diff options
Diffstat (limited to 'libavcodec/ppc/vc1dsp_altivec.c')
| -rw-r--r-- | libavcodec/ppc/vc1dsp_altivec.c | 29 |
1 files changed, 18 insertions, 11 deletions
diff --git a/libavcodec/ppc/vc1dsp_altivec.c b/libavcodec/ppc/vc1dsp_altivec.c index fc82502..bbadb2a 100644 --- a/libavcodec/ppc/vc1dsp_altivec.c +++ b/libavcodec/ppc/vc1dsp_altivec.c @@ -2,20 +2,20 @@ * VC-1 and WMV3 decoder - DSP functions AltiVec-optimized * Copyright (c) 2006 Konstantin Shishkov * - * 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 */ @@ -28,7 +28,7 @@ #include "libavcodec/vc1dsp.h" -#if HAVE_ALTIVEC && HAVE_BIGENDIAN +#if HAVE_ALTIVEC // main steps of 8x8 transform #define STEP8(s0, s1, s2, s3, s4, s5, s6, s7, vec_rnd) \ @@ -306,16 +306,23 @@ static void vc1_inv_trans_8x4_altivec(uint8_t *dest, ptrdiff_t stride, src2 = vec_pack(s2, sA); src3 = vec_pack(s3, sB); +#if HAVE_BIGENDIAN p0 = vec_lvsl (0, dest); p1 = vec_lvsl (stride, dest); p = vec_splat_u8 (-1); perm0 = vec_mergeh (p, p0); perm1 = vec_mergeh (p, p1); +#define GET_TMP2(dst, p) \ + tmp = vec_ld (0, dest); \ + tmp2 = (vector signed short)vec_perm (tmp, vec_splat_u8(0), p); +#else +#define GET_TMP2(dst,p) \ + tmp = vec_vsx_ld (0, dst); \ + tmp2 = (vector signed short)vec_mergeh (tmp, vec_splat_u8(0)); +#endif #define ADD(dest,src,perm) \ - /* *(uint64_t *)&tmp = *(uint64_t *)dest; */ \ - tmp = vec_ld (0, dest); \ - tmp2 = (vector signed short)vec_perm (tmp, vec_splat_u8(0), perm); \ + GET_TMP2(dest, perm); \ tmp3 = vec_adds (tmp2, src); \ tmp = vec_packsu (tmp3, tmp3); \ vec_ste ((vector unsigned int)tmp, 0, (unsigned int *)dest); \ @@ -342,11 +349,11 @@ static void vc1_inv_trans_8x4_altivec(uint8_t *dest, ptrdiff_t stride, #undef OP_U8_ALTIVEC #undef PREFIX_no_rnd_vc1_chroma_mc8_altivec -#endif /* HAVE_ALTIVEC && HAVE_BIGENDIAN */ +#endif /* HAVE_ALTIVEC */ av_cold void ff_vc1dsp_init_ppc(VC1DSPContext *dsp) { -#if HAVE_ALTIVEC && HAVE_BIGENDIAN +#if HAVE_ALTIVEC if (!PPC_ALTIVEC(av_get_cpu_flags())) return; @@ -354,5 +361,5 @@ av_cold void ff_vc1dsp_init_ppc(VC1DSPContext *dsp) dsp->vc1_inv_trans_8x4 = vc1_inv_trans_8x4_altivec; dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = put_no_rnd_vc1_chroma_mc8_altivec; dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = avg_no_rnd_vc1_chroma_mc8_altivec; -#endif /* HAVE_ALTIVEC && HAVE_BIGENDIAN */ +#endif /* HAVE_ALTIVEC */ } |
