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

lavc/aarch64: move macros calc_epelh, calc_epelh2, load_epel_filterh 

Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
Logan Lyu 2023-09-23 10:22:09 +08:00 committed by Martin Storsjö
parent 7ce5a2f640
commit c0374f77f4
1 changed files with 23 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
libavcodec/aarch64/hevcdsp_epel_neon.S
View File

@ -64,6 +64,29 @@ endconst
umlsl2 \dst\().8h, \src3\().16b, v3.16b
.endm
.macro load_epel_filterh freg, xreg
movrel \xreg, epel_filters
add \xreg, \xreg, \freg, lsl #2
ld1 {v0.8b}, [\xreg]
sxtl v0.8h, v0.8b
.endm
.macro calc_epelh dst, src0, src1, src2, src3
smull \dst\().4s, \src0\().4h, v0.h[0]
smlal \dst\().4s, \src1\().4h, v0.h[1]
smlal \dst\().4s, \src2\().4h, v0.h[2]
smlal \dst\().4s, \src3\().4h, v0.h[3]
sqshrn \dst\().4h, \dst\().4s, #6
.endm
.macro calc_epelh2 dst, tmp, src0, src1, src2, src3
smull2 \tmp\().4s, \src0\().8h, v0.h[0]
smlal2 \tmp\().4s, \src1\().8h, v0.h[1]
smlal2 \tmp\().4s, \src2\().8h, v0.h[2]
smlal2 \tmp\().4s, \src3\().8h, v0.h[3]
sqshrn2 \dst\().8h, \tmp\().4s, #6
.endm
.macro calc_all4
calc v16, v17, v18, v19
b.eq 2f
@ -1101,28 +1124,7 @@ endfunc
sqxtn2 v6.8h, v31.4s
.endm
.macro calc_epelh dst, src0, src1, src2, src3
smull \dst\().4s, \src0\().4h, v0.h[0]
smlal \dst\().4s, \src1\().4h, v0.h[1]
smlal \dst\().4s, \src2\().4h, v0.h[2]
smlal \dst\().4s, \src3\().4h, v0.h[3]
sqshrn \dst\().4h, \dst\().4s, #6
.endm
.macro calc_epelh2 dst, tmp, src0, src1, src2, src3
smull2 \tmp\().4s, \src0\().8h, v0.h[0]
smlal2 \tmp\().4s, \src1\().8h, v0.h[1]
smlal2 \tmp\().4s, \src2\().8h, v0.h[2]
smlal2 \tmp\().4s, \src3\().8h, v0.h[3]
sqshrn2 \dst\().8h, \tmp\().4s, #6
.endm
.macro load_epel_filterh freg, xreg
movrel \xreg, epel_filters
add \xreg, \xreg, \freg, lsl #2
ld1 {v0.8b}, [\xreg]
sxtl v0.8h, v0.8b
.endm
function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1
epel_uni_w_hv_start