From 358decd5bbc90480ddb536ade1330cd3b43209ff Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Mon, 25 Jul 2016 14:02:42 +0000 Subject: [PATCH] [AArch64][1/10] ARMv8.2-A FP16 data processing intrinsics gcc/ * config/aarch64/aarch64-simd.md (aarch64_): Use VALL_F16. (aarch64_ext): Likewise. (aarch64_rev): Likewise. * config/aarch64/aarch64.c (aarch64_evpc_trn): Support V4HFmode and V8HFmode. (aarch64_evpc_uzp): Likewise. (aarch64_evpc_zip): Likewise. (aarch64_evpc_ext): Likewise. (aarch64_evpc_rev): Likewise. * config/aarch64/arm_neon.h (__aarch64_vdup_lane_f16): New. (__aarch64_vdup_laneq_f16): New.. (__aarch64_vdupq_lane_f16): New. (__aarch64_vdupq_laneq_f16): New. (vbsl_f16): New. (vbslq_f16): New. (vdup_n_f16): New. (vdupq_n_f16): New. (vdup_lane_f16): New. (vdup_laneq_f16): New. (vdupq_lane_f16): New. (vdupq_laneq_f16): New. (vduph_lane_f16): New. (vduph_laneq_f16): New. (vext_f16): New. (vextq_f16): New. (vmov_n_f16): New. (vmovq_n_f16): New. (vrev64_f16): New. (vrev64q_f16): New. (vtrn1_f16): New. (vtrn1q_f16): New. (vtrn2_f16): New. (vtrn2q_f16): New. (vtrn_f16): New. (vtrnq_f16): New. (__INTERLEAVE_LIST): Support float16x4_t, float16x8_t. (vuzp1_f16): New. (vuzp1q_f16): New. (vuzp2_f16): New. (vuzp2q_f16): New. (vzip1_f16): New. (vzip2q_f16): New. (vmov_n_f16): Reimplement using vdup_n_f16. (vmovq_n_f16): Reimplement using vdupq_n_f16.. From-SVN: r238715 --- gcc/ChangeLog | 48 +++++ gcc/config/aarch64/aarch64-simd.md | 22 +-- gcc/config/aarch64/aarch64.c | 16 ++ gcc/config/aarch64/arm_neon.h | 275 ++++++++++++++++++++++++++++- 4 files changed, 346 insertions(+), 15 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index f82a4d3c888..1e3f304a79d 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,51 @@ +2016-07-25 Jiong Wang + + * config/aarch64/aarch64-simd.md + (aarch64_): Use VALL_F16. + (aarch64_ext): Likewise. + (aarch64_rev): Likewise. + * config/aarch64/aarch64.c (aarch64_evpc_trn): Support V4HFmode and + V8HFmode. + (aarch64_evpc_uzp): Likewise. + (aarch64_evpc_zip): Likewise. + (aarch64_evpc_ext): Likewise. + (aarch64_evpc_rev): Likewise. + * config/aarch64/arm_neon.h (__aarch64_vdup_lane_f16): New. + (__aarch64_vdup_laneq_f16): New.. + (__aarch64_vdupq_lane_f16): New. + (__aarch64_vdupq_laneq_f16): New. + (vbsl_f16): New. + (vbslq_f16): New. + (vdup_n_f16): New. + (vdupq_n_f16): New. + (vdup_lane_f16): New. + (vdup_laneq_f16): New. + (vdupq_lane_f16): New. + (vdupq_laneq_f16): New. + (vduph_lane_f16): New. + (vduph_laneq_f16): New. + (vext_f16): New. + (vextq_f16): New. + (vmov_n_f16): New. + (vmovq_n_f16): New. + (vrev64_f16): New. + (vrev64q_f16): New. + (vtrn1_f16): New. + (vtrn1q_f16): New. + (vtrn2_f16): New. + (vtrn2q_f16): New. + (vtrn_f16): New. + (vtrnq_f16): New. + (__INTERLEAVE_LIST): Support float16x4_t, float16x8_t. + (vuzp1_f16): New. + (vuzp1q_f16): New. + (vuzp2_f16): New. + (vuzp2q_f16): New. + (vzip1_f16): New. + (vzip2q_f16): New. + (vmov_n_f16): Reimplement using vdup_n_f16. + (vmovq_n_f16): Reimplement using vdupq_n_f16.. + 2016-07-25 Jiong Wang * config/aarch64/aarch64.c (aarch64_add_constant): New parameter diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index a19d1711b5b..251ad972a4b 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -5219,10 +5219,10 @@ ) (define_insn "aarch64_" - [(set (match_operand:VALL 0 "register_operand" "=w") - (unspec:VALL [(match_operand:VALL 1 "register_operand" "w") - (match_operand:VALL 2 "register_operand" "w")] - PERMUTE))] + [(set (match_operand:VALL_F16 0 "register_operand" "=w") + (unspec:VALL_F16 [(match_operand:VALL_F16 1 "register_operand" "w") + (match_operand:VALL_F16 2 "register_operand" "w")] + PERMUTE))] "TARGET_SIMD" "\\t%0., %1., %2." [(set_attr "type" "neon_permute")] @@ -5230,11 +5230,11 @@ ;; Note immediate (third) operand is lane index not byte index. (define_insn "aarch64_ext" - [(set (match_operand:VALL 0 "register_operand" "=w") - (unspec:VALL [(match_operand:VALL 1 "register_operand" "w") - (match_operand:VALL 2 "register_operand" "w") - (match_operand:SI 3 "immediate_operand" "i")] - UNSPEC_EXT))] + [(set (match_operand:VALL_F16 0 "register_operand" "=w") + (unspec:VALL_F16 [(match_operand:VALL_F16 1 "register_operand" "w") + (match_operand:VALL_F16 2 "register_operand" "w") + (match_operand:SI 3 "immediate_operand" "i")] + UNSPEC_EXT))] "TARGET_SIMD" { operands[3] = GEN_INT (INTVAL (operands[3]) @@ -5245,8 +5245,8 @@ ) (define_insn "aarch64_rev" - [(set (match_operand:VALL 0 "register_operand" "=w") - (unspec:VALL [(match_operand:VALL 1 "register_operand" "w")] + [(set (match_operand:VALL_F16 0 "register_operand" "=w") + (unspec:VALL_F16 [(match_operand:VALL_F16 1 "register_operand" "w")] REVERSE))] "TARGET_SIMD" "rev\\t%0., %1." diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c index 5560516c9f1..381cf7d3b85 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -12286,6 +12286,8 @@ aarch64_evpc_trn (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_trn2v4si; break; case V2SImode: gen = gen_aarch64_trn2v2si; break; case V2DImode: gen = gen_aarch64_trn2v2di; break; + case V4HFmode: gen = gen_aarch64_trn2v4hf; break; + case V8HFmode: gen = gen_aarch64_trn2v8hf; break; case V4SFmode: gen = gen_aarch64_trn2v4sf; break; case V2SFmode: gen = gen_aarch64_trn2v2sf; break; case V2DFmode: gen = gen_aarch64_trn2v2df; break; @@ -12304,6 +12306,8 @@ aarch64_evpc_trn (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_trn1v4si; break; case V2SImode: gen = gen_aarch64_trn1v2si; break; case V2DImode: gen = gen_aarch64_trn1v2di; break; + case V4HFmode: gen = gen_aarch64_trn1v4hf; break; + case V8HFmode: gen = gen_aarch64_trn1v8hf; break; case V4SFmode: gen = gen_aarch64_trn1v4sf; break; case V2SFmode: gen = gen_aarch64_trn1v2sf; break; case V2DFmode: gen = gen_aarch64_trn1v2df; break; @@ -12369,6 +12373,8 @@ aarch64_evpc_uzp (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_uzp2v4si; break; case V2SImode: gen = gen_aarch64_uzp2v2si; break; case V2DImode: gen = gen_aarch64_uzp2v2di; break; + case V4HFmode: gen = gen_aarch64_uzp2v4hf; break; + case V8HFmode: gen = gen_aarch64_uzp2v8hf; break; case V4SFmode: gen = gen_aarch64_uzp2v4sf; break; case V2SFmode: gen = gen_aarch64_uzp2v2sf; break; case V2DFmode: gen = gen_aarch64_uzp2v2df; break; @@ -12387,6 +12393,8 @@ aarch64_evpc_uzp (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_uzp1v4si; break; case V2SImode: gen = gen_aarch64_uzp1v2si; break; case V2DImode: gen = gen_aarch64_uzp1v2di; break; + case V4HFmode: gen = gen_aarch64_uzp1v4hf; break; + case V8HFmode: gen = gen_aarch64_uzp1v8hf; break; case V4SFmode: gen = gen_aarch64_uzp1v4sf; break; case V2SFmode: gen = gen_aarch64_uzp1v2sf; break; case V2DFmode: gen = gen_aarch64_uzp1v2df; break; @@ -12457,6 +12465,8 @@ aarch64_evpc_zip (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_zip2v4si; break; case V2SImode: gen = gen_aarch64_zip2v2si; break; case V2DImode: gen = gen_aarch64_zip2v2di; break; + case V4HFmode: gen = gen_aarch64_zip2v4hf; break; + case V8HFmode: gen = gen_aarch64_zip2v8hf; break; case V4SFmode: gen = gen_aarch64_zip2v4sf; break; case V2SFmode: gen = gen_aarch64_zip2v2sf; break; case V2DFmode: gen = gen_aarch64_zip2v2df; break; @@ -12475,6 +12485,8 @@ aarch64_evpc_zip (struct expand_vec_perm_d *d) case V4SImode: gen = gen_aarch64_zip1v4si; break; case V2SImode: gen = gen_aarch64_zip1v2si; break; case V2DImode: gen = gen_aarch64_zip1v2di; break; + case V4HFmode: gen = gen_aarch64_zip1v4hf; break; + case V8HFmode: gen = gen_aarch64_zip1v8hf; break; case V4SFmode: gen = gen_aarch64_zip1v4sf; break; case V2SFmode: gen = gen_aarch64_zip1v2sf; break; case V2DFmode: gen = gen_aarch64_zip1v2df; break; @@ -12519,6 +12531,8 @@ aarch64_evpc_ext (struct expand_vec_perm_d *d) case V8HImode: gen = gen_aarch64_extv8hi; break; case V2SImode: gen = gen_aarch64_extv2si; break; case V4SImode: gen = gen_aarch64_extv4si; break; + case V4HFmode: gen = gen_aarch64_extv4hf; break; + case V8HFmode: gen = gen_aarch64_extv8hf; break; case V2SFmode: gen = gen_aarch64_extv2sf; break; case V4SFmode: gen = gen_aarch64_extv4sf; break; case V2DImode: gen = gen_aarch64_extv2di; break; @@ -12594,6 +12608,8 @@ aarch64_evpc_rev (struct expand_vec_perm_d *d) case V2SImode: gen = gen_aarch64_rev64v2si; break; case V4SFmode: gen = gen_aarch64_rev64v4sf; break; case V2SFmode: gen = gen_aarch64_rev64v2sf; break; + case V8HFmode: gen = gen_aarch64_rev64v8hf; break; + case V4HFmode: gen = gen_aarch64_rev64v4hf; break; default: return false; } diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h index b0ab1d33d37..fd5f094de6a 100644 --- a/gcc/config/aarch64/arm_neon.h +++ b/gcc/config/aarch64/arm_neon.h @@ -466,6 +466,8 @@ typedef struct poly16x8x4_t #define __aarch64_vdup_lane_any(__size, __q, __a, __b) \ vdup##__q##_n_##__size (__aarch64_vget_lane_any (__a, __b)) +#define __aarch64_vdup_lane_f16(__a, __b) \ + __aarch64_vdup_lane_any (f16, , __a, __b) #define __aarch64_vdup_lane_f32(__a, __b) \ __aarch64_vdup_lane_any (f32, , __a, __b) #define __aarch64_vdup_lane_f64(__a, __b) \ @@ -492,6 +494,8 @@ typedef struct poly16x8x4_t __aarch64_vdup_lane_any (u64, , __a, __b) /* __aarch64_vdup_laneq internal macros. */ +#define __aarch64_vdup_laneq_f16(__a, __b) \ + __aarch64_vdup_lane_any (f16, , __a, __b) #define __aarch64_vdup_laneq_f32(__a, __b) \ __aarch64_vdup_lane_any (f32, , __a, __b) #define __aarch64_vdup_laneq_f64(__a, __b) \ @@ -518,6 +522,8 @@ typedef struct poly16x8x4_t __aarch64_vdup_lane_any (u64, , __a, __b) /* __aarch64_vdupq_lane internal macros. */ +#define __aarch64_vdupq_lane_f16(__a, __b) \ + __aarch64_vdup_lane_any (f16, q, __a, __b) #define __aarch64_vdupq_lane_f32(__a, __b) \ __aarch64_vdup_lane_any (f32, q, __a, __b) #define __aarch64_vdupq_lane_f64(__a, __b) \ @@ -544,6 +550,8 @@ typedef struct poly16x8x4_t __aarch64_vdup_lane_any (u64, q, __a, __b) /* __aarch64_vdupq_laneq internal macros. */ +#define __aarch64_vdupq_laneq_f16(__a, __b) \ + __aarch64_vdup_lane_any (f16, q, __a, __b) #define __aarch64_vdupq_laneq_f32(__a, __b) \ __aarch64_vdup_lane_any (f32, q, __a, __b) #define __aarch64_vdupq_laneq_f64(__a, __b) \ @@ -10213,6 +10221,12 @@ vaddvq_f64 (float64x2_t __a) /* vbsl */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vbsl_f16 (uint16x4_t __a, float16x4_t __b, float16x4_t __c) +{ + return __builtin_aarch64_simd_bslv4hf_suss (__a, __b, __c); +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vbsl_f32 (uint32x2_t __a, float32x2_t __b, float32x2_t __c) { @@ -10288,6 +10302,12 @@ vbsl_u64 (uint64x1_t __a, uint64x1_t __b, uint64x1_t __c) {__builtin_aarch64_simd_bsldi_uuuu (__a[0], __b[0], __c[0])}; } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vbslq_f16 (uint16x8_t __a, float16x8_t __b, float16x8_t __c) +{ + return __builtin_aarch64_simd_bslv8hf_suss (__a, __b, __c); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vbslq_f32 (uint32x4_t __a, float32x4_t __b, float32x4_t __c) { @@ -13243,6 +13263,12 @@ vcvtpq_u64_f64 (float64x2_t __a) /* vdup_n */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vdup_n_f16 (float16_t __a) +{ + return (float16x4_t) {__a, __a, __a, __a}; +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vdup_n_f32 (float32_t __a) { @@ -13317,6 +13343,12 @@ vdup_n_u64 (uint64_t __a) /* vdupq_n */ +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vdupq_n_f16 (float16_t __a) +{ + return (float16x8_t) {__a, __a, __a, __a, __a, __a, __a, __a}; +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vdupq_n_f32 (float32_t __a) { @@ -13394,6 +13426,12 @@ vdupq_n_u64 (uint64_t __a) /* vdup_lane */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vdup_lane_f16 (float16x4_t __a, const int __b) +{ + return __aarch64_vdup_lane_f16 (__a, __b); +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vdup_lane_f32 (float32x2_t __a, const int __b) { @@ -13468,6 +13506,12 @@ vdup_lane_u64 (uint64x1_t __a, const int __b) /* vdup_laneq */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vdup_laneq_f16 (float16x8_t __a, const int __b) +{ + return __aarch64_vdup_laneq_f16 (__a, __b); +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vdup_laneq_f32 (float32x4_t __a, const int __b) { @@ -13541,6 +13585,13 @@ vdup_laneq_u64 (uint64x2_t __a, const int __b) } /* vdupq_lane */ + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vdupq_lane_f16 (float16x4_t __a, const int __b) +{ + return __aarch64_vdupq_lane_f16 (__a, __b); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vdupq_lane_f32 (float32x2_t __a, const int __b) { @@ -13614,6 +13665,13 @@ vdupq_lane_u64 (uint64x1_t __a, const int __b) } /* vdupq_laneq */ + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vdupq_laneq_f16 (float16x8_t __a, const int __b) +{ + return __aarch64_vdupq_laneq_f16 (__a, __b); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vdupq_laneq_f32 (float32x4_t __a, const int __b) { @@ -13706,6 +13764,13 @@ vdupb_lane_u8 (uint8x8_t __a, const int __b) } /* vduph_lane */ + +__extension__ static __inline float16_t __attribute__ ((__always_inline__)) +vduph_lane_f16 (float16x4_t __a, const int __b) +{ + return __aarch64_vget_lane_any (__a, __b); +} + __extension__ static __inline poly16_t __attribute__ ((__always_inline__)) vduph_lane_p16 (poly16x4_t __a, const int __b) { @@ -13725,6 +13790,7 @@ vduph_lane_u16 (uint16x4_t __a, const int __b) } /* vdups_lane */ + __extension__ static __inline float32_t __attribute__ ((__always_inline__)) vdups_lane_f32 (float32x2_t __a, const int __b) { @@ -13785,6 +13851,13 @@ vdupb_laneq_u8 (uint8x16_t __a, const int __b) } /* vduph_laneq */ + +__extension__ static __inline float16_t __attribute__ ((__always_inline__)) +vduph_laneq_f16 (float16x8_t __a, const int __b) +{ + return __aarch64_vget_lane_any (__a, __b); +} + __extension__ static __inline poly16_t __attribute__ ((__always_inline__)) vduph_laneq_p16 (poly16x8_t __a, const int __b) { @@ -13804,6 +13877,7 @@ vduph_laneq_u16 (uint16x8_t __a, const int __b) } /* vdups_laneq */ + __extension__ static __inline float32_t __attribute__ ((__always_inline__)) vdups_laneq_f32 (float32x4_t __a, const int __b) { @@ -13843,6 +13917,19 @@ vdupd_laneq_u64 (uint64x2_t __a, const int __b) /* vext */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vext_f16 (float16x4_t __a, float16x4_t __b, __const int __c) +{ + __AARCH64_LANE_CHECK (__a, __c); +#ifdef __AARCH64EB__ + return __builtin_shuffle (__b, __a, + (uint16x4_t) {4 - __c, 5 - __c, 6 - __c, 7 - __c}); +#else + return __builtin_shuffle (__a, __b, + (uint16x4_t) {__c, __c + 1, __c + 2, __c + 3}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vext_f32 (float32x2_t __a, float32x2_t __b, __const int __c) { @@ -13974,6 +14061,22 @@ vext_u64 (uint64x1_t __a, uint64x1_t __b, __const int __c) return __a; } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vextq_f16 (float16x8_t __a, float16x8_t __b, __const int __c) +{ + __AARCH64_LANE_CHECK (__a, __c); +#ifdef __AARCH64EB__ + return __builtin_shuffle (__b, __a, + (uint16x8_t) {8 - __c, 9 - __c, 10 - __c, 11 - __c, + 12 - __c, 13 - __c, 14 - __c, + 15 - __c}); +#else + return __builtin_shuffle (__a, __b, + (uint16x8_t) {__c, __c + 1, __c + 2, __c + 3, + __c + 4, __c + 5, __c + 6, __c + 7}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vextq_f32 (float32x4_t __a, float32x4_t __b, __const int __c) { @@ -14609,8 +14712,7 @@ vld1q_u64 (const uint64_t *a) __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 }; + return vdup_n_f16 (*__a); } __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) @@ -14690,8 +14792,7 @@ vld1_dup_u64 (const uint64_t* __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 }; + return vdupq_n_f16 (*__a); } __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) @@ -18294,6 +18395,12 @@ vmlsq_laneq_u32 (uint32x4_t __a, uint32x4_t __b, /* vmov_n_ */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vmov_n_f16 (float16_t __a) +{ + return vdup_n_f16 (__a); +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vmov_n_f32 (float32_t __a) { @@ -18366,6 +18473,12 @@ vmov_n_u64 (uint64_t __a) return (uint64x1_t) {__a}; } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vmovq_n_f16 (float16_t __a) +{ + return vdupq_n_f16 (__a); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vmovq_n_f32 (float32_t __a) { @@ -21123,6 +21236,12 @@ vrev32q_u16 (uint16x8_t a) return __builtin_shuffle (a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); } +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vrev64_f16 (float16x4_t __a) +{ + return __builtin_shuffle (__a, (uint16x4_t) { 3, 2, 1, 0 }); +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vrev64_f32 (float32x2_t a) { @@ -21177,6 +21296,12 @@ vrev64_u32 (uint32x2_t a) return __builtin_shuffle (a, (uint32x2_t) { 1, 0 }); } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vrev64q_f16 (float16x8_t __a) +{ + return __builtin_shuffle (__a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vrev64q_f32 (float32x4_t a) { @@ -24129,6 +24254,16 @@ vtbx4_p8 (poly8x8_t __r, poly8x8x4_t __tab, uint8x8_t __idx) /* vtrn */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vtrn1_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 1, 7, 3}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 2, 6}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vtrn1_f32 (float32x2_t __a, float32x2_t __b) { @@ -24219,6 +24354,16 @@ vtrn1_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vtrn1q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 1, 11, 3, 13, 5, 15, 7}); +#else + return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 8, 2, 10, 4, 12, 6, 14}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vtrn1q_f32 (float32x4_t __a, float32x4_t __b) { @@ -24345,6 +24490,16 @@ vtrn1q_u64 (uint64x2_t __a, uint64x2_t __b) #endif } +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vtrn2_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 6, 2}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 5, 3, 7}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vtrn2_f32 (float32x2_t __a, float32x2_t __b) { @@ -24435,6 +24590,16 @@ vtrn2_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vtrn2q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 0, 10, 2, 12, 4, 14, 6}); +#else + return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 9, 3, 11, 5, 13, 7, 15}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vtrn2q_f32 (float32x4_t __a, float32x4_t __b) { @@ -24561,6 +24726,12 @@ vtrn2q_u64 (uint64x2_t __a, uint64x2_t __b) #endif } +__extension__ static __inline float16x4x2_t __attribute__ ((__always_inline__)) +vtrn_f16 (float16x4_t __a, float16x4_t __b) +{ + return (float16x4x2_t) {vtrn1_f16 (__a, __b), vtrn2_f16 (__a, __b)}; +} + __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vtrn_f32 (float32x2_t a, float32x2_t b) { @@ -24615,6 +24786,12 @@ vtrn_u32 (uint32x2_t a, uint32x2_t b) return (uint32x2x2_t) {vtrn1_u32 (a, b), vtrn2_u32 (a, b)}; } +__extension__ static __inline float16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_f16 (float16x8_t __a, float16x8_t __b) +{ + return (float16x8x2_t) {vtrn1q_f16 (__a, __b), vtrn2q_f16 (__a, __b)}; +} + __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vtrnq_f32 (float32x4_t a, float32x4_t b) { @@ -24863,6 +25040,7 @@ vuqaddd_s64 (int64_t __a, uint64_t __b) } #define __INTERLEAVE_LIST(op) \ + __DEFINTERLEAVE (op, float16x4x2_t, float16x4_t, f16,) \ __DEFINTERLEAVE (op, float32x2x2_t, float32x2_t, f32,) \ __DEFINTERLEAVE (op, poly8x8x2_t, poly8x8_t, p8,) \ __DEFINTERLEAVE (op, poly16x4x2_t, poly16x4_t, p16,) \ @@ -24872,6 +25050,7 @@ vuqaddd_s64 (int64_t __a, uint64_t __b) __DEFINTERLEAVE (op, uint8x8x2_t, uint8x8_t, u8,) \ __DEFINTERLEAVE (op, uint16x4x2_t, uint16x4_t, u16,) \ __DEFINTERLEAVE (op, uint32x2x2_t, uint32x2_t, u32,) \ + __DEFINTERLEAVE (op, float16x8x2_t, float16x8_t, f16, q) \ __DEFINTERLEAVE (op, float32x4x2_t, float32x4_t, f32, q) \ __DEFINTERLEAVE (op, poly8x16x2_t, poly8x16_t, p8, q) \ __DEFINTERLEAVE (op, poly16x8x2_t, poly16x8_t, p16, q) \ @@ -24884,6 +25063,16 @@ vuqaddd_s64 (int64_t __a, uint64_t __b) /* vuzp */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vuzp1_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {5, 7, 1, 3}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 2, 4, 6}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vuzp1_f32 (float32x2_t __a, float32x2_t __b) { @@ -24974,6 +25163,16 @@ vuzp1_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vuzp1q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x8_t) {9, 11, 13, 15, 1, 3, 5, 7}); +#else + return __builtin_shuffle (__a, __b, (uint16x8_t) {0, 2, 4, 6, 8, 10, 12, 14}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vuzp1q_f32 (float32x4_t __a, float32x4_t __b) { @@ -25100,6 +25299,16 @@ vuzp1q_u64 (uint64x2_t __a, uint64x2_t __b) #endif } +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vuzp2_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 6, 0, 2}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {1, 3, 5, 7}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vuzp2_f32 (float32x2_t __a, float32x2_t __b) { @@ -25190,6 +25399,16 @@ vuzp2_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vuzp2q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x8_t) {8, 10, 12, 14, 0, 2, 4, 6}); +#else + return __builtin_shuffle (__a, __b, (uint16x8_t) {1, 3, 5, 7, 9, 11, 13, 15}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vuzp2q_f32 (float32x4_t __a, float32x4_t __b) { @@ -25320,6 +25539,16 @@ __INTERLEAVE_LIST (uzp) /* vzip */ +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vzip1_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {6, 2, 7, 3}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {0, 4, 1, 5}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vzip1_f32 (float32x2_t __a, float32x2_t __b) { @@ -25410,6 +25639,18 @@ vzip1_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vzip1q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, + (uint16x8_t) {12, 4, 13, 5, 14, 6, 15, 7}); +#else + return __builtin_shuffle (__a, __b, + (uint16x8_t) {0, 8, 1, 9, 2, 10, 3, 11}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vzip1q_f32 (float32x4_t __a, float32x4_t __b) { @@ -25539,6 +25780,16 @@ vzip1q_u64 (uint64x2_t __a, uint64x2_t __b) #endif } +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vzip2_f16 (float16x4_t __a, float16x4_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, (uint16x4_t) {4, 0, 5, 1}); +#else + return __builtin_shuffle (__a, __b, (uint16x4_t) {2, 6, 3, 7}); +#endif +} + __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vzip2_f32 (float32x2_t __a, float32x2_t __b) { @@ -25629,6 +25880,18 @@ vzip2_u32 (uint32x2_t __a, uint32x2_t __b) #endif } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vzip2q_f16 (float16x8_t __a, float16x8_t __b) +{ +#ifdef __AARCH64EB__ + return __builtin_shuffle (__a, __b, + (uint16x8_t) {8, 0, 9, 1, 10, 2, 11, 3}); +#else + return __builtin_shuffle (__a, __b, + (uint16x8_t) {4, 12, 5, 13, 6, 14, 7, 15}); +#endif +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vzip2q_f32 (float32x4_t __a, float32x4_t __b) { @@ -25768,6 +26031,7 @@ __INTERLEAVE_LIST (zip) #undef __aarch64_vget_lane_any #undef __aarch64_vdup_lane_any +#undef __aarch64_vdup_lane_f16 #undef __aarch64_vdup_lane_f32 #undef __aarch64_vdup_lane_f64 #undef __aarch64_vdup_lane_p8 @@ -25780,6 +26044,7 @@ __INTERLEAVE_LIST (zip) #undef __aarch64_vdup_lane_u16 #undef __aarch64_vdup_lane_u32 #undef __aarch64_vdup_lane_u64 +#undef __aarch64_vdup_laneq_f16 #undef __aarch64_vdup_laneq_f32 #undef __aarch64_vdup_laneq_f64 #undef __aarch64_vdup_laneq_p8 @@ -25792,6 +26057,7 @@ __INTERLEAVE_LIST (zip) #undef __aarch64_vdup_laneq_u16 #undef __aarch64_vdup_laneq_u32 #undef __aarch64_vdup_laneq_u64 +#undef __aarch64_vdupq_lane_f16 #undef __aarch64_vdupq_lane_f32 #undef __aarch64_vdupq_lane_f64 #undef __aarch64_vdupq_lane_p8 @@ -25804,6 +26070,7 @@ __INTERLEAVE_LIST (zip) #undef __aarch64_vdupq_lane_u16 #undef __aarch64_vdupq_lane_u32 #undef __aarch64_vdupq_lane_u64 +#undef __aarch64_vdupq_laneq_f16 #undef __aarch64_vdupq_laneq_f32 #undef __aarch64_vdupq_laneq_f64 #undef __aarch64_vdupq_laneq_p8 -- 2.30.2