[julia-users] Re: best way to run parallel julia in batch mode?

2014-09-02 Thread Travis Porco
thanks much. I have had to go down to 31 workers in some instances after all. On Saturday, August 30, 2014 5:08:18 AM UTC-7, Florian Oswald wrote: > > sorry correct my call to > > julia -p 32 exper.jl > myout.out > > (without the first < , not sure that makes a difference) > > On Saturday, 30 Aug

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-30 Thread Florian Oswald
sorry correct my call to julia -p 32 exper.jl > myout.out (without the first < , not sure that makes a difference) On Saturday, 30 August 2014 12:58:57 UTC+1, Florian Oswald wrote: > > @require should work for what you want. i usually run batch jobs like this > > julia -p 32 < exper.jl > myout.o

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-30 Thread Florian Oswald
@require should work for what you want. i usually run batch jobs like this julia -p 32 < exper.jl > myout.out maybe give it a try? also, do you have 32 CPUs? not sure how stable this is if you use plenty more processes than cores. here is a working example for a large cluster: https://github.co

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Travis Porco
julia> versioninfo() Julia Version 0.3.1-pre+405 Commit 444fafe* (2014-08-27 20:11 UTC) Platform Info: System: Linux (x86_64-linux-gnu) CPU: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz WORD_SIZE: 64 BLAS: libopenblas (USE64BITINT DYNAMIC_ARCH NO_AFFINITY Sandybridge) LAPACK: libopenblas LI

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Travis Porco
Thanks, it works quite well. All are on the same machine and read the same filesystem: Version 0.3.1-pre+405 (2014-08-27 20:11 UTC) Commit 444fafe* (2 days old master) x86_64-linux-gnu julia> @everywhere begin include("ee.jl") end julia> wsum = @parallel (+) for i

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Jake Bolewski
The above example should only work if all nodes have access to the same filesystem. Is this the case? On Friday, August 29, 2014 9:23:31 PM UTC-4, Jake Bolewski wrote: > > Does the following work? > > julia> @everywhere begin >include("ee.jl") >end > > julia> wsum = @parallel (+)

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Jake Bolewski
Does the following work? julia> @everywhere begin include("ee.jl") end julia> wsum = @parallel (+) for ii in 1:16384 sq(ii) end It also helps to give us your versioninfo(). On Friday, August 29, 2014 9:11:52 PM UTC-4, Travis Porco wrote: > > Hi, interactive works

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Travis Porco
Hi, interactive works fine with 32, script fails for smaller numbers. Julia Version 0.3.1-pre+405 (2014-08-27 20:11 UTC) Commit 444fafe* (2 days old master), Ubuntu 12.04.3 LTS (GNU/Linux 3.2.0-54-virtual x86_64). Thanks. On Friday, August 29, 2014 10:15:54 AM UTC-7, Travis Porco wrote: > > H

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Jake Bolewski
Your example works fine for me: julia-av/base [jcb/arrayview●] » julia -p 10 exp.jl wsum => 1466149724160 Does it still fail with a smaller processor count. Does the interactive version work? julia-av/base [jcb/arrayview●] » julia _ _ _ _(_)_ | A fresh approach to te

[julia-users] Re: best way to run parallel julia in batch mode?

2014-08-29 Thread Travis Porco
More detail: Given file exper.jl being require("ee.jl") wsum = @parallel (+) for ii in 1:16384 sq(ii) end and ee.jl being function sq(n) n*n end terminal session gives julia> include("exper.jl") 1466149724160 but: nohup ../julia/julia -p 32 < exper.jl & yields a cascade of these: except