diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9f84b6ef837..42864914945 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2015-10-08  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* config/i386/i386.c (ix86_compute_frame_layout): Round up the
+	SSE register save area to 16 bytes only if the incoming stack
+	boundary is no less than 16 bytes.
+
 2015-10-08  Jeff Law  <law@redhat.com>
 
 	* tree-ssa-phiopt.c (factor_out_conversion): Add missing calls to
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index a24bd26c96a..4806a7cffa2 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -11383,9 +11383,14 @@ ix86_compute_frame_layout (struct ix86_frame *frame)
   if (frame->nsseregs)
     {
       /* The only ABI that has saved SSE registers (Win64) also has a
-         16-byte aligned default stack, and thus we don't need to be
-	 within the re-aligned local stack frame to save them.  */
-      offset = ROUND_UP (offset, 16);
+	 16-byte aligned default stack, and thus we don't need to be
+	 within the re-aligned local stack frame to save them.  In case
+	 incoming stack boundary is aligned to less than 16 bytes,
+	 unaligned move of SSE register will be emitted, so there is
+	 no point to round up the SSE register save area outside the
+	 re-aligned local stack frame to 16 bytes.  */
+      if (ix86_incoming_stack_boundary >= 128)
+	offset = ROUND_UP (offset, 16);
       offset += frame->nsseregs * 16;
     }
   frame->sse_reg_save_offset = offset;