diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:32:43 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 17:32:43 +0000 |
commit | 6bf0a5cb5034a7e684dcc3500e841785237ce2dd (patch) | |
tree | a68f146d7fa01f0134297619fbe7e33db084e0aa /media/ffvpx/libavutil/float_dsp.h | |
parent | Initial commit. (diff) | |
download | thunderbird-6bf0a5cb5034a7e684dcc3500e841785237ce2dd.tar.xz thunderbird-6bf0a5cb5034a7e684dcc3500e841785237ce2dd.zip |
Adding upstream version 1:115.7.0.upstream/1%115.7.0upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'media/ffvpx/libavutil/float_dsp.h')
-rw-r--r-- | media/ffvpx/libavutil/float_dsp.h | 219 |
1 files changed, 219 insertions, 0 deletions
diff --git a/media/ffvpx/libavutil/float_dsp.h b/media/ffvpx/libavutil/float_dsp.h new file mode 100644 index 0000000000..7cad9fc622 --- /dev/null +++ b/media/ffvpx/libavutil/float_dsp.h @@ -0,0 +1,219 @@ +/* + * 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 AVUTIL_FLOAT_DSP_H +#define AVUTIL_FLOAT_DSP_H + +#include "config.h" + +typedef struct AVFloatDSPContext { + /** + * Calculate the entry wise product of two vectors of floats and store the result in + * a vector of floats. + * + * @param dst output vector + * constraints: 32-byte aligned + * @param src0 first input vector + * constraints: 32-byte aligned + * @param src1 second input vector + * constraints: 32-byte aligned + * @param len number of elements in the input + * constraints: multiple of 16 + */ + void (*vector_fmul)(float *dst, const float *src0, const float *src1, + int len); + + /** + * Multiply a vector of floats by a scalar float and add to + * destination vector. Source and destination vectors must + * overlap exactly or not at all. + * + * @param dst result vector + * constraints: 32-byte aligned + * @param src input vector + * constraints: 32-byte aligned + * @param mul scalar value + * @param len length of vector + * constraints: multiple of 16 + */ + void (*vector_fmac_scalar)(float *dst, const float *src, float mul, + int len); + + /** + * Multiply a vector of doubles by a scalar double and add to + * destination vector. Source and destination vectors must + * overlap exactly or not at all. + * + * @param dst result vector + * constraints: 32-byte aligned + * @param src input vector + * constraints: 32-byte aligned + * @param mul scalar value + * @param len length of vector + * constraints: multiple of 16 + */ + void (*vector_dmac_scalar)(double *dst, const double *src, double mul, + int len); + + /** + * Multiply a vector of floats by a scalar float. Source and + * destination vectors must overlap exactly or not at all. + * + * @param dst result vector + * constraints: 16-byte aligned + * @param src input vector + * constraints: 16-byte aligned + * @param mul scalar value + * @param len length of vector + * constraints: multiple of 4 + */ + void (*vector_fmul_scalar)(float *dst, const float *src, float mul, + int len); + + /** + * Multiply a vector of double by a scalar double. Source and + * destination vectors must overlap exactly or not at all. + * + * @param dst result vector + * constraints: 32-byte aligned + * @param src input vector + * constraints: 32-byte aligned + * @param mul scalar value + * @param len length of vector + * constraints: multiple of 8 + */ + void (*vector_dmul_scalar)(double *dst, const double *src, double mul, + int len); + + /** + * Overlap/add with window function. + * Used primarily by MDCT-based audio codecs. + * Source and destination vectors must overlap exactly or not at all. + * + * @param dst result vector + * constraints: 16-byte aligned + * @param src0 first source vector + * constraints: 16-byte aligned + * @param src1 second source vector + * constraints: 16-byte aligned + * @param win half-window vector + * constraints: 16-byte aligned + * @param len length of vector + * constraints: multiple of 4 + */ + void (*vector_fmul_window)(float *dst, const float *src0, + const float *src1, const float *win, int len); + + /** + * Calculate the entry wise product of two vectors of floats, add a third vector of + * floats and store the result in a vector of floats. + * + * @param dst output vector + * constraints: 32-byte aligned + * @param src0 first input vector + * constraints: 32-byte aligned + * @param src1 second input vector + * constraints: 32-byte aligned + * @param src2 third input vector + * constraints: 32-byte aligned + * @param len number of elements in the input + * constraints: multiple of 16 + */ + void (*vector_fmul_add)(float *dst, const float *src0, const float *src1, + const float *src2, int len); + + /** + * Calculate the entry wise product of two vectors of floats, and store the result + * in a vector of floats. The second vector of floats is iterated over + * in reverse order. + * + * @param dst output vector + * constraints: 32-byte aligned + * @param src0 first input vector + * constraints: 32-byte aligned + * @param src1 second input vector + * constraints: 32-byte aligned + * @param len number of elements in the input + * constraints: multiple of 16 + */ + void (*vector_fmul_reverse)(float *dst, const float *src0, + const float *src1, int len); + + /** + * Calculate the sum and difference of two vectors of floats. + * + * @param v1 first input vector, sum output, 16-byte aligned + * @param v2 second input vector, difference output, 16-byte aligned + * @param len length of vectors, multiple of 4 + */ + void (*butterflies_float)(float *av_restrict v1, float *av_restrict v2, int len); + + /** + * Calculate the scalar product of two vectors of floats. + * + * @param v1 first vector, 16-byte aligned + * @param v2 second vector, 16-byte aligned + * @param len length of vectors, multiple of 4 + * + * @return sum of elementwise products + */ + float (*scalarproduct_float)(const float *v1, const float *v2, int len); + + /** + * Calculate the entry wise product of two vectors of doubles and store the result in + * a vector of doubles. + * + * @param dst output vector + * constraints: 32-byte aligned + * @param src0 first input vector + * constraints: 32-byte aligned + * @param src1 second input vector + * constraints: 32-byte aligned + * @param len number of elements in the input + * constraints: multiple of 16 + */ + void (*vector_dmul)(double *dst, const double *src0, const double *src1, + int len); +} AVFloatDSPContext; + +/** + * Return the scalar product of two vectors. + * + * @param v1 first input vector + * @param v2 first input vector + * @param len number of elements + * + * @return sum of elementwise products + */ +float avpriv_scalarproduct_float_c(const float *v1, const float *v2, int len); + +void ff_float_dsp_init_aarch64(AVFloatDSPContext *fdsp); +void ff_float_dsp_init_arm(AVFloatDSPContext *fdsp); +void ff_float_dsp_init_ppc(AVFloatDSPContext *fdsp, int strict); +void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp); +void ff_float_dsp_init_x86(AVFloatDSPContext *fdsp); +void ff_float_dsp_init_mips(AVFloatDSPContext *fdsp); + +/** + * Allocate a float DSP context. + * + * @param strict setting to non-zero avoids using functions which may not be IEEE-754 compliant + */ +AVFloatDSPContext *avpriv_float_dsp_alloc(int strict); + +#endif /* AVUTIL_FLOAT_DSP_H */ |