[openmp][amdgpu] Replace unsigned long with uint64_t

[JonChesterfield]

Summary

Some types need to be 64 bit. Unsigned long is a hazard there.

openmp/libomptarget/plugins/amdgpu/impl/internal.h

 #error "Missing TARGET_NAME macro"
 #endif
 #define DEBUG_PREFIX "Target " GETNAME(TARGET_NAME) " RTL"
 #include "Debug.h"
 
 #define MAX_NUM_KERNELS (1024 * 16)
 
 typedef struct impl_implicit_args_s {
-  unsigned long offset_x;
-  unsigned long offset_y;
-  unsigned long offset_z;
-  unsigned long hostcall_ptr;
-  unsigned long unused0;
-  unsigned long unused1;
-  unsigned long unused2;
+  uint64_t offset_x;
+  uint64_t offset_y;
+  uint64_t offset_z;
+  uint64_t hostcall_ptr;
+  uint64_t unused0;
+  uint64_t unused1;
+  uint64_t unused2;
 } impl_implicit_args_t;
 static_assert(sizeof(impl_implicit_args_t) == 56, "");
 
 // ---------------------- Kernel Start -------------
 typedef struct atl_kernel_info_s {
   uint64_t kernel_object;
   uint32_t group_segment_size;
   uint32_t private_segment_size;

openmp/libomptarget/plugins/amdgpu/src/rtl.cpp

 #include "llvm/Frontend/OpenMP/OMPConstants.h"
 #include "llvm/Frontend/OpenMP/OMPGridValues.h"
 
 // hostrpc interface, FIXME: consider moving to its own include these are
 // statically linked into amdgpu/plugin if present from hostrpc_services.a,
 // linked as --whole-archive to override the weak symbols that are used to
 // implement a fallback for toolchains that do not yet have a hostrpc library.
 extern "C" {
-unsigned long hostrpc_assign_buffer(hsa_agent_t agent, hsa_queue_t *this_Q,
-                                    uint32_t device_id);
+uint64_t hostrpc_assign_buffer(hsa_agent_t agent, hsa_queue_t *this_Q,
 hsa_status_t hostrpc_init();
 hsa_status_t hostrpc_terminate();
 
 __attribute__((weak)) hsa_status_t hostrpc_init() { return HSA_STATUS_SUCCESS; }
 __attribute__((weak)) hsa_status_t hostrpc_terminate() {
   return HSA_STATUS_SUCCESS;
 }
-__attribute__((weak)) unsigned long
-hostrpc_assign_buffer(hsa_agent_t, hsa_queue_t *, uint32_t device_id) {
+__attribute__((weak)) uint64_t hostrpc_assign_buffer(hsa_agent_t, hsa_queue_t *,
+                                                     uint32_t device_id) {
   DP("Warning: Attempting to assign hostrpc to device %u, but hostrpc library "
      "missing\n",
      device_id);
   return 0;
 }
 }
 
 // Heuristic parameters used for kernel launch
if (!ArgPool) {
       impl_args->offset_z = 0;
 
       // assign a hostcall buffer for the selected Q
       if (__atomic_load_n(&DeviceInfo.hostcall_required, __ATOMIC_ACQUIRE)) {
         // hostrpc_assign_buffer is not thread safe, and this function is
         // under a multiple reader lock, not a writer lock.
         static pthread_mutex_t hostcall_init_lock = PTHREAD_MUTEX_INITIALIZER;
         pthread_mutex_lock(&hostcall_init_lock);
-        unsigned long buffer = hostrpc_assign_buffer(
-            DeviceInfo.HSAAgents[device_id], queue, device_id);
+        uint64_t buffer = hostrpc_assign_buffer(DeviceInfo.HSAAgents[device_id],
+                                                queue, device_id);
         pthread_mutex_unlock(&hostcall_init_lock);
         if (!buffer) {
           DP("hostrpc_assign_buffer failed, gpu would dereference null and "
              "error\n");
           return OFFLOAD_FAIL;
         }
 
         if (KernelInfoEntry.implicit_argument_count >= 4) {