[libomptarget] Harmonize emitting CUDA errors and general debug messages.

[Meinersbur]

Summary

Ensures that CUDA fail reasons (such as "No CUDA-capable device detected") are printed together with libomptarget's debug message (e.g. "Error when setting CUDA context"). Previously, the former was printed only in CMAKE_BUILD_TYPE=Debug builds while the latter was enabled by LIBOMPTARGET_ENABLE_DEBUG,

With this change, also only call cuGetErrorString when the error will be printed.

Suggested-by: Ye Luo

[grokos]

This patch makes debug output more consistent, thanks!

[ye-luo]

LGTM. One fewer hidden knob!

libomptarget/plugins/cuda/CMakeLists.txt

elseif(NOT LIBOMPTARGET_DEP_CUDA_DRIVER_FOUND)
   return()
 endif()
 
 libomptarget_say("Building CUDA offloading plugin.")
 
 # Define the suffix for the runtime messaging dumps.
 add_definitions(-DTARGET_NAME=CUDA)
 
-if(LIBOMPTARGET_CMAKE_BUILD_TYPE MATCHES debug)
-    add_definitions(-DCUDA_ERROR_REPORT)
-endif()
-
 include_directories(${LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS})
 include_directories(${LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS})
 
 add_library(omptarget.rtl.cuda SHARED src/rtl.cpp)
 
 # Install plugin under the lib destination folder.
 install(TARGETS omptarget.rtl.cuda LIBRARY DESTINATION "${OPENMP_INSTALL_LIBDIR}")
 
 target_link_libraries(omptarget.rtl.cuda
   ${LIBOMPTARGET_DEP_CUDA_DRIVER_LIBRARIES}
   ${LIBOMPTARGET_DEP_LIBELF_LIBRARIES}
   "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/../exports")
 
 # Report to the parent scope that we are building a plugin for CUDA.
 set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS} nvptx64-nvidia-cuda" PARENT_SCOPE)

libomptarget/plugins/cuda/src/rtl.cpp

 #define GETNAME2(name) #name
 #define GETNAME(name) GETNAME2(name)
 #define DP(...) \
   do { \
     if (DebugLevel > 0) { \
       DEBUGP("Target " GETNAME(TARGET_NAME) " RTL", __VA_ARGS__); \
     } \
   } while (false)
-#else // OMPTARGET_DEBUG
-#define DP(...) {}
-#endif // OMPTARGET_DEBUG
-
-#include "../../common/elf_common.c"
 
 // Utility for retrieving and printing CUDA error string.
-#ifdef CUDA_ERROR_REPORT
-#define CUDA_ERR_STRING(err)                                                   \
-  do {                                                                         \
-    const char *errStr;                                                        \
-    cuGetErrorString(err, &errStr);                                            \
-    DP("CUDA error is: %s\n", errStr);                                         \
-  } while (0)
-#else
-#define CUDA_ERR_STRING(err)                                                   \
-  {}
-#endif
+#define CUDA_ERR_STRING(err) \
+  do { \
+    if (DebugLevel > 0) { \
+      const char *errStr; \
+      cuGetErrorString(err, &errStr); \
+      DEBUGP("Target " GETNAME(TARGET_NAME) " RTL", "CUDA error is: %s\n", errStr); \
+    } \
+  } while (false)
+#else // OMPTARGET_DEBUG
+#define DP(...) {}
+#define CUDA_ERR_STRING(err) {}
+#endif // OMPTARGET_DEBUG
+
+#include "../../common/elf_common.c"
 
 /// Keep entries table per device.
 struct FuncOrGblEntryTy {
   __tgt_target_table Table;
   std::vector<__tgt_offload_entry> Entries;
 };
 
 enum ExecutionModeType {