On Jun 09, 09 13:57:45 +0200, Rafał Miłecki wrote:
First of all, why do we use DynamicClockGating only for (rhdPtr->ChipSet < RHD_R600)? Is this enabled by default on everything newer than R600?
Apparently we just don't know what this is doing on R6xx and up. If you want to experiment here, be my guest! I'd love to change this to something more reasonable for R6xx as well, but we need more and especially consistent tests including measuring used power for that.
How does DynamicClockGating work? Does GPU knows itself all (unused) hardware blocks than he can stop clocking?
Good question. No idea.
What actually is EnableASIC_StaticPwrMgt? Is this something we need to enable before using DynamicClockGating? If so, what other AtomBIOS commands depend on EnableASIC_StaticPwrMgt?
Good question. Again, no idea. This code is basically ported from radeon. Alex implemented it there, I assume by asking bios guys what to do to reduce power consumption.
Could someone explain shortly other AtomBIOS commands like: ASIC_StaticPwrMgtStatusChange, DynamicMemorySettings, MemoryTraining
Memory training is necessary for DDR5 memory only. And AFAIK it's done
automatically.
Matthias
--
Matthias Hopf