| 1 |
dnl S/390-32/esame mpn_mul_basecase. |
| 2 |
|
| 3 |
dnl Copyright 2011 Free Software Foundation, Inc. |
| 4 |
|
| 5 |
dnl This file is part of the GNU MP Library. |
| 6 |
dnl |
| 7 |
dnl The GNU MP Library is free software; you can redistribute it and/or modify |
| 8 |
dnl it under the terms of either: |
| 9 |
dnl |
| 10 |
dnl * the GNU Lesser General Public License as published by the Free |
| 11 |
dnl Software Foundation; either version 3 of the License, or (at your |
| 12 |
dnl option) any later version. |
| 13 |
dnl |
| 14 |
dnl or |
| 15 |
dnl |
| 16 |
dnl * the GNU General Public License as published by the Free Software |
| 17 |
dnl Foundation; either version 2 of the License, or (at your option) any |
| 18 |
dnl later version. |
| 19 |
dnl |
| 20 |
dnl or both in parallel, as here. |
| 21 |
dnl |
| 22 |
dnl The GNU MP Library is distributed in the hope that it will be useful, but |
| 23 |
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
| 24 |
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
| 25 |
dnl for more details. |
| 26 |
dnl |
| 27 |
dnl You should have received copies of the GNU General Public License and the |
| 28 |
dnl GNU Lesser General Public License along with the GNU MP Library. If not, |
| 29 |
dnl see https://www.gnu.org/licenses/. |
| 30 |
|
| 31 |
include(`../config.m4') |
| 32 |
|
| 33 |
C cycles/limb |
| 34 |
C z900 ? |
| 35 |
C z990 ? |
| 36 |
C z9 ? |
| 37 |
C z10 ? |
| 38 |
C z196 ? |
| 39 |
|
| 40 |
C TODO |
| 41 |
C * Perhaps add special case for un <= 2. |
| 42 |
C * Replace loops by faster code. The mul_1 and addmul_1 loops could be sped |
| 43 |
C up by about 10%. |
| 44 |
|
| 45 |
C INPUT PARAMETERS |
| 46 |
define(`rp', `%r2') |
| 47 |
define(`up', `%r3') |
| 48 |
define(`un', `%r4') |
| 49 |
define(`vp', `%r5') |
| 50 |
define(`vn', `%r6') |
| 51 |
|
| 52 |
define(`zero', `%r8') |
| 53 |
|
| 54 |
ASM_START() |
| 55 |
PROLOGUE(mpn_mul_basecase) |
| 56 |
chi un, 2 |
| 57 |
jhe L(ge2) |
| 58 |
|
| 59 |
C un = vn = 1 |
| 60 |
l %r1, 0(vp) |
| 61 |
ml %r0, 0(up) |
| 62 |
st %r1, 0(rp) |
| 63 |
st %r0, 4(rp) |
| 64 |
br %r14 |
| 65 |
|
| 66 |
L(ge2): C jne L(gen) |
| 67 |
|
| 68 |
|
| 69 |
L(gen): |
| 70 |
C mul_1 ======================================================================= |
| 71 |
|
| 72 |
stm %r6, %r12, 24(%r15) |
| 73 |
lhi zero, 0 |
| 74 |
ahi un, -1 |
| 75 |
|
| 76 |
l %r7, 0(vp) |
| 77 |
l %r11, 0(up) |
| 78 |
lhi %r12, 4 C init index register |
| 79 |
mlr %r10, %r7 |
| 80 |
lr %r9, un |
| 81 |
st %r11, 0(rp) |
| 82 |
cr %r15, %r15 C clear carry flag |
| 83 |
|
| 84 |
L(tm): l %r1, 0(%r12,up) |
| 85 |
mlr %r0, %r7 |
| 86 |
alcr %r1, %r10 |
| 87 |
lr %r10, %r0 C copy high part to carry limb |
| 88 |
st %r1, 0(%r12,rp) |
| 89 |
la %r12, 4(%r12) |
| 90 |
brct %r9, L(tm) |
| 91 |
|
| 92 |
alcr %r0, zero |
| 93 |
st %r0, 0(%r12,rp) |
| 94 |
|
| 95 |
C addmul_1 loop =============================================================== |
| 96 |
|
| 97 |
ahi vn, -1 |
| 98 |
je L(outer_end) |
| 99 |
L(outer_loop): |
| 100 |
|
| 101 |
la rp, 4(rp) C rp += 1 |
| 102 |
la vp, 4(vp) C up += 1 |
| 103 |
l %r7, 0(vp) |
| 104 |
l %r11, 0(up) |
| 105 |
lhi %r12, 4 C init index register |
| 106 |
mlr %r10, %r7 |
| 107 |
lr %r9, un |
| 108 |
al %r11, 0(rp) |
| 109 |
st %r11, 0(rp) |
| 110 |
|
| 111 |
L(tam): l %r1, 0(%r12,up) |
| 112 |
l %r11, 0(%r12,rp) |
| 113 |
mlr %r0, %r7 |
| 114 |
alcr %r1, %r11 |
| 115 |
alcr %r0, zero |
| 116 |
alr %r1, %r10 |
| 117 |
lr %r10, %r0 |
| 118 |
st %r1, 0(%r12,rp) |
| 119 |
la %r12, 4(%r12) |
| 120 |
brct %r9, L(tam) |
| 121 |
|
| 122 |
alcr %r0, zero |
| 123 |
st %r0, 0(%r12,rp) |
| 124 |
|
| 125 |
brct vn, L(outer_loop) |
| 126 |
L(outer_end): |
| 127 |
|
| 128 |
lm %r6, %r12, 24(%r15) |
| 129 |
br %r14 |
| 130 |
EPILOGUE() |