public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/64003] valgrind complains about get_attr_length_nobnd in insn-attrtab.c from i386.md
Date: Fri, 24 Jul 2015 08:32:00 -0000 [thread overview]
Message-ID: <bug-64003-4-3aH7qEOXmv@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-64003-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=64003
Uroš Bizjak <ubizjak at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |dcb314 at hotmail dot com
--- Comment #29 from Uroš Bizjak <ubizjak at gmail dot com> ---
*** Bug 66987 has been marked as a duplicate of this bug. ***
>From gcc-bugs-return-493173-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org Fri Jul 24 08:32:28 2015
Return-Path: <gcc-bugs-return-493173-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Delivered-To: listarch-gcc-bugs@gcc.gnu.org
Received: (qmail 4186 invoked by alias); 24 Jul 2015 08:32:28 -0000
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
Delivered-To: mailing list gcc-bugs@gcc.gnu.org
Received: (qmail 4106 invoked by uid 48); 24 Jul 2015 08:32:24 -0000
From: "ubizjak at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c/66987] valgrind error in get_attr_length_nobnd
Date: Fri, 24 Jul 2015 08:32:00 -0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: c
X-Bugzilla-Version: 6.0
X-Bugzilla-Keywords:
X-Bugzilla-Severity: normal
X-Bugzilla-Who: ubizjak at gmail dot com
X-Bugzilla-Status: RESOLVED
X-Bugzilla-Resolution: DUPLICATE
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags:
X-Bugzilla-Changed-Fields: bug_status resolution
Message-ID: <bug-66987-4-cyFxTEY1b1@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-66987-4@http.gcc.gnu.org/bugzilla/>
References: <bug-66987-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-SW-Source: 2015-07/txt/msg02063.txt.bz2
Content-length: 643
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66987
Uroš Bizjak <ubizjak at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |RESOLVED
Resolution|--- |DUPLICATE
--- Comment #1 from Uroš Bizjak <ubizjak at gmail dot com> ---
This is actualy a dup of 64003, I removed extra jmp patterns in r225138.
Let's fix this properly using ADJUST_INSN_LENGTH, as suggested in the PR 64003
*** This bug has been marked as a duplicate of bug 64003 ***
>From gcc-bugs-return-493175-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org Fri Jul 24 08:34:13 2015
Return-Path: <gcc-bugs-return-493175-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Delivered-To: listarch-gcc-bugs@gcc.gnu.org
Received: (qmail 27115 invoked by alias); 24 Jul 2015 08:34:13 -0000
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
Delivered-To: mailing list gcc-bugs@gcc.gnu.org
Received: (qmail 27085 invoked by uid 48); 24 Jul 2015 08:34:09 -0000
From: "neleai at seznam dot cz" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/66989] New: poor performance of builtin_isfinite on x64
Date: Fri, 24 Jul 2015 08:34:00 -0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: middle-end
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords:
X-Bugzilla-Severity: normal
X-Bugzilla-Who: neleai at seznam dot cz
X-Bugzilla-Status: UNCONFIRMED
X-Bugzilla-Resolution:
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags:
X-Bugzilla-Changed-Fields: bug_id short_desc product version bug_status bug_severity priority component assigned_to reporter target_milestone
Message-ID: <bug-66989-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-SW-Source: 2015-07/txt/msg02065.txt.bz2
Content-length: 6066
https://gcc.gnu.org/bugzilla/show_bug.cgi?idf989
Bug ID: 66989
Summary: poor performance of builtin_isfinite on x64
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: neleai at seznam dot cz
Target Milestone: ---
This is another part of considering floating classification builtin
performance. This starts to be more cpu dependent as benchmark show large
improvement for core2 but almost none for haswell.
#define EXTRACT_WORDS64(i, d) \
do { \
int64_t i_; \
asm ("movq %1, %0" : "=rm" (i_) : "x" ((double) (d))); \
(i) = i_; \
} while (0)
int I2
isfinite2 (double dx)
{
unsigned long x;
EXTRACT_WORDS64(dx, x);
if (2 * x < 0xffe0000000000000)
return 1;
else
return 0;
}
core2:
don't inline
conditional add
branched
real 0m1.334s
user 0m1.334s
sys 0m0.000s
builtin
real 0m1.577s
user 0m1.576s
sys 0m0.000s
branch
branched
real 0m1.453s
user 0m1.452s
sys 0m0.000s
builtin
real 0m1.335s
user 0m1.334s
sys 0m0.000s
sum
branched
real 0m1.336s
user 0m1.335s
sys 0m0.000s
builtin
real 0m1.575s
user 0m1.573s
sys 0m0.000s
inline outer call
conditional add
branched
real 0m1.046s
user 0m1.046s
sys 0m0.000s
builtin
real 0m0.972s
user 0m0.971s
sys 0m0.000s
branch
branched
real 0m0.849s
user 0m0.845s
sys 0m0.003s
builtin
real 0m0.971s
user 0m0.970s
sys 0m0.002s
sum
branched
real 0m1.097s
user 0m1.095s
sys 0m0.000s
builtin
real 0m1.104s
user 0m1.100s
sys 0m0.003s
inline inner call
conditional add
branched
real 0m0.981s
user 0m0.980s
sys 0m0.000s
builtin
real 0m0.971s
user 0m0.971s
sys 0m0.000s
branch
branched
real 0m0.849s
user 0m0.848s
sys 0m0.000s
builtin
real 0m0.970s
user 0m0.969s
sys 0m0.000s
sum
branched
real 0m1.094s
user 0m1.094s
sys 0m0.000s
builtin
real 0m1.101s
user 0m1.100s
sys 0m0.000s
tigth loop
conditional add
branched
real 0m0.365s
user 0m0.364s
sys 0m0.000s
builtin
real 0m0.433s
user 0m0.433s
sys 0m0.000s
branch
branched
real 0m0.126s
user 0m0.126s
sys 0m0.000s
builtin
real 0m0.368s
user 0m0.367s
sys 0m0.000s
sum
branched
real 0m0.367s
user 0m0.365s
sys 0m0.000s
builtin
real 0m0.632s
user 0m0.631s
sys 0m0.000s
fx10
don't inline
conditional add
branched
real 0m1.297s
user 0m1.295s
sys 0m0.004s
builtin
real 0m1.300s
user 0m1.299s
sys 0m0.004s
branch
branched
real 0m0.657s
user 0m0.658s
sys 0m0.000s
builtin
real 0m0.677s
user 0m0.677s
sys 0m0.000s
sum
branched
real 0m1.296s
user 0m1.295s
sys 0m0.004s
builtin
real 0m1.313s
user 0m1.315s
sys 0m0.000s
inline outer call
conditional add
branched
real 0m1.296s
user 0m1.298s
sys 0m0.000s
builtin
real 0m1.297s
user 0m1.298s
sys 0m0.000s
branch
branched
real 0m0.365s
user 0m0.366s
sys 0m0.000s
builtin
real 0m0.412s
user 0m0.409s
sys 0m0.004s
sum
branched
real 0m1.302s
user 0m1.304s
sys 0m0.000s
builtin
real 0m1.305s
user 0m1.307s
sys 0m0.000s
inline inner call
conditional add
branched
real 0m1.299s
user 0m1.300s
sys 0m0.000s
builtin
real 0m1.296s
user 0m1.297s
sys 0m0.000s
branch
branched
real 0m0.509s
user 0m0.509s
sys 0m0.000s
builtin
real 0m0.539s
user 0m0.539s
sys 0m0.001s
sum
branched
real 0m1.301s
user 0m1.303s
sys 0m0.000s
builtin
real 0m1.307s
user 0m1.309s
sys 0m0.000s
tigth loop
conditional add
branched
real 0m0.369s
user 0m0.369s
sys 0m0.000s
builtin
real 0m0.362s
user 0m0.362s
sys 0m0.000s
branch
branched
real 0m0.152s
user 0m0.152s
sys 0m0.000s
builtin
real 0m0.260s
user 0m0.257s
sys 0m0.004s
sum
branched
real 0m0.362s
user 0m0.362s
sys 0m0.001s
builtin
real 0m0.399s
user 0m0.399s
sys 0m0.001s
haswelldon't inline
conditional add
branched
real 0m0.697s
user 0m0.698s
sys 0m0.000s
builtin
real 0m0.802s
user 0m0.803s
sys 0m0.000s
branch
branched
real 0m0.697s
user 0m0.698s
sys 0m0.000s
builtin
real 0m0.796s
user 0m0.793s
sys 0m0.003s
sum
branched
real 0m0.717s
user 0m0.717s
sys 0m0.000s
builtin
real 0m0.802s
user 0m0.802s
sys 0m0.000s
inline outer call
conditional add
branched
real 0m0.695s
user 0m0.695s
sys 0m0.000s
builtin
real 0m0.695s
user 0m0.695s
sys 0m0.000s
branch
branched
real 0m0.390s
user 0m0.387s
sys 0m0.003s
builtin
real 0m0.413s
user 0m0.412s
sys 0m0.000s
sum
branched
real 0m0.695s
user 0m0.702s
sys 0m0.000s
builtin
real 0m0.696s
user 0m0.697s
sys 0m0.000s
inline inner call
conditional add
branched
real 0m0.695s
user 0m0.696s
sys 0m0.000s
builtin
real 0m0.696s
user 0m0.692s
sys 0m0.003s
branch
branched
real 0m0.388s
user 0m0.388s
sys 0m0.000s
builtin
real 0m0.388s
user 0m0.388s
sys 0m0.000s
sum
branched
real 0m0.695s
user 0m0.695s
sys 0m0.000s
builtin
real 0m0.695s
user 0m0.695s
sys 0m0.000s
tigth loop
conditional add
branched
real 0m0.233s
user 0m0.232s
sys 0m0.000s
builtin
real 0m0.232s
user 0m0.232s
sys 0m0.000s
branch
branched
real 0m0.080s
user 0m0.080s
sys 0m0.000s
builtin
real 0m0.161s
user 0m0.160s
sys 0m0.000s
sum
branched
real 0m0.232s
user 0m0.232s
sys 0m0.000s
builtin
real 0m0.310s
user 0m0.310s
sys 0m0.000s
next prev parent reply other threads:[~2015-07-24 8:32 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-20 18:39 [Bug rtl-optimization/64003] New: " dmalcolm at gcc dot gnu.org
2014-11-20 18:41 ` [Bug rtl-optimization/64003] " dmalcolm at gcc dot gnu.org
2014-11-20 18:54 ` dmalcolm at gcc dot gnu.org
2014-11-20 19:23 ` dmalcolm at gcc dot gnu.org
2014-11-20 19:27 ` dmalcolm at gcc dot gnu.org
2014-11-20 19:41 ` dmalcolm at gcc dot gnu.org
2014-11-21 19:04 ` [Bug target/64003] " dmalcolm at gcc dot gnu.org
2014-12-02 2:20 ` dmalcolm at gcc dot gnu.org
2014-12-02 15:40 ` dmalcolm at gcc dot gnu.org
2014-12-02 15:48 ` dmalcolm at gcc dot gnu.org
2014-12-02 15:54 ` dmalcolm at gcc dot gnu.org
2014-12-02 16:08 ` dmalcolm at gcc dot gnu.org
2014-12-02 16:13 ` dmalcolm at gcc dot gnu.org
2014-12-04 9:24 ` amylaar at gcc dot gnu.org
2014-12-04 18:43 ` law at redhat dot com
2014-12-04 18:44 ` law at redhat dot com
2014-12-04 19:19 ` amylaar at gcc dot gnu.org
2014-12-04 19:38 ` enkovich.gnu at gmail dot com
2014-12-04 19:45 ` amylaar at gcc dot gnu.org
2014-12-04 19:51 ` law at redhat dot com
2014-12-04 19:54 ` law at redhat dot com
2014-12-05 10:07 ` enkovich.gnu at gmail dot com
2014-12-05 10:08 ` enkovich.gnu at gmail dot com
2014-12-05 10:38 ` ubizjak at gmail dot com
2014-12-05 10:50 ` ubizjak at gmail dot com
2014-12-05 14:19 ` rsandifo at gcc dot gnu.org
2014-12-05 15:01 ` enkovich.gnu at gmail dot com
2014-12-05 16:01 ` ienkovich at gcc dot gnu.org
2015-04-16 14:08 ` ienkovich at gcc dot gnu.org
2015-07-24 8:32 ` ubizjak at gmail dot com [this message]
2015-07-24 8:36 ` ubizjak at gmail dot com
2015-07-24 16:26 ` uros at gcc dot gnu.org
2015-07-24 16:31 ` ubizjak at gmail dot com
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=bug-64003-4-3aH7qEOXmv@http.gcc.gnu.org/bugzilla/ \
--to=gcc-bugzilla@gcc.gnu.org \
--cc=gcc-bugs@gcc.gnu.org \
/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).