Path: utzoo!attcan!utgpu!news-server.csri.toronto.edu!rutgers!usc!snorkelwacker.mit.edu!bloom-beacon!eru!hagbard!sunic!ugle.unit.no!nuug!ulrik!ulrik!oles From: oles@kelvin.uio.no (Ole Swang) Newsgroups: comp.benchmarks Subject: Re: Ole Swang's benchmark: Sum of Harmonic Series Message-ID: Date: 19 Dec 90 10:11:11 GMT References: <44125@mips.mips.COM> <1990Dec19.004003.20667@dirtydog.ima.isc.com> Sender: news@ulrik.uio.no (USENET News System) Organization: University of Oslo, Norway Lines: 76 In-Reply-To: suitti@ima.isc.com's message of 19 Dec 90 00:40:03 GMT Organization: Interactive Systems, Cambridge, MA 02138-5302 In article <20667@dirtydog.ima.isc.com> suitti@ima.isc.com (Stephen Uitti) writes: < different translations into C deleted > > >I'm not sure why Mark used such an odd float format. I prefer >the output "16.695311, 0" to " r = 1.6695311e+01, i = 0". >Does this match the FORTRAN output? That is system dependent. The statement WRITE(*,*) picks a default format. (on most systems, it _does_ match) < stuff about do-while and efficiency deleted > >It is interesting that you want to add up the small stuff first. >That coding happens to be quicker on most machines, too. Not on the Cray! The time went up to 0.36 secs (that's 24 percent more) when using negative increment. Explanation, anyone? The answer differed in the tenth digit. Here is another update, containing Stephen's additions and a couple that was mailed to me (thanks!) Cray X/MP 216 0.29 MIPS RC6280 3.3 HP9000/870 6.7 (new) MIPS RC3230 Magnum 8.1 Convex C 120 8.7 Sun SPARCstation II 10.0 Sun 4/75 10.1 (new) DECstation 5000/200 10.5 DECsystem 5400 13.1 HP9000/845 13.7 (new) DECstation 3100 15.9 (new) Sun SPARCstation 1+ 33.0 VAX 6330/VMS5.3 FPA 41.9 Compaq 486/25 44.4 HP9000/825 53.9 VAX 8650/VMS5.3 FPA 55.3 Compaq 386/33 71.7 VAX 8600/VMS5.2 FPA 77.1 Compaq 386/25 99.8 Sun 3/60 (m68881) 105.6 VAX 11/780 614.1 < comments on reliability deleted > >Cost effectiveness is something that hasn't been discussed much. > >A 386/25 system will be obsolete in 3 years, and costs about >$4,500 dollars for that time for a system capably of running this >sort of application. That's $1,500 per year. It performs 6.15 >times better than the VAX 780. This gives us a rough cost >effectiveness of $240/VAX MIP. > $1500 / (614.1 / 99.8) > >Is anyone brave enough to figure this out for a Cray? ... a PC/XT? Without having investigated, I'm quite sure that a high-end Cray, for the time being, is the worst computer in the world when it comes to cost-effectiveness. On the other hand, you would not like to use a workstation for a well vectorizing, iterative algorithm that reads a few hundred Mb from disk for each iteration. (this is the kind of algorithm that eats most of the cycles in a typical quantum chemical calculation, which is what I use computers for (when I'm not reading news)) >Stephen. >suitti@ima.isc.com -- ----------------------------------------------------------------------- Ole Swang assistant lecturer, Dept. of Chemistry, U .of Oslo -----------------------------------------------------------------------