first running multithreaded version. nasty deadlock bug exists. Realizing that Perhaps I should just have each thread running a completely separate situation. Why synchronize when you don't need to?

debug.rad

@@ -1,6 +1,7 @@
 // raddbg 0.9.21 project file
 
 recent_file: path: "inc/genetic.h"
+recent_file: path: "inc/sync.h"
 recent_file: path: "../../../../../Program Files/Microsoft Visual Studio/2022/Community/VC/Tools/MSVC/14.42.34433/include/algorithm"
 recent_file: path: "../../../../../Program Files/Microsoft Visual Studio/2022/Community/VC/Tools/MSVC/14.42.34433/include/xutility"
 recent_file: path: "src/main.cpp"

inc/genetic.h

@@ -8,6 +8,7 @@
 #include "rand.h"
 
 using namespace sync;
+using namespace std;
 
 namespace genetic {
 
@@ -83,6 +84,66 @@ template <class T> Array<T> make_array(int len) {
      };
 }
 
+template<class T>
+struct MutateJob {
+    T* cell;
+};
+
+template<class T>
+struct CrossoverJob {
+    Array<T*> parents;
+    Array<T*> children;
+};
+
+template<class T>
+struct FitnessJob {
+    T* cell;
+    CellTracker* track;
+};
+
+enum class JobType {
+    MUTATE,
+    CROSSOVER,
+    FITNESS
+};
+
+template<class T>
+union Job {
+    MutateJob<T> m;
+    CrossoverJob<T> c;
+    FitnessJob<T> f;
+};
+
+// Yes. I am aware of variant
+// For some reason I like this better
+template<class T>
+struct TaggedJob {
+    Job<T> data;
+    JobType type;
+};
+
+template<class T>
+struct WorkQueue {
+    Array<TaggedJob<T>> jobs;
+    int read_i, write_i, batch_size;
+    bool done_writing, work_complete, stop; // These catch some edge conditions
+    Mutex m;
+    ConditionVar done;
+    ConditionVar jobs_ready;
+};
+
+template<class T>
+struct WorkerThreadArgs {
+    WorkQueue<T> &q;
+    Strategy<T> &s;
+};
+
+template<class T> WorkQueue<T> make_work_queue(int len, int batch_size);
+template<class T> bool tryget_job_batch(WorkQueue<T> &q, int len, Array<TaggedJob<T>>* out_batch, bool* out_batch_is_end);
+
+template<class T>
+DWORD worker(LPVOID args);
+
 template <class T> Stats<T> run(Strategy<T> strat) {
     Stats<T> stats;
 
@@ -97,17 +158,42 @@ template <class T> Stats<T> run(Strategy<T> strat) {
     Array<CellTracker> trackers = make_array<CellTracker>(strat.num_cells);
     for (int i = 0; i < trackers.len; i++) trackers[i] = { .score=0, .cellid=i };
 
+    // Create work queue
+    // Worst case size is every cell mutated, crossed, and evaluated...? Not quite, but 3x should be upper bound
+    WorkQueue<T> q = make_work_queue<T>(3*strat.num_cells, strat.batch_size);
+    WorkerThreadArgs<T> args = {q, strat};
+
+    // Create worker threads
+    Thread *threads = (Thread*)malloc(sizeof(Thread*)*strat.num_threads);
+    for (int i = 0; i < strat.num_threads; i++) {
+	threads[i] = make_thread(worker<T>, &args);
+    }
+
     stats.setup_time = now() - start_setup;
 
     // *********** ALGORITHM ************
     TimeSpan start_algo = now();
     for (int gen = 0; gen < strat.num_generations; gen++) {
+	// Reset work queue
+	lock(q.m);
+	q.read_i = 0;
+	q.write_i = 0;
+	q.work_complete = false;
+	q.done_writing = false;
+	unlock(q.m);
+
 	// 1. mutate
 	for (int i = 0; i < trackers.len; i++) {
 	    if (abs(norm_rand(strat.rand_seed)) < strat.mutation_chance) {
-		strat.mutate(cells[trackers[i].cellid]);
+		MutateJob<T> mj = {&cells[trackers[i].cellid]};
+		TaggedJob<T> job;
+		job.data.m = mj;
+		job.type=JobType::MUTATE;
+		q.jobs[q.write_i++] = job;
 	    }
 	}
+	wake_all(q.jobs_ready); // There are available jobs for the worker threads!
+
 	// 2. crossover
 	if (strat.enable_crossover) {
 	    int npar = strat.crossover_parent_num;
@@ -115,9 +201,11 @@ template <class T> Stats<T> run(Strategy<T> strat) {
 
 	    int parent_end = npar;
 	    int child_begin = trackers.len-nchild;
-	    Array<T*> parents = make_array<T*>(npar);
-	    Array<T*> children = make_array<T*>(nchild);
 	    while (parent_end <= child_begin) {
+
+		// TODO: Variable size arrays please. This is rediculous.
+		Array<T*> parents = make_array<T*>(npar);
+		Array<T*> children = make_array<T*>(nchild);
 		// Get pointers to all the parent cells
 		for (int i = parent_end-npar; i < parent_end; i++) {
 		    parents[i - (parent_end-npar)] = &cells[trackers[i].cellid];
@@ -127,25 +215,50 @@ template <class T> Stats<T> run(Strategy<T> strat) {
 		for (int i = child_begin; i < child_begin+nchild; i++) {
 		    children[i-child_begin] = &cells[trackers[i].cellid];
 		}
-		strat.crossover(parents, children);
+		CrossoverJob<T> cj = {parents, children};
+		TaggedJob<T> job;
+		job.data.c=cj;
+		job.type=JobType::CROSSOVER;
+		q.jobs[q.write_i++] = job;
 		parent_end += strat.crossover_parent_stride;
 		child_begin -= nchild;
 	    }
-	    free(parents.data);
-	    free(children.data);
+	    wake_all(q.jobs_ready); // There are available jobs for the worker threads!
 	}
+
 	// 3. evaluate
 	if (strat.test_all) {
 	    for (int i = 0; i < trackers.len; i++) {
-		trackers[i].score = strat.fitness(cells[trackers[i].cellid]);
+		FitnessJob<T> fj = {&cells[trackers[i].cellid], &trackers[i]};
+		TaggedJob<T> job;
+		job.data.f=fj;
+		job.type=JobType::FITNESS;
+		if (i == trackers.len-1) lock(q.m);
+		q.jobs[q.write_i++] = job;
+		if (i == trackers.len-1) { q.done_writing = true; unlock(q.m); }
 	    }
 	} else {
+	    lock(q.m);
 	    for (int i = 0; i < trackers.len; i++) {
 		if (abs(norm_rand(strat.rand_seed)) < strat.test_chance) {
-		    trackers[i].score = strat.fitness(cells[trackers[i].cellid]);
+		    FitnessJob<T> fj = {&cells[trackers[i].cellid], &trackers[i]};
+		    TaggedJob<T> job;
+		    job.data.f=fj;
+		    job.type=JobType::FITNESS;
+		    q.jobs[q.write_i++] = job;
 		}
 	    }
+	    q.done_writing = true;
+	    unlock(q.m);
 	}
+	wake_all(q.jobs_ready);
+
+	// Wait until the work is finished
+	lock(q.m);
+	if (!q.work_complete) 
+	    wait(q.done, q.m, infinite_ts);
+	unlock(q.m);
+
 	// 4. sort
 	std::sort(&trackers[0], &trackers[trackers.len-1], [strat](CellTracker &a, CellTracker &b){ return strat.higher_fitness_is_better ? a.score > b.score : a.score < b.score; });
 
@@ -153,8 +266,105 @@ template <class T> Stats<T> run(Strategy<T> strat) {
 	stats.best_cell.push_back(cells[trackers[0].cellid]);
 	stats.best_cell_fitness.push_back(trackers[0].score);
     }
+
+    q.stop = true;
+    wake_all(q.jobs_ready);
+    // TODO: join all threads
+
+    // TODO: There's some data freeing that should really be done here
     stats.run_time = now() - start_algo;
     return stats;
 }
 
+template<class T> WorkQueue<T> make_work_queue(int len, int batch_size) {
+    return {
+	.jobs=make_array<TaggedJob<T>>(len),
+	.read_i=0,
+	.write_i=0,
+	.batch_size=batch_size,
+	.done_writing=false,
+	.work_complete=false,
+	.m=make_mutex(),
+	.done=make_condition_var(),
+	.jobs_ready=make_condition_var()
+    };
+}
+
+template<class T> bool tryget_job_batch(WorkQueue<T> &q, Array<TaggedJob<T>>* out_batch, bool* out_batch_is_end) {
+    lock(q.m);
+    if (q.stop) {
+	unlock(q.m);
+	return false;
+    }
+
+    // Keep waiting till jobs are available
+    while (q.read_i >= q.write_i) {
+	wait(q.jobs_ready, q.m, infinite_ts); 
+	
+	if (q.stop) {
+	    unlock(q.m);
+	    return false;
+	}
+    }
+
+    // Yay! Let's grab some jobs to do
+
+    // If the batch we're about to grab moves read_i to write_i and the producer
+    // is done writing, we should let our callee know it's handling this gen's last 
+    // batch know that way it sets work_complete and signals done.
+    *out_batch_is_end = q.done_writing && q.read_i + q.batch_size >= q.write_i;
+
+    out_batch->data = &q.jobs[q.read_i];
+    out_batch->len = min(q.batch_size, q.write_i - q.read_i);
+    q.read_i += q.batch_size;
+    unlock(q.m);
+    return true;
+}
+
+template<class T>
+void work_batch(Array<TaggedJob<T>> batch, Strategy<T> &s) {
+    for (int i = 0; i < batch.len; i++) {
+	switch (batch[i].type) {
+	    case JobType::MUTATE: {
+		MutateJob<T> mj = batch[i].data.m;
+		s.mutate(*mj.cell);
+	    } break;
+	    case JobType::CROSSOVER: {
+		CrossoverJob<T> cj = batch[i].data.c;
+		s.crossover(cj.parents, cj.children);
+	    } break;
+	    case JobType::FITNESS: {	
+		FitnessJob<T> fj = batch[i].data.f;
+		fj.track->score = s.fitness(*fj.cell);
+	    } break;
+	    default: {
+		assert(false);
+	    }
+	}
+    }
+}
+
+template<class T>
+DWORD worker(LPVOID args) {
+    WorkerThreadArgs<T>* wa = static_cast<WorkerThreadArgs<T>*>(args);
+    WorkQueue<T> &q = wa->q;
+    Strategy<T> &s = wa->s;
+
+    // These are written by tryget_job_batch
+    bool batch_is_end;
+    Array<TaggedJob<T>> batch;
+
+    while (tryget_job_batch(q, &batch, &batch_is_end)) {
+	work_batch(batch, s);
+	if (batch_is_end) {
+	    lock(q.m);
+	    q.work_complete = true;
+	    wake_one(q.done);
+	    unlock(q.m);
+	}
+    }
+
+    return NULL;
+}
+
 } // namespace genetic

inc/sync.h

@@ -15,7 +15,7 @@ typedef LARGE_INTEGER TimeSpan;
 typedef DWORD (WINAPI *ThreadFunc)(_In_ LPVOID lpParameter);
 typedef LPVOID ThreadArg;
 
-const TimeSpan infinite_ts = { .QuadPart = LLONG_MAX };
+const TimeSpan infinite_ts = { .QuadPart=LLONG_MAX };
 
 LARGE_INTEGER _init_freq() {
     LARGE_INTEGER freq;

src/main.cpp

@@ -56,8 +56,8 @@ float fitness(const Array<float> &cell) {
 int main(int argc, char **argv) {
     int num_gens = 2000;
     Strategy<Array<float>> strat {
-        .num_threads = 1,
-        .batch_size  = 1,
+        .num_threads = 15,
+        .batch_size  = 1000,
         .num_cells   = 100000,
         .num_generations = num_gens,
         .test_all = true,