blob: d74fe0cde42315c9ce37d607d48ff0fee198fef6 [file] [log] [blame]
* Copyright (c) 2017 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 "./vpx_config.h"
#include "vpx/vpx_integer.h"
static INLINE int32x2_t horizontal_add_int16x8(const int16x8_t a) {
const int32x4_t b = vpaddlq_s16(a);
const int64x2_t c = vpaddlq_s32(b);
return vadd_s32(vreinterpret_s32_s64(vget_low_s64(c)),
static INLINE uint32x2_t horizontal_add_uint16x8(const uint16x8_t a) {
const uint32x4_t b = vpaddlq_u16(a);
const uint64x2_t c = vpaddlq_u32(b);
return vadd_u32(vreinterpret_u32_u64(vget_low_u64(c)),
static INLINE uint32x2_t horizontal_add_long_uint16x8(const uint16x8_t a,
const uint16x8_t b) {
const uint32x4_t c = vpaddlq_u16(a);
const uint32x4_t d = vpadalq_u16(c, b);
const uint64x2_t e = vpaddlq_u32(d);
return vadd_u32(vreinterpret_u32_u64(vget_low_u64(e)),
static INLINE uint32x2_t horizontal_add_uint32x4(const uint32x4_t a) {
const uint64x2_t b = vpaddlq_u32(a);
return vadd_u32(vreinterpret_u32_u64(vget_low_u64(b)),