From: Vineet Gupta <Vineet.Gupta1@synopsys.com>
To: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>,
"mingo@redhat.com" <mingo@redhat.com>,
"ak@linux.intel.com" <ak@linux.intel.com>,
"Michael Ellerman" <mpe@ellerman.id.au>,
Jiri Olsa <jolsa@redhat.com>,
"Arnaldo Carvalho de Melo" <acme@kernel.org>,
Paul Mackerras <paulus@samba.org>
Cc: "linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [RFC][PATCH 0/4] perf: Enable symbolic event names
Date: Sat, 2 May 2015 07:02:11 +0000 [thread overview]
Message-ID: <C2D7FE5348E1B147BCA15975FBA230756659D931@IN01WEMBXB.internal.synopsys.com> (raw)
In-Reply-To: 1430463941-26109-1-git-send-email-sukadev@linux.vnet.ibm.com
On Friday 01 May 2015 12:35 PM, Sukadev Bhattiprolu wrote:=0A=
> Implement ability to specify Power PMU events by their symbolic event=0A=
> names rather than raw codes. This approach pulls tables of the Power7=0A=
> and Power8 PMU events into the perf source tree and uses these tables=0A=
> to create aliases for the PMU events. With these aliases users can run:=
=0A=
> =0A=
> perf stat -e PM_1PLUS_PPC_CMPL:ku sleep 1=0A=
> or=0A=
> perf stat -e cpu/PM_VSU_SINGLE/ sleep 1=0A=
> =0A=
> This is an early POC patchset based on discussions with Jiri Olsa,=0A=
> Michael Ellerman and Ingo Molnar. Lightly tested on Power7 and Power8.=0A=
> =0A=
> Can other architectures can implement arch_get_events_table() and similar=
ly =0A=
> use symoblic event names?=0A=
=0A=
=0A=
Yes, ARC can certainly use this infrastructure. Our hardware conditions are=
=0A=
actually 1-8 char strings. So using raw events requires me to first convert=
the=0A=
string to ASCII.=0A=
=0A=
> =0A=
> I am also assuming that if the header files like power8-events.h are=0A=
> easily readable, we don't need the JSON files anymore?=0A=
> =0A=
> TODO:=0A=
> - Maybe translate event names to lower-case?=0A=
> - Allow perf to process event descriptions (need Andi Kleen's patch)=0A=
> =0A=
> =0A=
> Sukadev Bhattiprolu (4):=0A=
> perf: Create a table of Power7 PMU events=0A=
> perf: Create a table of Power8 PMU events=0A=
> perf/powerpc: Move mfspr and friends to header file=0A=
> perf: Create aliases for Power PMU events=0A=
> =0A=
> tools/perf/arch/powerpc/util/Build | 2 +-=0A=
> tools/perf/arch/powerpc/util/header.c | 9 +-=0A=
> tools/perf/arch/powerpc/util/header.h | 9 +=0A=
> tools/perf/arch/powerpc/util/pmu-events.c | 52 +=0A=
> tools/perf/arch/powerpc/util/pmu-events.h | 17 +=0A=
> tools/perf/arch/powerpc/util/power7-events.h | 3315 +++++++++++++=0A=
> tools/perf/arch/powerpc/util/power8-events.h | 6408 ++++++++++++++++++++=
++++++=0A=
> tools/perf/util/pmu.c | 77 +=0A=
> tools/perf/util/pmu.h | 10 +=0A=
> 9 files changed, 9890 insertions(+), 9 deletions(-)=0A=
> create mode 100644 tools/perf/arch/powerpc/util/header.h=0A=
> create mode 100644 tools/perf/arch/powerpc/util/pmu-events.c=0A=
> create mode 100644 tools/perf/arch/powerpc/util/pmu-events.h=0A=
> create mode 100644 tools/perf/arch/powerpc/util/power7-events.h=0A=
> create mode 100644 tools/perf/arch/powerpc/util/power8-events.h=0A=
> =0A=
=0A=
prev parent reply other threads:[~2015-05-02 7:02 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-01 7:05 [RFC][PATCH 0/4] perf: Enable symbolic event names Sukadev Bhattiprolu
2015-05-01 7:05 ` [RFC][PATCH 1/4] perf: Create a table of Power7 PMU events Sukadev Bhattiprolu
2015-05-01 7:05 ` [RFC][PATCH 2/4] perf: Create a table of Power8 " Sukadev Bhattiprolu
2015-05-01 7:05 ` [RFC][PATCH 3/4] perf/powerpc: Move mfspr and friends to header file Sukadev Bhattiprolu
2015-05-01 7:05 ` [RFC][PATCH 4/4] perf: Create aliases for PMU events Sukadev Bhattiprolu
2015-05-02 7:04 ` Vineet Gupta
2015-05-02 15:38 ` Jiri Olsa
2015-05-04 11:44 ` Andi Kleen
2015-05-02 7:02 ` Vineet Gupta [this message]
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=C2D7FE5348E1B147BCA15975FBA230756659D931@IN01WEMBXB.internal.synopsys.com \
--to=vineet.gupta1@synopsys.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.org \
--cc=sukadev@linux.vnet.ibm.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 NNTP newsgroup(s).