[AArch64] Add support for float16x{4,8}_t vectors/builtins

gcc/:

	* config/aarch64/aarch64.c (aarch64_vector_mode_supported_p): Support
	V4HFmode and V8HFmode.
	(aarch64_split_simd_move): Add case for V8HFmode.
	* config/aarch64/aarch64-builtins.c (v4hf_UP, v8hf_UP): Define.
	(aarch64_simd_builtin_std_type): Handle HFmode.
	(aarch64_init_simd_builtin_types): Include Float16x4_t and Float16x8_t.

	* config/aarch64/aarch64-simd.md (mov<mode>, aarch64_get_lane<mode>,
	aarch64_ld1<VALL:mode>, aarch64_st1<VALL:mode): Use VALL_F16 iterator.
	(aarch64_be_ld1<mode>, aarch64_be_st1<mode>): Use VALLDI_F16 iterator.

	* config/aarch64/aarch64-simd-builtin-types.def: Add Float16x4_t,
	Float16x8_t.

	* config/aarch64/aarch64-simd-builtins.def (ld1, st1): Use VALL_F16.
	* config/aarch64/arm_neon.h (float16x4_t, float16x8_t, float16_t):
	New typedefs.
	(vget_lane_f16, vgetq_lane_f16, vset_lane_f16, vsetq_lane_f16,
	vld1_f16, vld1q_f16, vst1_f16, vst1q_f16, vst1_lane_f16,
	vst1q_lane_f16): New.
	* config/aarch64/iterators.md (VD, VQ, VQ_NO2E): Add vectors of HFmode.
	(VALLDI_F16, VALL_F16): New.
	(Vmtype, VEL, VCONQ, VHALF, V_TWO_ELEM, V_THREE_ELEM, V_FOUR_ELEM, q):
	Add cases for V4HF and V8HF.
	(VDBL, VRL2, VRL3, VRL4): Add V4HF case.

gcc/testsuite/:

	* g++.dg/abi/mangle-neon-aarch64.C: Add cases for float16x4_t and
	float16x8_t.
	* gcc.target/aarch64/vset_lane_1.c: Likewise.
	* gcc.target/aarch64/vld1-vst1_1.c: Likewise.
	* gcc.target/aarch64/vld1_lane.c: Likewise.

From-SVN: r227542

14 files changed, 187 insertions, 28 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index ddeb0a1..2f3254a 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,33 @@
 2015-09-08  Alan Lawrence  <alan.lawrence@arm.com>
 
+	* config/aarch64/aarch64.c (aarch64_vector_mode_supported_p): Support
+	V4HFmode and V8HFmode.
+	(aarch64_split_simd_move): Add case for V8HFmode.
+	* config/aarch64/aarch64-builtins.c (v4hf_UP, v8hf_UP): Define.
+	(aarch64_simd_builtin_std_type): Handle HFmode.
+	(aarch64_init_simd_builtin_types): Include Float16x4_t and Float16x8_t.
+
+	* config/aarch64/aarch64-simd.md (mov<mode>, aarch64_get_lane<mode>,
+	aarch64_ld1<VALL:mode>, aarch64_st1<VALL:mode): Use VALL_F16 iterator.
+	(aarch64_be_ld1<mode>, aarch64_be_st1<mode>): Use VALLDI_F16 iterator.
+
+	* config/aarch64/aarch64-simd-builtin-types.def: Add Float16x4_t,
+	Float16x8_t.
+
+	* config/aarch64/aarch64-simd-builtins.def (ld1, st1): Use VALL_F16.
+	* config/aarch64/arm_neon.h (float16x4_t, float16x8_t, float16_t):
+	New typedefs.
+	(vget_lane_f16, vgetq_lane_f16, vset_lane_f16, vsetq_lane_f16,
+	vld1_f16, vld1q_f16, vst1_f16, vst1q_f16, vst1_lane_f16,
+	vst1q_lane_f16): New.
+	* config/aarch64/iterators.md (VD, VQ, VQ_NO2E): Add vectors of HFmode.
+	(VALLDI_F16, VALL_F16): New.
+	(Vmtype, VEL, VCONQ, VHALF, V_TWO_ELEM, V_THREE_ELEM, V_FOUR_ELEM, q):
+	Add cases for V4HF and V8HF.
+	(VDBL, VRL2, VRL3, VRL4): Add V4HF case.
+
+2015-09-08  Alan Lawrence  <alan.lawrence@arm.com>
+
 	* config/arm/arm-builtins.c (VAR11, VAR12): New.
 	* config/arm/arm_neon_builtins.def (vcombine, vld2_dup, vld3_dup,
 	vld4_dup): Add v4hf variant.
diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
index e3a90b5..243fa9f 100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -61,6 +61,7 @@
 
 #define v8qi_UP  V8QImode
 #define v4hi_UP  V4HImode
+#define v4hf_UP  V4HFmode
 #define v2si_UP  V2SImode
 #define v2sf_UP  V2SFmode
 #define v1df_UP  V1DFmode
@@ -68,6 +69,7 @@
 #define df_UP    DFmode
 #define v16qi_UP V16QImode
 #define v8hi_UP  V8HImode
+#define v8hf_UP  V8HFmode
 #define v4si_UP  V4SImode
 #define v4sf_UP  V4SFmode
 #define v2di_UP  V2DImode
@@ -520,6 +522,8 @@ aarch64_simd_builtin_std_type (enum machine_mode mode,
       return aarch64_simd_intCI_type_node;
     case XImode:
       return aarch64_simd_intXI_type_node;
+    case HFmode:
+      return aarch64_fp16_type_node;
     case SFmode:
       return float_type_node;
     case DFmode:
@@ -604,6 +608,8 @@ aarch64_init_simd_builtin_types (void)
   aarch64_simd_types[Poly64x2_t].eltype = aarch64_simd_types[Poly64_t].itype;
 
   /* Continue with standard types.  */
+  aarch64_simd_types[Float16x4_t].eltype = aarch64_fp16_type_node;
+  aarch64_simd_types[Float16x8_t].eltype = aarch64_fp16_type_node;
   aarch64_simd_types[Float32x2_t].eltype = float_type_node;
   aarch64_simd_types[Float32x4_t].eltype = float_type_node;
   aarch64_simd_types[Float64x1_t].eltype = double_type_node;
diff --git a/gcc/config/aarch64/aarch64-simd-builtin-types.def b/gcc/config/aarch64/aarch64-simd-builtin-types.def
index bb54e56..ea219b7 100644
--- a/gcc/config/aarch64/aarch64-simd-builtin-types.def
+++ b/gcc/config/aarch64/aarch64-simd-builtin-types.def
@@ -44,6 +44,8 @@
   ENTRY (Poly16x8_t, V8HI, poly, 12)
   ENTRY (Poly64x1_t, DI, poly, 12)
   ENTRY (Poly64x2_t, V2DI, poly, 12)
+  ENTRY (Float16x4_t, V4HF, none, 13)
+  ENTRY (Float16x8_t, V8HF, none, 13)
   ENTRY (Float32x2_t, V2SF, none, 13)
   ENTRY (Float32x4_t, V4SF, none, 13)
   ENTRY (Float64x1_t, V1DF, none, 13)
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index d0f298a..39ff34e 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -367,11 +367,11 @@
   VAR1 (UNOP, float_extend_lo_, 0, v2df)
   VAR1 (UNOP, float_truncate_lo_, 0, v2sf)
 
-  /* Implemented by aarch64_ld1<VALL:mode>.  */
-  BUILTIN_VALL (LOAD1, ld1, 0)
+  /* Implemented by aarch64_ld1<VALL_F16:mode>.  */
+  BUILTIN_VALL_F16 (LOAD1, ld1, 0)
 
-  /* Implemented by aarch64_st1<VALL:mode>.  */
-  BUILTIN_VALL (STORE1, st1, 0)
+  /* Implemented by aarch64_st1<VALL_F16:mode>.  */
+  BUILTIN_VALL_F16 (STORE1, st1, 0)
 
   /* Implemented by fma<mode>4.  */
   BUILTIN_VDQF (TERNOP, fma, 4)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 75fa0ab..1bd6a19a 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -19,8 +19,8 @@
 ;; <http://www.gnu.org/licenses/>.
 
 (define_expand "mov<mode>"
-  [(set (match_operand:VALL 0 "nonimmediate_operand" "")
-	(match_operand:VALL 1 "general_operand" ""))]
+  [(set (match_operand:VALL_F16 0 "nonimmediate_operand" "")
+	(match_operand:VALL_F16 1 "general_operand" ""))]
   "TARGET_SIMD"
   "
     if (GET_CODE (operands[0]) == MEM)
@@ -2450,7 +2450,7 @@
 (define_insn "aarch64_get_lane<mode>"
   [(set (match_operand:<VEL> 0 "aarch64_simd_nonimmediate_operand" "=r, w, Utv")
 	(vec_select:<VEL>
-	  (match_operand:VALL 1 "register_operand" "w, w, w")
+	  (match_operand:VALL_F16 1 "register_operand" "w, w, w")
 	  (parallel [(match_operand:SI 2 "immediate_operand" "i, i, i")])))]
   "TARGET_SIMD"
   {
@@ -4243,8 +4243,9 @@
 )
 
 (define_insn "aarch64_be_ld1<mode>"
-  [(set (match_operand:VALLDI 0	"register_operand" "=w")
-	(unspec:VALLDI [(match_operand:VALLDI 1 "aarch64_simd_struct_operand" "Utv")]
+  [(set (match_operand:VALLDI_F16 0	"register_operand" "=w")
+	(unspec:VALLDI_F16 [(match_operand:VALLDI_F16 1
+			     "aarch64_simd_struct_operand" "Utv")]
 	UNSPEC_LD1))]
   "TARGET_SIMD"
   "ld1\\t{%0<Vmtype>}, %1"
@@ -4252,8 +4253,8 @@
 )
 
 (define_insn "aarch64_be_st1<mode>"
-  [(set (match_operand:VALLDI 0 "aarch64_simd_struct_operand" "=Utv")
-	(unspec:VALLDI [(match_operand:VALLDI 1 "register_operand" "w")]
+  [(set (match_operand:VALLDI_F16 0 "aarch64_simd_struct_operand" "=Utv")
+	(unspec:VALLDI_F16 [(match_operand:VALLDI_F16 1 "register_operand" "w")]
 	UNSPEC_ST1))]
   "TARGET_SIMD"
   "st1\\t{%1<Vmtype>}, %0"
@@ -4542,16 +4543,16 @@
   DONE;
 })
 
-(define_expand "aarch64_ld1<VALL:mode>"
- [(match_operand:VALL 0 "register_operand")
+(define_expand "aarch64_ld1<VALL_F16:mode>"
+ [(match_operand:VALL_F16 0 "register_operand")
   (match_operand:DI 1 "register_operand")]
   "TARGET_SIMD"
 {
-  machine_mode mode = <VALL:MODE>mode;
+  machine_mode mode = <VALL_F16:MODE>mode;
   rtx mem = gen_rtx_MEM (mode, operands[1]);
 
   if (BYTES_BIG_ENDIAN)
-    emit_insn (gen_aarch64_be_ld1<VALL:mode> (operands[0], mem));
+    emit_insn (gen_aarch64_be_ld1<VALL_F16:mode> (operands[0], mem));
   else
     emit_move_insn (operands[0], mem);
   DONE;
@@ -4895,16 +4896,16 @@
   DONE;
 })
 
-(define_expand "aarch64_st1<VALL:mode>"
+(define_expand "aarch64_st1<VALL_F16:mode>"
  [(match_operand:DI 0 "register_operand")
-  (match_operand:VALL 1 "register_operand")]
+  (match_operand:VALL_F16 1 "register_operand")]
   "TARGET_SIMD"
 {
-  machine_mode mode = <VALL:MODE>mode;
+  machine_mode mode = <VALL_F16:MODE>mode;
   rtx mem = gen_rtx_MEM (mode, operands[0]);
 
   if (BYTES_BIG_ENDIAN)
-    emit_insn (gen_aarch64_be_st1<VALL:mode> (mem, operands[1]));
+    emit_insn (gen_aarch64_be_st1<VALL_F16:mode> (mem, operands[1]));
   else
     emit_move_insn (mem, operands[1]);
   DONE;
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index bc612e4..5951045 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -1383,6 +1383,9 @@ aarch64_split_simd_move (rtx dst, rtx src)
 	case V2DImode:
 	  gen = gen_aarch64_split_simd_movv2di;
 	  break;
+	case V8HFmode:
+	  gen = gen_aarch64_split_simd_movv8hf;
+	  break;
 	case V4SFmode:
 	  gen = gen_aarch64_split_simd_movv4sf;
 	  break;
@@ -9780,6 +9783,7 @@ aarch64_vector_mode_supported_p (machine_mode mode)
 	  || mode == V2SImode  || mode == V4HImode
 	  || mode == V8QImode || mode == V2SFmode
 	  || mode == V4SFmode || mode == V2DFmode
+	  || mode == V4HFmode || mode == V8HFmode
 	  || mode == V1DFmode))
     return true;
 
diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index 1e5f5db..9669e01 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -875,7 +875,8 @@ extern enum aarch64_code_model aarch64_cmodel;
 /* Modes valid for AdvSIMD Q registers.  */
 #define AARCH64_VALID_SIMD_QREG_MODE(MODE) \
   ((MODE) == V4SImode || (MODE) == V8HImode || (MODE) == V16QImode \
-   || (MODE) == V4SFmode || (MODE) == V2DImode || mode == V2DFmode)
+   || (MODE) == V4SFmode || (MODE) == V8HFmode || (MODE) == V2DImode \
+   || (MODE) == V2DFmode)
 
 #define ENDIAN_LANE_N(mode, n)  \
   (BYTES_BIG_ENDIAN ? GET_MODE_NUNITS (mode) - 1 - n : n)
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 6dfebe7..5f61b5b 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -39,6 +39,7 @@ typedef __Int8x8_t int8x8_t;
 typedef __Int16x4_t int16x4_t;
 typedef __Int32x2_t int32x2_t;
 typedef __Int64x1_t int64x1_t;
+typedef __Float16x4_t float16x4_t;
 typedef __Float32x2_t float32x2_t;
 typedef __Poly8x8_t poly8x8_t;
 typedef __Poly16x4_t poly16x4_t;
@@ -51,6 +52,7 @@ typedef __Int8x16_t int8x16_t;
 typedef __Int16x8_t int16x8_t;
 typedef __Int32x4_t int32x4_t;
 typedef __Int64x2_t int64x2_t;
+typedef __Float16x8_t float16x8_t;
 typedef __Float32x4_t float32x4_t;
 typedef __Float64x2_t float64x2_t;
 typedef __Poly8x16_t poly8x16_t;
@@ -66,6 +68,7 @@ typedef __Poly16_t poly16_t;
 typedef __Poly64_t poly64_t;
 typedef __Poly128_t poly128_t;
 
+typedef __fp16 float16_t;
 typedef float float32_t;
 typedef double float64_t;
 
@@ -2690,6 +2693,12 @@ vcreate_p16 (uint64_t __a)
 
 /* vget_lane  */
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vget_lane_f16 (float16x4_t __a, const int __b)
+{
+  return __aarch64_vget_lane_any (__a, __b);
+}
+
 __extension__ static __inline float32_t __attribute__ ((__always_inline__))
 vget_lane_f32 (float32x2_t __a, const int __b)
 {
@@ -2764,6 +2773,12 @@ vget_lane_u64 (uint64x1_t __a, const int __b)
 
 /* vgetq_lane  */
 
+__extension__ static __inline float16_t __attribute__ ((__always_inline__))
+vgetq_lane_f16 (float16x8_t __a, const int __b)
+{
+  return __aarch64_vget_lane_any (__a, __b);
+}
+
 __extension__ static __inline float32_t __attribute__ ((__always_inline__))
 vgetq_lane_f32 (float32x4_t __a, const int __b)
 {
@@ -4424,6 +4439,12 @@ vreinterpretq_u32_p16 (poly16x8_t __a)
 
 /* vset_lane  */
 
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vset_lane_f16 (float16_t __elem, float16x4_t __vec, const int __index)
+{
+  return __aarch64_vset_lane_any (__elem, __vec, __index);
+}
+
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vset_lane_f32 (float32_t __elem, float32x2_t __vec, const int __index)
 {
@@ -4498,6 +4519,12 @@ vset_lane_u64 (uint64_t __elem, uint64x1_t __vec, const int __index)
 
 /* vsetq_lane  */
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vsetq_lane_f16 (float16_t __elem, float16x8_t __vec, const int __index)
+{
+  return __aarch64_vset_lane_any (__elem, __vec, __index);
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vsetq_lane_f32 (float32_t __elem, float32x4_t __vec, const int __index)
 {
@@ -14628,6 +14655,12 @@ vfmsq_laneq_f64 (float64x2_t __a, float64x2_t __b,
 
 /* vld1 */
 
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vld1_f16 (const float16_t *__a)
+{
+  return __builtin_aarch64_ld1v4hf (__a);
+}
+
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vld1_f32 (const float32_t *a)
 {
@@ -14707,6 +14740,12 @@ vld1_u64 (const uint64_t *a)
 
 /* vld1q */
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vld1q_f16 (const float16_t *__a)
+{
+  return __builtin_aarch64_ld1v8hf (__a);
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vld1q_f32 (const float32_t *a)
 {
@@ -14935,6 +14974,12 @@ vld1q_dup_u64 (const uint64_t* __a)
 
 /* vld1_lane  */
 
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vld1_lane_f16 (const float16_t *__src, float16x4_t __vec, const int __lane)
+{
+  return __aarch64_vset_lane_any (*__src, __vec, __lane);
+}
+
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
 vld1_lane_f32 (const float32_t *__src, float32x2_t __vec, const int __lane)
 {
@@ -15009,6 +15054,12 @@ vld1_lane_u64 (const uint64_t *__src, uint64x1_t __vec, const int __lane)
 
 /* vld1q_lane  */
 
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vld1q_lane_f16 (const float16_t *__src, float16x8_t __vec, const int __lane)
+{
+  return __aarch64_vset_lane_any (*__src, __vec, __lane);
+}
+
 __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
 vld1q_lane_f32 (const float32_t *__src, float32x4_t __vec, const int __lane)
 {
@@ -21977,6 +22028,12 @@ vsrid_n_u64 (uint64_t __a, uint64_t __b, const int __c)
 /* vst1 */
 
 __extension__ static __inline void __attribute__ ((__always_inline__))
+vst1_f16 (float16_t *__a, float16x4_t __b)
+{
+  __builtin_aarch64_st1v4hf (__a, __b);
+}
+
+__extension__ static __inline void __attribute__ ((__always_inline__))
 vst1_f32 (float32_t *a, float32x2_t b)
 {
   __builtin_aarch64_st1v2sf ((__builtin_aarch64_simd_sf *) a, b);
@@ -22056,6 +22113,12 @@ vst1_u64 (uint64_t *a, uint64x1_t b)
 /* vst1q */
 
 __extension__ static __inline void __attribute__ ((__always_inline__))
+vst1q_f16 (float16_t *__a, float16x8_t __b)
+{
+  __builtin_aarch64_st1v8hf (__a, __b);
+}
+
+__extension__ static __inline void __attribute__ ((__always_inline__))
 vst1q_f32 (float32_t *a, float32x4_t b)
 {
   __builtin_aarch64_st1v4sf ((__builtin_aarch64_simd_sf *) a, b);
@@ -22136,6 +22199,12 @@ vst1q_u64 (uint64_t *a, uint64x2_t b)
 /* vst1_lane */
 
 __extension__ static __inline void __attribute__ ((__always_inline__))
+vst1_lane_f16 (float16_t *__a, float16x4_t __b, const int __lane)
+{
+  *__a = __aarch64_vget_lane_any (__b, __lane);
+}
+
+__extension__ static __inline void __attribute__ ((__always_inline__))
 vst1_lane_f32 (float32_t *__a, float32x2_t __b, const int __lane)
 {
   *__a = __aarch64_vget_lane_any (__b, __lane);
@@ -22210,6 +22279,12 @@ vst1_lane_u64 (uint64_t *__a, uint64x1_t __b, const int __lane)
 /* vst1q_lane */
 
 __extension__ static __inline void __attribute__ ((__always_inline__))
+vst1q_lane_f16 (float16_t *__a, float16x8_t __b, const int __lane)
+{
+  *__a = __aarch64_vget_lane_any (__b, __lane);
+}
+
+__extension__ static __inline void __attribute__ ((__always_inline__))
 vst1q_lane_f32 (float32_t *__a, float32x4_t __b, const int __lane)
 {
   *__a = __aarch64_vget_lane_any (__b, __lane);
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 475aa6e..3e4f07d 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -52,7 +52,7 @@
 (define_mode_iterator VSDQ_I_DI [V8QI V16QI V4HI V8HI V2SI V4SI V2DI DI])
 
 ;; Double vector modes.
-(define_mode_iterator VD [V8QI V4HI V2SI V2SF])
+(define_mode_iterator VD [V8QI V4HI V4HF V2SI V2SF])
 
 ;; vector, 64-bit container, all integer modes
 (define_mode_iterator VD_BHSI [V8QI V4HI V2SI])
@@ -61,10 +61,10 @@
 (define_mode_iterator VDQ_BHSI [V8QI V16QI V4HI V8HI V2SI V4SI])
 
 ;; Quad vector modes.
-(define_mode_iterator VQ [V16QI V8HI V4SI V2DI V4SF V2DF])
+(define_mode_iterator VQ [V16QI V8HI V4SI V2DI V8HF V4SF V2DF])
 
 ;; VQ without 2 element modes.
-(define_mode_iterator VQ_NO2E [V16QI V8HI V4SI V4SF])
+(define_mode_iterator VQ_NO2E [V16QI V8HI V4SI V8HF V4SF])
 
 ;; Quad vector with only 2 element modes.
 (define_mode_iterator VQ_2E [V2DI V2DF])
@@ -97,13 +97,21 @@
 ;; Vector Float modes with 2 elements.
 (define_mode_iterator V2F [V2SF V2DF])
 
-;; All modes.
+;; All vector modes on which we support any arithmetic operations.
 (define_mode_iterator VALL [V8QI V16QI V4HI V8HI V2SI V4SI V2DI V2SF V4SF V2DF])
 
-;; All vector modes and DI.
+;; All vector modes suitable for moving, loading, and storing.
+(define_mode_iterator VALL_F16 [V8QI V16QI V4HI V8HI V2SI V4SI V2DI
+				V4HF V8HF V2SF V4SF V2DF])
+
+;; All vector modes barring HF modes, plus DI.
 (define_mode_iterator VALLDI [V8QI V16QI V4HI V8HI V2SI V4SI V2DI V2SF V4SF V2DF DI])
 
-;; All vector modes and DI and DF.
+;; All vector modes and DI.
+(define_mode_iterator VALLDI_F16 [V8QI V16QI V4HI V8HI V2SI V4SI V2DI
+				  V4HF V8HF V2SF V4SF V2DF DI])
+
+;; All vector modes barring HF modes, plus DI and DF.
 (define_mode_iterator VALLDIF [V8QI V16QI V4HI V8HI V2SI V4SI
 			       V2DI V2SF V4SF V2DF DI DF])
 
@@ -361,7 +369,8 @@
 (define_mode_attr Vmtype [(V8QI ".8b") (V16QI ".16b")
 			 (V4HI ".4h") (V8HI  ".8h")
 			 (V2SI ".2s") (V4SI  ".4s")
-			 (V2DI ".2d") (V2SF ".2s")
+			 (V2DI ".2d") (V4HF ".4h")
+			 (V8HF ".8h") (V2SF ".2s")
 			 (V4SF ".4s") (V2DF ".2d")
 			 (DI   "")    (SI   "")
 			 (HI   "")    (QI   "")
@@ -398,6 +407,7 @@
 			(V4HI "HI") (V8HI "HI")
                         (V2SI "SI") (V4SI "SI")
                         (DI "DI")   (V2DI "DI")
+                        (V4HF "HF") (V8HF "HF")
                         (V2SF "SF") (V4SF "SF")
                         (V2DF "DF") (DF "DF")
 			(SI   "SI") (HI   "HI")
@@ -416,6 +426,7 @@
 			 (V4HI "V8HI") (V8HI "V8HI")
 			 (V2SI "V4SI") (V4SI "V4SI")
 			 (DI   "V2DI") (V2DI "V2DI")
+			 (V4HF "V8HF") (V8HF "V8HF")
 			 (V2SF "V2SF") (V4SF "V4SF")
 			 (V2DF "V2DF") (SI   "V4SI")
 			 (HI   "V8HI") (QI   "V16QI")])
@@ -425,10 +436,12 @@
 			 (V4HI "V2HI")  (V8HI  "V4HI")
 			 (V2SI "SI")    (V4SI  "V2SI")
 			 (V2DI "DI")    (V2SF  "SF")
-			 (V4SF "V2SF")  (V2DF  "DF")])
+			 (V4SF "V2SF")  (V4HF "V2HF")
+			 (V8HF "V4HF")  (V2DF  "DF")])
 
 ;; Double modes of vector modes.
 (define_mode_attr VDBL [(V8QI "V16QI") (V4HI "V8HI")
+			(V4HF "V8HF")
 			(V2SI "V4SI")  (V2SF "V4SF")
 			(SI   "V2SI")  (DI   "V2DI")
 			(DF   "V2DF")])
@@ -539,14 +552,17 @@
 (define_mode_attr nregs [(OI "2") (CI "3") (XI "4")])
 
 (define_mode_attr VRL2 [(V8QI "V32QI") (V4HI "V16HI")
+			(V4HF "V16HF")
 			(V2SI "V8SI")  (V2SF "V8SF")
 			(DI   "V4DI")  (DF   "V4DF")])
 
 (define_mode_attr VRL3 [(V8QI "V48QI") (V4HI "V24HI")
+			(V4HF "V24HF")
 			(V2SI "V12SI")  (V2SF "V12SF")
 			(DI   "V6DI")  (DF   "V6DF")])
 
 (define_mode_attr VRL4 [(V8QI "V64QI") (V4HI "V32HI")
+			(V4HF "V32HF")
 			(V2SI "V16SI")  (V2SF "V16SF")
 			(DI   "V8DI")  (DF   "V8DF")])
 
@@ -559,6 +575,7 @@
                               (V2SI "V2SI") (V4SI "V2SI")
                               (DI "V2DI")   (V2DI "V2DI")
                               (V2SF "V2SF") (V4SF "V2SF")
+                              (V4HF "SF") (V8HF "SF")
                               (DF "V2DI")   (V2DF "V2DI")])
 
 ;; Similar, for three elements.
@@ -567,6 +584,7 @@
                                 (V2SI "BLK") (V4SI "BLK")
                                 (DI "EI")    (V2DI "EI")
                                 (V2SF "BLK") (V4SF "BLK")
+                                (V4HF "BLK") (V8HF "BLK")
                                 (DF "EI")    (V2DF "EI")])
 
 ;; Similar, for four elements.
@@ -575,6 +593,7 @@
                                (V2SI "V4SI") (V4SI "V4SI")
                                (DI "OI")     (V2DI "OI")
                                (V2SF "V4SF") (V4SF "V4SF")
+                               (V4HF "V4HF") (V8HF "V4HF")
                                (DF "OI")     (V2DF "OI")])
 
 
@@ -633,6 +652,7 @@
 		     (V4HI "") (V8HI  "_q")
 		     (V2SI "") (V4SI  "_q")
 		     (DI   "") (V2DI  "_q")
+		     (V4HF "") (V8HF "_q")
 		     (V2SF "") (V4SF  "_q")
 			       (V2DF  "_q")
 		     (QI "") (HI "") (SI "") (DI "") (SF "") (DF "")])
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e75dec7..1d8e585 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,11 @@
+2015-09-08  Alan Lawrence  <alan.lawrence@arm.com>
+
+	* g++.dg/abi/mangle-neon-aarch64.C: Add cases for float16x4_t and
+	float16x8_t.
+	* gcc.target/aarch64/vset_lane_1.c: Likewise.
+	* gcc.target/aarch64/vld1-vst1_1.c: Likewise.
+	* gcc.target/aarch64/vld1_lane.c: Likewise.
+
 2015-09-08  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/67369
diff --git a/gcc/testsuite/g++.dg/abi/mangle-neon-aarch64.C b/gcc/testsuite/g++.dg/abi/mangle-neon-aarch64.C
index 09a20dc..5740c02 100644
--- a/gcc/testsuite/g++.dg/abi/mangle-neon-aarch64.C
+++ b/gcc/testsuite/g++.dg/abi/mangle-neon-aarch64.C
@@ -13,6 +13,7 @@ void f3 (uint8x8_t a) {}
 void f4 (uint16x4_t a) {}
 void f5 (uint32x2_t a) {}
 void f23 (uint64x1_t a) {}
+void f61 (float16x4_t a) {}
 void f6 (float32x2_t a) {}
 void f7 (poly8x8_t a) {}
 void f8 (poly16x4_t a) {}
@@ -25,6 +26,7 @@ void f13 (uint8x16_t a) {}
 void f14 (uint16x8_t a) {}
 void f15 (uint32x4_t a) {}
 void f16 (uint64x2_t a) {}
+void f171 (float16x8_t a) {}
 void f17 (float32x4_t a) {}
 void f18 (float64x2_t a) {}
 void f19 (poly8x16_t a) {}
@@ -42,6 +44,7 @@ void g1 (int8x16_t, int8x16_t) {}
 // { dg-final { scan-assembler "_Z2f412__Uint16x4_t:" } }
 // { dg-final { scan-assembler "_Z2f512__Uint32x2_t:" } }
 // { dg-final { scan-assembler "_Z3f2312__Uint64x1_t:" } }
+// { dg-final { scan-assembler "_Z3f6113__Float16x4_t:" } }
 // { dg-final { scan-assembler "_Z2f613__Float32x2_t:" } }
 // { dg-final { scan-assembler "_Z2f711__Poly8x8_t:" } }
 // { dg-final { scan-assembler "_Z2f812__Poly16x4_t:" } }
@@ -53,6 +56,7 @@ void g1 (int8x16_t, int8x16_t) {}
 // { dg-final { scan-assembler "_Z3f1412__Uint16x8_t:" } }
 // { dg-final { scan-assembler "_Z3f1512__Uint32x4_t:" } }
 // { dg-final { scan-assembler "_Z3f1612__Uint64x2_t:" } }
+// { dg-final { scan-assembler "_Z4f17113__Float16x8_t:" } }
 // { dg-final { scan-assembler "_Z3f1713__Float32x4_t:" } }
 // { dg-final { scan-assembler "_Z3f1813__Float64x2_t:" } }
 // { dg-final { scan-assembler "_Z3f1912__Poly8x16_t:" } }
diff --git a/gcc/testsuite/gcc.target/aarch64/vld1-vst1_1.c b/gcc/testsuite/gcc.target/aarch64/vld1-vst1_1.c
index f8c6edb..fa9ef0f 100644
--- a/gcc/testsuite/gcc.target/aarch64/vld1-vst1_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/vld1-vst1_1.c
@@ -31,6 +31,7 @@ THING (int8x8_t, 8, int8_t, _s8)	\
 THING (uint8x8_t, 8, uint8_t, _u8)	\
 THING (int16x4_t, 4, int16_t, _s16)	\
 THING (uint16x4_t, 4, uint16_t, _u16)	\
+THING (float16x4_t, 4, float16_t, _f16)	\
 THING (int32x2_t, 2, int32_t, _s32)	\
 THING (uint32x2_t, 2, uint32_t, _u32)	\
 THING (float32x2_t, 2, float32_t, _f32) \
@@ -38,6 +39,7 @@ THING (int8x16_t, 16, int8_t, q_s8)	\
 THING (uint8x16_t, 16, uint8_t, q_u8)	\
 THING (int16x8_t, 8, int16_t, q_s16)	\
 THING (uint16x8_t, 8, uint16_t, q_u16)	\
+THING (float16x8_t, 8, float16_t, q_f16)\
 THING (int32x4_t, 4, int32_t, q_s32)	\
 THING (uint32x4_t, 4, uint32_t, q_u32)	\
 THING (float32x4_t, 4, float32_t, q_f32)\
diff --git a/gcc/testsuite/gcc.target/aarch64/vld1_lane.c b/gcc/testsuite/gcc.target/aarch64/vld1_lane.c
index 463c88c..c70df71 100644
--- a/gcc/testsuite/gcc.target/aarch64/vld1_lane.c
+++ b/gcc/testsuite/gcc.target/aarch64/vld1_lane.c
@@ -16,6 +16,7 @@ VARIANT (int32, , 2, _s32, 0)	\
 VARIANT (int64, , 1, _s64, 0)	\
 VARIANT (poly8, , 8, _p8, 7)	\
 VARIANT (poly16, , 4, _p16, 2)	\
+VARIANT (float16, , 4, _f16, 3)	\
 VARIANT (float32, , 2, _f32, 1)	\
 VARIANT (float64, , 1, _f64, 0)	\
 VARIANT (uint8, q, 16, _u8, 13)	\
@@ -28,6 +29,7 @@ VARIANT (int32, q, 4, _s32, 1)	\
 VARIANT (int64, q, 2, _s64, 1)	\
 VARIANT (poly8, q, 16, _p8, 7)	\
 VARIANT (poly16, q, 8, _p16, 4)	\
+VARIANT (float16, q, 8, _f16, 3)\
 VARIANT (float32, q, 4, _f32, 2)\
 VARIANT (float64, q, 2, _f64, 1)
 
@@ -76,6 +78,7 @@ main (int argc, char **argv)
   int64_t int64_data = 0x1234567890abcdefLL;
   poly8_t poly8_data = 13;
   poly16_t poly16_data = 11111;
+  float16_t float16_data = 8.75;
   float32_t float32_data = 3.14159;
   float64_t float64_data = 1.010010001;
 
diff --git a/gcc/testsuite/gcc.target/aarch64/vset_lane_1.c b/gcc/testsuite/gcc.target/aarch64/vset_lane_1.c
index 5fb1139..bc0132c 100644
--- a/gcc/testsuite/gcc.target/aarch64/vset_lane_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/vset_lane_1.c
@@ -16,6 +16,7 @@ VARIANT (int32_t, , 2, int32x2_t, _s32, 0)	\
 VARIANT (int64_t, , 1, int64x1_t, _s64, 0)	\
 VARIANT (poly8_t, , 8, poly8x8_t, _p8, 6)	\
 VARIANT (poly16_t, , 4, poly16x4_t, _p16, 2)	\
+VARIANT (float16_t, , 4, float16x4_t, _f16, 3)	\
 VARIANT (float32_t, , 2, float32x2_t, _f32, 1)	\
 VARIANT (float64_t, , 1, float64x1_t, _f64, 0)	\
 VARIANT (uint8_t, q, 16, uint8x16_t, _u8, 11)	\
@@ -28,6 +29,7 @@ VARIANT (int32_t, q, 4, int32x4_t, _s32, 3)	\
 VARIANT (int64_t, q, 2, int64x2_t, _s64, 0)	\
 VARIANT (poly8_t, q, 16, poly8x16_t, _p8, 14)	\
 VARIANT (poly16_t, q, 8, poly16x8_t, _p16, 6)	\
+VARIANT (float16_t, q, 8, float16x8_t, _f16, 6)	\
 VARIANT (float32_t, q, 4, float32x4_t, _f32, 2) \
 VARIANT (float64_t, q, 2, float64x2_t, _f64, 1)
 
@@ -76,6 +78,9 @@ main (int argc, char **argv)
   poly8_t poly8_t_data[16] =
       { 0, 7, 13, 18, 22, 25, 27, 28, 29, 31, 34, 38, 43, 49, 56, 64 };
   poly16_t poly16_t_data[8] = { 11111, 2222, 333, 44, 5, 65432, 54321, 43210 };
+  float16_t float16_t_data[8] = { 1.25, 4.5, 7.875, 2.3125, 5.675, 8.875,
+      3.6875, 6.75};
+
   float32_t float32_t_data[4] = { 3.14159, 2.718, 1.414, 100.0 };
   float64_t float64_t_data[2] = { 1.01001000100001, 12345.6789 };