From ac22385931f847cdabde4df8b0f6450d0ad14de1 Mon Sep 17 00:00:00 2001
From: Michael Niedermayer <michaelni@gmx.at>
Date: Thu, 18 Dec 2008 02:36:48 +0000
Subject: H.264 idct functions that include the chroma, inter luma and intra16
 luma loops thus avoiding the calling overhead. New functions are not yet
 used.

Originally committed as revision 16206 to svn://svn.ffmpeg.org/ffmpeg/trunk
---
 libavcodec/h264idct.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

(limited to 'libavcodec/h264idct.c')

diff --git a/libavcodec/h264idct.c b/libavcodec/h264idct.c
index 571e2e91d1..7ef7a2a4d5 100644
--- a/libavcodec/h264idct.c
+++ b/libavcodec/h264idct.c
@@ -165,3 +165,55 @@ void ff_h264_idct8_dc_add_c(uint8_t *dst, DCTELEM *block, int stride){
         dst += stride;
     }
 }
+
+//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 + 2*4]={
+ 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,
+ 1+1*8, 2+1*8,
+ 1+2*8, 2+2*8,
+ 1+4*8, 2+4*8,
+ 1+5*8, 2+5*8,
+};
+
+void ff_h264_idct_add16_c(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]){
+    int i;
+    for(i=0; i<16; i++){
+        int nnz = nnzc[ scan8[i] ];
+        if(nnz){
+            if(nnz==1 && block[i*16]) ff_h264_idct_dc_add_c(dst + block_offset[i], block + i*16, stride);
+            else                      idct_internal        (dst + block_offset[i], block + i*16, stride, 4, 6, 1);
+        }
+    }
+}
+
+void ff_h264_idct_add16intra_c(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]){
+    int i;
+    for(i=0; i<16; i++){
+        if(nnzc[ scan8[i] ]) idct_internal        (dst + block_offset[i], block + i*16, stride, 4, 6, 1);
+        else if(block[i*16]) ff_h264_idct_dc_add_c(dst + block_offset[i], block + i*16, stride);
+    }
+}
+
+void ff_h264_idct8_add4_c(uint8_t *dst, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]){
+    int i;
+    for(i=0; i<16; i+=4){
+        int nnz = nnzc[ scan8[i] ];
+        if(nnz){
+            if(nnz==1 && block[i*16]) ff_h264_idct8_dc_add_c(dst + block_offset[i], block + i*16, stride);
+            else                      ff_h264_idct8_add_c   (dst + block_offset[i], block + i*16, stride);
+        }
+    }
+}
+
+void ff_h264_idct_add8_c(uint8_t **dest, const int *block_offset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]){
+    int i;
+    for(i=16; i<16+8; i++){
+        if(nnzc[ scan8[i] ])
+            ff_h264_idct_add_c   (dest[(i&4)>>2] + block_offset[i], block + i*16, stride);
+        else if(block[i*16])
+            ff_h264_idct_dc_add_c(dest[(i&4)>>2] + block_offset[i], block + i*16, stride);
+    }
+}
-- 
cgit v1.2.3