From: "J. Dekker" <jdek@itanimul.li>
To: ffmpeg-devel@ffmpeg.org
Subject: [FFmpeg-devel] [PATCH v3 5/6] lavc/aarch64: clean-up sao band 8x8 function formatting
Date: Tue, 4 Jan 2022 06:20:17 +0100
Message-ID: <20220104052018.9541-5-jdek@itanimul.li> (raw)
In-Reply-To: <20220104052018.9541-1-jdek@itanimul.li>
Signed-off-by: J. Dekker <jdek@itanimul.li>
---
libavcodec/aarch64/hevcdsp_sao_neon.S | 65 +++++++++++----------------
1 file changed, 25 insertions(+), 40 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_sao_neon.S b/libavcodec/aarch64/hevcdsp_sao_neon.S
index 167b9676d8..73b0b3b056 100644
--- a/libavcodec/aarch64/hevcdsp_sao_neon.S
+++ b/libavcodec/aarch64/hevcdsp_sao_neon.S
@@ -30,24 +30,21 @@
// int width, int height)
function ff_hevc_sao_band_filter_8x8_8_neon, export=1
sub sp, sp, #64
- stp xzr, xzr, [sp]
- stp xzr, xzr, [sp, #16]
- stp xzr, xzr, [sp, #32]
- stp xzr, xzr, [sp, #48]
+ stp xzr, xzr, [sp]
+ stp xzr, xzr, [sp, #16]
+ stp xzr, xzr, [sp, #32]
+ stp xzr, xzr, [sp, #48]
mov w8, #4
-0:
- ldrsh x9, [x4, x8, lsl #1] // x9 = sao_offset_val[k+1]
+0: ldrsh x9, [x4, x8, lsl #1] // sao_offset_val[k+1]
subs w8, w8, #1
- add w10, w8, w5 // x10 = k + sao_left_class
- and w10, w10, #0x1F
+ add w10, w8, w5 // k + sao_left_class
+ and w10, w10, #0x1F
strh w9, [sp, x10, lsl #1]
bne 0b
- ld1 {v16.16b-v19.16b}, [sp], #64
- movi v20.8h, #1
-1: // beginning of line
- mov w8, w6
-2:
- // Simple layout for accessing 16bit values
+ ld1 {v16.16b-v19.16b}, [sp], #64
+ movi v20.8h, #1
+1: mov w8, w6 // beginning of line
+2: // Simple layout for accessing 16bit values
// with 8bit LUT.
//
// 00 01 02 03 04 05 06 07
@@ -55,33 +52,21 @@ function ff_hevc_sao_band_filter_8x8_8_neon, export=1
// |xDE#xAD|xCA#xFE|xBE#xEF|xFE#xED|....
// +----------------------------------->
// i-0 i-1 i-2 i-3
- // dst[x] = av_clip_pixel(src[x] + offset_table[src[x] >> shift]);
- ld1 {v2.8b}, [x1]
- // load src[x]
- uxtl v0.8h, v2.8b
- // >> shift
- ushr v2.8h, v0.8h, #3 // BIT_DEPTH - 3
- // x2 (access lower short)
- shl v1.8h, v2.8h, #1 // low (x2, accessing short)
- // +1 access upper short
- add v3.8h, v1.8h, v20.8h
- // shift insert index to upper byte
- sli v1.8h, v3.8h, #8
- // table
- tbx v2.16b, {v16.16b-v19.16b}, v1.16b
- // src[x] + table
- add v1.8h, v0.8h, v2.8h
- // clip + narrow
- sqxtun v4.8b, v1.8h
- // store
- st1 {v4.8b}, [x0]
- // done 8 pixels
- subs w8, w8, #8
+ ld1 {v2.8b}, [x1] // dst[x] = av_clip_pixel(src[x] + offset_table[src[x] >> shift]);
+ uxtl v0.8h, v2.8b // load src[x]
+ ushr v2.8h, v0.8h, #3 // >> BIT_DEPTH - 3
+ shl v1.8h, v2.8h, #1 // low (x2, accessing short)
+ add v3.8h, v1.8h, v20.8h // +1 access upper short
+ sli v1.8h, v3.8h, #8 // shift insert index to upper byte
+ tbx v2.16b, {v16.16b-v19.16b}, v1.16b // table
+ add v1.8h, v0.8h, v2.8h // src[x] + table
+ sqxtun v4.8b, v1.8h // clip + narrow
+ st1 {v4.8b}, [x0] // store
+ subs w8, w8, #8 // done 8 pixels
bne 2b
- // finished line
- subs w7, w7, #1
- add x0, x0, x2 // dst += stride_dst
- add x1, x1, x3 // src += stride_src
+ subs w7, w7, #1 // finished line, prep. new
+ add x0, x0, x2 // dst += stride_dst
+ add x1, x1, x3 // src += stride_src
bne 1b
ret
endfunc
--
2.32.0 (Apple Git-132)
_______________________________________________
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".
next prev parent reply other threads:[~2022-01-04 5:21 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-04 5:20 [FFmpeg-devel] [PATCH v3 1/6] lavc/arm: dont assign hevc_qpel functions for non-multiple of 8 widths J. Dekker
2022-01-04 5:20 ` [FFmpeg-devel] [PATCH v3 2/6] Revert "arm: hevc_qpel: Fix the assembly to work with non-multiple of 8 widths" J. Dekker
2022-01-04 5:20 ` [FFmpeg-devel] [PATCH v3 3/6] lavc/aarch64: add hevc sao edge 16x16 J. Dekker
2022-01-04 5:20 ` [FFmpeg-devel] [PATCH v3 4/6] lavc/aarch64: add hevc sao edge 8x8 J. Dekker
2022-01-04 5:20 ` J. Dekker [this message]
2022-01-04 5:20 ` [FFmpeg-devel] [PATCH v3 6/6] lavc/aarch64: add hevc sao band 8x8 tiling J. Dekker
2022-01-04 9:41 ` Martin Storsjö
2022-01-04 13:34 ` J. Dekker
2022-01-05 6:46 ` [FFmpeg-devel] [PATCH v3 1/6] lavc/arm: dont assign hevc_qpel functions for non-multiple of 8 widths Andreas Rheinhardt
2022-01-05 8:30 ` 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=20220104052018.9541-5-jdek@itanimul.li \
--to=jdek@itanimul.li \
--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