[AARCH64] implements neon vld1_*_x2 intrinsics

From dfdd8eba9fb49a776cdf8d82c0e34db0fb30d1b5 Mon Sep 17 00:00:00 2001
From: Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
Date: Sat, 30 Sep 2017 04:51:08 +1000
Subject: [PATCH] add missing ld1 x2 builtins

---
 gcc/config/aarch64/aarch64-simd-builtins.def       |   6 +-
 gcc/config/aarch64/aarch64-simd.md                 |  48 +++
 gcc/config/aarch64/arm_neon.h                      | 336 +++++++++++++++++++++
 .../gcc.target/aarch64/advsimd-intrinsics/vld1x2.c |  71 +++++
 4 files changed, 460 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index d713d5d..90736ba 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -86,6 +86,10 @@ 
   VAR1 (SETREGP, set_qregoi, 0, v2di)
   VAR1 (SETREGP, set_qregci, 0, v2di)
   VAR1 (SETREGP, set_qregxi, 0, v2di)
+  /* Implemented by aarch64_ld1x2<VQ:mode>. */
+  BUILTIN_VQ (LOADSTRUCT, ld1x2, 0)
+  /* Implemented by aarch64_ld1x2<VDC:mode>. */
+  BUILTIN_VDC (LOADSTRUCT, ld1x2, 0)
   /* Implemented by aarch64_ld<VSTRUCT:nregs><VDC:mode>.  */
   BUILTIN_VDC (LOADSTRUCT, ld2, 0)
   BUILTIN_VDC (LOADSTRUCT, ld3, 0)
@@ -563,4 +567,4 @@ 
   BUILTIN_GPI (UNOP, fix_truncdf, 2)
   BUILTIN_GPI_I16 (UNOPUS, fixuns_trunchf, 2)
   BUILTIN_GPI (UNOPUS, fixuns_truncsf, 2)
-  BUILTIN_GPI (UNOPUS, fixuns_truncdf, 2)
\ No newline at end of file
+  BUILTIN_GPI (UNOPUS, fixuns_truncdf, 2)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 70e9339..a7ed594 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -5071,6 +5071,33 @@ 
   DONE;
 })
 
+(define_expand "aarch64_ld1x2<VQ:mode>"
+ [(match_operand:OI 0 "register_operand" "=w")
+  (match_operand:DI 1 "register_operand" "r")
+  (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+  "TARGET_SIMD"
+{
+  machine_mode mode = OImode;
+  rtx mem = gen_rtx_MEM (mode, operands[1]);
+
+  emit_insn (gen_aarch64_simd_ld1<VQ:mode>_x2 (operands[0], mem));
+  DONE;
+})
+
+(define_expand "aarch64_ld1x2<VDC:mode>"
+ [(match_operand:OI 0 "register_operand" "=w")
+  (match_operand:DI 1 "register_operand" "r")
+  (unspec:VDC [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+  "TARGET_SIMD"
+{
+  machine_mode mode = OImode;
+  rtx mem = gen_rtx_MEM (mode, operands[1]);
+
+  emit_insn (gen_aarch64_simd_ld1<VDC:mode>_x2 (operands[0], mem));
+  DONE;
+})
+
+
 (define_expand "aarch64_ld<VSTRUCT:nregs>_lane<VALLDIF:mode>"
   [(match_operand:VSTRUCT 0 "register_operand" "=w")
 	(match_operand:DI 1 "register_operand" "w")
@@ -5458,6 +5485,27 @@ 
   [(set_attr "type" "neon_load1_all_lanes")]
 )
 
+(define_insn "aarch64_simd_ld1<mode>_x2"
+  [(set (match_operand:OI 0 "register_operand" "=w")
+	(unspec:OI [(match_operand:OI 1 "aarch64_simd_struct_operand" "Utv")
+		    (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+		   UNSPEC_LD1))]
+  "TARGET_SIMD"
+  "ld1\\t{%S0.<Vtype> - %T0.<Vtype>}, %1"
+  [(set_attr "type" "neon_load1_2reg<q>")]
+)
+
+(define_insn "aarch64_simd_ld1<mode>_x2"
+  [(set (match_operand:OI 0 "register_operand" "=w")
+	(unspec:OI [(match_operand:OI 1 "aarch64_simd_struct_operand" "Utv")
+		    (unspec:VDC [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+		   UNSPEC_LD1))]
+  "TARGET_SIMD"
+  "ld1\\t{%S0.<Vtype> - %T0.<Vtype>}, %1"
+  [(set_attr "type" "neon_load1_2reg<q>")]
+)
+
+
 (define_insn "aarch64_frecpe<mode>"
   [(set (match_operand:VHSDF 0 "register_operand" "=w")
 	(unspec:VHSDF [(match_operand:VHSDF 1 "register_operand" "w")]
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index d7b30b0..0f49cfd 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -17228,6 +17228,342 @@  vld1q_u8 (const uint8_t *a)
     __builtin_aarch64_ld1v16qi ((const __builtin_aarch64_simd_qi *) a);
 }
 
+__extension__ extern __inline uint8x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_u8_x2 (const uint8_t *__a)
+{
+  uint8x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8qi ((const __builtin_aarch64_simd_qi *) __a);
+  ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
+  ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int8x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_s8_x2 (const uint8_t *__a)
+{
+  int8x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8qi ((const __builtin_aarch64_simd_qi *) __a);
+  ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
+  ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_u16_x2 (const uint16_t *__a)
+{
+  uint16x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
+  ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_s16_x2 (const int16_t *__a)
+{
+  int16x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
+  ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint32x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_u32_x2 (const uint32_t *__a)
+{
+  uint32x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2si ((const __builtin_aarch64_simd_si *) __a);
+  ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
+  ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int32x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_s32_x2 (const uint32_t *__a)
+{
+  int32x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2si ((const __builtin_aarch64_simd_si *) __a);
+  ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
+  ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint64x1x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_u64_x2 (const uint64_t *__a)
+{
+  uint64x1x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
+  ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int64x1x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_s64_x2 (const int64_t *__a)
+{
+  int64x1x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
+  ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_f16_x2 (const float16_t *__a)
+{
+  float16x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4hf ((const __builtin_aarch64_simd_hf *) __a);
+  ret.val[0] = (float16x4_t) __builtin_aarch64_get_dregoiv4hf (__o, 0);
+  ret.val[1] = (float16x4_t) __builtin_aarch64_get_dregoiv4hf (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float32x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_f32_x2 (const float32_t *__a)
+{
+  float32x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2sf ((const __builtin_aarch64_simd_sf *) __a);
+  ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 0);
+  ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float64x1x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_f64_x2 (const float64_t *__a)
+{
+  float64x1x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2df ((const __builtin_aarch64_simd_df *) __a);
+  ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 0)};
+  ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 1)};
+  return ret;
+}
+
+__extension__ extern __inline poly8x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_p8_x2 (const poly8_t *__a)
+{
+  poly8x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8qi ((const __builtin_aarch64_simd_qi *) __a);
+  ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
+  ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline poly16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_p16_x2 (const poly16_t *__a)
+{
+  poly16x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
+  ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline poly64x1x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1_p64_x2 (const poly64_t *__a)
+{
+  poly64x1x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (poly64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
+  ret.val[1] = (poly64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint8x16x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_u8_x2 (const uint8_t *__a)
+{
+  uint8x16x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v16qi ((const __builtin_aarch64_simd_qi *) __a);
+  ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
+  ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int8x16x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_s8_x2 (const int8_t *__a)
+{
+  int8x16x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v16qi ((const __builtin_aarch64_simd_qi *) __a);
+  ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
+  ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_u16_x2 (const uint16_t *__a)
+{
+  uint16x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
+  ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_s16_x2 (const int16_t *__a)
+{
+  int16x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
+  ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_u32_x2 (const uint32_t *__a)
+{
+  uint32x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4si ((const __builtin_aarch64_simd_si *) __a);
+  ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
+  ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_s32_x2 (const int32_t *__a)
+{
+  int32x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4si ((const __builtin_aarch64_simd_si *) __a);
+  ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
+  ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline uint64x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_u64_x2 (const uint64_t *__a)
+{
+  uint64x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
+  ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline int64x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_s64_x2 (const int64_t *__a)
+{
+  int64x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
+  ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_f16_x2 (const float16_t *__a)
+{
+  float16x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8hf ((const __builtin_aarch64_simd_hf *) __a);
+  ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregoiv8hf (__o, 0);
+  ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregoiv8hf (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float32x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_f32_x2 (const float32_t *__a)
+{
+  float32x4x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v4sf ((const __builtin_aarch64_simd_sf *) __a);
+  ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 0);
+  ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline float64x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_f64_x2 (const float64_t *__a)
+{
+  float64x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2df ((const __builtin_aarch64_simd_df *) __a);
+  ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 0);
+  ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline poly8x16x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_p8_x2 (const poly8_t *__a)
+{
+  poly8x16x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v16qi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
+  ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline poly16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_p16_x2 (const poly16_t *__a)
+{
+  poly16x8x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v8hi ((const __builtin_aarch64_simd_hi *) __a);
+  ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
+  ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
+  return ret;
+}
+
+__extension__ extern __inline poly64x2x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld1q_p64_x2 (const poly64_t *__a)
+{
+  poly64x2x2_t ret;
+  __builtin_aarch64_simd_oi __o;
+  __o = __builtin_aarch64_ld1x2v2di ((const __builtin_aarch64_simd_di *) __a);
+  ret.val[0] = (poly64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
+  ret.val[1] = (poly64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
+  return ret;
+}
+
 __extension__ extern __inline uint16x8_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_u16 (const uint16_t *a)
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
new file mode 100644
index 0000000..0a43d0d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
@@ -0,0 +1,71 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3" } */
+
+#include <arm_neon.h>
+
+extern void abort (void);
+
+#define TESTMETH(BASE, ELTS, SUFFIX)	\
+int __attribute__ ((noinline))			\
+test_vld##SUFFIX##_x2 ()			\
+{						\
+  BASE##_t data[ELTS * 2];			\
+  BASE##_t temp[ELTS * 2];			\
+  BASE##x##ELTS##x##2##_t vectors;		\
+  int i,j;					\
+  for (i = 0; i < ELTS * 2; i++)		\
+    data [i] = (BASE##_t) 2*i + 1;		\
+  asm volatile ("" : : : "memory");		\
+  vectors = vld1##SUFFIX##_x2 (data);		\
+  vst1##SUFFIX (temp, vectors.val[0]);		\
+  vst1##SUFFIX (&temp[ELTS], vectors.val[1]);	\
+  asm volatile ("" : : : "memory");		\
+  for (j = 0; j < ELTS * 2; j++)		\
+    if (temp[j] != data[j])			\
+      return 1;					\
+  return 0;					\
+}
+
+#define VARIANTS(VARIANT)	\
+VARIANT (uint8, 8, _u8)		\
+VARIANT (uint16, 4, _u16)	\
+VARIANT (uint32, 2, _u32)	\
+VARIANT (uint64, 1, _u64)	\
+VARIANT (int8, 8, _s8)		\
+VARIANT (int16, 4, _s16)	\
+VARIANT (int32, 2, _s32)	\
+VARIANT (int64, 1, _s64)	\
+VARIANT (poly8, 8, _p8)		\
+VARIANT (poly16, 4, _p16)	\
+VARIANT (float16, 4, _f16)	\
+VARIANT (float32, 2, _f32)	\
+VARIANT (float64, 1, _f64)	\
+VARIANT (uint8, 16, q_u8)	\
+VARIANT (uint16, 8, q_u16)	\
+VARIANT (uint32, 4, q_u32)	\
+VARIANT (uint64, 2, q_u64)	\
+VARIANT (int8, 16, q_s8)	\
+VARIANT (int16, 8, q_s16)	\
+VARIANT (int32, 4, q_s32)	\
+VARIANT (int64, 2, q_s64)	\
+VARIANT (poly8, 16, q_p8)	\
+VARIANT (poly16, 8, q_p16)	\
+VARIANT (float16, 8, q_f16)	\
+VARIANT (float32, 4, q_f32)	\
+VARIANT (float64, 2, q_f64)
+
+/* Tests of vld1_x2 and vld1q_x2.  */
+VARIANTS (TESTMETH)
+
+#define CHECK(BASE, ELTS, SUFFIX)	\
+  if (test_vld##SUFFIX##_x2 () != 0)	\
+    abort ();
+
+int
+main (int argc, char **argv)
+{
+  VARIANTS (CHECK)
+
+  return 0;
+}
+
-- 
2.7.4