mirror of https://github.com/FFmpeg/FFmpeg.git
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.
96 lines
3.1 KiB
96 lines
3.1 KiB
7 months ago
|
/*
|
||
|
|
* Copyright (c) 2024 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 "libavutil/riscv/asm.S"
|
||
|
|
|
||
|
|
#if __riscv_xlen >= 64
|
||
|
|
func ff_vp7_luma_dc_wht_rvv, zve32x
|
||
|
|
csrwi vxrm, 0
|
||
|
|
li t4, 12540
|
||
|
|
vsetivli zero, 4, e16, mf2, ta, ma
|
||
|
|
vlseg4e16.v v0, (a1)
|
||
|
|
li t6, 30274
|
||
|
|
vwmul.vx v8, v1, t4
|
||
|
|
li t5, 23170
|
||
|
|
vwmul.vx v9, v3, t6
|
||
|
|
addi t1, sp, -12 * 2
|
||
|
|
vwmul.vx v10, v1, t6
|
||
|
|
addi t2, sp, -8 * 2
|
||
|
|
vwmul.vx v11, v3, t4
|
||
|
|
addi t3, sp, -4 * 2
|
||
|
|
vwadd.vv v4, v0, v2
|
||
|
|
addi sp, sp, -16 * 2
|
||
|
|
vwsub.vv v5, v0, v2
|
||
|
|
vsetvli zero, zero, e32, m1, ta, ma
|
||
|
|
vadd.vv v7, v10, v11
|
||
|
|
vmul.vx v4, v4, t5
|
||
|
|
vsub.vv v6, v8, v9
|
||
|
|
vmul.vx v5, v5, t5
|
||
|
|
vadd.vv v0, v4, v7
|
||
|
|
vsub.vv v3, v4, v7
|
||
|
|
vadd.vv v1, v5, v6
|
||
|
|
vsub.vv v2, v5, v6
|
||
|
|
vsetvli zero, zero, e16, mf2, ta, ma
|
||
|
|
vnsra.wi v4, v0, 14
|
||
|
|
vnsra.wi v7, v3, 14
|
||
|
|
vnsra.wi v5, v1, 14
|
||
|
|
vnsra.wi v6, v2, 14
|
||
|
|
vsseg4e16.v v4, (sp)
|
||
|
|
vle16.v v0, (sp)
|
||
|
|
vle16.v v1, (t1)
|
||
|
|
vle16.v v2, (t2)
|
||
|
|
vle16.v v3, (t3)
|
||
|
|
vwmul.vx v8, v1, t4
|
||
|
|
li t0, 16 * 2
|
||
|
|
vwmul.vx v9, v3, t6
|
||
|
|
addi t1, a0, 1 * 4 * 16 * 2
|
||
|
|
vwmul.vx v10, v1, t6
|
||
|
|
addi t2, a0, 2 * 4 * 16 * 2
|
||
|
|
vwmul.vx v11, v3, t4
|
||
|
|
addi t3, a0, 3 * 4 * 16 * 2
|
||
|
|
vwadd.vv v4, v0, v2
|
||
|
|
vwsub.vv v5, v0, v2
|
||
|
|
vsetvli zero, zero, e32, m1, ta, ma
|
||
|
|
vmul.vx v4, v4, t5
|
||
|
|
sd zero, (a1)
|
||
|
|
vadd.vv v7, v10, v11
|
||
|
|
sd zero, 8(a1)
|
||
|
|
vmul.vx v5, v5, t5
|
||
|
|
sd zero, 16(a1)
|
||
|
|
vsub.vv v6, v8, v9
|
||
|
|
sd zero, 24(a1)
|
||
|
|
vadd.vv v0, v4, v7
|
||
|
|
addi sp, sp, 16 * 2
|
||
|
|
vsub.vv v3, v4, v7
|
||
|
|
vadd.vv v1, v5, v6
|
||
|
|
vsub.vv v2, v5, v6
|
||
|
|
vsetvli zero, zero, e16, mf2, ta, ma
|
||
|
|
vnclip.wi v4, v0, 18
|
||
|
|
vnclip.wi v5, v1, 18
|
||
|
|
vnclip.wi v6, v2, 18
|
||
|
|
vnclip.wi v7, v3, 18
|
||
|
|
vsse16.v v4, (a0), t0
|
||
|
|
vsse16.v v5, (t1), t0
|
||
|
|
vsse16.v v6, (t2), t0
|
||
|
|
vsse16.v v7, (t3), t0
|
||
|
|
ret
|
||
|
|
endfunc
|
||
|
|
#endif
|