dxva2: Keep code shared between dxva2 and d3d11va under the correct #if

[ffmpeg] / libavcodec / h264idct_template.c

diff --git a/libavcodec/h264idct_template.c b/libavcodec/h264idct_template.c
index 554483c0573ff97ffa849820a4d9a3144dab0bbb..08a71cd4e96643bf49cc86537681571b8554c440 100644 (file)
--- a/libavcodec/h264idct_template.c
+++ b/libavcodec/h264idct_template.c
@@ -27,27 +27,10 @@
 
 #include "bit_depth_template.c"
 #include "libavutil/common.h"
+#include "h264dec.h"
+#include "h264idct.h"
 
-#ifndef AVCODEC_H264IDCT_INTERNAL_H
-#define AVCODEC_H264IDCT_INTERNAL_H
-//FIXME this table is a duplicate from h264data.h, and will be removed once the tables from, h264 have been split
-static const uint8_t scan8[16*3]={
- 4+ 1*8, 5+ 1*8, 4+ 2*8, 5+ 2*8,
- 6+ 1*8, 7+ 1*8, 6+ 2*8, 7+ 2*8,
- 4+ 3*8, 5+ 3*8, 4+ 4*8, 5+ 4*8,
- 6+ 3*8, 7+ 3*8, 6+ 4*8, 7+ 4*8,
- 4+ 6*8, 5+ 6*8, 4+ 7*8, 5+ 7*8,
- 6+ 6*8, 7+ 6*8, 6+ 7*8, 7+ 7*8,
- 4+ 8*8, 5+ 8*8, 4+ 9*8, 5+ 9*8,
- 6+ 8*8, 7+ 8*8, 6+ 9*8, 7+ 9*8,
- 4+11*8, 5+11*8, 4+12*8, 5+12*8,
- 6+11*8, 7+11*8, 6+12*8, 7+12*8,
- 4+13*8, 5+13*8, 4+14*8, 5+14*8,
- 6+13*8, 7+13*8, 6+14*8, 7+14*8
-};
-#endif
-
-void FUNCC(ff_h264_idct_add)(uint8_t *_dst, DCTELEM *_block, int stride)
+void FUNCC(ff_h264_idct_add)(uint8_t *_dst, int16_t *_block, int stride)
 {
     int i;
     pixel *dst = (pixel*)_dst;
@@ -79,9 +62,11 @@ void FUNCC(ff_h264_idct_add)(uint8_t *_dst, DCTELEM *_block, int stride)
         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));
     }
+
+    memset(block, 0, 16 * sizeof(dctcoef));
 }
 
-void FUNCC(ff_h264_idct8_add)(uint8_t *_dst, DCTELEM *_block, int stride){
+void FUNCC(ff_h264_idct8_add)(uint8_t *_dst, int16_t *_block, int stride){
     int i;
     pixel *dst = (pixel*)_dst;
     dctcoef *block = (dctcoef*)_block;
@@ -151,14 +136,18 @@ void FUNCC(ff_h264_idct8_add)(uint8_t *_dst, DCTELEM *_block, int stride){
         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) );
     }
+
+    memset(block, 0, 64 * sizeof(dctcoef));
 }
 
 // assumes all AC coefs are 0
-void FUNCC(ff_h264_idct_dc_add)(uint8_t *_dst, DCTELEM *block, int stride){
+void FUNCC(ff_h264_idct_dc_add)(uint8_t *_dst, int16_t *_block, int stride){
     int i, j;
-    int dc = (((dctcoef*)block)[0] + 32) >> 6;
     pixel *dst = (pixel*)_dst;
+    dctcoef *block = (dctcoef*)_block;
+    int dc = (block[0] + 32) >> 6;
     stride /= sizeof(pixel);
+    block[0] = 0;
     for( j = 0; j < 4; j++ )
     {
         for( i = 0; i < 4; i++ )
@@ -167,10 +156,12 @@ void FUNCC(ff_h264_idct_dc_add)(uint8_t *_dst, DCTELEM *block, int stride){
     }
 }
 
-void FUNCC(ff_h264_idct8_dc_add)(uint8_t *_dst, DCTELEM *block, int stride){
+void FUNCC(ff_h264_idct8_dc_add)(uint8_t *_dst, int16_t *_block, int stride){
     int i, j;
-    int dc = (((dctcoef*)block)[0] + 32) >> 6;
     pixel *dst = (pixel*)_dst;
+    dctcoef *block = (dctcoef*)_block;
+    int dc = (block[0] + 32) >> 6;
+    block[0] = 0;
     stride /= sizeof(pixel);
     for( j = 0; j < 8; j++ )
     {
@@ -180,7 +171,7 @@ void FUNCC(ff_h264_idct8_dc_add)(uint8_t *_dst, DCTELEM *block, int stride){
     }
 }
 
-void FUNCC(ff_h264_idct_add16)(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[15*8]){
+void FUNCC(ff_h264_idct_add16)(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
     int i;
     for(i=0; i<16; i++){
         int nnz = nnzc[ scan8[i] ];
@@ -191,7 +182,7 @@ void FUNCC(ff_h264_idct_add16)(uint8_t *dst, const int *block_offset, DCTELEM *b
     }
 }
 
-void FUNCC(ff_h264_idct_add16intra)(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[15*8]){
+void FUNCC(ff_h264_idct_add16intra)(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
     int i;
     for(i=0; i<16; i++){
         if(nnzc[ scan8[i] ])             FUNCC(ff_h264_idct_add   )(dst + block_offset[i], block + i*16*sizeof(pixel), stride);
@@ -199,7 +190,7 @@ void FUNCC(ff_h264_idct_add16intra)(uint8_t *dst, const int *block_offset, DCTEL
     }
 }
 
-void FUNCC(ff_h264_idct8_add4)(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[15*8]){
+void FUNCC(ff_h264_idct8_add4)(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
     int i;
     for(i=0; i<16; i+=4){
         int nnz = nnzc[ scan8[i] ];
@@ -210,7 +201,7 @@ void FUNCC(ff_h264_idct8_add4)(uint8_t *dst, const int *block_offset, DCTELEM *b
     }
 }
 
-void FUNCC(ff_h264_idct_add8)(uint8_t **dest, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[15*8]){
+void FUNCC(ff_h264_idct_add8)(uint8_t **dest, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
     int i, j;
     for(j=1; j<3; j++){
         for(i=j*16; i<j*16+4; i++){
@@ -222,7 +213,7 @@ void FUNCC(ff_h264_idct_add8)(uint8_t **dest, const int *block_offset, DCTELEM *
     }
 }
 
-void FUNCC(ff_h264_idct_add8_422)(uint8_t **dest, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[15*8]){
+void FUNCC(ff_h264_idct_add8_422)(uint8_t **dest, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
     int i, j;
 
     for(j=1; j<3; j++){
@@ -248,7 +239,7 @@ void FUNCC(ff_h264_idct_add8_422)(uint8_t **dest, const int *block_offset, DCTEL
  * IDCT transforms the 16 dc values and dequantizes them.
  * @param qmul quantization parameter
  */
-void FUNCC(ff_h264_luma_dc_dequant_idct)(DCTELEM *_output, DCTELEM *_input, int qmul){
+void FUNCC(ff_h264_luma_dc_dequant_idct)(int16_t *_output, int16_t *_input, int qmul){
 #define stride 16
     int i;
     int temp[16];
@@ -283,7 +274,7 @@ void FUNCC(ff_h264_luma_dc_dequant_idct)(DCTELEM *_output, DCTELEM *_input, int
 #undef stride
 }
 
-void FUNCC(ff_h264_chroma422_dc_dequant_idct)(DCTELEM *_block, int qmul){
+void FUNCC(ff_h264_chroma422_dc_dequant_idct)(int16_t *_block, int qmul){
     const int stride= 16*2;
     const int xStride= 16;
     int i;
@@ -310,7 +301,7 @@ void FUNCC(ff_h264_chroma422_dc_dequant_idct)(DCTELEM *_block, int qmul){
     }
 }
 
-void FUNCC(ff_h264_chroma_dc_dequant_idct)(DCTELEM *_block, int qmul){
+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;