diff --git a/openmp/runtime/src/kmp_runtime.cpp b/openmp/runtime/src/kmp_runtime.cpp
--- a/openmp/runtime/src/kmp_runtime.cpp
+++ b/openmp/runtime/src/kmp_runtime.cpp
@@ -3547,6 +3547,10 @@
     newCapacity = newCapacity <= (__kmp_sys_max_nth >> 1) ? (newCapacity << 1)
                                                           : __kmp_sys_max_nth;
   } while (newCapacity < minimumRequiredCapacity);
+  // If hidden helper thread is enabled, we also need to count the number
+  if (__kmp_enable_hidden_helper) {
+    newCapacity += __kmp_hidden_helper_threads_num;
+  }
   newThreads = (kmp_info_t **)__kmp_allocate(
       (sizeof(kmp_info_t *) + sizeof(kmp_root_t *)) * newCapacity + CACHE_LINE);
   newRoot =
diff --git a/openmp/runtime/src/kmp_settings.cpp b/openmp/runtime/src/kmp_settings.cpp
--- a/openmp/runtime/src/kmp_settings.cpp
+++ b/openmp/runtime/src/kmp_settings.cpp
@@ -504,9 +504,10 @@
     nth = (4 * __kmp_xproc);
 
   // If hidden helper task is enabled, we initialize the thread capacity with
-  // extra
-  // __kmp_hidden_helper_threads_num.
-  nth += __kmp_hidden_helper_threads_num;
+  // extra __kmp_hidden_helper_threads_num.
+  if (__kmp_enable_hidden_helper) {
+    nth += __kmp_hidden_helper_threads_num;
+  }
 
   if (nth > __kmp_max_nth)
     nth = __kmp_max_nth;
diff --git a/openmp/runtime/test/tasking/hidden_helper_task/num_threads.cpp b/openmp/runtime/test/tasking/hidden_helper_task/num_threads.cpp
new file mode 100644
--- /dev/null
+++ b/openmp/runtime/test/tasking/hidden_helper_task/num_threads.cpp
@@ -0,0 +1,35 @@
+// RUN: %libomp-cxx-compile-and-run
+
+#include <omp.h>
+
+#include <algorithm>
+#include <cassert>
+#include <vector>
+
+int main(int argc, char *argv[]) {
+  constexpr const int __kmp_hidden_helper_threads_num = 8;
+  const int __kmp_threads_capacity =
+      std::min(std::max(std::max(32, 4 * omp_get_num_threads()),
+                        4 * omp_get_num_procs()),
+               std::numeric_limits<int>::max());
+  const int capacity = __kmp_threads_capacity + __kmp_hidden_helper_threads_num;
+  const int N = 2 * capacity;
+
+  std::vector<int> data(N);
+
+#pragma omp parallel for
+  for (unsigned i = 0; i < N; ++i) {
+    data[i] = i;
+  }
+
+#pragma omp parallel for num_threads(N)
+  for (unsigned i = 0; i < N; ++i) {
+    data[i] += i;
+  }
+
+  for (unsigned i = 0; i < N; ++i) {
+    assert(data[i] == 2 * i);
+  }
+
+  return 0;
+}