On Wed, Nov 16, 2011 at 18:02, Kevin Hilman <khil...@ti.com> wrote: > Felipe Balbi <ba...@ti.com> writes: > >> From: Nishanth Menon <n...@ti.com> >> >> SmartReflex should be disabled while entering low power mode due to >> the following reasons: > [...] > > Nishanth, in the end, didn't you decide to drop this patch? >
Yes, I did eventually, once we implemented DVFS for GPU, Ducati, HSI, and other drivers, there was no real way to ensure sequence of suspend sequencing even after moving this to suspend_noirq. some of the other reasons: if I disabled Smartreflex and went to Nominal voltage on MPU, and say MPU was at "performance" mode of 1.5GHz or so, thermal scenarios got worse due on hot corner samples - these tend to have higher leakage and thermal characteristics tend to be more pronounced. The option of throttling frequency down while suspend was not really a good option in comparison to switching off smart reflex in the last possible moment - in pmxxx.c Regards, Nishanth Menon -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
