From: Peter Zijlstra <peterz@infradead.org>
To: Paul Mackerras <paulus@samba.org>
Cc: Lin Ming <ming.m.lin@intel.com>, Ingo Molnar <mingo@elte.hu>,
Andi Kleen <andi@firstfloor.org>,
Stephane Eranian <eranian@google.com>,
Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
linux-kernel <linux-kernel@vger.kernel.org>,
Anton Blanchard <anton@samba.org>
Subject: Re: [PATCH 1/4] perf: Add memory load/store events generic code
Date: Wed, 06 Jul 2011 15:58:38 +0200 [thread overview]
Message-ID: <1309960718.3282.289.camel@twins> (raw)
In-Reply-To: <20110705230217.GA9584@bloggs.ozlabs.ibm.com>
On Wed, 2011-07-06 at 09:02 +1000, Paul Mackerras wrote:
> On Tue, Jul 05, 2011 at 02:03:38PM +0200, Peter Zijlstra wrote:
> > On Mon, 2011-07-04 at 10:44 +0200, Peter Zijlstra wrote:
> > > Anton, Paulus, IIRC PowerPC had some sort of Data-Source indication,
> > > would you have some docs available on the PowerPC PMU?
> >
> > Going through
> > http://www.power.org/resources/downloads/PowerISA_V2.06B_V2_PUBLIC.pdf
> >
> > Book III-S, Appendix B
> >
> > I can only find the SDAR thing (which I assume is what PERF_SAMPLE_DATA
> > uses) but no mention of extra bits describing where the data was sourced
> > from. For some reason I had the impression PPC64 had the capability to
> > tell if a load/store was from/to L1/2/3/DRAM etc.
> >
> > Now since the above document is in fact not an exhaustive spec of a
> > particular chip but more an outline of what a regular ppc64 chip should
> > have, with lots of room for implementation specific extensions it
> > doesn't say much at all.
> >
> > So do you know of such a feature for PPC64 and if so, where's the
> > docs? :-)
>
> Unfortunately the P7 PMU documentation is not available publicly yet. :(
Are the P6/P6+ PMU docs? That at least would give me something to look
at.
> There are events that can be used to count how many times data or
> instructions get loaded from different places in the memory
> subsystem. There are 15 separate DATA_FROM_xxx events, for instance,
> that count things like "number of times data was loaded from L2 or L3
> cache on another chip and the cache line was in shared state".
> They're great if you want fine detail on memory traffic but perhaps
> not so good if you want a broad overview (there are separate events
> for L1 and L2 accesses and misses though).
>
> I've attached a table of P7 PMU events. Look for the PM_DATA_FROM_xxx
> and PM_INST_FROM_xxx events.
Ok, so those are regular events and perf covers that capability.
The thing we're talking about is Intel PEBS Load Latency/Precise Store
and AMD IBS where together with a mem op retired event (mem loads
retired for Load-Latency, mem stores retired for Precise Store) provides
an additional field describing where the load/store was sourced from.
Such additional data would require the addition of a PERF_SAMPLE_SOURCE
field or similar, for some reason or other I was under the impression
some of the PPC chips had something similar. But if not, it saves us
having to worry about that.
next prev parent reply other threads:[~2011-07-06 13:59 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-04 8:02 [PATCH 0/4] perf: memory load/store events generalization Lin Ming
2011-07-04 8:02 ` [PATCH 1/4] perf: Add memory load/store events generic code Lin Ming
2011-07-04 8:33 ` Peter Zijlstra
2011-07-04 8:44 ` Peter Zijlstra
2011-07-05 12:03 ` Peter Zijlstra
2011-07-05 23:02 ` Paul Mackerras
2011-07-06 13:58 ` Peter Zijlstra [this message]
2011-07-08 7:18 ` Anton Blanchard
2011-07-08 15:18 ` Peter Zijlstra
2011-08-08 11:57 ` Peter Zijlstra
2011-08-08 11:59 ` Peter Zijlstra
2011-07-04 22:01 ` Andi Kleen
2011-07-05 8:43 ` Peter Zijlstra
2011-07-04 11:08 ` Peter Zijlstra
2011-07-04 11:16 ` Peter Zijlstra
2011-07-04 21:52 ` Andi Kleen
2011-07-05 11:54 ` Lin Ming
2011-07-05 14:17 ` Peter Zijlstra
2011-07-06 5:53 ` Lin Ming
2011-07-06 13:51 ` Peter Zijlstra
2011-07-07 2:01 ` Lin Ming
2011-07-04 8:02 ` [PATCH 2/4] perf, x86: Add Intel Nhm/Wsm/Snb load latency support Lin Ming
2011-07-05 13:17 ` Peter Zijlstra
2011-07-05 13:34 ` Lin Ming
2011-07-22 18:58 ` Stephane Eranian
2011-07-04 8:02 ` [PATCH 3/4] perf, x86: Add Intel SandyBridge pricise store support Lin Ming
2011-07-11 8:32 ` Peter Zijlstra
2011-07-11 8:57 ` Lin Ming
2011-07-11 8:52 ` Peter Zijlstra
2011-07-04 8:02 ` [PATCH 4/4] perf, tool: Add new command "perf mem" Lin Ming
2011-07-04 22:00 ` Andi Kleen
2011-07-05 1:35 ` Lin Ming
2011-07-22 18:55 ` [PATCH 0/4] perf: memory load/store events generalization Stephane Eranian
2011-07-22 21:01 ` Andi Kleen
2011-07-22 21:14 ` Stephane Eranian
2011-07-22 21:43 ` Andi Kleen
2011-07-22 21:59 ` Stephane Eranian
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=1309960718.3282.289.camel@twins \
--to=peterz@infradead.org \
--cc=acme@ghostprotocols.net \
--cc=andi@firstfloor.org \
--cc=anton@samba.org \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.m.lin@intel.com \
--cc=mingo@elte.hu \
--cc=paulus@samba.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 NNTP newsgroup(s).