On Wed, Mar 08, 2006 at 03:15:16PM -0800, Russ Blaine wrote: > mechanism itself is also really convoluted
Sure, it's a Pentium 4 :) > clean, responsible API. You do raise a good point, though, that perhaps > on Pentium IV we could use PEBS underneath the current proposed APIs to > deliver richer data with less overhead than on processors where all we > have is the standard overflow interrupt. The reason I ask is that there's certain cases where it's really useful for low-level tuning of hand-crafted assembly. Often the impreciseness makes analysis difficult. Having said that, I agree it's not particularly important. regards john _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
