From fcfce895d320e916fe82ccc0b51701355770ad3b Mon Sep 17 00:00:00 2001
From: Alan Lawrence <alan.lawrence@arm.com>
Date: Tue, 18 Nov 2014 11:06:05 +0000
Subject: [PATCH] [AArch64]Replace temporary assembler for vld1_dup

        * config/aarch64/arm_neon.h (vld1_dup_f32, vld1_dup_f64, vld1_dup_p8,
        vld1_dup_p16, vld1_dup_s8, vld1_dup_s16, vld1_dup_s32, vld1_dup_s64,
        vld1_dup_u8, vld1_dup_u16, vld1_dup_u32, vld1_dup_u64, vld1q_dup_f32,
        vld1q_dup_f64, vld1q_dup_p8, vld1q_dup_p16, vld1q_dup_s8, vld1q_dup_s16,
        vld1q_dup_s32, vld1q_dup_s64, vld1q_dup_u8, vld1q_dup_u16,
        vld1q_dup_u32, vld1q_dup_u64): Replace inline asm with vdup_n_ and
        pointer dereference.

From-SVN: r217705
---
 gcc/ChangeLog                 |  10 +
 gcc/config/aarch64/arm_neon.h | 412 ++++++++++++----------------------
 2 files changed, 158 insertions(+), 264 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 78ed17c69e0..d3205b27515 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,13 @@
+2014-11-18  Alan Lawrence  <alan.lawrence@arm.com>
+
+	* config/aarch64/arm_neon.h (vld1_dup_f32, vld1_dup_f64, vld1_dup_p8,
+	vld1_dup_p16, vld1_dup_s8, vld1_dup_s16, vld1_dup_s32, vld1_dup_s64,
+	vld1_dup_u8, vld1_dup_u16, vld1_dup_u32, vld1_dup_u64, vld1q_dup_f32,
+	vld1q_dup_f64, vld1q_dup_p8, vld1q_dup_p16, vld1q_dup_s8, vld1q_dup_s16,
+	vld1q_dup_s32, vld1q_dup_s64, vld1q_dup_u8, vld1q_dup_u16,
+	vld1q_dup_u32, vld1q_dup_u64): Replace inline asm with vdup_n_ and
+	pointer dereference.
+
 2014-11-18  Marc Glisse  <marc.glisse@inria.fr>
 
 	* tree.c (element_mode, integer_truep): New functions.
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 86d9a8160e4..921a5db1c14 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -6119,270 +6119,6 @@ vhsubq_u32 (uint32x4_t a, uint32x4_t b)
   return result;
 }
 
-__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
-vld1_dup_f32 (const float32_t * a)
-{
-  float32x2_t result;
-  __asm__ ("ld1r {%0.2s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
-vld1_dup_f64 (const float64_t * a)
-{
-  float64x1_t result;
-  __asm__ ("ld1r {%0.1d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
-vld1_dup_p8 (const poly8_t * a)
-{
-  poly8x8_t result;
-  __asm__ ("ld1r {%0.8b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
-vld1_dup_p16 (const poly16_t * a)
-{
-  poly16x4_t result;
-  __asm__ ("ld1r {%0.4h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vld1_dup_s8 (const int8_t * a)
-{
-  int8x8_t result;
-  __asm__ ("ld1r {%0.8b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
-vld1_dup_s16 (const int16_t * a)
-{
-  int16x4_t result;
-  __asm__ ("ld1r {%0.4h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
-vld1_dup_s32 (const int32_t * a)
-{
-  int32x2_t result;
-  __asm__ ("ld1r {%0.2s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
-vld1_dup_s64 (const int64_t * a)
-{
-  int64x1_t result;
-  __asm__ ("ld1r {%0.1d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vld1_dup_u8 (const uint8_t * a)
-{
-  uint8x8_t result;
-  __asm__ ("ld1r {%0.8b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
-vld1_dup_u16 (const uint16_t * a)
-{
-  uint16x4_t result;
-  __asm__ ("ld1r {%0.4h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
-vld1_dup_u32 (const uint32_t * a)
-{
-  uint32x2_t result;
-  __asm__ ("ld1r {%0.2s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
-vld1_dup_u64 (const uint64_t * a)
-{
-  uint64x1_t result;
-  __asm__ ("ld1r {%0.1d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
-vld1q_dup_f32 (const float32_t * a)
-{
-  float32x4_t result;
-  __asm__ ("ld1r {%0.4s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
-vld1q_dup_f64 (const float64_t * a)
-{
-  float64x2_t result;
-  __asm__ ("ld1r {%0.2d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
-vld1q_dup_p8 (const poly8_t * a)
-{
-  poly8x16_t result;
-  __asm__ ("ld1r {%0.16b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
-vld1q_dup_p16 (const poly16_t * a)
-{
-  poly16x8_t result;
-  __asm__ ("ld1r {%0.8h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vld1q_dup_s8 (const int8_t * a)
-{
-  int8x16_t result;
-  __asm__ ("ld1r {%0.16b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
-vld1q_dup_s16 (const int16_t * a)
-{
-  int16x8_t result;
-  __asm__ ("ld1r {%0.8h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
-vld1q_dup_s32 (const int32_t * a)
-{
-  int32x4_t result;
-  __asm__ ("ld1r {%0.4s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
-vld1q_dup_s64 (const int64_t * a)
-{
-  int64x2_t result;
-  __asm__ ("ld1r {%0.2d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vld1q_dup_u8 (const uint8_t * a)
-{
-  uint8x16_t result;
-  __asm__ ("ld1r {%0.16b}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
-vld1q_dup_u16 (const uint16_t * a)
-{
-  uint16x8_t result;
-  __asm__ ("ld1r {%0.8h}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
-vld1q_dup_u32 (const uint32_t * a)
-{
-  uint32x4_t result;
-  __asm__ ("ld1r {%0.4s}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
-vld1q_dup_u64 (const uint64_t * a)
-{
-  uint64x2_t result;
-  __asm__ ("ld1r {%0.2d}, %1"
-	   : "=w"(result)
-	   : "Utv"(*a)
-	   : /* No clobbers */);
-  return result;
-}
-
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vmla_n_f32 (float32x2_t a, float32x2_t b, float32_t c)
 {
@@ -16118,6 +15854,154 @@ vld1q_u64 (const uint64_t *a)
     __builtin_aarch64_ld1v2di ((const __builtin_aarch64_simd_di *) a);
 }
 
+/* vld1_dup  */
+
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vld1_dup_f32 (const float32_t* __a)
+{
+  return vdup_n_f32 (*__a);
+}
+
+__extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
+vld1_dup_f64 (const float64_t* __a)
+{
+  return vdup_n_f64 (*__a);
+}
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vld1_dup_p8 (const poly8_t* __a)
+{
+  return vdup_n_p8 (*__a);
+}
+
+__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
+vld1_dup_p16 (const poly16_t* __a)
+{
+  return vdup_n_p16 (*__a);
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vld1_dup_s8 (const int8_t* __a)
+{
+  return vdup_n_s8 (*__a);
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vld1_dup_s16 (const int16_t* __a)
+{
+  return vdup_n_s16 (*__a);
+}
+
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vld1_dup_s32 (const int32_t* __a)
+{
+  return vdup_n_s32 (*__a);
+}
+
+__extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
+vld1_dup_s64 (const int64_t* __a)
+{
+  return vdup_n_s64 (*__a);
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vld1_dup_u8 (const uint8_t* __a)
+{
+  return vdup_n_u8 (*__a);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vld1_dup_u16 (const uint16_t* __a)
+{
+  return vdup_n_u16 (*__a);
+}
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vld1_dup_u32 (const uint32_t* __a)
+{
+  return vdup_n_u32 (*__a);
+}
+
+__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
+vld1_dup_u64 (const uint64_t* __a)
+{
+  return vdup_n_u64 (*__a);
+}
+
+/* vld1q_dup  */
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vld1q_dup_f32 (const float32_t* __a)
+{
+  return vdupq_n_f32 (*__a);
+}
+
+__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
+vld1q_dup_f64 (const float64_t* __a)
+{
+  return vdupq_n_f64 (*__a);
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vld1q_dup_p8 (const poly8_t* __a)
+{
+  return vdupq_n_p8 (*__a);
+}
+
+__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
+vld1q_dup_p16 (const poly16_t* __a)
+{
+  return vdupq_n_p16 (*__a);
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vld1q_dup_s8 (const int8_t* __a)
+{
+  return vdupq_n_s8 (*__a);
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vld1q_dup_s16 (const int16_t* __a)
+{
+  return vdupq_n_s16 (*__a);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vld1q_dup_s32 (const int32_t* __a)
+{
+  return vdupq_n_s32 (*__a);
+}
+
+__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
+vld1q_dup_s64 (const int64_t* __a)
+{
+  return vdupq_n_s64 (*__a);
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vld1q_dup_u8 (const uint8_t* __a)
+{
+  return vdupq_n_u8 (*__a);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vld1q_dup_u16 (const uint16_t* __a)
+{
+  return vdupq_n_u16 (*__a);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vld1q_dup_u32 (const uint32_t* __a)
+{
+  return vdupq_n_u32 (*__a);
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vld1q_dup_u64 (const uint64_t* __a)
+{
+  return vdupq_n_u64 (*__a);
+}
+
 /* vld1_lane  */
 
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
-- 
2.30.2