From aed39a3aa3ea68b14dce3395fb14b1416541e6c6 Mon Sep 17 00:00:00 2001 From: Joe Ramsay Date: Wed, 28 Jun 2023 12:19:36 +0100 Subject: aarch64: Add vector implementations of cos routines Replace the loop-over-scalar placeholder routines with optimised implementations from Arm Optimized Routines (AOR). Also add some headers containing utilities for aarch64 libmvec routines, and update libm-test-ulps. Data tables for new routines are used via a pointer with a barrier on it, in order to prevent overly aggressive constant inlining in GCC. This allows a single adrp, combined with offset loads, to be used for every constant in the table. Special-case handlers are marked NOINLINE in order to confine the save/restore overhead of switching from vector to normal calling standard. This way we only incur the extra memory access in the exceptional cases. NOINLINE definitions have been moved to math_private.h in order to reduce duplication. AOR exposes a config option, WANT_SIMD_EXCEPT, to enable selective masking (and later fixing up) of invalid lanes, in order to trigger fp exceptions correctly (AdvSIMD only). This is tested and maintained in AOR, however it is configured off at source level here for performance reasons. We keep the WANT_SIMD_EXCEPT blocks in routine sources to greatly simplify the upstreaming process from AOR to glibc. Reviewed-by: Szabolcs Nagy --- sysdeps/aarch64/fpu/sve_utils.h | 55 ----------------------------------------- 1 file changed, 55 deletions(-) delete mode 100644 sysdeps/aarch64/fpu/sve_utils.h (limited to 'sysdeps/aarch64/fpu/sve_utils.h') diff --git a/sysdeps/aarch64/fpu/sve_utils.h b/sysdeps/aarch64/fpu/sve_utils.h deleted file mode 100644 index 5ce3d2e8d6..0000000000 --- a/sysdeps/aarch64/fpu/sve_utils.h +++ /dev/null @@ -1,55 +0,0 @@ -/* Helpers for SVE vector math functions. - - Copyright (C) 2023 Free Software Foundation, Inc. - This file is part of the GNU C Library. - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, see - . */ - -#include - -#define SV_NAME_F1(fun) _ZGVsMxv_##fun##f -#define SV_NAME_D1(fun) _ZGVsMxv_##fun -#define SV_NAME_F2(fun) _ZGVsMxvv_##fun##f -#define SV_NAME_D2(fun) _ZGVsMxvv_##fun - -static __always_inline svfloat32_t -sv_call_f32 (float (*f) (float), svfloat32_t x, svfloat32_t y, svbool_t cmp) -{ - svbool_t p = svpfirst (cmp, svpfalse ()); - while (svptest_any (cmp, p)) - { - float elem = svclastb_n_f32 (p, 0, x); - elem = (*f) (elem); - svfloat32_t y2 = svdup_n_f32 (elem); - y = svsel_f32 (p, y2, y); - p = svpnext_b32 (cmp, p); - } - return y; -} - -static __always_inline svfloat64_t -sv_call_f64 (double (*f) (double), svfloat64_t x, svfloat64_t y, svbool_t cmp) -{ - svbool_t p = svpfirst (cmp, svpfalse ()); - while (svptest_any (cmp, p)) - { - double elem = svclastb_n_f64 (p, 0, x); - elem = (*f) (elem); - svfloat64_t y2 = svdup_n_f64 (elem); - y = svsel_f64 (p, y2, y); - p = svpnext_b64 (cmp, p); - } - return y; -} -- cgit 1.4.1