diff options
Diffstat (limited to 'libavcodec/arm/vp9mc_neon.S')
-rw-r--r-- | libavcodec/arm/vp9mc_neon.S | 25 |
1 files changed, 11 insertions, 14 deletions
diff --git a/libavcodec/arm/vp9mc_neon.S b/libavcodec/arm/vp9mc_neon.S index 8d43ff1..bd8cda7 100644 --- a/libavcodec/arm/vp9mc_neon.S +++ b/libavcodec/arm/vp9mc_neon.S @@ -1,20 +1,20 @@ /* * Copyright (c) 2016 Google Inc. * - * This file is part of Libav. + * This file is part of FFmpeg. * - * Libav is free software; you can redistribute it and/or + * FFmpeg 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, + * FFmpeg 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 + * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ @@ -286,8 +286,7 @@ function \type\()_8tap_\size\()h_\idx1\idx2 sub r3, r3, #8 .endif @ Load the filter vector - vld1.8 {d0}, [r12,:64] - vmovl.s8 q0, d0 + vld1.16 {q0}, [r12,:128] 1: .if \size >= 16 mov r12, r5 @@ -416,9 +415,9 @@ function ff_vp9_\type\()_\filter\()\size\()_h_neon, export=1 ldr r5, [sp, #20] .endif movrelx r12, X(ff_vp9_subpel_filters), r6 - add r12, r12, 120*\offset - 8 + add r12, r12, 256*\offset cmp r5, #8 - add r12, r12, r5, lsl #3 + add r12, r12, r5, lsl #4 mov r5, #\size .if \size >= 16 bge \type\()_8tap_16h_34 @@ -551,8 +550,7 @@ do_8tap_h_filters 4 function \type\()_8tap_8v_\idx1\idx2 sub r2, r2, r3, lsl #1 sub r2, r2, r3 - vld1.8 {d0}, [r12, :64] - vmovl.s8 q0, d0 + vld1.16 {q0}, [r12, :128] 1: mov r12, r4 @@ -622,8 +620,7 @@ do_8tap_8v avg, 4, 3 function \type\()_8tap_4v_\idx1\idx2 sub r2, r2, r3, lsl #1 sub r2, r2, r3 - vld1.8 {d0}, [r12, :64] - vmovl.s8 q0, d0 + vld1.16 {q0}, [r12, :128] vld1.32 {d2[]}, [r2], r3 vld1.32 {d3[]}, [r2], r3 @@ -693,8 +690,8 @@ function ff_vp9_\type\()_\filter\()\size\()_v_neon, export=1 ldr r4, [sp, #72] movrelx r12, X(ff_vp9_subpel_filters), r5 ldr r5, [sp, #80] - add r12, r12, 120*\offset - 8 - add r12, r12, r5, lsl #3 + add r12, r12, 256*\offset + add r12, r12, r5, lsl #4 cmp r5, #8 mov r5, #\size .if \size >= 8 |