From 6b695e5c628734b9801fcf53149687cb4fe6926e Mon Sep 17 00:00:00 2001 From: Wilco Dijkstra Date: Tue, 19 Sep 2023 14:03:48 +0100 Subject: AArch64: Remove -0.0 check from vector sin Remove the unnecessary extra checks for sin (-0.0) from vector sin/sinf, improving performance. Passes regress. Reviewed-by: Szabolcs Nagy --- sysdeps/aarch64/fpu/sin_advsimd.c | 7 +------ sysdeps/aarch64/fpu/sinf_advsimd.c | 7 +------ 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/sysdeps/aarch64/fpu/sin_advsimd.c b/sysdeps/aarch64/fpu/sin_advsimd.c index ddc4142..0389b33 100644 --- a/sysdeps/aarch64/fpu/sin_advsimd.c +++ b/sysdeps/aarch64/fpu/sin_advsimd.c @@ -56,7 +56,7 @@ float64x2_t VPCS_ATTR V_NAME_D1 (sin) (float64x2_t x) { const struct data *d = ptr_barrier (&data); float64x2_t n, r, r2, r3, r4, y, t1, t2, t3; - uint64x2_t odd, cmp, eqz; + uint64x2_t odd, cmp; #if WANT_SIMD_EXCEPT /* Detect |x| <= TinyBound or |x| >= RangeVal. If fenv exceptions are to be @@ -70,7 +70,6 @@ float64x2_t VPCS_ATTR V_NAME_D1 (sin) (float64x2_t x) cmp = vcageq_f64 (d->range_val, x); cmp = vceqzq_u64 (cmp); /* cmp = ~cmp. */ #endif - eqz = vceqzq_f64 (x); /* n = rint(|x|/pi). */ n = vfmaq_f64 (d->shift, d->inv_pi, r); @@ -96,10 +95,6 @@ float64x2_t VPCS_ATTR V_NAME_D1 (sin) (float64x2_t x) y = vfmaq_f64 (t3, y, r4); y = vfmaq_f64 (r, y, r3); - /* Sign of 0 is discarded by polynomial, so copy it back here. */ - if (__glibc_unlikely (v_any_u64 (eqz))) - y = vbslq_f64 (eqz, x, y); - if (__glibc_unlikely (v_any_u64 (cmp))) return special_case (x, y, odd, cmp); return vreinterpretq_f64_u64 (veorq_u64 (vreinterpretq_u64_f64 (y), odd)); diff --git a/sysdeps/aarch64/fpu/sinf_advsimd.c b/sysdeps/aarch64/fpu/sinf_advsimd.c index b67d37f..0e78cf5 100644 --- a/sysdeps/aarch64/fpu/sinf_advsimd.c +++ b/sysdeps/aarch64/fpu/sinf_advsimd.c @@ -56,7 +56,7 @@ float32x4_t VPCS_ATTR V_NAME_F1 (sin) (float32x4_t x) { const struct data *d = ptr_barrier (&data); float32x4_t n, r, r2, y; - uint32x4_t odd, cmp, eqz; + uint32x4_t odd, cmp; #if WANT_SIMD_EXCEPT uint32x4_t ir = vreinterpretq_u32_f32 (vabsq_f32 (x)); @@ -70,7 +70,6 @@ float32x4_t VPCS_ATTR V_NAME_F1 (sin) (float32x4_t x) cmp = vcageq_f32 (d->range_val, x); cmp = vceqzq_u32 (cmp); /* cmp = ~cmp. */ #endif - eqz = vceqzq_f32 (x); /* n = rint(|x|/pi) */ n = vfmaq_f32 (d->shift, d->inv_pi, r); @@ -89,10 +88,6 @@ float32x4_t VPCS_ATTR V_NAME_F1 (sin) (float32x4_t x) y = vfmaq_f32 (C (0), y, r2); y = vfmaq_f32 (r, vmulq_f32 (y, r2), r); - /* Sign of 0 is discarded by polynomial, so copy it back here. */ - if (__glibc_unlikely (v_any_u32 (eqz))) - y = vbslq_f32 (eqz, x, y); - if (__glibc_unlikely (v_any_u32 (cmp))) return special_case (x, y, odd, cmp); return vreinterpretq_f32_u32 (veorq_u32 (vreinterpretq_u32_f32 (y), odd)); -- cgit v1.1