diff options
| author | Joe Ramsay <Joe.Ramsay@arm.com> | 2023-11-27 17:02:55 +0000 |
|---|---|---|
| committer | Szabolcs Nagy <szabolcs.nagy@arm.com> | 2023-11-29 15:03:36 +0000 |
| commit | 7b12776584c51dbecb1033e107f6b9f45de47a1b (patch) | |
| tree | e1a1fa3bb711f55a55d6c18b51f8f5945fc0aa4c | |
| parent | bc6d79f4ae99206e7ec7d6a8c5abf26cdefc8bff (diff) | |
| download | glibc-7b12776584c51dbecb1033e107f6b9f45de47a1b.zip glibc-7b12776584c51dbecb1033e107f6b9f45de47a1b.tar.gz glibc-7b12776584c51dbecb1033e107f6b9f45de47a1b.tar.bz2 | |
aarch64: Improve special-case handling in AdvSIMD double-precision libmvec routines
Avoids emitting many saves/restores of vector registers, reduces the
amount of code generated around the scalar fallback.
| -rw-r--r-- | sysdeps/aarch64/fpu/v_math.h | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/sysdeps/aarch64/fpu/v_math.h b/sysdeps/aarch64/fpu/v_math.h index cfc87f8..d286eb8 100644 --- a/sysdeps/aarch64/fpu/v_math.h +++ b/sysdeps/aarch64/fpu/v_math.h @@ -137,7 +137,13 @@ v_lookup_u64 (const uint64_t *tab, uint64x2_t idx) static inline float64x2_t v_call_f64 (double (*f) (double), float64x2_t x, float64x2_t y, uint64x2_t p) { - return (float64x2_t){ p[0] ? f (x[0]) : y[0], p[1] ? f (x[1]) : y[1] }; + double p1 = p[1]; + double x1 = x[1]; + if (__glibc_likely (p[0])) + y[0] = f (x[0]); + if (__glibc_likely (p1)) + y[1] = f (x1); + return y; } static inline float64x2_t v_call2_f64 (double (*f) (double, double), float64x2_t x1, float64x2_t x2, |