[Clang] Fix 'gpuintrin.h' match when included with no arch set

Summary:
These require `+ptx` features to be set even though they're guarded by
the `__nvvm_reflect`. Rather than figure out how to hack around that
with the `target` attribute I'm just going to disable it for 'generic'
builds and use the slow version for now.

Author: jhuber6

clang/lib/Headers/nvptxintrin.h

@@ -179,8 +179,10 @@ __gpu_shuffle_idx_u64(uint64_t __lane_mask, uint32_t __idx, uint64_t __x,
 _DEFAULT_FN_ATTRS static __inline__ uint64_t
 __gpu_match_any_u32(uint64_t __lane_mask, uint32_t __x) {
   // Newer targets can use the dedicated CUDA support.
-  if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
+#if __CUDA_ARCH__ >= 700
+  if (__nvvm_reflect("__CUDA_ARCH") >= 700)
     return __nvvm_match_any_sync_i32(__lane_mask, __x);
+#endif
 
   uint32_t __match_mask = 0;
   bool __done = 0;
@@ -200,8 +202,10 @@ __gpu_match_any_u32(uint64_t __lane_mask, uint32_t __x) {
 _DEFAULT_FN_ATTRS static __inline__ uint64_t
 __gpu_match_any_u64(uint64_t __lane_mask, uint64_t __x) {
   // Newer targets can use the dedicated CUDA support.
+#if __CUDA_ARCH__ >= 700
   if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
     return __nvvm_match_any_sync_i64(__lane_mask, __x);
+#endif
 
   uint64_t __match_mask = 0;
 
@@ -223,9 +227,11 @@ __gpu_match_any_u64(uint64_t __lane_mask, uint64_t __x) {
 _DEFAULT_FN_ATTRS static __inline__ uint64_t
 __gpu_match_all_u32(uint64_t __lane_mask, uint32_t __x) {
   // Newer targets can use the dedicated CUDA support.
+#if __CUDA_ARCH__ >= 700
   int predicate;
   if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
     return __nvvm_match_all_sync_i32p(__lane_mask, __x, &predicate);
+#endif
 
   uint32_t __first = __gpu_read_first_lane_u64(__lane_mask, __x);
   uint64_t __ballot = __gpu_ballot(__lane_mask, __x == __first);
@@ -236,9 +242,11 @@ __gpu_match_all_u32(uint64_t __lane_mask, uint32_t __x) {
 _DEFAULT_FN_ATTRS static __inline__ uint64_t
 __gpu_match_all_u64(uint64_t __lane_mask, uint64_t __x) {
   // Newer targets can use the dedicated CUDA support.
+#if __CUDA_ARCH__ >= 700
   int predicate;
   if (__CUDA_ARCH__ >= 700 || __nvvm_reflect("__CUDA_ARCH") >= 700)
     return __nvvm_match_all_sync_i64p(__lane_mask, __x, &predicate);
+#endif
 
   uint64_t __first = __gpu_read_first_lane_u64(__lane_mask, __x);
   uint64_t __ballot = __gpu_ballot(__lane_mask, __x == __first);