Return to addmul_1.S CVS log

Up to [local] / OpenXM_contrib / gmp / mpn / arm

Annotation of OpenXM_contrib/gmp/mpn/arm/addmul_1.S, Revision 1.1.1.1

1.1       maekawa     1: @ ARM mpn_mul_1 -- Multiply a limb vector with a limb and add the result to a
                      2: @ second limb vector.
                      3: @ Contributed by Robert Harley.
                      4:
                      5: @ Copyright (C) 1998, 2000 Free Software Foundation, Inc.
                      6:
                      7: @ This file is part of the GNU MP Library.
                      8:
                      9: @ The GNU MP Library is free software; you can redistribute it and/or modify
                     10: @ it under the terms of the GNU Lesser General Public License as published by
                     11: @ the Free Software Foundation; either version 2.1 of the License, or (at your
                     12: @ option) any later version.
                     13:
                     14: @ The GNU MP Library is distributed in the hope that it will be useful, but
                     15: @ WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
                     16: @ or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
                     17: @ License for more details.
                     18:
                     19: @ You should have received a copy of the GNU Lesser General Public License
                     20: @ along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
                     21: @ the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
                     22: @ MA 02111-1307, USA.
                     23:
                     24: #define p r0
                     25: #define a r1
                     26: #define n r2
                     27: #define w r3
                     28:
                     29: #define z r11
                     30:
                     31: #define ip r12
                     32: #define sp r13
                     33: #define lr r14
                     34: #define pc r15
                     35:
                     36: .text
                     37:        .align  0
                     38:        .global __gmpn_addmul_1
                     39:        .type   __gmpn_addmul_1,%function
                     40: __gmpn_addmul_1:
                     41:        stmfd   sp!, { r8-r11, lr }
                     42:        mov     z, #0
                     43:        mov     ip, #0
                     44:        movs    n, n, lsr #1
                     45:        bcc     skip1
                     46:        ldr     lr, [a], #4
                     47:        ldr     r9, [p]
                     48:        umlal   r9, ip, w, lr
                     49:        str     r9, [p], #4
                     50: skip1:
                     51:        movs    n, n, lsr #1
                     52:        bcc     skip2
                     53:        ldmia   p, { r9, r10 }
                     54:        adds    r8, ip, r9
                     55:        adc     r9, z, #0
                     56:        ldmia   a!, { ip, lr }
                     57:        umlal   r8, r9, w, ip
                     58:        adds    r9, r9, r10
                     59:        adc     ip, z, #0
                     60:        umlal   r9, ip, w, lr
                     61:        stmia   p!, { r8, r9 }
                     62: skip2:
                     63:        teq     n, #0
                     64:        beq     return
                     65:        stmfd   sp!, { r4-r7 }
                     66: addmul_loop:
                     67:        ldmia   p, { r5, r6, r7, r8 }
                     68:        adds    r4, ip, r5
                     69:        adc     r5, z, #0
                     70:        ldmia   a!, { r9, r10, ip, lr }
                     71:        umlal   r4, r5, w, r9
                     72:        adds    r5, r5, r6
                     73:        adc     r6, z, #0
                     74:        umlal   r5, r6, w, r10
                     75:        adds    r6, r6, r7
                     76:        adc     r7, z, #0
                     77:        umlal   r6, r7, w, ip
                     78:        adds    r7, r7, r8
                     79:        adc     ip, z, #0
                     80:        umlal   r7, ip, w, lr
                     81:        subs    n, n, #1
                     82:        stmia   p!, { r4, r5, r6, r7 }
                     83:        bne     addmul_loop
                     84:        ldmfd   sp!, { r4-r7 }
                     85: return:
                     86:        mov     r0, ip
                     87:        ldmfd   sp!, { r8-r11, pc }
                     88: end:
                     89:        .size   __gmpn_addmul_1, end - __gmpn_addmul_1