diff options
author | Alexandra Hajkova <alexandra@khirnov.net> | 2016-12-11 12:10:19 +0100 |
---|---|---|
committer | Diego Biurrun <diego@biurrun.de> | 2016-12-12 09:25:16 +0100 |
commit | b0e6b3f4777910d61083976aa9fc78a1e0731aae (patch) | |
tree | 5ee56e64ea7481c8c05f6dea539d82e0287e8006 /libavcodec/ppc/hevcdsp_template.c | |
parent | fc368497f2fff54ddf5316224c573c9d1939fb25 (diff) | |
download | ffmpeg-b0e6b3f4777910d61083976aa9fc78a1e0731aae.tar.gz |
hevc: ppc: Add HEVC 4x4 IDCT for PowerPC
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Diffstat (limited to 'libavcodec/ppc/hevcdsp_template.c')
-rw-r--r-- | libavcodec/ppc/hevcdsp_template.c | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/libavcodec/ppc/hevcdsp_template.c b/libavcodec/ppc/hevcdsp_template.c new file mode 100644 index 0000000000..a68ee18dbb --- /dev/null +++ b/libavcodec/ppc/hevcdsp_template.c @@ -0,0 +1,48 @@ +/* + * Copyright (c) Alexandra Hajkova + * + * 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 + */ + +static void FUNC(ff_hevc_idct_4x4, BIT_DEPTH)(int16_t *coeffs, int col_limit) +{ + const int shift = 7; + const int shift2 = 20 - BIT_DEPTH; + vector int16_t src_01, src_23; + vector int32_t res[4]; + vector int16_t res_packed[2]; + + src_01 = vec_ld(0, coeffs); + src_23 = vec_ld(16, coeffs); + + transform4x4(src_01, src_23, res, shift, coeffs); + src_01 = vec_packs(res[0], res[1]); + src_23 = vec_packs(res[2], res[3]); + scale(res, res_packed, shift); + // transpose + src_01 = vec_perm(res_packed[0], res_packed[1], mask[0]); + src_23 = vec_perm(res_packed[0], res_packed[1], mask[1]); + + transform4x4(src_01, src_23, res, shift2, coeffs); + scale(res, res_packed, shift2); + // transpose + src_01 = vec_perm(res_packed[0], res_packed[1], mask[0]); + src_23 = vec_perm(res_packed[0], res_packed[1], mask[1]); + + vec_st(src_01, 0, coeffs); + vec_st(src_23, 16, coeffs); +} |