glibc/sysdeps/generic/string-fzi.h

72 lines
1.9 KiB
C
Raw Normal View History

Add string vectorized find and detection functions This patch adds generic string find and detection meant to be used in generic vectorized string implementation. The idea is to decompose the basic string operation so each architecture can reimplement if it provides any specialized hardware instruction. The 'string-misc.h' provides miscellaneous functions: - extractbyte: extracts the byte from an specific index. - repeat_bytes: setup an word by replicate the argument on each byte. The 'string-fza.h' provides zero byte detection functions: - find_zero_low, find_zero_all, find_eq_low, find_eq_all, find_zero_eq_low, find_zero_eq_all, and find_zero_ne_all The 'string-fzb.h' provides boolean zero byte detection functions: - has_zero: determine if any byte within a word is zero. - has_eq: determine byte equality between two words. - has_zero_eq: determine if any byte within a word is zero along with byte equality between two words. The 'string-fzi.h' provides positions for string-fza.h results: - index_first: return index of first zero byte within a word. - index_last: return index of first byte different between two words. The 'string-fzc.h' provides a combined version of fza and fzi: - index_first_zero_eq: return index of first zero byte within a word or first byte different between two words. - index_first_zero_ne: return index of first zero byte within a word or first byte equal between two words. - index_last_zero: return index of last zero byte within a word. - index_last_eq: return index of last byte different between two words. The 'string-shift.h' provides a way to mask off parts of a work based on some alignmnet (to handle unaligned arguments): - shift_find, shift_find_last. Co-authored-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
2023-01-10 21:00:53 +00:00
/* Zero byte detection; indexes. Generic C version.
Copyright (C) 2023-2024 Free Software Foundation, Inc.
Add string vectorized find and detection functions This patch adds generic string find and detection meant to be used in generic vectorized string implementation. The idea is to decompose the basic string operation so each architecture can reimplement if it provides any specialized hardware instruction. The 'string-misc.h' provides miscellaneous functions: - extractbyte: extracts the byte from an specific index. - repeat_bytes: setup an word by replicate the argument on each byte. The 'string-fza.h' provides zero byte detection functions: - find_zero_low, find_zero_all, find_eq_low, find_eq_all, find_zero_eq_low, find_zero_eq_all, and find_zero_ne_all The 'string-fzb.h' provides boolean zero byte detection functions: - has_zero: determine if any byte within a word is zero. - has_eq: determine byte equality between two words. - has_zero_eq: determine if any byte within a word is zero along with byte equality between two words. The 'string-fzi.h' provides positions for string-fza.h results: - index_first: return index of first zero byte within a word. - index_last: return index of first byte different between two words. The 'string-fzc.h' provides a combined version of fza and fzi: - index_first_zero_eq: return index of first zero byte within a word or first byte different between two words. - index_first_zero_ne: return index of first zero byte within a word or first byte equal between two words. - index_last_zero: return index of last zero byte within a word. - index_last_eq: return index of last byte different between two words. The 'string-shift.h' provides a way to mask off parts of a work based on some alignmnet (to handle unaligned arguments): - shift_find, shift_find_last. Co-authored-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
2023-01-10 21:00:53 +00:00
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
<http://www.gnu.org/licenses/>. */
#ifndef _STRING_FZI_H
#define _STRING_FZI_H 1
#include <limits.h>
#include <endian.h>
#include <string-fza.h>
static __always_inline int
clz (find_t c)
{
if (sizeof (find_t) == sizeof (unsigned long))
return __builtin_clzl (c);
else
return __builtin_clzll (c);
}
static __always_inline int
ctz (find_t c)
{
if (sizeof (find_t) == sizeof (unsigned long))
return __builtin_ctzl (c);
else
return __builtin_ctzll (c);
}
/* A subroutine for the index_zero functions. Given a test word C, return
the (memory order) index of the first byte (in memory order) that is
non-zero. */
static __always_inline unsigned int
index_first (find_t c)
{
int r;
if (__BYTE_ORDER == __LITTLE_ENDIAN)
r = ctz (c);
else
r = clz (c);
return r / CHAR_BIT;
}
/* Similarly, but return the (memory order) index of the last byte that is
non-zero. */
static __always_inline unsigned int
index_last (find_t c)
{
int r;
if (__BYTE_ORDER == __LITTLE_ENDIAN)
r = clz (c);
else
r = ctz (c);
return sizeof (find_t) - 1 - (r / CHAR_BIT);
}
#endif /* STRING_FZI_H */