mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2025-01-08 13:22:53 +02:00
lavu/floatdsp: RISC-V V vector_fmul_scalar
This is based on existing code from the VLC git tree with two minor changes to account for the different function prototypes.
This commit is contained in:
parent
39357cad37
commit
a6c10d05fe
@ -156,6 +156,8 @@ av_cold AVFloatDSPContext *avpriv_float_dsp_alloc(int bit_exact)
|
||||
ff_float_dsp_init_arm(fdsp);
|
||||
#elif ARCH_PPC
|
||||
ff_float_dsp_init_ppc(fdsp, bit_exact);
|
||||
#elif ARCH_RISCV
|
||||
ff_float_dsp_init_riscv(fdsp);
|
||||
#elif ARCH_X86
|
||||
ff_float_dsp_init_x86(fdsp);
|
||||
#elif ARCH_MIPS
|
||||
|
@ -205,6 +205,7 @@ 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);
|
||||
|
||||
|
@ -1 +1,3 @@
|
||||
OBJS += riscv/cpu.o
|
||||
OBJS += riscv/float_dsp_init.o \
|
||||
riscv/cpu.o
|
||||
RVV-OBJS += riscv/float_dsp_rvv.o
|
||||
|
39
libavutil/riscv/float_dsp_init.c
Normal file
39
libavutil/riscv/float_dsp_init.c
Normal file
@ -0,0 +1,39 @@
|
||||
/*
|
||||
* Copyright © 2022 Rémi Denis-Courmont.
|
||||
*
|
||||
* 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 "config.h"
|
||||
#include "libavutil/attributes.h"
|
||||
#include "libavutil/cpu.h"
|
||||
#include "libavutil/float_dsp.h"
|
||||
|
||||
void ff_vector_fmul_scalar_rvv(float *dst, const float *src, float mul,
|
||||
int len);
|
||||
|
||||
av_cold void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp)
|
||||
{
|
||||
#if HAVE_RVV
|
||||
int flags = av_get_cpu_flags();
|
||||
|
||||
if (flags & AV_CPU_FLAG_RVV_F32)
|
||||
fdsp->vector_fmul_scalar = ff_vector_fmul_scalar_rvv;
|
||||
#endif
|
||||
}
|
39
libavutil/riscv/float_dsp_rvv.S
Normal file
39
libavutil/riscv/float_dsp_rvv.S
Normal file
@ -0,0 +1,39 @@
|
||||
/*
|
||||
* Copyright © 2022 Rémi Denis-Courmont.
|
||||
*
|
||||
* 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 "asm.S"
|
||||
|
||||
// (a0) = (a1) * fa0 [0..a2-1]
|
||||
func ff_vector_fmul_scalar_rvv, zve32f
|
||||
NOHWF fmv.w.x fa0, a2
|
||||
NOHWF mv a2, a3
|
||||
1:
|
||||
vsetvli t0, a2, e32, m1, ta, ma
|
||||
vle32.v v16, (a1)
|
||||
sub a2, a2, t0
|
||||
vfmul.vf v16, v16, fa0
|
||||
sh2add a1, t0, a1
|
||||
vse32.v v16, (a0)
|
||||
sh2add a0, t0, a0
|
||||
bnez a2, 1b
|
||||
|
||||
ret
|
||||
endfunc
|
Loading…
Reference in New Issue
Block a user