From: Alain Frisch <alain.frisch@lexifi.com>
To: "Yotam Barnoy" <yotambarnoy@gmail.com>,
"Frédéric Bour" <frederic.bour@lakaban.net>
Cc: "Gerd Stolpmann" <info@gerd-stolpmann.de>,
"Soegtrop, Michael" <michael.soegtrop@intel.com>,
"Christoph Höger" <christoph.hoeger@tu-berlin.de>,
"caml-list@inria.fr" <caml-list@inria.fr>
Subject: Re: [Caml-list] Closing the performance gap to C
Date: Wed, 21 Dec 2016 12:25:36 +0100 [thread overview]
Message-ID: <1506c421-618a-28d4-9a7b-7ba49baf47fa@lexifi.com> (raw)
In-Reply-To: <CAN6ygOnHptFUozfYQCVW8uySkGJHt5hS0jR_ZEkiH4K89+DU6w@mail.gmail.com>
On 19/12/2016 18:19, Yotam Barnoy wrote:
> Yes, this is a current weak point of OCaml compilation, which I've
> reported here (https://caml.inria.fr/mantis/view.php?id=7289). The
> only real solution to this currently is to improve Flambda to the
> point that unboxing is done at the Flambda level rather than at
> cmmgen.
The issue could very well be addressed outside flambda, at the cmmgen
level. See https://caml.inria.fr/mantis/view.php?id=5894 . Making
flambda aware of boxing can help its inlining decisions, but the notion
of having specialized unboxing calling convention is not really tied to
flambda.
Pushing #5894 forward could have a direct impact on numerical code. I
think it would really be useful to work on that, even if flambda also
does something along these lines, at some point.
-- Alain
next prev parent reply other threads:[~2016-12-21 11:25 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-17 13:01 Christoph Höger
2016-12-17 13:02 ` Christoph Höger
2016-12-19 10:58 ` Soegtrop, Michael
2016-12-19 11:51 ` Gerd Stolpmann
2016-12-19 14:52 ` Soegtrop, Michael
2016-12-19 16:41 ` Gerd Stolpmann
2016-12-19 17:09 ` Frédéric Bour
2016-12-19 17:19 ` Yotam Barnoy
2016-12-21 11:25 ` Alain Frisch [this message]
2016-12-21 14:45 ` Yotam Barnoy
2016-12-21 16:06 ` Alain Frisch
2016-12-21 16:31 ` Gerd Stolpmann
2016-12-21 16:39 ` Yotam Barnoy
2016-12-21 16:47 ` Gabriel Scherer
2016-12-21 16:51 ` Yotam Barnoy
2016-12-21 16:56 ` Mark Shinwell
2016-12-21 17:43 ` Alain Frisch
2016-12-22 8:39 ` Mark Shinwell
2016-12-22 17:23 ` Pierre Chambart
2016-12-21 17:35 ` Alain Frisch
2016-12-19 15:48 ` Ivan Gotovchits
2016-12-19 16:44 ` Yotam Barnoy
2016-12-19 16:59 ` Ivan Gotovchits
2016-12-21 9:08 ` Christoph Höger
2016-12-23 12:18 ` Oleg
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=1506c421-618a-28d4-9a7b-7ba49baf47fa@lexifi.com \
--to=alain.frisch@lexifi.com \
--cc=caml-list@inria.fr \
--cc=christoph.hoeger@tu-berlin.de \
--cc=frederic.bour@lakaban.net \
--cc=info@gerd-stolpmann.de \
--cc=michael.soegtrop@intel.com \
--cc=yotambarnoy@gmail.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 NNTP newsgroup(s).