diff options
Diffstat (limited to 'libavcodec/arm/mpegvideoencdsp_armv6.S')
| -rw-r--r-- | libavcodec/arm/mpegvideoencdsp_armv6.S | 76 |
1 files changed, 76 insertions, 0 deletions
diff --git a/libavcodec/arm/mpegvideoencdsp_armv6.S b/libavcodec/arm/mpegvideoencdsp_armv6.S new file mode 100644 index 0000000000..99db501b25 --- /dev/null +++ b/libavcodec/arm/mpegvideoencdsp_armv6.S @@ -0,0 +1,76 @@ +/* + * Copyright (c) 2009 Mans Rullgard <mans@mansr.com> + * + * This file is part of Libav. + * + * Libav is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * Libav is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with Libav; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/arm/asm.S" + +function ff_pix_norm1_armv6, export=1 + push {r4-r6, lr} + mov r12, #16 + mov lr, #0 +1: + ldm r0, {r2-r5} + uxtb16 r6, r2 + uxtb16 r2, r2, ror #8 + smlad lr, r6, r6, lr + uxtb16 r6, r3 + smlad lr, r2, r2, lr + uxtb16 r3, r3, ror #8 + smlad lr, r6, r6, lr + uxtb16 r6, r4 + smlad lr, r3, r3, lr + uxtb16 r4, r4, ror #8 + smlad lr, r6, r6, lr + uxtb16 r6, r5 + smlad lr, r4, r4, lr + uxtb16 r5, r5, ror #8 + smlad lr, r6, r6, lr + subs r12, r12, #1 + add r0, r0, r1 + smlad lr, r5, r5, lr + bgt 1b + + mov r0, lr + pop {r4-r6, pc} +endfunc + +function ff_pix_sum_armv6, export=1 + push {r4-r7, lr} + mov r12, #16 + mov r2, #0 + mov r3, #0 + mov lr, #0 + ldr r4, [r0] +1: + subs r12, r12, #1 + ldr r5, [r0, #4] + usada8 r2, r4, lr, r2 + ldr r6, [r0, #8] + usada8 r3, r5, lr, r3 + ldr r7, [r0, #12] + usada8 r2, r6, lr, r2 + beq 2f + ldr_pre r4, r0, r1 + usada8 r3, r7, lr, r3 + bgt 1b +2: + usada8 r3, r7, lr, r3 + add r0, r2, r3 + pop {r4-r7, pc} +endfunc |