RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

sws/riscv: add forward-edge CFI landing pads

This commit is contained in:
Rémi Denis-Courmont 2024-07-22 22:17:40 +03:00
parent b5c111272b
commit 4f2472909e
4 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
libswscale/riscv/input_rvv.S
View File

@ -21,12 +21,14 @@
#include "libavutil/riscv/asm.S" #include "libavutil/riscv/asm.S"
func ff_bgr24ToY_rvv, zve32x func ff_bgr24ToY_rvv, zve32x
lpad 0
lw t1, 8(a5) # BY lw t1, 8(a5) # BY
lw t3, 0(a5) # RY lw t3, 0(a5) # RY
j 1f j 1f
endfunc endfunc
func ff_rgb24ToY_rvv, zve32x, zba func ff_rgb24ToY_rvv, zve32x, zba
lpad 0
lw t1, 0(a5) # RY lw t1, 0(a5) # RY
lw t3, 8(a5) # BY lw t3, 8(a5) # BY
1: 1:
@ -55,6 +57,7 @@ func ff_rgb24ToY_rvv, zve32x, zba
endfunc endfunc
func ff_bgr24ToUV_rvv, zve32x func ff_bgr24ToUV_rvv, zve32x
lpad 0
lw t1, 20(a6) # BU lw t1, 20(a6) # BU
lw t4, 32(a6) # BV lw t4, 32(a6) # BV
lw t3, 12(a6) # RU lw t3, 12(a6) # RU
@ -63,6 +66,7 @@ func ff_bgr24ToUV_rvv, zve32x
endfunc endfunc
func ff_rgb24ToUV_rvv, zve32x, zba func ff_rgb24ToUV_rvv, zve32x, zba
lpad 0
lw t1, 12(a6) # RU lw t1, 12(a6) # RU
lw t4, 24(a6) # RV lw t4, 24(a6) # RV
lw t3, 20(a6) # BU lw t3, 20(a6) # BU
@ -101,6 +105,7 @@ func ff_rgb24ToUV_rvv, zve32x, zba
endfunc endfunc
func ff_bgr24ToUV_half_rvv, zve32x func ff_bgr24ToUV_half_rvv, zve32x
lpad 0
lw t1, 20(a6) # BU lw t1, 20(a6) # BU
lw t4, 32(a6) # BV lw t4, 32(a6) # BV
lw t3, 12(a6) # RU lw t3, 12(a6) # RU
@ -109,6 +114,7 @@ func ff_bgr24ToUV_half_rvv, zve32x
endfunc endfunc
func ff_rgb24ToUV_half_rvv, zve32x, zba func ff_rgb24ToUV_half_rvv, zve32x, zba
lpad 0
lw t1, 12(a6) # RU lw t1, 12(a6) # RU
lw t4, 24(a6) # RV lw t4, 24(a6) # RV
lw t3, 20(a6) # BU lw t3, 20(a6) # BU
@ -152,12 +158,14 @@ endfunc
.macro rgba_input chr0, chr1, high .macro rgba_input chr0, chr1, high
func ff_\chr1\()ToY_rvv, zve32x func ff_\chr1\()ToY_rvv, zve32x
lpad 0
lw t1, 8(a5) # BY lw t1, 8(a5) # BY
lw t3, 0(a5) # RY lw t3, 0(a5) # RY
j 1f j 1f
endfunc endfunc
func ff_\chr0\()ToY_rvv, zve32x, zba func ff_\chr0\()ToY_rvv, zve32x, zba
lpad 0
lw t1, 0(a5) # RY lw t1, 0(a5) # RY
lw t3, 8(a5) # BY lw t3, 8(a5) # BY
1: 1:
@ -192,6 +200,7 @@ func ff_\chr0\()ToY_rvv, zve32x, zba
endfunc endfunc
func ff_\chr1\()ToUV_rvv, zve32x func ff_\chr1\()ToUV_rvv, zve32x
lpad 0
lw t1, 20(a6) # BU lw t1, 20(a6) # BU
lw t4, 32(a6) # BV lw t4, 32(a6) # BV
lw t3, 12(a6) # RU lw t3, 12(a6) # RU
@ -200,6 +209,7 @@ func ff_\chr1\()ToUV_rvv, zve32x
endfunc endfunc
func ff_\chr0\()ToUV_rvv, zve32x, zba func ff_\chr0\()ToUV_rvv, zve32x, zba
lpad 0
lw t1, 12(a6) # RU lw t1, 12(a6) # RU
lw t4, 24(a6) # RV lw t4, 24(a6) # RV
lw t3, 20(a6) # BU lw t3, 20(a6) # BU
@ -244,6 +254,7 @@ func ff_\chr0\()ToUV_rvv, zve32x, zba
endfunc endfunc
func ff_\chr1\()ToUV_half_rvv, zve32x func ff_\chr1\()ToUV_half_rvv, zve32x
lpad 0
lw t1, 20(a6) # BU lw t1, 20(a6) # BU
lw t4, 32(a6) # BV lw t4, 32(a6) # BV
lw t3, 12(a6) # RU lw t3, 12(a6) # RU
@ -252,6 +263,7 @@ func ff_\chr1\()ToUV_half_rvv, zve32x
endfunc endfunc
func ff_\chr0\()ToUV_half_rvv, zve32x, zba func ff_\chr0\()ToUV_half_rvv, zve32x, zba
lpad 0
lw t1, 12(a6) # RU lw t1, 12(a6) # RU
lw t4, 24(a6) # RV lw t4, 24(a6) # RV
lw t3, 20(a6) # BU lw t3, 20(a6) # BU

4
libswscale/riscv/range_rvv.S
View File

@ -21,6 +21,7 @@
#include "libavutil/riscv/asm.S" #include "libavutil/riscv/asm.S"
func ff_range_lum_to_jpeg_16_rvv, zve32x, zba func ff_range_lum_to_jpeg_16_rvv, zve32x, zba
lpad 0
li t1, 30189 li t1, 30189
li t2, 19077 li t2, 19077
li t3, -39057361 li t3, -39057361
@ -42,6 +43,7 @@ func ff_range_lum_to_jpeg_16_rvv, zve32x, zba
endfunc endfunc
func ff_range_lum_from_jpeg_16_rvv, zve32x, zba func ff_range_lum_from_jpeg_16_rvv, zve32x, zba
lpad 0
li t1, 14071 li t1, 14071
li t2, 33561947 li t2, 33561947
1: 1:
@ -61,6 +63,7 @@ func ff_range_lum_from_jpeg_16_rvv, zve32x, zba
endfunc endfunc
func ff_range_chr_to_jpeg_16_rvv, zve32x, zba func ff_range_chr_to_jpeg_16_rvv, zve32x, zba
lpad 0
li t1, 30775 li t1, 30775
li t2, 4663 li t2, 4663
li t3, -9289992 li t3, -9289992
@ -89,6 +92,7 @@ func ff_range_chr_to_jpeg_16_rvv, zve32x, zba
endfunc endfunc
func ff_range_chr_from_jpeg_16_rvv, zve32x, zba func ff_range_chr_from_jpeg_16_rvv, zve32x, zba
lpad 0
li t1, 1799 li t1, 1799
li t2, 4081085 li t2, 4081085
1: 1:

1
libswscale/riscv/rgb2rgb_rvb.S
View File

@ -24,6 +24,7 @@
#if (__riscv_xlen >= 64) #if (__riscv_xlen >= 64)
func ff_shuffle_bytes_3210_rvb, zba, zbb func ff_shuffle_bytes_3210_rvb, zba, zbb
lpad 0
srli a2, a2, 2 srli a2, a2, 2
bswap32_rvb a1, a0, a2 bswap32_rvb a1, a0, a2
endfunc endfunc

7
libswscale/riscv/rgb2rgb_rvv.S
View File

@ -21,11 +21,13 @@
#include "libavutil/riscv/asm.S" #include "libavutil/riscv/asm.S"
func ff_shuffle_bytes_0321_rvv, zve32x func ff_shuffle_bytes_0321_rvv, zve32x
lpad 0
li t1, 0x00ff00ff li t1, 0x00ff00ff
j 1f j 1f
endfunc endfunc
func ff_shuffle_bytes_2103_rvv, zve32x, zba func ff_shuffle_bytes_2103_rvv, zve32x, zba
lpad 0
li t1, ~0x00ff00ff li t1, ~0x00ff00ff
1: 1:
not t2, t1 not t2, t1
@ -49,12 +51,14 @@ func ff_shuffle_bytes_2103_rvv, zve32x, zba
endfunc endfunc
func ff_shuffle_bytes_1230_rvv, zve32x func ff_shuffle_bytes_1230_rvv, zve32x
lpad 0
li t1, 24 li t1, 24
li t2, 8 li t2, 8
j 3f j 3f
endfunc endfunc
func ff_shuffle_bytes_3012_rvv, zve32x, zba func ff_shuffle_bytes_3012_rvv, zve32x, zba
lpad 0
li t1, 8 li t1, 8
li t2, 24 li t2, 24
3: 3:
@ -75,6 +79,7 @@ func ff_shuffle_bytes_3012_rvv, zve32x, zba
endfunc endfunc
func ff_interleave_bytes_rvv, zve32x, zba func ff_interleave_bytes_rvv, zve32x, zba
lpad 0
1: 1:
mv t0, a0 mv t0, a0
mv t1, a1 mv t1, a1
@ -101,6 +106,7 @@ func ff_interleave_bytes_rvv, zve32x, zba
endfunc endfunc
func ff_deinterleave_bytes_rvv, zve32x, zba func ff_deinterleave_bytes_rvv, zve32x, zba
lpad 0
1: 1:
mv t0, a0 mv t0, a0
mv t1, a1 mv t1, a1
@ -127,6 +133,7 @@ func ff_deinterleave_bytes_rvv, zve32x, zba
endfunc endfunc
.macro yuy2_to_i422p luma, chroma .macro yuy2_to_i422p luma, chroma
lpad 0
srai t4, a4, 1 // pixel width -> chroma width srai t4, a4, 1 // pixel width -> chroma width
lw t6, (sp) lw t6, (sp)
slli t5, a4, 1 // pixel width -> (source) byte width slli t5, a4, 1 // pixel width -> (source) byte width