From: Jakub Jelinek <jakub@redhat.com>
To: Hongtao Liu <crazylht@gmail.com>
Cc: Jason Merrill <jason@redhat.com>,
Jonathan Wakely <jwakely@redhat.com>,
"Joseph S. Myers" <joseph@codesourcery.com>,
Bruce Korb <bkorb@gnu.org>,
gcc-patches@gcc.gnu.org
Subject: Re: [PATCH] c++: Implement P1467R9 - Extended floating-point types and standard names compiler part except for bfloat16 [PR106652]
Date: Tue, 20 Sep 2022 10:51:18 +0200 [thread overview]
Message-ID: <Yyl/BkcvjpWW3Jyz@tucnak> (raw)
In-Reply-To: <CAMZc-bxB2fVAxVbBmqOj-ixTJybuX-V9dT2FvjrQR-wWRR7HkQ@mail.gmail.com>
On Tue, Sep 20, 2022 at 11:35:07AM +0800, Hongtao Liu wrote:
> > The question is (mainly for aarch64, arm and x86 backend maintainers) if we
> > shouldn't support it, in the PR there is a partial patch to do so, but
> > the big question is if it should be supported as the __bf16 type those
> > 3 targets use with u6__bf16 mangling and remove those *_invalid_* cases
> > and add conversions to/from at least SFmode but probably also DFmode, TFmode
> > and XFmode on x86 and implement arithmetics on those through conversion to
> > SFmode, performing arithmetics there and conversion back.
> > Conversion from BFmode to SFmode is easy, left shift by 16 and ought to be
> > implemented inline, SFmode -> BFmode conversion is harder,
> > I think it is roughly:
> I'm not sure if there should be any floating point exceptions for
> BFmode operation.
> For x86, there's no floating point exceptions for AVX512_BF16 related
> instructions
As long as __bf16 is just an extension, supporting or not supporting
exceptions on sNaNs is just fine I think, but I'm afraid it is different
for std::bfloat16_t. If we claim we support it (define that type
in <stdfloat>, predefine __STD_BFLOAT16_TYPE__), then it needs to follow
ISO/IEC/IEEE 60559, and I'm afraid that means also exceptions and the like.
While the IEEE spec doesn't cover the exact bfloat16 format, C++ talks about
a format with these and these number of bits here and there that behaves
like in IEEE otherwise.
Whether we support std::bfloat16_t at all is our choice, if we do support
it, whether we support it with __bf16 underlying type or come up with
something different, it is up to us, and with -ffast-math/-Ofast etc.
we can certainly use hw instructions for it which don't raise exceptions.
At least that is my limited understanding of it...
Jakub
next prev parent reply other threads:[~2022-09-20 8:51 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-12 8:05 Jakub Jelinek
2022-09-12 19:36 ` Joseph Myers
2022-09-12 20:52 ` Jakub Jelinek
2022-09-12 21:00 ` Jakub Jelinek
2022-09-13 17:50 ` Joseph Myers
2022-09-16 11:48 ` Jason Merrill
2022-09-16 17:34 ` Jakub Jelinek
2022-09-17 8:58 ` Jason Merrill
2022-09-19 16:39 ` Jakub Jelinek
2022-09-26 21:15 ` Jason Merrill
2022-09-26 22:11 ` Jakub Jelinek
2022-09-20 3:35 ` Hongtao Liu
2022-09-20 7:14 ` Hongtao Liu
2022-09-20 8:51 ` Jakub Jelinek [this message]
2022-09-22 15:56 ` [RFC PATCH] __trunc{tf,xf,df,sf,hf}bf2, __truncbfhf2 and __extendbfsf2 Jakub Jelinek
2022-09-23 0:44 ` Hongtao Liu
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=Yyl/BkcvjpWW3Jyz@tucnak \
--to=jakub@redhat.com \
--cc=bkorb@gnu.org \
--cc=crazylht@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jason@redhat.com \
--cc=joseph@codesourcery.com \
--cc=jwakely@redhat.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).