On Wed, Aug 23, 2017 at 05:51:38PM +0000, Rogozhkin, Dmitry V wrote:
> And there is another problem associated with the "perf stat -e <event>
> -a": since 8 events are initialized, I get metric values multiplied by
> 8. How I am supposed to fix that? I suspect that this is somehow related
> to cpumask attribute exposed by some other PMUs, for example uncore.
> They are doing something like:
>
> static cpumask_t uncore_cpu_mask;
>
> static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
>
> static struct attribute *uncore_pmu_attrs[] = {
> &dev_attr_cpumask.attr,
> NULL,
> };
>
> static struct attribute_group uncore_pmu_attr_group = {
> .attrs = uncore_pmu_attrs,
> };
>
> Should i915 follow this way as well?
Ah, so much for reading emails in parts, yes! that is what userspace
needs to know in order to DTRT.
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
