gcc/ChangeLog:
* config/aarch64/aarch64-simd.md (aarch64_float_truncate_lo_v2sf):
Reparameterize to...
(aarch64_float_truncate_lo_<mode>): ...this, for both V2SF and V4HF.
(aarch64_float_truncate_hi_v4sf): Reparameterize to...
(aarch64_float_truncate_hi_<Vdbl>): ...this, for both V4SF and V8HF.
* config/aarch64/aarch64-simd-builtins.def (float_truncate_hi_): Add
v8hf variant.
(float_truncate_lo_): Use BUILTIN_VDF iterator.
* config/aarch64/arm_neon.h (vreinterpret_p8_f16, vreinterpret_p16_f16,
vreinterpret_f16_f64, vreinterpret_f16_s8, vreinterpret_f16_s16,
vreinterpret_f16_s32, vreinterpret_f16_s64, vreinterpret_f16_f32,
vreinterpret_f16_u8, vreinterpret_f16_u16, vreinterpret_f16_u32,
vreinterpret_f16_u64, vreinterpret_f16_p8, vreinterpret_f16_p16,
vreinterpretq_f16_f64, vreinterpretq_f16_s8, vreinterpretq_f16_s16,
vreinterpretq_f16_s32, vreinterpretq_f16_s64, vreinterpretq_f16_f32,
vreinterpretq_f16_u8, vreinterpretq_f16_u16, vreinterpretq_f16_u32,
vreinterpretq_f16_u64, vreinterpretq_f16_p8, vreinterpretq_f16_p16,
vreinterpret_f32_f16, vreinterpret_f64_f16, vreinterpret_s64_f16,
vreinterpret_u64_f16, vreinterpretq_u64_f16, vreinterpret_s8_f16,
vreinterpret_s16_f16, vreinterpret_s32_f16, vreinterpret_u8_f16,
vreinterpret_u16_f16, vreinterpret_u32_f16, vget_low_f16, vget_high_f16,
vcvt_f16_f32, vcvt_high_f16_f32): New.
* config/aarch64/iterators.md (VDF, Vdtype): New.
(VWIDE, Vmwtype): Add cases for V4HF and V2SF.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/vget_high_1.c: Add float16x8->float16x4 case.
* gcc.target/aarch64/vget_low_1.c: Likewise.
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 6298063d13c444d9b7c6cb0c14cfabce611f0d56..ea84055476c9e56e78d1b843e0b028e85a672ee6 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -4857,6 +4857,12 @@ vsetq_lane_u64 (uint64_t __elem, uint64x2_t __vec, const int __index)
uint64x1_t lo = vcreate_u64 (vgetq_lane_u64 (tmp, 0)); \
return vreinterpret_##__TYPE##_u64 (lo);
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vget_low_f16 (float16x8_t __a)
+{
+ __GET_LOW (f16);
+}
+
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_low_f32 (float32x4_t __a)
{
@@ -4936,6 +4942,12 @@ vget_low_u64 (uint64x2_t __a)
uint64x1_t hi = vcreate_u64 (vgetq_lane_u64 (tmp, 1)); \
return vreinterpret_##__TYPE##_u64 (hi);
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vget_high_f16 (float16x8_t __a)
+{
+ __GET_HIGH (f16);
+}
+
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vget_high_f32 (float32x4_t __a)
{
diff --git a/gcc/testsuite/gcc.target/aarch64/vget_high_1.c b/gcc/testsuite/gcc.target/aarch64/vget_high_1.c
index 4cb872da2cd269df5290a6af928ed958c4fecd09..b6b57e0c5468dbf571ec9e9196ac2d0fa3754d7a 100644
--- a/gcc/testsuite/gcc.target/aarch64/vget_high_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/vget_high_1.c
@@ -14,6 +14,7 @@ VARIANT (int8_t, 8, int8x8_t, int8x16_t, s8) \
VARIANT (int16_t, 4, int16x4_t, int16x8_t, s16) \
VARIANT (int32_t, 2, int32x2_t, int32x4_t, s32) \
VARIANT (int64_t, 1, int64x1_t, int64x2_t, s64) \
+VARIANT (float16_t, 4, float16x4_t, float16x8_t, f16) \
VARIANT (float32_t, 2, float32x2_t, float32x4_t, f32) \
VARIANT (float64_t, 1, float64x1_t, float64x2_t, f64)
@@ -51,6 +52,8 @@ main (int argc, char **argv)
int16_t int16_t_data[8] = { -17, 19, 3, -999, 44048, 505, 9999, 1000};
int32_t int32_t_data[4] = { 123456789, -987654321, -135792468, 975318642 };
int64_t int64_t_data[2] = {0xfedcba9876543210LL, 0xdeadbabecafebeefLL };
+ 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 };
diff --git a/gcc/testsuite/gcc.target/aarch64/vget_low_1.c b/gcc/testsuite/gcc.target/aarch64/vget_low_1.c
index f8016ef73124981f7042957521f42754566e9518..2223676521c4c10b2d839746873eb559559d76ba 100644
--- a/gcc/testsuite/gcc.target/aarch64/vget_low_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/vget_low_1.c
@@ -14,6 +14,7 @@ VARIANT (int8_t, 8, int8x8_t, int8x16_t, s8) \
VARIANT (int16_t, 4, int16x4_t, int16x8_t, s16) \
VARIANT (int32_t, 2, int32x2_t, int32x4_t, s32) \
VARIANT (int64_t, 1, int64x1_t, int64x2_t, s64) \
+VARIANT (float16_t, 4, float16x4_t, float16x8_t, f16) \
VARIANT (float32_t, 2, float32x2_t, float32x4_t, f32) \
VARIANT (float64_t, 1, float64x1_t, float64x2_t, f64)
@@ -51,6 +52,8 @@ main (int argc, char **argv)
int16_t int16_t_data[8] = { -17, 19, 3, -999, 44048, 505, 9999, 1000};
int32_t int32_t_data[4] = { 123456789, -987654321, -135792468, 975318642 };
int64_t int64_t_data[2] = {0xfedcba9876543210LL, 0xdeadbabecafebeefLL };
+ 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 };
