[clang] [Headers][X86] Use `__builtin_elementwise_ctlz` instead of avx512cd intrinsics. (PR #155089)

[via cfe-commits]

================
@@ -63,10 +69,9 @@ _mm512_maskz_conflict_epi32 (__mmask16 __U, __m512i __A)
                                             (__v16si)_mm512_setzero_si512());
 }
 
-static __inline__ __m512i __DEFAULT_FN_ATTRS
-_mm512_lzcnt_epi32 (__m512i __A)
-{
-  return (__m512i) __builtin_ia32_vplzcntd_512 ((__v16si) __A);
+static __inline__ __m512i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm512_lzcnt_epi32(__m512i __A) {
+  return (__m512i)__builtin_elementwise_ctlz((__v16si)__A);
----------------
moorabbit wrote:

I suspect that people using x86 intrinsics are primarily interested in the optimized builds.

https://github.com/llvm/llvm-project/pull/155089