libvpx: Pull from upstream

source/libvpx/vp9/encoder/x86/vp9_avg_intrin_sse2.c

 /*
  *  Copyright (c) 2014 The WebM project authors. All Rights Reserved.
  *
  *  Use of this source code is governed by a BSD-style license
  *  that can be found in the LICENSE file in the root of the source
  *  tree. An additional intellectual property rights grant can be found
  *  in the file PATENTS.  All contributing project authors may
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
@@ skipping 246 matching lines @@
     __m128i coeff0 = _mm_load_si128((const __m128i *)coeff);
     __m128i coeff1 = _mm_load_si128((const __m128i *)(coeff + 64));
     __m128i coeff2 = _mm_load_si128((const __m128i *)(coeff + 128));
     __m128i coeff3 = _mm_load_si128((const __m128i *)(coeff + 192));
 
     __m128i b0 = _mm_add_epi16(coeff0, coeff1);
     __m128i b1 = _mm_sub_epi16(coeff0, coeff1);
     __m128i b2 = _mm_add_epi16(coeff2, coeff3);
     __m128i b3 = _mm_sub_epi16(coeff2, coeff3);
 
+    b0 = _mm_srai_epi16(b0, 1);
+    b1 = _mm_srai_epi16(b1, 1);
+    b2 = _mm_srai_epi16(b2, 1);
+    b3 = _mm_srai_epi16(b3, 1);
+
     coeff0 = _mm_add_epi16(b0, b2);
     coeff1 = _mm_add_epi16(b1, b3);
-    coeff0 = _mm_srai_epi16(coeff0, 1);
-    coeff1 = _mm_srai_epi16(coeff1, 1);
     _mm_store_si128((__m128i *)coeff, coeff0);
     _mm_store_si128((__m128i *)(coeff + 64), coeff1);
 
     coeff2 = _mm_sub_epi16(b0, b2);
     coeff3 = _mm_sub_epi16(b1, b3);
-    coeff2 = _mm_srai_epi16(coeff2, 1);
-    coeff3 = _mm_srai_epi16(coeff3, 1);
     _mm_store_si128((__m128i *)(coeff + 128), coeff2);
     _mm_store_si128((__m128i *)(coeff + 192), coeff3);
 
     coeff += 8;
   }
 }
 
 int16_t vp9_satd_sse2(const int16_t *coeff, int length) {
   int i;
   __m128i sum = _mm_load_si128((const __m128i *)coeff);
@@ skipping 126 matching lines @@
 
   v1  = _mm_srli_si128(sse, 8);
   sse = _mm_add_epi32(sse, v1);
   v1  = _mm_srli_epi64(sse, 32);
   sse = _mm_add_epi32(sse, v1);
 
   mean = _mm_extract_epi16(sum, 0);
 
   return _mm_cvtsi128_si32(sse) - ((mean * mean) >> (bwl + 2));
 }