[ARM] PR68532 Fix up vzip recognition for big endian

gcc/ChangeLog:

2016-02-09  Charles Baylis  <charles.baylis@linaro.org>

        PR target/68532
        * config/arm/arm.c (arm_evpc_neon_vzip): Allow for big endian lane
        order.
        * config/arm/arm_neon.h (vzipq_s8): Adjust shuffle patterns for big
        endian.
        (vzipq_s16): Likewise.
        (vzipq_s32): Likewise.
        (vzipq_f32): Likewise.
        (vzipq_u8): Likewise.
        (vzipq_u16): Likewise.
        (vzipq_u32): Likewise.
        (vzipq_p8): Likewise.
        (vzipq_p16): Likewise.

From-SVN: r233252

3 files changed, 52 insertions, 30 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 28029a8..5bc8a22 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,6 +1,22 @@
 2016-02-09  Charles Baylis  <charles.baylis@linaro.org>
 
 	PR target/68532
+	* config/arm/arm.c (arm_evpc_neon_vzip): Allow for big endian lane
+	order.
+	* config/arm/arm_neon.h (vzipq_s8): Adjust shuffle patterns for big
+	endian.
+	(vzipq_s16): Likewise.
+	(vzipq_s32): Likewise.
+	(vzipq_f32): Likewise.
+	(vzipq_u8): Likewise.
+	(vzipq_u16): Likewise.
+	(vzipq_u32): Likewise.
+	(vzipq_p8): Likewise.
+	(vzipq_p16): Likewise.
+
+2016-02-09  Charles Baylis  <charles.baylis@linaro.org>
+
+	PR target/68532
 	* config/arm/arm.c (neon_endian_lane_map): New function.
 	(neon_vector_pair_endian_lane_map): New function.
 	(arm_evpc_neon_vuzp): Allow for big endian lane order.
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index ab8cfff..27aecf7 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -28313,15 +28313,20 @@ arm_evpc_neon_vzip (struct expand_vec_perm_d *d)
   unsigned int i, high, mask, nelt = d->nelt;
   rtx out0, out1, in0, in1;
   rtx (*gen)(rtx, rtx, rtx, rtx);
+  int first_elem;
+  bool is_swapped;
 
   if (GET_MODE_UNIT_SIZE (d->vmode) >= 8)
     return false;
 
-  /* Note that these are little-endian tests.  Adjust for big-endian later.  */
+  is_swapped = BYTES_BIG_ENDIAN;
+
+  first_elem = d->perm[neon_endian_lane_map (d->vmode, 0) ^ is_swapped];
+
   high = nelt / 2;
-  if (d->perm[0] == high)
+  if (first_elem == neon_endian_lane_map (d->vmode, high))
     ;
-  else if (d->perm[0] == 0)
+  else if (first_elem == neon_endian_lane_map (d->vmode, 0))
     high = 0;
   else
     return false;
@@ -28329,11 +28334,15 @@ arm_evpc_neon_vzip (struct expand_vec_perm_d *d)
 
   for (i = 0; i < nelt / 2; i++)
     {
-      unsigned elt = (i + high) & mask;
-      if (d->perm[i * 2] != elt)
+      unsigned elt =
+	neon_pair_endian_lane_map (d->vmode, i + high) & mask;
+      if (d->perm[neon_pair_endian_lane_map (d->vmode, 2 * i + is_swapped)]
+	  != elt)
 	return false;
-      elt = (elt + nelt) & mask;
-      if (d->perm[i * 2 + 1] != elt)
+      elt =
+	neon_pair_endian_lane_map (d->vmode, i + nelt + high) & mask;
+      if (d->perm[neon_pair_endian_lane_map (d->vmode, 2 * i + !is_swapped)]
+	  != elt)
 	return false;
     }
 
@@ -28357,11 +28366,8 @@ arm_evpc_neon_vzip (struct expand_vec_perm_d *d)
 
   in0 = d->op0;
   in1 = d->op1;
-  if (BYTES_BIG_ENDIAN)
-    {
-      std::swap (in0, in1);
-      high = !high;
-    }
+  if (is_swapped)
+    std::swap (in0, in1);
 
   out0 = d->target;
   out1 = gen_reg_rtx (d->vmode);
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index e807ad1..94bbef5 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -8453,9 +8453,9 @@ vzipq_s8 (int8x16_t __a, int8x16_t __b)
   int8x16x2_t __rv;
 #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 });
+      { 20, 4, 21, 5, 22, 6, 23, 7, 16, 0, 17, 1, 18, 2, 19, 3 });
   __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 });
+      { 28, 12, 29, 13, 30, 14, 31, 15, 24, 8, 25, 9, 26, 10, 27, 11 });
 #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 });
@@ -8471,9 +8471,9 @@ vzipq_s16 (int16x8_t __a, int16x8_t __b)
   int16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 12, 4, 13, 5, 14, 6, 15, 7 });
+      { 10, 2, 11, 3, 8, 0, 9, 1 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 0, 9, 1, 10, 2, 11, 3 });
+      { 14, 6, 15, 7, 12, 4, 13, 5 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 8, 1, 9, 2, 10, 3, 11 });
@@ -8488,8 +8488,8 @@ vzipq_s32 (int32x4_t __a, int32x4_t __b)
 {
   int32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 4, 0 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 7, 3, 6, 2 });
 #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 });
@@ -8502,8 +8502,8 @@ vzipq_f32 (float32x4_t __a, float32x4_t __b)
 {
   float32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 4, 0 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 7, 3, 6, 2 });
 #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 });
@@ -8517,9 +8517,9 @@ vzipq_u8 (uint8x16_t __a, uint8x16_t __b)
   uint8x16x2_t __rv;
 #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 });
+      { 20, 4, 21, 5, 22, 6, 23, 7, 16, 0, 17, 1, 18, 2, 19, 3 });
   __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 });
+      { 28, 12, 29, 13, 30, 14, 31, 15, 24, 8, 25, 9, 26, 10, 27, 11 });
 #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 });
@@ -8535,9 +8535,9 @@ vzipq_u16 (uint16x8_t __a, uint16x8_t __b)
   uint16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 12, 4, 13, 5, 14, 6, 15, 7 });
+      { 10, 2, 11, 3, 8, 0, 9, 1 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 0, 9, 1, 10, 2, 11, 3 });
+      { 14, 6, 15, 7, 12, 4, 13, 5 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 8, 1, 9, 2, 10, 3, 11 });
@@ -8552,8 +8552,8 @@ vzipq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
   uint32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 4, 0 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 7, 3, 6, 2 });
 #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 });
@@ -8567,9 +8567,9 @@ vzipq_p8 (poly8x16_t __a, poly8x16_t __b)
   poly8x16x2_t __rv;
 #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 });
+      { 20, 4, 21, 5, 22, 6, 23, 7, 16, 0, 17, 1, 18, 2, 19, 3 });
   __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 });
+      { 28, 12, 29, 13, 30, 14, 31, 15, 24, 8, 25, 9, 26, 10, 27, 11 });
 #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 });
@@ -8585,9 +8585,9 @@ vzipq_p16 (poly16x8_t __a, poly16x8_t __b)
   poly16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 12, 4, 13, 5, 14, 6, 15, 7 });
+      { 10, 2, 11, 3, 8, 0, 9, 1 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 0, 9, 1, 10, 2, 11, 3 });
+      { 14, 6, 15, 7, 12, 4, 13, 5 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 8, 1, 9, 2, 10, 3, 11 });