From: Lynne <dev@lynne.ee>
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] [PATCH 2/2] swscale/ppc/swscale_ppc_template: Reindent after the previous commit
Date: Thu, 4 Apr 2024 06:01:40 +0200 (CEST)
Message-ID: <NubGEpt--3-9@lynne.ee> (raw)
In-Reply-To: <GV1P250MB073779BE2727AE926A3E08AA8F3C2@GV1P250MB0737.EURP250.PROD.OUTLOOK.COM>
Apr 4, 2024, 04:58 by andreas.rheinhardt@outlook.com:
> Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
> ---
> libswscale/ppc/swscale_ppc_template.c | 107 +++++++++++++-------------
> 1 file changed, 53 insertions(+), 54 deletions(-)
>
> diff --git a/libswscale/ppc/swscale_ppc_template.c b/libswscale/ppc/swscale_ppc_template.c
> index e9abd33cbf..3c2addd4a4 100644
> --- a/libswscale/ppc/swscale_ppc_template.c
> +++ b/libswscale/ppc/swscale_ppc_template.c
> @@ -101,70 +101,69 @@ static void FUNC(hScale_real)(SwsContext *c, int16_t *dst, int dstW,
> const uint8_t *src, const int16_t *filter,
> const int32_t *filterPos, int filterSize)
> {
> - register int i;
> LOCAL_ALIGNED(16, int, tempo, [4]);
>
> - switch (filterSize) {
> - case 4:
> - for (i = 0; i < dstW; i++) {
> - register int srcPos = filterPos[i];
> -
> - vector unsigned char src_vF = unaligned_load(srcPos, src);
> - vector signed short src_v, filter_v;
> - vector signed int val_vEven, val_s;
> - src_v = // vec_unpackh sign-extends...
> - (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> - // now put our elements in the even slots
> - src_v = vec_mergeh(src_v, (vector signed short)vzero);
> - GET_VF4(i, filter_v, filter);
> - val_vEven = vec_mule(src_v, filter_v);
> - val_s = vec_sums(val_vEven, vzero);
> - vec_st(val_s, 0, tempo);
> - dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> - }
> + switch (filterSize) {
> + case 4:
> + for (register int i = 0; i < dstW; i++) {
> + register int srcPos = filterPos[i];
> +
> + vector unsigned char src_vF = unaligned_load(srcPos, src);
> + vector signed short src_v, filter_v;
> + vector signed int val_vEven, val_s;
> + src_v = // vec_unpackh sign-extends...
> + (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> + // now put our elements in the even slots
> + src_v = vec_mergeh(src_v, (vector signed short)vzero);
> + GET_VF4(i, filter_v, filter);
> + val_vEven = vec_mule(src_v, filter_v);
> + val_s = vec_sums(val_vEven, vzero);
> + vec_st(val_s, 0, tempo);
> + dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> + }
> break;
> - case 8:
> - for (i = 0; i < dstW; i++) {
> - register int srcPos = filterPos[i];
> - vector unsigned char src_vF, av_unused src_v0, av_unused src_v1;
> - vector unsigned char av_unused permS;
> - vector signed short src_v, filter_v;
> - vector signed int val_v, val_s;
> - FIRST_LOAD(src_v0, srcPos, src, permS);
> - LOAD_SRCV8(srcPos, 0, src, permS, src_v0, src_v1, src_vF);
> - src_v = // vec_unpackh sign-extends...
> - (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> - filter_v = vec_ld(i << 4, filter);
> - val_v = vec_msums(src_v, filter_v, (vector signed int)vzero);
> - val_s = vec_sums(val_v, vzero);
> - vec_st(val_s, 0, tempo);
> - dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> - }
> + case 8:
> + for (register int i = 0; i < dstW; i++) {
> + register int srcPos = filterPos[i];
> + vector unsigned char src_vF, av_unused src_v0, av_unused src_v1;
> + vector unsigned char av_unused permS;
> + vector signed short src_v, filter_v;
> + vector signed int val_v, val_s;
> + FIRST_LOAD(src_v0, srcPos, src, permS);
> + LOAD_SRCV8(srcPos, 0, src, permS, src_v0, src_v1, src_vF);
> + src_v = // vec_unpackh sign-extends...
> + (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> + filter_v = vec_ld(i << 4, filter);
> + val_v = vec_msums(src_v, filter_v, (vector signed int)vzero);
> + val_s = vec_sums(val_v, vzero);
> + vec_st(val_s, 0, tempo);
> + dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> + }
> break;
>
> - case 16:
> - for (i = 0; i < dstW; i++) {
> - register int srcPos = filterPos[i];
> + case 16:
> + for (register int i = 0; i < dstW; i++) {
> + register int srcPos = filterPos[i];
>
> - vector unsigned char src_vF = unaligned_load(srcPos, src);
> - vector signed short src_vA = // vec_unpackh sign-extends...
> - (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> - vector signed short src_vB = // vec_unpackh sign-extends...
> - (vector signed short)(VEC_MERGEL((vector unsigned char)vzero, src_vF));
> - vector signed short filter_v0 = vec_ld(i << 5, filter);
> - vector signed short filter_v1 = vec_ld((i << 5) + 16, filter);
> + vector unsigned char src_vF = unaligned_load(srcPos, src);
> + vector signed short src_vA = // vec_unpackh sign-extends...
> + (vector signed short)(VEC_MERGEH((vector unsigned char)vzero, src_vF));
> + vector signed short src_vB = // vec_unpackh sign-extends...
> + (vector signed short)(VEC_MERGEL((vector unsigned char)vzero, src_vF));
> + vector signed short filter_v0 = vec_ld(i << 5, filter);
> + vector signed short filter_v1 = vec_ld((i << 5) + 16, filter);
>
> - vector signed int val_acc = vec_msums(src_vA, filter_v0, (vector signed int)vzero);
> - vector signed int val_v = vec_msums(src_vB, filter_v1, val_acc);
> + vector signed int val_acc = vec_msums(src_vA, filter_v0, (vector signed int)vzero);
> + vector signed int val_v = vec_msums(src_vB, filter_v1, val_acc);
>
> - vector signed int val_s = vec_sums(val_v, vzero);
> + vector signed int val_s = vec_sums(val_v, vzero);
>
> - VEC_ST(val_s, 0, tempo);
> - dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> - }
> + VEC_ST(val_s, 0, tempo);
> + dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1);
> + }
> break;
>
> - default:
> + default:
> for (register int i = 0; i < dstW; i++) {
> register int j;
> register int srcPos = filterPos[i];
> @@ -174,5 +173,5 @@ static void FUNC(hScale_real)(SwsContext *c, int16_t *dst, int dstW,
> dst[i] = FFMIN(val >> 7, (1 << 15) - 1);
> }
> break;
> - }
> + }
> }
>
Patchset LGTM.
I missed those in the previous broken PPC code removal I did.
_______________________________________________
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".
prev parent reply other threads:[~2024-04-04 4:01 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-04 2:57 [FFmpeg-devel] [PATCH 1/2] swscale/ppc/swscale_ppc_template: Remove code not passing checkasm Andreas Rheinhardt
2024-04-04 2:58 ` [FFmpeg-devel] [PATCH 2/2] swscale/ppc/swscale_ppc_template: Reindent after the previous commit Andreas Rheinhardt
2024-04-04 4:01 ` Lynne [this message]
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=NubGEpt--3-9@lynne.ee \
--to=dev@lynne.ee \
--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