #include <stdio.h>
-#include <omp.h>
+#include <time.h>
 
 
 #include "../src/common/include/colors.h"
@@ -21,10 +21,10 @@ int main(int argc, char* argv[]) {
     printf("Taille des images:    %dx%d\n", dataset->width, dataset->height);
 
     // Calcul du temps de chargement des images une à une
-    double start_time, end_time;
+    clock_t start_time, end_time;
 
     int N = min(100000, dataset->numImages);
-    start_time = omp_get_wtime();
+    start_time = clock();
     printf("Chargement de %d images\n", N);
     for (int i=0; i < N; i++) {
         imgRawImage* image = loadJpegImageFile(dataset->fileNames[i]);
@@ -32,7 +32,7 @@ int main(int argc, char* argv[]) {
         free(image);
     }
     printf("OK\n");
-    end_time = omp_get_wtime();
+    end_time = clock();
     printf("Temps par image (calculé sur une moyenne de %d): %lf s\n", N, (end_time - start_time)/N);
 
     for (int i=0; i < (int)dataset->numImages; i++) {

test/cnn_matrix_multiplication.cu

@@ -3,7 +3,7 @@
 #include <stdbool.h>
 #include <math.h>
 #include <time.h>
-#include <omp.h>
+#include <time.h>
 
 #include "../src/cnn/include/matrix_multiplication.h"
 #include "../src/common/include/memory_management.h"
@@ -72,8 +72,8 @@ bool check_matrices_equality(float** m1, float** m2, int n, int p, int acceptati
 }
 
 void run_matrices_test(int n, int p, int q) {
-    double start_time, end_time;
+    clock_t start_time, end_time;
-    double cpu_time_used, gpu_time_used;
+    clock_t cpu_time_used, gpu_time_used;
 
     float** matrix1 = create_matrix(n, p);
     float** matrix2 = create_matrix(p, q);
@@ -81,16 +81,16 @@ void run_matrices_test(int n, int p, int q) {
     float** result_cpu = create_empty_matrix(n, q);
 
     printf("(%d,%d)x(%d,%d) Data generation complete.\n", n, p, p, q);
-    start_time = omp_get_wtime();
+    start_time = clock();
     matrix_multiplication_device(matrix1, matrix2, result_gpu, n, p, q);
-    end_time = omp_get_wtime();
+    end_time = clock();
 
     cpu_time_used = end_time - start_time;
     printf("(%d,%d)x(%d,%d) Time used for GPU: %lf seconds\n", n, p, p, q, cpu_time_used);
     
-    start_time = omp_get_wtime();
+    start_time = clock();
     matrix_multiplication_host(matrix1, matrix2, result_cpu, n, p, q);
-    end_time = omp_get_wtime();
+    end_time = clock();
 
     gpu_time_used = end_time - start_time;
     printf("(%d,%d)x(%d,%d) Time used for CPU: %lf seconds\n", n, p, p, q, gpu_time_used);
@@ -134,7 +134,7 @@ int main() {
     }
     printf(GREEN "OK\n" RESET);
 
-    srand(time(NULL));
+    srand(clock());
     run_matrices_test(200, 1000, 200);
     run_matrices_test(200, 1000, 20);
     run_matrices_test(20, 1000, 200);