diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 298e4b3..a11fd5b 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -3039,6 +3039,36 @@
   [(parallel [(set (match_dup 0) (match_dup 1))
 	      (set (match_dup 1) (match_dup 0))])])
 
+;; Replace a double word swap that requires 4 mov insns with a
+;; 3 mov insn implementation (or an xchg when optimizing for size).
+(define_peephole2
+  [(set (match_operand:DWIH 0 "general_reg_operand")
+	(match_operand:DWIH 1 "general_reg_operand"))
+   (set (match_operand:DWIH 2 "general_reg_operand")
+	(match_operand:DWIH 3 "general_reg_operand"))
+   (clobber (match_operand:<DWI> 4 "general_reg_operand"))
+   (set (match_dup 3) (match_dup 0))
+   (set (match_dup 1) (match_dup 2))]
+  "REGNO (operands[0]) != REGNO (operands[3])
+   && REGNO (operands[1]) != REGNO (operands[2])
+   && REGNO (operands[1]) != REGNO (operands[3])
+   && REGNO (operands[3]) == REGNO (operands[4])
+   && peep2_reg_dead_p (4, operands[0])
+   && peep2_reg_dead_p (5, operands[2])"
+  [(parallel [(set (match_dup 1) (match_dup 3))
+	      (set (match_dup 3) (match_dup 1))])]
+{
+  if (!optimize_insn_for_size_p ())
+    {
+      rtx tmp = REGNO (operands[0]) > REGNO (operands[2]) ? operands[0]
+							  : operands[2];
+      emit_move_insn (tmp, operands[1]);
+      emit_move_insn (operands[1], operands[3]);
+      emit_move_insn (operands[3], tmp);
+      DONE;
+    }
+})
+
 (define_expand "movstrict<mode>"
   [(set (strict_low_part (match_operand:SWI12 0 "register_operand"))
 	(match_operand:SWI12 1 "general_operand"))]
diff --git a/gcc/testsuite/gcc.target/i386/pr43644.c b/gcc/testsuite/gcc.target/i386/pr43644.c
new file mode 100644
index 0000000..ffdf31c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr43644.c
@@ -0,0 +1,11 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+__int128 foo(__int128 x, __int128 y)
+{
+  return x+y;
+}
+
+/* { dg-final { scan-assembler-times "movq" 2 } } */
+/* { dg-final { scan-assembler-not "push" } } */
+/* { dg-final { scan-assembler-not "pop" } } */