From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <sourceware-bugzilla@sourceware.org>
Received: by sourceware.org (Postfix, from userid 48)
 id 05FED388E80B; Wed, 10 Mar 2021 15:11:18 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 05FED388E80B
From: "vries at gcc dot gnu.org" <sourceware-bugzilla@sourceware.org>
To: dwz@sourceware.org
Subject: [Bug default/27557] Use threading at sub-file level
Date: Wed, 10 Mar 2021 15:11:17 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: dwz
X-Bugzilla-Component: default
X-Bugzilla-Version: unspecified
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: vries at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: nobody at sourceware dot org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: attachments.created
Message-ID: <bug-27557-11298-OrAhfD6LP8@http.sourceware.org/bugzilla/>
In-Reply-To: <bug-27557-11298@http.sourceware.org/bugzilla/>
References: <bug-27557-11298@http.sourceware.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://sourceware.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: dwz@sourceware.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Dwz mailing list <dwz.sourceware.org>
List-Unsubscribe: <https://sourceware.org/mailman/options/dwz>,
 <mailto:dwz-request@sourceware.org?subject=unsubscribe>
List-Archive: <https://sourceware.org/pipermail/dwz/>
List-Help: <mailto:dwz-request@sourceware.org?subject=help>
List-Subscribe: <https://sourceware.org/mailman/listinfo/dwz>,
 <mailto:dwz-request@sourceware.org?subject=subscribe>
X-List-Received-Date: Wed, 10 Mar 2021 15:11:18 -0000

https://sourceware.org/bugzilla/show_bug.cgi?id=3D27557

--- Comment #2 from Tom de Vries <vries at gcc dot gnu.org> ---
Created attachment 13301
  --> https://sourceware.org/bugzilla/attachment.cgi?id=3D13301&action=3Ded=
it
Updated demonstrator patch

Now uses 8 threads, also does checksum_ref_die threaded.

Slightly better results: realtime now 14.7% less:
...
real:
series:  6130 6150 6160 6140 6150 6200 6230 6170 6220 6240
mean:  6179.00 (100%)
stddev:  40.12
series:  5220 5200 5220 5330 5220 5190 5430 5210 5200 5510
mean:  5273.00 (85.34%)
stddev:  112.55

user:
series:  5720 5790 5830 5730 5790 5850 5880 5820 5820 5840
mean:  5807.00 (100%)
stddev:  50.78
series:  7200 7170 7160 7240 7210 7090 7120 7160 7140 7070
mean:  7156.00 (123.23%)
stddev:  53.17

sys:
series:  400 340 320 390 350 340 340 340 390 390
mean:  360.00 (100%)
stddev:  29.06
series:  350 350 370 340 300 330 400 330 300 370
mean:  344.00 (95.56%)
stddev:  31.34

mem:
series:  1260484 1260480 1260420 1260412 1260416 1260540 1260420 1260548
1260656 1260420
mean:  1260479.60 (100%)
stddev:  80.78
series:  1260928 1260940 1260732 1260876 1260696 1260740 1260808 1260924
1260760 1260996
mean:  1260840.00 (100.03%)
stddev:  105.54
...

Additional known problem: Inter-CU references during checksum_ref_die.  Aga=
in,
should be rare.

--=20
You are receiving this mail because:
You are on the CC list for the bug.=