mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-20 22:41:11 +00:00
910d281b21
Since the horizontal and vertical filters are identical except for a transposition, this uses a common subprocedure with an ad-hoc ABI. To preserve return-address stack prediction, a link register has to be used (c.f. the "Control Transfer Instructions" from the RISC-V ISA Manual). The alternate/temporary link register T0 is used here, so that the normal RA is preserved (something Arm cannot do!). To load the strength value based on `qscale`, the shortest possible and PIC-compatible sequence is used: AUIPC; ADD; LBU. The classic LLA; ADD; LBU sequence would add one more instruction since LLA is a convenience alias for AUIPC; ADDI. To ensure that this trick works, relocation relaxation is disabled. To implement the two signed divisions by a power of two toward zero: (x / (1 << SHIFT)) the code relies on the small range of integers involved, computing: (x + (x >> (16 - SHIFT))) >> SHIFT rather than the more general: (x + ((x >> (16 - 1)) & ((1 << SHIFT) - 1))) >> SHIFT Thus one ANDI instruction is avoided. T-Head C908: h263dsp.h_loop_filter_c: 228.2 h263dsp.h_loop_filter_rvv_i32: 144.0 h263dsp.v_loop_filter_c: 242.7 h263dsp.v_loop_filter_rvv_i32: 114.0 (C is probably worse in real use due to less predictible branches.)
130 lines
3.4 KiB
C
130 lines
3.4 KiB
C
/*
|
|
* 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 <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/common.h"
|
|
#include "config.h"
|
|
#include "h263dsp.h"
|
|
|
|
const uint8_t ff_h263_loop_filter_strength[32] = {
|
|
0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
|
|
7, 8, 8, 8, 9, 9, 9, 10, 10, 10, 11, 11, 11, 12, 12, 12
|
|
};
|
|
|
|
static void h263_h_loop_filter_c(uint8_t *src, int stride, int qscale)
|
|
{
|
|
int y;
|
|
const int strength = ff_h263_loop_filter_strength[qscale];
|
|
|
|
for (y = 0; y < 8; y++) {
|
|
int d1, d2, ad1;
|
|
int p0 = src[y * stride - 2];
|
|
int p1 = src[y * stride - 1];
|
|
int p2 = src[y * stride + 0];
|
|
int p3 = src[y * stride + 1];
|
|
int d = (p0 - p3 + 4 * (p2 - p1)) / 8;
|
|
|
|
if (d < -2 * strength)
|
|
d1 = 0;
|
|
else if (d < -strength)
|
|
d1 = -2 * strength - d;
|
|
else if (d < strength)
|
|
d1 = d;
|
|
else if (d < 2 * strength)
|
|
d1 = 2 * strength - d;
|
|
else
|
|
d1 = 0;
|
|
|
|
p1 += d1;
|
|
p2 -= d1;
|
|
if (p1 & 256)
|
|
p1 = ~(p1 >> 31);
|
|
if (p2 & 256)
|
|
p2 = ~(p2 >> 31);
|
|
|
|
src[y * stride - 1] = p1;
|
|
src[y * stride + 0] = p2;
|
|
|
|
ad1 = FFABS(d1) >> 1;
|
|
|
|
d2 = av_clip((p0 - p3) / 4, -ad1, ad1);
|
|
|
|
src[y * stride - 2] = p0 - d2;
|
|
src[y * stride + 1] = p3 + d2;
|
|
}
|
|
}
|
|
|
|
static void h263_v_loop_filter_c(uint8_t *src, int stride, int qscale)
|
|
{
|
|
int x;
|
|
const int strength = ff_h263_loop_filter_strength[qscale];
|
|
|
|
for (x = 0; x < 8; x++) {
|
|
int d1, d2, ad1;
|
|
int p0 = src[x - 2 * stride];
|
|
int p1 = src[x - 1 * stride];
|
|
int p2 = src[x + 0 * stride];
|
|
int p3 = src[x + 1 * stride];
|
|
int d = (p0 - p3 + 4 * (p2 - p1)) / 8;
|
|
|
|
if (d < -2 * strength)
|
|
d1 = 0;
|
|
else if (d < -strength)
|
|
d1 = -2 * strength - d;
|
|
else if (d < strength)
|
|
d1 = d;
|
|
else if (d < 2 * strength)
|
|
d1 = 2 * strength - d;
|
|
else
|
|
d1 = 0;
|
|
|
|
p1 += d1;
|
|
p2 -= d1;
|
|
if (p1 & 256)
|
|
p1 = ~(p1 >> 31);
|
|
if (p2 & 256)
|
|
p2 = ~(p2 >> 31);
|
|
|
|
src[x - 1 * stride] = p1;
|
|
src[x + 0 * stride] = p2;
|
|
|
|
ad1 = FFABS(d1) >> 1;
|
|
|
|
d2 = av_clip((p0 - p3) / 4, -ad1, ad1);
|
|
|
|
src[x - 2 * stride] = p0 - d2;
|
|
src[x + stride] = p3 + d2;
|
|
}
|
|
}
|
|
|
|
av_cold void ff_h263dsp_init(H263DSPContext *ctx)
|
|
{
|
|
ctx->h263_h_loop_filter = h263_h_loop_filter_c;
|
|
ctx->h263_v_loop_filter = h263_v_loop_filter_c;
|
|
|
|
#if ARCH_RISCV
|
|
ff_h263dsp_init_riscv(ctx);
|
|
#elif ARCH_X86
|
|
ff_h263dsp_init_x86(ctx);
|
|
#elif ARCH_MIPS
|
|
ff_h263dsp_init_mips(ctx);
|
|
#endif
|
|
}
|