libvpx: Pull from upstream

source/libvpx/vp8/common/arm/neon/bilinearpredict_neon.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.
  */
 
 #include <arm_neon.h>
 
-static const uint16_t bifilter4_coeff[8][2] = {
+static const uint8_t bifilter4_coeff[8][2] = {
     {128,   0},
     {112,  16},
     { 96,  32},
     { 80,  48},
     { 64,  64},
     { 48,  80},
     { 32,  96},
     { 16, 112}
 };
 
@@ skipping 33 matching lines @@
     } else {
         d2u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d3u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d4u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d5u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d6u8 = vld1_u8(src_ptr);
 
         q1u8 = vcombine_u8(d2u8, d3u8);
         q2u8 = vcombine_u8(d4u8, d5u8);
 
-        d0u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][0]);
-        d1u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][1]);
+        d0u8 = vdup_n_u8(bifilter4_coeff[xoffset][0]);
+        d1u8 = vdup_n_u8(bifilter4_coeff[xoffset][1]);
 
         q4u64  = vshrq_n_u64(vreinterpretq_u64_u8(q1u8), 8);
         q5u64  = vshrq_n_u64(vreinterpretq_u64_u8(q2u8), 8);
         d12u64 = vshr_n_u64(vreinterpret_u64_u8(d6u8), 8);
 
         d0u32x2 = vzip_u32(vreinterpret_u32_u8(vget_low_u8(q1u8)),
                            vreinterpret_u32_u8(vget_high_u8(q1u8)));
         d1u32x2 = vzip_u32(vreinterpret_u32_u8(vget_low_u8(q2u8)),
                            vreinterpret_u32_u8(vget_high_u8(q2u8)));
         d2u32x2 = vzip_u32(vreinterpret_u32_u64(vget_low_u64(q4u64)),
@@ skipping 69 matching lines @@
         d24u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d25u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d26u8 = vld1_u8(src_ptr);
     } else {
         q1u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q2u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q3u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q4u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q5u8 = vld1q_u8(src_ptr);
 
-        d0u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][0]);
-        d1u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][1]);
+        d0u8 = vdup_n_u8(bifilter4_coeff[xoffset][0]);
+        d1u8 = vdup_n_u8(bifilter4_coeff[xoffset][1]);
 
         q6u16 = vmull_u8(vget_low_u8(q1u8), d0u8);
         q7u16 = vmull_u8(vget_low_u8(q2u8), d0u8);
         q8u16 = vmull_u8(vget_low_u8(q3u8), d0u8);
         q9u16 = vmull_u8(vget_low_u8(q4u8), d0u8);
         q10u16 = vmull_u8(vget_low_u8(q5u8), d0u8);
 
         d3u8 = vext_u8(vget_low_u8(q1u8), vget_high_u8(q1u8), 1);
         d5u8 = vext_u8(vget_low_u8(q2u8), vget_high_u8(q2u8), 1);
         d7u8 = vext_u8(vget_low_u8(q3u8), vget_high_u8(q3u8), 1);
@@ skipping 68 matching lines @@
         d27u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d28u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d29u8 = vld1_u8(src_ptr); src_ptr += src_pixels_per_line;
         d30u8 = vld1_u8(src_ptr);
     } else {
         q1u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q2u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q3u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
         q4u8 = vld1q_u8(src_ptr); src_ptr += src_pixels_per_line;
 
-        d0u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][0]);
-        d1u8 = vdup_n_u8((uint8_t)bifilter4_coeff[xoffset][1]);
+        d0u8 = vdup_n_u8(bifilter4_coeff[xoffset][0]);
+        d1u8 = vdup_n_u8(bifilter4_coeff[xoffset][1]);
 
         q6u16 = vmull_u8(vget_low_u8(q1u8), d0u8);
         q7u16 = vmull_u8(vget_low_u8(q2u8), d0u8);
         q8u16 = vmull_u8(vget_low_u8(q3u8), d0u8);
         q9u16 = vmull_u8(vget_low_u8(q4u8), d0u8);
 
         d3u8 = vext_u8(vget_low_u8(q1u8), vget_high_u8(q1u8), 1);
         d5u8 = vext_u8(vget_low_u8(q2u8), vget_high_u8(q2u8), 1);
         d7u8 = vext_u8(vget_low_u8(q3u8), vget_high_u8(q3u8), 1);
         d9u8 = vext_u8(vget_low_u8(q4u8), vget_high_u8(q4u8), 1);
@@ skipping 430 matching lines @@
 
         q11u8 = q15u8;
 
         vst1q_u8((uint8_t *)dst_ptr, q1u8); dst_ptr += dst_pitch;
         vst1q_u8((uint8_t *)dst_ptr, q2u8); dst_ptr += dst_pitch;
         vst1q_u8((uint8_t *)dst_ptr, q3u8); dst_ptr += dst_pitch;
         vst1q_u8((uint8_t *)dst_ptr, q4u8); dst_ptr += dst_pitch;
     }
     return;
 }