Lazyly reinit threads after a fork in OMP mode

This initializes the per-thread memory buffers which get
cleared/released on a fork via pthread_at_fork. Not doing so leads to
each thread calling blas_memory_alloc on almost every execution which
slows down the code significantly as the threads race for the memory
allocation using locks to serialize that.

Author: Flamefire

driver/others/blas_server_omp.c

@@ -48,6 +48,21 @@
 
 #else
 
+#ifndef likely
+#ifdef __GNUC__
+#define likely(x) __builtin_expect(!!(x), 1)
+#else
+#define likely(x) (x)
+#endif
+#endif
+#ifndef unlikely
+#ifdef __GNUC__
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#else
+#define unlikely(x) (x)
+#endif
+#endif
+
 #ifndef OMP_SCHED
 #define OMP_SCHED static
 #endif
@@ -350,6 +365,9 @@ static void exec_threads(blas_queue_t *queue, int buf_index){
 
 int exec_blas(BLASLONG num, blas_queue_t *queue){
 
+  // Handle lazy re-init of the thread-pool after a POSIX fork
+  if (unlikely(blas_server_avail == 0)) blas_thread_init();
+
   BLASLONG i, buf_index;
 
   if ((num <= 0) || (queue == NULL)) return 0;