I tried with the latest 0.3.3 release and with 0.4.0-dev+1061 version, but
both are giving errors.
As Amit has already created a similar issue, should I still open another
issue ?
Regards,
Kapil Agarwal
On Mon, Nov 24, 2014 at 5:23 AM, Tim Holy wrote:
> That error message sequence reminds
DArray
Here is the code as well
https://github.com/kapiliitr/JuliaBenchmarks/blob/master/ptrans.jl
Regards,
Kapil Agarwal
On Sun, Nov 23, 2014 at 11:22 PM, Viral Shah wrote:
> Are you using SharedArray or DArray?
>
> -viral
>
>
> On Monday, November 24, 2014 9:18:08 AM UTC+5
I don't think I am using that much memory. The following is my top result
PID USER PR NI VIRT RES SHR S %CPU %MEMTIME+ COMMAND
16290 kagarwal 20 0 1127m 100m 10m R 99.7 0.4 1:41.06 ptrans.jl
Regards,
Kapil Agarwal
On Sun, Nov 23, 2014 at 11:03 PM, Amit Murthy wrote:
elements and around 50-200 worker processes.
I have a machine with 24 cores and around 24 GB memory, so could this be a
problem with my system or is there a limit to how many workers Julia can
launch and allocate memory ?
Thanks
Kapil
Okay, one mistake I made was to specify [1:6] in the arguments when I
should have done [2:7] as worker threads are indexed from 2. But, I am yet
to figure how to assign worker ids in a horizontal manner.
ᐧ
Regards,
Kapil Agarwal
On Thu, Nov 20, 2014 at 6:00 PM, Kapil Agarwal wrote:
> Hi
&g
Hi
I am facing a similar problem, so I am not starting a new thread.
julia> addprocs(6);
julia> b=rand(6,6);
julia> c=distribute(b,[1:6],(2,3))
#using the distribute function as mentioned in this thread
This does not work as expected. Firstly, the matrix is distributed among
the master process
Hi
I am unable to figure out what should I pass as input parameters to the
gemm! function. The function declaration asks for function BlasChar,
StridedVecOrMat. StridedMatrix. Are they same as a normal Char and Array?
--
Kapil
Solved it I think
size=500;
a = fill(1.0,size);
b = fill(2.0,size);
c = fill(0.0,size);
if isdefined(:PARALLEL)
a = distribute(a);
b = distribute(b);
c = distribute(c);
end
ᐧ
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 2:05 PM, Kapil
);
end
Now, when I try to access the arrays, there is lot of overhead.
How can this be fixed ?
ᐧ
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 1:52 PM, Stefan Karpinski
wrote:
> On Sat, Nov 1, 2014 at 1:45 PM, Kapil wrote:
>
>> global size;
>> global times;
>>
However, the same code when I tried to run in my original codebase is not
leading to performance improvement.
I have updated the code and will try to find out what could be the problem.
ᐧ
Thanks !
Kapil Agarwal
[i]=a[i]
end
end
ᐧ
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 1:16 PM, Stefan Karpinski
wrote:
> No, it's the non-constant globals although JIT compilation is also an
> issue.
>
> On Sat, Nov 1, 2014 at 1:15 PM, Kapil wrote:
>
>> okay, I think this is because ju
okay, I think this is because julia will first compile the code and so the
performance is slow, subsequent runs would give improved performance
ᐧ
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 1:10 PM, Kapil wrote:
> The updated code is available at
> https://github.com/kap
seconds.
ᐧ
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 12:36 PM, Jason Merrill wrote:
> On Saturday, November 1, 2014 9:35:03 AM UTC-7, Jason Merrill wrote:
>>
>> On Saturday, November 1, 2014 9:15:43 AM UTC-7, Kapil Agarwal wrote:
>>>
>>> I need those variable
em as
arguments each time ? That is very cumbersome.
For multiple processes, I am in fact using DArrays, and I am unaware how
IPC takes place in Julia, but there is there an efficient way in Julia for
the same ?
Regards,
Kapil Agarwal
On Sat, Nov 1, 2014 at 11:42 AM, Stefan Karpinski
wrote:
>
What could be the reason behind this ? Could this be a problem in my
implementation or is this just the way Julia is implemented ?
Thanks
--
Kapil
So, the followup question is why is it that currently, multiple instances
of julia cannot be started ?
ᐧ
Regards,
Kapil Agarwal
On Wed, Oct 29, 2014 at 3:27 PM, Stefan Karpinski
wrote:
> NFS is kind of a nightmare for many reasons but it is standard on
> clusters, so my advice wasn&#x
What do you mean by that ?
Actually I am running it on a remote machine in a cluster.
ᐧ
Regards,
Kapil Agarwal
On Wed, Oct 29, 2014 at 3:16 PM, Stefan Karpinski
wrote:
> Don't use NFS ;-)
>
> On Wed, Oct 29, 2014 at 2:44 PM, Kapil Agarwal
> wrote:
>
>> Hi
>>
&
unable to delete this file as it says
rm: cannot remove `.nfs0ba780820191': Device or resource busy
What should be done about this ?
--
Kapil
age 0.029588 seconds. Is Julia that
much faster than C ?
--
Kapil
Oh okay. In that case, shouldn't an error be generated at compile time ?
ᐧ
Regards,
Kapil Agarwal
On Tue, Oct 28, 2014 at 10:02 PM, Andreas Noack <
andreasnoackjen...@gmail.com> wrote:
> times[1] is the first element of the matrix times. Hence, then writing
> times[1][1]
ERROR: `setindex!` has no method matching setindex!(::Float64, ::Float64,
::Int64)
What could be the problem ?
Kapil
IN)
in _jl_spawn at process.jl:217
in spawn at process.jl:348
in open at ./process.jl:397
in launch_local_workers at multi.jl:1136
in start_cluster_workers at multi.jl:1004
in addprocs at multi.jl:1237
Kapil
ption on exception on exception
on exception on exception on exception on exception on exception on
exception on exception on exception on exception on exception on exception
on exception on WARNING: Unable to terminate all workers
What could be the issue ?
Regards,
Kapil Agarwal
_start at ./client.jl:354
in _start_3B_1715 at
/nethome/kagarwal39/julia-0.3.1/julia/usr/bin/../lib/julia/sys.so
while loading /nethome/kagarwal39/HPPCProject/temp/ex2.jl, in expression
starting on line 12
ᐧ
Regards,
Kapil Agarwal
.
ᐧ
Regards,
Kapil Agarwal
On Fri, Oct 17, 2014 at 11:35 PM, Iain Dunning
wrote:
> Its definitely one of the least-documented-by-example parts of Julia,
> partly because its inherently complicated to make a realistic workload that
> doesn't require too much background knowledge. You
Yeah, I've seen that too.
If there aren't any else, I assume that not many people have experimented
with parallel Julia.
I am actually looking to write some parallel benchmarks using Julia, which
if successful, can be included then.
ᐧ
Regards,
Kapil Agarwal
On Fri, Oct 17, 2014 a
Still, are there any resources other than the documentation to learn what
all can be done for parallel computing in julia ?
ᐧ
Regards,
Kapil Agarwal
On Fri, Oct 17, 2014 at 10:42 PM, Isaiah Norton
wrote:
> The recommended version right now for most users is 0.3, for this reason.
> 0.4 i
other tutorials.
Kapil
Hi
Anybody have any ideas regarding PBS support in Julia, so that I can move
in the correct direction ? I have a PBS managed cluster and I wish to start
Julia parallel programs using 'qsub
Does Julia cluster managers have any support for PBS managed cluster yet ?
ClusterManagers.jl has a comment "PBS doesn't have the same semantics as
SGE wrt to file accumulate, a different solution will have to be found".
ᐧ
Regards,
Kapil Agarwal
On Mon, Oct 13, 2014 at 6:43 P
I installed Julia, is it not included with Julia ?
ᐧ
Regards,
Kapil Agarwal
On Mon, Oct 13, 2014 at 6:42 PM, Stefan Karpinski <
stefan.karpin...@gmail.com> wrote:
> Did you install the package?
>
>
> On Oct 13, 2014, at 6:38 PM, Kapil wrote:
>
> ᐧ
> Also, I get th
ᐧ
Also, I get the following error
julia> import ClusterManagers
ERROR: ClusterManagers not found
in require at ./loading.jl:49
in require_3B_3951 at /nethome/kagarwal39/julia/usr/bin/../lib/julia/sys.so
Can you tell what am I doing wrong here ?
On Mon, Oct 13, 2014 at 6:33 PM, Kapil Agar
default queue has a 1h limit in our
> setup).
>
> ---david
>
> On Saturday, October 11, 2014 7:05:15 PM UTC+2, Isaiah wrote:
>>
>> Have you tried ClusterManagers? It appears to have qsub support:
>> https://github.com/JuliaLang/ClusterManagers.jl/blob/master/src
. Please delete or regenerate
sys.{so,dll,dylib}.
What could be the problem ? Do I need to manually install Julia on each
node ? What if there are are hundreds of nodes ?
Regards,
Kapil
Hi
I am using a cluster in which jobs are started on remote nodes are using
qsub.
How can I add these nodes while running Julia from the head node ?
Also, each node has multiple cores, so I need to make use of those cores as
well.
Regards,
Kapil Agarwal
ᐧ
Okay, I'll use the official documentation. The link is on julialang.org, so
I thought it was a tutorial accepted by the julia-dev.
ᐧ
Regards,
Kapil Agarwal
On Sat, Oct 11, 2014 at 12:27 PM, Andreas Noack <
andreasnoackjen...@gmail.com> wrote:
> You'll have to fetch the re
run_work_thunk at multi.jl:601
in anonymous at task.jl:6
What could be the problem ?
ᐧ
Regards,
Kapil Agarwal
On Sat, Oct 11, 2014 at 12:20 PM, Kapil wrote:
> Okay,
> I went to this link
> http://www.admin-magazine.com/HPC/Articles/Parallel-Julia-Jumping-Right-In
> which is listed
Okay,
I went to this link
http://www.admin-magazine.com/HPC/Articles/Parallel-Julia-Jumping-Right-In
which is listed in the Julia learning resources where it is written as
remote_call.
Maybe the link should be fixed.
ᐧ
Regards,
Kapil Agarwal
On Sat, Oct 11, 2014 at 12:18 PM, Andreas Noack
Hi
I started Julia with 'julia -q -p 2' and then ran 'r = remote_call(2, +, 2,
2)' and I get 'ERROR: remote_call not defined'.
Please help me solve the issue.
I am using a machine with 16 cores.
Kapil
Hi
Anyone has any ideas about this? And will this affect any further
development using julia?
On Oct 2, 2014 12:22 PM, "Kapil" wrote:
> I get the following output
>
> julia> addprocs(1)
> 1-element Array{Int64,1}:
> 2
>
> ᐧ
>
> Regards,
> Kapil
I get the following output
julia> addprocs(1)
1-element Array{Int64,1}:
2
ᐧ
Regards,
Kapil Agarwal
On Thu, Oct 2, 2014 at 12:21 PM, Elliot Saba wrote:
> Hmmm. Looks like there's a problem with pthreads? What happens if you
> type addprocs(1)?
> On Oct 2, 2014 8:30 A
The errors are the same as the ones I had sent in a text file two mails
earlier. Still, I have attached the file again.
ᐧ
Regards,
Kapil Agarwal
On Thu, Oct 2, 2014 at 11:26 AM, Stefan Karpinski <
stefan.karpin...@gmail.com> wrote:
> Please send error output as text rather than images.
Yes, the julia interpreter starts with ./julia
ᐧ
Regards,
Kapil Agarwal
On Thu, Oct 2, 2014 at 2:23 AM, Elliot Saba wrote:
> Can you start julia normally? E.g. can you run `./julia` and get a REPL?
> -E
>
Hi
After installing Julia, I ran 'make testall' but it gave me errors. I have
attached the file containing errors.
How can this be fixed ?
Kapil
[32;1mJULIA[0m [37;1mtest/all[0m
signal (6): Aborted
gsignal at /lib64/libc.so.6 (unknown line)
abort at /lib64/libc.so.6 (un
.
Another thing that I was thinking was implementing the benchmark tests
at http://icl.cs.utk.edu/hpcc/ in Julia in parallel. Would that be a good
project and beneficial to the Julia community ?
Regards,
Kapil
to benchmark highly parallel
applications with Julia.
Actually, I am looking at Julia for a college project and have access to a
HPC cluster and am thinking to implement graph algorithms. I would
appreciate if you could give me some suggestions on my idea.
Thanks
Kapil
>
> > On Monday,
done
by the julia-dev team or in case any one is aware of any such benchmarks
that could help me go about it.
Thanks
Kapil
47 matches
Mail list logo
