Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1301530
| From | Peter Zijlstra <peterz@infradead.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions |
| Date | 2016-01-05 14:40 +0100 |
| Message-ID | <qNA0a-3p1-1@gated-at.bofh.it> (permalink) |
| References | (3 earlier) <qH0sq-4lf-27@gated-at.bofh.it> <qH0LM-4tM-9@gated-at.bofh.it> <qH0Vs-4xe-9@gated-at.bofh.it> <qH1HP-55K-13@gated-at.bofh.it> <qNA0a-3p1-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Mon, Dec 21, 2015 at 10:55:29AM +0000, Suzuki K. Poulose wrote: > Thanks for that hint. Here is what I cam up with. We don't reschedule > the events, all we need to do is group the writes to the counters. Hence > we could as well add a flag for those events which need programming > and perform the write in pmu::pmu_enable(). I'm still somewhat confused.. > Grouping the writes to counters can ammortise the cost of the operation > on PMUs where it is expensive (e.g, CCI-500). This rationale makes me think you want to reduce the number of counter writes, not batch them per-se. So why are you unconditionally writing all counters, instead of only those that changed? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread
Re: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions Peter Zijlstra <peterz@infradead.org> - 2016-01-05 14:40 +0100
Re: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions "Suzuki K. Poulose" <Suzuki.Poulose@arm.com> - 2016-01-05 14:50 +0100
Re: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions Peter Zijlstra <peterz@infradead.org> - 2016-01-05 16:00 +0100
csiph-web