From mboxrd@z Thu Jan 1 00:00:00 1970 MIME-Version: 1.0 In-Reply-To: References: Date: Sat, 28 Mar 2009 07:11:58 +0800 Message-ID: <1d5d51400903271611q63646b09g2ff0b821ee898dc9@mail.gmail.com> From: Fernan Bolando To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [9fans] plan9 for calculations Topicbox-Message-UUID: cb4934fc-ead4-11e9-9d60-3106f5b1d025 On Sat, Mar 28, 2009 at 5:31 AM, Rudolf Sykora wrote: > Hello everybody, > > I noticed there are some thoughts about using plan9 on supercomputers. > For me supercomputers are usually used to do some heavy calculations. > And this leads me to a question. What software is then used for > programming these calculations? (I mean e.g. linear algebra, i.e. > matrix, calculations.) Where can one read about that? > > More, it also leads me to a (perhaps) simpler question. What is the > situations with ordinary machines? > > Untill now I have used several libraries in linux, all of them somehow > based on lapack. I used C language (c-lapack), python (numpy), and now > I do some programming in Fortran (Intel MKL). From my experience I > would say: writing programs in C is a nightmare (for me next to no-go > again), using python with numpy is a breeze, using Fortran (95) is > sort of fine. C and Fortran run faster than python, but the factor, > when I played with it, surprised me to be sth. like 3x (expecting a > worse result). > > Now I've been thinking, If I were to write sth. in plan9, what would > be the way to try? > Recently I heard about eigen2 library, which seems to be nice (high > performance, few dependencies), but for C++... > > Thank you for any suggestion > Ruda > > PS.: It could be that plan9, being more a os-research system than > anything else, is simply no suitable for such a use (there are no > plotting libraries, other utilities). Perhaps it's not a good idea at > all to try to use plan9 like that because it would be more work than > anything. Maybe using linux for such things with all its tools is just > ok. If you share this idea, just say it too, please. > > Its not supercomputer level, but I have a sparse matrix solver in my contrib. I use it along with haskell as simple replacement for octave. It is mostly a collection of scripts right I am hoping to consolidate it later as a single package. I also cannot give you a alot of example mainly because it will translate to an actual project I did for my day job although those were done on mathcad I did notice that for some plotting needs simply piping it plot command is adequate instead of bloating my tools with plot routines. fernan -- http://www.fernski.com