[libc] Use __builtin_ctzll instead of __builtin_ctzl in elements_x86.h.

[sivachandra]

Summary

builtin_ctzl takes an unsigned long argument which need not be 64-bit
long on all platforms. Using builtin_ctzll, which takes an unsigned
long long argument, ensures that 64-bit values will be handled on a
wider range of platforms.

Without this change, the test corresponding to M512 fails in Windows.

[gchatelet]

LGTM thx!

libc/src/string/memory_utils/elements_x86.h

static int ThreeWayCompare(const char *a, const char *b) {
     return CharDiff(a, b, mask);
   }
 
   static void SplatSet(char *dst, const unsigned char value) {
     Base::Store(dst, Base::GetSplattedValue(value));
   }
 
   static int CharDiff(const char *a, const char *b, uint64_t mask) {
-    const size_t diff_index = __builtin_ctzl(mask);
+    const size_t diff_index = __builtin_ctzll(mask);
     const int ca = (unsigned char)a[diff_index];
     const int cb = (unsigned char)b[diff_index];
     return ca - cb;
   }
 };
 
 struct M128 {
   static constexpr size_t kSize = 16;