Index: ChangeLog
===================================================================
--- ChangeLog	(revision 246706)
+++ ChangeLog	(working copy)
@@ -1,3 +1,10 @@
+2017-04-05  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/70703
+	* ira-color.c (update_costs_from_allocno): Use the smallest mode.
+	(update_conflict_hard_regno_costs): Use long instead of unsigned
+	arithmetic for cost calculation.
+
 2017-04-05  Jakub Jelinek  <jakub@redhat.com>
 	    Bernd Edlinger  <bernd.edlinger@hotmail.de>
 
Index: testsuite/ChangeLog
===================================================================
--- testsuite/ChangeLog	(revision 246706)
+++ testsuite/ChangeLog	(working copy)
@@ -1,3 +1,8 @@
+2017-04-05  Vladimir Makarov  <vmakarov@redhat.com>
+
+	PR rtl-optimization/70703
+	* gcc.target/i386/pr70703.c: New.
+
 2017-04-05  Jakub Jelinek  <jakub@redhat.com>
 
 	PR sanitizer/80308
Index: ira-color.c
===================================================================
--- ira-color.c	(revision 246536)
+++ ira-color.c	(working copy)
@@ -1367,6 +1367,16 @@ update_costs_from_allocno (ira_allocno_t
 	      || ALLOCNO_ASSIGNED_P (another_allocno))
 	    continue;
 
+	  if (GET_MODE_SIZE (ALLOCNO_MODE (cp->second)) < GET_MODE_SIZE (mode))
+	    /* If we have different modes use the smallest one.  It is
+	       a sub-register move.  It is hard to predict what LRA
+	       will reload (the pseudo or its sub-register) but LRA
+	       will try to minimize the data movement.  Also for some
+	       register classes bigger modes might be invalid,
+	       e.g. DImode for AREG on x86.  For such cases the
+	       register move cost will be maximal. */
+	    mode = ALLOCNO_MODE (cp->second);
+	  
 	  cost = (cp->second == allocno
 		  ? ira_register_move_cost[mode][rclass][aclass]
 		  : ira_register_move_cost[mode][aclass][rclass]);
@@ -1512,7 +1522,7 @@ update_conflict_hard_regno_costs (int *c
 		index = ira_class_hard_reg_index[aclass][hard_regno];
 		if (index < 0)
 		  continue;
-		cost = (int) ((unsigned) conflict_costs [i] * mult) / div;
+		cost = (int) (((long) conflict_costs [i] * mult) / div);
 		if (cost == 0)
 		  continue;
 		cont_p = true;
Index: testsuite/gcc.target/i386/pr70703.c
===================================================================
--- testsuite/gcc.target/i386/pr70703.c	(nonexistent)
+++ testsuite/gcc.target/i386/pr70703.c	(working copy)
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fomit-frame-pointer" } */
+/* { dg-require-effective-target ia32 } */
+/* { dg-final { scan-assembler "movl\t\\\$6700417, %eax" } } */
+
+unsigned ud_x_641_mul(unsigned x) {
+    /* optimized version of x / 641 */
+    return ((unsigned long long)x * 0x663d81) >> 32;
+}