ffmpeg/libswscale
Rémi Denis-Courmont c2b38619c0 swscale/rgb2rgb2: rework RISC-V V shuffle_bytes_{1230,3012}
This avoids strided loads.

Before:
shuffle_bytes_1230_rvv_i32: 308.7
shuffle_bytes_3012_rvv_i32: 308.7

After:
shuffle_bytes_1230_rvv_i32: 46.7
shuffle_bytes_3012_rvv_i32: 46.7
2023-07-21 22:18:02 +03:00
..
aarch64 sw_scale: Add specializations for hscale 16 to 19 2022-11-01 15:24:58 +02:00
arm
loongarch swscale/la: Add following builtin optimized functions 2023-05-25 21:05:15 +02:00
ppc swscale/ppc: remove hScale8To19_vsx 2023-05-20 20:07:18 +02:00
riscv swscale/rgb2rgb2: rework RISC-V V shuffle_bytes_{1230,3012} 2023-07-21 22:18:02 +03:00
tests
x86 x86: replace explicit REP_RETs with RETs 2023-02-01 04:23:55 +01:00
alphablend.c
bayer_template.c
gamma.c
half2float.c
hscale_fast_bilinear.c
hscale.c
input.c lsws: add in/out support for the new 12-bit 2-plane 422 and 444 pixfmts 2023-05-29 00:41:35 +02:00
libswscale.v
log2_tab.c
Makefile
options.c
output.c swscale/output: Bias 16bps output calculations to improve non overflowing range for GBRP16/GBRPF32 2022-11-04 22:44:16 +01:00
rgb2rgb_template.c
rgb2rgb.c
rgb2rgb.h
slice.c
swscale_internal.h
swscale_unscaled.c
swscale.c
swscale.h
swscaleres.rc
utils.c lsws: add in/out support for the new 12-bit 2-plane 422 and 444 pixfmts 2023-05-29 00:41:35 +02:00
version_major.h Bump major versions of all libraries 2023-02-09 15:35:14 +01:00
version.c
version.h swscale: bump minor for implementing support for the new pixfmts 2023-05-29 00:42:02 +02:00
vscale.c
yuv2rgb.c