diff options
Diffstat (limited to 'libavcodec/h264idct_template.c')
-rw-r--r-- | libavcodec/h264idct_template.c | 178 |
1 files changed, 89 insertions, 89 deletions
diff --git a/libavcodec/h264idct_template.c b/libavcodec/h264idct_template.c index 08a71cd..5993ae2 100644 --- a/libavcodec/h264idct_template.c +++ b/libavcodec/h264idct_template.c @@ -2,20 +2,20 @@ * H.264 IDCT * Copyright (c) 2004-2011 Michael Niedermayer <michaelni@gmx.at> * - * 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 */ @@ -35,15 +35,15 @@ void FUNCC(ff_h264_idct_add)(uint8_t *_dst, int16_t *_block, int stride) int i; pixel *dst = (pixel*)_dst; dctcoef *block = (dctcoef*)_block; - stride /= sizeof(pixel); + stride >>= sizeof(pixel)-1; block[0] += 1 << 5; for(i=0; i<4; i++){ - const int z0= block[i + 4*0] + block[i + 4*2]; - const int z1= block[i + 4*0] - block[i + 4*2]; - const int z2= (block[i + 4*1]>>1) - block[i + 4*3]; - const int z3= block[i + 4*1] + (block[i + 4*3]>>1); + const SUINT z0= block[i + 4*0] + (unsigned)block[i + 4*2]; + const SUINT z1= block[i + 4*0] - (unsigned)block[i + 4*2]; + const SUINT z2= (block[i + 4*1]>>1) - (unsigned)block[i + 4*3]; + const SUINT z3= block[i + 4*1] + (unsigned)(block[i + 4*3]>>1); block[i + 4*0]= z0 + z3; block[i + 4*1]= z1 + z2; @@ -52,15 +52,15 @@ void FUNCC(ff_h264_idct_add)(uint8_t *_dst, int16_t *_block, int stride) } for(i=0; i<4; i++){ - const int z0= block[0 + 4*i] + block[2 + 4*i]; - const int z1= block[0 + 4*i] - block[2 + 4*i]; - const int z2= (block[1 + 4*i]>>1) - block[3 + 4*i]; - const int z3= block[1 + 4*i] + (block[3 + 4*i]>>1); - - dst[i + 0*stride]= av_clip_pixel(dst[i + 0*stride] + ((z0 + z3) >> 6)); - dst[i + 1*stride]= av_clip_pixel(dst[i + 1*stride] + ((z1 + z2) >> 6)); - dst[i + 2*stride]= av_clip_pixel(dst[i + 2*stride] + ((z1 - z2) >> 6)); - dst[i + 3*stride]= av_clip_pixel(dst[i + 3*stride] + ((z0 - z3) >> 6)); + const SUINT z0= block[0 + 4*i] + (SUINT)block[2 + 4*i]; + const SUINT z1= block[0 + 4*i] - (SUINT)block[2 + 4*i]; + const SUINT z2= (block[1 + 4*i]>>1) - (SUINT)block[3 + 4*i]; + const SUINT z3= block[1 + 4*i] + (SUINT)(block[3 + 4*i]>>1); + + dst[i + 0*stride]= av_clip_pixel(dst[i + 0*stride] + ((int)(z0 + z3) >> 6)); + dst[i + 1*stride]= av_clip_pixel(dst[i + 1*stride] + ((int)(z1 + z2) >> 6)); + dst[i + 2*stride]= av_clip_pixel(dst[i + 2*stride] + ((int)(z1 - z2) >> 6)); + dst[i + 3*stride]= av_clip_pixel(dst[i + 3*stride] + ((int)(z0 - z3) >> 6)); } memset(block, 0, 16 * sizeof(dctcoef)); @@ -70,31 +70,31 @@ void FUNCC(ff_h264_idct8_add)(uint8_t *_dst, int16_t *_block, int stride){ int i; pixel *dst = (pixel*)_dst; dctcoef *block = (dctcoef*)_block; - stride /= sizeof(pixel); + stride >>= sizeof(pixel)-1; block[0] += 32; for( i = 0; i < 8; i++ ) { - const int a0 = block[i+0*8] + block[i+4*8]; - const int a2 = block[i+0*8] - block[i+4*8]; - const int a4 = (block[i+2*8]>>1) - block[i+6*8]; - const int a6 = (block[i+6*8]>>1) + block[i+2*8]; - - const int b0 = a0 + a6; - const int b2 = a2 + a4; - const int b4 = a2 - a4; - const int b6 = a0 - a6; - - const int a1 = -block[i+3*8] + block[i+5*8] - block[i+7*8] - (block[i+7*8]>>1); - const int a3 = block[i+1*8] + block[i+7*8] - block[i+3*8] - (block[i+3*8]>>1); - const int a5 = -block[i+1*8] + block[i+7*8] + block[i+5*8] + (block[i+5*8]>>1); - const int a7 = block[i+3*8] + block[i+5*8] + block[i+1*8] + (block[i+1*8]>>1); - - const int b1 = (a7>>2) + a1; - const int b3 = a3 + (a5>>2); - const int b5 = (a3>>2) - a5; - const int b7 = a7 - (a1>>2); + const unsigned int a0 = block[i+0*8] + (unsigned)block[i+4*8]; + const unsigned int a2 = block[i+0*8] - (unsigned)block[i+4*8]; + const unsigned int a4 = (block[i+2*8]>>1) - (unsigned)block[i+6*8]; + const unsigned int a6 = (block[i+6*8]>>1) + (unsigned)block[i+2*8]; + + const unsigned int b0 = a0 + a6; + const unsigned int b2 = a2 + a4; + const unsigned int b4 = a2 - a4; + const unsigned int b6 = a0 - a6; + + const int a1 = -block[i+3*8] + (unsigned)block[i+5*8] - block[i+7*8] - (block[i+7*8]>>1); + const int a3 = block[i+1*8] + (unsigned)block[i+7*8] - block[i+3*8] - (block[i+3*8]>>1); + const int a5 = -block[i+1*8] + (unsigned)block[i+7*8] + block[i+5*8] + (block[i+5*8]>>1); + const int a7 = block[i+3*8] + (unsigned)block[i+5*8] + block[i+1*8] + (block[i+1*8]>>1); + + const int b1 = (a7>>2) + (unsigned)a1; + const int b3 = (unsigned)a3 + (a5>>2); + const int b5 = (a3>>2) - (unsigned)a5; + const int b7 = (unsigned)a7 - (a1>>2); block[i+0*8] = b0 + b7; block[i+7*8] = b0 - b7; @@ -107,34 +107,34 @@ void FUNCC(ff_h264_idct8_add)(uint8_t *_dst, int16_t *_block, int stride){ } for( i = 0; i < 8; i++ ) { - const int a0 = block[0+i*8] + block[4+i*8]; - const int a2 = block[0+i*8] - block[4+i*8]; - const int a4 = (block[2+i*8]>>1) - block[6+i*8]; - const int a6 = (block[6+i*8]>>1) + block[2+i*8]; - - const int b0 = a0 + a6; - const int b2 = a2 + a4; - const int b4 = a2 - a4; - const int b6 = a0 - a6; - - const int a1 = -block[3+i*8] + block[5+i*8] - block[7+i*8] - (block[7+i*8]>>1); - const int a3 = block[1+i*8] + block[7+i*8] - block[3+i*8] - (block[3+i*8]>>1); - const int a5 = -block[1+i*8] + block[7+i*8] + block[5+i*8] + (block[5+i*8]>>1); - const int a7 = block[3+i*8] + block[5+i*8] + block[1+i*8] + (block[1+i*8]>>1); - - const int b1 = (a7>>2) + a1; - const int b3 = a3 + (a5>>2); - const int b5 = (a3>>2) - a5; - const int b7 = a7 - (a1>>2); - - dst[i + 0*stride] = av_clip_pixel( dst[i + 0*stride] + ((b0 + b7) >> 6) ); - dst[i + 1*stride] = av_clip_pixel( dst[i + 1*stride] + ((b2 + b5) >> 6) ); - dst[i + 2*stride] = av_clip_pixel( dst[i + 2*stride] + ((b4 + b3) >> 6) ); - dst[i + 3*stride] = av_clip_pixel( dst[i + 3*stride] + ((b6 + b1) >> 6) ); - dst[i + 4*stride] = av_clip_pixel( dst[i + 4*stride] + ((b6 - b1) >> 6) ); - dst[i + 5*stride] = av_clip_pixel( dst[i + 5*stride] + ((b4 - b3) >> 6) ); - dst[i + 6*stride] = av_clip_pixel( dst[i + 6*stride] + ((b2 - b5) >> 6) ); - dst[i + 7*stride] = av_clip_pixel( dst[i + 7*stride] + ((b0 - b7) >> 6) ); + const unsigned a0 = block[0+i*8] + (unsigned)block[4+i*8]; + const unsigned a2 = block[0+i*8] - (unsigned)block[4+i*8]; + const unsigned a4 = (block[2+i*8]>>1) - (unsigned)block[6+i*8]; + const unsigned a6 = (block[6+i*8]>>1) + (unsigned)block[2+i*8]; + + const unsigned b0 = a0 + a6; + const unsigned b2 = a2 + a4; + const unsigned b4 = a2 - a4; + const unsigned b6 = a0 - a6; + + const int a1 = -(unsigned)block[3+i*8] + block[5+i*8] - block[7+i*8] - (block[7+i*8]>>1); + const int a3 = (unsigned)block[1+i*8] + block[7+i*8] - block[3+i*8] - (block[3+i*8]>>1); + const int a5 = -(unsigned)block[1+i*8] + block[7+i*8] + block[5+i*8] + (block[5+i*8]>>1); + const int a7 = (unsigned)block[3+i*8] + block[5+i*8] + block[1+i*8] + (block[1+i*8]>>1); + + const unsigned b1 = (a7>>2) + (unsigned)a1; + const unsigned b3 = (unsigned)a3 + (a5>>2); + const unsigned b5 = (a3>>2) - (unsigned)a5; + const unsigned b7 = (unsigned)a7 - (a1>>2); + + dst[i + 0*stride] = av_clip_pixel( dst[i + 0*stride] + ((int)(b0 + b7) >> 6) ); + dst[i + 1*stride] = av_clip_pixel( dst[i + 1*stride] + ((int)(b2 + b5) >> 6) ); + dst[i + 2*stride] = av_clip_pixel( dst[i + 2*stride] + ((int)(b4 + b3) >> 6) ); + dst[i + 3*stride] = av_clip_pixel( dst[i + 3*stride] + ((int)(b6 + b1) >> 6) ); + dst[i + 4*stride] = av_clip_pixel( dst[i + 4*stride] + ((int)(b6 - b1) >> 6) ); + dst[i + 5*stride] = av_clip_pixel( dst[i + 5*stride] + ((int)(b4 - b3) >> 6) ); + dst[i + 6*stride] = av_clip_pixel( dst[i + 6*stride] + ((int)(b2 - b5) >> 6) ); + dst[i + 7*stride] = av_clip_pixel( dst[i + 7*stride] + ((int)(b0 - b7) >> 6) ); } memset(block, 0, 64 * sizeof(dctcoef)); @@ -261,15 +261,15 @@ void FUNCC(ff_h264_luma_dc_dequant_idct)(int16_t *_output, int16_t *_input, int for(i=0; i<4; i++){ const int offset= x_offset[i]; - const int z0= temp[4*0+i] + temp[4*2+i]; - const int z1= temp[4*0+i] - temp[4*2+i]; - const int z2= temp[4*1+i] - temp[4*3+i]; - const int z3= temp[4*1+i] + temp[4*3+i]; - - output[stride* 0+offset]= ((((z0 + z3)*qmul + 128 ) >> 8)); - output[stride* 1+offset]= ((((z1 + z2)*qmul + 128 ) >> 8)); - output[stride* 4+offset]= ((((z1 - z2)*qmul + 128 ) >> 8)); - output[stride* 5+offset]= ((((z0 - z3)*qmul + 128 ) >> 8)); + const SUINT z0= temp[4*0+i] + temp[4*2+i]; + const SUINT z1= temp[4*0+i] - temp[4*2+i]; + const SUINT z2= temp[4*1+i] - temp[4*3+i]; + const SUINT z3= temp[4*1+i] + temp[4*3+i]; + + output[stride* 0+offset]= (int)((z0 + z3)*qmul + 128 ) >> 8; + output[stride* 1+offset]= (int)((z1 + z2)*qmul + 128 ) >> 8; + output[stride* 4+offset]= (int)((z1 - z2)*qmul + 128 ) >> 8; + output[stride* 5+offset]= (int)((z0 - z3)*qmul + 128 ) >> 8; } #undef stride } @@ -289,22 +289,22 @@ void FUNCC(ff_h264_chroma422_dc_dequant_idct)(int16_t *_block, int qmul){ for(i=0; i<2; i++){ const int offset= x_offset[i]; - const int z0= temp[2*0+i] + temp[2*2+i]; - const int z1= temp[2*0+i] - temp[2*2+i]; - const int z2= temp[2*1+i] - temp[2*3+i]; - const int z3= temp[2*1+i] + temp[2*3+i]; - - block[stride*0+offset]= ((z0 + z3)*qmul + 128) >> 8; - block[stride*1+offset]= ((z1 + z2)*qmul + 128) >> 8; - block[stride*2+offset]= ((z1 - z2)*qmul + 128) >> 8; - block[stride*3+offset]= ((z0 - z3)*qmul + 128) >> 8; + const SUINT z0= temp[2*0+i] + temp[2*2+i]; + const SUINT z1= temp[2*0+i] - temp[2*2+i]; + const SUINT z2= temp[2*1+i] - temp[2*3+i]; + const SUINT z3= temp[2*1+i] + temp[2*3+i]; + + block[stride*0+offset]= (int)((z0 + z3)*qmul + 128) >> 8; + block[stride*1+offset]= (int)((z1 + z2)*qmul + 128) >> 8; + block[stride*2+offset]= (int)((z1 - z2)*qmul + 128) >> 8; + block[stride*3+offset]= (int)((z0 - z3)*qmul + 128) >> 8; } } void FUNCC(ff_h264_chroma_dc_dequant_idct)(int16_t *_block, int qmul){ const int stride= 16*2; const int xStride= 16; - int a,b,c,d,e; + SUINT a,b,c,d,e; dctcoef *block = (dctcoef*)_block; a= block[stride*0 + xStride*0]; @@ -317,8 +317,8 @@ void FUNCC(ff_h264_chroma_dc_dequant_idct)(int16_t *_block, int qmul){ b= c-d; c= c+d; - block[stride*0 + xStride*0]= ((a+c)*qmul) >> 7; - block[stride*0 + xStride*1]= ((e+b)*qmul) >> 7; - block[stride*1 + xStride*0]= ((a-c)*qmul) >> 7; - block[stride*1 + xStride*1]= ((e-b)*qmul) >> 7; + block[stride*0 + xStride*0]= (int)((a+c)*qmul) >> 7; + block[stride*0 + xStride*1]= (int)((e+b)*qmul) >> 7; + block[stride*1 + xStride*0]= (int)((a-c)*qmul) >> 7; + block[stride*1 + xStride*1]= (int)((e-b)*qmul) >> 7; } |