From: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
To: ffmpeg-devel@ffmpeg.org
Subject: Re: [FFmpeg-devel] [PATCH 06/11] avutil/half2float: adjust conversion of NaN
Date: Wed, 10 Aug 2022 23:43:39 +0200
Message-ID: <DB6PR0101MB22144FCD3B0FECF6825557D58F659@DB6PR0101MB2214.eurprd01.prod.exchangelabs.com> (raw)
In-Reply-To: <423b2beb-9ad6-003e-be31-e3237f9f9788@rothenpieler.org>
Timo Rothenpieler:
> On 10.08.2022 23:24, Andreas Rheinhardt wrote:
>> Timo Rothenpieler:
>>> IEEE-754 differentiates two different kind of NaNs.
>>> Quiet and Signaling ones. They are differentiated by the MSB of the
>>> mantissa.
>>>
>>> For whatever reason, actual hardware conversion of half to single always
>>> sets the signaling bit to 1 if the mantissa is != 0, and to 0 if it's 0.
>>> So our code has to follow suite or fate-testing hardware float16 will be
>>> impossible.
>>
>> What does the exr spec say about quiet and signaling nans?
>
> Not sure how exr would be involved here.
Your patch changes the output of an exr-test. The output of the exr
decoder is presumably determined by the exr spec. There is after all the
possibility that what hardware does in hardware and what this patch does
in software is incompatible with what exr specifies.
> But I tested this on both aarch64, x86 with sse2 emulation and x86 f16c
> on alderlake and zen2.
> They all perfectly agree and match 100% what this changed code produces
> for the entire range of 65k possible values.
> _______________________________________________
> 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".
next prev parent reply other threads:[~2022-08-10 21:43 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-10 20:47 [FFmpeg-devel] [PATCH 01/11] lavu/pixfmt: add packed RGBA float16 format Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 02/11] avutil/hwcontext_d3d11va: add support for rgbaf16 pixel format Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 03/11] avfilter/vsrc_ddagrab: add rgbaf16 output support Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 04/11] avfilter/vsrc_ddagrab: add options for more control over output format fallback Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 05/11] avutil: move half-precision float helper to avutil Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 06/11] avutil/half2float: adjust conversion of NaN Timo Rothenpieler
2022-08-10 21:24 ` Andreas Rheinhardt
2022-08-10 21:36 ` Timo Rothenpieler
2022-08-10 21:43 ` Andreas Rheinhardt [this message]
2022-08-10 21:53 ` Timo Rothenpieler
2022-08-10 22:14 ` Mark Reid
2022-08-10 22:18 ` James Almer
2022-08-10 22:28 ` Timo Rothenpieler
2022-08-10 22:37 ` Mark Reid
2022-08-10 22:55 ` Timo Rothenpieler
2022-08-11 2:18 ` Mark Reid
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 07/11] avutil/half2float: move tables to header-internal structs Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 08/11] avutil/half2float: move non-inline init code out of header Timo Rothenpieler
2022-08-11 20:46 ` Michael Niedermayer
2022-08-11 20:50 ` Andreas Rheinhardt
2022-08-11 21:16 ` Michael Niedermayer
2022-08-11 21:31 ` Andreas Rheinhardt
2022-08-14 19:32 ` Michael Niedermayer
2022-08-15 4:20 ` Andreas Rheinhardt
2022-08-15 18:09 ` Michael Niedermayer
2022-08-14 21:54 ` Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 09/11] avutil/half2float: use native _Float16 if available Timo Rothenpieler
2022-08-10 21:03 ` Andreas Rheinhardt
2022-08-10 21:58 ` Timo Rothenpieler
2022-08-10 22:02 ` James Almer
2022-08-10 22:51 ` [FFmpeg-devel] [PATCH v2 " Timo Rothenpieler
2022-08-11 0:14 ` James Almer
2022-08-11 11:50 ` Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 10/11] swscale: add SwsContext parameter to input functions Timo Rothenpieler
2022-08-10 20:52 ` Timo Rothenpieler
2022-08-10 21:55 ` Andreas Rheinhardt
2022-08-10 22:02 ` Timo Rothenpieler
2022-08-10 20:47 ` [FFmpeg-devel] [PATCH 11/11] swscale/input: add rgbaf16 input support Timo Rothenpieler
2022-08-10 21:37 ` Timo Rothenpieler
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=DB6PR0101MB22144FCD3B0FECF6825557D58F659@DB6PR0101MB2214.eurprd01.prod.exchangelabs.com \
--to=andreas.rheinhardt@outlook.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