Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: Hubert Mazur <hum@semihalf.com>
To: ffmpeg-devel@ffmpeg.org
Cc: gjb@semihalf.com, upstream@semihalf.com, jswinney@amazon.com,
	Hubert Mazur <hum@semihalf.com>,
	martin@martin.st, mw@semihalf.com, spop@amazon.com
Subject: [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16
Date: Thu,  8 Sep 2022 11:25:06 +0200
Message-ID: <20220908092507.63319-5-hum@semihalf.com> (raw)
In-Reply-To: <20220908092507.63319-1-hum@semihalf.com>

Provide optimized implementation for vsse_intra16 for arm64.

Performance tests are shown below.
- vsse_4_c: 155.2
- vsse_4_neon: 36.2

Benchmarks and tests are run with checkasm tool on AWS Graviton 3.

Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
 libavcodec/aarch64/me_cmp_init_aarch64.c |  3 ++
 libavcodec/aarch64/me_cmp_neon.S         | 63 ++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index af83f7ed1e..8c295d5457 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -47,6 +47,8 @@ int vsad_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
                       ptrdiff_t stride, int h) ;
 int vsse16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
                 ptrdiff_t stride, int h);
+int vsse_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
+                      ptrdiff_t stride, int h);
 
 av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 {
@@ -69,5 +71,6 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->vsad[4] = vsad_intra16_neon;
 
         c->vsse[0] = vsse16_neon;
+        c->vsse[4] = vsse_intra16_neon;
     }
 }
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index ce198ea227..cf2b8da425 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -784,3 +784,66 @@ function vsad_intra16_neon, export=1
 
         ret
 endfunc
+
+function vsse_intra16_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *dummy
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        ld1             {v0.16b}, [x1], x3
+        movi            v16.4s, #0
+        movi            v17.4s, #0
+
+        sub             w4, w4, #1 // we need to make h-1 iterations
+        cmp             w4, #3
+        b.lt            2f
+
+1:
+        // v = abs( pix1[0] - pix1[0 + stride] )
+        // score = sum( v * v )
+        ld1             {v1.16b}, [x1], x3
+        ld1             {v2.16b}, [x1], x3
+        uabd            v30.16b, v0.16b, v1.16b
+        ld1             {v3.16b}, [x1], x3
+        umull           v29.8h, v30.8b, v30.8b
+        umull2          v28.8h, v30.16b, v30.16b
+        uabd            v27.16b, v1.16b, v2.16b
+        uadalp          v16.4s, v29.8h
+        umull           v26.8h, v27.8b, v27.8b
+        umull2          v27.8h, v27.16b, v27.16b
+        uadalp          v17.4s, v28.8h
+        uabd            v25.16b, v2.16b, v3.16b
+        uadalp          v16.4s, v26.8h
+        umull           v24.8h, v25.8b, v25.8b
+        umull2          v25.8h, v25.16b, v25.16b
+        uadalp          v17.4s, v27.8h
+        sub             w4, w4, #3
+        uadalp          v16.4s, v24.8h
+        cmp             w4, #3
+        uadalp          v17.4s, v25.8h
+        mov             v0.16b, v3.16b
+
+        b.ge            1b
+        cbz             w4, 3f
+
+// iterate by one
+2:
+        ld1             {v1.16b}, [x1], x3
+        subs            w4, w4, #1
+        uabd            v30.16b, v0.16b, v1.16b
+        mov             v0.16b, v1.16b
+        umull           v29.8h, v30.8b, v30.8b
+        umull2          v30.8h, v30.16b, v30.16b
+        uadalp          v16.4s, v29.8h
+        uadalp          v17.4s, v30.8h
+        cbnz            w4, 2b
+
+3:
+        add             v16.4s, v16.4s, v17.4S
+        uaddlv          d17, v16.4s
+        fmov            w0, s17
+
+        ret
+endfunc
-- 
2.34.1

_______________________________________________
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".

  parent reply	other threads:[~2022-09-08  9:26 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-08  9:25 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
2022-09-08  9:25 ` [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16 Hubert Mazur
2022-09-08  9:25 ` [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16 Hubert Mazur
2022-09-08  9:25 ` [FFmpeg-devel] [PATCH 3/5] lavc/aarch64: Add neon implementation for vsad_intra16 Hubert Mazur
2022-09-08  9:25 ` Hubert Mazur [this message]
2022-09-08  9:25 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-09-09  7:32 ` [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Martin Storsjö
  -- strict thread matches above, loose matches on Subject: below --
2022-09-06 10:27 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16 Hubert Mazur
2022-08-22 15:26 [FFmpeg-devel] [PATCH 0/5] me_cmp: Provide arm64 neon implementations Hubert Mazur
2022-08-22 15:26 ` [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16 Hubert Mazur
2022-09-04 20:59   ` Martin Storsjö

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=20220908092507.63319-5-hum@semihalf.com \
    --to=hum@semihalf.com \
    --cc=ffmpeg-devel@ffmpeg.org \
    --cc=gjb@semihalf.com \
    --cc=jswinney@amazon.com \
    --cc=martin@martin.st \
    --cc=mw@semihalf.com \
    --cc=spop@amazon.com \
    --cc=upstream@semihalf.com \
    /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