Skip to content

R
riscv-gcc-1
Commit 77efea31 by Felix Yang Committed by Fei Yang
Options

re PR target/63173 (performance problem with simd intrinsics vld2_dup_* on aarch64-none-elf) 

        PR target/63173
        * config/aarch64/arm_neon.h (__LD2R_FUNC): Remove macro.
        (__LD3R_FUNC): Ditto.
        (__LD4R_FUNC): Ditto.
        (vld2_dup_s8, vld2_dup_s16, vld2_dup_s32, vld2_dup_f32, vld2_dup_f64,
         vld2_dup_u8, vld2_dup_u16, vld2_dup_u32, vld2_dup_p8, vld2_dup_p16
         vld2_dup_s64, vld2_dup_u64, vld2q_dup_s8, vld2q_dup_p8, 
         vld2q_dup_s16, vld2q_dup_p16, vld2q_dup_s32, vld2q_dup_s64, 
         vld2q_dup_u8, vld2q_dup_u16, vld2q_dup_u32, vld2q_dup_u64 
         vld2q_dup_f32, vld2q_dup_f64): Rewrite using builtin functions.
        (vld3_dup_s64, vld3_dup_u64, vld3_dup_f64, vld3_dup_s8 
         vld3_dup_p8, vld3_dup_s16, vld3_dup_p16, vld3_dup_s32 
         vld3_dup_u8, vld3_dup_u16, vld3_dup_u32, vld3_dup_f32
         vld3q_dup_s8, vld3q_dup_p8, vld3q_dup_s16, vld3q_dup_p16 
         vld3q_dup_s32, vld3q_dup_s64, vld3q_dup_u8, vld3q_dup_u16 
         vld3q_dup_u32, vld3q_dup_u64, vld3q_dup_f32, vld3q_dup_f64): Likewise.
        (vld4_dup_s64, vld4_dup_u64, vld4_dup_f64, vld4_dup_s8 
         vld4_dup_p8, vld4_dup_s16, vld4_dup_p16, vld4_dup_s32 
         vld4_dup_u8, vld4_dup_u16, vld4_dup_u32, vld4_dup_f32 
         vld4q_dup_s8, vld4q_dup_p8, vld4q_dup_s16, vld4q_dup_p16 
         vld4q_dup_s32, vld4q_dup_s64, vld4q_dup_u8, vld4q_dup_u16 
         vld4q_dup_u32, vld4q_dup_u64, vld4q_dup_f32, vld4q_dup_f64): Likewise.
        * config/aarch64/aarch64.md (define_c_enum "unspec"): Add
        UNSPEC_LD2_DUP, UNSPEC_LD3_DUP, UNSPEC_LD4_DUP.
        * config/aarch64/aarch64-simd-builtins.def (ld2r, ld3r, ld4r): New
        builtins.
        * config/aarch64/aarch64-simd.md (aarch64_simd_ld2r<mode>): New pattern.
        (aarch64_simd_ld3r<mode>): Likewise.
        (aarch64_simd_ld4r<mode>): Likewise.
        (aarch64_ld2r<mode>): New expand.
        (aarch64_ld3r<mode>): Likewise.
        (aarch64_ld4r<mode>): Likewise.

Co-Authored-By: Jiji Jiang <jiangjiji@huawei.com>

From-SVN: r216630
parent e7d8c702
Showing with 978 additions and 120 deletions
gcc/ChangeLog
2014-10-24 Felix Yang <felix.yang@huawei.com>
Jiji Jiang <jiangjiji@huawei.com>
PR target/63173
* config/aarch64/arm_neon.h (__LD2R_FUNC): Remove macro.
(__LD3R_FUNC): Ditto.
(__LD4R_FUNC): Ditto.
(vld2_dup_s8, vld2_dup_s16, vld2_dup_s32, vld2_dup_f32, vld2_dup_f64,
vld2_dup_u8, vld2_dup_u16, vld2_dup_u32, vld2_dup_p8, vld2_dup_p16
vld2_dup_s64, vld2_dup_u64, vld2q_dup_s8, vld2q_dup_p8,
vld2q_dup_s16, vld2q_dup_p16, vld2q_dup_s32, vld2q_dup_s64,
vld2q_dup_u8, vld2q_dup_u16, vld2q_dup_u32, vld2q_dup_u64
vld2q_dup_f32, vld2q_dup_f64): Rewrite using builtin functions.
(vld3_dup_s64, vld3_dup_u64, vld3_dup_f64, vld3_dup_s8
vld3_dup_p8, vld3_dup_s16, vld3_dup_p16, vld3_dup_s32
vld3_dup_u8, vld3_dup_u16, vld3_dup_u32, vld3_dup_f32
vld3q_dup_s8, vld3q_dup_p8, vld3q_dup_s16, vld3q_dup_p16
vld3q_dup_s32, vld3q_dup_s64, vld3q_dup_u8, vld3q_dup_u16
vld3q_dup_u32, vld3q_dup_u64, vld3q_dup_f32, vld3q_dup_f64): Likewise.
(vld4_dup_s64, vld4_dup_u64, vld4_dup_f64, vld4_dup_s8
vld4_dup_p8, vld4_dup_s16, vld4_dup_p16, vld4_dup_s32
vld4_dup_u8, vld4_dup_u16, vld4_dup_u32, vld4_dup_f32
vld4q_dup_s8, vld4q_dup_p8, vld4q_dup_s16, vld4q_dup_p16
vld4q_dup_s32, vld4q_dup_s64, vld4q_dup_u8, vld4q_dup_u16
vld4q_dup_u32, vld4q_dup_u64, vld4q_dup_f32, vld4q_dup_f64): Likewise.
* config/aarch64/aarch64.md (define_c_enum "unspec"): Add
UNSPEC_LD2_DUP, UNSPEC_LD3_DUP, UNSPEC_LD4_DUP.
* config/aarch64/aarch64-simd-builtins.def (ld2r, ld3r, ld4r): New
builtins.
* config/aarch64/aarch64-simd.md (aarch64_simd_ld2r<mode>): New pattern.
(aarch64_simd_ld3r<mode>): Likewise.
(aarch64_simd_ld4r<mode>): Likewise.
(aarch64_ld2r<mode>): New expand.
(aarch64_ld3r<mode>): Likewise.
(aarch64_ld4r<mode>): Likewise.
2014-10-24 Maxim Kuvyrkov <maxim.kuvyrkov@gmail.com>
* rtlanal.c (get_base_term): Handle SCRATCH.
gcc/config/aarch64/aarch64-simd-builtins.def
......@@ -83,6 +83,10 @@
BUILTIN_VQ (LOADSTRUCT, ld2, 0)
BUILTIN_VQ (LOADSTRUCT, ld3, 0)
BUILTIN_VQ (LOADSTRUCT, ld4, 0)
/* Implemented by aarch64_ld<VSTRUCT:nregs>r<VALLDIF:mode>. */
BUILTIN_VALLDIF (LOADSTRUCT, ld2r, 0)
BUILTIN_VALLDIF (LOADSTRUCT, ld3r, 0)
BUILTIN_VALLDIF (LOADSTRUCT, ld4r, 0)
/* Implemented by aarch64_st<VSTRUCT:nregs><VDC:mode>. */
BUILTIN_VDC (STORESTRUCT, st2, 0)
BUILTIN_VDC (STORESTRUCT, st3, 0)
......
gcc/config/aarch64/aarch64-simd.md
......@@ -3991,6 +3991,16 @@
[(set_attr "type" "neon_load2_2reg<q>")]
)
(define_insn "aarch64_simd_ld2r<mode>"
[(set (match_operand:OI 0 "register_operand" "=w")
(unspec:OI [(match_operand:<V_TWO_ELEM> 1 "aarch64_simd_struct_operand" "Utv")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY) ]
UNSPEC_LD2_DUP))]
"TARGET_SIMD"
"ld2r\\t{%S0.<Vtype> - %T0.<Vtype>}, %1"
[(set_attr "type" "neon_load2_all_lanes<q>")]
)
(define_insn "vec_store_lanesoi<mode>"
[(set (match_operand:OI 0 "aarch64_simd_struct_operand" "=Utv")
(unspec:OI [(match_operand:OI 1 "register_operand" "w")
......@@ -4022,6 +4032,16 @@
[(set_attr "type" "neon_load3_3reg<q>")]
)
(define_insn "aarch64_simd_ld3r<mode>"
[(set (match_operand:CI 0 "register_operand" "=w")
(unspec:CI [(match_operand:<V_THREE_ELEM> 1 "aarch64_simd_struct_operand" "Utv")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY) ]
UNSPEC_LD3_DUP))]
"TARGET_SIMD"
"ld3r\\t{%S0.<Vtype> - %U0.<Vtype>}, %1"
[(set_attr "type" "neon_load3_all_lanes<q>")]
)
(define_insn "vec_store_lanesci<mode>"
[(set (match_operand:CI 0 "aarch64_simd_struct_operand" "=Utv")
(unspec:CI [(match_operand:CI 1 "register_operand" "w")
......@@ -4053,6 +4073,16 @@
[(set_attr "type" "neon_load4_4reg<q>")]
)
(define_insn "aarch64_simd_ld4r<mode>"
[(set (match_operand:XI 0 "register_operand" "=w")
(unspec:XI [(match_operand:<V_FOUR_ELEM> 1 "aarch64_simd_struct_operand" "Utv")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY) ]
UNSPEC_LD4_DUP))]
"TARGET_SIMD"
"ld4r\\t{%S0.<Vtype> - %V0.<Vtype>}, %1"
[(set_attr "type" "neon_load4_all_lanes<q>")]
)
(define_insn "vec_store_lanesxi<mode>"
[(set (match_operand:XI 0 "aarch64_simd_struct_operand" "=Utv")
(unspec:XI [(match_operand:XI 1 "register_operand" "w")
......@@ -4193,6 +4223,45 @@
aarch64_simd_disambiguate_copy (operands, dest, src, 4);
})
(define_expand "aarch64_ld2r<mode>"
[(match_operand:OI 0 "register_operand" "=w")
(match_operand:DI 1 "register_operand" "w")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
"TARGET_SIMD"
{
enum machine_mode mode = <V_TWO_ELEM>mode;
rtx mem = gen_rtx_MEM (mode, operands[1]);
emit_insn (gen_aarch64_simd_ld2r<mode> (operands[0], mem));
DONE;
})
(define_expand "aarch64_ld3r<mode>"
[(match_operand:CI 0 "register_operand" "=w")
(match_operand:DI 1 "register_operand" "w")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
"TARGET_SIMD"
{
enum machine_mode mode = <V_THREE_ELEM>mode;
rtx mem = gen_rtx_MEM (mode, operands[1]);
emit_insn (gen_aarch64_simd_ld3r<mode> (operands[0], mem));
DONE;
})
(define_expand "aarch64_ld4r<mode>"
[(match_operand:XI 0 "register_operand" "=w")
(match_operand:DI 1 "register_operand" "w")
(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
"TARGET_SIMD"
{
enum machine_mode mode = <V_FOUR_ELEM>mode;
rtx mem = gen_rtx_MEM (mode, operands[1]);
emit_insn (gen_aarch64_simd_ld4r<mode> (operands[0],mem));
DONE;
})
(define_insn "aarch64_ld2<mode>_dreg"
[(set (match_operand:OI 0 "register_operand" "=w")
(subreg:OI
......
gcc/config/aarch64/aarch64.md
......@@ -90,8 +90,11 @@
UNSPEC_GOTTINYPIC
UNSPEC_LD1
UNSPEC_LD2
UNSPEC_LD2_DUP
UNSPEC_LD3
UNSPEC_LD3_DUP
UNSPEC_LD4
UNSPEC_LD4_DUP
UNSPEC_MB
UNSPEC_NOP
UNSPEC_PRLG_STK
......
gcc/config/aarch64/arm_neon.h
......@@ -11765,46 +11765,6 @@ __STRUCTN (poly, 8, 4)
__STRUCTN (float, 64, 4)
#undef __STRUCTN
#define __LD2R_FUNC(rettype, structtype, ptrtype, \
regsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
__attribute__ ((__always_inline__)) \
vld2 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \
{ \
rettype result; \
__asm__ ("ld2r {v16." #regsuffix ", v17." #regsuffix "}, %1\n\t" \
"st1 {v16." #regsuffix ", v17." #regsuffix "}, %0\n\t" \
: "=Q"(result) \
: "Q"(*(const structtype *)ptr) \
: "memory", "v16", "v17"); \
return result; \
}
__LD2R_FUNC (float32x2x2_t, float32x2_t, float32_t, 2s, f32,)
__LD2R_FUNC (float64x1x2_t, float64x2_t, float64_t, 1d, f64,)
__LD2R_FUNC (poly8x8x2_t, poly8x2_t, poly8_t, 8b, p8,)
__LD2R_FUNC (poly16x4x2_t, poly16x2_t, poly16_t, 4h, p16,)
__LD2R_FUNC (int8x8x2_t, int8x2_t, int8_t, 8b, s8,)
__LD2R_FUNC (int16x4x2_t, int16x2_t, int16_t, 4h, s16,)
__LD2R_FUNC (int32x2x2_t, int32x2_t, int32_t, 2s, s32,)
__LD2R_FUNC (int64x1x2_t, int64x2_t, int64_t, 1d, s64,)
__LD2R_FUNC (uint8x8x2_t, uint8x2_t, uint8_t, 8b, u8,)
__LD2R_FUNC (uint16x4x2_t, uint16x2_t, uint16_t, 4h, u16,)
__LD2R_FUNC (uint32x2x2_t, uint32x2_t, uint32_t, 2s, u32,)
__LD2R_FUNC (uint64x1x2_t, uint64x2_t, uint64_t, 1d, u64,)
__LD2R_FUNC (float32x4x2_t, float32x2_t, float32_t, 4s, f32, q)
__LD2R_FUNC (float64x2x2_t, float64x2_t, float64_t, 2d, f64, q)
__LD2R_FUNC (poly8x16x2_t, poly8x2_t, poly8_t, 16b, p8, q)
__LD2R_FUNC (poly16x8x2_t, poly16x2_t, poly16_t, 8h, p16, q)
__LD2R_FUNC (int8x16x2_t, int8x2_t, int8_t, 16b, s8, q)
__LD2R_FUNC (int16x8x2_t, int16x2_t, int16_t, 8h, s16, q)
__LD2R_FUNC (int32x4x2_t, int32x2_t, int32_t, 4s, s32, q)
__LD2R_FUNC (int64x2x2_t, int64x2_t, int64_t, 2d, s64, q)
__LD2R_FUNC (uint8x16x2_t, uint8x2_t, uint8_t, 16b, u8, q)
__LD2R_FUNC (uint16x8x2_t, uint16x2_t, uint16_t, 8h, u16, q)
__LD2R_FUNC (uint32x4x2_t, uint32x2_t, uint32_t, 4s, u32, q)
__LD2R_FUNC (uint64x2x2_t, uint64x2_t, uint64_t, 2d, u64, q)
#define __LD2_LANE_FUNC(rettype, ptrtype, regsuffix, \
lnsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
......@@ -11847,46 +11807,6 @@ __LD2_LANE_FUNC (uint16x8x2_t, uint16_t, 8h, h, u16, q)
__LD2_LANE_FUNC (uint32x4x2_t, uint32_t, 4s, s, u32, q)
__LD2_LANE_FUNC (uint64x2x2_t, uint64_t, 2d, d, u64, q)
#define __LD3R_FUNC(rettype, structtype, ptrtype, \
regsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
__attribute__ ((__always_inline__)) \
vld3 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \
{ \
rettype result; \
__asm__ ("ld3r {v16." #regsuffix " - v18." #regsuffix "}, %1\n\t" \
"st1 {v16." #regsuffix " - v18." #regsuffix "}, %0\n\t" \
: "=Q"(result) \
: "Q"(*(const structtype *)ptr) \
: "memory", "v16", "v17", "v18"); \
return result; \
}
__LD3R_FUNC (float32x2x3_t, float32x3_t, float32_t, 2s, f32,)
__LD3R_FUNC (float64x1x3_t, float64x3_t, float64_t, 1d, f64,)
__LD3R_FUNC (poly8x8x3_t, poly8x3_t, poly8_t, 8b, p8,)
__LD3R_FUNC (poly16x4x3_t, poly16x3_t, poly16_t, 4h, p16,)
__LD3R_FUNC (int8x8x3_t, int8x3_t, int8_t, 8b, s8,)
__LD3R_FUNC (int16x4x3_t, int16x3_t, int16_t, 4h, s16,)
__LD3R_FUNC (int32x2x3_t, int32x3_t, int32_t, 2s, s32,)
__LD3R_FUNC (int64x1x3_t, int64x3_t, int64_t, 1d, s64,)
__LD3R_FUNC (uint8x8x3_t, uint8x3_t, uint8_t, 8b, u8,)
__LD3R_FUNC (uint16x4x3_t, uint16x3_t, uint16_t, 4h, u16,)
__LD3R_FUNC (uint32x2x3_t, uint32x3_t, uint32_t, 2s, u32,)
__LD3R_FUNC (uint64x1x3_t, uint64x3_t, uint64_t, 1d, u64,)
__LD3R_FUNC (float32x4x3_t, float32x3_t, float32_t, 4s, f32, q)
__LD3R_FUNC (float64x2x3_t, float64x3_t, float64_t, 2d, f64, q)
__LD3R_FUNC (poly8x16x3_t, poly8x3_t, poly8_t, 16b, p8, q)
__LD3R_FUNC (poly16x8x3_t, poly16x3_t, poly16_t, 8h, p16, q)
__LD3R_FUNC (int8x16x3_t, int8x3_t, int8_t, 16b, s8, q)
__LD3R_FUNC (int16x8x3_t, int16x3_t, int16_t, 8h, s16, q)
__LD3R_FUNC (int32x4x3_t, int32x3_t, int32_t, 4s, s32, q)
__LD3R_FUNC (int64x2x3_t, int64x3_t, int64_t, 2d, s64, q)
__LD3R_FUNC (uint8x16x3_t, uint8x3_t, uint8_t, 16b, u8, q)
__LD3R_FUNC (uint16x8x3_t, uint16x3_t, uint16_t, 8h, u16, q)
__LD3R_FUNC (uint32x4x3_t, uint32x3_t, uint32_t, 4s, u32, q)
__LD3R_FUNC (uint64x2x3_t, uint64x3_t, uint64_t, 2d, u64, q)
#define __LD3_LANE_FUNC(rettype, ptrtype, regsuffix, \
lnsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
......@@ -11929,46 +11849,6 @@ __LD3_LANE_FUNC (uint16x8x3_t, uint16_t, 8h, h, u16, q)
__LD3_LANE_FUNC (uint32x4x3_t, uint32_t, 4s, s, u32, q)
__LD3_LANE_FUNC (uint64x2x3_t, uint64_t, 2d, d, u64, q)
#define __LD4R_FUNC(rettype, structtype, ptrtype, \
regsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
__attribute__ ((__always_inline__)) \
vld4 ## Q ## _dup_ ## funcsuffix (const ptrtype *ptr) \
{ \
rettype result; \
__asm__ ("ld4r {v16." #regsuffix " - v19." #regsuffix "}, %1\n\t" \
"st1 {v16." #regsuffix " - v19." #regsuffix "}, %0\n\t" \
: "=Q"(result) \
: "Q"(*(const structtype *)ptr) \
: "memory", "v16", "v17", "v18", "v19"); \
return result; \
}
__LD4R_FUNC (float32x2x4_t, float32x4_t, float32_t, 2s, f32,)
__LD4R_FUNC (float64x1x4_t, float64x4_t, float64_t, 1d, f64,)
__LD4R_FUNC (poly8x8x4_t, poly8x4_t, poly8_t, 8b, p8,)
__LD4R_FUNC (poly16x4x4_t, poly16x4_t, poly16_t, 4h, p16,)
__LD4R_FUNC (int8x8x4_t, int8x4_t, int8_t, 8b, s8,)
__LD4R_FUNC (int16x4x4_t, int16x4_t, int16_t, 4h, s16,)
__LD4R_FUNC (int32x2x4_t, int32x4_t, int32_t, 2s, s32,)
__LD4R_FUNC (int64x1x4_t, int64x4_t, int64_t, 1d, s64,)
__LD4R_FUNC (uint8x8x4_t, uint8x4_t, uint8_t, 8b, u8,)
__LD4R_FUNC (uint16x4x4_t, uint16x4_t, uint16_t, 4h, u16,)
__LD4R_FUNC (uint32x2x4_t, uint32x4_t, uint32_t, 2s, u32,)
__LD4R_FUNC (uint64x1x4_t, uint64x4_t, uint64_t, 1d, u64,)
__LD4R_FUNC (float32x4x4_t, float32x4_t, float32_t, 4s, f32, q)
__LD4R_FUNC (float64x2x4_t, float64x4_t, float64_t, 2d, f64, q)
__LD4R_FUNC (poly8x16x4_t, poly8x4_t, poly8_t, 16b, p8, q)
__LD4R_FUNC (poly16x8x4_t, poly16x4_t, poly16_t, 8h, p16, q)
__LD4R_FUNC (int8x16x4_t, int8x4_t, int8_t, 16b, s8, q)
__LD4R_FUNC (int16x8x4_t, int16x4_t, int16_t, 8h, s16, q)
__LD4R_FUNC (int32x4x4_t, int32x4_t, int32_t, 4s, s32, q)
__LD4R_FUNC (int64x2x4_t, int64x4_t, int64_t, 2d, s64, q)
__LD4R_FUNC (uint8x16x4_t, uint8x4_t, uint8_t, 16b, u8, q)
__LD4R_FUNC (uint16x8x4_t, uint16x4_t, uint16_t, 8h, u16, q)
__LD4R_FUNC (uint32x4x4_t, uint32x4_t, uint32_t, 4s, u32, q)
__LD4R_FUNC (uint64x2x4_t, uint64x4_t, uint64_t, 2d, u64, q)
#define __LD4_LANE_FUNC(rettype, ptrtype, regsuffix, \
lnsuffix, funcsuffix, Q) \
__extension__ static __inline rettype \
......@@ -17583,6 +17463,872 @@ vld4q_f64 (const float64_t * __a)
return ret;
}
/* vldn_dup */
__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_s8 (const int8_t * __a)
{
int8x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
return ret;
}
__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_s16 (const int16_t * __a)
{
int16x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
return ret;
}
__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_s32 (const int32_t * __a)
{
int32x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
return ret;
}
__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_f32 (const float32_t * __a)
{
float32x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 0);
ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregoiv2sf (__o, 1);
return ret;
}
__extension__ static __inline float64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_f64 (const float64_t * __a)
{
float64x1x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rdf ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 0)};
ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregoidf (__o, 1)};
return ret;
}
__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_u8 (const uint8_t * __a)
{
uint8x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
return ret;
}
__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_u16 (const uint16_t * __a)
{
uint16x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
return ret;
}
__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__))
vld2_dup_u32 (const uint32_t * __a)
{
uint32x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 0);
ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregoiv2si (__o, 1);
return ret;
}
__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__))
vld2_dup_p8 (const poly8_t * __a)
{
poly8x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 0);
ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregoiv8qi (__o, 1);
return ret;
}
__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__))
vld2_dup_p16 (const poly16_t * __a)
{
poly16x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 0);
ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregoiv4hi (__o, 1);
return ret;
}
__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_s64 (const int64_t * __a)
{
int64x1x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
return ret;
}
__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__))
vld2_dup_u64 (const uint64_t * __a)
{
uint64x1x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 0);
ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregoidi (__o, 1);
return ret;
}
__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_s8 (const int8_t * __a)
{
int8x16x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
return ret;
}
__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_p8 (const poly8_t * __a)
{
poly8x16x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
return ret;
}
__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_s16 (const int16_t * __a)
{
int16x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
return ret;
}
__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_p16 (const poly16_t * __a)
{
poly16x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
return ret;
}
__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_s32 (const int32_t * __a)
{
int32x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
return ret;
}
__extension__ static __inline int64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_s64 (const int64_t * __a)
{
int64x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
return ret;
}
__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__))
vld2q_dup_u8 (const uint8_t * __a)
{
uint8x16x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 0);
ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregoiv16qi (__o, 1);
return ret;
}
__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__))
vld2q_dup_u16 (const uint16_t * __a)
{
uint16x8x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 0);
ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregoiv8hi (__o, 1);
return ret;
}
__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_u32 (const uint32_t * __a)
{
uint32x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 0);
ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregoiv4si (__o, 1);
return ret;
}
__extension__ static __inline uint64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_u64 (const uint64_t * __a)
{
uint64x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 0);
ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregoiv2di (__o, 1);
return ret;
}
__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__))
vld2q_dup_f32 (const float32_t * __a)
{
float32x4x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv4sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 0);
ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregoiv4sf (__o, 1);
return ret;
}
__extension__ static __inline float64x2x2_t __attribute__ ((__always_inline__))
vld2q_dup_f64 (const float64_t * __a)
{
float64x2x2_t ret;
__builtin_aarch64_simd_oi __o;
__o = __builtin_aarch64_ld2rv2df ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 0);
ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregoiv2df (__o, 1);
return ret;
}
__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_s64 (const int64_t * __a)
{
int64x1x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
return ret;
}
__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_u64 (const uint64_t * __a)
{
uint64x1x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 0);
ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 1);
ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregcidi (__o, 2);
return ret;
}
__extension__ static __inline float64x1x3_t __attribute__ ((__always_inline__))
vld3_dup_f64 (const float64_t * __a)
{
float64x1x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rdf ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 0)};
ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 1)};
ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregcidf (__o, 2)};
return ret;
}
__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_s8 (const int8_t * __a)
{
int8x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
return ret;
}
__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_p8 (const poly8_t * __a)
{
poly8x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
return ret;
}
__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_s16 (const int16_t * __a)
{
int16x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
return ret;
}
__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_p16 (const poly16_t * __a)
{
poly16x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
return ret;
}
__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_s32 (const int32_t * __a)
{
int32x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
return ret;
}
__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__))
vld3_dup_u8 (const uint8_t * __a)
{
uint8x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 0);
ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 1);
ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregciv8qi (__o, 2);
return ret;
}
__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__))
vld3_dup_u16 (const uint16_t * __a)
{
uint16x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 0);
ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 1);
ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregciv4hi (__o, 2);
return ret;
}
__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_u32 (const uint32_t * __a)
{
uint32x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 0);
ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 1);
ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregciv2si (__o, 2);
return ret;
}
__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__))
vld3_dup_f32 (const float32_t * __a)
{
float32x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 0);
ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 1);
ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregciv2sf (__o, 2);
return ret;
}
__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_s8 (const int8_t * __a)
{
int8x16x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
return ret;
}
__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_p8 (const poly8_t * __a)
{
poly8x16x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
return ret;
}
__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_s16 (const int16_t * __a)
{
int16x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
return ret;
}
__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_p16 (const poly16_t * __a)
{
poly16x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
return ret;
}
__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_s32 (const int32_t * __a)
{
int32x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
return ret;
}
__extension__ static __inline int64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_s64 (const int64_t * __a)
{
int64x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
return ret;
}
__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__))
vld3q_dup_u8 (const uint8_t * __a)
{
uint8x16x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 0);
ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 1);
ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregciv16qi (__o, 2);
return ret;
}
__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__))
vld3q_dup_u16 (const uint16_t * __a)
{
uint16x8x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 0);
ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 1);
ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregciv8hi (__o, 2);
return ret;
}
__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_u32 (const uint32_t * __a)
{
uint32x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 0);
ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 1);
ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregciv4si (__o, 2);
return ret;
}
__extension__ static __inline uint64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_u64 (const uint64_t * __a)
{
uint64x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 0);
ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 1);
ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregciv2di (__o, 2);
return ret;
}
__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__))
vld3q_dup_f32 (const float32_t * __a)
{
float32x4x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv4sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 0);
ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 1);
ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregciv4sf (__o, 2);
return ret;
}
__extension__ static __inline float64x2x3_t __attribute__ ((__always_inline__))
vld3q_dup_f64 (const float64_t * __a)
{
float64x2x3_t ret;
__builtin_aarch64_simd_ci __o;
__o = __builtin_aarch64_ld3rv2df ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 0);
ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 1);
ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregciv2df (__o, 2);
return ret;
}
__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_s64 (const int64_t * __a)
{
int64x1x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
ret.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
ret.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
ret.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
return ret;
}
__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_u64 (const uint64_t * __a)
{
uint64x1x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rdi ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
ret.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
ret.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
ret.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
return ret;
}
__extension__ static __inline float64x1x4_t __attribute__ ((__always_inline__))
vld4_dup_f64 (const float64_t * __a)
{
float64x1x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rdf ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 0)};
ret.val[1] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 1)};
ret.val[2] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 2)};
ret.val[3] = (float64x1_t) {__builtin_aarch64_get_dregxidf (__o, 3)};
return ret;
}
__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_s8 (const int8_t * __a)
{
int8x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
ret.val[1] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
ret.val[2] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
ret.val[3] = (int8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
return ret;
}
__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_p8 (const poly8_t * __a)
{
poly8x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
ret.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
ret.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
ret.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
return ret;
}
__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_s16 (const int16_t * __a)
{
int16x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
ret.val[1] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
ret.val[2] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
ret.val[3] = (int16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
return ret;
}
__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_p16 (const poly16_t * __a)
{
poly16x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
ret.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
ret.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
ret.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
return ret;
}
__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_s32 (const int32_t * __a)
{
int32x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
ret.val[1] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
ret.val[2] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
ret.val[3] = (int32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
return ret;
}
__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__))
vld4_dup_u8 (const uint8_t * __a)
{
uint8x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 0);
ret.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 1);
ret.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 2);
ret.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxiv8qi (__o, 3);
return ret;
}
__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__))
vld4_dup_u16 (const uint16_t * __a)
{
uint16x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 0);
ret.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 1);
ret.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 2);
ret.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxiv4hi (__o, 3);
return ret;
}
__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_u32 (const uint32_t * __a)
{
uint32x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 0);
ret.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 1);
ret.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 2);
ret.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxiv2si (__o, 3);
return ret;
}
__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__))
vld4_dup_f32 (const float32_t * __a)
{
float32x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 0);
ret.val[1] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 1);
ret.val[2] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 2);
ret.val[3] = (float32x2_t) __builtin_aarch64_get_dregxiv2sf (__o, 3);
return ret;
}
__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_s8 (const int8_t * __a)
{
int8x16x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
return ret;
}
__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_p8 (const poly8_t * __a)
{
poly8x16x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
return ret;
}
__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_s16 (const int16_t * __a)
{
int16x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
return ret;
}
__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_p16 (const poly16_t * __a)
{
poly16x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
return ret;
}
__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_s32 (const int32_t * __a)
{
int32x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
ret.val[3] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
return ret;
}
__extension__ static __inline int64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_s64 (const int64_t * __a)
{
int64x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
return ret;
}
__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__))
vld4q_dup_u8 (const uint8_t * __a)
{
uint8x16x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv16qi ((const __builtin_aarch64_simd_qi *) __a);
ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 0);
ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 1);
ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 2);
ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv16qi (__o, 3);
return ret;
}
__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__))
vld4q_dup_u16 (const uint16_t * __a)
{
uint16x8x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv8hi ((const __builtin_aarch64_simd_hi *) __a);
ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 0);
ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 1);
ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 2);
ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv8hi (__o, 3);
return ret;
}
__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_u32 (const uint32_t * __a)
{
uint32x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4si ((const __builtin_aarch64_simd_si *) __a);
ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
ret.val[3] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
return ret;
}
__extension__ static __inline uint64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_u64 (const uint64_t * __a)
{
uint64x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2di ((const __builtin_aarch64_simd_di *) __a);
ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 0);
ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 1);
ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 2);
ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv2di (__o, 3);
return ret;
}
__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__))
vld4q_dup_f32 (const float32_t * __a)
{
float32x4x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv4sf ((const __builtin_aarch64_simd_sf *) __a);
ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 0);
ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 1);
ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 2);
ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4sf (__o, 3);
return ret;
}
__extension__ static __inline float64x2x4_t __attribute__ ((__always_inline__))
vld4q_dup_f64 (const float64_t * __a)
{
float64x2x4_t ret;
__builtin_aarch64_simd_xi __o;
__o = __builtin_aarch64_ld4rv2df ((const __builtin_aarch64_simd_df *) __a);
ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 0);
ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 1);
ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 2);
ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv2df (__o, 3);
return ret;
}
/* vmax */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment