mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2025-01-12 18:31:37 +00:00
lavc/idctdsp: improve R-V V put_signed_pixels_clamped
This follows the same idea as with pixblockdsp, but applied at the other end, whilst writing data at the end of the function.
This commit is contained in:
parent
3ea2310e89
commit
600c6f1b55
@ -42,24 +42,15 @@ func ff_put_pixels_clamped_rvv, zve32x
|
||||
ret
|
||||
endfunc
|
||||
|
||||
func ff_put_signed_pixels_clamped_rvv, zve32x
|
||||
vsetivli zero, 8, e16, m1, ta, ma
|
||||
vlseg8e16.v v24, (a0)
|
||||
|
||||
li t1, 128
|
||||
vsetivli zero, 8, e8, mf2, ta, ma
|
||||
vnclip.wi v16, v24, 0
|
||||
vnclip.wi v17, v25, 0
|
||||
vnclip.wi v18, v26, 0
|
||||
vnclip.wi v19, v27, 0
|
||||
vnclip.wi v20, v28, 0
|
||||
vnclip.wi v21, v29, 0
|
||||
vnclip.wi v22, v30, 0
|
||||
vnclip.wi v23, v31, 0
|
||||
vsetvli t0, zero, e8, m8, ta, ma
|
||||
vadd.vx v16, v16, t1
|
||||
vsetivli zero, 8, e8, mf2, ta, ma
|
||||
vssseg8e8.v v16, (a1), a2
|
||||
func ff_put_signed_pixels_clamped_rvv, zve64x
|
||||
li t0, 8 * 8
|
||||
vsetvli zero, t0, e8, m4, ta, ma
|
||||
vle16.v v24, (a0)
|
||||
li t1, 128
|
||||
vnclip.wi v16, v24, 0
|
||||
vadd.vx v16, v16, t1
|
||||
vsetivli zero, 8, e8, mf2, ta, ma
|
||||
vsse64.v v16, (a1), a2
|
||||
ret
|
||||
endfunc
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user