| 1 | /* Add two limb vectors of equal, non-zero length for PowerPC. |
|---|
| 2 | Copyright (C) 1997-2024 Free Software Foundation, Inc. |
|---|
| 3 | This file is part of the GNU C Library. |
|---|
| 4 | |
|---|
| 5 | The GNU C Library is free software; you can redistribute it and/or |
|---|
| 6 | modify it under the terms of the GNU Lesser General Public |
|---|
| 7 | License as published by the Free Software Foundation; either |
|---|
| 8 | version 2.1 of the License, or (at your option) any later version. |
|---|
| 9 | |
|---|
| 10 | The GNU C Library is distributed in the hope that it will be useful, |
|---|
| 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
|---|
| 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
|---|
| 13 | Lesser General Public License for more details. |
|---|
| 14 | |
|---|
| 15 | You should have received a copy of the GNU Lesser General Public |
|---|
| 16 | License along with the GNU C Library; if not, see |
|---|
| 17 | <https://www.gnu.org/licenses/>. */ |
|---|
| 18 | |
|---|
| 19 | #include <sysdep.h> |
|---|
| 20 | |
|---|
| 21 | /* mp_limb_t mpn_add_n (mp_ptr res_ptr, mp_srcptr s1_ptr, mp_srcptr s2_ptr, |
|---|
| 22 | mp_size_t size) |
|---|
| 23 | Calculate s1+s2 and put result in res_ptr; return carry, 0 or 1. */ |
|---|
| 24 | |
|---|
| 25 | /* Note on optimisation: This code is optimal for the 601. Almost every other |
|---|
| 26 | possible 2-unrolled inner loop will not be. Also, watch out for the |
|---|
| 27 | alignment... */ |
|---|
| 28 | |
|---|
| 29 | EALIGN (__mpn_add_n, 3, 0) |
|---|
| 30 | |
|---|
| 31 | /* Set up for loop below. */ |
|---|
| 32 | mtcrf 0x01,r6 |
|---|
| 33 | srwi. r7,r6,1 |
|---|
| 34 | li r10,0 |
|---|
| 35 | mtctr r7 |
|---|
| 36 | bt 31,L(2) |
|---|
| 37 | |
|---|
| 38 | /* Clear the carry. */ |
|---|
| 39 | addic r0,r0,0 |
|---|
| 40 | /* Adjust pointers for loop. */ |
|---|
| 41 | addi r3,r3,-4 |
|---|
| 42 | addi r4,r4,-4 |
|---|
| 43 | addi r5,r5,-4 |
|---|
| 44 | b L(0) |
|---|
| 45 | |
|---|
| 46 | L(2): lwz r7,0(r5) |
|---|
| 47 | lwz r6,0(r4) |
|---|
| 48 | addc r6,r6,r7 |
|---|
| 49 | stw r6,0(r3) |
|---|
| 50 | beq L(1) |
|---|
| 51 | |
|---|
| 52 | /* The loop. */ |
|---|
| 53 | |
|---|
| 54 | /* Align start of loop to an odd word boundary to guarantee that the |
|---|
| 55 | last two words can be fetched in one access (for 601). */ |
|---|
| 56 | L(0): lwz r9,4(r4) |
|---|
| 57 | lwz r8,4(r5) |
|---|
| 58 | lwzu r6,8(r4) |
|---|
| 59 | lwzu r7,8(r5) |
|---|
| 60 | adde r8,r9,r8 |
|---|
| 61 | stw r8,4(r3) |
|---|
| 62 | adde r6,r6,r7 |
|---|
| 63 | stwu r6,8(r3) |
|---|
| 64 | bdnz L(0) |
|---|
| 65 | /* Return the carry. */ |
|---|
| 66 | L(1): addze r3,r10 |
|---|
| 67 | blr |
|---|
| 68 | END (__mpn_add_n) |
|---|
| 69 | |
|---|
