diff --git a/libgomp/config/nvptx/target.c b/libgomp/config/nvptx/target.c
index 3d815bb0cb6..2eb545f812f 100644
--- a/libgomp/config/nvptx/target.c
+++ b/libgomp/config/nvptx/target.c
@@ -26,28 +26,41 @@
 #include "libgomp.h"
 #include <limits.h>
 
+extern int __gomp_team_num __attribute__((shared));
+
 bool
 GOMP_teams4 (unsigned int num_teams_lower, unsigned int num_teams_upper,
 	     unsigned int thread_limit, bool first)
 {
+  unsigned int num_blocks, block_id;
+  asm ("mov.u32 %0, %%nctaid.x;" : "=r" (num_blocks));
   if (!first)
-    return false;
+    {
+      unsigned int team_num;
+      if (num_blocks > gomp_num_teams_var)
+	return false;
+      team_num = __gomp_team_num;
+      if (team_num > gomp_num_teams_var - num_blocks)
+	return false;
+      __gomp_team_num = team_num + num_blocks;
+      return true;
+    }
   if (thread_limit)
     {
       struct gomp_task_icv *icv = gomp_icv (true);
       icv->thread_limit_var
 	= thread_limit > INT_MAX ? UINT_MAX : thread_limit;
     }
-  unsigned int num_blocks, block_id;
-  asm ("mov.u32 %0, %%nctaid.x;" : "=r" (num_blocks));
-  asm ("mov.u32 %0, %%ctaid.x;" : "=r" (block_id));
-  /* FIXME: If num_teams_lower > num_blocks, we want to loop multiple
-     times for some CTAs.  */
-  (void) num_teams_lower;
-  if (!num_teams_upper || num_teams_upper >= num_blocks)
+  if (!num_teams_upper)
     num_teams_upper = num_blocks;
-  else if (block_id >= num_teams_upper)
+  else if (num_blocks < num_teams_lower)
+    num_teams_upper = num_teams_lower;
+  else if (num_blocks < num_teams_upper)
+    num_teams_upper = num_blocks;
+  asm ("mov.u32 %0, %%ctaid.x;" : "=r" (block_id));
+  if (block_id >= num_teams_upper)
     return false;
+  __gomp_team_num = block_id;
   gomp_num_teams_var = num_teams_upper - 1;
   return true;
 }
diff --git a/libgomp/config/nvptx/team.c b/libgomp/config/nvptx/team.c
index e2359643d7e..cabf01815e9 100644
--- a/libgomp/config/nvptx/team.c
+++ b/libgomp/config/nvptx/team.c
@@ -32,6 +32,7 @@
 #include <string.h>
 
 struct gomp_thread *nvptx_thrs __attribute__((shared,nocommon));
+int __gomp_team_num __attribute__((shared,nocommon));
 
 static void gomp_thread_start (struct gomp_thread_pool *);
 
@@ -57,6 +58,7 @@ gomp_nvptx_main (void (*fn) (void *), void *fn_data)
       /* Starting additional threads is not supported.  */
       gomp_global_icv.dyn_var = true;
 
+      __gomp_team_num = 0;
       nvptx_thrs = alloca (ntids * sizeof (*nvptx_thrs));
       memset (nvptx_thrs, 0, ntids * sizeof (*nvptx_thrs));
 
diff --git a/libgomp/config/nvptx/teams.c b/libgomp/config/nvptx/teams.c
index 631cb1c7add..60fb11df006 100644
--- a/libgomp/config/nvptx/teams.c
+++ b/libgomp/config/nvptx/teams.c
@@ -28,6 +28,8 @@
 
 #include "libgomp.h"
 
+extern int __gomp_team_num __attribute__((shared));
+
 void
 GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
 		unsigned int thread_limit, unsigned int flags)
@@ -48,9 +50,7 @@ omp_get_num_teams (void)
 int
 omp_get_team_num (void)
 {
-  int ctaid;
-  asm ("mov.u32 %0, %%ctaid.x;" : "=r" (ctaid));
-  return ctaid;
+  return __gomp_team_num;
 }
 
 ialias (omp_get_num_teams)