[PATCH 3/14][ARM] Add float16x8_t intrinsics

[Alan Lawrence <alan dot lawrence at arm dot com>]

This is a respin of https://gcc.gnu.org/ml/gcc-patches/2015-01/msg01439.html , 
again fixing a wrong 'lane index out of bounds' error for vgetq_lane_f16 and 
vsetq_lane-f16 at -O0, and dropping vdupq_n_f16 and vdupq_lane_f16 as these are 
not in the ACLE spec.

The vld1, vldN, vldN_lane and corresponding intrinsics follow in patch 4/14.

Bootstrapped + check-gcc on arm-none-linux-gnueabihf.

gcc/ChangeLog:

	* config/arm/arm_neon.h (vgetq_lane_f16, vsetq_lane_f16, vld1q_lane_f16,
	vld1q_dup_f16, vreinterpretq_p8_f16, vreinterpretq_p16_f16,
	vreinterpretq_f16_p8, vreinterpretq_f16_p16, vreinterpretq_f16_f32,
	vreinterpretq_f16_p64, vreinterpretq_f16_p128, vreinterpretq_f16_s64,
	vreinterpretq_f16_u64, vreinterpretq_f16_s8, vreinterpretq_f16_s16,
	vreinterpretq_f16_s32, vreinterpretq_f16_u8, vreinterpretq_f16_u16,
	vreinterpretq_f16_u32, vreinterpretq_f32_f16, vreinterpretq_p64_f16,
	vreinterpretq_p128_f16, vreinterpretq_s64_f16, vreinterpretq_u64_f16,
	vreinterpretq_s8_f16, vreinterpretq_s16_f16, vreinterpretq_s32_f16,
	vreinterpretq_u8_f16, vreinterpretq_u16_f16, vreinterpretq_u32_f16):
	New.

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index a958f63ca3084bf7cfaf6420e535d69f50efa6b6..db73c70c6e4ca99db62ff4055a33bfe00db29039 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -5282,6 +5282,15 @@ vgetq_lane_s32 (int32x4_t __a, const int __b)
   return (int32_t)__builtin_neon_vget_lanev4si (__a, __b);
 }
 
+#define vgetq_lane_f16(__v, __idx)		\
+  __extension__					\
+    ({						\
+      float16x8_t __vec = (__v);		\
+      __builtin_arm_lane_check (8, __idx);	\
+      float16_t __res = __vec[__idx];		\
+      __res;					\
+    })
+
 __extension__ static __inline float32_t __attribute__ ((__always_inline__))
 vgetq_lane_f32 (float32x4_t __a, const int __b)
 {
@@ -5424,6 +5433,16 @@ vsetq_lane_s32 (int32_t __a, int32x4_t __b, const int __c)
   return (int32x4_t)__builtin_neon_vset_lanev4si ((__builtin_neon_si) __a, __b, __c);
 }
 
+#define vsetq_lane_f16(__e, __v, __idx)		\
+  __extension__					\
+    ({						\
+      float16_t __elem = (__e);			\
+      float16x8_t __vec = (__v);		\
+      __builtin_arm_lane_check (8, __idx);	\
+      __vec[__idx] = __elem;			\
+      __vec;					\
+    })
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vsetq_lane_f32 (float32_t __a, float32x4_t __b, const int __c)
 {
@@ -8907,6 +8926,12 @@ vld1q_lane_s32 (const int32_t * __a, int32x4_t __b, const int __c)
   return (int32x4_t)__builtin_neon_vld1_lanev4si ((const __builtin_neon_si *) __a, __b, __c);
 }
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vld1q_lane_f16 (const float16_t * __a, float16x8_t __b, const int __c)
+{
+  return vsetq_lane_f16 (*__a, __b, __c);
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vld1q_lane_f32 (const float32_t * __a, float32x4_t __b, const int __c)
 {
@@ -9062,6 +9087,13 @@ vld1q_dup_s32 (const int32_t * __a)
   return (int32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) __a);
 }
 
+__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)
 {
@@ -12856,6 +12888,12 @@ vreinterpretq_p8_p16 (poly16x8_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)__builtin_neon_vreinterpretv16qiv4sf (__a);
@@ -12932,6 +12970,12 @@ vreinterpretq_p16_p8 (poly8x16_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)__builtin_neon_vreinterpretv8hiv4sf (__a);
@@ -13001,6 +13045,88 @@ vreinterpretq_p16_u32 (uint32x4_t __a)
   return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4si ((int32x4_t) __a);
 }
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_p8 (poly8x16_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_p16 (poly16x8_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_f32 (float32x4_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+#ifdef __ARM_FEATURE_CRYPTO
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_p64 (poly64x2_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+#endif
+#ifdef __ARM_FEATURE_CRYPTO
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_p128 (poly128_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+#endif
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_s64 (int64x2_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_u64 (uint64x2_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_s8 (int8x16_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_s16 (int16x8_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_s32 (int32x4_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_u8 (uint8x16_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_u16 (uint16x8_t __a)
+{
+  return (float16x8_t) __a;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vreinterpretq_f16_u32 (uint32x4_t __a)
+{
+  return (float16x8_t) __a;
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_f32_p8 (poly8x16_t __a)
 {
@@ -13013,6 +13139,12 @@ vreinterpretq_f32_p16 (poly16x8_t __a)
   return (float32x4_t)__builtin_neon_vreinterpretv4sfv8hi ((int16x8_t) __a);
 }
 
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vreinterpretq_f32_f16 (float16x8_t __a)
+{
+  return (float32x4_t) __a;
+}
+
 #ifdef __ARM_FEATURE_CRYPTO
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_f32_p64 (poly64x2_t __a)
@@ -13095,6 +13227,14 @@ vreinterpretq_p64_p16 (poly16x8_t __a)
 #endif
 #ifdef __ARM_FEATURE_CRYPTO
 __extension__ static __inline poly64x2_t __attribute__ ((__always_inline__))
+vreinterpretq_p64_f16 (float16x8_t __a)
+{
+  return (poly64x2_t) __a;
+}
+
+#endif
+#ifdef __ARM_FEATURE_CRYPTO
+__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__))
 vreinterpretq_p64_f32 (float32x4_t __a)
 {
   return (poly64x2_t)__builtin_neon_vreinterpretv2div4sf (__a);
@@ -13191,6 +13331,14 @@ vreinterpretq_p128_p16 (poly16x8_t __a)
 #endif
 #ifdef __ARM_FEATURE_CRYPTO
 __extension__ static __inline poly128_t __attribute__ ((__always_inline__))
+vreinterpretq_p128_f16 (float16x8_t __a)
+{
+  return (poly128_t) __a;
+}
+
+#endif
+#ifdef __ARM_FEATURE_CRYPTO
+__extension__ static __inline poly128_t __attribute__ ((__always_inline__))
 vreinterpretq_p128_f32 (float32x4_t __a)
 {
   return (poly128_t)__builtin_neon_vreinterprettiv4sf (__a);
@@ -13282,6 +13430,12 @@ vreinterpretq_s64_p16 (poly16x8_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)__builtin_neon_vreinterpretv2div4sf (__a);
@@ -13358,6 +13512,12 @@ vreinterpretq_u64_p16 (poly16x8_t __a)
 }
 
 __extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vreinterpretq_u64_f16 (float16x8_t __a)
+{
+  return (uint64x2_t) __a;
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
 vreinterpretq_u64_f32 (float32x4_t __a)
 {
   return (uint64x2_t)__builtin_neon_vreinterpretv2div4sf (__a);
@@ -13434,6 +13594,12 @@ vreinterpretq_s8_p16 (poly16x8_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)__builtin_neon_vreinterpretv16qiv4sf (__a);
@@ -13510,6 +13676,12 @@ vreinterpretq_s16_p16 (poly16x8_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)__builtin_neon_vreinterpretv8hiv4sf (__a);
@@ -13586,6 +13758,12 @@ vreinterpretq_s32_p16 (poly16x8_t __a)
 }
 
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vreinterpretq_s32_f16 (float16x8_t __a)
+{
+  return (int32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vreinterpretq_s32_f32 (float32x4_t __a)
 {
   return (int32x4_t)__builtin_neon_vreinterpretv4siv4sf (__a);
@@ -13662,6 +13840,12 @@ vreinterpretq_u8_p16 (poly16x8_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)__builtin_neon_vreinterpretv16qiv4sf (__a);
@@ -13738,6 +13922,12 @@ vreinterpretq_u16_p16 (poly16x8_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)__builtin_neon_vreinterpretv8hiv4sf (__a);
@@ -13814,6 +14004,12 @@ vreinterpretq_u32_p16 (poly16x8_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)__builtin_neon_vreinterpretv4siv4sf (__a);