From: "Kewen.Lin" <linkw@linux.ibm.com>
To: Jakub Jelinek <jakub@redhat.com>
Cc: Michael Meissner <meissner@linux.ibm.com>,
gcc-patches@gcc.gnu.org,
Segher Boessenkool <segher@kernel.crashing.org>,
Peter Bergner <bergner@linux.ibm.com>,
David Edelsohn <dje.gcc@gmail.com>,
Will Schmidt <will_schmidt@vnet.ibm.com>,
William Seurer <seurer@gcc.gnu.org>,
Joseph Myers <joseph@codesourcery.com>
Subject: Re: [PATCH 2/3] Make __float128 use the _Float128 type, PR target/107299
Date: Thu, 15 Dec 2022 15:54:05 +0800 [thread overview]
Message-ID: <62a5ce3a-74e0-d8a2-d1e9-919a7183300d@linux.ibm.com> (raw)
In-Reply-To: <Y5mmj4stv5b/KWmz@tucnak>
on 2022/12/14 18:33, Jakub Jelinek wrote:
> On Wed, Dec 14, 2022 at 06:11:26PM +0800, Kewen.Lin wrote:
>>> The hacks with different precisions of powerpc 128-bit floating types are
>>> very unfortunate, it is I assume because the middle-end asserted that scalar
>>> floating point types with different modes have different precision.
>>> We no longer assert that, as BFmode and HFmode (__bf16 and _Float16) have
>>> the same 16-bit precision as well and e.g. C++ FE knows to treat standard
>>> vs. extended floating point types vs. other unknown floating point types
>>> differently in finding result type of binary operations or in which type
>>> comparisons will be done.
>>
>> It's good news, for now those three long double modes on Power have different
>> precisions, if they can have the same precision, I'd expect the ICE should be
>> gone.
>
> I'm talking mainly about r13-3292, the asserts now check different modes
> have different precision unless it is half vs. brain or vice versa, but
> could be changed further, but if the precision is the same, the FEs
> and the middle-end needs to know how to deal with those.
> For C++23, say when __ibm128 is the same as long double and _Float128 is
> supported, the 2 types are unordered (neither is a subset or superset of
> the other because there are many _Float128 values one can't represent
> in double double (whether anything with exponent larger than what double
> can represent or most of the more precise values), but because of the
> variable precision there are double double values that can't be represented
> in _Float128 either) and so we can error on comparisons of those or on
> arithmetics with such arguments (unless explicitly converted first).
> But for backwards compatibility we can't do that for __float128 vs. __ibm128
> and so need to backwards compatibly decide what wins. And for the
> middle-end say even for mode conversions decide what is widening and what is
> narrowing even when they are unordered.
Thanks for the pointer! I don't have good understanding on the backwards
compatibility on those conversions, guessing Mike, Segher and David would have
more insights.
BR,
Kewen
next prev parent reply other threads:[~2022-12-15 7:54 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-02 2:39 Patch [0/3] for PR target/107299 (GCC does not build on PowerPC when long double is IEEE 128-bit) Michael Meissner
2022-11-02 2:40 ` [PATCH 1/3] Rework 128-bit complex multiply and divide, PR target/107299 Michael Meissner
2022-11-07 15:41 ` Ping: " Michael Meissner
2022-11-29 17:43 ` Ping #2: " Michael Meissner
2022-12-02 17:58 ` Ping #3: " Michael Meissner
2022-12-06 9:36 ` Kewen.Lin
2022-12-07 6:44 ` Michael Meissner
2022-12-07 7:55 ` Kewen.Lin
2022-12-08 22:04 ` Michael Meissner
2022-12-12 10:20 ` Kewen.Lin
2022-12-13 6:14 ` Michael Meissner
2022-12-13 13:51 ` Segher Boessenkool
2022-12-14 8:45 ` Kewen.Lin
2022-12-13 6:23 ` Michael Meissner
2022-11-02 2:42 ` [PATCH 2/3] Make __float128 use the _Float128 type, " Michael Meissner
2022-11-07 15:43 ` Ping: " Michael Meissner
2022-11-29 17:44 ` Michael Meissner
2022-12-02 18:01 ` Ping #3: " Michael Meissner
2022-12-06 11:27 ` Kewen.Lin
2022-12-14 8:46 ` Kewen.Lin
2022-12-14 9:36 ` Jakub Jelinek
2022-12-14 10:11 ` Kewen.Lin
2022-12-14 10:33 ` Jakub Jelinek
2022-12-15 7:54 ` Kewen.Lin [this message]
2022-12-15 7:45 ` Kewen.Lin
2022-12-15 18:28 ` Joseph Myers
2022-12-15 18:49 ` Segher Boessenkool
2022-12-15 18:56 ` Jakub Jelinek
2022-12-15 20:26 ` Segher Boessenkool
2022-12-15 17:59 ` Segher Boessenkool
2022-12-16 0:09 ` Michael Meissner
2022-12-16 17:55 ` Segher Boessenkool
2022-12-16 21:53 ` Michael Meissner
2023-01-11 20:24 ` Michael Meissner
2022-11-02 2:44 ` [PATCH 3/3] Update float 128-bit conversions, " Michael Meissner
2022-11-07 15:44 ` Ping: " Michael Meissner
2022-11-29 17:46 ` Ping #3: " Michael Meissner
2022-12-02 18:04 ` Michael Meissner
2022-12-06 14:56 ` Patch [0/3] for PR target/107299 (GCC does not build on PowerPC when long double is IEEE 128-bit) Segher Boessenkool
2022-12-06 15:03 ` Jakub Jelinek
2022-12-13 14:11 ` Segher Boessenkool
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=62a5ce3a-74e0-d8a2-d1e9-919a7183300d@linux.ibm.com \
--to=linkw@linux.ibm.com \
--cc=bergner@linux.ibm.com \
--cc=dje.gcc@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jakub@redhat.com \
--cc=joseph@codesourcery.com \
--cc=meissner@linux.ibm.com \
--cc=segher@kernel.crashing.org \
--cc=seurer@gcc.gnu.org \
--cc=will_schmidt@vnet.ibm.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).