[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <875yu8njkz.fsf@mpe.ellerman.id.au>
Date: Fri, 08 Oct 2021 16:58:52 +1100
From: Michael Ellerman <mpe@...erman.id.au>
To: Segher Boessenkool <segher@...nel.crashing.org>,
"Paul A. Clarke" <pc@...ibm.com>
Cc: Kajol Jain <kjain@...ux.ibm.com>, maddy@...ux.vnet.ibm.com,
rnsastry@...ux.ibm.com, linuxppc-dev@...ts.ozlabs.org,
linux-kernel@...r.kernel.org, acme@...nel.org,
linux-perf-users@...r.kernel.org, atrajeev@...ux.vnet.ibm.com,
jolsa@...hat.com
Subject: Re: [PATCH] perf vendor events power10: Add metric events json file
for power10 platform
Segher Boessenkool <segher@...nel.crashing.org> writes:
> On Thu, Oct 07, 2021 at 08:47:50AM -0500, Paul A. Clarke wrote:
>> On Wed, Oct 06, 2021 at 12:32:48PM -0500, Paul A. Clarke wrote:
>> > > + {
>> > > + "BriefDescription": "Average cycles per instruction when the instruction finishes at dispatch",
>> >
>> > I'm not sure what that means.
>>
>> After doing a bit of research, I think it might be a bit more clear as:
>> "Average cycles per instruction when the NTF instruction finishes at dispatch"
>
> Is "next to finish" some defined and/or sensible term in this context?
> Or do you mean NTC here? Or what :-)
Yeah I am also more familiar with NTC.
But those descriptions originally come from a spreadsheet we're given,
and they do include NTF as an acronym.
eg. search for NTF in here:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/pmu-events/arch/powerpc/power9/metrics.json
>From the context it does presumably mean "next to finish".
cheers
Powered by blists - more mailing lists