[libomptarget] Drop assert.h, use freestanding for amdgcn devicertl

[JonChesterfield]

Summary

[libomptarget] Drop assert.h, use freestanding for amdgcn devicertl

Promotes the runtime assert to a link time error for the unimplemented
fallback functions. Enables amdgcn to build with only clang provided
headers, which makes it less likely to break other builds when enabled.

[jdoerfert]

LG

openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt

if (DEFINED LIBOMPTARGET_AMDGCN_GFXLIST)
   set(mcpus ${LIBOMPTARGET_AMDGCN_GFXLIST})
 endif()
 
 macro(add_cuda_bc_library)
   set(cu_cmd ${AOMP_BINDIR}/clang++
     -xc++
     -c
     -std=c++14
+    -ffreestanding
     -target amdgcn
     -emit-llvm
     -Xclang -aux-triple -Xclang x86_64-unknown-linux-gnu # see nvptx
     -fopenmp -fopenmp-cuda-mode -Xclang -fopenmp-is-device
     -D__AMDGCN__
     -Xclang -target-cpu -Xclang ${mcpu}
     -fvisibility=default
     -Wno-unused-value

openmp/libomptarget/deviceRTLs/common/include/target/shuffle.h

 //
 // Note: We unify the mask type to uint64_t instead of __kmpc_impl_lanemask_t.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LIBOMPTARGET_DEVICERTL_SHUFFLE_H
 #define LIBOMPTARGET_DEVICERTL_SHUFFLE_H
 
-#include <assert.h>
 #include <stdint.h>
 
 #pragma omp declare target
 
 /// External shuffle API
 ///
 ///{
 

 ///{
 unsigned GetLaneId();
 unsigned GetWarpSize();
 void __kmpc_impl_unpack(uint64_t val, uint32_t &lo, uint32_t &hi);
 uint64_t __kmpc_impl_pack(uint32_t lo, uint32_t hi);
 ///}
 
 /// Fallback implementations of the shuffle sync idiom.
+/// Unavailable at present (would error at link time if used).
 ///
 ///{
 
-inline int32_t __kmpc_impl_shfl_sync(uint64_t Mask, int32_t Var,
-                                     int32_t SrcLane) {
-  assert(false &&
-         "Fallback version of __kmpc_impl_shfl_sync is not available!");
-}
+int32_t __kmpc_impl_shfl_sync(uint64_t Mask, int32_t Var, int32_t SrcLane);
 
-inline int32_t __kmpc_impl_shfl_down_sync(uint64_t Mask, int32_t Var,
-                                          uint32_t Delta, int32_t Width) {
-  assert(false &&
-         "Fallback version of __kmpc_impl_shfl_down_sync is not available!");
-}
+int32_t __kmpc_impl_shfl_down_sync(uint64_t Mask, int32_t Var, uint32_t Delta,
+                                   int32_t Width);
 
 ///}
 
 /// AMDGCN implementations of the shuffle sync idiom.
 ///
 ///{
 #pragma omp begin declare variant match(device = {arch(amdgcn)})