mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-12 19:18:44 +02:00
d452db8410
Notes: - The loop is biased toward no unescaped bytes as that should be most common. - The input byte array is slid rather than the (8 times smaller) bit-mask, as RISC-V V does not provide a bit-mask (or bit-wise) slide instruction. - There are two comparisons with 0 per iteration, for the same reason. - In case of match, bytes are copied until the first match, and the loop is restarted after the escape byte. Vector compression (vcompress.vm) could discard all escape bytes but that is slower if escape bytes are rare. Further optimisations should be possible, e.g.: - processing 2 bytes fewer per iteration to get rid of a 2 slides, - taking a short cut if the input vector contains less than 2 zeroes. But this is a good starting point: T-Head C908: vc1dsp.vc1_unescape_buffer_c: 12749.5 vc1dsp.vc1_unescape_buffer_rvv_i32: 6009.0 SpacemiT X60: vc1dsp.vc1_unescape_buffer_c: 11038.0 vc1dsp.vc1_unescape_buffer_rvv_i32: 2061.0
215 lines
6.9 KiB
ArmAsm
215 lines
6.9 KiB
ArmAsm
/*
|
|
* Copyright (c) 2023 Institue of Software Chinese Academy of Sciences (ISCAS).
|
|
* 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"
|
|
|
|
func ff_vc1_inv_trans_8x8_dc_rvv, zve64x
|
|
lh t2, (a2)
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vlse64.v v0, (a0), a1
|
|
sh1add t2, t2, t2
|
|
addi t2, t2, 1
|
|
srai t2, t2, 1
|
|
sh1add t2, t2, t2
|
|
addi t2, t2, 16
|
|
srai t2, t2, 5
|
|
li t0, 8*8
|
|
vsetvli zero, t0, e16, m8, ta, ma
|
|
vzext.vf2 v8, v0
|
|
vadd.vx v8, v8, t2
|
|
vmax.vx v8, v8, zero
|
|
vsetvli zero, zero, e8, m4, ta, ma
|
|
vnclipu.wi v0, v8, 0
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vsse64.v v0, (a0), a1
|
|
ret
|
|
endfunc
|
|
|
|
func ff_vc1_inv_trans_4x8_dc_rvv, zve32x
|
|
lh t2, (a2)
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vlse32.v v0, (a0), a1
|
|
slli t1, t2, 4
|
|
add t2, t2, t1
|
|
addi t2, t2, 4
|
|
srai t2, t2, 3
|
|
sh1add t2, t2, t2
|
|
slli t2, t2, 2
|
|
addi t2, t2, 64
|
|
srai t2, t2, 7
|
|
li t0, 4*8
|
|
vsetvli zero, t0, e16, m4, ta, ma
|
|
vzext.vf2 v4, v0
|
|
vadd.vx v4, v4, t2
|
|
vmax.vx v4, v4, zero
|
|
vsetvli zero, zero, e8, m2, ta, ma
|
|
vnclipu.wi v0, v4, 0
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vsse32.v v0, (a0), a1
|
|
ret
|
|
endfunc
|
|
|
|
func ff_vc1_inv_trans_8x4_dc_rvv, zve64x
|
|
lh t2, (a2)
|
|
vsetivli zero, 4, e8, mf4, ta, ma
|
|
vlse64.v v0, (a0), a1
|
|
sh1add t2, t2, t2
|
|
addi t2, t2, 1
|
|
srai t2, t2, 1
|
|
slli t1, t2, 4
|
|
add t2, t2, t1
|
|
addi t2, t2, 64
|
|
srai t2, t2, 7
|
|
li t0, 8*4
|
|
vsetvli zero, t0, e16, m4, ta, ma
|
|
vzext.vf2 v4, v0
|
|
vadd.vx v4, v4, t2
|
|
vmax.vx v4, v4, zero
|
|
vsetvli zero, zero, e8, m2, ta, ma
|
|
vnclipu.wi v0, v4, 0
|
|
vsetivli zero, 4, e8, mf4, ta, ma
|
|
vsse64.v v0, (a0), a1
|
|
ret
|
|
endfunc
|
|
|
|
func ff_vc1_inv_trans_4x4_dc_rvv, zve32x
|
|
lh t2, (a2)
|
|
vsetivli zero, 4, e8, mf4, ta, ma
|
|
vlse32.v v0, (a0), a1
|
|
slli t1, t2, 4
|
|
add t2, t2, t1
|
|
addi t2, t2, 4
|
|
srai t2, t2, 3
|
|
slli t1, t2, 4
|
|
add t2, t2, t1
|
|
addi t2, t2, 64
|
|
srai t2, t2, 7
|
|
vsetivli zero, 4*4, e16, m2, ta, ma
|
|
vzext.vf2 v2, v0
|
|
vadd.vx v2, v2, t2
|
|
vmax.vx v2, v2, zero
|
|
vsetvli zero, zero, e8, m1, ta, ma
|
|
vnclipu.wi v0, v2, 0
|
|
vsetivli zero, 4, e8, mf4, ta, ma
|
|
vsse32.v v0, (a0), a1
|
|
ret
|
|
endfunc
|
|
|
|
.macro mspel_op op pos n1 n2
|
|
add t1, \pos, a2
|
|
v\op\()e8.v v\n1, (\pos)
|
|
sh1add \pos, a2, \pos
|
|
v\op\()e8.v v\n2, (t1)
|
|
.endm
|
|
|
|
.macro mspel_op_all op pos a1 a2 a3 a4 a5 a6 a7 a8 a9 a10 a11 a12 a13 a14 a15 a16
|
|
mspel_op \op \pos \a1 \a2
|
|
mspel_op \op \pos \a3 \a4
|
|
mspel_op \op \pos \a5 \a6
|
|
mspel_op \op \pos \a7 \a8
|
|
mspel_op \op \pos \a9 \a10
|
|
mspel_op \op \pos \a11 \a12
|
|
mspel_op \op \pos \a13 \a14
|
|
mspel_op \op \pos \a15 \a16
|
|
.endm
|
|
|
|
func ff_avg_pixels16x16_rvv, zve32x
|
|
csrwi vxrm, 0
|
|
vsetivli zero, 16, e8, m1, ta, ma
|
|
mspel_op_all l a1 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
|
|
mspel_op_all l a0 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
|
|
vsetvli t0, zero, e8, m8, ta, ma
|
|
sub a0, a0, a2
|
|
vaaddu.vv v0, v0, v16
|
|
neg a2, a2
|
|
vaaddu.vv v8, v8, v24
|
|
vsetivli zero, 16, e8, m1, ta, ma
|
|
mspel_op_all s a0 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0
|
|
|
|
ret
|
|
endfunc
|
|
|
|
func ff_avg_pixels8x8_rvv, zve64x
|
|
csrwi vxrm, 0
|
|
li t0, 64
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vlse64.v v16, (a1), a2
|
|
vlse64.v v8, (a0), a2
|
|
vsetvli zero, t0, e8, m4, ta, ma
|
|
vaaddu.vv v16, v16, v8
|
|
vsetivli zero, 8, e8, mf2, ta, ma
|
|
vsse64.v v16, (a0), a2
|
|
|
|
ret
|
|
endfunc
|
|
|
|
func ff_vc1_unescape_buffer_rvv, zve32x
|
|
vsetivli zero, 2, e8, m1, ta, ma
|
|
vmv.v.i v8, -1
|
|
li t4, 1
|
|
vmv.v.i v12, -1
|
|
li t3, -1
|
|
mv t5, a2
|
|
blez a1, 3f
|
|
1:
|
|
vsetvli t0, a1, e8, m4, ta, ma
|
|
vle8.v v16, (a0)
|
|
vslideup.vi v8, v16, 2
|
|
addi t0, t0, -1 # we cannot fully process the last element
|
|
vslideup.vi v12, v16, 1
|
|
vslide1down.vx v20, v16, t3
|
|
vsetvli zero, t0, e8, m4, ta, ma
|
|
vmseq.vi v0, v8, 0
|
|
vmseq.vi v1, v12, 0
|
|
vmseq.vi v2, v16, 3
|
|
vmand.mm v0, v0, v1
|
|
vmsltu.vi v3, v20, 4
|
|
vmand.mm v0, v0, v2
|
|
vmand.mm v0, v0, v3
|
|
vfirst.m t2, v0
|
|
bgez t2, 4f # found an escape byte?
|
|
|
|
vse8.v v16, (a2)
|
|
addi t2, t0, -2
|
|
add a2, a2, t0
|
|
2:
|
|
vslidedown.vx v8, v16, t2
|
|
sub a1, a1, t0
|
|
vslidedown.vi v12, v8, 1
|
|
add a0, a0, t0
|
|
bgtu a1, t4, 1b // size > 1
|
|
|
|
lb t0, (a0)
|
|
sb t0, (a2) # copy last byte (cannot be escaped)
|
|
addi a2, a2, 1
|
|
3:
|
|
sub a0, a2, t5
|
|
ret
|
|
4:
|
|
vsetvli zero, t2, e8, m4, ta, ma
|
|
vse8.v v16, (a2)
|
|
addi t0, t2, 1
|
|
add a2, a2, t2
|
|
addi t2, t2, -1
|
|
vsetvli zero, t0, e8, m4, ta, ma
|
|
j 2b
|
|
endfunc
|