| xf.li | bfc6e71 | 2025-02-07 01:54:34 -0800 | [diff] [blame^] | 1 | ! sparc __mpn_rshift -- |
| 2 | ! |
| 3 | ! Copyright (C) 1995-2016 Free Software Foundation, Inc. |
| 4 | ! |
| 5 | ! This file is part of the GNU MP Library. |
| 6 | ! |
| 7 | ! The GNU MP Library is free software; you can redistribute it and/or modify |
| 8 | ! it under the terms of the GNU Lesser General Public License as published by |
| 9 | ! the Free Software Foundation; either version 2.1 of the License, or (at your |
| 10 | ! option) any later version. |
| 11 | ! |
| 12 | ! The GNU MP Library is distributed in the hope that it will be useful, but |
| 13 | ! WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
| 14 | ! or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public |
| 15 | ! License for more details. |
| 16 | ! |
| 17 | ! You should have received a copy of the GNU Lesser General Public License |
| 18 | ! along with the GNU MP Library; see the file COPYING.LIB. If not, |
| 19 | ! see <http://www.gnu.org/licenses/>. |
| 20 | |
| 21 | |
| 22 | ! INPUT PARAMETERS |
| 23 | ! RES_PTR %o0 |
| 24 | ! SRC_PTR %o1 |
| 25 | ! SIZE %o2 |
| 26 | ! CNT %o3 |
| 27 | |
| 28 | #include <sysdep.h> |
| 29 | |
| 30 | ENTRY(__mpn_rshift) |
| 31 | ld [%o1],%g2 ! load first limb |
| 32 | sub %g0,%o3,%o5 ! negate shift count |
| 33 | add %o2,-1,%o2 |
| 34 | andcc %o2,4-1,%g4 ! number of limbs in first loop |
| 35 | sll %g2,%o5,%g1 ! compute function result |
| 36 | be LOC(0) ! if multiple of 4 limbs, skip first loop |
| 37 | st %g1,[%sp+80] |
| 38 | |
| 39 | sub %o2,%g4,%o2 ! adjust count for main loop |
| 40 | |
| 41 | LOC(loop0): |
| 42 | ld [%o1+4],%g3 |
| 43 | add %o0,4,%o0 |
| 44 | add %o1,4,%o1 |
| 45 | addcc %g4,-1,%g4 |
| 46 | srl %g2,%o3,%o4 |
| 47 | sll %g3,%o5,%g1 |
| 48 | mov %g3,%g2 |
| 49 | or %o4,%g1,%o4 |
| 50 | bne LOC(loop0) |
| 51 | st %o4,[%o0-4] |
| 52 | |
| 53 | LOC(0): tst %o2 |
| 54 | be LOC(end) |
| 55 | nop |
| 56 | |
| 57 | LOC(loop): |
| 58 | ld [%o1+4],%g3 |
| 59 | add %o0,16,%o0 |
| 60 | addcc %o2,-4,%o2 |
| 61 | srl %g2,%o3,%o4 |
| 62 | sll %g3,%o5,%g1 |
| 63 | |
| 64 | ld [%o1+8],%g2 |
| 65 | srl %g3,%o3,%g4 |
| 66 | or %o4,%g1,%o4 |
| 67 | st %o4,[%o0-16] |
| 68 | sll %g2,%o5,%g1 |
| 69 | |
| 70 | ld [%o1+12],%g3 |
| 71 | srl %g2,%o3,%o4 |
| 72 | or %g4,%g1,%g4 |
| 73 | st %g4,[%o0-12] |
| 74 | sll %g3,%o5,%g1 |
| 75 | |
| 76 | ld [%o1+16],%g2 |
| 77 | srl %g3,%o3,%g4 |
| 78 | or %o4,%g1,%o4 |
| 79 | st %o4,[%o0-8] |
| 80 | sll %g2,%o5,%g1 |
| 81 | |
| 82 | add %o1,16,%o1 |
| 83 | or %g4,%g1,%g4 |
| 84 | bne LOC(loop) |
| 85 | st %g4,[%o0-4] |
| 86 | |
| 87 | LOC(end): |
| 88 | srl %g2,%o3,%g2 |
| 89 | st %g2,[%o0-0] |
| 90 | retl |
| 91 | ld [%sp+80],%o0 |
| 92 | |
| 93 | END(__mpn_rshift) |