diff --git a/openmp/libomptarget/DeviceRTL/include/Configuration.h b/openmp/libomptarget/DeviceRTL/include/Configuration.h
--- a/openmp/libomptarget/DeviceRTL/include/Configuration.h
+++ b/openmp/libomptarget/DeviceRTL/include/Configuration.h
@@ -18,7 +18,10 @@
 namespace _OMP {
 namespace config {
 
-enum DebugLevel : int32_t { Assertion };
+enum DebugKind : uint32_t {
+  Assertion = 1 << 0,
+  FunctionTracing = 1 << 1,
+};
 
 /// Return the number of devices in the system, same number as returned on the
 /// host by omp_get_num_devices.
@@ -29,12 +32,12 @@
 uint32_t getDeviceNum();
 
 /// Return the user choosen debug level.
-uint32_t getDebugLevel();
+uint32_t getDebugKind();
 
 /// Return the amount of dynamic shared memory that was allocated at launch.
 uint64_t getDynamicMemorySize();
 
-bool isDebugMode(DebugLevel Level);
+bool isDebugMode(DebugKind Level);
 
 } // namespace config
 } // namespace _OMP
diff --git a/openmp/libomptarget/DeviceRTL/include/Debug.h b/openmp/libomptarget/DeviceRTL/include/Debug.h
--- a/openmp/libomptarget/DeviceRTL/include/Debug.h
+++ b/openmp/libomptarget/DeviceRTL/include/Debug.h
@@ -37,4 +37,11 @@
 
 ///}
 
+#define ENTER DebugEntryRAII Entry(__FILE__, __LINE__, __PRETTY_FUNCTION__);
+
+struct DebugEntryRAII {
+  DebugEntryRAII(const char *File, const unsigned Line, const char *Function);
+  ~DebugEntryRAII();
+};
+
 #endif
diff --git a/openmp/libomptarget/DeviceRTL/src/Configuration.cpp b/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
--- a/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
@@ -18,7 +18,7 @@
 using namespace _OMP;
 
 struct DeviceEnvironmentTy {
-  uint32_t DebugLevel;
+  uint32_t DebugKind;
   uint32_t NumDevices;
   uint32_t DeviceNum;
   uint64_t DynamicMemSize;
@@ -32,8 +32,8 @@
 DeviceEnvironmentTy CONSTANT(omptarget_device_environment)
     __attribute__((used));
 
-uint32_t config::getDebugLevel() {
-  return __omp_rtl_debug_kind & omptarget_device_environment.DebugLevel;
+uint32_t config::getDebugKind() {
+  return __omp_rtl_debug_kind & omptarget_device_environment.DebugKind;
 }
 
 uint32_t config::getNumDevices() {
@@ -48,8 +48,8 @@
   return omptarget_device_environment.DynamicMemSize;
 }
 
-bool config::isDebugMode(config::DebugLevel Level) {
-  return config::getDebugLevel() > Level;
+bool config::isDebugMode(config::DebugKind Kind) {
+  return config::getDebugKind() & Kind;
 }
 
 #pragma omp end declare target
diff --git a/openmp/libomptarget/DeviceRTL/src/Debug.cpp b/openmp/libomptarget/DeviceRTL/src/Debug.cpp
--- a/openmp/libomptarget/DeviceRTL/src/Debug.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/Debug.cpp
@@ -12,6 +12,7 @@
 
 #include "Debug.h"
 #include "Configuration.h"
+#include "Mapping.h"
 
 using namespace _OMP;
 
@@ -19,7 +20,7 @@
 
 extern "C" {
 void __assert_assume(bool cond, const char *exp, const char *file, int line) {
-  if (!cond && config::isDebugMode(config::DebugLevel::Assertion)) {
+  if (!cond && config::isDebugMode(config::DebugKind::Assertion)) {
     PRINTF("ASSERTION failed: %s at %s, line %d\n", exp, file, line);
     __builtin_trap();
   }
@@ -47,4 +48,29 @@
 #pragma omp end declare variant
 ///}
 
+namespace {
+/// Current indentation level for the function trace. Only accessed by thread 0.
+uint32_t Level = 0;
+} // namespace
+
+DebugEntryRAII::DebugEntryRAII(const char *File, const unsigned Line,
+                               const char *Function) {
+  if (mapping::getThreadIdInBlock() == 0 &&
+      config::isDebugMode(config::DebugKind::FunctionTracing)) {
+
+    for (int I = 0; I < Level; ++I)
+      PRINTF("%s", "  ");
+
+    PRINTF("%s:%u: Thread %u Entering %s:\n", File, Line,
+           mapping::getThreadIdInBlock(), Function);
+    Level++;
+  }
+}
+
+DebugEntryRAII::~DebugEntryRAII() {
+  if (mapping::getThreadIdInBlock() == 0 &&
+      config::isDebugMode(config::DebugKind::FunctionTracing))
+    Level--;
+}
+
 #pragma omp end declare target