> On Feb 20, 2025, at 01:40, Krzysztof Pyrkosz via ffmpeg-devel
> <ffmpeg-devel@ffmpeg.org> wrote:
>
> ---
>
> Before and after on A78
>
> dmvr_8_12x20_neon: 86.2 ( 6.90x)
> dmvr_8_20x12_neon: 94.8 ( 5.93x)
> dmvr_8_20x20_neon: 141.5 ( 6.50x)
> dmvr_12_12x20_neon: 158.0 ( 3.76x)
> dmvr_12_20x12_neon: 151.2 ( 3.73x)
> dmvr_12_20x20_neon: 247.2 ( 3.71x)
> dmvr_hv_8_12x20_neon: 423.2 ( 3.75x)
> dmvr_hv_8_20x12_neon: 434.0 ( 3.69x)
> dmvr_hv_8_20x20_neon: 706.0 ( 3.69x)
>
> dmvr_8_12x20_neon: 77.2 ( 7.70x)
> dmvr_8_20x12_neon: 66.5 ( 8.49x)
> dmvr_8_20x20_neon: 92.2 ( 9.90x)
> dmvr_12_12x20_neon: 80.2 ( 7.38x)
> dmvr_12_20x12_neon: 58.2 ( 9.59x)
> dmvr_12_20x20_neon: 90.0 (10.15x)
> dmvr_hv_8_12x20_neon: 369.0 ( 4.34x)
> dmvr_hv_8_20x12_neon: 355.8 ( 4.49x)
> dmvr_hv_8_20x20_neon: 574.2 ( 4.51x)
>
> libavcodec/aarch64/vvc/inter.S | 72 ++++++++++------------------------
> 1 file changed, 20 insertions(+), 52 deletions(-)
>
> diff --git a/libavcodec/aarch64/vvc/inter.S b/libavcodec/aarch64/vvc/inter.S
> index c9d698ee29..45add44b6e 100644
> --- a/libavcodec/aarch64/vvc/inter.S
> +++ b/libavcodec/aarch64/vvc/inter.S
> @@ -369,22 +369,18 @@ function ff_vvc_dmvr_8_neon, export=1
> 1:
> cbz w15, 2f
> ldr q0, [src], #16
> - uxtl v1.8h, v0.8b
> - uxtl2 v2.8h, v0.16b
> - ushl v1.8h, v1.8h, v16.8h
> - ushl v2.8h, v2.8h, v16.8h
Please remove assignment to v16. LGTM otherwise.
> + ushll v1.8h, v0.8b, #2
> + ushll2 v2.8h, v0.16b, #2
> stp q1, q2, [dst], #32
> b 3f
> 2:
> ldr d0, [src], #8
> - uxtl v1.8h, v0.8b
> - ushl v1.8h, v1.8h, v16.8h
> + ushll v1.8h, v0.8b, #2
> str q1, [dst], #16
> 3:
> subs height, height, #1
> ldr s3, [src], #4
> - uxtl v4.8h, v3.8b
> - ushl v4.4h, v4.4h, v16.4h
> + ushll v4.8h, v3.8b, #2
> st1 {v4.4h}, [dst], x7
>
> add src, src, src_stride
> @@ -399,42 +395,24 @@ function ff_vvc_dmvr_12_neon, export=1
> cmp width, #16
> sub src_stride, src_stride, x6, lsl #1
> cset w15, gt // width > 16
> - movi v16.8h, #2 // offset4
> sub x7, x7, x6, lsl #1
> 1:
> cbz w15, 2f
> ldp q0, q1, [src], #32
> - uaddl v2.4s, v0.4h, v16.4h
> - uaddl2 v3.4s, v0.8h, v16.8h
> - uaddl v4.4s, v1.4h, v16.4h
> - uaddl2 v5.4s, v1.8h, v16.8h
> - ushr v2.4s, v2.4s, #2
> - ushr v3.4s, v3.4s, #2
> - ushr v4.4s, v4.4s, #2
> - ushr v5.4s, v5.4s, #2
> - uqxtn v2.4h, v2.4s
> - uqxtn2 v2.8h, v3.4s
> - uqxtn v4.4h, v4.4s
> - uqxtn2 v4.8h, v5.4s
> -
> - stp q2, q4, [dst], #32
> + urshr v0.8h, v0.8h, #2
> + urshr v1.8h, v1.8h, #2
> +
> + stp q0, q1, [dst], #32
> b 3f
> 2:
> ldr q0, [src], #16
> - uaddl v2.4s, v0.4h, v16.4h
> - uaddl2 v3.4s, v0.8h, v16.8h
> - ushr v2.4s, v2.4s, #2
> - ushr v3.4s, v3.4s, #2
> - uqxtn v2.4h, v2.4s
> - uqxtn2 v2.8h, v3.4s
> - str q2, [dst], #16
> + urshr v0.8h, v0.8h, #2
> + str q0, [dst], #16
> 3:
> subs height, height, #1
> ldr d0, [src], #8
> - uaddl v3.4s, v0.4h, v16.4h
> - ushr v3.4s, v3.4s, #2
> - uqxtn v3.4h, v3.4s
> - st1 {v3.4h}, [dst], x7
> + urshr v0.4h, v0.4h, #2
> + st1 {v0.4h}, [dst], x7
>
> add src, src, src_stride
> b.ne 1b
> @@ -462,8 +440,6 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> ldrb w10, [x12]
> ldrb w11, [x12, #1]
> sxtw x6, w6
> - movi v30.8h, #(1 << (8 - 7)) // offset1
> - movi v31.8h, #8 // offset2
> dup v2.8h, w10 // filter_y[0]
> dup v3.8h, w11 // filter_y[1]
>
> @@ -491,10 +467,8 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> mul v16.8h, v16.8h, v0.8h
> mla v6.8h, v7.8h, v1.8h
> mla v16.8h, v17.8h, v1.8h
> - add v6.8h, v6.8h, v30.8h
> - add v16.8h, v16.8h, v30.8h
> - ushr v6.8h, v6.8h, #(8 - 6)
> - ushr v7.8h, v16.8h, #(8 - 6)
> + urshr v6.8h, v6.8h, #(8 - 6)
> + urshr v7.8h, v16.8h, #(8 - 6)
> stp q6, q7, [x13], #32
>
> cbz w10, 3f
> @@ -504,10 +478,8 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> mul v17.8h, v17.8h, v2.8h
> mla v16.8h, v6.8h, v3.8h
> mla v17.8h, v7.8h, v3.8h
> - add v16.8h, v16.8h, v31.8h
> - add v17.8h, v17.8h, v31.8h
> - ushr v16.8h, v16.8h, #4
> - ushr v17.8h, v17.8h, #4
> + urshr v16.8h, v16.8h, #4
> + urshr v17.8h, v17.8h, #4
> stp q16, q17, [x14], #32
> b 3f
> 2:
> @@ -518,8 +490,7 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> uxtl v6.8h, v4.8b
> mul v6.8h, v6.8h, v0.8h
> mla v6.8h, v7.8h, v1.8h
> - add v6.8h, v6.8h, v30.8h
> - ushr v6.8h, v6.8h, #(8 - 6)
> + urshr v6.8h, v6.8h, #(8 - 6)
> str q6, [x13], #16
>
> cbz w10, 3f
> @@ -527,8 +498,7 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> ldr q16, [x12], #16
> mul v16.8h, v16.8h, v2.8h
> mla v16.8h, v6.8h, v3.8h
> - add v16.8h, v16.8h, v31.8h
> - ushr v16.8h, v16.8h, #4
> + urshr v16.8h, v16.8h, #4
> str q16, [x14], #16
> 3:
> ldur s5, [src, #1]
> @@ -537,8 +507,7 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> uxtl v6.8h, v4.8b
> mul v6.4h, v6.4h, v0.4h
> mla v6.4h, v7.4h, v1.4h
> - add v6.4h, v6.4h, v30.4h
> - ushr v6.4h, v6.4h, #(8 - 6)
> + urshr v6.4h, v6.4h, #(8 - 6)
> str d6, [x13], #8
>
> cbz w10, 4f
> @@ -546,8 +515,7 @@ function ff_vvc_dmvr_hv_8_neon, export=1
> ldr d16, [x12], #8
> mul v16.4h, v16.4h, v2.4h
> mla v16.4h, v6.4h, v3.4h
> - add v16.4h, v16.4h, v31.4h
> - ushr v16.4h, v16.4h, #4
> + urshr v16.4h, v16.4h, #4
> str d16, [x14], #8
> 4:
> subs height, height, #1
> --
> 2.47.2
>
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
>
> To unsubscribe, visit link above, or email
> ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
