* adding integer/floating point AAN implementations for DCT 2-4-8

Originally committed as revision 2430 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 files changed, 107 insertions, 0 deletions

diff --git a/libavcodec/jfdctfst.c b/libavcodec/jfdctfst.c
index 899768d361..acaf284cd2 100644
--- a/libavcodec/jfdctfst.c
+++ b/libavcodec/jfdctfst.c
@@ -228,6 +228,113 @@ fdct_ifast (DCTELEM * data)
   }
 }
 
+/*
+ * Perform the forward 2-4-8 DCT on one block of samples.
+ */
+
+GLOBAL(void)
+fdct_ifast248 (DCTELEM * data)
+{
+  DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
+  DCTELEM tmp10, tmp11, tmp12, tmp13;
+  DCTELEM z1, z2, z3, z4, z5, z11, z13;
+  DCTELEM *dataptr;
+  int ctr;
+  SHIFT_TEMPS
+
+  /* Pass 1: process rows. */
+
+  dataptr = data;
+  for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
+    tmp0 = dataptr[0] + dataptr[7];
+    tmp7 = dataptr[0] - dataptr[7];
+    tmp1 = dataptr[1] + dataptr[6];
+    tmp6 = dataptr[1] - dataptr[6];
+    tmp2 = dataptr[2] + dataptr[5];
+    tmp5 = dataptr[2] - dataptr[5];
+    tmp3 = dataptr[3] + dataptr[4];
+    tmp4 = dataptr[3] - dataptr[4];
+    
+    /* Even part */
+    
+    tmp10 = tmp0 + tmp3;	/* phase 2 */
+    tmp13 = tmp0 - tmp3;
+    tmp11 = tmp1 + tmp2;
+    tmp12 = tmp1 - tmp2;
+    
+    dataptr[0] = tmp10 + tmp11; /* phase 3 */
+    dataptr[4] = tmp10 - tmp11;
+    
+    z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781); /* c4 */
+    dataptr[2] = tmp13 + z1;	/* phase 5 */
+    dataptr[6] = tmp13 - z1;
+    
+    /* Odd part */
+
+    tmp10 = tmp4 + tmp5;	/* phase 2 */
+    tmp11 = tmp5 + tmp6;
+    tmp12 = tmp6 + tmp7;
+
+    /* The rotator is modified from fig 4-8 to avoid extra negations. */
+    z5 = MULTIPLY(tmp10 - tmp12, FIX_0_382683433); /* c6 */
+    z2 = MULTIPLY(tmp10, FIX_0_541196100) + z5; /* c2-c6 */
+    z4 = MULTIPLY(tmp12, FIX_1_306562965) + z5; /* c2+c6 */
+    z3 = MULTIPLY(tmp11, FIX_0_707106781); /* c4 */
+
+    z11 = tmp7 + z3;		/* phase 5 */
+    z13 = tmp7 - z3;
+
+    dataptr[5] = z13 + z2;	/* phase 6 */
+    dataptr[3] = z13 - z2;
+    dataptr[1] = z11 + z4;
+    dataptr[7] = z11 - z4;
+
+    dataptr += DCTSIZE;		/* advance pointer to next row */
+  }
+
+  /* Pass 2: process columns. */
+
+  dataptr = data;
+  for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
+    tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*1];
+    tmp1 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*3];
+    tmp2 = dataptr[DCTSIZE*4] + dataptr[DCTSIZE*5];
+    tmp3 = dataptr[DCTSIZE*6] + dataptr[DCTSIZE*7];
+    tmp4 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*1];
+    tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*3];
+    tmp6 = dataptr[DCTSIZE*4] - dataptr[DCTSIZE*5];
+    tmp7 = dataptr[DCTSIZE*6] - dataptr[DCTSIZE*7];
+
+    /* Even part */
+    
+    tmp10 = tmp0 + tmp3;
+    tmp11 = tmp1 + tmp2;
+    tmp12 = tmp1 - tmp2;
+    tmp13 = tmp0 - tmp3;
+    
+    dataptr[DCTSIZE*0] = tmp10 + tmp11;
+    dataptr[DCTSIZE*4] = tmp10 - tmp11;
+    
+    z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781);
+    dataptr[DCTSIZE*2] = tmp13 + z1;
+    dataptr[DCTSIZE*6] = tmp13 - z1;
+
+    tmp10 = tmp4 + tmp7;
+    tmp11 = tmp5 + tmp6;
+    tmp12 = tmp5 - tmp6;
+    tmp13 = tmp4 - tmp7;
+    
+    dataptr[DCTSIZE*1] = tmp10 + tmp11;
+    dataptr[DCTSIZE*5] = tmp10 - tmp11;
+    
+    z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781);
+    dataptr[DCTSIZE*3] = tmp13 + z1;
+    dataptr[DCTSIZE*7] = tmp13 - z1;
+    
+    dataptr++;			/* advance pointer to next column */
+  }
+}
+
 
 #undef GLOBAL
 #undef CONST_BITS