diff --git a/package/base/gcc/gcc41/gcc-4.1.1-16byte-stack-alignment.patch b/package/base/gcc/gcc41/gcc-4.1.1-16byte-stack-alignment.patch
new file mode 100644
index 000000000..b4a229649
--- /dev/null
+++ b/package/base/gcc/gcc41/gcc-4.1.1-16byte-stack-alignment.patch
@@ -0,0 +1,70 @@
+see 
+http://gcc.gnu.org/bugzilla/show_bug.cgi?id=13685
+http://gcc.gnu.org/bugzilla/show_bug.cgi?id=28621
+http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27537
+
+Index: gcc-4.1.1/gcc/testsuite/gcc.target/i386/pr13685.c
+===================================================================
+--- gcc-4.1.1/gcc/testsuite/gcc.target/i386/pr13685.c	(Revision 0)
++++ gcc-4.1.1/gcc/testsuite/gcc.target/i386/pr13685.c	(Revision 116870)
+@@ -0,0 +1,39 @@
++/* PR target/13685 */
++/* { dg-do run } */
++/* { dg-options "-Os -msse" } */
++#include <stdlib.h>
++#include <stdio.h>
++#include <xmmintrin.h>
++#include "../../gcc.dg/i386-cpuid.h"
++
++void foo (__m128 *, __m64 *, int);
++
++__m128 xmm0 = { 0 };
++__m64 mm0 = { 0 };
++
++int
++main ()
++{
++  unsigned long cpu_facilities = i386_cpuid ();
++  
++  if ((cpu_facilities & (bit_MMX | bit_SSE | bit_CMOV))
++      != (bit_MMX | bit_SSE | bit_CMOV))
++    /* If host has no SSE support, pass.  */
++    return 0;
++
++  foo (&xmm0, &mm0, 4);
++  return 0;
++}
++
++void
++foo (__m128 *dst, __m64 *src, int n)
++{
++  __m128 xmm0 = { 0 };
++  while (n > 64)
++    {
++      puts ("");
++      xmm0 = _mm_cvtpi32_ps (xmm0, *src);
++      *dst = xmm0;
++      n--;
++    }
++}
+Index: gcc-4.1.1/gcc/config/i386/i386.c
+===================================================================
+--- gcc-4.1.1/gcc/config/i386/i386.c	(Revision 116859)
++++ gcc-4.1.1/gcc/config/i386/i386.c	(Revision 116870)
+@@ -1899,12 +1899,10 @@
+     }
+ 
+   /* Validate -mpreferred-stack-boundary= value, or provide default.
+-     The default of 128 bits is for Pentium III's SSE __m128, but we
+-     don't want additional code to keep the stack aligned when
+-     optimizing for code size.  */
+-  ix86_preferred_stack_boundary = (optimize_size
+-				   ? TARGET_64BIT ? 128 : 32
+-				   : 128);
++     The default of 128 bits is for Pentium III's SSE __m128.  We can't
++     change it because of optimize_size.  Otherwise, we can't mix object
++     files compiled with -Os and -On.  */
++  ix86_preferred_stack_boundary = 128;
+   if (ix86_preferred_stack_boundary_string)
+     {
+       i = atoi (ix86_preferred_stack_boundary_string);