[FFmpeg-devel] [PATCH 5/6] sws/riscv: add forward-edge CFI landing pads
Rémi Denis-Courmont
remi at remlab.net
Mon Jul 22 22:38:17 EEST 2024
---
libswscale/riscv/input_rvv.S | 12 ++++++++++++
libswscale/riscv/range_rvv.S | 4 ++++
libswscale/riscv/rgb2rgb_rvb.S | 1 +
libswscale/riscv/rgb2rgb_rvv.S | 7 +++++++
4 files changed, 24 insertions(+)
diff --git a/libswscale/riscv/input_rvv.S b/libswscale/riscv/input_rvv.S
index 1d7de59c66..0562e55921 100644
--- a/libswscale/riscv/input_rvv.S
+++ b/libswscale/riscv/input_rvv.S
@@ -21,12 +21,14 @@
#include "libavutil/riscv/asm.S"
func ff_bgr24ToY_rvv, zve32x
+ lpad 0
lw t1, 8(a5) # BY
lw t3, 0(a5) # RY
j 1f
endfunc
func ff_rgb24ToY_rvv, zve32x
+ lpad 0
lw t1, 0(a5) # RY
lw t3, 8(a5) # BY
1:
@@ -55,6 +57,7 @@ func ff_rgb24ToY_rvv, zve32x
endfunc
func ff_bgr24ToUV_rvv, zve32x
+ lpad 0
lw t1, 20(a6) # BU
lw t4, 32(a6) # BV
lw t3, 12(a6) # RU
@@ -63,6 +66,7 @@ func ff_bgr24ToUV_rvv, zve32x
endfunc
func ff_rgb24ToUV_rvv, zve32x
+ lpad 0
lw t1, 12(a6) # RU
lw t4, 24(a6) # RV
lw t3, 20(a6) # BU
@@ -101,6 +105,7 @@ func ff_rgb24ToUV_rvv, zve32x
endfunc
func ff_bgr24ToUV_half_rvv, zve32x
+ lpad 0
lw t1, 20(a6) # BU
lw t4, 32(a6) # BV
lw t3, 12(a6) # RU
@@ -109,6 +114,7 @@ func ff_bgr24ToUV_half_rvv, zve32x
endfunc
func ff_rgb24ToUV_half_rvv, zve32x
+ lpad 0
lw t1, 12(a6) # RU
lw t4, 24(a6) # RV
lw t3, 20(a6) # BU
@@ -152,12 +158,14 @@ endfunc
.macro rgba_input chr0, chr1, high
func ff_\chr1\()ToY_rvv, zve32x
+ lpad 0
lw t1, 8(a5) # BY
lw t3, 0(a5) # RY
j 1f
endfunc
func ff_\chr0\()ToY_rvv, zve32x
+ lpad 0
lw t1, 0(a5) # RY
lw t3, 8(a5) # BY
1:
@@ -192,6 +200,7 @@ func ff_\chr0\()ToY_rvv, zve32x
endfunc
func ff_\chr1\()ToUV_rvv, zve32x
+ lpad 0
lw t1, 20(a6) # BU
lw t4, 32(a6) # BV
lw t3, 12(a6) # RU
@@ -200,6 +209,7 @@ func ff_\chr1\()ToUV_rvv, zve32x
endfunc
func ff_\chr0\()ToUV_rvv, zve32x
+ lpad 0
lw t1, 12(a6) # RU
lw t4, 24(a6) # RV
lw t3, 20(a6) # BU
@@ -244,6 +254,7 @@ func ff_\chr0\()ToUV_rvv, zve32x
endfunc
func ff_\chr1\()ToUV_half_rvv, zve32x
+ lpad 0
lw t1, 20(a6) # BU
lw t4, 32(a6) # BV
lw t3, 12(a6) # RU
@@ -252,6 +263,7 @@ func ff_\chr1\()ToUV_half_rvv, zve32x
endfunc
func ff_\chr0\()ToUV_half_rvv, zve32x
+ lpad 0
lw t1, 12(a6) # RU
lw t4, 24(a6) # RV
lw t3, 20(a6) # BU
diff --git a/libswscale/riscv/range_rvv.S b/libswscale/riscv/range_rvv.S
index 9da80e6199..1d71ef29f6 100644
--- a/libswscale/riscv/range_rvv.S
+++ b/libswscale/riscv/range_rvv.S
@@ -21,6 +21,7 @@
#include "libavutil/riscv/asm.S"
func ff_range_lum_to_jpeg_16_rvv, zve32x
+ lpad 0
li t1, 30189
li t2, 19077
li t3, -39057361
@@ -42,6 +43,7 @@ func ff_range_lum_to_jpeg_16_rvv, zve32x
endfunc
func ff_range_lum_from_jpeg_16_rvv, zve32x
+ lpad 0
li t1, 14071
li t2, 33561947
1:
@@ -61,6 +63,7 @@ func ff_range_lum_from_jpeg_16_rvv, zve32x
endfunc
func ff_range_chr_to_jpeg_16_rvv, zve32x
+ lpad 0
li t1, 30775
li t2, 4663
li t3, -9289992
@@ -89,6 +92,7 @@ func ff_range_chr_to_jpeg_16_rvv, zve32x
endfunc
func ff_range_chr_from_jpeg_16_rvv, zve32x
+ lpad 0
li t1, 1799
li t2, 4081085
1:
diff --git a/libswscale/riscv/rgb2rgb_rvb.S b/libswscale/riscv/rgb2rgb_rvb.S
index af127b32ed..d9e56d77be 100644
--- a/libswscale/riscv/rgb2rgb_rvb.S
+++ b/libswscale/riscv/rgb2rgb_rvb.S
@@ -24,6 +24,7 @@
#if (__riscv_xlen >= 64)
func ff_shuffle_bytes_3210_rvb, zbb
+ lpad 0
srli a2, a2, 2
bswap32_rvb a1, a0, a2
endfunc
diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S
index 19f7aaf67d..8ca1ad94b2 100644
--- a/libswscale/riscv/rgb2rgb_rvv.S
+++ b/libswscale/riscv/rgb2rgb_rvv.S
@@ -21,11 +21,13 @@
#include "libavutil/riscv/asm.S"
func ff_shuffle_bytes_0321_rvv, zve32x
+ lpad 0
li t1, 0x00ff00ff
j 1f
endfunc
func ff_shuffle_bytes_2103_rvv, zve32x
+ lpad 0
li t1, ~0x00ff00ff
1:
not t2, t1
@@ -49,12 +51,14 @@ func ff_shuffle_bytes_2103_rvv, zve32x
endfunc
func ff_shuffle_bytes_1230_rvv, zve32x
+ lpad 0
li t1, 24
li t2, 8
j 3f
endfunc
func ff_shuffle_bytes_3012_rvv, zve32x
+ lpad 0
li t1, 8
li t2, 24
3:
@@ -75,6 +79,7 @@ func ff_shuffle_bytes_3012_rvv, zve32x
endfunc
func ff_interleave_bytes_rvv, zve32x
+ lpad 0
1:
mv t0, a0
mv t1, a1
@@ -101,6 +106,7 @@ func ff_interleave_bytes_rvv, zve32x
endfunc
func ff_deinterleave_bytes_rvv, zve32x
+ lpad 0
1:
mv t0, a0
mv t1, a1
@@ -127,6 +133,7 @@ func ff_deinterleave_bytes_rvv, zve32x
endfunc
.macro yuy2_to_i422p luma, chroma
+ lpad 0
srai t4, a4, 1 // pixel width -> chroma width
lw t6, (sp)
slli t5, a4, 1 // pixel width -> (source) byte width
--
2.45.2
More information about the ffmpeg-devel
mailing list