Date: Fri, 12 Mar 2004 14:45:52 -0500 From: Jem Matzan <valour@thejemreport.com> To: freebsd-amd64@freebsd.org Subject: Re: Peer review of AMD64/FreeBSD article Message-ID: <40521370.5030806@thejemreport.com> In-Reply-To: <20040312181837.GD56805@funkthat.com> References: <4051A841.9020205@thejemreport.com> <20040312181837.GD56805@funkthat.com>
next in thread | previous in thread | raw e-mail | index | archive | help
John-Mark Gurney wrote: >Jem Matzan wrote this message on Fri, Mar 12, 2004 at 07:08 -0500: > > >>I've just finished writing this article comparing performance between an >>Athlon64 in 32-bit and 64-bit mode using FreeBSD: >> >>http://www.thejemreport.com/lab64/amd64vsi386.php >> >>(this is a temporary address which will later redirect to the published >>article) >> >> > >A comment on the article, you mention: >Curiously the Pentium4 times are impossible; according to the numbers for -j3 and -j4, it takes longer to execute the utility than it does to complete the entire process. This is either a bug in the time command (in relation to multithreading, perhaps), or something isn't reporting properly. > >You said that you enabled HyperThreading, and THIS is the reason for >the imposible times. Since w/ HT it appears as if there are two cpus >and two processes are running on each of these CPU's, you end up with >a user time that can be 2x real time. > >Hope this helps. > > > Thanks -- I'll change the article to reflect that. I was hoping someone would shed some light on why the user time was off like that... -Jem
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?40521370.5030806>