libavcodec: aarch64: Don't clobber v8 in the h%4 case in ff_pix_abs16_xy2_neon

Checkasm doesn't currently test this codepath.

Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
Martin Storsjö 2022-07-12 23:51:36 +03:00
parent 9450f75974
commit 02e7853fd9

View File

@ -189,11 +189,11 @@ function ff_pix_abs16_xy2_neon, export=1
urshr v16.8h, v16.8h, #2 // shift right by 2 0..7 (rounding shift right)
urshr v17.8h, v17.8h, #2 // shift right by 2 8..15
uxtl2 v8.8h, v1.16b // 8->16 bits pix1 8..15
uxtl2 v7.8h, v1.16b // 8->16 bits pix1 8..15
uxtl v1.8h, v1.8b // 8->16 bits pix1 0..7
uabd v6.8h, v1.8h, v16.8h // absolute difference 0..7
uaba v6.8h, v8.8h, v17.8h // absolute difference accumulate 8..15
uaba v6.8h, v7.8h, v17.8h // absolute difference accumulate 8..15
mov v2.16b, v18.16b // pix3 -> pix2
mov v3.16b, v19.16b // pix3+1 -> pix2+1
uaddlv s6, v6.8h // add up accumulator in v6