On Tue, Jan 05, 2016 at 01:43:30PM +, Suzuki K. Poulose wrote:
> On 05/01/16 13:37, Peter Zijlstra wrote:
> >On Mon, Dec 21, 2015 at 10:55:29AM +, 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 th
On 05/01/16 13:37, Peter Zijlstra wrote:
On Mon, Dec 21, 2015 at 10:55:29AM +, 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
On Mon, Dec 21, 2015 at 10:55:29AM +, 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 t
On Fri, Dec 18, 2015 at 12:47:51PM +0100, Peter Zijlstra wrote:
> On Fri, Dec 18, 2015 at 10:58:17AM +, Suzuki K. Poulose wrote:
>
> > We have a global Enable/Disable for CCI PMU and thats what we use
> > currently. To be able to reprogram the counters with the event period
> > (we program the
On Fri, Dec 18, 2015 at 10:58:17AM +, Suzuki K. Poulose wrote:
> We have a global Enable/Disable for CCI PMU and thats what we use
> currently. To be able to reprogram the counters with the event period
> (we program the counter with a specific count in pmu::start() and at
> overflow irq handl
On 18/12/15 10:42, Peter Zijlstra wrote:
On Fri, Dec 18, 2015 at 10:28:23AM +, Suzuki K. Poulose wrote:
On 17/12/15 18:42, Peter Zijlstra wrote:
I thought about that, but was not sure if pmu->stop() is guaranteed to be
called on all the events scheduled on the PMU when we pmu::pmu_disable().
On Fri, Dec 18, 2015 at 10:28:23AM +, Suzuki K. Poulose wrote:
> On 17/12/15 18:42, Peter Zijlstra wrote:
> >The above doesn't look like it has a failure case, in which case you can
> >achieve the same simpler, using pmu::pmu_{dis,en}able().
> >
>
> I thought about that, but was not sure if p
On 17/12/15 18:42, Peter Zijlstra wrote:
On Thu, Dec 17, 2015 at 05:49:12PM +, Suzuki K. Poulose wrote:
We keep track of only the 'ADD' transactions. While we are in a
transaction, we keep track of the indices allocated for the events
and delay the following operations until the transaction
On Thu, Dec 17, 2015 at 05:49:12PM +, Suzuki K. Poulose wrote:
> This patch adds the transaction hooks for CCI PMU, which can be
> later exploited to amortise the cost of writing the counters for
> CCI-500 PMU.
>
> We keep track of only the 'ADD' transactions. While we are in a
> transaction,
This patch adds the transaction hooks for CCI PMU, which can be
later exploited to amortise the cost of writing the counters for
CCI-500 PMU.
We keep track of only the 'ADD' transactions. While we are in a
transaction, we keep track of the indices allocated for the events
and delay the following o
10 matches
Mail list logo
