From 3c45591b76e95fcf783cef17ad01923a55da885c Mon Sep 17 00:00:00 2001 From: Charles Baylis Date: Fri, 11 Dec 2015 18:51:48 +0000 Subject: [PATCH 2/2] [ARM] Fix up vzip recognition for big endian gcc/ChangeLog: 2015-12-15 Charles Baylis * 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. Change-Id: I327678f5e73c1de2f413c1d22769ab42ce1d6c16 --- gcc/config/arm/arm.c | 23 +++++++++++++++-------- gcc/config/arm/arm_neon.h | 36 ++++++++++++++++++------------------ 2 files changed, 33 insertions(+), 26 deletions(-) diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c index f921186..a73bccf 100644 --- a/gcc/config/arm/arm.c +++ b/gcc/config/arm/arm.c @@ -28300,15 +28300,21 @@ 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; + is_swapped = BYTES_BIG_ENDIAN ? true : false; + /* Note that these are little-endian tests. Adjust for big-endian later. */ + first_elem = d->perm[arm_neon_endian_lane_map (d->vmode, 0) ^ is_swapped]; + high = nelt / 2; - if (d->perm[0] == high) + if (first_elem == arm_neon_endian_lane_map (d->vmode, high)) ; - else if (d->perm[0] == 0) + else if (first_elem == arm_neon_endian_lane_map (d->vmode, 0)) high = 0; else return false; @@ -28316,11 +28322,13 @@ 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 = arm_neon_vector_pair_endian_lane_map(d->vmode, i + high) & mask; + if (d->perm[arm_neon_vector_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 = + arm_neon_vector_pair_endian_lane_map (d->vmode, i + nelt + high) + & mask; + if (d->perm[arm_neon_vector_pair_endian_lane_map (d->vmode, 2 * i + !is_swapped)] != elt) return false; } @@ -28344,10 +28352,9 @@ arm_evpc_neon_vzip (struct expand_vec_perm_d *d) in0 = d->op0; in1 = d->op1; - if (BYTES_BIG_ENDIAN) + if (is_swapped) { std::swap (in0, in1); - high = !high; } out0 = d->target; diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h index 2c5d9e9..d56788a 100644 --- a/gcc/config/arm/arm_neon.h +++ b/gcc/config/arm/arm_neon.h @@ -8341,9 +8341,9 @@ 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 }); @@ -8359,9 +8359,9 @@ 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 }); @@ -8376,8 +8376,8 @@ 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 }); @@ -8390,8 +8390,8 @@ 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 }); @@ -8405,9 +8405,9 @@ 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 }); @@ -8423,9 +8423,9 @@ 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 }); @@ -8440,8 +8440,8 @@ 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 }); @@ -8455,9 +8455,9 @@ 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 }); @@ -8473,9 +8473,9 @@ 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 }); -- 1.9.1