On Mon, 10 Oct 2011, Jean Pihet wrote: > On Fri, Oct 7, 2011 at 6:17 AM, Paul Walmsley <paul@xxxxxxxxx> wrote: > > On Wed, 21 Sep 2011, jean.pihet@xxxxxxxxxxxxxx wrote: > > > >> From: Jean Pihet <j-pihet@xxxxxx> > >> > >> Figures are added to the power domains structs for RET and OFF modes. > >> > >> Note: the latency figures for MPU, PER, CORE, NEON have been obtained > >> from actual measurements. > >> The latency figures for the other power domains are preliminary and > >> shall be added. > >> > >> Cf. http://www.omappedia.org/wiki/Power_Management_Device_Latencies_Measurement > >> for a detailed explanation on where are the numbers magically coming from. > >> > >> Tested on OMAP3 Beagleboard in RET/OFF using wake-up latency constraints > >> on MPU, CORE and PER. > > > > Do the CSWR measurements include the time for the PMIC to scale the > > voltage, or do they just represent the time to enter and exit clock stop > > (presumably with DPLL idling)? > > As described at [1] the measurements have not been performed with > sys_offmode and sys_clkreq signals toggling correctly, because of the > lack of support for it in the kernel. > However the results are including a correction for the sys_offmode > transition time (11.5ms), but no correction for the sys_clkreq signal > (which should be 1ms for sysclk on, 2.5ms for sysclk off). > > [1] http://www.omappedia.org/wiki/Power_Management_Device_Latencies_Measurement#cpuidle_results OK. sys_offmode only applies to OFF mode. Voltage scaling can also occur during RETENTION and INACTIVE ("sleep"). So were these results with retention and voltage scaling disabled? - Paul _______________________________________________ linux-pm mailing list linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/linux-pm
