From: Drew Dunne <asdunne-at-google.com@ffmpeg.org>
To: ffmpeg-devel@ffmpeg.org
Cc: Drew Dunne <asdunne@google.com>
Subject: [FFmpeg-devel] [PATCH] swscale/output: Use av_sat_add32 in yuv2rgba64 templates to avoid underflow
Date: Mon, 12 Dec 2022 20:08:28 +0000
Message-ID: <20221212200828.329839-1-asdunne@google.com> (raw)
Previously I sent this patch to solve an overflow in these templates. That
patch wasn't used in favor of one that biased the output calculations to
avoid the double clipping. Now I've found an underflow case, which I've put
the command below, and I'll attach an input image in a reply.
./ffmpeg \
-f rawvideo -video_size 64x64 -pixel_format yuva420p10le \
-i yuv2rgb_underflow_w64h64.yuva \
-filter_complex \
"scale=flags=bicubic+full_chroma_int+full_chroma_inp+bitexact+accurate_rnd:in_color_matrix=bt2020:out_color_matrix=bt2020:in_range=mpeg:out_range=mpeg,format=rgba64[out]" \
-f rawvideo -codec:v:0 rawvideo -pixel_format rgba64 -map '[out]' \
-y underflow_w64h64.rgba64
The previous overflow case was in this thread:
https://ffmpeg.org/pipermail/ffmpeg-devel/2022-November/303532.html
---
libswscale/output.c | 96 ++++++++++++++++++++++-----------------------
1 file changed, 48 insertions(+), 48 deletions(-)
diff --git a/libswscale/output.c b/libswscale/output.c
index 5c85bff971..8abf043d73 100644
--- a/libswscale/output.c
+++ b/libswscale/output.c
@@ -1109,20 +1109,20 @@ yuv2rgba64_X_c_template(SwsContext *c, const int16_t *lumFilter,
B = U * c->yuv2rgb_u2b_coeff;
// 8 bits: 30 - 22 = 8 bits, 16 bits: 30 bits - 14 = 16 bits
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y1) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y1)) >> 14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A1 , 30) >> 14);
- output_pixel(&dest[4], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[6], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[6], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
output_pixel(&dest[7], av_clip_uintp2(A2 , 30) >> 14);
dest += 8;
} else {
- output_pixel(&dest[3], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[4], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[3], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
dest += 6;
}
}
@@ -1175,20 +1175,20 @@ yuv2rgba64_2_c_template(SwsContext *c, const int32_t *buf[2],
A2 += 1 << 13;
}
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y1) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y1)) >> 14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A1 , 30) >> 14);
- output_pixel(&dest[4], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[6], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[6], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
output_pixel(&dest[7], av_clip_uintp2(A2 , 30) >> 14);
dest += 8;
} else {
- output_pixel(&dest[3], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[4], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[3], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
dest += 6;
}
}
@@ -1232,20 +1232,20 @@ yuv2rgba64_1_c_template(SwsContext *c, const int32_t *buf0,
G = V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
B = U * c->yuv2rgb_u2b_coeff;
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y1) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y1)) >> 14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A1 , 30) >> 14);
- output_pixel(&dest[4], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[6], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[6], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
output_pixel(&dest[7], av_clip_uintp2(A2 , 30) >> 14);
dest += 8;
} else {
- output_pixel(&dest[3], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[4], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[3], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
dest += 6;
}
}
@@ -1278,20 +1278,20 @@ yuv2rgba64_1_c_template(SwsContext *c, const int32_t *buf0,
G = V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
B = U * c->yuv2rgb_u2b_coeff;
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y1) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y1) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y1)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y1)) >> 14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A1 , 30) >> 14);
- output_pixel(&dest[4], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[6], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[6], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
output_pixel(&dest[7], av_clip_uintp2(A2 , 30) >> 14);
dest += 8;
} else {
- output_pixel(&dest[3], av_clip_uintp2(((R_B + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[4], av_clip_uintp2((( G + Y2) >> 14) + (1<<15), 16));
- output_pixel(&dest[5], av_clip_uintp2(((B_R + Y2) >> 14) + (1<<15), 16));
+ output_pixel(&dest[3], av_clip_uintp2(((av_sat_add32(R_B, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[4], av_clip_uintp2(((av_sat_add32( G, Y2)) >> 14) + (1<<15), 16));
+ output_pixel(&dest[5], av_clip_uintp2(((av_sat_add32(B_R, Y2)) >> 14) + (1<<15), 16));
dest += 6;
}
}
@@ -1351,9 +1351,9 @@ yuv2rgba64_full_X_c_template(SwsContext *c, const int16_t *lumFilter,
B = U * c->yuv2rgb_u2b_coeff;
// 8bit: 30 - 22 = 8bit, 16bit: 30bit - 14 = 16bit
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y)>>14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y)>>14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y)>>14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y))>>14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A, 30) >> 14);
dest += 4;
@@ -1404,9 +1404,9 @@ yuv2rgba64_full_2_c_template(SwsContext *c, const int32_t *buf[2],
A += 1 << 13;
}
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y))>>14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A, 30) >> 14);
dest += 4;
@@ -1448,9 +1448,9 @@ yuv2rgba64_full_1_c_template(SwsContext *c, const int32_t *buf0,
G = V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
B = U * c->yuv2rgb_u2b_coeff;
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y))>>14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A, 30) >> 14);
dest += 4;
@@ -1481,9 +1481,9 @@ yuv2rgba64_full_1_c_template(SwsContext *c, const int32_t *buf0,
G = V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
B = U * c->yuv2rgb_u2b_coeff;
- output_pixel(&dest[0], av_clip_uintp2(((R_B + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[1], av_clip_uintp2((( G + Y) >> 14) + (1<<15), 16));
- output_pixel(&dest[2], av_clip_uintp2(((B_R + Y) >> 14) + (1<<15), 16));
+ output_pixel(&dest[0], av_clip_uintp2(((av_sat_add32(R_B, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[1], av_clip_uintp2(((av_sat_add32( G, Y))>>14) + (1<<15), 16));
+ output_pixel(&dest[2], av_clip_uintp2(((av_sat_add32(B_R, Y))>>14) + (1<<15), 16));
if (eightbytes) {
output_pixel(&dest[3], av_clip_uintp2(A, 30) >> 14);
dest += 4;
--
2.39.0.rc1.256.g54fd8350bd-goog
_______________________________________________
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 reply other threads:[~2022-12-12 20:08 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-12-12 20:08 Drew Dunne [this message]
2022-12-12 20:09 ` Drew Dunne
2022-12-13 20:32 ` Michael Niedermayer
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=20221212200828.329839-1-asdunne@google.com \
--to=asdunne-at-google.com@ffmpeg.org \
--cc=asdunne@google.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