Date: Sun, 28 Jul 1996 08:30:30 -0700 (PDT) From: "Jonathan M. Bresler" <jmb> To: rsnow@lgc.com (Rob Snow) Cc: freebsd-chat@freebsd.org Subject: Re: PPro flops numbers out there? Message-ID: <199607281530.IAA26767@freefall.freebsd.org> In-Reply-To: <Pine.SGI.3.93.960728031102.5501A-100000@dympna> from "Rob Snow" at Jul 28, 96 03:12:25 am
next in thread | previous in thread | raw e-mail | index | archive | help
Rob Snow wrote: > > > Hmm, does anyone have some flops (flops 2.0) numbers out there for a > PPro-200? > > I'm getting about 25 or so. This seems low. if flops are a single number attempt to chacaterize computation speed (barf) no, i dont. if you want an excellent computation benchmark that provides a graph of computation vs data set size, i have results for a PPro 150 running single user 2.1.0 (computer by dell, dont remember the chipset ;( all the details make a significant difference once the data set is larger that the processors on-chip/in-package cache. at that point you start to use the memory/cache system, etc...) its called Hint. it will also provide a single number result. written by people at ames lab to measure the speed of their supercomputers. results are available for a variety of machines (from a Intel Paragon 1840 node (single number result: 633.21) to a DEC 2100 (0.33)) the url is http://www.scl.ameslab.gov/scl/HINT/HINT.html the "Interactive graphing of HINT" url on that page is broken. use the one below instead. http://gemini.scl.ameslab.gov:8080/cgi-bin/master.cgi jmb ps. arghhhh...the results are at work! will mail them separately. -- Jonathan M. Bresler FreeBSD Postmaster jmb@FreeBSD.ORG FreeBSD--4.4BSD Unix for PC clones, source included. http://www.freebsd.org/ PGP 2.6.2 Fingerprint: 31 57 41 56 06 C1 40 13 C5 1C E3 E5 DC 62 0E FB
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199607281530.IAA26767>