Added 4x4 SATD (Hadamard)

Taken from HM 13.0

src/picture.c

@@ -368,6 +368,101 @@ double image_psnr(pixel *frame1, pixel *frame2, int32_t x, int32_t y)
   return 10 * log10((pixels * PSNRMAX) / ((double)error_sum));
 }
 
+/**
+ * \brief  Calculate SATD between two 4x4 blocks inside bigger arrays.
+ * From HM 13.0
+ */
+static unsigned satd_16bit_4x4(pixel *piOrg,pixel *piCur)
+{
+  int32_t k, satd = 0, diff[16], m[16], d[16];
+  int32_t iStrideOrg = 4, iStrideCur = 4;
+  for( k = 0; k < 16; k+=4 ) {
+    diff[k+0] = piOrg[0] - piCur[0];
+    diff[k+1] = piOrg[1] - piCur[1];
+    diff[k+2] = piOrg[2] - piCur[2];
+    diff[k+3] = piOrg[3] - piCur[3];
+
+    piCur += iStrideCur;
+    piOrg += iStrideOrg;
+  }
+
+  /*===== hadamard transform =====*/
+  m[ 0] = diff[ 0] + diff[12];
+  m[ 1] = diff[ 1] + diff[13];
+  m[ 2] = diff[ 2] + diff[14];
+  m[ 3] = diff[ 3] + diff[15];
+  m[ 4] = diff[ 4] + diff[ 8];
+  m[ 5] = diff[ 5] + diff[ 9];
+  m[ 6] = diff[ 6] + diff[10];
+  m[ 7] = diff[ 7] + diff[11];
+  m[ 8] = diff[ 4] - diff[ 8];
+  m[ 9] = diff[ 5] - diff[ 9];
+  m[10] = diff[ 6] - diff[10];
+  m[11] = diff[ 7] - diff[11];
+  m[12] = diff[ 0] - diff[12];
+  m[13] = diff[ 1] - diff[13];
+  m[14] = diff[ 2] - diff[14];
+  m[15] = diff[ 3] - diff[15];
+
+  d[ 0] = m[ 0] + m[ 4];
+  d[ 1] = m[ 1] + m[ 5];
+  d[ 2] = m[ 2] + m[ 6];
+  d[ 3] = m[ 3] + m[ 7];
+  d[ 4] = m[ 8] + m[12];
+  d[ 5] = m[ 9] + m[13];
+  d[ 6] = m[10] + m[14];
+  d[ 7] = m[11] + m[15];
+  d[ 8] = m[ 0] - m[ 4];
+  d[ 9] = m[ 1] - m[ 5];
+  d[10] = m[ 2] - m[ 6];
+  d[11] = m[ 3] - m[ 7];
+  d[12] = m[12] - m[ 8];
+  d[13] = m[13] - m[ 9];
+  d[14] = m[14] - m[10];
+  d[15] = m[15] - m[11];
+
+  m[ 0] = d[ 0] + d[ 3];
+  m[ 1] = d[ 1] + d[ 2];
+  m[ 2] = d[ 1] - d[ 2];
+  m[ 3] = d[ 0] - d[ 3];
+  m[ 4] = d[ 4] + d[ 7];
+  m[ 5] = d[ 5] + d[ 6];
+  m[ 6] = d[ 5] - d[ 6];
+  m[ 7] = d[ 4] - d[ 7];
+  m[ 8] = d[ 8] + d[11];
+  m[ 9] = d[ 9] + d[10];
+  m[10] = d[ 9] - d[10];
+  m[11] = d[ 8] - d[11];
+  m[12] = d[12] + d[15];
+  m[13] = d[13] + d[14];
+  m[14] = d[13] - d[14];
+  m[15] = d[12] - d[15];
+
+  d[ 0] = m[ 0] + m[ 1];
+  d[ 1] = m[ 0] - m[ 1];
+  d[ 2] = m[ 2] + m[ 3];
+  d[ 3] = m[ 3] - m[ 2];
+  d[ 4] = m[ 4] + m[ 5];
+  d[ 5] = m[ 4] - m[ 5];
+  d[ 6] = m[ 6] + m[ 7];
+  d[ 7] = m[ 7] - m[ 6];
+  d[ 8] = m[ 8] + m[ 9];
+  d[ 9] = m[ 8] - m[ 9];
+  d[10] = m[10] + m[11];
+  d[11] = m[11] - m[10];
+  d[12] = m[12] + m[13];
+  d[13] = m[12] - m[13];
+  d[14] = m[14] + m[15];
+  d[15] = m[15] - m[14];
+
+  for (k=0; k<16; ++k) {
+    satd += abs(d[k]);
+  }
+  satd = ((satd+1)>>1);
+
+  return satd;
+}
+
 /**
  * \brief  Calculate SATD between two 8x8 blocks inside bigger arrays.
  */
@@ -463,9 +558,9 @@ static unsigned satd_16bit_8x8_general(pixel *piOrg, int32_t iStrideOrg,
   return sad;
 }
 
-// Function macro for defining hadamart calculating functions
-// for fixed size blocks. They calculate hadamart for integer
-// multiples of 8x8 with the 8x8 hadamart function.
+// Function macro for defining hadamard calculating functions
+// for fixed size blocks. They calculate hadamard for integer
+// multiples of 8x8 with the 8x8 hadamard function.
 #define SATD_NXN(n, pixel_type, suffix) \
   static unsigned satd_ ## suffix ## _ ## n ## x ## n( \
                   pixel_type *block1, pixel_type *block2) \
@@ -523,6 +618,8 @@ SAD_NXN(64, pixel, 16bit)
 cost_16bit_nxn_func get_satd_16bit_nxn_func(unsigned n)
 {
   switch (n) {
+  case 4:
+    return &satd_16bit_4x4;
   case 8:
     return &satd_16bit_8x8;
   case 16: