[9/14,AArch64] vld1(q?)_dup, missing vreinterpretq intrinsics

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 88723231e5c32faf3bc68eccdf4e3a2b104b57b9..6d98b2e08221c3e25c4f66e6058b4f228d90a094 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -2993,6 +2993,12 @@  vreinterpretq_p8_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vreinterpretq_p8_f16 (float16x8_t __a)
+{
+  return (poly8x16_t) __a;
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
 vreinterpretq_p8_f32 (float32x4_t __a)
 {
   return (poly8x16_t) __a;
@@ -3131,6 +3137,12 @@  vreinterpretq_p16_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_p16_f16 (float16x8_t __a)
+{
+  return (poly16x8_t) __a;
+}
+
+__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
 vreinterpretq_p16_f32 (float32x4_t __a)
 {
   return (poly16x8_t) __a;
@@ -3383,6 +3395,12 @@  vreinterpret_f32_p16 (poly16x4_t __a)
 }
 
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vreinterpretq_f32_f16 (float16x8_t __a)
+{
+  return (float32x4_t) __a;
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_f32_f64 (float64x2_t __a)
 {
   return (float32x4_t) __a;
@@ -3521,6 +3539,12 @@  vreinterpret_f64_u64 (uint64x1_t __a)
 }
 
 __extension__ static __inline float64x2_t __attribute__((__always_inline__))
+vreinterpretq_f64_f16 (float16x8_t __a)
+{
+  return (float64x2_t) __a;
+}
+
+__extension__ static __inline float64x2_t __attribute__((__always_inline__))
 vreinterpretq_f64_f32 (float32x4_t __a)
 {
   return (float64x2_t) __a;
@@ -3683,6 +3707,12 @@  vreinterpretq_s64_s32 (int32x4_t __a)
 }
 
 __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
+vreinterpretq_s64_f16 (float16x8_t __a)
+{
+  return (int64x2_t) __a;
+}
+
+__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
 vreinterpretq_s64_f32 (float32x4_t __a)
 {
   return (int64x2_t) __a;
@@ -3965,6 +3995,12 @@  vreinterpretq_s8_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vreinterpretq_s8_f16 (float16x8_t __a)
+{
+  return (int8x16_t) __a;
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vreinterpretq_s8_f32 (float32x4_t __a)
 {
   return (int8x16_t) __a;
@@ -4103,6 +4139,12 @@  vreinterpretq_s16_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_s16_f16 (float16x8_t __a)
+{
+  return (int16x8_t) __a;
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vreinterpretq_s16_f32 (float32x4_t __a)
 {
   return (int16x8_t) __a;
@@ -4241,6 +4283,12 @@  vreinterpretq_s32_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vreinterpretq_s32_f16 (float16x8_t __a)
+{
+  return (int32x4_t) __a;
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_s32_f32 (float32x4_t __a)
 {
   return (int32x4_t) __a;
@@ -4385,6 +4433,12 @@  vreinterpretq_u8_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vreinterpretq_u8_f16 (float16x8_t __a)
+{
+  return (uint8x16_t) __a;
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vreinterpretq_u8_f32 (float32x4_t __a)
 {
   return (uint8x16_t) __a;
@@ -4523,6 +4577,12 @@  vreinterpretq_u16_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_u16_f16 (float16x8_t __a)
+{
+  return (uint16x8_t) __a;
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vreinterpretq_u16_f32 (float32x4_t __a)
 {
   return (uint16x8_t) __a;
@@ -4661,6 +4721,12 @@  vreinterpretq_u32_s64 (int64x2_t __a)
 }
 
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vreinterpretq_u32_f16 (float16x8_t __a)
+{
+  return (uint32x4_t) __a;
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_u32_f32 (float32x4_t __a)
 {
   return (uint32x4_t) __a;
@@ -15107,6 +15173,13 @@  vld1q_u64 (const uint64_t *a)
 
 /* vld1_dup  */
 
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vld1_dup_f16 (const float16_t* __a)
+{
+  float16_t __f = *__a;
+  return (float16x4_t) { __f, __f, __f, __f };
+}
+
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vld1_dup_f32 (const float32_t* __a)
 {
@@ -15181,6 +15254,13 @@  vld1_dup_u64 (const uint64_t* __a)
 
 /* vld1q_dup  */
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vld1q_dup_f16 (const float16_t* __a)
+{
+  float16_t __f = *__a;
+  return (float16x8_t) { __f, __f, __f, __f, __f, __f, __f, __f };
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vld1q_dup_f32 (const float32_t* __a)
 {