[OPENMP][NVPTX]Fix __kmpc_flush to flush the memory per system, not per block.

[ABataev]

Summary

According to the standard, after memory flushing the changes in the
memory must be visible to all the threads in all teams. Patch fixes
this.

[gtbercea]

LG

openmp/trunk/libomptarget/deviceRTLs/nvptx/src/sync.cu

 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Flush
 ////////////////////////////////////////////////////////////////////////////////
 
 EXTERN void __kmpc_flush(kmp_Ident *loc) {
   PRINT0(LD_IO, "call kmpc_flush\n");
-  __threadfence_block();
+  __threadfence_system();
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // Vote
 ////////////////////////////////////////////////////////////////////////////////
 
 EXTERN int32_t __kmpc_warp_active_thread_mask() {
   PRINT0(LD_IO, "call __kmpc_warp_active_thread_mask\n");
   return __ACTIVEMASK();
 }