| 1 | /* |
| 2 | * simple math operations |
| 3 | * Copyright (c) 2001, 2002 Fabrice Bellard |
| 4 | * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al |
| 5 | * |
| 6 | * This file is part of FFmpeg. |
| 7 | * |
| 8 | * FFmpeg is free software; you can redistribute it and/or |
| 9 | * modify it under the terms of the GNU Lesser General Public |
| 10 | * License as published by the Free Software Foundation; either |
| 11 | * version 2.1 of the License, or (at your option) any later version. |
| 12 | * |
| 13 | * FFmpeg is distributed in the hope that it will be useful, |
| 14 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 15 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 16 | * Lesser General Public License for more details. |
| 17 | * |
| 18 | * You should have received a copy of the GNU Lesser General Public |
| 19 | * License along with FFmpeg; if not, write to the Free Software |
| 20 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 21 | */ |
| 22 | |
| 23 | #ifndef AVCODEC_PPC_MATHOPS_H |
| 24 | #define AVCODEC_PPC_MATHOPS_H |
| 25 | |
| 26 | #include <stdint.h> |
| 27 | #include "config.h" |
| 28 | #include "libavutil/common.h" |
| 29 | |
| 30 | #if HAVE_PPC4XX |
| 31 | /* signed 16x16 -> 32 multiply add accumulate */ |
| 32 | #define MAC16(rt, ra, rb) \ |
| 33 | __asm__ ("maclhw %0, %2, %3" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb)); |
| 34 | |
| 35 | /* signed 16x16 -> 32 multiply */ |
| 36 | #define MUL16(ra, rb) \ |
| 37 | ({ int __rt; \ |
| 38 | __asm__ ("mullhw %0, %1, %2" : "=r" (__rt) : "r" (ra), "r" (rb)); \ |
| 39 | __rt; }) |
| 40 | #endif |
| 41 | |
| 42 | #define MULH MULH |
| 43 | static inline av_const int MULH(int a, int b){ |
| 44 | int r; |
| 45 | __asm__ ("mulhw %0, %1, %2" : "=r"(r) : "r"(a), "r"(b)); |
| 46 | return r; |
| 47 | } |
| 48 | |
| 49 | #if !ARCH_PPC64 |
| 50 | static inline av_const int64_t MAC64(int64_t d, int a, int b) |
| 51 | { |
| 52 | union { uint64_t x; unsigned hl[2]; } x = { d }; |
| 53 | int h, l; |
| 54 | __asm__ ("mullw %3, %4, %5 \n\t" |
| 55 | "mulhw %2, %4, %5 \n\t" |
| 56 | "addc %1, %1, %3 \n\t" |
| 57 | "adde %0, %0, %2 \n\t" |
| 58 | : "+r"(x.hl[0]), "+r"(x.hl[1]), "=&r"(h), "=&r"(l) |
| 59 | : "r"(a), "r"(b)); |
| 60 | return x.x; |
| 61 | } |
| 62 | #define MAC64(d, a, b) ((d) = MAC64(d, a, b)) |
| 63 | |
| 64 | static inline av_const int64_t MLS64(int64_t d, int a, int b) |
| 65 | { |
| 66 | union { uint64_t x; unsigned hl[2]; } x = { d }; |
| 67 | int h, l; |
| 68 | __asm__ ("mullw %3, %4, %5 \n\t" |
| 69 | "mulhw %2, %4, %5 \n\t" |
| 70 | "subfc %1, %3, %1 \n\t" |
| 71 | "subfe %0, %2, %0 \n\t" |
| 72 | : "+r"(x.hl[0]), "+r"(x.hl[1]), "=&r"(h), "=&r"(l) |
| 73 | : "r"(a), "r"(b)); |
| 74 | return x.x; |
| 75 | } |
| 76 | #define MLS64(d, a, b) ((d) = MLS64(d, a, b)) |
| 77 | #endif |
| 78 | |
| 79 | #endif /* AVCODEC_PPC_MATHOPS_H */ |