PR/61062 Fix arm_neon.h ZIP/UZP/TRN for bigendian.

gcc/ChangeLog:

	* config/arm/arm_neon.h (vtrn_s8, vtrn_s16, vtrn_u8, vtrn_u16, vtrn_p8,
	vtrn_p16, vtrn_s32, vtrn_f32, vtrn_u32, vtrnq_s8, vtrnq_s16, vtrnq_s32,
	vtrnq_f32, vtrnq_u8, vtrnq_u16, vtrnq_u32, vtrnq_p8, vtrnq_p16, vzip_s8,
	vzip_s16, vzip_u8, vzip_u16, vzip_p8, vzip_p16, vzip_s32, vzip_f32,
	vzip_u32, vzipq_s8, vzipq_s16, vzipq_s32, vzipq_f32, vzipq_u8,
	vzipq_u16, vzipq_u32, vzipq_p8, vzipq_p16, vuzp_s8, vuzp_s16, vuzp_s32,
	vuzp_f32, vuzp_u8, vuzp_u16, vuzp_u32, vuzp_p8, vuzp_p16, vuzpq_s8,
	vuzpq_s16, vuzpq_s32, vuzpq_f32, vuzpq_u8, vuzpq_u16, vuzpq_u32,
	vuzpq_p8, vuzpq_p16): Correct mask for bigendian.

gcc/testsuite/ChangeLog:

	* gcc.target/arm/pr48252.c (main): Expect same result as endian-neutral.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@211369 138bc75d-0d04-0410-961f-82ee72b054a4

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 567a237..ef49127 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2014-06-09  Alan Lawrence  <alan.lawrence@arm.com>
+
+       PR target/61062
+       * config/arm/arm_neon.h (vtrn_s8, vtrn_s16, vtrn_u8, vtrn_u16, vtrn_p8,
+       vtrn_p16, vtrn_s32, vtrn_f32, vtrn_u32, vtrnq_s8, vtrnq_s16, vtrnq_s32,
+       vtrnq_f32, vtrnq_u8, vtrnq_u16, vtrnq_u32, vtrnq_p8, vtrnq_p16, vzip_s8,
+       vzip_s16, vzip_u8, vzip_u16, vzip_p8, vzip_p16, vzip_s32, vzip_f32,
+       vzip_u32, vzipq_s8, vzipq_s16, vzipq_s32, vzipq_f32, vzipq_u8,
+       vzipq_u16, vzipq_u32, vzipq_p8, vzipq_p16, vuzp_s8, vuzp_s16, vuzp_s32,
+       vuzp_f32, vuzp_u8, vuzp_u16, vuzp_u32, vuzp_p8, vuzp_p16, vuzpq_s8,
+       vuzpq_s16, vuzpq_s32, vuzpq_f32, vuzpq_u8, vuzpq_u16, vuzpq_u32,
+       vuzpq_p8, vuzpq_p16): Correct mask for bigendian.
+
 2014-06-09  Jan Hubicka  <hubicka@ucw.cz>
 
        * tree-core.h (tree_decl_with_vis): Remove section_name.

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index af2d3b3..3e29f44 100644 (file)
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -7731,12 +7731,32 @@ vbslq_p16 (uint16x8_t __a, poly16x8_t __b, poly16x8_t __c)
   return (poly16x8_t)__builtin_neon_vbslv8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c);
 }
 
+/* For big-endian, the shuffle masks for ZIP, UZP and TRN must be changed as
+   follows. (nelt = the number of elements within a vector.)
+
+   Firstly, a value of N within a mask, becomes (N ^ (nelt - 1)), as gcc vector
+   extension's indexing scheme is reversed *within each vector* (relative to the
+   neon intrinsics view), but without changing which of the two vectors.
+
+   Secondly, the elements within each mask are reversed, as the mask is itself a
+   vector, and will itself be loaded in reverse order (again, relative to the
+   neon intrinsics view, i.e. that would result from a "vld1" instruction).  */
+
 __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
 vtrn_s8 (int8x8_t __a, int8x8_t __b)
 {
   int8x8x2_t __rv;
-  __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7744,8 +7764,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
 vtrn_s16 (int16x4_t __a, int16x4_t __b)
 {
   int16x4x2_t __rv;
-  __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7753,8 +7778,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
 vtrn_u8 (uint8x8_t __a, uint8x8_t __b)
 {
   uint8x8x2_t __rv;
-  __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7762,8 +7796,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
 vtrn_u16 (uint16x4_t __a, uint16x4_t __b)
 {
   uint16x4x2_t __rv;
-  __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7771,8 +7810,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
 vtrn_p8 (poly8x8_t __a, poly8x8_t __b)
 {
   poly8x8x2_t __rv;
-  __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7780,8 +7828,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
 vtrn_p16 (poly16x4_t __a, poly16x4_t __b)
 {
   poly16x4x2_t __rv;
-  __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7789,8 +7842,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
 vtrn_s32 (int32x2_t __a, int32x2_t __b)
 {
   int32x2x2_t __rv;
-  __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7798,8 +7856,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
 vtrn_f32 (float32x2_t __a, float32x2_t __b)
 {
   float32x2x2_t __rv;
-  __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7807,8 +7870,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
 vtrn_u32 (uint32x2_t __a, uint32x2_t __b)
 {
   uint32x2x2_t __rv;
-  __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7816,8 +7884,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
 vtrnq_s8 (int8x16_t __a, int8x16_t __b)
 {
   int8x16x2_t __rv;
-  __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
-  __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -7825,8 +7902,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
 vtrnq_s16 (int16x8_t __a, int16x8_t __b)
 {
   int16x8x2_t __rv;
-  __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7834,8 +7920,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
 vtrnq_s32 (int32x4_t __a, int32x4_t __b)
 {
   int32x4x2_t __rv;
-  __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7843,8 +7934,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
 vtrnq_f32 (float32x4_t __a, float32x4_t __b)
 {
   float32x4x2_t __rv;
-  __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7852,8 +7948,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
 vtrnq_u8 (uint8x16_t __a, uint8x16_t __b)
 {
   uint8x16x2_t __rv;
-  __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
-  __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -7861,8 +7966,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
 vtrnq_u16 (uint16x8_t __a, uint16x8_t __b)
 {
   uint16x8x2_t __rv;
-  __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7870,8 +7984,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
 vtrnq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
   uint32x4x2_t __rv;
-  __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
-  __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7879,8 +7998,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
 vtrnq_p8 (poly8x16_t __a, poly8x16_t __b)
 {
   poly8x16x2_t __rv;
-  __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
-  __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -7888,8 +8016,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
 vtrnq_p16 (poly16x8_t __a, poly16x8_t __b)
 {
   poly16x8x2_t __rv;
-  __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 });
-  __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 1, 11, 3, 13, 5, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 10, 2, 12, 4, 14, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 2, 10, 4, 12, 6, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 9, 3, 11, 5, 13, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7897,8 +8034,17 @@ __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
 vzip_s8 (int8x8_t __a, int8x8_t __b)
 {
   int8x8x2_t __rv;
-  __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7906,8 +8052,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
 vzip_s16 (int16x4_t __a, int16x4_t __b)
 {
   int16x4x2_t __rv;
-  __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7915,8 +8066,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
 vzip_u8 (uint8x8_t __a, uint8x8_t __b)
 {
   uint8x8x2_t __rv;
-  __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7924,8 +8084,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
 vzip_u16 (uint16x4_t __a, uint16x4_t __b)
 {
   uint16x4x2_t __rv;
-  __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7933,8 +8098,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
 vzip_p8 (poly8x8_t __a, poly8x8_t __b)
 {
   poly8x8x2_t __rv;
-  __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7942,8 +8116,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
 vzip_p16 (poly16x4_t __a, poly16x4_t __b)
 {
   poly16x4x2_t __rv;
-  __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -7951,8 +8130,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
 vzip_s32 (int32x2_t __a, int32x2_t __b)
 {
   int32x2x2_t __rv;
-  __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7960,8 +8144,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
 vzip_f32 (float32x2_t __a, float32x2_t __b)
 {
   float32x2x2_t __rv;
-  __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7969,8 +8158,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
 vzip_u32 (uint32x2_t __a, uint32x2_t __b)
 {
   uint32x2x2_t __rv;
-  __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -7978,8 +8172,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
 vzipq_s8 (int8x16_t __a, int8x16_t __b)
 {
   int8x16x2_t __rv;
-  __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
-  __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -7987,8 +8190,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
 vzipq_s16 (int16x8_t __a, int16x8_t __b)
 {
   int16x8x2_t __rv;
-  __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -7996,8 +8208,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
 vzipq_s32 (int32x4_t __a, int32x4_t __b)
 {
   int32x4x2_t __rv;
-  __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -8005,8 +8222,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
 vzipq_f32 (float32x4_t __a, float32x4_t __b)
 {
   float32x4x2_t __rv;
-  __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -8014,8 +8236,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
 vzipq_u8 (uint8x16_t __a, uint8x16_t __b)
 {
   uint8x16x2_t __rv;
-  __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
-  __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -8023,8 +8254,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
 vzipq_u16 (uint16x8_t __a, uint16x8_t __b)
 {
   uint16x8x2_t __rv;
-  __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -8032,8 +8272,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
 vzipq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
   uint32x4x2_t __rv;
-  __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
-  __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 });
+#endif
   return __rv;
 }
 
@@ -8041,8 +8286,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
 vzipq_p8 (poly8x16_t __a, poly8x16_t __b)
 {
   poly8x16x2_t __rv;
-  __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
-  __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 });
+#endif
   return __rv;
 }
 
@@ -8050,8 +8304,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
 vzipq_p16 (poly16x8_t __a, poly16x8_t __b)
 {
   poly16x8x2_t __rv;
-  __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 });
-  __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 12, 4, 13, 5, 14, 6, 15, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 0, 9, 1, 10, 2, 11, 3 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 8, 1, 9, 2, 10, 3, 11 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 4, 12, 5, 13, 6, 14, 7, 15 });
+#endif
   return __rv;
 }
 
@@ -8059,8 +8322,17 @@ __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
 vuzp_s8 (int8x8_t __a, int8x8_t __b)
 {
   int8x8x2_t __rv;
-  __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 
@@ -8068,8 +8340,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
 vuzp_s16 (int16x4_t __a, int16x4_t __b)
 {
   int16x4x2_t __rv;
-  __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8077,8 +8354,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
 vuzp_s32 (int32x2_t __a, int32x2_t __b)
 {
   int32x2x2_t __rv;
-  __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -8086,8 +8368,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
 vuzp_f32 (float32x2_t __a, float32x2_t __b)
 {
   float32x2x2_t __rv;
-  __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -8095,8 +8382,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
 vuzp_u8 (uint8x8_t __a, uint8x8_t __b)
 {
   uint8x8x2_t __rv;
-  __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 
@@ -8104,8 +8400,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
 vuzp_u16 (uint16x4_t __a, uint16x4_t __b)
 {
   uint16x4x2_t __rv;
-  __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8113,8 +8414,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
 vuzp_u32 (uint32x2_t __a, uint32x2_t __b)
 {
   uint32x2x2_t __rv;
-  __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
-  __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 });
+#endif
   return __rv;
 }
 
@@ -8122,8 +8428,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
 vuzp_p8 (poly8x8_t __a, poly8x8_t __b)
 {
   poly8x8x2_t __rv;
-  __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 
@@ -8131,8 +8446,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
 vuzp_p16 (poly16x4_t __a, poly16x4_t __b)
 {
   poly16x4x2_t __rv;
-  __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8140,8 +8460,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
 vuzpq_s8 (int8x16_t __a, int8x16_t __b)
 {
   int8x16x2_t __rv;
-  __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
-  __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#endif
   return __rv;
 }
 
@@ -8149,8 +8478,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
 vuzpq_s16 (int16x8_t __a, int16x8_t __b)
 {
   int16x8x2_t __rv;
-  __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 
@@ -8158,8 +8496,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
 vuzpq_s32 (int32x4_t __a, int32x4_t __b)
 {
   int32x4x2_t __rv;
-  __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8167,8 +8510,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
 vuzpq_f32 (float32x4_t __a, float32x4_t __b)
 {
   float32x4x2_t __rv;
-  __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8176,8 +8524,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
 vuzpq_u8 (uint8x16_t __a, uint8x16_t __b)
 {
   uint8x16x2_t __rv;
-  __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
-  __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#endif
   return __rv;
 }
 
@@ -8185,8 +8542,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
 vuzpq_u16 (uint16x8_t __a, uint16x8_t __b)
 {
   uint16x8x2_t __rv;
-  __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 
@@ -8194,8 +8560,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
 vuzpq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
   uint32x4x2_t __rv;
-  __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
-  __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 });
+#endif
   return __rv;
 }
 
@@ -8203,8 +8574,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
 vuzpq_p8 (poly8x16_t __a, poly8x16_t __b)
 {
   poly8x16x2_t __rv;
-  __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
-  __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 });
+#endif
   return __rv;
 }
 
@@ -8212,8 +8592,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
 vuzpq_p16 (poly16x8_t __a, poly16x8_t __b)
 {
   poly16x8x2_t __rv;
-  __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 });
-  __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 });
+#ifdef __ARM_BIG_ENDIAN
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 9, 11, 13, 15, 1, 3, 5, 7 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 8, 10, 12, 14, 0, 2, 4, 6 });
+#else
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 0, 2, 4, 6, 8, 10, 12, 14 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
+      { 1, 3, 5, 7, 9, 11, 13, 15 });
+#endif
   return __rv;
 }
 

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 6932ebe..cbf634b 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2014-06-09  Alan Lawrence  <alan.lawrence@arm.com>
+
+       PR target/61062
+       * gcc.target/arm/pr48252.c (main): Expect same result as endian-neutral.
+
 2014-06-09  Francois-Xavier Coudert  <fxcoudert@gcc.gnu.org>
 
        PR fortran/45187

diff --git a/gcc/testsuite/gcc.target/arm/pr48252.c b/gcc/testsuite/gcc.target/arm/pr48252.c
index 17f729b..250d5e4 100644 (file)
--- a/gcc/testsuite/gcc.target/arm/pr48252.c
+++ b/gcc/testsuite/gcc.target/arm/pr48252.c
@@ -15,7 +15,6 @@ int main(void)
     uint8x8x2_t vd1, vd2;
     union {uint8x8_t v; uint8_t buf[8];} d1, d2, d3, d4;
     int i;
-    uint8_t odd, even;
 
     vd1 = vzip_u8(v1, vdup_n_u8(0));
     vd2 = vzip_u8(v2, vdup_n_u8(0));
@@ -25,17 +24,9 @@ int main(void)
     vst1_u8(d3.buf, vd2.val[0]);
     vst1_u8(d4.buf, vd2.val[1]);
 
-#ifdef __ARMEL__
-    odd = 1;
-    even = 0;
-#else
-    odd = 0;
-    even = 1;
-#endif
-
     for (i = 0; i < 8; i++)
-      if ((i % 2 == even && d4.buf[i] != 2)
-          || (i % 2 == odd && d4.buf[i] != 0))
+      if ((i % 2 == 0 && d4.buf[i] != 2)
+          || (i % 2 == 1 && d4.buf[i] != 0))
          abort ();
 
     return 0;