[x265] [PATCH] primitves: add c primitives for the following :

[Aarthi Thirumalai]

# HG changeset patch
# User Aarthi Thirumalai
# Date 1381488011 -19800
#      Fri Oct 11 16:10:11 2013 +0530
# Node ID 9b9c6766967dc99cab93c3e09514346606125b3e
# Parent  c6d89dc62e191f56f63dbcb1781a6494da50a70d
primitves: add c primitives for the following :

compute AC energy for each block
copy pixels of chroma plane

diff -r c6d89dc62e19 -r 9b9c6766967d source/common/pixel.cpp
--- a/source/common/pixel.cpp	Fri Oct 11 01:47:53 2013 -0500
+++ b/source/common/pixel.cpp	Fri Oct 11 16:10:11 2013 +0530
@@ -688,6 +688,33 @@
     }
     return ssim;
 }
+
+template<int w, int h>
+uint64_t pixel_var(pixel *pix, intptr_t i_stride)
+{
+    uint32_t sum = 0, sqr = 0;
+    for (int y = 0; y < h; y++)
+    {
+        for (int x = 0; x < w; x++)
+        {
+            sum += pix[x];
+            sqr += pix[x] * pix[x];
+        }
+        pix += i_stride;
+    }
+    return sum + ((uint64_t)sqr << 32);
+}
+
+void plane_copy_deinterleave_chroma(pixel *dstu, intptr_t dstuStride, pixel *dstv, intptr_t dstvStride,
+                                    pixel *src,  intptr_t srcStride, int w, int h)
+{
+    for (int y = 0; y < h; y++, dstu += dstuStride, dstv += dstvStride, src += srcStride)
+        for (int x = 0; x < w; x++)
+        {
+            dstu[x] = src[2 * x];
+            dstv[x] = src[2 * x + 1];
+        }
+}
 }  // end anonymous namespace
 
 namespace x265 {
@@ -905,5 +932,9 @@
     p.frame_init_lowres_core = frame_init_lowres_core;
     p.ssim_4x4x2_core = ssim_4x4x2_core;
     p.ssim_end_4 = ssim_end_4;
+
+    p.var[PARTITION_16x16] = pixel_var<16,16>;
+    p.var[PARTITION_8x8] = pixel_var<8,8>;
+    p.plane_copy_deinterleave_c = plane_copy_deinterleave_chroma;
 }
 }
diff -r c6d89dc62e19 -r 9b9c6766967d source/common/primitives.h
--- a/source/common/primitives.h	Fri Oct 11 01:47:53 2013 -0500
+++ b/source/common/primitives.h	Fri Oct 11 16:10:11 2013 +0530
@@ -202,6 +202,8 @@
 typedef void (*extendCURowBorder_t)(pixel* txt, intptr_t stride, int width, int height, int marginX);
 typedef void (*ssim_4x4x2_core_t)(const pixel *pix1, intptr_t stride1, const pixel *pix2, intptr_t stride2, ssim_t sums[2][4]);
 typedef float (*ssim_end4_t)(ssim_t sum0[5][4], ssim_t sum1[5][4], int width);
+typedef uint64_t (*var_t)(pixel *pix, intptr_t stride);
+typedef void (*plane_copy_deinterleave_t)(pixel *dstu, intptr_t dstuStride, pixel *dstv, intptr_t dstvStride, pixel *src,  intptr_t srcStride, int w, int h);
 
 /* Define a structure containing function pointers to optimized encoder
  * primitives.  Each pointer can reference either an assembly routine,
@@ -261,6 +263,8 @@
     downscale_t     frame_init_lowres_core;
     ssim_4x4x2_core_t ssim_4x4x2_core;
     ssim_end4_t       ssim_end_4;
+    var_t             var[NUM_PARTITIONS];
+    plane_copy_deinterleave_t plane_copy_deinterleave_c;
 };
 
 /* This copy of the table is what gets used by the encoder.