Re: instruction cache throttling
On Tuesday 17 May 2005 23:39, John Steele Scott wrote:
> datasheet), then ICTC is only going to reduce power consumption for loads
> which will be using 100% of CPU at high speed. But this application is not
> particularly useful for a desktop machine.
Speaking of this... kernel scheduling folks seem to spend a lot of effort
trying to work out how best to figure out what an application needs to do,
and then how best to schedule that. Has anyone ever thought of adding a new
kernel API so applications can actually TELL the kernel what way they're
about to behave? Wouldn't that be a lot simpler and more reliable? I mean,
you could still assume a default workload for apps that haven't added those
few extra lines of code to optimise for Linux.
--
Lee.
Please send replies to the list, not to my email address.
Reply to: