Port renaming changes from AOMedia
Cherry-Picked the following commits:
0defd8f Changed "WebM" to "AOMedia" & "webm" to "aomedia"
54e6676 Replace "VPx" by "AVx"
5082a36 Change "Vpx" to "Avx"
7df44f1 Replace "Vp9" w/ "Av1"
967f722 Remove kVp9CodecId
828f30c Change "Vp8" to "AOM"
030b5ff AUTHORS regenerated
2524cae Add ref-mv experimental flag
016762b Change copyright notice to AOMedia form
81e5526 Replace vp9 w/ av1
9b94565 Add missing files
fa8ca9f Change "vp9" to "av1"
ec838b7 Convert "vp8" to "aom"
80edfa0 Change "VP9" to "AV1"
d1a11fb Change "vp8" to "aom"
7b58251 Point to WebM test data
dd1a5c8 Replace "VP8" with "AOM"
ff00fc0 Change "VPX" to "AOM"
01dee0b Change "vp10" to "av1" in source code
cebe6f0 Convert "vpx" to "aom"
17b0567 rename vp10*.mk to av1_*.mk
fe5f8a8 rename files vp10_* to av1_*
Change-Id: I6fc3d18eb11fc171e46140c836ad5339cf6c9419
diff --git a/aom_dsp/arm/aom_convolve_avg_neon.c b/aom_dsp/arm/aom_convolve_avg_neon.c
new file mode 100644
index 0000000..cfdfed9
--- /dev/null
+++ b/aom_dsp/arm/aom_convolve_avg_neon.c
@@ -0,0 +1,144 @@
+/*
+ * 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>
+
+#include "./aom_dsp_rtcd.h"
+#include "aom/aom_integer.h"
+
+void aom_convolve_avg_neon(const uint8_t *src, // r0
+ ptrdiff_t src_stride, // r1
+ uint8_t *dst, // r2
+ ptrdiff_t dst_stride, // r3
+ const int16_t *filter_x, int filter_x_stride,
+ const int16_t *filter_y, int filter_y_stride, int w,
+ int h) {
+ uint8_t *d;
+ uint8x8_t d0u8, d1u8, d2u8, d3u8;
+ uint32x2_t d0u32, d2u32;
+ uint8x16_t q0u8, q1u8, q2u8, q3u8, q8u8, q9u8, q10u8, q11u8;
+ (void)filter_x;
+ (void)filter_x_stride;
+ (void)filter_y;
+ (void)filter_y_stride;
+
+ d = dst;
+ if (w > 32) { // avg64
+ for (; h > 0; h -= 1) {
+ q0u8 = vld1q_u8(src);
+ q1u8 = vld1q_u8(src + 16);
+ q2u8 = vld1q_u8(src + 32);
+ q3u8 = vld1q_u8(src + 48);
+ src += src_stride;
+ q8u8 = vld1q_u8(d);
+ q9u8 = vld1q_u8(d + 16);
+ q10u8 = vld1q_u8(d + 32);
+ q11u8 = vld1q_u8(d + 48);
+ d += dst_stride;
+
+ q0u8 = vrhaddq_u8(q0u8, q8u8);
+ q1u8 = vrhaddq_u8(q1u8, q9u8);
+ q2u8 = vrhaddq_u8(q2u8, q10u8);
+ q3u8 = vrhaddq_u8(q3u8, q11u8);
+
+ vst1q_u8(dst, q0u8);
+ vst1q_u8(dst + 16, q1u8);
+ vst1q_u8(dst + 32, q2u8);
+ vst1q_u8(dst + 48, q3u8);
+ dst += dst_stride;
+ }
+ } else if (w == 32) { // avg32
+ for (; h > 0; h -= 2) {
+ q0u8 = vld1q_u8(src);
+ q1u8 = vld1q_u8(src + 16);
+ src += src_stride;
+ q2u8 = vld1q_u8(src);
+ q3u8 = vld1q_u8(src + 16);
+ src += src_stride;
+ q8u8 = vld1q_u8(d);
+ q9u8 = vld1q_u8(d + 16);
+ d += dst_stride;
+ q10u8 = vld1q_u8(d);
+ q11u8 = vld1q_u8(d + 16);
+ d += dst_stride;
+
+ q0u8 = vrhaddq_u8(q0u8, q8u8);
+ q1u8 = vrhaddq_u8(q1u8, q9u8);
+ q2u8 = vrhaddq_u8(q2u8, q10u8);
+ q3u8 = vrhaddq_u8(q3u8, q11u8);
+
+ vst1q_u8(dst, q0u8);
+ vst1q_u8(dst + 16, q1u8);
+ dst += dst_stride;
+ vst1q_u8(dst, q2u8);
+ vst1q_u8(dst + 16, q3u8);
+ dst += dst_stride;
+ }
+ } else if (w > 8) { // avg16
+ for (; h > 0; h -= 2) {
+ q0u8 = vld1q_u8(src);
+ src += src_stride;
+ q1u8 = vld1q_u8(src);
+ src += src_stride;
+ q2u8 = vld1q_u8(d);
+ d += dst_stride;
+ q3u8 = vld1q_u8(d);
+ d += dst_stride;
+
+ q0u8 = vrhaddq_u8(q0u8, q2u8);
+ q1u8 = vrhaddq_u8(q1u8, q3u8);
+
+ vst1q_u8(dst, q0u8);
+ dst += dst_stride;
+ vst1q_u8(dst, q1u8);
+ dst += dst_stride;
+ }
+ } else if (w == 8) { // avg8
+ for (; h > 0; h -= 2) {
+ d0u8 = vld1_u8(src);
+ src += src_stride;
+ d1u8 = vld1_u8(src);
+ src += src_stride;
+ d2u8 = vld1_u8(d);
+ d += dst_stride;
+ d3u8 = vld1_u8(d);
+ d += dst_stride;
+
+ q0u8 = vcombine_u8(d0u8, d1u8);
+ q1u8 = vcombine_u8(d2u8, d3u8);
+ q0u8 = vrhaddq_u8(q0u8, q1u8);
+
+ vst1_u8(dst, vget_low_u8(q0u8));
+ dst += dst_stride;
+ vst1_u8(dst, vget_high_u8(q0u8));
+ dst += dst_stride;
+ }
+ } else { // avg4
+ for (; h > 0; h -= 2) {
+ d0u32 = vld1_lane_u32((const uint32_t *)src, d0u32, 0);
+ src += src_stride;
+ d0u32 = vld1_lane_u32((const uint32_t *)src, d0u32, 1);
+ src += src_stride;
+ d2u32 = vld1_lane_u32((const uint32_t *)d, d2u32, 0);
+ d += dst_stride;
+ d2u32 = vld1_lane_u32((const uint32_t *)d, d2u32, 1);
+ d += dst_stride;
+
+ d0u8 = vrhadd_u8(vreinterpret_u8_u32(d0u32), vreinterpret_u8_u32(d2u32));
+
+ d0u32 = vreinterpret_u32_u8(d0u8);
+ vst1_lane_u32((uint32_t *)dst, d0u32, 0);
+ dst += dst_stride;
+ vst1_lane_u32((uint32_t *)dst, d0u32, 1);
+ dst += dst_stride;
+ }
+ }
+ return;
+}