diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c index f6b41d9c200d6300dee65ba60ae94488231a8a38..e47545b111762b95242d8f8de1a26f7bd11992ae 100644 --- a/gcc/config/aarch64/aarch64-builtins.c +++ b/gcc/config/aarch64/aarch64-builtins.c @@ -2394,6 +2394,68 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt) 1, args[0]); gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt)); break; + BUILTIN_VSDQ_I_DI (BINOP, ashl, 3, NONE) + { + tree cst = args[1]; + tree ctype = TREE_TYPE (cst); + if (INTEGRAL_TYPE_P (ctype) + && TREE_CODE (cst) == INTEGER_CST) + { + wide_int wcst = wi::to_wide (cst); + if (wi::neg_p (wcst, TYPE_SIGN (ctype))) + new_stmt = + gimple_build_assign (gimple_call_lhs (stmt), + RSHIFT_EXPR, args[0], + wide_int_to_tree (ctype, + wi::abs (wcst))); + else + new_stmt = + gimple_build_assign (gimple_call_lhs (stmt), + LSHIFT_EXPR, args[0], args[1]); + } + } + break; + BUILTIN_VSDQ_I_DI (BINOP, sshl, 0, NONE) + BUILTIN_VSDQ_I_DI (BINOP_UUS, ushl, 0, NONE) + { + tree cst = args[1]; + tree ctype = TREE_TYPE (cst); + HOST_WIDE_INT bits = GET_MODE_UNIT_BITSIZE (TYPE_MODE (TREE_TYPE (args[0]))); + if (INTEGRAL_TYPE_P (ctype) + && TREE_CODE (cst) == INTEGER_CST) + { + wide_int wcst = wi::to_wide (cst); + wide_int abs_cst = wi::abs (wcst); + if (wi::eq_p (abs_cst, bits)) + break; + + if (wi::neg_p (wcst, TYPE_SIGN (ctype))) + new_stmt = + gimple_build_assign (gimple_call_lhs (stmt), + RSHIFT_EXPR, args[0], + wide_int_to_tree (ctype, abs_cst)); + else + new_stmt = + gimple_build_assign (gimple_call_lhs (stmt), + LSHIFT_EXPR, args[0], args[1]); + } + } + break; + BUILTIN_VDQ_I (SHIFTIMM, ashr, 3, NONE) + VAR1 (SHIFTIMM, ashr_simd, 0, NONE, di) + BUILTIN_VDQ_I (USHIFTIMM, lshr, 3, NONE) + VAR1 (USHIFTIMM, lshr_simd, 0, NONE, di) + { + tree cst = args[1]; + tree ctype = TREE_TYPE (cst); + HOST_WIDE_INT bits = GET_MODE_UNIT_BITSIZE (TYPE_MODE (TREE_TYPE (args[0]))); + if (INTEGRAL_TYPE_P (ctype) + && TREE_CODE (cst) == INTEGER_CST + && wi::ne_p (wi::to_wide (cst), bits)) + new_stmt = gimple_build_assign (gimple_call_lhs (stmt), + RSHIFT_EXPR, args[0], args[1]); + } + break; BUILTIN_GPF (BINOP, fmulx, 0, ALL) { gcc_assert (nargs == 2); diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def index 402453aa9bba5949da43c984c4603196b1efd092..bbe0a4a3c4aea4187e7b1a9f10ab60e79df7b138 100644 --- a/gcc/config/aarch64/aarch64-simd-builtins.def +++ b/gcc/config/aarch64/aarch64-simd-builtins.def @@ -409,7 +409,7 @@ BUILTIN_VDQ_I (SHIFTIMM, ashr, 3, NONE) VAR1 (SHIFTIMM, ashr_simd, 0, NONE, di) - BUILTIN_VDQ_I (SHIFTIMM, lshr, 3, NONE) + BUILTIN_VDQ_I (USHIFTIMM, lshr, 3, NONE) VAR1 (USHIFTIMM, lshr_simd, 0, NONE, di) /* Implemented by aarch64_shr_n. */ BUILTIN_VSDQ_I_DI (SHIFTIMM, srshr_n, 0, NONE) diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h index 635a223b59eb0f64304351939d444411b697af81..c4ef5f7f7e3658c830893931ef5a874842410e10 100644 --- a/gcc/config/aarch64/arm_neon.h +++ b/gcc/config/aarch64/arm_neon.h @@ -27400,21 +27400,21 @@ __extension__ extern __inline uint8x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshr_n_u8 (uint8x8_t __a, const int __b) { - return (uint8x8_t) __builtin_aarch64_lshrv8qi ((int8x8_t) __a, __b); + return __builtin_aarch64_lshrv8qi_uus (__a, __b); } __extension__ extern __inline uint16x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshr_n_u16 (uint16x4_t __a, const int __b) { - return (uint16x4_t) __builtin_aarch64_lshrv4hi ((int16x4_t) __a, __b); + return __builtin_aarch64_lshrv4hi_uus (__a, __b); } __extension__ extern __inline uint32x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshr_n_u32 (uint32x2_t __a, const int __b) { - return (uint32x2_t) __builtin_aarch64_lshrv2si ((int32x2_t) __a, __b); + return __builtin_aarch64_lshrv2si_uus (__a, __b); } __extension__ extern __inline uint64x1_t @@ -27456,28 +27456,28 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshrq_n_u8 (uint8x16_t __a, const int __b) { - return (uint8x16_t) __builtin_aarch64_lshrv16qi ((int8x16_t) __a, __b); + return __builtin_aarch64_lshrv16qi_uus (__a, __b); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshrq_n_u16 (uint16x8_t __a, const int __b) { - return (uint16x8_t) __builtin_aarch64_lshrv8hi ((int16x8_t) __a, __b); + return __builtin_aarch64_lshrv8hi_uus (__a, __b); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshrq_n_u32 (uint32x4_t __a, const int __b) { - return (uint32x4_t) __builtin_aarch64_lshrv4si ((int32x4_t) __a, __b); + return __builtin_aarch64_lshrv4si_uus (__a, __b); } __extension__ extern __inline uint64x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vshrq_n_u64 (uint64x2_t __a, const int __b) { - return (uint64x2_t) __builtin_aarch64_lshrv2di ((int64x2_t) __a, __b); + return __builtin_aarch64_lshrv2di_uus (__a, __b); } __extension__ extern __inline int64_t diff --git a/gcc/testsuite/gcc.target/aarch64/signbit-2.c b/gcc/testsuite/gcc.target/aarch64/signbit-2.c new file mode 100644 index 0000000000000000000000000000000000000000..e4e9afc854317cb599fa8118a1117c5a52e6f497 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/signbit-2.c @@ -0,0 +1,36 @@ +/* { dg-do assemble } */ +/* { dg-options "-O1 --save-temps" } */ + +#include + +int32x2_t foo1 (int32x2_t a) +{ + return vshr_n_s32 (vneg_s32 (a), 31); +} + +int32x4_t foo2 (int32x4_t a) +{ + return vshrq_n_s32 (vnegq_s32 (a), 31); +} + +int16x8_t foo3 (int16x8_t a) +{ + return vshrq_n_s16 (vnegq_s16 (a), 15); +} + +int16x4_t foo4 (int16x4_t a) +{ + return vshr_n_s16 (vneg_s16 (a), 15); +} + +int8x16_t foo5 (int8x16_t a) +{ + return vshrq_n_s8 (vnegq_s8 (a), 7); +} + +int8x8_t foo6 (int8x8_t a) +{ + return vshr_n_s8 (vneg_s8 (a), 7); +} + +/* { dg-final { scan-assembler-times {\tcmgt\t} 6 } } */