From: Andi Kleen <ak@suse.de>
To: Bernd Schmidt <bernds_cb1@t-online.de>
Cc: Andi Kleen <ak@suse.de>, Nicholas Miell <nmiell@comcast.net>,
Stephane Eranian <eranian@hpl.hp.com>,
Ray Bryant <raybry@mpdtxmail.amd.com>,
discuss@x86-64.org, linux-kernel@vger.kernel.org,
perfctr-devel@lists.sourceforge.net
Subject: Re: [discuss] Re: [Perfctr-devel] Re: Enabling RDPMC in user space by default
Date: Wed, 30 Nov 2005 00:46:17 +0100 [thread overview]
Message-ID: <20051129234617.GY19515@wotan.suse.de> (raw)
In-Reply-To: <438CE416.3060707@t-online.de>
> I happen to have an old program which uses RDTSC frequently for timing
> purposes. That seemed like a good idea at the time, but I guess it
> should be updated. The question is, what replacement is there? I don't
> want to have to use a syscall every 50 instructions or so. Feel free to
> laugh, but suggesting a workable replacement might be more helpful.
Well, you're asking me to write all the points from the documentation
in advance. Not tonight (or look up the full thread in the l-k archives,
I think I covered most)
But right now gettimeofday or clock_gettime(CLOCK_MONOTONIC) is
probably your best option. It tries to be reasonable fast depending
on hardware capabilities (and when you measure on P4
even basic RDTSC is quite slow). At least on x86-64 gettimeofday
isn't a real system call, but actually often stays in ring 3.
If you want to measure instructions in cycles in the future you can probably
use RDPMC 0, but that's not implemented yet. It won't be a replacement
for a timer for other purposes.
-Andi
next prev parent reply other threads:[~2005-11-29 23:46 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-11-29 15:15 Andi Kleen
2005-11-29 16:04 ` Mikael Pettersson
2005-11-29 16:17 ` Andi Kleen
2005-11-29 16:56 ` Ray Bryant
2005-11-29 16:15 ` Andi Kleen
2005-11-29 18:09 ` [Perfctr-devel] " Stephane Eranian
2005-11-29 18:13 ` Andi Kleen
2005-11-29 18:29 ` John Reiser
2005-11-29 18:38 ` Andi Kleen
2005-11-29 19:05 ` Lee Revell
2005-11-29 21:43 ` Nicholas Miell
2005-11-29 21:52 ` Andi Kleen
2005-11-29 22:19 ` Stephane Eranian
2005-11-29 22:51 ` [discuss] " Andi Kleen
2005-11-30 16:01 ` Stephane Eranian
2005-11-30 16:23 ` Andi Kleen
2005-12-01 23:41 ` Stephane Eranian
2005-12-02 0:07 ` Andi Kleen
2005-12-02 7:09 ` Stephane Eranian
2005-12-02 11:36 ` Andi Kleen
2005-11-29 22:33 ` Nicholas Miell
2005-11-29 22:43 ` Andi Kleen
2005-11-29 23:02 ` Nicholas Miell
2005-11-29 23:17 ` Andi Kleen
2005-11-29 23:29 ` Nicholas Miell
2005-11-29 23:39 ` Andi Kleen
2005-11-29 23:56 ` David Gibson
2005-11-30 0:34 ` Andi Kleen
2005-11-30 0:52 ` David Gibson
2005-11-30 1:04 ` [discuss] " Andi Kleen
2005-11-30 0:50 ` Ray Bryant
2005-11-30 0:38 ` Andi Kleen
2005-11-30 7:38 ` Stephane Eranian
2005-11-30 8:22 ` Nicholas Miell
2005-11-30 15:48 ` Stephane Eranian
2005-11-29 23:07 ` David Gibson
2005-11-29 23:18 ` [discuss] " Andi Kleen
2005-11-29 23:28 ` Bernd Schmidt
2005-11-29 23:46 ` Andi Kleen [this message]
2005-11-30 2:39 ` Zwane Mwaikambo
2005-11-30 3:38 ` Andi Kleen
2005-12-01 4:08 ` Zwane Mwaikambo
2005-12-01 13:05 ` Andi Kleen
2005-12-01 17:01 ` Zwane Mwaikambo
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=20051129234617.GY19515@wotan.suse.de \
--to=ak@suse.de \
--cc=bernds_cb1@t-online.de \
--cc=discuss@x86-64.org \
--cc=eranian@hpl.hp.com \
--cc=linux-kernel@vger.kernel.org \
--cc=nmiell@comcast.net \
--cc=perfctr-devel@lists.sourceforge.net \
--cc=raybry@mpdtxmail.amd.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
all inboxes | Powered by JetHome®