libvpx: Pull from upstream

source/libvpx/vp9/encoder/arm/neon/vp9_dct_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.
  */
 
@@ skipping 14 matching lines @@
   {
     const int32x4_t a = vpaddlq_s16(sum);
     const int64x2_t b = vpaddlq_s32(a);
     const int32x2_t c = vadd_s32(vreinterpret_s32_s64(vget_low_s64(b)),
                                  vreinterpret_s32_s64(vget_high_s64(b)));
     output[0] = vget_lane_s16(vreinterpret_s16_s32(c), 0);
     output[1] = 0;
   }
 }
 
+void vp9_fdct8x8_quant_neon(const int16_t *input, int stride,
+                            int16_t* coeff_ptr, intptr_t n_coeffs,
+                            int skip_block, const int16_t* zbin_ptr,
+                            const int16_t* round_ptr, const int16_t* quant_ptr,
+                            const int16_t* quant_shift_ptr,
+                            int16_t* qcoeff_ptr, int16_t* dqcoeff_ptr,
+                            const int16_t* dequant_ptr, uint16_t* eob_ptr,
+                            const int16_t* scan_ptr,
+                            const int16_t* iscan_ptr) {
+  int16_t temp_buffer[64];
+  (void)coeff_ptr;
+
+  vp9_fdct8x8_neon(input, temp_buffer, stride);
+  vp9_quantize_fp_neon(temp_buffer, n_coeffs, skip_block, zbin_ptr, round_ptr,
+                       quant_ptr, quant_shift_ptr, qcoeff_ptr, dqcoeff_ptr,
+                       dequant_ptr, eob_ptr, scan_ptr, iscan_ptr);
+}
+
 void vp9_fdct8x8_neon(const int16_t *input, int16_t *final_output, int stride) {
   int i;
   // stage 1
   int16x8_t input_0 = vshlq_n_s16(vld1q_s16(&input[0 * stride]), 2);
   int16x8_t input_1 = vshlq_n_s16(vld1q_s16(&input[1 * stride]), 2);
   int16x8_t input_2 = vshlq_n_s16(vld1q_s16(&input[2 * stride]), 2);
   int16x8_t input_3 = vshlq_n_s16(vld1q_s16(&input[3 * stride]), 2);
   int16x8_t input_4 = vshlq_n_s16(vld1q_s16(&input[4 * stride]), 2);
   int16x8_t input_5 = vshlq_n_s16(vld1q_s16(&input[5 * stride]), 2);
   int16x8_t input_6 = vshlq_n_s16(vld1q_s16(&input[6 * stride]), 2);
@@ skipping 169 matching lines @@
     vst1q_s16(&final_output[1 * 8], input_1);
     vst1q_s16(&final_output[2 * 8], input_2);
     vst1q_s16(&final_output[3 * 8], input_3);
     vst1q_s16(&final_output[4 * 8], input_4);
     vst1q_s16(&final_output[5 * 8], input_5);
     vst1q_s16(&final_output[6 * 8], input_6);
     vst1q_s16(&final_output[7 * 8], input_7);
   }
 }