36 lines
1.1 KiB
C
36 lines
1.1 KiB
C
|
/*
|
||
|
|
* 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_dsp_rtcd.h"
|
||
|
|
#include "./vpx_config.h"
|
||
|
|
|
||
|
|
void vpx_fdct8x8_1_neon(const int16_t *input, tran_low_t *output, int stride) {
|
||
|
|
int r;
|
||
|
|
int16x8_t sum = vld1q_s16(&input[0]);
|
||
|
|
for (r = 1; r < 8; ++r) {
|
||
|
|
const int16x8_t input_00 = vld1q_s16(&input[r * stride]);
|
||
|
|
sum = vaddq_s16(sum, input_00);
|
||
|
|
}
|
||
|
|
{
|
||
|
|
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)));
|
||
|
|
#if CONFIG_VP9_HIGHBITDEPTH
|
||
|
|
output[0] = vget_lane_s32(c, 0);
|
||
|
|
#else
|
||
|
|
output[0] = vget_lane_s16(vreinterpret_s16_s32(c), 0);
|
||
|
|
#endif
|
||
|
|
output[1] = 0;
|
||
|
|
}
|
||
|
|
}
|