Return to mul_1.asm CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / x86 / pentium4 / sse2

Annotation of OpenXM_contrib/gmp/mpn/x86/pentium4/sse2/mul_1.asm, Revision 1.1.1.1

1.1       ohara       1: dnl  Intel Pentium-4 mpn_mul_1 -- Multiply a limb vector with a limb and store
                      2: dnl  the result in a second limb vector.
                      3:
                      4: dnl  Copyright 2001, 2002 Free Software Foundation, Inc.
                      5: dnl
                      6: dnl  This file is part of the GNU MP Library.
                      7: dnl
                      8: dnl  The GNU MP Library is free software; you can redistribute it and/or
                      9: dnl  modify it under the terms of the GNU Lesser General Public License as
                     10: dnl  published by the Free Software Foundation; either version 2.1 of the
                     11: dnl  License, or (at your option) any later version.
                     12: dnl
                     13: dnl  The GNU MP Library is distributed in the hope that it will be useful,
                     14: dnl  but WITHOUT ANY WARRANTY; without even the implied warranty of
                     15: dnl  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
                     16: dnl  Lesser General Public License for more details.
                     17: dnl
                     18: dnl  You should have received a copy of the GNU Lesser General Public
                     19: dnl  License along with the GNU MP Library; see the file COPYING.LIB.  If
                     20: dnl  not, write to the Free Software Foundation, Inc., 59 Temple Place -
                     21: dnl  Suite 330, Boston, MA 02111-1307, USA.
                     22:
                     23: include(`../config.m4')
                     24:
                     25:
                     26: C P4: 4 cycles/limb
                     27:
                     28:
                     29: C mp_limb_t mpn_mul_1 (mp_ptr dst, mp_srcptr src, mp_size_t size,
                     30: C                      mp_limb_t multiplier);
                     31: C mp_limb_t mpn_mul_1c (mp_ptr dst, mp_srcptr src, mp_size_t size,
                     32: C                       mp_limb_t multiplier, mp_limb_t carry);
                     33: C
                     34: C Only the carry limb propagation is on the dependent chain, hence 4 c/l.
                     35:
                     36: defframe(PARAM_CARRY,     20)
                     37: defframe(PARAM_MULTIPLIER,16)
                     38: defframe(PARAM_SIZE,      12)
                     39: defframe(PARAM_SRC,       8)
                     40: defframe(PARAM_DST,       4)
                     41:
                     42:        TEXT
                     43:        ALIGN(16)
                     44: PROLOGUE(mpn_mul_1c)
                     45: deflit(`FRAME',0)
                     46:        movd    PARAM_CARRY, %mm0
                     47:        jmp     L(start_1c)
                     48: EPILOGUE()
                     49:
                     50: PROLOGUE(mpn_mul_1)
                     51: deflit(`FRAME',0)
                     52:        pxor    %mm0, %mm0
                     53: L(start_1c):
                     54:        movl    PARAM_SRC, %eax
                     55:        movd    PARAM_MULTIPLIER, %mm7
                     56:        movl    PARAM_DST, %edx
                     57:        movl    PARAM_SIZE, %ecx
                     58:
                     59: L(top):
                     60:        C eax   src, incrementing
                     61:        C ebx
                     62:        C ecx   counter, size iterations
                     63:        C edx   dst, incrementing
                     64:        C
                     65:        C mm0   carry limb
                     66:        C mm7   multiplier
                     67:
                     68:        movd    (%eax), %mm1
                     69:        addl    $4, %eax
                     70:        pmuludq %mm7, %mm1
                     71:
                     72:        paddq   %mm1, %mm0
                     73:        movd    %mm0, (%edx)
                     74:        addl    $4, %edx
                     75:
                     76:        psrlq   $32, %mm0
                     77:
                     78:        subl    $1, %ecx
                     79:        jnz     L(top)
                     80:
                     81:
                     82:        movd    %mm0, %eax
                     83:        emms
                     84:        ret
                     85:
                     86: EPILOGUE()