diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index a6f444340fd..0d288cb81ba 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -4037,6 +4037,22 @@ nvptx_single (unsigned mask, basic_block from, basic_block to)
 	return;
     }
 
+  /* NVPTX_BARSYNC barriers are placed immediately before NVPTX_JOIN
+     in order to ensure that all of the threads in a CTA reach the
+     barrier.  Don't nueter BLOCK if head is NVPTX_BARSYNC and tail is
+     NVPTX_JOIN.  */
+  if (from == to
+      && recog_memoized (head) == CODE_FOR_nvptx_barsync
+      && recog_memoized (tail) == CODE_FOR_nvptx_join)
+    return;
+
+  /* Adjust HEAD to point to the NVPTX_JOIN instruction after a
+     NVPTX_BARSYNC, so that any successive state neutering code does
+     not get placed before the dummy JOIN comment. */
+  if (recog_memoized (head) == CODE_FOR_nvptx_barsync
+      && recog_memoized (NEXT_INSN (head)) == CODE_FOR_nvptx_join)
+    head = NEXT_INSN (head);
+
   /* Insert the vector test inside the worker test.  */
   unsigned mode;
   rtx_insn *before = tail;
@@ -4057,7 +4073,23 @@ nvptx_single (unsigned mask, basic_block from, basic_block to)
 	  br = gen_br_true (pred, label);
 	else
 	  br = gen_br_true_uni (pred, label);
-	emit_insn_before (br, head);
+
+	if (recog_memoized (head) == CODE_FOR_nvptx_forked
+	    && recog_memoized (NEXT_INSN (head)) == CODE_FOR_nvptx_barsync)
+	  {
+	    head = NEXT_INSN (head);
+	    emit_insn_after (br, head);
+	  }
+	else if (recog_memoized (head) == CODE_FOR_nvptx_join)
+	  {
+	    if (recog_memoized (NEXT_INSN (head)) == CODE_FOR_br_true_uni
+		&& mode == GOMP_DIM_VECTOR)
+	      emit_insn_after (br, NEXT_INSN (head));
+	    else
+	      emit_insn_after (br, head);
+	  }
+	else
+	  emit_insn_before (br, head);
 
 	LABEL_NUSES (label)++;
 	if (tail_branch)
@@ -4276,7 +4308,7 @@ nvptx_process_pars (parallel *par)
       nvptx_wpropagate (true, par->forked_block, par->fork_insn);
       /* Insert begin and end synchronizations.  */
       emit_insn_after (nvptx_wsync (false), par->forked_insn);
-      emit_insn_before (nvptx_wsync (true), par->joining_insn);
+      emit_insn_before (nvptx_wsync (true), par->join_insn);
     }
   else if (par->mask & GOMP_DIM_MASK (GOMP_DIM_VECTOR))
     nvptx_vpropagate (par->forked_block, par->forked_insn);