dnl IA-64 mpn_submul_1 -- Multiply a limb vector with a limb and subtract the
dnl result from a second limb vector.
dnl Contributed to the GNU project by Torbjorn Granlund.
dnl Copyright 2000-2004 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C Itanium: 4.0
C Itanium 2: 2.25 (alignment dependent, sometimes it seems to need 3 c/l)
C TODO
C * Optimize feed-in and wind-down code, both for speed andcode size.
C * Handle low limb input and results specially, using a common stf8 in the
C epilogue.
C * Delay r8, r10 initialization, put cmp-p6 in 1st bundle and br .Ldone in
C 2nd bundle. This will allow the bbb bundle to be one cycle earlier and
C save a cycle.
ifdef(`HAVE_ABI_32',
` addp4 rp = 0, rp C M I
addp4 up = 0, up C M I
zxt4 n = n C I ;; ')
{.mmi mov r10 = rp C M I mov r9 = up C M I sub vl = r0, vl C M I negate vl
}
{.mmi
ldf8 f8 = [rp], 8 C M
ldf8 f7 = [up], 8 C M add r19 = -1, n C M I n - 1 ;;
}
{.mmi cmp.eq p6, p0 = 0, vl C M I mov r8 = 0 C M I zero cylimb mov r2 = ar.lc C I0
}
{.mmi
setf.sig f6 = vl C M2 M3 and r14 = 3, n C M I shr.u r19 = r19, 2 C I0 ;;
}
{.mmb nop0 cmp.eq p10, p0 = 0, r14 C M I
(p6) br.spnt .Ldone C B vl == 0
}
{.mmi cmp.eq p11, p0 = 2, r14 C M I cmp.eq p12, p0 = 3, r14 C M I mov ar.lc = r19 C I0
}
{.bbb
(p10) br.dptk .Lb00 C B
(p11) br.dptk .Lb10 C B
(p12) br.dptk .Lb11 C B ;;
}
.Lb01: br.cloop.dptk .grt1
xma.l f39 = f7, f6, f8
xma.hu f43 = f7, f6, f8 ;;
getf.sig r27 = f39 C lo
getf.sig r31 = f43 C hi
ld8 r20 = [r9], 8
br .Lcj1
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.16Bemerkung:
(vorverarbeitet am 2026-10-01)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.