diff options
Diffstat (limited to 'libavcodec/ppc/hevcdsp.c')
-rw-r--r-- | libavcodec/ppc/hevcdsp.c | 36 |
1 files changed, 26 insertions, 10 deletions
diff --git a/libavcodec/ppc/hevcdsp.c b/libavcodec/ppc/hevcdsp.c index f77943b..c1d562a 100644 --- a/libavcodec/ppc/hevcdsp.c +++ b/libavcodec/ppc/hevcdsp.c @@ -1,20 +1,21 @@ -/* SIMD-optimized IDCT functions for HEVC decoding +/* + * SIMD-optimized IDCT functions for HEVC decoding * Copyright (c) Alexandra Hajkova * - * 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 */ @@ -40,8 +41,9 @@ static const vec_u8 mask[2] = { { 0x04, 0x05, 0x0C, 0x0D, 0x14, 0x15, 0x1C, 0x1D, 0x06, 0x07, 0x0E, 0x0F, 0x16, 0x17, 0x1E, 0x1F }, }; -static void transform4x4(vec_s16 src_01, vec_s16 src_23, vec_s32 res[4], - const int shift, int16_t *coeffs) +static av_always_inline void transform4x4(vec_s16 src_01, vec_s16 src_23, + vec_s32 res[4], const int shift, + int16_t *coeffs) { vec_s16 src_02, src_13; vec_s32 zero = vec_splat_s32(0); @@ -56,7 +58,13 @@ static void transform4x4(vec_s16 src_01, vec_s16 src_23, vec_s32 res[4], e1 = vec_msums(src_02, trans4[2], zero); o1 = vec_msums(src_13, trans4[3], zero); - add = vec_sl(vec_splat_s32(1), vec_splat_u32(shift - 1)); + switch(shift) { + case 7: add = vec_sl(vec_splat_s32(1), vec_splat_u32( 7 - 1)); break; + case 10: add = vec_sl(vec_splat_s32(1), vec_splat_u32(10 - 1)); break; + case 12: add = vec_sl(vec_splat_s32(1), vec_splat_u32(12 - 1)); break; + default: abort(); + } + e0 = vec_add(e0, add); e1 = vec_add(e1, add); @@ -66,10 +74,18 @@ static void transform4x4(vec_s16 src_01, vec_s16 src_23, vec_s32 res[4], res[3] = vec_sub(e0, o0); } -static void scale(vec_s32 res[4], vec_s16 res_packed[2], int shift) +static av_always_inline void scale(vec_s32 res[4], vec_s16 res_packed[2], + const int shift) { int i; - vec_u32 v_shift = vec_splat_u32(shift); + vec_u32 v_shift; + + switch(shift) { + case 7: v_shift = vec_splat_u32(7) ; break; + case 10: v_shift = vec_splat_u32(10); break; + case 12: v_shift = vec_splat_u32(12); break; + default: abort(); + } for (i = 0; i < 4; i++) res[i] = vec_sra(res[i], v_shift); |