You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

105 lines
4.0 KiB

/*
* VP9 compatible video decoder
*
* Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com>
* Copyright (C) 2013 Clément Bœsch <u pkh me>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "config.h"
#include "libavutil/attributes.h"
#include "libavutil/avassert.h"
#include "libavutil/mem_internal.h"
#include "vp9dsp.h"
const DECLARE_ALIGNED(16, int16_t, ff_vp9_subpel_filters)[3][16][8] = {
[FILTER_8TAP_REGULAR] = {
{ 0, 0, 0, 128, 0, 0, 0, 0 },
{ 0, 1, -5, 126, 8, -3, 1, 0 },
{ -1, 3, -10, 122, 18, -6, 2, 0 },
{ -1, 4, -13, 118, 27, -9, 3, -1 },
{ -1, 4, -16, 112, 37, -11, 4, -1 },
{ -1, 5, -18, 105, 48, -14, 4, -1 },
{ -1, 5, -19, 97, 58, -16, 5, -1 },
{ -1, 6, -19, 88, 68, -18, 5, -1 },
{ -1, 6, -19, 78, 78, -19, 6, -1 },
{ -1, 5, -18, 68, 88, -19, 6, -1 },
{ -1, 5, -16, 58, 97, -19, 5, -1 },
{ -1, 4, -14, 48, 105, -18, 5, -1 },
{ -1, 4, -11, 37, 112, -16, 4, -1 },
{ -1, 3, -9, 27, 118, -13, 4, -1 },
{ 0, 2, -6, 18, 122, -10, 3, -1 },
{ 0, 1, -3, 8, 126, -5, 1, 0 },
}, [FILTER_8TAP_SHARP] = {
{ 0, 0, 0, 128, 0, 0, 0, 0 },
{ -1, 3, -7, 127, 8, -3, 1, 0 },
{ -2, 5, -13, 125, 17, -6, 3, -1 },
{ -3, 7, -17, 121, 27, -10, 5, -2 },
{ -4, 9, -20, 115, 37, -13, 6, -2 },
{ -4, 10, -23, 108, 48, -16, 8, -3 },
{ -4, 10, -24, 100, 59, -19, 9, -3 },
{ -4, 11, -24, 90, 70, -21, 10, -4 },
{ -4, 11, -23, 80, 80, -23, 11, -4 },
{ -4, 10, -21, 70, 90, -24, 11, -4 },
{ -3, 9, -19, 59, 100, -24, 10, -4 },
{ -3, 8, -16, 48, 108, -23, 10, -4 },
{ -2, 6, -13, 37, 115, -20, 9, -4 },
{ -2, 5, -10, 27, 121, -17, 7, -3 },
{ -1, 3, -6, 17, 125, -13, 5, -2 },
{ 0, 1, -3, 8, 127, -7, 3, -1 },
}, [FILTER_8TAP_SMOOTH] = {
{ 0, 0, 0, 128, 0, 0, 0, 0 },
{ -3, -1, 32, 64, 38, 1, -3, 0 },
{ -2, -2, 29, 63, 41, 2, -3, 0 },
{ -2, -2, 26, 63, 43, 4, -4, 0 },
{ -2, -3, 24, 62, 46, 5, -4, 0 },
{ -2, -3, 21, 60, 49, 7, -4, 0 },
{ -1, -4, 18, 59, 51, 9, -4, 0 },
{ -1, -4, 16, 57, 53, 12, -4, -1 },
{ -1, -4, 14, 55, 55, 14, -4, -1 },
{ -1, -4, 12, 53, 57, 16, -4, -1 },
{ 0, -4, 9, 51, 59, 18, -4, -1 },
{ 0, -4, 7, 49, 60, 21, -3, -2 },
{ 0, -4, 5, 46, 62, 24, -3, -2 },
{ 0, -4, 4, 43, 63, 26, -2, -2 },
{ 0, -3, 2, 41, 63, 29, -2, -2 },
{ 0, -3, 1, 38, 64, 32, -1, -3 },
}
};
av_cold void ff_vp9dsp_init(VP9DSPContext *dsp, int bpp, int bitexact)
{
if (bpp == 8) {
ff_vp9dsp_init_8(dsp);
} else if (bpp == 10) {
ff_vp9dsp_init_10(dsp);
} else {
av_assert0(bpp == 12);
ff_vp9dsp_init_12(dsp);
}
aarch64: vp9: Add NEON optimizations of VP9 MC functions This work is sponsored by, and copyright, Google. These are ported from the ARM version; it is essentially a 1:1 port with no extra added features, but with some hand tuning (especially for the plain copy/avg functions). The ARM version isn't very register starved to begin with, so there's not much to be gained from having more spare registers here - we only avoid having to clobber callee-saved registers. Examples of runtimes vs the 32 bit version, on a Cortex A53: ARM AArch64 vp9_avg4_neon: 27.2 23.7 vp9_avg8_neon: 56.5 54.7 vp9_avg16_neon: 169.9 167.4 vp9_avg32_neon: 585.8 585.2 vp9_avg64_neon: 2460.3 2294.7 vp9_avg_8tap_smooth_4h_neon: 132.7 125.2 vp9_avg_8tap_smooth_4hv_neon: 478.8 442.0 vp9_avg_8tap_smooth_4v_neon: 126.0 93.7 vp9_avg_8tap_smooth_8h_neon: 241.7 234.2 vp9_avg_8tap_smooth_8hv_neon: 690.9 646.5 vp9_avg_8tap_smooth_8v_neon: 245.0 205.5 vp9_avg_8tap_smooth_64h_neon: 11273.2 11280.1 vp9_avg_8tap_smooth_64hv_neon: 22980.6 22184.1 vp9_avg_8tap_smooth_64v_neon: 11549.7 10781.1 vp9_put4_neon: 18.0 17.2 vp9_put8_neon: 40.2 37.7 vp9_put16_neon: 97.4 99.5 vp9_put32_neon/armv8: 346.0 307.4 vp9_put64_neon/armv8: 1319.0 1107.5 vp9_put_8tap_smooth_4h_neon: 126.7 118.2 vp9_put_8tap_smooth_4hv_neon: 465.7 434.0 vp9_put_8tap_smooth_4v_neon: 113.0 86.5 vp9_put_8tap_smooth_8h_neon: 229.7 221.6 vp9_put_8tap_smooth_8hv_neon: 658.9 621.3 vp9_put_8tap_smooth_8v_neon: 215.0 187.5 vp9_put_8tap_smooth_64h_neon: 10636.7 10627.8 vp9_put_8tap_smooth_64hv_neon: 21076.8 21026.9 vp9_put_8tap_smooth_64v_neon: 9635.0 9632.4 These are generally about as fast as the corresponding ARM routines on the same CPU (at least on the A53), in most cases marginally faster. The speedup vs C code is pretty much the same as for the 32 bit case; on the A53 it's around 6-13x for ther larger 8tap filters. The exact speedup varies a little, since the C versions generally don't end up exactly as slow/fast as on 32 bit. This is an adapted cherry-pick from libav commit 383d96aa2229f644d9bd77b821ed3a309da5e9fc. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
8 years ago
if (ARCH_AARCH64) ff_vp9dsp_init_aarch64(dsp, bpp);
arm: vp9: Add NEON optimizations of VP9 MC functions This work is sponsored by, and copyright, Google. The filter coefficients are signed values, where the product of the multiplication with one individual filter coefficient doesn't overflow a 16 bit signed value (the largest filter coefficient is 127). But when the products are accumulated, the resulting sum can overflow the 16 bit signed range. Instead of accumulating in 32 bit, we accumulate the largest product (either index 3 or 4) last with a saturated addition. (The VP8 MC asm does something similar, but slightly simpler, by accumulating each half of the filter separately. In the VP9 MC filters, each half of the filter can also overflow though, so the largest component has to be handled individually.) Examples of relative speedup compared to the C version, from checkasm: Cortex A7 A8 A9 A53 vp9_avg4_neon: 1.71 1.15 1.42 1.49 vp9_avg8_neon: 2.51 3.63 3.14 2.58 vp9_avg16_neon: 2.95 6.76 3.01 2.84 vp9_avg32_neon: 3.29 6.64 2.85 3.00 vp9_avg64_neon: 3.47 6.67 3.14 2.80 vp9_avg_8tap_smooth_4h_neon: 3.22 4.73 2.76 4.67 vp9_avg_8tap_smooth_4hv_neon: 3.67 4.76 3.28 4.71 vp9_avg_8tap_smooth_4v_neon: 5.52 7.60 4.60 6.31 vp9_avg_8tap_smooth_8h_neon: 6.22 9.04 5.12 9.32 vp9_avg_8tap_smooth_8hv_neon: 6.38 8.21 5.72 8.17 vp9_avg_8tap_smooth_8v_neon: 9.22 12.66 8.15 11.10 vp9_avg_8tap_smooth_64h_neon: 7.02 10.23 5.54 11.58 vp9_avg_8tap_smooth_64hv_neon: 6.76 9.46 5.93 9.40 vp9_avg_8tap_smooth_64v_neon: 10.76 14.13 9.46 13.37 vp9_put4_neon: 1.11 1.47 1.00 1.21 vp9_put8_neon: 1.23 2.17 1.94 1.48 vp9_put16_neon: 1.63 4.02 1.73 1.97 vp9_put32_neon: 1.56 4.92 2.00 1.96 vp9_put64_neon: 2.10 5.28 2.03 2.35 vp9_put_8tap_smooth_4h_neon: 3.11 4.35 2.63 4.35 vp9_put_8tap_smooth_4hv_neon: 3.67 4.69 3.25 4.71 vp9_put_8tap_smooth_4v_neon: 5.45 7.27 4.49 6.52 vp9_put_8tap_smooth_8h_neon: 5.97 8.18 4.81 8.56 vp9_put_8tap_smooth_8hv_neon: 6.39 7.90 5.64 8.15 vp9_put_8tap_smooth_8v_neon: 9.03 11.84 8.07 11.51 vp9_put_8tap_smooth_64h_neon: 6.78 9.48 4.88 10.89 vp9_put_8tap_smooth_64hv_neon: 6.99 8.87 5.94 9.56 vp9_put_8tap_smooth_64v_neon: 10.69 13.30 9.43 14.34 For the larger 8tap filters, the speedup vs C code is around 5-14x. This is significantly faster than libvpx's implementation of the same functions, at least when comparing the put_8tap_smooth_64 functions (compared to vpx_convolve8_horiz_neon and vpx_convolve8_vert_neon from libvpx). Absolute runtimes from checkasm: Cortex A7 A8 A9 A53 vp9_put_8tap_smooth_64h_neon: 20150.3 14489.4 19733.6 10863.7 libvpx vpx_convolve8_horiz_neon: 52623.3 19736.4 21907.7 25027.7 vp9_put_8tap_smooth_64v_neon: 14455.0 12303.9 13746.4 9628.9 libvpx vpx_convolve8_vert_neon: 42090.0 17706.2 17659.9 16941.2 Thus, on the A9, the horizontal filter is only marginally faster than libvpx, while our version is significantly faster on the other cores, and the vertical filter is significantly faster on all cores. The difference is especially large on the A7. The libvpx implementation does the accumulation in 32 bit, which probably explains most of the differences. This is an adapted cherry-pick from libav commits ffbd1d2b0002576ef0d976a41ff959c635373fdc, 392caa65df3efa8b2d48a80f08a6af4892c61c08, 557c1675cf0e803b2fee43b4c8b58433842c84d0 and 11623217e3c9b859daee544e31acdd0821b61039. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
8 years ago
if (ARCH_ARM) ff_vp9dsp_init_arm(dsp, bpp);
if (ARCH_X86) ff_vp9dsp_init_x86(dsp, bpp, bitexact);
if (ARCH_MIPS) ff_vp9dsp_init_mips(dsp, bpp);
if (ARCH_LOONGARCH) ff_vp9dsp_init_loongarch(dsp, bpp);
}