mirror of
https://sourceware.org/git/glibc.git
synced 2025-11-28 23:44:09 +03:00
476e962af7
To enable “longlong.h” removal, the udiv_qrnnd is moved to a gmp-arch.h
file. It allows each architecture to implement its own arch-specific
optimizations. The generic implementation now uses a static inline,
which provides better type checking than the GNU extension to cast the
asm constraint (and it works better with clang).
Most of the architecture uses the generic implementation, which is
expanded from a macro, except for alpha, x86, m68k, sh, and sparc.
I kept that alpha, which uses out-of-the-line implementations and x86,
where there is no easy way to use the div{q} instruction from C code.
For the rest, the compiler generates good enough code.
The hppa also provides arch-specific implementations, but they are not
routed in “longlong.h” and thus never used.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
57 lines
1.6 KiB
C
57 lines
1.6 KiB
C
/* mpn_mul_1 -- Multiply a limb vector with a single limb and
|
|
store the product in a second limb vector.
|
|
|
|
Copyright (C) 1991-2025 Free Software Foundation, Inc.
|
|
|
|
This file is part of the GNU MP Library.
|
|
|
|
The GNU MP 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 MP 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 MP Library; see the file COPYING.LIB. If not, see
|
|
<https://www.gnu.org/licenses/>. */
|
|
|
|
#include <gmp.h>
|
|
#include "gmp-impl.h"
|
|
#include "longlong.h"
|
|
#include <gmp-arch.h>
|
|
|
|
mp_limb_t
|
|
mpn_mul_1 (register mp_ptr res_ptr, register mp_srcptr s1_ptr,
|
|
mp_size_t s1_size, register mp_limb_t s2_limb)
|
|
{
|
|
register mp_limb_t cy_limb;
|
|
register mp_size_t j;
|
|
register mp_limb_t prod_high, prod_low;
|
|
|
|
/* The loop counter and index J goes from -S1_SIZE to -1. This way
|
|
the loop becomes faster. */
|
|
j = -s1_size;
|
|
|
|
/* Offset the base pointers to compensate for the negative indices. */
|
|
s1_ptr -= j;
|
|
res_ptr -= j;
|
|
|
|
cy_limb = 0;
|
|
do
|
|
{
|
|
umul_ppmm (prod_high, prod_low, s1_ptr[j], s2_limb);
|
|
|
|
prod_low += cy_limb;
|
|
cy_limb = (prod_low < cy_limb) + prod_high;
|
|
|
|
res_ptr[j] = prod_low;
|
|
}
|
|
while (++j != 0);
|
|
|
|
return cy_limb;
|
|
}
|