simple_idct: add 10-bit version

Signed-off-by: Mans Rullgard <mans@mansr.com>

1 files changed, 9 insertions, 329 deletions

diff --git a/libavcodec/simple_idct.c b/libavcodec/simple_idct.c
index 0ffbfcaf33..b62658bdb3 100644
--- a/libavcodec/simple_idct.c
+++ b/libavcodec/simple_idct.c
@@ -25,339 +25,19 @@
  * simpleidct in C.
  */
 
-/*
-  based upon some outcommented c code from mpeg2dec (idct_mmx.c
-  written by Aaron Holtzman <aholtzma@ess.engr.uvic.ca>)
- */
-
 #include "libavutil/intreadwrite.h"
 #include "avcodec.h"
 #include "dsputil.h"
 #include "mathops.h"
 #include "simple_idct.h"
 
-#define W1  22725  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W2  21407  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W3  19266  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W4  16383  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W5  12873  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W6  8867   //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define W7  4520   //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
-#define ROW_SHIFT 11
-#define COL_SHIFT 20 // 6
-
-static inline void idctRowCondDC (DCTELEM * row)
-{
-        int a0, a1, a2, a3, b0, b1, b2, b3;
-
-#if HAVE_FAST_64BIT
-#define ROW0_MASK (0xffffLL << 48 * HAVE_BIGENDIAN)
-        if (((((uint64_t *)row)[0] & ~ROW0_MASK) | ((uint64_t *)row)[1]) == 0) {
-            uint64_t temp = (row[0] << 3) & 0xffff;
-            temp += temp << 16;
-            temp += temp << 32;
-            ((uint64_t *)row)[0] = temp;
-            ((uint64_t *)row)[1] = temp;
-            return;
-        }
-#else
-        if (!(((uint32_t*)row)[1] |
-              ((uint32_t*)row)[2] |
-              ((uint32_t*)row)[3] |
-              row[1])) {
-            uint32_t temp = (row[0] << 3) & 0xffff;
-            temp += temp << 16;
-            ((uint32_t*)row)[0]=((uint32_t*)row)[1] =
-                ((uint32_t*)row)[2]=((uint32_t*)row)[3] = temp;
-            return;
-        }
-#endif
-
-        a0 = (W4 * row[0]) + (1 << (ROW_SHIFT - 1));
-        a1 = a0;
-        a2 = a0;
-        a3 = a0;
-
-        /* no need to optimize : gcc does it */
-        a0 += W2 * row[2];
-        a1 += W6 * row[2];
-        a2 -= W6 * row[2];
-        a3 -= W2 * row[2];
-
-        b0 = MUL16(W1, row[1]);
-        MAC16(b0, W3, row[3]);
-        b1 = MUL16(W3, row[1]);
-        MAC16(b1, -W7, row[3]);
-        b2 = MUL16(W5, row[1]);
-        MAC16(b2, -W1, row[3]);
-        b3 = MUL16(W7, row[1]);
-        MAC16(b3, -W5, row[3]);
-
-        if (AV_RN64A(row + 4)) {
-            a0 += W4*row[4] + W6*row[6];
-            a1 += - W4*row[4] - W2*row[6];
-            a2 += - W4*row[4] + W2*row[6];
-            a3 += W4*row[4] - W6*row[6];
-
-            MAC16(b0, W5, row[5]);
-            MAC16(b0, W7, row[7]);
-
-            MAC16(b1, -W1, row[5]);
-            MAC16(b1, -W5, row[7]);
-
-            MAC16(b2, W7, row[5]);
-            MAC16(b2, W3, row[7]);
-
-            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;
-}
-
-static inline void idctSparseColPut (uint8_t *dest, int line_size,
-                                     DCTELEM * col)
-{
-        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 +=  + W2*col[8*2];
-        a1 +=  + W6*col[8*2];
-        a2 +=  - W6*col[8*2];
-        a3 +=  - W2*col[8*2];
-
-        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]);
-        MAC16(b2, - W1, col[8*3]);
-        MAC16(b3, - W5, col[8*3]);
-
-        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]) {
-            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]){
-            a0 += + W6*col[8*6];
-            a1 += - W2*col[8*6];
-            a2 += + W2*col[8*6];
-            a3 += - W6*col[8*6];
-        }
-
-        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;
-        dest[0] = cm[(a1 + b1) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a2 + b2) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a3 + b3) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a3 - b3) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a2 - b2) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a1 - b1) >> COL_SHIFT];
-        dest += line_size;
-        dest[0] = cm[(a0 - b0) >> COL_SHIFT];
-}
-
-static inline void idctSparseColAdd (uint8_t *dest, int line_size,
-                                     DCTELEM * col)
-{
-        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 +=  + W2*col[8*2];
-        a1 +=  + W6*col[8*2];
-        a2 +=  - W6*col[8*2];
-        a3 +=  - W2*col[8*2];
-
-        b0 = MUL16(W1, col[8*1]);
-        b1 = MUL16(W3, col[8*1]);
-        b2 = MUL16(W5, col[8*1]);
-        b3 = MUL16(W7, col[8*1]);
+#define BIT_DEPTH 8
+#include "simple_idct_template.c"
+#undef BIT_DEPTH
 
-        MAC16(b0, + W3, col[8*3]);
-        MAC16(b1, - W7, col[8*3]);
-        MAC16(b2, - W1, col[8*3]);
-        MAC16(b3, - W5, col[8*3]);
-
-        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]) {
-            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]){
-            a0 += + W6*col[8*6];
-            a1 += - W2*col[8*6];
-            a2 += + W2*col[8*6];
-            a3 += - W6*col[8*6];
-        }
-
-        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;
-        dest[0] = cm[dest[0] + ((a1 + b1) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a2 + b2) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a3 + b3) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a3 - b3) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a2 - b2) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a1 - b1) >> COL_SHIFT)];
-        dest += line_size;
-        dest[0] = cm[dest[0] + ((a0 - b0) >> COL_SHIFT)];
-}
-
-static inline void idctSparseCol (DCTELEM * col)
-{
-        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 +=  + W2*col[8*2];
-        a1 +=  + W6*col[8*2];
-        a2 +=  - W6*col[8*2];
-        a3 +=  - W2*col[8*2];
-
-        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]);
-        MAC16(b2, - W1, col[8*3]);
-        MAC16(b3, - W5, col[8*3]);
-
-        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]) {
-            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]){
-            a0 += + W6*col[8*6];
-            a1 += - W2*col[8*6];
-            a2 += + W2*col[8*6];
-            a3 += - W6*col[8*6];
-        }
-
-        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);
-        col[16] = ((a2 + b2) >> COL_SHIFT);
-        col[24] = ((a3 + b3) >> COL_SHIFT);
-        col[32] = ((a3 - b3) >> COL_SHIFT);
-        col[40] = ((a2 - b2) >> COL_SHIFT);
-        col[48] = ((a1 - b1) >> COL_SHIFT);
-        col[56] = ((a0 - b0) >> COL_SHIFT);
-}
-
-void ff_simple_idct_put(uint8_t *dest, int line_size, DCTELEM *block)
-{
-    int i;
-    for(i=0; i<8; i++)
-        idctRowCondDC(block + i*8);
-
-    for(i=0; i<8; i++)
-        idctSparseColPut(dest + i, line_size, block + i);
-}
-
-void ff_simple_idct_add(uint8_t *dest, int line_size, DCTELEM *block)
-{
-    int i;
-    for(i=0; i<8; i++)
-        idctRowCondDC(block + i*8);
-
-    for(i=0; i<8; i++)
-        idctSparseColAdd(dest + i, line_size, block + i);
-}
-
-void ff_simple_idct(DCTELEM *block)
-{
-    int i;
-    for(i=0; i<8; i++)
-        idctRowCondDC(block + i*8);
-
-    for(i=0; i<8; i++)
-        idctSparseCol(block + i);
-}
+#define BIT_DEPTH 10
+#include "simple_idct_template.c"
+#undef BIT_DEPTH
 
 /* 2x4x8 idct */
 
@@ -428,7 +108,7 @@ void ff_simple_idct248_put(uint8_t *dest, int line_size, DCTELEM *block)
 
     /* IDCT8 on each line */
     for(i=0; i<8; i++) {
-        idctRowCondDC(block + i*8);
+        idctRowCondDC_8(block + i*8);
     }
 
     /* IDCT4 and store */
@@ -503,7 +183,7 @@ void ff_simple_idct84_add(uint8_t *dest, int line_size, DCTELEM *block)
 
     /* IDCT8 on each line */
     for(i=0; i<4; i++) {
-        idctRowCondDC(block + i*8);
+        idctRowCondDC_8(block + i*8);
     }
 
     /* IDCT4 and store */
@@ -523,7 +203,7 @@ void ff_simple_idct48_add(uint8_t *dest, int line_size, DCTELEM *block)
 
     /* IDCT8 and store */
     for(i=0; i<4; i++){
-        idctSparseColAdd(dest + i, line_size, block + i);
+        idctSparseColAdd_8(dest + i, line_size, block + i);
     }
 }