Index: openmp/trunk/libomptarget/deviceRTLs/nvptx/src/counter_groupi.h
===================================================================
--- openmp/trunk/libomptarget/deviceRTLs/nvptx/src/counter_groupi.h
+++ openmp/trunk/libomptarget/deviceRTLs/nvptx/src/counter_groupi.h
@@ -45,7 +45,7 @@
 
 // set priv to n, to be used in later waitOrRelease
 INLINE void omptarget_nvptx_CounterGroup::Complete(Counter &priv, Counter n) {
-  PRINT(LD_SYNCD, "complete priv counter 0x%llx with val %lld->%lld (+%d)\n",
+  PRINT(LD_SYNCD, "complete priv counter 0x%llx with val %llu->%llu (+%llu)\n",
         P64(&priv), P64(priv), P64(priv + n), n);
   priv += n;
 }
Index: openmp/trunk/libomptarget/deviceRTLs/nvptx/src/libcall.cu
===================================================================
--- openmp/trunk/libomptarget/deviceRTLs/nvptx/src/libcall.cu
+++ openmp/trunk/libomptarget/deviceRTLs/nvptx/src/libcall.cu
@@ -55,7 +55,7 @@
     rc = GetNumberOfProcsInTeam();
     ASSERT0(LT_FUSSY, rc >= 0, "bad number of threads");
   }
-  PRINT(LD_IO, "call omp_get_max_threads() return %\n", rc);
+  PRINT(LD_IO, "call omp_get_max_threads() return %d\n", rc);
   return rc;
 }
 
@@ -192,7 +192,7 @@
           omp_sched_t sched = currTaskDescr->GetRuntimeSched();
           PRINT(LD_ALL,
                 "task descr %s %d: %s, in par %d, dyn %d, rt sched %d,"
-                " chunk %lld; tid %d, tnum %d, nthreads %d\n",
+                " chunk %" PRIu64 "; tid %d, tnum %d, nthreads %d\n",
                 "ancestor", steps,
                 (currTaskDescr->IsParallelConstruct() ? "par" : "task"),
                 currTaskDescr->InParallelRegion(), currTaskDescr->IsDynamic(),
@@ -261,7 +261,7 @@
     omptarget_nvptx_TaskDescr *currTaskDescr = getMyTopTaskDescriptor();
     currTaskDescr->SetRuntimeSched(kind);
     currTaskDescr->RuntimeChunkSize() = modifier;
-    PRINT(LD_IOD, "omp_set_schedule did set sched %d & modif %d\n",
+    PRINT(LD_IOD, "omp_set_schedule did set sched %d & modif %" PRIu64 "\n",
           (int)currTaskDescr->GetRuntimeSched(),
           currTaskDescr->RuntimeChunkSize());
   }
Index: openmp/trunk/libomptarget/deviceRTLs/nvptx/src/loop.cu
===================================================================
--- openmp/trunk/libomptarget/deviceRTLs/nvptx/src/loop.cu
+++ openmp/trunk/libomptarget/deviceRTLs/nvptx/src/loop.cu
@@ -240,8 +240,8 @@
     // Process schedule.
     if (tnum == 1 || tripCount <= 1 || OrderedSchedule(schedule)) {
       PRINT(LD_LOOP,
-            "go sequential as tnum=%d, trip count %lld, ordered sched=%d\n",
-            tnum, P64(tripCount), schedule);
+            "go sequential as tnum=%ld, trip count %lld, ordered sched=%d\n",
+            (long)tnum, P64(tripCount), schedule);
       schedule = kmp_sched_static_chunk;
       chunk = tripCount; // one thread gets the whole loop
 
@@ -301,8 +301,8 @@
       omptarget_nvptx_threadPrivateContext->NextLowerBound(tid) = lb;
       omptarget_nvptx_threadPrivateContext->Stride(tid) = stride;
       PRINT(LD_LOOP,
-            "dispatch init (static chunk) : num threads = %d, ub = %lld,"
-            "next lower bound = %lld, stride = %lld\n",
+            "dispatch init (static chunk) : num threads = %d, ub =  %" PRId64 ","
+            "next lower bound = %llu, stride = %llu\n",
             GetNumberOfOmpThreads(tid, isSPMDMode(), isRuntimeUninitialized()),
             omptarget_nvptx_threadPrivateContext->LoopUpperBound(tid),
             omptarget_nvptx_threadPrivateContext->NextLowerBound(tid),
@@ -322,8 +322,8 @@
       omptarget_nvptx_threadPrivateContext->NextLowerBound(tid) = lb;
       omptarget_nvptx_threadPrivateContext->Stride(tid) = stride;
       PRINT(LD_LOOP,
-            "dispatch init (static nochunk) : num threads = %d, ub = %lld,"
-            "next lower bound = %lld, stride = %lld\n",
+            "dispatch init (static nochunk) : num threads = %d, ub = %" PRId64 ","
+            "next lower bound = %llu, stride = %llu\n",
             GetNumberOfOmpThreads(tid, isSPMDMode(), isRuntimeUninitialized()),
             omptarget_nvptx_threadPrivateContext->LoopUpperBound(tid),
             omptarget_nvptx_threadPrivateContext->NextLowerBound(tid),
@@ -338,8 +338,8 @@
       omptarget_nvptx_threadPrivateContext->Chunk(tid) = chunk;
       omptarget_nvptx_threadPrivateContext->EventsNumber(tid) = eventNum;
       PRINT(LD_LOOP,
-            "dispatch init (dyn) : num threads = %d, ub = %lld, chunk %lld, "
-            "events number = %lld\n",
+            "dispatch init (dyn) : num threads = %d, ub = %" PRId64 ", chunk %" PRIu64 ", "
+            "events number = %llu\n",
             GetNumberOfOmpThreads(tid, isSPMDMode(), isRuntimeUninitialized()),
             omptarget_nvptx_threadPrivateContext->LoopUpperBound(tid),
             omptarget_nvptx_threadPrivateContext->Chunk(tid),
Index: openmp/trunk/libomptarget/deviceRTLs/nvptx/src/omptarget-nvptx.h
===================================================================
--- openmp/trunk/libomptarget/deviceRTLs/nvptx/src/omptarget-nvptx.h
+++ openmp/trunk/libomptarget/deviceRTLs/nvptx/src/omptarget-nvptx.h
@@ -19,6 +19,8 @@
 #include <stdint.h>
 #include <stdlib.h>
 
+#include <inttypes.h>
+
 // cuda includes
 #include <cuda.h>
 #include <math.h>
Index: openmp/trunk/libomptarget/deviceRTLs/nvptx/src/supporti.h
===================================================================
--- openmp/trunk/libomptarget/deviceRTLs/nvptx/src/supporti.h
+++ openmp/trunk/libomptarget/deviceRTLs/nvptx/src/supporti.h
@@ -177,8 +177,8 @@
 INLINE void *SafeMalloc(size_t size, const char *msg) // check if success
 {
   void *ptr = malloc(size);
-  PRINT(LD_MEM, "malloc data of size %d for %s: 0x%llx\n", size, msg, P64(ptr));
-  ASSERT(LT_SAFETY, ptr, "failed to allocate %d bytes for %s\n", size, msg);
+  PRINT(LD_MEM, "malloc data of size %zu for %s: 0x%llx\n", size, msg, P64(ptr));
+  ASSERT(LT_SAFETY, ptr, "failed to allocate %zu bytes for %s\n", size, msg);
   return ptr;
 }