xenia-project/FFmpeg
1
0
Fork 0
mirror of https://github.com/xenia-project/FFmpeg.git synced 2024-11-24 20:19:55 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

simple_idct: use MUL16 and MAC16 from mathops.h

Browse Source 
Originally committed as revision 16362 to svn://svn.ffmpeg.org/ffmpeg/trunk
This commit is contained in:
Måns Rullgård 2008-12-27 16:25:36 +00:00
parent 643d2e880f
commit edf7c2b26f
1 changed files with 17 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
libavcodec/simple_idct.c
View File

@ -31,6 +31,7 @@
*/
#include "avcodec.h"
#include "dsputil.h"
#include "mathops.h"
#include "simple_idct.h"
#if 0
@ -55,26 +56,6 @@
#define COL_SHIFT 20 // 6
#endif
#if defined(ARCH_PPC_405)
/* signed 16x16 -> 32 multiply add accumulate */
#define MAC16(rt, ra, rb) \
__asm__ ("maclhw %0, %2, %3" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb));
/* signed 16x16 -> 32 multiply */
#define MUL16(rt, ra, rb) \
__asm__ ("mullhw %0, %1, %2" : "=r" (rt) : "r" (ra), "r" (rb));
#else
/* signed 16x16 -> 32 multiply add accumulate */
#define MAC16(rt, ra, rb) rt += (ra) * (rb)
/* signed 16x16 -> 32 multiply */
#define MUL16(rt, ra, rb) rt = (ra) * (rb)
#endif
static inline void idctRowCondDC (DCTELEM * row)
{
int a0, a1, a2, a3, b0, b1, b2, b3;
@ -137,13 +118,13 @@ static inline void idctRowCondDC (DCTELEM * row)
a2 -= W6 * row[2];
a3 -= W2 * row[2];
MUL16(b0, W1, row[1]);
b0 = MUL16(W1, row[1]);
MAC16(b0, W3, row[3]);
MUL16(b1, W3, row[1]);
b1 = MUL16(W3, row[1]);
MAC16(b1, -W7, row[3]);
MUL16(b2, W5, row[1]);
b2 = MUL16(W5, row[1]);
MAC16(b2, -W1, row[3]);
MUL16(b3, W7, row[1]);
b3 = MUL16(W7, row[1]);
MAC16(b3, -W5, row[3]);
#ifdef HAVE_FAST_64BIT
@ -197,10 +178,10 @@ static inline void idctSparseColPut (uint8_t *dest, int line_size,
a2 += - W6*col[8*2];
a3 += - W2*col[8*2];
MUL16(b0, W1, col[8*1]);
MUL16(b1, W3, col[8*1]);
MUL16(b2, W5, col[8*1]);
MUL16(b3, W7, col[8*1]);
b0 = MUL16(W1, col[8*1]);
b1 = MUL16(W3, col[8*1]);
b2 = MUL16(W5, col[8*1]);
b3 = MUL16(W7, col[8*1]);
MAC16(b0, + W3, col[8*3]);
MAC16(b1, - W7, col[8*3]);
@ -269,10 +250,10 @@ static inline void idctSparseColAdd (uint8_t *dest, int line_size,
a2 += - W6*col[8*2];
a3 += - W2*col[8*2];
MUL16(b0, W1, col[8*1]);
MUL16(b1, W3, col[8*1]);
MUL16(b2, W5, col[8*1]);
MUL16(b3, W7, col[8*1]);
b0 = MUL16(W1, col[8*1]);
b1 = MUL16(W3, col[8*1]);
b2 = MUL16(W5, col[8*1]);
b3 = MUL16(W7, col[8*1]);
MAC16(b0, + W3, col[8*3]);
MAC16(b1, - W7, col[8*3]);
@ -339,10 +320,10 @@ static inline void idctSparseCol (DCTELEM * col)
a2 += - W6*col[8*2];
a3 += - W2*col[8*2];
MUL16(b0, W1, col[8*1]);
MUL16(b1, W3, col[8*1]);
MUL16(b2, W5, col[8*1]);
MUL16(b3, W7, col[8*1]);
b0 = MUL16(W1, col[8*1]);
b1 = MUL16(W3, col[8*1]);
b2 = MUL16(W5, col[8*1]);
b3 = MUL16(W7, col[8*1]);
MAC16(b0, + W3, col[8*3]);
MAC16(b1, - W7, col[8*3]);