diff options
| author | prathamesh.kulkarni <prathamesh.kulkarni@linaro.org> | 2021-07-12 15:18:21 +0530 |
|---|---|---|
| committer | prathamesh.kulkarni <prathamesh.kulkarni@linaro.org> | 2021-07-12 15:18:21 +0530 |
| commit | 6785eb595981abd93ad85edcfdf1d2e43c0841f5 (patch) | |
| tree | 15a94f749bdb369cd9dad95212224f110333c9c6 /gcc/config/arm | |
| parent | 9b8b37d1b6301855213b8d4860feaeb74d464c6b (diff) | |
| download | gcc-6785eb595981abd93ad85edcfdf1d2e43c0841f5.zip gcc-6785eb595981abd93ad85edcfdf1d2e43c0841f5.tar.gz gcc-6785eb595981abd93ad85edcfdf1d2e43c0841f5.tar.bz2 | |
arm/66791: Replace builtins for unsigned and fp vmul_n intrinsics.
gcc/ChangeLog:
PR target/66791
* config/arm/arm_neon.h (vmul_n_u32): Replace call to builtin with
__a * __b.
(vmulq_n_u32): Likewise.
(vmul_n_f32): Gate __a * __b on __FAST_MATH__.
(vmulq_n_f32): Likewise.
(vmul_n_f16): Likewise.
(vmulq_n_f16): Likewise.
gcc/testsuite/ChangeLog:
PR target/66791
* gcc.target/arm/armv8_2-fp16-neon-2.c: Adjust.
Diffstat (limited to 'gcc/config/arm')
| -rw-r--r-- | gcc/config/arm/arm_neon.h | 24 |
1 files changed, 20 insertions, 4 deletions
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h index f42a15f..41b596b 100644 --- a/gcc/config/arm/arm_neon.h +++ b/gcc/config/arm/arm_neon.h @@ -8384,21 +8384,25 @@ __extension__ extern __inline float32x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmul_n_f32 (float32x2_t __a, float32_t __b) { +#ifdef __FAST_MATH__ + return __a * __b; +#else return (float32x2_t)__builtin_neon_vmul_nv2sf (__a, (__builtin_neon_sf) __b); +#endif } __extension__ extern __inline uint16x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmul_n_u16 (uint16x4_t __a, uint16_t __b) { - return (uint16x4_t)__builtin_neon_vmul_nv4hi ((int16x4_t) __a, (__builtin_neon_hi) __b); + return __a * __b; } __extension__ extern __inline uint32x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmul_n_u32 (uint32x2_t __a, uint32_t __b) { - return (uint32x2_t)__builtin_neon_vmul_nv2si ((int32x2_t) __a, (__builtin_neon_si) __b); + return __a * __b; } __extension__ extern __inline int16x8_t @@ -8419,21 +8423,25 @@ __extension__ extern __inline float32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmulq_n_f32 (float32x4_t __a, float32_t __b) { +#ifdef __FAST_MATH__ + return __a * __b; +#else return (float32x4_t)__builtin_neon_vmul_nv4sf (__a, (__builtin_neon_sf) __b); +#endif } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmulq_n_u16 (uint16x8_t __a, uint16_t __b) { - return (uint16x8_t)__builtin_neon_vmul_nv8hi ((int16x8_t) __a, (__builtin_neon_hi) __b); + return __a * __b; } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmulq_n_u32 (uint32x4_t __a, uint32_t __b) { - return (uint32x4_t)__builtin_neon_vmul_nv4si ((int32x4_t) __a, (__builtin_neon_si) __b); + return __a * __b; } __extension__ extern __inline int32x4_t @@ -17740,7 +17748,11 @@ __extension__ extern __inline float16x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmul_n_f16 (float16x4_t __a, float16_t __b) { +#ifdef __FAST_MATH__ + return __a * __b; +#else return __builtin_neon_vmul_nv4hf (__a, __b); +#endif } __extension__ extern __inline float16x8_t @@ -17765,7 +17777,11 @@ __extension__ extern __inline float16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) vmulq_n_f16 (float16x8_t __a, float16_t __b) { +#ifdef __FAST_MATH__ + return __a * __b; +#else return __builtin_neon_vmul_nv8hf (__a, __b); +#endif } __extension__ extern __inline float16x4_t |