From 8beb9a0dc9e0a11bd582bfaef8cbed5a38adc8a1 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 8 Jul 2016 15:26:51 +0000 Subject: [AArch64] Use fmin/fmax for v[min|max]nm{q} intrinsics smin/smax will actually honor quiet NaN. gcc/ * config/aarch64/aarch64-simd-builtins.def (smax): Remove float variants. (smin): Likewise. (fmax): New entry. (fmin): Likewise. * config/aarch64/arm_neon.h (vmaxnm_f32): Use __builtin_aarch64_fmaxv2sf. (vmaxnmq_f32): Likewise. (vmaxnmq_f64): Likewise. (vminnm_f32): Likewise. (vminnmq_f32): Likewise. (vminnmq_f64): Likewise. gcc/testsuite/ * gcc.target/aarch64/simd/vminmaxnm_1.c: New. From-SVN: r238166 --- gcc/config/aarch64/aarch64-simd-builtins.def | 8 ++++++-- gcc/config/aarch64/arm_neon.h | 12 ++++++------ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'gcc/config') diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def index 3e4740c..f1ad325 100644 --- a/gcc/config/aarch64/aarch64-simd-builtins.def +++ b/gcc/config/aarch64/aarch64-simd-builtins.def @@ -244,13 +244,17 @@ /* Implemented by 3. smax variants map to fmaxnm, smax_nan variants map to fmax. */ - BUILTIN_VDQIF (BINOP, smax, 3) - BUILTIN_VDQIF (BINOP, smin, 3) + BUILTIN_VDQ_BHSI (BINOP, smax, 3) + BUILTIN_VDQ_BHSI (BINOP, smin, 3) BUILTIN_VDQ_BHSI (BINOP, umax, 3) BUILTIN_VDQ_BHSI (BINOP, umin, 3) BUILTIN_VDQF (BINOP, smax_nan, 3) BUILTIN_VDQF (BINOP, smin_nan, 3) + /* Implemented by 3. */ + BUILTIN_VDQF (BINOP, fmax, 3) + BUILTIN_VDQF (BINOP, fmin, 3) + /* Implemented by aarch64_p. */ BUILTIN_VDQ_BHSI (BINOP, smaxp, 0) BUILTIN_VDQ_BHSI (BINOP, sminp, 0) diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h index ed24b59..b0ab1d3 100644 --- a/gcc/config/aarch64/arm_neon.h +++ b/gcc/config/aarch64/arm_neon.h @@ -17588,19 +17588,19 @@ vpminnms_f32 (float32x2_t a) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vmaxnm_f32 (float32x2_t __a, float32x2_t __b) { - return __builtin_aarch64_smaxv2sf (__a, __b); + return __builtin_aarch64_fmaxv2sf (__a, __b); } __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vmaxnmq_f32 (float32x4_t __a, float32x4_t __b) { - return __builtin_aarch64_smaxv4sf (__a, __b); + return __builtin_aarch64_fmaxv4sf (__a, __b); } __extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) vmaxnmq_f64 (float64x2_t __a, float64x2_t __b) { - return __builtin_aarch64_smaxv2df (__a, __b); + return __builtin_aarch64_fmaxv2df (__a, __b); } /* vmaxv */ @@ -17818,19 +17818,19 @@ vminq_u32 (uint32x4_t __a, uint32x4_t __b) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) vminnm_f32 (float32x2_t __a, float32x2_t __b) { - return __builtin_aarch64_sminv2sf (__a, __b); + return __builtin_aarch64_fminv2sf (__a, __b); } __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vminnmq_f32 (float32x4_t __a, float32x4_t __b) { - return __builtin_aarch64_sminv4sf (__a, __b); + return __builtin_aarch64_fminv4sf (__a, __b); } __extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) vminnmq_f64 (float64x2_t __a, float64x2_t __b) { - return __builtin_aarch64_sminv2df (__a, __b); + return __builtin_aarch64_fminv2df (__a, __b); } /* vminv */ -- cgit v1.1