Start devloping vulkan

Xenith/core.cpp

@@ -1,6 +1,9 @@
-#include "core.h"
+#include "core.hpp"
 #include <cmath>
 #include <cstdlib>
+#include <omp.h> 
+
+#define MAX_CORES 16
 
 NeuralNetwork::NeuralNetwork(LayerStructure_t layers[], int count) : numLayers(count) {
     for (int i = 0; i < count; i++) sizes.push_back(layers[i].size);
@@ -39,29 +42,42 @@ std::vector<double> NeuralNetwork::feedForward(const std::vector<double>& input)
 
 
 double NeuralNetwork::train(const std::vector<double>& input, const std::vector<double>& target, double lr) {
-    std::vector<double> pred = feedForward(input);
+    omp_set_num_threads(MAX_CORES);
 
+    std::vector<double> pred = feedForward(input);
     std::vector<std::vector<double>> errors(numLayers);
     errors[numLayers - 1].resize(sizes[numLayers - 1]);
-
+    
     double totalErr = 0;
-    for (int i = 0; i < sizes[numLayers-1]; i++) {
+
+    for (int i = 0; i < sizes[numLayers - 1]; i++) {
         double e = target[i] - pred[i];
-        errors[numLayers-1][i] = e * pred[i] * (1.0 - pred[i]);
+        errors[numLayers - 1][i] = e * pred[i] * (1.0 - pred[i]);
         totalErr += e * e;
     }
+
     for (int i = numLayers - 2; i > 0; i--) {
         errors[i].resize(sizes[i]);
+    
+        #pragma omp parallel for
         for (int j = 0; j < sizes[i]; j++) {
             double e = 0;
-            for (int k = 0; k < sizes[i+1]; k++) e += errors[i+1][k] * weights[i][k][j];
+            for (int k = 0; k < sizes[i + 1]; k++) {
+                e += errors[i + 1][k] * weights[i][k][j];
+            }
             errors[i][j] = e * outputs[i][j] * (1.0 - outputs[i][j]);
         }
     }
     for (int i = 0; i < numLayers - 1; i++) {
-        for (int j = 0; j < sizes[i+1]; j++) {
-            for (int k = 0; k < sizes[i]; k++) weights[i][j][k] += lr * errors[i+1][j] * outputs[i][k];
-            biases[i][j] += lr * errors[i+1][j];
+        #pragma omp parallel for
+        for (int j = 0; j < sizes[i + 1]; j++) {
+            double errorTerm = lr * errors[i + 1][j];
+            
+            // Вложенный цикл обновления весов
+            for (int k = 0; k < sizes[i]; k++) {
+                weights[i][j][k] += errorTerm * outputs[i][k];
+            }
+            biases[i][j] += errorTerm;
         }
     }