Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: flow gg <hlefthleft@gmail.com>
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] [PATCH 5/5] lavc/vp8dsp: factor R-V V EPEL functions for all lengths
Date: Sun, 26 May 2024 02:16:22 +0800
Message-ID: <CAEa-L+vckRxKu79v7o8VnZkSHX_Frm671z2cGod718HJAybKpA@mail.gmail.com> (raw)
In-Reply-To: <20240525153840.78147-5-remi@remlab.net>

Would it be better to replace the two vsetvlstatic8 and vsetvlstatic16 with
two vsetvl? This would require the previous patch and this one to work
together, increasing the number of lines of code and making the code a bit
harder to read.
Additionally, I have a question about patch 4 'save one R-V GPR' and patch
5. Should they be submitted as a single patch? Because patch 4 looks
similar to what I initially submitted, and you suggested changing it to
save lines of code. If it is only for patch 5, shouldn't they be combined
together?

Rémi Denis-Courmont <remi@remlab.net> 于2024年5月25日周六 23:39写道:

> ---
>  libavcodec/riscv/vp8dsp_rvv.S | 56 ++++++++++++++++++++---------------
>  1 file changed, 32 insertions(+), 24 deletions(-)
>
> diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
> index a4fcd158a5..002e7f3174 100644
> --- a/libavcodec/riscv/vp8dsp_rvv.S
> +++ b/libavcodec/riscv/vp8dsp_rvv.S
> @@ -32,16 +32,6 @@
>  .endif
>  .endm
>
> -.macro vsetvlstatic16 len
> -.if \len <= 4
> -        vsetivli        zero, \len, e16, mf2, ta, ma
> -.elseif \len <= 8
> -        vsetivli        zero, \len, e16, m1, ta, ma
> -.elseif \len <= 16
> -        vsetivli        zero, \len, e16, m2, ta, ma
> -.endif
> -.endm
> -
>  .macro vp8_idct_dc_add
>          vlse32.v      v0, (a0), a2
>          lh            a5, 0(a1)
> @@ -181,13 +171,8 @@ const subpel_filters
>          .byte 0,  -1,  12, 123,  -6, 0
>  endconst
>
> -.macro epel len size type
> -func ff_put_vp8_epel\len\()_\type\()\size\()_rvv, zve32x
> -.ifc \type,v
> -        addi            t0, a6, -1
> -.else
> -        addi            t0, a5, -1
> -.endif
> +.macro epel_common size, type
> +func ff_put_vp8_epel_\type\()\size\().rvv, zve32x
>          lla             t2, subpel_filters
>          sh1add          t0, t0, t0
>          sh1add          t0, t0, t2
> @@ -198,7 +183,6 @@ func ff_put_vp8_epel\len\()_\type\()\size\()_rvv,
> zve32x
>          lb              t5, 5(t0)
>          lb              t0, (t0)
>  .endif
> -        vsetvlstatic8   \len
>  1:
>          addi            a4, a4, -1
>  .ifc \type,v
> @@ -236,11 +220,11 @@ func ff_put_vp8_epel\len\()_\type\()\size\()_rvv,
> zve32x
>          vwmaccsu.vx     v16, t1, v22
>          vwmaccsu.vx     v16, t4, v28
>          vwadd.wx        v16, v16, t6
> -        vsetvlstatic16  \len
> +        vsetvl          zero, zero, a6 # e16
>          vwadd.vv        v24, v16, v20
>          vnsra.wi        v24, v24, 7
>          vmax.vx         v24, v24, zero
> -        vsetvlstatic8   \len
> +        vsetvl          zero, zero, a5 # e8
>          vnclipu.wi      v30, v24, 0
>          add             a2, a2, a3
>          vse8.v          v30, (a0)
> @@ -251,9 +235,33 @@ func ff_put_vp8_epel\len\()_\type\()\size\()_rvv,
> zve32x
>  endfunc
>  .endm
>
> +.macro epel len, size, type
> +func ff_put_vp8_epel\len\()_\type\()\size\()_rvv, zve32x
> +.ifc \type,v
> +        addi    t0, a6, -1
> +.else
> +        addi    t0, a5, -1
> +.endif
> +.if \len <= 4
> +        li      a5, 0306 # e8, mf4, ta, ma
> +        li      a6, 0317 # e16, mf2, ta, ma
> +.elseif \len <= 8
> +        li      a5, 0307 # e8, mf2, ta, ma
> +        li      a6, 0310 # e16, m1, ta, ma
> +.else # if len <= 16
> +        li      a5, 0300 # e8, m1, ta, ma
> +        li      a6, 0311 # e16, m2, ta, ma
> +.endif
> +        vsetvlstatic8 \len
> +        j       ff_put_vp8_epel_\type\()\size\().rvv
> +endfunc
> +.endm
> +
> +.irp type,h,v
> +.irp size,4,6
> +epel_common \size, \type
>  .irp len,16,8,4
> -epel \len 6 h
> -epel \len 4 h
> -epel \len 6 v
> -epel \len 4 v
> +epel \len, \size, \type
> +.endr
> +.endr
>  .endr
> --
> 2.45.1
>
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
>
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request@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-request@ffmpeg.org with subject "unsubscribe".

  reply	other threads:[~2024-05-25 18:16 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-25 15:38 [FFmpeg-devel] [PATCH 1/5] lavc/vp8dsp: avoid one multiplication on RISC-V Rémi Denis-Courmont
2024-05-25 15:38 ` [FFmpeg-devel] [PATCH 2/5] lavc/vp8dsp: expand single use R-V macros Rémi Denis-Courmont
2024-05-25 15:38 ` [FFmpeg-devel] [PATCH 3/5] lavc/vp8dsp: factor R-V V bilin functions Rémi Denis-Courmont
2024-05-25 15:38 ` [FFmpeg-devel] [PATCH 4/5] lavc/vp8dsp: save one R-V GPR Rémi Denis-Courmont
2024-05-25 15:38 ` [FFmpeg-devel] [PATCH 5/5] lavc/vp8dsp: factor R-V V EPEL functions for all lengths Rémi Denis-Courmont
2024-05-25 18:16   ` flow gg [this message]
2024-05-25 18:29     ` Rémi Denis-Courmont
2024-05-25 18:56       ` flow gg
2024-05-25 19:15         ` Rémi Denis-Courmont

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAEa-L+vckRxKu79v7o8VnZkSHX_Frm671z2cGod718HJAybKpA@mail.gmail.com \
    --to=hlefthleft@gmail.com \
    --cc=ffmpeg-devel@ffmpeg.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git