| 1 |
dnl PowerPC-64/mode32 mpn_add_n -- Add two limb vectors of the same length > 0 |
| 2 |
dnl and store sum in a third limb vector. |
| 3 |
|
| 4 |
dnl Copyright 1999-2001, 2003, 2005 Free Software Foundation, Inc. |
| 5 |
|
| 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 modify |
| 9 |
dnl it under the terms of either: |
| 10 |
dnl |
| 11 |
dnl * the GNU Lesser General Public License as published by the Free |
| 12 |
dnl Software Foundation; either version 3 of the License, or (at your |
| 13 |
dnl option) any later version. |
| 14 |
dnl |
| 15 |
dnl or |
| 16 |
dnl |
| 17 |
dnl * the GNU General Public License as published by the Free Software |
| 18 |
dnl Foundation; either version 2 of the License, or (at your option) any |
| 19 |
dnl later version. |
| 20 |
dnl |
| 21 |
dnl or both in parallel, as here. |
| 22 |
dnl |
| 23 |
dnl The GNU MP Library is distributed in the hope that it will be useful, but |
| 24 |
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
| 25 |
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
| 26 |
dnl for more details. |
| 27 |
dnl |
| 28 |
dnl You should have received copies of the GNU General Public License and the |
| 29 |
dnl GNU Lesser General Public License along with the GNU MP Library. If not, |
| 30 |
dnl see https://www.gnu.org/licenses/. |
| 31 |
|
| 32 |
include(`../config.m4') |
| 33 |
|
| 34 |
C cycles/limb |
| 35 |
C POWER3/PPC630: ? |
| 36 |
C POWER4/PPC970: 4.25 |
| 37 |
|
| 38 |
C INPUT PARAMETERS |
| 39 |
C rp r3 |
| 40 |
C up r4 |
| 41 |
C vp r5 |
| 42 |
C n r6 |
| 43 |
|
| 44 |
ASM_START() |
| 45 |
PROLOGUE(mpn_add_n) |
| 46 |
mtctr r6 C copy size into CTR |
| 47 |
addic r0, r0, 0 C clear cy |
| 48 |
ld r8, 0(r4) C load least significant s1 limb |
| 49 |
ld r0, 0(r5) C load least significant s2 limb |
| 50 |
addi r3, r3, -8 C offset res_ptr, it's updated before it's used |
| 51 |
bdz L(end) C If done, skip loop |
| 52 |
|
| 53 |
L(oop): ld r9, 8(r4) C load s1 limb |
| 54 |
ld r10, 8(r5) C load s2 limb |
| 55 |
adde r7, r0, r8 C add limbs with cy, set cy |
| 56 |
srdi r6, r0, 32 |
| 57 |
srdi r11, r8, 32 |
| 58 |
adde r6, r6, r11 C add high limb parts, set cy |
| 59 |
std r7, 8(r3) C store result limb |
| 60 |
bdz L(exit) C decrement CTR and exit if done |
| 61 |
ldu r8, 16(r4) C load s1 limb and update s1_ptr |
| 62 |
ldu r0, 16(r5) C load s2 limb and update s2_ptr |
| 63 |
adde r7, r10, r9 C add limbs with cy, set cy |
| 64 |
srdi r6, r10, 32 |
| 65 |
srdi r11, r9, 32 |
| 66 |
adde r6, r6, r11 C add high limb parts, set cy |
| 67 |
stdu r7, 16(r3) C store result limb and update res_ptr |
| 68 |
bdnz L(oop) C decrement CTR and loop back |
| 69 |
|
| 70 |
L(end): adde r7, r0, r8 |
| 71 |
srdi r6, r0, 32 |
| 72 |
srdi r11, r8, 32 |
| 73 |
adde r6, r6, r11 C add limbs with cy, set cy |
| 74 |
std r7, 8(r3) C store ultimate result limb |
| 75 |
li r3, 0 C load cy into ... |
| 76 |
addze r4, r3 C ... return value register |
| 77 |
blr |
| 78 |
L(exit): adde r7, r10, r9 |
| 79 |
srdi r6, r10, 32 |
| 80 |
srdi r11, r9, 32 |
| 81 |
adde r6, r6, r11 C add limbs with cy, set cy |
| 82 |
std r7, 16(r3) |
| 83 |
li r3, 0 C load cy into ... |
| 84 |
addze r4, r3 C ... return value register |
| 85 |
blr |
| 86 |
EPILOGUE() |