From: Szabolcs Nagy <Szabolcs.Nagy@arm.com>
To: Richard Biener <richard.guenther@gmail.com>,
Giuliano Augusto Faulin Belinassi <giuliano.belinassi@usp.br>
Cc: nd <nd@arm.com>, GCC Development <gcc@gcc.gnu.org>,
"kernel-usp@googlegroups.com" <kernel-usp@googlegroups.com>,
"gold@ime.usp.br" <gold@ime.usp.br>,
"alfredo.goldman@gmail.com" <alfredo.goldman@gmail.com>
Subject: Re: Parallelize the compilation using Threads
Date: Thu, 15 Nov 2018 18:36:00 -0000 [thread overview]
Message-ID: <1a6444d6-7d37-84cb-8bb2-52d6c37a51ad@arm.com> (raw)
In-Reply-To: <CAFiYyc1kogmJ_5suHg+7fDaNjrYZnGjNGq4dew5uvc+w6-_BKQ@mail.gmail.com>
On 15/11/18 10:29, Richard Biener wrote:
> In my view (I proposed the thing) the most interesting parts are
> getting GCCs global state documented and reduced. The parallelization
> itself is an interesting experiment but whether there will be any
> substantial improvement for builds that can already benefit from make
> parallelism remains a question.
in the common case (project with many small files, much more than
core count) i'd expect a regression:
if gcc itself tries to parallelize that introduces inter thread
synchronization and potential false sharing in gcc (e.g. malloc
locks) that does not exist with make parallelism (glibc can avoid
some atomic instructions when a process is single threaded).
next prev parent reply other threads:[~2018-11-15 18:07 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-15 10:12 Giuliano Augusto Faulin Belinassi
2018-11-15 11:44 ` Richard Biener
2018-11-15 15:54 ` Jonathan Wakely
2018-11-15 18:07 ` Jeff Law
2018-11-15 18:36 ` Szabolcs Nagy [this message]
2018-11-16 14:25 ` Martin Jambor
2018-11-16 22:40 ` Giuliano Augusto Faulin Belinassi
2018-11-19 14:36 ` Richard Biener
2018-12-12 15:46 ` Giuliano Augusto Faulin Belinassi
2018-12-13 8:12 ` Bin.Cheng
2018-12-14 14:15 ` Giuliano Belinassi
2018-12-17 11:06 ` Richard Biener
2019-01-14 11:42 ` Giuliano Belinassi
2019-01-14 12:23 ` Richard Biener
2019-01-15 21:45 ` Giuliano Belinassi
2019-01-16 12:44 ` Richard Biener
2019-02-07 14:14 ` Giuliano Belinassi
2019-02-11 21:46 ` Giuliano Belinassi
2019-02-12 14:12 ` Richard Biener
2019-02-16 4:35 ` Oleg Endo
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=1a6444d6-7d37-84cb-8bb2-52d6c37a51ad@arm.com \
--to=szabolcs.nagy@arm.com \
--cc=alfredo.goldman@gmail.com \
--cc=gcc@gcc.gnu.org \
--cc=giuliano.belinassi@usp.br \
--cc=gold@ime.usp.br \
--cc=kernel-usp@googlegroups.com \
--cc=nd@arm.com \
--cc=richard.guenther@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 read-only IMAP folder(s) and NNTP newsgroup(s).