X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fppc%2Fvc1dsp_altivec.c;h=6c110dba475cab24ae20cd022934baf63e0109f5;hb=d160a2fb4caa6c4e931b13c87663d8e81dc04882;hp=05edb53b7c7248ffb07cd1ffa9fad48f8485d57c;hpb=381efba0ecedd41575f99ba9e9bd3826551079f6;p=ffmpeg diff --git a/libavcodec/ppc/vc1dsp_altivec.c b/libavcodec/ppc/vc1dsp_altivec.c index 05edb53b7c7..6c110dba475 100644 --- a/libavcodec/ppc/vc1dsp_altivec.c +++ b/libavcodec/ppc/vc1dsp_altivec.c @@ -2,29 +2,28 @@ * VC-1 and WMV3 decoder - DSP functions AltiVec-optimized * Copyright (c) 2006 Konstantin Shishkov * - * This file is part of FFmpeg. + * This file is part of Libav. * - * FFmpeg is free software; you can redistribute it and/or + * 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. * - * FFmpeg is distributed in the hope that it will be useful, + * 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 FFmpeg; if not, write to the Free Software + * License along with Libav; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ +#include "libavutil/ppc/types_altivec.h" +#include "libavutil/ppc/util_altivec.h" #include "libavcodec/dsputil.h" #include "libavcodec/vc1dsp.h" -#include "util_altivec.h" -#include "dsputil_altivec.h" - // main steps of 8x8 transform #define STEP8(s0, s1, s2, s3, s4, s5, s6, s7, vec_rnd) \ do { \ @@ -130,8 +129,7 @@ do { \ /** Do inverse transform on 8x8 block */ -static void vc1_inv_trans_8x8_altivec(DCTELEM block[64], - int sign, int rangered) +static void vc1_inv_trans_8x8_altivec(DCTELEM block[64]) { vector signed short src0, src1, src2, src3, src4, src5, src6, src7; vector signed int s0, s1, s2, s3, s4, s5, s6, s7; @@ -145,9 +143,6 @@ static void vc1_inv_trans_8x8_altivec(DCTELEM block[64], const vector unsigned int vec_2 = vec_splat_u32(2); const vector signed int vec_1s = vec_splat_s32(1); const vector unsigned int vec_1 = vec_splat_u32(1); - const vector unsigned short rangered_shift = vec_splat_u16(1); - const vector signed short signed_bias = vec_sl(vec_splat_s16(4), - vec_splat_u16(4)); src0 = vec_ld( 0, block); src1 = vec_ld( 16, block); @@ -217,27 +212,6 @@ static void vc1_inv_trans_8x8_altivec(DCTELEM block[64], src6 = vec_pack(sE, s6); src7 = vec_pack(sF, s7); - if (rangered) { - if (!sign) { - src0 = vec_sub(src0, signed_bias); - src1 = vec_sub(src1, signed_bias); - src2 = vec_sub(src2, signed_bias); - src3 = vec_sub(src3, signed_bias); - src4 = vec_sub(src4, signed_bias); - src5 = vec_sub(src5, signed_bias); - src6 = vec_sub(src6, signed_bias); - src7 = vec_sub(src7, signed_bias); - } - src0 = vec_sl(src0, rangered_shift); - src1 = vec_sl(src1, rangered_shift); - src2 = vec_sl(src2, rangered_shift); - src3 = vec_sl(src3, rangered_shift); - src4 = vec_sl(src4, rangered_shift); - src5 = vec_sl(src5, rangered_shift); - src6 = vec_sl(src6, rangered_shift); - src7 = vec_sl(src7, rangered_shift); - } - vec_st(src0, 0, block); vec_st(src1, 16, block); vec_st(src2, 32, block); @@ -248,36 +222,6 @@ static void vc1_inv_trans_8x8_altivec(DCTELEM block[64], vec_st(src7,112, block); } -static void vc1_inv_trans_8x8_add_altivec(uint8_t *dest, int stride, DCTELEM *b) -{ - vc1_inv_trans_8x8_altivec(b, 0, 0); - ff_add_pixels_clamped_c(b, dest, stride); -} - -static void vc1_inv_trans_8x8_put_signed_altivec(uint8_t *dest, int stride, DCTELEM *b) -{ - vc1_inv_trans_8x8_altivec(b, 1, 0); - ff_put_signed_pixels_clamped_c(b, dest, stride); -} - -static void vc1_inv_trans_8x8_put_signed_rangered_altivec(uint8_t *dest, int stride, DCTELEM *b) -{ - vc1_inv_trans_8x8_altivec(b, 1, 1); - ff_put_signed_pixels_clamped_c(b, dest, stride); -} - -static void vc1_inv_trans_8x8_put_altivec(uint8_t *dest, int stride, DCTELEM *b) -{ - vc1_inv_trans_8x8_altivec(b, 0, 0); - ff_put_pixels_clamped_c(b, dest, stride); -} - -static void vc1_inv_trans_8x8_put_rangered_altivec(uint8_t *dest, int stride, DCTELEM *b) -{ - vc1_inv_trans_8x8_altivec(b, 0, 1); - ff_put_pixels_clamped_c(b, dest, stride); -} - /** Do inverse transform on 8x4 part of block */ static void vc1_inv_trans_8x4_altivec(uint8_t *dest, int stride, DCTELEM *block) @@ -381,13 +325,13 @@ static void vc1_inv_trans_8x4_altivec(uint8_t *dest, int stride, DCTELEM *block) #define OP_U8_ALTIVEC PUT_OP_U8_ALTIVEC #define PREFIX_no_rnd_vc1_chroma_mc8_altivec put_no_rnd_vc1_chroma_mc8_altivec -#include "h264_template_altivec.c" +#include "h264_altivec_template.c" #undef OP_U8_ALTIVEC #undef PREFIX_no_rnd_vc1_chroma_mc8_altivec #define OP_U8_ALTIVEC AVG_OP_U8_ALTIVEC #define PREFIX_no_rnd_vc1_chroma_mc8_altivec avg_no_rnd_vc1_chroma_mc8_altivec -#include "h264_template_altivec.c" +#include "h264_altivec_template.c" #undef OP_U8_ALTIVEC #undef PREFIX_no_rnd_vc1_chroma_mc8_altivec @@ -396,11 +340,7 @@ void ff_vc1dsp_init_altivec(VC1DSPContext* dsp) if (!(av_get_cpu_flags() & AV_CPU_FLAG_ALTIVEC)) return; - dsp->vc1_inv_trans_8x8_add = vc1_inv_trans_8x8_add_altivec; - dsp->vc1_inv_trans_8x8_put_signed[0] = vc1_inv_trans_8x8_put_signed_altivec; - dsp->vc1_inv_trans_8x8_put_signed[1] = vc1_inv_trans_8x8_put_signed_rangered_altivec; - dsp->vc1_inv_trans_8x8_put[0] = vc1_inv_trans_8x8_put_altivec; - dsp->vc1_inv_trans_8x8_put[1] = vc1_inv_trans_8x8_put_rangered_altivec; + dsp->vc1_inv_trans_8x8 = vc1_inv_trans_8x8_altivec; 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;