move h264 idct to its own file and call via function pointer in DspContext

allow h264 idct to be used for lowres=1

Originally committed as revision 3524 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 files changed, 70 insertions, 0 deletions

diff --git a/libavcodec/h264idct.c b/libavcodec/h264idct.c
new file mode 100644
index 0000000000..551197d37e
--- /dev/null
+++ b/libavcodec/h264idct.c
@@ -0,0 +1,70 @@
+/*
+ * H.264 IDCT
+ * Copyright (c) 2004 Michael Niedermayer <michaelni@gmx.at>
+ *
+ * This library 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.
+ *
+ * This library 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
+ *
+ */
+ 
+/**
+ * @file h264-idct.c
+ * H.264 IDCT.
+ * @author Michael Niedermayer <michaelni@gmx.at>
+ */
+ 
+#include "dsputil.h"
+
+static always_inline void idct_internal(uint8_t *dst, DCTELEM *block, int stride, int block_stride, int shift, int add){
+    int i;
+    uint8_t *cm = cropTbl + MAX_NEG_CROP;
+
+    block[0] += 1<<(shift-1);
+
+    for(i=0; i<4; i++){
+        const int z0=  block[0 + block_stride*i]     +  block[2 + block_stride*i];
+        const int z1=  block[0 + block_stride*i]     -  block[2 + block_stride*i];
+        const int z2= (block[1 + block_stride*i]>>1) -  block[3 + block_stride*i];
+        const int z3=  block[1 + block_stride*i]     + (block[3 + block_stride*i]>>1);
+
+        block[0 + block_stride*i]= z0 + z3;
+        block[1 + block_stride*i]= z1 + z2;
+        block[2 + block_stride*i]= z1 - z2;
+        block[3 + block_stride*i]= z0 - z3;
+    }
+
+    for(i=0; i<4; i++){
+        const int z0=  block[i + block_stride*0]     +  block[i + block_stride*2];
+        const int z1=  block[i + block_stride*0]     -  block[i + block_stride*2];
+        const int z2= (block[i + block_stride*1]>>1) -  block[i + block_stride*3];
+        const int z3=  block[i + block_stride*1]     + (block[i + block_stride*3]>>1);
+
+        dst[i + 0*stride]= cm[ add*dst[i + 0*stride] + ((z0 + z3) >> shift) ];
+        dst[i + 1*stride]= cm[ add*dst[i + 1*stride] + ((z1 + z2) >> shift) ];
+        dst[i + 2*stride]= cm[ add*dst[i + 2*stride] + ((z1 - z2) >> shift) ];
+        dst[i + 3*stride]= cm[ add*dst[i + 3*stride] + ((z0 - z3) >> shift) ];
+    }
+}
+
+void ff_h264_idct_add_c(uint8_t *dst, DCTELEM *block, int stride){
+    idct_internal(dst, block, stride, 4, 6, 1);
+}
+
+void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block){
+    idct_internal(dst, block, stride, 8, 3, 1);
+}
+
+void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block){
+    idct_internal(dst, block, stride, 8, 3, 0);
+}