libvpx: Pull from upstream

source/libvpx/vp9/common/x86/vp9_filter_sse2.c

 /*
  *  Copyright (c) 2012 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.
  */
 
 #include <assert.h> // for alignment checks
 #include <emmintrin.h> // SSE2
 #include "vp9/common/vp9_filter.h"
+#include "vpx_ports/emmintrin_compat.h"
 #include "vpx_ports/mem.h" // for DECLARE_ALIGNED
 #include "vp9_rtcd.h"
 
 // TODO(cd): After cleanup, commit faster versions for non 4x4 size. This is
 //           just a quick partial snapshot so that other can already use some
 //           speedup.
 // TODO(cd): Use vectorized 8 tap filtering code as speedup to pure C 6 tap
 //           filtering.
 // TODO(cd): Add some comments, better variable naming.
 // TODO(cd): Maybe use _mm_maddubs_epi16 if smaller filter coeficients (no sum
@@ skipping 256 matching lines @@
 ) {
   int i, j;
   for (i=0; i<16; i+=4) {
     for (j=0; j<16; j+=4) {
       vp9_filter_block2d_4x4_8_sse2(src_ptr + j + i*src_stride, src_stride,
                                     HFilter_aligned16, VFilter_aligned16,
                                     dst_ptr + j + i*dst_stride, dst_stride);
     }
   }
 }