Write vectorized 32-bit compare by hand for arm in scan16

ConflictSet.cpp

@@ -1776,10 +1776,32 @@ bool scan16(const InternalVersionT *vs, const uint8_t *is, int begin, int end,
   uint64_t mask = vget_lane_u64(
       vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(results), 4)), 0);
 
+#if INTERNAL_VERSION_32_BIT
+  uint32x4_t w4[4];
+  memcpy(w4, vs, sizeof(w4));
+  uint32_t rv;
+  memcpy(&rv, &readVersion, sizeof(rv));
+
+  int32x4_t z;
+  memset(&z, 0, sizeof(z));
+
+  uint16x4_t conflicting[4];
+  for (int i = 0; i < 4; ++i) {
+    conflicting[i] = vmovn_u32(vcgtq_s32(vsubq_u32(w4[i], vdupq_n_u32(rv)), z));
+  }
+  auto combined =
+      vcombine_u8(vmovn_u16(vcombine_u16(conflicting[0], conflicting[1])),
+                  vmovn_u16(vcombine_u16(conflicting[2], conflicting[3])));
+
+  uint64_t compared = vget_lane_u64(
+      vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(combined), 4)), 0);
+#else
   uint64_t compared = 0;
   for (int i = 0; i < 16; ++i) {
     compared |= uint64_t(vs[i] > readVersion) << (i << 2);
   }
+#endif
+
   return !(compared & mask);
 
 #elif defined(HAS_AVX)