diff options
author | Justin Ruggles <justin.ruggles@gmail.com> | 2012-05-21 20:58:41 +0400 |
---|---|---|
committer | Justin Ruggles <justin.ruggles@gmail.com> | 2012-06-08 21:14:38 +0400 |
commit | d5a7229ba4aabc2b6407c731d9175879ae54c5ea (patch) | |
tree | 0596aaae9622f0f7b7e5d689b20ab3dc82f59897 /libavutil/ppc/float_dsp_altivec.c | |
parent | 98db4e2a4e35ccc2406004216270ceaa1c6a7d00 (diff) |
Add a float DSP framework to libavutil
Move vector_fmul() from DSPContext to AVFloatDSPContext.
Diffstat (limited to 'libavutil/ppc/float_dsp_altivec.c')
-rw-r--r-- | libavutil/ppc/float_dsp_altivec.c | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/libavutil/ppc/float_dsp_altivec.c b/libavutil/ppc/float_dsp_altivec.c new file mode 100644 index 0000000000..f08abc8d6f --- /dev/null +++ b/libavutil/ppc/float_dsp_altivec.c @@ -0,0 +1,37 @@ +/* + * Copyright (c) 2006 Luca Barbato <lu_zero@gentoo.org> + * + * 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 "util_altivec.h" + +void ff_vector_fmul_altivec(float *dst, const float *src0, const float *src1, + int len) +{ + int i; + vector float d0, d1, s, zero = (vector float)vec_splat_u32(0); + for (i = 0; i < len - 7; i += 8) { + d0 = vec_ld( 0, src0 + i); + s = vec_ld( 0, src1 + i); + d1 = vec_ld(16, src0 + i); + d0 = vec_madd(d0, s, zero); + d1 = vec_madd(d1, vec_ld(16, src1 + i), zero); + vec_st(d0, 0, dst + i); + vec_st(d1, 16, dst + i); + } +} |