IRIX and Software

Hello

Have two SGI, Tezro quad and Fuel 700, i interconect the 2 Sgi by switch in fiber 1Gb, make array, the two machine found and view in aview app, i intention to use the 5 processor for make render in maya.

The problem is when i write in terminal
mpirun -a myarray -nt 5 maya or any-app

same result not work only run in my local macine, quit the app and report error

" could not run executable "

Any solution ..???

Applications have to be specifically written with the intention of using MPI at runtime. It doesn't just distribute any old program across a given set of machines.

I had never heard that Maya was built that way, but I'm not a Maya user so I might easily have missed something. What makes you think Maya was built to be used with MPI?

In Irix is possible run one App in one or more machine in parallel for render or intesive calc ?

Make cluster in array my two macine show 5Processor/12GB ram for make ??? for make any Job ???

In 2003 my mac xserver g5 and workstation g5 quad xgrid show one machine 15Ghz for any app.

If possible i don't understanding the Irix.

I buy sgi becouse 1990-96 i make animation 3D in Amiga, Imagine 3D and Lightwave but impossible buy one Sgi ( many money), today i relife my dream for make 3D in SGI.

Thanks
Marino

See "What does MPI: could not run executable mean?" at techpubs:

http://techpubs.sgi.com/library/dynaweb_docs/0620/SGI_Developer/books/MPT_MPI_PM/sgi_html/ch08.html#id5192535

tooR wrote: In 2003 my mac xserver g5 and workstation g5 quad xgrid show one machine 15Ghz for any app.

Sure, but did Xgrid let you decide one day to run Photoshop, or Microsoft Word, or SimCity across those machines without modification? Only if the author/company creating the app designed in Xgrid support, would something like that work. Or if you built your own app to use Xgrid. Or perhaps if you had something that involved lots of small command-line jobs, like compilation or batch rendering, where you could start the command line jobs via Xgrid's command line tools.

Generally speaking, you need something designed to run in a distributed manner. Even the most common examples that aren't, like building code with distcc - the compiler isn't specifically designed to be distributed, but the compilation controller ("distcc") definitely is.

Maya can probably spread back-end rendering jobs across multiple machines - again, I'm not a Maya user, but it seems likely. But MPI won't let you automatically parallelize and distribute the front-end GUI application at runtime.

smj wrote: Maya can probably spread back-end rendering jobs across multiple machines - again, I'm not a Maya user, but it seems likely. But MPI won't let you automatically parallelize and distribute the front-end GUI application at runtime.

I'm not a Maya user either but there's threads here ... hey guys ! look up ! FAQ, Search, Members, User Control Panel. It's the one that starts with an 'S'.

Anyhoo, the gist of the discussion in the past was that the renderer built in to Maya would use multiple processors up to four. (Not MPI, cpu's.) But in actual testing, performance maxed at about two. There may have been some limitations related to the license, also.

Distributed rendering is generally done by other applications, not Maya. That Search thing might shed some light on which ones, if any, use MPI. foetz could probably chime in here ...

hamei wrote: foetz could probably chime in here ...

why me?
but okay


local rendering:
the default maya renderer can use up to 8 cpus at once. assuming your machine has at least 8
however, unlike the powercaster/tracer from the various alias packages the maya default renderer's smp skills are limited. a number of preprocessing stages such as shadow maps e.g. make use of only one. one of the bigger disappointments when switching from poweranimator to maya.
for mental ray it depends on the license and maya version you have. e.g. v5 supported up to 8 without any special software or license. later versions got that cut down to 2. if you wanna use more you have to get an extra license and install the standalone stuff so if you have more than 2 cpus and wanna use mental ray stick to maya5

distributed/network rendering:
for the default renderer use the good old dispatcher for delegating jobs across multiple, networked machines. see the maya docs for details.
for mental ray it works as it always works with mental ray. see the maya docs for that, too

foetz wrote: why me?

Horse's mouth

Hello

ok, i read the manual maya for find info multi cpu by network, Thanks.

The array work, in aview show 2N5P12GB-Ram but run job in any app installed, alias 11, photoshop, illustrator, eclipse, matador, maya, poweranimator only work in localhost machine.
When i check the array by command ascheck have one error the second node not responding.

Very rare problem becouse one show fine and other check error.