diff --git a/src/include/port/pg_lfind.h b/src/include/port/pg_lfind.h
index d575e733d3..0625cac6b5 100644
--- a/src/include/port/pg_lfind.h
+++ b/src/include/port/pg_lfind.h
@@ -151,7 +151,7 @@ pg_lfind32(uint32 key, uint32 *base, uint32 nelem)
 		result = vector32_or(tmp1, tmp2);
 
 		/* see if there was a match */
-		if (vector8_is_highbit_set((Vector8) result))
+		if (vector32_is_highbit_set(result))
 		{
 			Assert(assert_result == true);
 			return true;
diff --git a/src/include/port/simd.h b/src/include/port/simd.h
index b538ac070f..0ff1549083 100644
--- a/src/include/port/simd.h
+++ b/src/include/port/simd.h
@@ -274,6 +274,28 @@ vector8_is_highbit_set(const Vector8 v)
 #endif
 }
 
+/*
+ * Exactly like vector32_is_highbit_set except for the input type, so it
+ * looks at each byte separately.
+ *
+ * XXX x86 uses the same underlying type for 8-bit, 16-bit, and 32-bit
+ * integer elements, but Arm does not, hence the need for a separate
+ * function. We could instead adopt the behavior of Arm's vmaxvq_u32(), i.e.
+ * check each 32-bit element, but that would require an additional mask
+ * operation on x86.
+ */
+#ifndef USE_NO_SIMD
+static inline bool
+vector32_is_highbit_set(const Vector32 v)
+{
+#if defined(USE_NEON)
+	return vector8_is_highbit_set((Vector8) v);
+#else
+	return vector8_is_highbit_set(v);
+#endif
+}
+#endif							/* ! USE_NO_SIMD */
+
 /*
  * Return the bitwise OR of the inputs
  */