diff --git a/clang/lib/Basic/Builtins.cpp b/clang/lib/Basic/Builtins.cpp
index 885abdc152e3a..8e38ec98277e7 100644
--- a/clang/lib/Basic/Builtins.cpp
+++ b/clang/lib/Basic/Builtins.cpp
@@ -225,7 +225,8 @@ void Builtin::Context::initializeBuiltins(IdentifierTable &Table,
     // Step #3: Register target-specific builtins for AuxTarget.
     for (const auto &Shard : AuxTargetShards)
       for (const auto &I : Shard.Infos) {
-        Table.get(I.getName(Shard)).setBuiltinID(ID);
+        if (builtinIsSupported(*Shard.Strings, I, LangOpts))
+          Table.get(I.getName(Shard)).setBuiltinID(ID);
         ++ID;
       }
   }
diff --git a/clang/lib/Headers/cpuid.h b/clang/lib/Headers/cpuid.h
index ce8c79e77dc18..52addb7bfa856 100644
--- a/clang/lib/Headers/cpuid.h
+++ b/clang/lib/Headers/cpuid.h
@@ -345,15 +345,10 @@ static __inline int __get_cpuid_count (unsigned int __leaf,
 // In some configurations, __cpuidex is defined as a builtin (primarily
 // -fms-extensions) which will conflict with the __cpuidex definition below.
 #if !(__has_builtin(__cpuidex))
-// In some cases, offloading will set the host as the aux triple and define the
-// builtin. Given __has_builtin does not detect builtins on aux triples, we need
-// to explicitly check for some offloading cases.
-#ifndef __NVPTX__
 static __inline void __cpuidex(int __cpu_info[4], int __leaf, int __subleaf) {
   __cpuid_count(__leaf, __subleaf, __cpu_info[0], __cpu_info[1], __cpu_info[2],
                 __cpu_info[3]);
 }
 #endif
-#endif
 
 #endif /* __CPUID_H */
diff --git a/clang/test/Headers/__cpuidex_conflict.c b/clang/test/Headers/__cpuidex_conflict.c
index d14ef293e586d..e911036a1d953 100644
--- a/clang/test/Headers/__cpuidex_conflict.c
+++ b/clang/test/Headers/__cpuidex_conflict.c
@@ -5,7 +5,7 @@
 
 // Ensure that we do not run into conflicts when offloading.
 // RUN: %clang_cc1 %s -DIS_STATIC=static -ffreestanding -fopenmp -fopenmp-is-target-device -aux-triple x86_64-unknown-linux-gnu
-// RUN: %clang_cc1 -DIS_STATIC="" -triple nvptx64-nvidia-cuda -aux-triple x86_64-unknown-linux-gnu -aux-target-cpu x86-64 -fcuda-is-device -internal-isystem /home/gha/llvm-project/build/lib/clang/22/include -x cuda %s -o -
+// RUN: %clang_cc1 -DIS_STATIC=static -triple nvptx64-nvidia-cuda -aux-triple x86_64-unknown-linux-gnu -aux-target-cpu x86-64 -fcuda-is-device -x cuda %s -o -
 
 typedef __SIZE_TYPE__ size_t;