[libomptarget][devicertl] Wrap source in declare target pragmas

[libomptarget][devicertl] Wrap source in declare target pragmas

Factored out of D93135 / D94745. C++ and cuda ignore unknown pragmas
so this is a NFC for the current implementation language. Removes noise
from patches for building deviceRTL as openmp.

Reviewed By: tianshilei1992

Differential Revision: https://reviews.llvm.org/D95048

openmp/libomptarget/deviceRTLs/amdgcn/src/amdgcn_locks.hip

@@ -14,6 +14,7 @@
 // a SIMD => wavefront mapping once that is implemented.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/debug.h"
 
@@ -26,3 +27,5 @@ DEVICE void __kmpc_impl_destroy_lock(omp_lock_t *) { warn(); }
 DEVICE void __kmpc_impl_set_lock(omp_lock_t *) { warn(); }
 DEVICE void __kmpc_impl_unset_lock(omp_lock_t *) { warn(); }
 DEVICE int __kmpc_impl_test_lock(omp_lock_t *lock) { warn(); }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/amdgcn/src/amdgcn_smid.hip

@@ -5,6 +5,7 @@
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "target_impl.h"
 
@@ -59,3 +60,5 @@ DEVICE uint32_t __kmpc_impl_smid() {
       ENCODE_HWREG(HW_ID_SE_ID_SIZE, HW_ID_SE_ID_OFFSET, HW_ID));
   return (se_id << HW_ID_CU_ID_SIZE) + cu_id;
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/amdgcn/src/target_impl.hip

@@ -9,6 +9,7 @@
 // Definitions of target specific functions
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "target_impl.h"
 
@@ -151,3 +152,5 @@ EXTERN uint32_t __kmpc_amdgcn_gpu_num_threads() {
 // Stub implementations
 DEVICE void *__kmpc_impl_malloc(size_t) { return nullptr; }
 DEVICE void __kmpc_impl_free(void *) {}
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/cancel.cu

@@ -9,6 +9,7 @@
 // Interface to be used in the implementation of OpenMP cancel.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "interface.h"
 #include "common/debug.h"
@@ -26,3 +27,5 @@ EXTERN int32_t __kmpc_cancel(kmp_Ident *loc, int32_t global_tid,
   // disabled
   return 0;
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/critical.cu

@@ -9,6 +9,7 @@
 // This file contains the implementation of critical with KMPC interface
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "interface.h"
 #include "common/debug.h"
@@ -26,3 +27,5 @@ void __kmpc_end_critical(kmp_Ident *loc, int32_t global_tid,
   PRINT0(LD_IO, "call to kmpc_end_critical()\n");
   omp_unset_lock((omp_lock_t *)lck);
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/data_sharing.cu

@@ -9,6 +9,8 @@
 // This file contains the implementation of data sharing environments
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
+
 #include "common/omptarget.h"
 #include "target_impl.h"
 
@@ -275,3 +277,4 @@ EXTERN void __kmpc_restore_team_static_memory(int16_t isSPMDExecutionMode,
   omptarget_nvptx_simpleMemoryManager.Release();
 }
 
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/libcall.cu

@@ -10,6 +10,7 @@
 // invoked by the user in an OpenMP region
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "common/target_atomic.h"
@@ -362,3 +363,5 @@ EXTERN int omp_test_lock(omp_lock_t *lock) {
   PRINT(LD_IO, "call omp_test_lock() return %d\n", rc);
   return rc;
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/loop.cu

@@ -11,6 +11,7 @@
 // interface as loops.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "target_impl.h"
@@ -754,3 +755,5 @@ void __kmpc_for_static_init_8u_simple_generic(
 EXTERN void __kmpc_for_static_fini(kmp_Ident *loc, int32_t global_tid) {
   PRINT0(LD_IO, "call kmpc_for_static_fini\n");
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/omp_data.cu

@@ -9,6 +9,7 @@
 // This file contains the data objects used on the GPU device.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "common/device_environment.h"
@@ -66,3 +67,5 @@ DEVICE SHARED void *ReductionScratchpadPtr;
 // Data sharing related variables.
 ////////////////////////////////////////////////////////////////////////////////
 DEVICE SHARED omptarget_nvptx_SharedArgs omptarget_nvptx_globalArgs;
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/omptarget.cu

@@ -9,6 +9,7 @@
 // This file contains the initialization code for the GPU
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "target_impl.h"
@@ -157,3 +158,5 @@ EXTERN int8_t __kmpc_is_spmd_exec_mode() {
   PRINT0(LD_IO | LD_PAR, "call to __kmpc_is_spmd_exec_mode\n");
   return isSPMDMode();
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/parallel.cu

@@ -31,6 +31,7 @@
 //    To make a long story short...
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "target_impl.h"
@@ -300,3 +301,5 @@ EXTERN void __kmpc_push_proc_bind(kmp_Ident *loc, uint32_t tid,
                                   int proc_bind) {
   PRINT(LD_IO, "call kmpc_push_proc_bind %d\n", (int)proc_bind);
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/reduction.cu

@@ -9,6 +9,7 @@
 // This file contains the implementation of reduction with KMPC interface.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "common/target_atomic.h"
@@ -312,3 +313,4 @@ EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait_v2(
   return 0;
 }
 
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/support.cu

@@ -9,6 +9,7 @@
 // Wrapper implementation to some functions natively supported by the GPU.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/support.h"
 #include "common/debug.h"
@@ -264,3 +265,4 @@ DEVICE char *GetTeamsReductionScratchpad() {
   return static_cast<char *>(ReductionScratchpadPtr) + 256;
 }
 
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/sync.cu

@@ -9,6 +9,7 @@
 // Include all synchronization.
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 #include "target_impl.h"
@@ -135,3 +136,5 @@ EXTERN void __kmpc_syncwarp(__kmpc_impl_lanemask_t Mask) {
   PRINT0(LD_IO, "call __kmpc_syncwarp\n");
   __kmpc_impl_syncwarp(Mask);
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/common/src/task.cu

@@ -26,6 +26,7 @@
 //    - end
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "common/omptarget.h"
 
@@ -214,3 +215,5 @@ EXTERN void __kmpc_taskloop(kmp_Ident *loc, uint32_t global_tid,
 
   __kmpc_omp_task_with_deps(loc, global_tid, newKmpTaskDescr, 0, 0, 0, 0);
 }
+
+#pragma omp end declare target

openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu

@@ -9,6 +9,7 @@
 // Definitions of target specific functions
 //
 //===----------------------------------------------------------------------===//
+#pragma omp declare target
 
 #include "target_impl.h"
 #include "common/debug.h"
@@ -158,3 +159,5 @@ DEVICE int __kmpc_impl_test_lock(omp_lock_t *lock) {
 
 DEVICE void *__kmpc_impl_malloc(size_t x) { return malloc(x); }
 DEVICE void __kmpc_impl_free(void *x) { free(x); }
+
+#pragma omp end declare target