[1/2,ARM] PR68532: Fix up vuzp for big endian

diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index d8a2745..e9aa982 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -28208,6 +28208,35 @@  arm_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel)
   arm_expand_vec_perm_1 (target, op0, op1, sel);
 }
 
+/* map lane ordering between architectural lane order, and GCC lane order,
+   taking into account ABI.  See comment above output_move_neon for details.  */
+static int
+neon_endian_lane_map (machine_mode mode, int lane)
+{
+  if (BYTES_BIG_ENDIAN)
+  {
+    int nelems = GET_MODE_NUNITS (mode);
+    /* Reverse lane order.  */
+    lane = (nelems - 1 - lane);
+    /* Reverse D register order, to match ABI.  */
+    if (GET_MODE_SIZE (mode) == 16)
+      lane = lane ^ (nelems / 2);
+  }
+  return lane;
+}
+
+/* some permutations index into pairs of vectors, this is a helper function
+   to map indexes into those pairs of vectors.  */
+static int
+neon_pair_endian_lane_map (machine_mode mode, int lane)
+{
+  int nelem = GET_MODE_NUNITS (mode);
+  if (BYTES_BIG_ENDIAN)
+    lane =
+      neon_endian_lane_map (mode, lane & (nelem - 1)) + (lane & nelem);
+  return lane;
+}
+
 /* Generate or test for an insn that supports a constant permutation.  */
 
 /* Recognize patterns for the VUZP insns.  */
@@ -28218,14 +28247,22 @@  arm_evpc_neon_vuzp (struct expand_vec_perm_d *d)
   unsigned int i, odd, mask, nelt = d->nelt;
   rtx out0, out1, in0, in1;
   rtx (*gen)(rtx, rtx, rtx, rtx);
+  int first_elem;
+  int swap;
 
   if (GET_MODE_UNIT_SIZE (d->vmode) >= 8)
     return false;
 
-  /* Note that these are little-endian tests.  Adjust for big-endian later.  */
-  if (d->perm[0] == 0)
+  /* arm_expand_vec_perm_const_1 () helpfully swaps the operands for the
+     big endian pattern on 64 bit vectors, so we correct for that.  */
+  swap = BYTES_BIG_ENDIAN && !d->one_vector_p
+    && GET_MODE_SIZE (d->vmode) == 8 ? d->nelt : 0;
+
+  first_elem = d->perm[neon_endian_lane_map (d->vmode, 0)] ^ swap;
+
+  if (first_elem == neon_endian_lane_map (d->vmode, 0))
     odd = 0;
-  else if (d->perm[0] == 1)
+  else if (first_elem == neon_endian_lane_map (d->vmode, 1))
     odd = 1;
   else
     return false;
@@ -28233,8 +28270,9 @@  arm_evpc_neon_vuzp (struct expand_vec_perm_d *d)
 
   for (i = 0; i < nelt; i++)
     {
-      unsigned elt = (i * 2 + odd) & mask;
-      if (d->perm[i] != elt)
+      unsigned elt =
+	(neon_pair_endian_lane_map (d->vmode, i) * 2 + odd) & mask;
+      if ((d->perm[i] ^ swap) != neon_pair_endian_lane_map (d->vmode, elt))
 	return false;
     }
 
@@ -28258,10 +28296,9 @@  arm_evpc_neon_vuzp (struct expand_vec_perm_d *d)
 
   in0 = d->op0;
   in1 = d->op1;
-  if (BYTES_BIG_ENDIAN)
+  if (swap)
     {
       std::swap (in0, in1);
-      odd = !odd;
     }
 
   out0 = d->target;
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 47816d5..2e014b6 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -8741,9 +8741,9 @@  vuzpq_s8 (int8x16_t __a, int8x16_t __b)
   int8x16x2_t __rv;
 #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 });
+      { 9, 11, 13, 15, 1, 3, 5, 7, 25, 27, 29, 31, 17, 19, 21, 23 });
   __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 });
+      { 8, 10, 12, 14, 0, 2, 4, 6, 24, 26, 28, 30, 16, 18, 20, 22 });
 #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 });
@@ -8759,9 +8759,9 @@  vuzpq_s16 (int16x8_t __a, int16x8_t __b)
   int16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 9, 11, 13, 15, 1, 3, 5, 7 });
+      { 5, 7, 1, 3, 13, 15, 9, 11 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 10, 12, 14, 0, 2, 4, 6 });
+      { 4, 6, 0, 2, 12, 14, 8, 10 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 2, 4, 6, 8, 10, 12, 14 });
@@ -8776,8 +8776,8 @@  vuzpq_s32 (int32x4_t __a, int32x4_t __b)
 {
   int32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 3, 1, 7, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 0, 6, 4 });
 #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 });
@@ -8790,8 +8790,8 @@  vuzpq_f32 (float32x4_t __a, float32x4_t __b)
 {
   float32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 3, 1, 7, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 0, 6, 4 });
 #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 });
@@ -8805,9 +8805,9 @@  vuzpq_u8 (uint8x16_t __a, uint8x16_t __b)
   uint8x16x2_t __rv;
 #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 });
+      { 9, 11, 13, 15, 1, 3, 5, 7, 25, 27, 29, 31, 17, 19, 21, 23 });
   __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 });
+      { 8, 10, 12, 14, 0, 2, 4, 6, 24, 26, 28, 30, 16, 18, 20, 22 });
 #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 });
@@ -8823,9 +8823,9 @@  vuzpq_u16 (uint16x8_t __a, uint16x8_t __b)
   uint16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 9, 11, 13, 15, 1, 3, 5, 7 });
+      { 5, 7, 1, 3, 13, 15, 9, 11 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 10, 12, 14, 0, 2, 4, 6 });
+      { 4, 6, 0, 2, 12, 14, 8, 10 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 2, 4, 6, 8, 10, 12, 14 });
@@ -8840,8 +8840,8 @@  vuzpq_u32 (uint32x4_t __a, uint32x4_t __b)
 {
   uint32x4x2_t __rv;
 #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 });
+  __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 3, 1, 7, 5 });
+  __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 0, 6, 4 });
 #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 });
@@ -8855,9 +8855,9 @@  vuzpq_p8 (poly8x16_t __a, poly8x16_t __b)
   poly8x16x2_t __rv;
 #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 });
+      { 9, 11, 13, 15, 1, 3, 5, 7, 25, 27, 29, 31, 17, 19, 21, 23 });
   __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 });
+      { 8, 10, 12, 14, 0, 2, 4, 6, 24, 26, 28, 30, 16, 18, 20, 22 });
 #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 });
@@ -8873,9 +8873,9 @@  vuzpq_p16 (poly16x8_t __a, poly16x8_t __b)
   poly16x8x2_t __rv;
 #ifdef __ARM_BIG_ENDIAN
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 9, 11, 13, 15, 1, 3, 5, 7 });
+      { 5, 7, 1, 3, 13, 15, 9, 11 });
   __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t)
-      { 8, 10, 12, 14, 0, 2, 4, 6 });
+      { 4, 6, 0, 2, 12, 14, 8, 10 });
 #else
   __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t)
       { 0, 2, 4, 6, 8, 10, 12, 14 });
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr68532.c b/gcc/testsuite/gcc.c-torture/execute/pr68532.c
new file mode 100644
index 0000000..3c40aa8
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr68532.c
@@ -0,0 +1,24 @@ 
+/* { dg-options "-O2 -ftree-vectorize -fno-vect-cost-model" } */
+
+#define SIZE 128
+unsigned short _Alignas (16) in[SIZE];
+
+extern void abort (void);
+
+__attribute__ ((noinline)) int
+test (unsigned short sum, unsigned short *in, int x)
+{
+  for (int j = 0; j < SIZE; j += 8)
+    sum += in[j] * x;
+  return sum;
+}
+
+int
+main ()
+{
+  for (int i = 0; i < SIZE; i++)
+    in[i] = i;
+  if (test (0, in, 1) != 960)
+    abort ();
+  return 0;
+}