Date: Wed, 21 Sep 2011 09:27:33 +0800 From: Adrian Chadd <adrian@freebsd.org> To: Anton Yuzhaninov <citrin@citrin.ru> Cc: freebsd-performance@freebsd.org Subject: Re: hwpmc overflow Message-ID: <CAJ-Vmo=m079Dko-erfSdWZaX6nqjxrTVt1U8P0kOK27g5kD8Bw@mail.gmail.com> In-Reply-To: <j5asv4$p7e$1@dough.gmane.org> References: <j5ae29$e6g$1@dough.gmane.org> <j5asv4$p7e$1@dough.gmane.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Is this an AMD class CPU? The way the counters work on some platforms is that they count _up_ to an overflow value, trigger the overflow interrupt, and PMC then is supposed to calculate what the original value was. It sounds like maybe that isn't working correctly for a certain class of counters? Adrian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-Vmo=m079Dko-erfSdWZaX6nqjxrTVt1U8P0kOK27g5kD8Bw>