[FFmpeg-devel] [PATCH 1/5] libavcodec: aarch64: Don't clobber v8 in the h%4 case in ff_pix_abs16_xy2_neon

[Swinney, Jonathan]

LGTM.

-- 

Jonathan Swinney

On 7/13/22, 3:49 PM, "Martin Storsjö" <martin at martin.st> wrote:

    CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you can confirm the sender and know the content is safe.



    Checkasm doesn't currently test this codepath.
    ---
     libavcodec/aarch64/me_cmp_neon.S | 4 ++--
     1 file changed, 2 insertions(+), 2 deletions(-)

    diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
    index e49d049fc2..31db3793d9 100644
    --- a/libavcodec/aarch64/me_cmp_neon.S
    +++ b/libavcodec/aarch64/me_cmp_neon.S
    @@ -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
    --
    2.25.1