From: Bernhard Reutner-Fischer <rep.dot.nop@gmail.com>
To: Lipeng Zhu <lipeng.zhu@intel.com>
Cc: fortran@gcc.gnu.org, gcc-patches@gcc.gnu.org,
hongjiu.lu@intel.com, tianyou.li@intel.com, pan.deng@intel.com,
wangyang.guo@intel.com
Subject: Re: [PATCH v4] libgfortran: Replace mutex with rwlock
Date: Mon, 8 May 2023 12:28:48 +0200 [thread overview]
Message-ID: <20230508122848.1dbf109a@nbbrfq> (raw)
In-Reply-To: <20230508094442.1413139-1-lipeng.zhu@intel.com>
On Mon, 8 May 2023 17:44:43 +0800
Lipeng Zhu <lipeng.zhu@intel.com> wrote:
> This patch try to introduce the rwlock and split the read/write to
> unit_root tree and unit_cache with rwlock instead of the mutex to
> increase CPU efficiency. In the get_gfc_unit function, the percentage
> to step into the insert_unit function is around 30%, in most instances,
> we can get the unit in the phase of reading the unit_cache or unit_root
> tree. So split the read/write phase by rwlock would be an approach to
> make it more parallel.
>
> BTW, the IPC metrics can gain around 9x in our test
> server with 220 cores. The benchmark we used is
> https://github.com/rwesson/NEAT
See commentary typos below.
You did not state if you regression tested the patch?
Other than that it LGTM but i cannot approve it.
> diff --git a/libgfortran/io/async.h b/libgfortran/io/async.h
> index ad226c8e856..0033cc74252 100644
> --- a/libgfortran/io/async.h
> +++ b/libgfortran/io/async.h
> @@ -210,6 +210,128 @@
> DEBUG_PRINTF ("%s" DEBUG_RED "ACQ:" DEBUG_NORM " %-30s %78p\n", aio_prefix, #mutex, mutex); \
> } while (0)
>
> +#ifdef __GTHREAD_RWLOCK_INIT
> +#define RWLOCK_DEBUG_ADD(rwlock) do { \
> + aio_rwlock_debug *n; \
> + n = xmalloc (sizeof(aio_rwlock_debug)); \
Missing space before the open brace: sizeof (
> diff --git a/libgfortran/io/unit.c b/libgfortran/io/unit.c
> index 82664dc5f98..62f1db21d34 100644
> --- a/libgfortran/io/unit.c
> +++ b/libgfortran/io/unit.c
> @@ -33,34 +33,36 @@ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
>
>
> /* IO locking rules:
> - UNIT_LOCK is a master lock, protecting UNIT_ROOT tree and UNIT_CACHE.
> + UNIT_RWLOCK is a master lock, protecting UNIT_ROOT tree and UNIT_CACHE.
> + And use the rwlock to spilt read and write phase to UNIT_ROOT tree
> + and UNIT_CACHE to increase CPU efficiency.
s/spilt/split. Maybe:
Using an rwlock improves efficiency by allowing us to separate readers
and writers of both UNIT_ROOT and UNIT_CACHE.
> @@ -350,6 +356,17 @@ retry:
> if (c == 0)
> break;
> }
> + /* We did not find a unit in the cache nor in the unit list, create a new
> + (locked) unit and insert into the unit list and cache.
> + Manipulating either or both the unit list and the unit cache requires to
> + hold a write-lock [for obvious reasons]:
> + 1. By separating the read/write lock, it will greatly reduce the contention
> + at the read part, while write part is not always necessary or most
> + unlikely once the unit hit in cache.
+ By separating the read/write lock, we will greatly reduce the contention
+ on the read part, while the write part is unlikely once the unit hits
+ the cache.
> + 2. We try to balance the implementation complexity and the performance
> + gains that fit into current cases we observed by just using a
> + pthread_rwlock. */
Let's drop 2.
thanks,
next prev parent reply other threads:[~2023-05-08 10:28 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20230424214534.77117b73 () nbbrfq>
2023-05-08 9:44 ` Lipeng Zhu
2023-05-08 10:28 ` Bernhard Reutner-Fischer [this message]
2023-05-09 2:32 Zhu, Lipeng
2023-05-16 7:08 ` Zhu, Lipeng
2023-05-23 2:53 ` Zhu, Lipeng
2023-05-24 19:18 ` Thomas Koenig
2023-08-18 3:06 ` Zhu, Lipeng
2023-09-14 8:33 ` Zhu, Lipeng
2023-10-23 1:21 ` Zhu, Lipeng
2023-10-23 5:52 ` Thomas Koenig
2023-10-23 23:59 ` Zhu, Lipeng
2023-11-01 10:14 ` Zhu, Lipeng
2023-11-02 9:58 ` Bernhard Reutner-Fischer
2023-11-23 9:36 ` Zhu, Lipeng
2023-12-07 5:18 ` Zhu, Lipeng
2023-05-25 12:40 Zhu, Lipeng
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=20230508122848.1dbf109a@nbbrfq \
--to=rep.dot.nop@gmail.com \
--cc=fortran@gcc.gnu.org \
--cc=gcc-patches@gcc.gnu.org \
--cc=hongjiu.lu@intel.com \
--cc=lipeng.zhu@intel.com \
--cc=pan.deng@intel.com \
--cc=tianyou.li@intel.com \
--cc=wangyang.guo@intel.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).