[OPENMP][NVPTX]Added/fixed debugging messages, NFC.

[ABataev]

Summary

Added or fixed new/old debugging messages for the better diagnostics.

[grokos]

libomptarget/deviceRTLs/nvptx/src/supporti.h

241–242

Why do we need to cast size to unsigned long long?

[ABataev]

libomptarget/deviceRTLs/nvptx/src/supporti.h

241–242

%zu modifier is not recognized and it leads to the crash at the runtime.

[grokos]

LGTM.

libomptarget/deviceRTLs/nvptx/src/omptarget-nvptx.cu

EXTERN void __kmpc_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime) {
   // set number of threads and thread limit in team to started value
   omptarget_nvptx_TaskDescr *currTaskDescr =
       omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(threadId);
   currTaskDescr->NThreads() = GetNumberOfWorkersInTeam();
   currTaskDescr->ThreadLimit() = ThreadLimit;
 }
 
 EXTERN void __kmpc_kernel_deinit(int16_t IsOMPRuntimeInitialized) {
+  PRINT0(LD_IO, "call to __kmpc_kernel_deinit\n");
   ASSERT0(LT_FUSSY, IsOMPRuntimeInitialized,
           "Generic always requires initialized runtime.");
   // Enqueue omp state object for use by another team.
   int slot = usedSlotIdx;
   omptarget_nvptx_device_State[slot].Enqueue(
       omptarget_nvptx_threadPrivateContext);
   // Done with work.  Kill the workers.
   omptarget_nvptx_workFn = 0;
if (threadId == 0) {
     int slot = usedSlotIdx;
     omptarget_nvptx_device_State[slot].Enqueue(
         omptarget_nvptx_threadPrivateContext);
   }
 }
 
 // Return true if the current target region is executed in SPMD mode.
 EXTERN int8_t __kmpc_is_spmd_exec_mode() {
+  PRINT0(LD_IO | LD_PAR, "call to __kmpc_is_spmd_exec_mode\n");
   return isSPMDMode();
 }

libomptarget/deviceRTLs/nvptx/src/parallel.cu

EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
   PRINT0(LD_IO | LD_PAR, "call to __kmpc_kernel_parallel\n");
 
   ASSERT0(LT_FUSSY, IsOMPRuntimeInitialized, "Expected initialized runtime.");
 
   // Work function and arguments for L1 parallel region.
   *WorkFn = omptarget_nvptx_workFn;
 
   // If this is the termination signal from the master, quit early.
-  if (!*WorkFn)
+  if (!*WorkFn) {
+    PRINT0(LD_IO | LD_PAR, "call to __kmpc_kernel_parallel finished\n");
     return false;
+  }
 
   // Only the worker threads call this routine and the master warp
   // never arrives here.  Therefore, use the nvptx thread id.
   int threadId = GetThreadIdInBlock();
   omptarget_nvptx_WorkDescr &workDescr = getMyWorkDescriptor();
   // Set to true for workers participating in the parallel region.
   bool isActive = false;
   // Initialize state for active threads.

libomptarget/deviceRTLs/nvptx/src/supporti.h

INLINE unsigned long PadBytes(unsigned long size,
   ASSERT(LT_FUSSY, (alignment & (alignment - 1)) == 0,
          "alignment %lu is not a power of 2\n", alignment);
   return (~(unsigned long)size + 1) & (alignment - 1);
 }
 
 INLINE void *SafeMalloc(size_t size, const char *msg) // check if success
 {
   void *ptr = malloc(size);
-  PRINT(LD_MEM, "malloc data of size %zu for %s: 0x%llx\n", size, msg,
-        (unsigned long long)ptr);
+  PRINT(LD_MEM, "malloc data of size %llu for %s: 0x%llx\n",
+        (unsigned long long)size, msg, (unsigned long long)ptr);
   return ptr;
 }
 
 INLINE void *SafeFree(void *ptr, const char *msg) {
   PRINT(LD_MEM, "free data ptr 0x%llx for %s\n", (unsigned long long)ptr, msg);
   free(ptr);
   return NULL;
 }