X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fsimple_idct.c;h=7bf0836aa4b8d3ef14ea60b5af4d069773215c36;hb=b1d31e2f1236f4f7791bb2b969c214b57ac2a1c0;hp=c751aabbcb3e52865f16f7a283dceb329c0ed473;hpb=115329f16062074e11ccf3b89ead6176606c9696;p=ffmpeg diff --git a/libavcodec/simple_idct.c b/libavcodec/simple_idct.c index c751aabbcb3..7bf0836aa4b 100644 --- a/libavcodec/simple_idct.c +++ b/libavcodec/simple_idct.c @@ -3,19 +3,21 @@ * * Copyright (c) 2001 Michael Niedermayer * - * This library is free software; you can redistribute it and/or + * This file is part of FFmpeg. + * + * 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 of the License, or (at your option) any later version. + * version 2.1 of the License, or (at your option) any later version. * - * This library 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 this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ /** @@ -75,14 +77,14 @@ static inline void idctRowCondDC (DCTELEM * row) { - int a0, a1, a2, a3, b0, b1, b2, b3; -#ifdef FAST_64BIT + int a0, a1, a2, a3, b0, b1, b2, b3; +#ifdef HAVE_FAST_64BIT uint64_t temp; #else uint32_t temp; #endif -#ifdef FAST_64BIT +#ifdef HAVE_FAST_64BIT #ifdef WORDS_BIGENDIAN #define ROW0_MASK 0xffff000000000000LL #else @@ -97,7 +99,7 @@ static inline void idctRowCondDC (DCTELEM * row) ((uint64_t *)row)[0] = temp; ((uint64_t *)row)[1] = temp; return; - } + } }else{ if (!(row[1]|row[2]|row[3]|row[4]|row[5]|row[6]|row[7])) { row[0]=row[1]=row[2]=row[3]=row[4]=row[5]=row[6]=row[7]= row[0] << 3; @@ -125,9 +127,9 @@ static inline void idctRowCondDC (DCTELEM * row) #endif a0 = (W4 * row[0]) + (1 << (ROW_SHIFT - 1)); - a1 = a0; - a2 = a0; - a3 = a0; + a1 = a0; + a2 = a0; + a3 = a0; /* no need to optimize : gcc does it */ a0 += W2 * row[2]; @@ -144,12 +146,12 @@ static inline void idctRowCondDC (DCTELEM * row) MUL16(b3, W7, row[1]); MAC16(b3, -W5, row[3]); -#ifdef FAST_64BIT +#ifdef HAVE_FAST_64BIT temp = ((uint64_t*)row)[1]; #else temp = ((uint32_t*)row)[2] | ((uint32_t*)row)[3]; #endif - if (temp != 0) { + if (temp != 0) { a0 += W4*row[4] + W6*row[6]; a1 += - W4*row[4] - W2*row[6]; a2 += - W4*row[4] + W2*row[6]; @@ -166,29 +168,29 @@ static inline void idctRowCondDC (DCTELEM * row) MAC16(b3, W3, row[5]); MAC16(b3, -W1, row[7]); - } - - row[0] = (a0 + b0) >> ROW_SHIFT; - row[7] = (a0 - b0) >> ROW_SHIFT; - row[1] = (a1 + b1) >> ROW_SHIFT; - row[6] = (a1 - b1) >> ROW_SHIFT; - row[2] = (a2 + b2) >> ROW_SHIFT; - row[5] = (a2 - b2) >> ROW_SHIFT; - row[3] = (a3 + b3) >> ROW_SHIFT; - row[4] = (a3 - b3) >> ROW_SHIFT; + } + + row[0] = (a0 + b0) >> ROW_SHIFT; + row[7] = (a0 - b0) >> ROW_SHIFT; + row[1] = (a1 + b1) >> ROW_SHIFT; + row[6] = (a1 - b1) >> ROW_SHIFT; + row[2] = (a2 + b2) >> ROW_SHIFT; + row[5] = (a2 - b2) >> ROW_SHIFT; + row[3] = (a3 + b3) >> ROW_SHIFT; + row[4] = (a3 - b3) >> ROW_SHIFT; } static inline void idctSparseColPut (uint8_t *dest, int line_size, DCTELEM * col) { - int a0, a1, a2, a3, b0, b1, b2, b3; - uint8_t *cm = cropTbl + MAX_NEG_CROP; + int a0, a1, a2, a3, b0, b1, b2, b3; + uint8_t *cm = ff_cropTbl + MAX_NEG_CROP; /* XXX: I did that only to give same values as previous code */ - a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); - a1 = a0; - a2 = a0; - a3 = a0; + a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); + a1 = a0; + a2 = a0; + a3 = a0; a0 += + W2*col[8*2]; a1 += + W6*col[8*2]; @@ -205,33 +207,33 @@ static inline void idctSparseColPut (uint8_t *dest, int line_size, MAC16(b2, - W1, col[8*3]); MAC16(b3, - W5, col[8*3]); - if(col[8*4]){ + if(col[8*4]){ a0 += + W4*col[8*4]; a1 += - W4*col[8*4]; a2 += - W4*col[8*4]; a3 += + W4*col[8*4]; - } + } - if (col[8*5]) { + if (col[8*5]) { MAC16(b0, + W5, col[8*5]); MAC16(b1, - W1, col[8*5]); MAC16(b2, + W7, col[8*5]); MAC16(b3, + W3, col[8*5]); - } + } - if(col[8*6]){ + if(col[8*6]){ a0 += + W6*col[8*6]; a1 += - W2*col[8*6]; a2 += + W2*col[8*6]; a3 += - W6*col[8*6]; - } + } - if (col[8*7]) { + if (col[8*7]) { MAC16(b0, + W7, col[8*7]); MAC16(b1, - W5, col[8*7]); MAC16(b2, + W3, col[8*7]); MAC16(b3, - W1, col[8*7]); - } + } dest[0] = cm[(a0 + b0) >> COL_SHIFT]; dest += line_size; @@ -253,14 +255,14 @@ static inline void idctSparseColPut (uint8_t *dest, int line_size, static inline void idctSparseColAdd (uint8_t *dest, int line_size, DCTELEM * col) { - int a0, a1, a2, a3, b0, b1, b2, b3; - uint8_t *cm = cropTbl + MAX_NEG_CROP; + int a0, a1, a2, a3, b0, b1, b2, b3; + uint8_t *cm = ff_cropTbl + MAX_NEG_CROP; /* XXX: I did that only to give same values as previous code */ - a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); - a1 = a0; - a2 = a0; - a3 = a0; + a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); + a1 = a0; + a2 = a0; + a3 = a0; a0 += + W2*col[8*2]; a1 += + W6*col[8*2]; @@ -277,33 +279,33 @@ static inline void idctSparseColAdd (uint8_t *dest, int line_size, MAC16(b2, - W1, col[8*3]); MAC16(b3, - W5, col[8*3]); - if(col[8*4]){ + if(col[8*4]){ a0 += + W4*col[8*4]; a1 += - W4*col[8*4]; a2 += - W4*col[8*4]; a3 += + W4*col[8*4]; - } + } - if (col[8*5]) { + if (col[8*5]) { MAC16(b0, + W5, col[8*5]); MAC16(b1, - W1, col[8*5]); MAC16(b2, + W7, col[8*5]); MAC16(b3, + W3, col[8*5]); - } + } - if(col[8*6]){ + if(col[8*6]){ a0 += + W6*col[8*6]; a1 += - W2*col[8*6]; a2 += + W2*col[8*6]; a3 += - W6*col[8*6]; - } + } - if (col[8*7]) { + if (col[8*7]) { MAC16(b0, + W7, col[8*7]); MAC16(b1, - W5, col[8*7]); MAC16(b2, + W3, col[8*7]); MAC16(b3, - W1, col[8*7]); - } + } dest[0] = cm[dest[0] + ((a0 + b0) >> COL_SHIFT)]; dest += line_size; @@ -324,13 +326,13 @@ static inline void idctSparseColAdd (uint8_t *dest, int line_size, static inline void idctSparseCol (DCTELEM * col) { - int a0, a1, a2, a3, b0, b1, b2, b3; + int a0, a1, a2, a3, b0, b1, b2, b3; /* XXX: I did that only to give same values as previous code */ - a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); - a1 = a0; - a2 = a0; - a3 = a0; + a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4)); + a1 = a0; + a2 = a0; + a3 = a0; a0 += + W2*col[8*2]; a1 += + W6*col[8*2]; @@ -347,33 +349,33 @@ static inline void idctSparseCol (DCTELEM * col) MAC16(b2, - W1, col[8*3]); MAC16(b3, - W5, col[8*3]); - if(col[8*4]){ + if(col[8*4]){ a0 += + W4*col[8*4]; a1 += - W4*col[8*4]; a2 += - W4*col[8*4]; a3 += + W4*col[8*4]; - } + } - if (col[8*5]) { + if (col[8*5]) { MAC16(b0, + W5, col[8*5]); MAC16(b1, - W1, col[8*5]); MAC16(b2, + W7, col[8*5]); MAC16(b3, + W3, col[8*5]); - } + } - if(col[8*6]){ + if(col[8*6]){ a0 += + W6*col[8*6]; a1 += - W2*col[8*6]; a2 += + W2*col[8*6]; a3 += - W6*col[8*6]; - } + } - if (col[8*7]) { + if (col[8*7]) { MAC16(b0, + W7, col[8*7]); MAC16(b1, - W5, col[8*7]); MAC16(b2, + W3, col[8*7]); MAC16(b3, - W1, col[8*7]); - } + } col[0 ] = ((a0 + b0) >> COL_SHIFT); col[8 ] = ((a1 + b1) >> COL_SHIFT); @@ -385,7 +387,7 @@ static inline void idctSparseCol (DCTELEM * col) col[56] = ((a0 - b0) >> COL_SHIFT); } -void simple_idct_put(uint8_t *dest, int line_size, DCTELEM *block) +void ff_simple_idct_put(uint8_t *dest, int line_size, DCTELEM *block) { int i; for(i=0; i<8; i++) @@ -395,7 +397,7 @@ void simple_idct_put(uint8_t *dest, int line_size, DCTELEM *block) idctSparseColPut(dest + i, line_size, block + i); } -void simple_idct_add(uint8_t *dest, int line_size, DCTELEM *block) +void ff_simple_idct_add(uint8_t *dest, int line_size, DCTELEM *block) { int i; for(i=0; i<8; i++) @@ -405,7 +407,7 @@ void simple_idct_add(uint8_t *dest, int line_size, DCTELEM *block) idctSparseColAdd(dest + i, line_size, block + i); } -void simple_idct(DCTELEM *block) +void ff_simple_idct(DCTELEM *block) { int i; for(i=0; i<8; i++) @@ -426,10 +428,10 @@ void simple_idct(DCTELEM *block) and the butterfly must be multiplied by 0.5 * sqrt(2.0) */ #define C_SHIFT (4+1+12) -static inline void idct4col(uint8_t *dest, int line_size, const DCTELEM *col) +static inline void idct4col_put(uint8_t *dest, int line_size, const DCTELEM *col) { int c0, c1, c2, c3, a0, a1, a2, a3; - const uint8_t *cm = cropTbl + MAX_NEG_CROP; + const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP; a0 = col[8*0]; a1 = col[8*2]; @@ -463,7 +465,7 @@ static inline void idct4col(uint8_t *dest, int line_size, const DCTELEM *col) /* XXX: I think a 1.0/sqrt(2) normalization should be needed to compensate the extra butterfly stage - I don't have the full DV specification */ -void simple_idct248_put(uint8_t *dest, int line_size, DCTELEM *block) +void ff_simple_idct248_put(uint8_t *dest, int line_size, DCTELEM *block) { int i; DCTELEM *ptr; @@ -489,8 +491,8 @@ void simple_idct248_put(uint8_t *dest, int line_size, DCTELEM *block) /* IDCT4 and store */ for(i=0;i<8;i++) { - idct4col(dest + i, 2 * line_size, block + i); - idct4col(dest + line_size + i, 2 * line_size, block + 8 + i); + idct4col_put(dest + i, 2 * line_size, block + i); + idct4col_put(dest + line_size + i, 2 * line_size, block + 8 + i); } } @@ -509,7 +511,7 @@ void simple_idct248_put(uint8_t *dest, int line_size, DCTELEM *block) static inline void idct4col_add(uint8_t *dest, int line_size, const DCTELEM *col) { int c0, c1, c2, c3, a0, a1, a2, a3; - const uint8_t *cm = cropTbl + MAX_NEG_CROP; + const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP; a0 = col[8*0]; a1 = col[8*1]; @@ -537,7 +539,7 @@ static inline void idct4col_add(uint8_t *dest, int line_size, const DCTELEM *col static inline void idct4row(DCTELEM *row) { int c0, c1, c2, c3, a0, a1, a2, a3; - //const uint8_t *cm = cropTbl + MAX_NEG_CROP; + //const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP; a0 = row[0]; a1 = row[1]; @@ -553,7 +555,7 @@ static inline void idct4row(DCTELEM *row) row[3]= (c0 - c1) >> R_SHIFT; } -void simple_idct84_add(uint8_t *dest, int line_size, DCTELEM *block) +void ff_simple_idct84_add(uint8_t *dest, int line_size, DCTELEM *block) { int i; @@ -568,7 +570,7 @@ void simple_idct84_add(uint8_t *dest, int line_size, DCTELEM *block) } } -void simple_idct48_add(uint8_t *dest, int line_size, DCTELEM *block) +void ff_simple_idct48_add(uint8_t *dest, int line_size, DCTELEM *block) { int i; @@ -583,3 +585,17 @@ void simple_idct48_add(uint8_t *dest, int line_size, DCTELEM *block) } } +void ff_simple_idct44_add(uint8_t *dest, int line_size, DCTELEM *block) +{ + int i; + + /* IDCT4 on each line */ + for(i=0; i<4; i++) { + idct4row(block + i*8); + } + + /* IDCT4 and store */ + for(i=0; i<4; i++){ + idct4col_add(dest + i, line_size, block + i); + } +}