diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h
index f2da340bb9..8bcd60d0ed 100644
--- a/include/tcg/tcg.h
+++ b/include/tcg/tcg.h
@@ -319,6 +319,22 @@ typedef enum TCGType {
 #endif
 } TCGType;
 
+/**
+ * tcg_type_size
+ * @t: type
+ *
+ * Return the size of the type in bytes.
+ */
+static inline int tcg_type_size(TCGType t)
+{
+    unsigned i = t;
+    if (i >= TCG_TYPE_V64) {
+        tcg_debug_assert(i < TCG_TYPE_COUNT);
+        i -= TCG_TYPE_V64 - 1;
+    }
+    return 4 << i;
+}
+
 /**
  * get_alignment_bits
  * @memop: MemOp value
diff --git a/tcg/tcg.c b/tcg/tcg.c
index a02086c482..f74507ba66 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -3038,22 +3038,22 @@ static bool liveness_pass_2(TCGContext *s)
 
 static void temp_allocate_frame(TCGContext *s, TCGTemp *ts)
 {
-    intptr_t off, size, align;
+    int size = tcg_type_size(ts->type);
+    int align;
+    intptr_t off;
 
     switch (ts->type) {
     case TCG_TYPE_I32:
-        size = align = 4;
+        align = 4;
         break;
     case TCG_TYPE_I64:
     case TCG_TYPE_V64:
-        size = align = 8;
+        align = 8;
         break;
     case TCG_TYPE_V128:
-        size = align = 16;
-        break;
     case TCG_TYPE_V256:
         /* Note that we do not require aligned storage for V256. */
-        size = 32, align = 16;
+        align = 16;
         break;
     default:
         g_assert_not_reached();
@@ -3593,8 +3593,8 @@ static void tcg_reg_alloc_dup(TCGContext *s, const TCGOp *op)
     TCGRegSet dup_out_regs, dup_in_regs;
     TCGTemp *its, *ots;
     TCGType itype, vtype;
-    intptr_t endian_fixup;
     unsigned vece;
+    int lowpart_ofs;
     bool ok;
 
     ots = arg_temp(op->args[0]);
@@ -3662,15 +3662,12 @@ static void tcg_reg_alloc_dup(TCGContext *s, const TCGOp *op)
         /* fall through */
 
     case TEMP_VAL_MEM:
-#if HOST_BIG_ENDIAN
-        endian_fixup = itype == TCG_TYPE_I32 ? 4 : 8;
-        endian_fixup -= 1 << vece;
-#else
-        endian_fixup = 0;
-#endif
-        /* Attempt to dup directly from the input memory slot. */
+        lowpart_ofs = 0;
+        if (HOST_BIG_ENDIAN) {
+            lowpart_ofs = tcg_type_size(itype) - (1 << vece);
+        }
         if (tcg_out_dupm_vec(s, vtype, vece, ots->reg, its->mem_base->reg,
-                             its->mem_offset + endian_fixup)) {
+                             its->mem_offset + lowpart_ofs)) {
             goto done;
         }
         /* Load the input into the destination vector register. */