lavc/riscv: Move VVC macro to h26x

This commit is contained in:
sunyuechi 2024-12-15 23:56:11 +08:00 committed by Nuo Mi
parent 89df9c4404
commit 9288196c0d
2 changed files with 132 additions and 112 deletions

127
libavcodec/riscv/h26x/asm.S Normal file
View File

@ -0,0 +1,127 @@
/*
* Copyright (c) 2024 Institue of Software Chinese Academy of Sciences (ISCAS).
*
* 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"
.macro vsetvlstatic8 w, vlen
.if \w == 2 && \vlen == 128
vsetivli zero, \w, e8, mf8, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e8, mf4, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e8, mf2, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e8, m1, ta, ma
.elseif \w <= 32 && \vlen == 128
li t0, \w
vsetvli zero, t0, e8, m2, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e8, mf8, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e8, mf4, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e8, mf2, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e8, m1, ta, ma
.elseif \w <= 64 && \vlen == 256
li t0, \w
vsetvli zero, t0, e8, m2, ta, ma
.else
li t0, \w
vsetvli zero, t0, e8, m4, ta, ma
.endif
.endm
.macro vsetvlstatic16 w, vlen
.if \w == 2 && \vlen == 128
vsetivli zero, \w, e16, mf4, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e16, mf2, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e16, m1, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e16, m2, ta, ma
.elseif \w <= 32 && \vlen == 128
li t0, \w
vsetvli zero, t0, e16, m4, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e16, mf4, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e16, mf2, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e16, m1, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e16, m2, ta, ma
.elseif \w <= 64 && \vlen == 256
li t0, \w
vsetvli zero, t0, e16, m4, ta, ma
.else
li t0, \w
vsetvli zero, t0, e16, m8, ta, ma
.endif
.endm
.macro vsetvlstatic32 w, vlen
.if \w == 2
vsetivli zero, \w, e32, mf2, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e32, m1, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e32, m2, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e32, m4, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e32, mf2, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e32, m1, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e32, m2, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e32, m4, ta, ma
.else
li t0, \w
vsetvli zero, t0, e32, m8, ta, ma
.endif
.endm
.macro POW2_JMP_TABLE id, vlen
const jmp_table_\id\vlen
.4byte \id\()2\vlen\()f - jmp_table_\id\vlen
.4byte \id\()4\vlen\()f - jmp_table_\id\vlen
.4byte \id\()8\vlen\()f - jmp_table_\id\vlen
.4byte \id\()16\vlen\()f - jmp_table_\id\vlen
.4byte \id\()32\vlen\()f - jmp_table_\id\vlen
.4byte \id\()64\vlen\()f - jmp_table_\id\vlen
.4byte \id\()128\vlen\()f - jmp_table_\id\vlen
endconst
.endm
.macro POW2_J vlen, id, w
clz t1, \w
neg t1, t1
lla t5, jmp_table_\id\vlen
sh2add t1, t1, t5
lw t1, ((__riscv_xlen-2)<<2)(t1)
add t1, t1, t5
jr t1
.endm

View File

@ -18,91 +18,7 @@
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/ */
#include "libavutil/riscv/asm.S" #include "libavcodec/riscv/h26x/asm.S"
.macro vsetvlstatic8 w, vlen
.if \w == 2 && \vlen == 128
vsetivli zero, \w, e8, mf8, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e8, mf4, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e8, mf2, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e8, m1, ta, ma
.elseif \w <= 32 && \vlen == 128
li t0, \w
vsetvli zero, t0, e8, m2, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e8, mf8, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e8, mf4, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e8, mf2, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e8, m1, ta, ma
.elseif \w <= 64 && \vlen == 256
li t0, \w
vsetvli zero, t0, e8, m2, ta, ma
.else
li t0, \w
vsetvli zero, t0, e8, m4, ta, ma
.endif
.endm
.macro vsetvlstatic16 w, vlen
.if \w == 2 && \vlen == 128
vsetivli zero, \w, e16, mf4, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e16, mf2, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e16, m1, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e16, m2, ta, ma
.elseif \w <= 32 && \vlen == 128
li t0, \w
vsetvli zero, t0, e16, m4, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e16, mf4, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e16, mf2, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e16, m1, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e16, m2, ta, ma
.elseif \w <= 64 && \vlen == 256
li t0, \w
vsetvli zero, t0, e16, m4, ta, ma
.else
li t0, \w
vsetvli zero, t0, e16, m8, ta, ma
.endif
.endm
.macro vsetvlstatic32 w, vlen
.if \w == 2
vsetivli zero, \w, e32, mf2, ta, ma
.elseif \w <= 4 && \vlen == 128
vsetivli zero, \w, e32, m1, ta, ma
.elseif \w <= 8 && \vlen == 128
vsetivli zero, \w, e32, m2, ta, ma
.elseif \w <= 16 && \vlen == 128
vsetivli zero, \w, e32, m4, ta, ma
.elseif \w <= 4 && \vlen == 256
vsetivli zero, \w, e32, mf2, ta, ma
.elseif \w <= 8 && \vlen == 256
vsetivli zero, \w, e32, m1, ta, ma
.elseif \w <= 16 && \vlen == 256
vsetivli zero, \w, e32, m2, ta, ma
.elseif \w <= 32 && \vlen == 256
li t0, \w
vsetvli zero, t0, e32, m4, ta, ma
.else
li t0, \w
vsetvli zero, t0, e32, m8, ta, ma
.endif
.endm
.macro avg w, vlen, id .macro avg w, vlen, id
\id\w\vlen: \id\w\vlen:
@ -157,35 +73,12 @@
ret ret
.endm .endm
.macro AVG_JMP_TABLE id, vlen
const jmp_table_\id\vlen
.4byte \id\()2\vlen\()f - jmp_table_\id\vlen
.4byte \id\()4\vlen\()f - jmp_table_\id\vlen
.4byte \id\()8\vlen\()f - jmp_table_\id\vlen
.4byte \id\()16\vlen\()f - jmp_table_\id\vlen
.4byte \id\()32\vlen\()f - jmp_table_\id\vlen
.4byte \id\()64\vlen\()f - jmp_table_\id\vlen
.4byte \id\()128\vlen\()f - jmp_table_\id\vlen
endconst
.endm
.macro AVG_J vlen, id
clz t1, a4
neg t1, t1
lla t5, jmp_table_\id\vlen
sh2add t1, t1, t5
lw t1, ((__riscv_xlen-2)<<2)(t1)
add t1, t1, t5
jr t1
.endm
.macro func_avg vlen .macro func_avg vlen
func ff_vvc_avg_8_rvv_\vlen\(), zve32x, zbb, zba func ff_vvc_avg_8_rvv_\vlen\(), zve32x, zbb, zba
lpad 0 lpad 0
AVG_JMP_TABLE 1, \vlen POW2_JMP_TABLE 1, \vlen
csrwi vxrm, 0 csrwi vxrm, 0
AVG_J \vlen, 1 POW2_J \vlen, 1, a4
.irp w,2,4,8,16,32,64,128 .irp w,2,4,8,16,32,64,128
avg \w, \vlen, 1 avg \w, \vlen, 1
.endr .endr
@ -265,7 +158,7 @@ func_avg 256
.macro func_w_avg vlen .macro func_w_avg vlen
func ff_vvc_w_avg_8_rvv_\vlen\(), zve32x, zbb, zba func ff_vvc_w_avg_8_rvv_\vlen\(), zve32x, zbb, zba
lpad 0 lpad 0
AVG_JMP_TABLE 2, \vlen POW2_JMP_TABLE 2, \vlen
csrwi vxrm, 0 csrwi vxrm, 0
addi t6, a6, 7 addi t6, a6, 7
ld t3, (sp) ld t3, (sp)
@ -275,7 +168,7 @@ func ff_vvc_w_avg_8_rvv_\vlen\(), zve32x, zbb, zba
add t4, t4, t5 add t4, t4, t5
addi t5, t6, -1 // shift - 1 addi t5, t6, -1 // shift - 1
sll t4, t4, t5 sll t4, t4, t5
AVG_J \vlen, 2 POW2_J \vlen, 2, a4
.irp w,2,4,8,16,32,64,128 .irp w,2,4,8,16,32,64,128
w_avg \w, \vlen, 2 w_avg \w, \vlen, 2
.endr .endr