From 3a901a0a409ffcb620c65da9faa1994ea2c434bf Mon Sep 17 00:00:00 2001
From: Seth Hamilton <shamilton@the-embedded-lab.com>
Date: Thu, 21 Aug 2025 00:41:51 -0500
Subject: [PATCH] working through compile bugs

---
 inc/genetic.h   |  28 +++++---
 src/genetic.cpp | 180 ++++++++++++++++++++++++++++++++++++------------
 src/main.cpp    | 174 ++++++++++++++++------------------------------
 3 files changed, 215 insertions(+), 167 deletions(-)

diff --git a/inc/genetic.h b/inc/genetic.h
index 9a32d83..61bae51 100644
--- a/inc/genetic.h
+++ b/inc/genetic.h
@@ -2,8 +2,7 @@
 
 namespace genetic {
 
-template <class T> struct ReadonlySpan;
-template <class T> struct Span;
+template <class T> struct Array;
 template <class T> struct Stats;
 template <class T> struct Strategy;
 
@@ -16,7 +15,8 @@ template <class T> struct Strategy {
                    // before accessing/locking the work queue again.
   int num_cells;   // Size of the population pool
   int num_generations; // Number of times (epochs) to run the algorithm
-  bool test_all; // Sets whether or not every cell is tested every generation
+  bool test_all; // Sets whether or not every cell's fitness is evaluated every
+                 // generation
   float test_chance; // Chance to test any given cell's fitness. Relevant only
                      // if test_all is false.
   bool enable_crossover; // Cells that score well in the evaluation stage
@@ -25,11 +25,17 @@ template <class T> struct Strategy {
   float crossover_mutation_chance; // Chance to mutate a child cell
   int crossover_parent_num;        // Number of unique high-scoring parents in a
                                    // crossover call.
-  int crossover_children_num;      // Number of children to expect the user to
-                                   // produce in the crossover function.
-  bool enable_mutation;            // Cells may be mutated
-                                   // before fitness evaluation
-  float mutation_chance; // Chance to mutate cells before fitness evaluation
+  int crossover_parent_stride; // Number of parents to skip over when moving to
+                               // the next set of parents. A stride of 1 would
+                               // produce maximum overlap because the set of
+                               // parents would only change by one every
+                               // crossover.
+  int crossover_children_num;  // Number of children to expect the user to
+                               // produce in the crossover function.
+  bool enable_mutation;          // Cells may be mutated
+                                 // before fitness evaluation
+  float mutation_chance; // Chance for any given cell to be mutated cells during
+                         // the mutation
   uint64_t rand_seed;
   bool higher_fitness_is_better; // Sets whether or not to consider higher
                                  // fitness values better or worse. Set this to
@@ -38,16 +44,16 @@ template <class T> struct Strategy {
   // User defined functions
   T (*make_default_cell)();
   void (*mutate)(T &cell_to_modify);
-  void (*crossover)(const Span<T *> parents, const Span<T *> out_children);
+  void (*crossover)(const Array<T *> parents, const Array<T *> out_children);
   float (*fitness)(const T &cell);
 };
 
 template <class T> struct Stats {
   std::vector<T> best_cell;
-  std::vector<float> average_fitness;
+  std::vector<float> best_cell_fitness;
 };
 
-template <class T> struct Span {
+template <class T> struct Array {
   T *_data;
   int len;
 
diff --git a/src/genetic.cpp b/src/genetic.cpp
index ab923a4..f89472c 100644
--- a/src/genetic.cpp
+++ b/src/genetic.cpp
@@ -1,9 +1,14 @@
-#include "genetic.h"
-#include "pthread.h"
+#include <algorithm>
+#include <cstdint>
+#include <cstdlib>
 #include <optional>
 #include <variant>
 #include <vector>
 
+#include "genetic.h"
+#include "pthread.h"
+#include "rand.h"
+
 #define NUM_QUEUE_RETRIES 10
 
 using namespace std;
@@ -19,23 +24,27 @@ template <class... Ts> overload(Ts...) -> overload<Ts...>;
 
 namespace genetic {
 
-template <class T> struct CellEntry {
+template <class T> struct cell_entry {
   float score;
   T *cell;
   bool stale;
 };
 
-template <class T> struct CrossoverJob {
-  Span<CellEntry<T> *> &parents;
-  Span<CellEntry<T> *> &children_out;
+template <class T> struct crossover_job {
+  Array<cell_entry<T> *> &parents;
+  Array<cell_entry<T> *> &children_out;
 };
 
-template <class T> struct FitnessJob {
-  CellEntry<T> *cell_entry;
+template <class T> struct fitness_job {
+  cell_entry<T> *cell_entry;
 };
 
-template <class T> struct WorkQueue {
-  variant<CrossoverJob<T>, FitnessJob<T>> *jobs;
+template <class T> struct mutate_job {
+  cell_entry<T> *cell_entry;
+};
+
+template <class T> struct work_queue {
+  variant<crossover_job<T>, fitness_job<T>, mutate_job<T>> *jobs;
   int len;
   int read_i;
   int write_i;
@@ -49,9 +58,9 @@ template <class T> struct WorkQueue {
   pthread_cond_t jobs_available_cond;
 };
 
-template <class T> WorkQueue<T> make_work_queue(int len) {
-  return {.jobs = (variant<FitnessJob<T>, CrossoverJob<T>> *)malloc(
-              sizeof(variant<FitnessJob<T>, CrossoverJob<T>>) * len),
+template <class T> work_queue<T> make_work_queue(int len) {
+  return {.jobs = (variant<fitness_job<T>, crossover_job<T>> *)malloc(
+              sizeof(variant<fitness_job<T>, crossover_job<T>>) * len),
           .len = len,
           .read_i = 0,
           .write_i = 0,
@@ -63,19 +72,19 @@ template <class T> WorkQueue<T> make_work_queue(int len) {
           .jobs_available_cond = PTHREAD_COND_INITIALIZER};
 }
 
-template <class T> struct JobBatch {
-  ReadonlySpan<variant<CrossoverJob<T>, FitnessJob<T>>> jobs;
+template <class T> struct job_batch {
+  Array<variant<crossover_job<T>, fitness_job<T>>> jobs;
   bool gen_complete;
 };
 
 template <class T>
-optional<JobBatch<T>> get_job_batch(WorkQueue<T> &queue, int batch_size,
-                                    bool *stop_flag) {
+optional<job_batch<T>> get_job_batch(work_queue<T> &queue, int batch_size,
+                                     bool *stop_flag) {
   while (true) {
     for (int i = 0; i < NUM_QUEUE_RETRIES; i++) {
       if (queue.read_i < queue.write_i &&
           pthread_mutex_trylock(&queue.data_mutex)) {
-        JobBatch<T> res;
+        job_batch<T> res;
         res.jobs._data = &queue._jobs[queue.read_i];
         int span_size = min(batch_size, queue.write_i - queue.read_i);
         res.jobs.len = span_size;
@@ -94,27 +103,41 @@ optional<JobBatch<T>> get_job_batch(WorkQueue<T> &queue, int batch_size,
   }
 }
 
-template <class T> struct WorkerThreadArgs {
+template <class T> struct worker_thread_args {
   Strategy<T> &strat;
-  WorkQueue<T> &queue;
+  work_queue<T> &queue;
   bool *stop_flag;
 };
 
-template <class T> void do_crossover_job(CrossoverJob<T> cj) {}
-
 template <class T> void *worker(void *args) {
-  WorkerThreadArgs<T> *work_args = (WorkerThreadArgs<T> *)args;
+  worker_thread_args<T> *work_args = (worker_thread_args<T> *)args;
   Strategy<T> &strat = work_args->strat;
-  WorkQueue<T> &queue = work_args->queue;
+  work_queue<T> &queue = work_args->queue;
   bool *stop_flag = work_args->stop_flag;
 
-  auto JobDispatcher = overload{
-      [strat](FitnessJob<T> fj) {
-        fj.cell_entry->result_out = strat.fitness(*(fj.cell_entry->cell));
-        fj.cell_entry->stale = true;
+  auto job_dispatcher = overload{
+      [strat](mutate_job<T> mj) {
+        strat.mutate(*mj.cell_entry->cell);
+        mj.cell_entry->stale = true;
       },
-      [strat](CrossoverJob<T> cj) {
-        strat.crossover(cj.parents, cj.children_out);
+      [strat](fitness_job<T> fj) {
+        fj.cell_entry->score = strat.fitness(*fj.cell_entry->cell);
+        fj.cell_entry->stale = false;
+      },
+      [strat](crossover_job<T> cj) {
+        Array<T *> parent_cells, child_cells;
+        parent_cells = {(T **)malloc(sizeof(T *) * cj.parents.len),
+                        cj.parents.len};
+        child_cells = {(T **)malloc(sizeof(T *) * cj.children_out.len),
+                       cj.children_out.len};
+        for (int i = 0; i < cj.parents.len; i++) {
+          parent_cells[i] = cj.parents[i].cell;
+        }
+        for (int i = 0; i < cj.children_out.len; i++) {
+          child_cells[i] = cj.children_out[i].cell;
+          cj.children_out[i].stale = true;
+        }
+        strat.crossover(parent_cells, child_cells);
       },
   };
 
@@ -125,7 +148,7 @@ template <class T> void *worker(void *args) {
 
     // Do the actual work
     for (int i = 0; i < batch->jobs.len; i++) {
-      visit(JobDispatcher, batch->jobs[i]);
+      visit(job_dispatcher, batch->jobs[i]);
     }
 
     if (batch->gen_complete) {
@@ -136,20 +159,24 @@ template <class T> void *worker(void *args) {
 
 template <class T> Stats<T> run(Strategy<T> strat) {
   Stats<T> stats;
-  WorkQueue<T> work_queue = make_work_queue<T>(strat.num_cells);
 
+  // The work queue is what all the worker threads will checking
+  // for jobs
+  work_queue<T> queue = make_work_queue<T>(strat.num_cells);
+
+  // The actual cells. Woo!
   T cells[strat.num_cells];
 
   // Using a vector so I can use the make_heap, push_heap, etc.
-  vector<CellEntry<T>> cell_queue;
+  vector<cell_entry<T>> cell_queue;
   for (int i = 0; i < strat.num_cells; i++) {
     cells[i] = strat.make_default_cell();
     cell_queue.push_back({0, &cells[i], true});
   }
 
   bool stop_flag = false;
-  WorkerThreadArgs<T> args = {
-      .strat = strat, .queue = work_queue, .stop_flag = &stop_flag};
+  worker_thread_args<T> args = {
+      .strat = strat, .queue = queue, .stop_flag = &stop_flag};
 
   // spawn worker threads
   pthread_t threads[strat.num_threads];
@@ -157,28 +184,95 @@ template <class T> Stats<T> run(Strategy<T> strat) {
     pthread_create(&threads[i], NULL, worker<T>, (void *)args);
   }
 
-  for (int i = 0; i < strat.num_generations; i++) {
-    // generate fitness jobs
-    if (strat.test_all) {
+  uint64_t rand_state = strat.rand_seed;
 
-    } else {
+  for (int i = 0; i < strat.num_generations; i++) {
+    // Mutate some random cells in the population
+    for (int i = 0; i < cell_queue.size(); i++) {
+      if (abs(norm_rand(rand_state)) < strat.mutation_chance) {
+        queue.jobs[queue.write_i] = mutate_job<T>{&cell_queue[i]};
+        queue.write_i++;
+      }
     }
+    pthread_cond_broadcast(&queue.jobs_available_cond);
+
+    // Potential issue here where mutations aren't done computing and fitness
+    // jobs begin. maybe need to gate this.
+
+    // Generate fitness jobs
+    for (int i = 0; i < cell_queue.size(); i++) {
+      if (cell_queue[i].stale &&
+          (strat.test_all || abs(norm_rand(rand_state)) < strat.test_chance)) {
+        queue.jobs[queue.write_i] = fitness_job<T>{&cell_queue[i]};
+        queue.write_i++;
+      }
+      pthread_cond_broadcast(&queue.jobs_available_cond);
+    }
+    queue.done_writing = true;
 
     // wait for fitness jobs to complete
-    // sort cells on performance
+    pthread_mutex_lock(&queue.gen_complete_mutex);
+
+    // Before going to sleep, do a quick check to see if the fitness jobs are
+    // already complete.
+    pthread_mutex_lock(&queue.data_mutex);
+    bool already_complete = queue.read_i != queue.write_i;
+    pthread_mutex_unlock(&queue.data_mutex);
+    if (already_complete) {
+      pthread_mutex_unlock(&queue.gen_complete_mutex);
+    } else {
+      pthread_cond_wait(&queue.gen_complete_cond, &queue.gen_complete_mutex);
+    }
+
+    // Sort cells on performance
+    std::sort(cell_queue.begin(), cell_queue.end(),
+              [strat](cell_entry<T> a, cell_entry<T> b) {
+                return strat.higher_fitness_is_better ? a > b : a < b;
+              });
+
+    printf("Top Score: %f\n", cell_queue[0].score);
+
+    if (!strat.enable_crossover)
+      continue;
+
     // generate crossover jobs
+    // dear god. forgive me father
+    queue.write_i = 0;
+    queue.read_i = 0;
+    int count = 0;
+    int n_par = strat.crossover_parent_num;
+    int n_child = strat.crossover_children_num;
+    int child_i = cell_queue.size() - 1;
+    int par_i = 0;
+    while (child_i - par_i <= n_par + n_child) {
+      Array<cell_entry<T> *> parents = {
+          (cell_entry<T> **)malloc(sizeof(cell_entry<T> *) * n_par), n_par};
+      Array<cell_entry<T> *> children = {
+          (cell_entry<T> **)malloc(sizeof(cell_entry<T> *) * n_child), n_child};
+
+      for (; par_i < par_i + n_par; par_i++) {
+        parents[i] = cell_queue[par_i];
+      }
+
+      for (; child_i > child_i - n_child; child_i--) {
+        children[i] = cell_queue[child_i];
+      }
+
+      queue.jobs[queue.write_i] = crossover_job<T>{parents, children};
+      par_i += strat.crossover_parent_stride;
+      child_i += strat.crossover_children_stride;
+    }
   }
 
   // stop worker threads
   stop_flag = true;
-  pthread_cond_broadcast(work_queue.jobs_available_cond);
+  pthread_cond_broadcast(&queue.jobs_available_cond);
   for (int i = 0; i < strat.num_threads; i++) {
     pthread_join(threads[i], NULL);
   }
 }
 
-template <class T> T &Span<T>::operator[](int i) {
-  assert(i >= 0 && i < len);
+template <class T> T &Array<T>::operator[](int i) {
   return _data[i];
 }
 
diff --git a/src/main.cpp b/src/main.cpp
index e60847d..7b07dbc 100644
--- a/src/main.cpp
+++ b/src/main.cpp
@@ -1,133 +1,81 @@
-#include <algorithm>
 #include <cassert>
+#include <cstdint>
 #include <cstdlib>
-#include <iostream>
-#include <vector>
+#include "genetic.h"
+#include "rand.h"
 
-#define MUTATION_CHANCE 1.0
+using namespace genetic;
 
-float norm_rand() { return (float)rand() / RAND_MAX; }
+const int len = 10;
+const float max_float = 9999.9f;
+static uint64_t seed = 12;
+static float num_mutate_chance = 0.5;
+static int num_parents = 2;
+static int num_children = 2;
 
-enum class ConstraintType {
-  PRODUCT = 0,
-  SUM = 1,
-  INDEX_EQ = 2,
-};
 
-struct Constraint {
-  ConstraintType type;
-  int optional_i;
-  float value;
-};
-static std::vector<Constraint> constraints;
+static int target_sum = 200;
+static int target_product = 300;
 
-struct Cell {
-  int n;
-  float *params;
-};
-
-Cell make_cell(int num_params) {
-  Cell res = {num_params, (float *)malloc(num_params * sizeof(float))};
-  for (int i = 0; i < num_params; i++) {
-    res.params[i] = 0;
-  }
-  return res;
+Array<float> make_new_arr() {
+    Array<float> arr = { (float*)malloc(sizeof(float)*len), len };
+    for (int i = 0; i < arr.len; i++) {
+        arr[i] = norm_rand(seed) * max_float;
+    }
+    return arr;
 }
 
-float get_cell_err(const Cell &a) {
-  float total_diff = 0;
-  for (auto c : constraints) {
-    switch (c.type) {
-    case ConstraintType::SUM: {
-      float sum = 0;
-      for (int i = 0; i < a.n; i++) {
-        sum += a.params[i];
-      }
-      total_diff += abs(c.value - sum);
-      break;
+void mutate(Array<float> &arr_to_mutate) {
+    for (int i = 0; i < len; i++) {
+        if (norm_rand(seed) < num_mutate_chance) {
+            arr_to_mutate[i] = norm_rand(seed) * max_float;
+        }
     }
-    case ConstraintType::PRODUCT: {
-      float prod = 1;
-      for (int i = 0; i < a.n; i++) {
-        prod *= a.params[i];
-      }
-      total_diff += abs(c.value - prod);
-      break;
-    }
-    case ConstraintType::INDEX_EQ: {
-      assert(c.optional_i < a.n);
-      total_diff += abs(c.value - a.params[c.optional_i]);
-      break;
-    }
-    }
-  }
-  return total_diff;
 }
 
-bool operator<(const Cell &a, const Cell &b) {
-  assert(a.n == b.n);
-  return get_cell_err(a) < get_cell_err(b);
+void crossover(const Array<Array<float>*> parents, const Array<Array<float> *> out_children) {
+    for (int i = 0; i < len; i++) {
+        (*out_children._data[0])[i] = i < len/2 ? (*parents._data[0])[i] : (*parents._data[1])[i];
+        (*out_children._data[1])[i] = i < len/2 ? (*parents._data[1])[i] : (*parents._data[0])[i];
+    }
 }
 
-void combine_cells(const Cell &a, const Cell &b, Cell *child) {
-  bool a_first = norm_rand() > 0.5f;
-  for (int i = 0; i < a.n; i++) {
-    float offset = norm_rand() * 10;
-    float roll = norm_rand();
-    if (a_first) {
-      child->params[i] = (i < a.n / 2 ? a.params[i] : b.params[i]) +
-                         (roll > 0.5 ? offset : -offset);
-    } else {
-      child->params[i] = (i < a.n / 2 ? b.params[i] : a.params[i]) +
-                         (roll > 0.5 ? offset : -offset);
+// norm_rand can go negative. fix in genetic.cpp
+// child stride doesn't make sense. Should always skip over child num
+
+float fitness(const Array<float> &cell) {
+    float sum = 0;
+    float product = 1;
+    for (int i = 0; i < cell.len; i++) {
+        sum += cell._data[i];
+        product *= cell._data[i];
     }
-  }
-  float r = norm_rand();
-  child->params[(int)r * (a.n - 1)] = r * 100.0;
+    return abs(sum - target_sum) + abs(product - target_product);
 }
 
 int main(int argc, char **argv) {
-  int num_params, num_cells, num_generations, num_constraints = 0;
-  std::cin >> num_params >> num_cells >> num_generations >> num_constraints;
+    Strategy<Array<float>> strat {
+        .num_threads = 1,
+        .batch_size  = 1,
+        .num_cells   = 10,
+        .num_generations = 10,
+        .test_all = true,
+        .test_chance = 0.0, // doesn't matter
+        .enable_crossover = true,
+        .enable_crossover_mutation = true,
+        .crossover_mutation_chance = 0.6f,
+        .crossover_parent_num = 2,
+        .crossover_parent_stride = 1,
+        .crossover_children_num = 2,
+        .enable_mutation = true,
+        .mutation_chance = 0.8,
+        .rand_seed = seed,
+        .higher_fitness_is_better = false,
+        .make_default_cell=make_new_arr,
+        .mutate=mutate,
+        .crossover=crossover,
+        .fitness=fitness
+    };
 
-  std::cout << num_params << " " << num_cells << " " << num_generations << " "
-            << num_constraints << std::endl;
-
-  for (int i = 0; i < num_constraints; i++) {
-    int type_in, optional_i = 0;
-    float value;
-    std::cin >> type_in >> value;
-    ConstraintType type = static_cast<ConstraintType>(type_in);
-    if (type == ConstraintType::INDEX_EQ) {
-      std::cin >> optional_i;
-    }
-    constraints.push_back({type, optional_i, value});
-  }
-
-  std::vector<Cell> cells;
-  for (int i = 0; i < num_cells; i++) {
-    cells.push_back(make_cell(num_params));
-  }
-
-  for (int i = 0; i < num_generations; i++) {
-    std::sort(cells.begin(), cells.end());
-    for (int j = 0; j < num_cells / 2; j++) {
-      combine_cells(cells[j], cells[j + 1], &cells[num_cells / 2 + j]);
-    }
-    if (i % 1000 == 0) {
-      std::cout << i << "\t" << get_cell_err(cells[0]) << std::endl;
-    }
-  }
-  std::cout << "Final Answer: ";
-  float sum = 0;
-  float product = 1;
-  for (int i = 0; i < cells[0].n; i++) {
-    std::cout << cells[0].params[i] << " ";
-    sum += cells[0].params[i];
-    product *= cells[0].params[i];
-  }
-  std::cout << std::endl;
-
-  std::cout << "Sum: " << sum << std::endl;
-  std::cout << "Product: " << product << std::endl;
+    auto res = run(strat);
 }