2024-02-28 13:29:19 +01:00
|
|
|
/*
|
|
|
|
|
* 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
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef AVCODEC_AACENCDSP_H
|
|
|
|
|
#define AVCODEC_AACENCDSP_H
|
|
|
|
|
|
|
|
|
|
#include <math.h>
|
|
|
|
|
|
|
|
|
|
#include "config.h"
|
|
|
|
|
|
|
|
|
|
#include "libavutil/macros.h"
|
|
|
|
|
|
|
|
|
|
typedef struct AACEncDSPContext {
|
|
|
|
|
void (*abs_pow34)(float *out, const float *in, const int size);
|
|
|
|
|
void (*quant_bands)(int *out, const float *in, const float *scaled,
|
|
|
|
|
int size, int is_signed, int maxval, const float Q34,
|
|
|
|
|
const float rounding);
|
|
|
|
|
} AACEncDSPContext;
|
|
|
|
|
|
|
|
|
|
void ff_aacenc_dsp_init_riscv(AACEncDSPContext *s);
|
|
|
|
|
void ff_aacenc_dsp_init_x86(AACEncDSPContext *s);
|
2025-01-24 19:58:26 +01:00
|
|
|
void ff_aacenc_dsp_init_aarch64(AACEncDSPContext *s);
|
2024-02-28 13:29:19 +01:00
|
|
|
|
|
|
|
|
static inline void abs_pow34_v(float *out, const float *in, const int size)
|
|
|
|
|
{
|
|
|
|
|
for (int i = 0; i < size; i++) {
|
|
|
|
|
float a = fabsf(in[i]);
|
|
|
|
|
out[i] = sqrtf(a * sqrtf(a));
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void quantize_bands(int *out, const float *in, const float *scaled,
|
|
|
|
|
int size, int is_signed, int maxval, const float Q34,
|
|
|
|
|
const float rounding)
|
|
|
|
|
{
|
|
|
|
|
for (int i = 0; i < size; i++) {
|
|
|
|
|
float qc = scaled[i] * Q34;
|
aacencdsp: Improve consistency with assembly, for x87 math
Currently, the aacencdsp checkasm tests fails for many seeds,
if the C code has been built with x87 math. This happens because
the excess precision of x87 math can make it end up rounding
to a different integer, and the checkasm tests checks that the
output integers match exactly between C and assembly.
One such failing case is "tests/checkasm/checkasm --test=aacencdsp
41" when compiled with GCC. When compiled with Clang, the test
seed 21 produces a failure.
To avoid the issue, we need to limit the precision of intermediates
to their nominal float range, matching the assembly implementations.
This can be achieved when compiling with GCC, by just adding a single
cast.
To observe the effect of this cast, compile the following
snippet,
int cast(float a, float b) {
return (int)
#ifdef CAST
(float)
#endif
(a + b);
}
with "gcc -m32 -std=c17 -O2", with/without -DCAST. For x86_64
cases (without the "-m32"), the cast doesn't make any difference
on the generated code.
This cast would seem to not have any effect, as a binary expression
with float inputs also would have the type float.
However, if compiling with GCC with -fexcess-precision=standard,
the cast forces limiting the precision according to the language
standard here - according to the GCC docs [1]:
> When compiling C or C++, if -fexcess-precision=standard is
> specified then excess precision follows the rules specified in
> ISO C99 or C++; in particular, both casts and assignments cause
> values to be rounded to their semantic types (whereas -ffloat-store
> only affects assignments). This option is enabled by default for
> C or C++ if a strict conformance option such as -std=c99 or
> -std=c++17 is used.
Ffmpeg's configure scripts enables -std=c17 by default.
This only helps with GCC though - the cast doesn't make any
difference for Clang. (Although, upstream Clang seems to default
to SSE math, while Ubuntu provided Clang defaults to x87 math.)
Limiting the precision with Clang would require casting to volatile
float for both intermediates here - and that does have a code
generation effect on all architectures.
[1] https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html
2025-08-22 23:26:11 +03:00
|
|
|
int tmp = (int)FFMIN((float)(qc + rounding), (float)maxval);
|
2024-02-28 13:29:19 +01:00
|
|
|
if (is_signed && in[i] < 0.0f) {
|
|
|
|
|
tmp = -tmp;
|
|
|
|
|
}
|
|
|
|
|
out[i] = tmp;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void ff_aacenc_dsp_init(AACEncDSPContext *s)
|
|
|
|
|
{
|
|
|
|
|
s->abs_pow34 = abs_pow34_v;
|
|
|
|
|
s->quant_bands = quantize_bands;
|
|
|
|
|
|
|
|
|
|
#if ARCH_RISCV
|
|
|
|
|
ff_aacenc_dsp_init_riscv(s);
|
|
|
|
|
#elif ARCH_X86
|
|
|
|
|
ff_aacenc_dsp_init_x86(s);
|
2025-01-24 19:58:26 +01:00
|
|
|
#elif ARCH_AARCH64
|
|
|
|
|
ff_aacenc_dsp_init_aarch64(s);
|
2024-02-28 13:29:19 +01:00
|
|
|
#endif
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif
|