Questions tagged [parallelization]

Questions on parallel computing in Mathematica.

215 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
1
vote
0answers
107 views

Simplify Vs FullSimplify

I performed an integral and received an extremely long answer. I tried running FullSimplify on the answer, and after 72 hours gave up. Does ...
1
vote
0answers
25 views

Parallelization option gives Import error for Package files

I have an issue when trying to use parallelization when loading a stand-alone Package. To simplify the question I have a few scenarios: The first scenario, with single-kernel evaluation, works fine: ...
1
vote
0answers
27 views

How to close a specific Kernel after completion of evaluation in ParallelDo

I have a particular code that I have to run over several different parameters. I am using ParallelDo to parallelize the process. Due to the nature of the evaluations some Kernels finish the ...
1
vote
0answers
28 views

ParalleTable can't use 100% CPU

I have two notebook. A.nb and B.nb. When I run the ParalleTable in A.nb, it will use 100% CPU. But I change some items in A.nb to get B.nb. When I run B.nb, it only used 50% CPU. I can't find the ...
1
vote
0answers
67 views

Faster methods for performing repeated list manipulations?

I've done my best to pore over the other posts on this site, and to the best of my ability I can't seem to find a good solution to my problem, so I apologize in advance if elements of my question are ...
1
vote
0answers
44 views

How to use Reap and Sow with ParallelDo

Consider the two cases: ...
1
vote
1answer
54 views

Monitoring Parallel Processes

I have a problem where my For loop will not get rid of my PrintTemporary monitor, and it means I end up with loads and loads of ...
1
vote
0answers
48 views

Is it possible to generate iterators dynamically during parallel processing?

I have a parallel processing code written in Wolfram Mathematica, similar to: ...
1
vote
0answers
181 views

How to use Mathematica with Slurm?

We have a cluster that uses Slurm. On each node we have put a license that allows for 128 computation kernels (we have a Mathematica for Sites License). How can we run Mathematica on more than one ...
1
vote
0answers
31 views

Having trouble distributing a large association to sub-kernels

The following seems to work based on memory usage. ...
1
vote
0answers
82 views

How can I devote all the cores to Mathematica?

I have a problem with the calculations speeds in xAct package. In fact, some of them take lots of seconds. Is there any way to speed up the calculations by engaging all the cores for Mathematica (or ...
1
vote
0answers
68 views

Write in ParallelTable

Why does ...
1
vote
0answers
69 views

Conversion of STL files to 3D Images

I am trying to convert some stl files to 3d images in MMA 11.3. I came across this post that contained some code making use of parallelization to speed up the process, as follows: ...
1
vote
0answers
47 views

How badly does switching kernel slow down or completely stop Mathematica running jobs?

I have a question on how to run two or more Mathematica jobs on one laptop. For example, I use a local kernel to run a job. Then I open another job and choose Kernel configuration option and choose ...
1
vote
0answers
50 views

Clustering different kernel versions

After a good bit of trial and error I have managed to cluster together two OS X machines. The master is running Mathematica 9.0 and the secondary 11.0. All was well and good, the remote command being ...
1
vote
0answers
114 views

WSTP with an MPI application

I'm looking to use WSTP to make functions defined in a C MPI application available to a remote Mathematica kernel. I've got this working for a non-MPI version of the application, but now wish to have ...
1
vote
0answers
52 views

Launching All Unoccupied Threads as Kernels [CPU Usage Assessment with Mathematica]

I'm working on a PC with 10 processor cores (20 threads), so it can support 20 concurrent computations. I often run simulations in the background on my PC such that some fraction of these, say 12, ...
1
vote
0answers
41 views

Can't open setting of Parallel Kernel Configuration on Mac and Windows after configuring remote kernels

In Mathematica 11.3 on Mac and Windows. Once I've set up the connection with gridMathemtaica's remote kernels. Then I close those machines/kernels and restart my Mathematica. When I click the ...
1
vote
0answers
17 views

ClearAttributes in ParallelDo

The following code ClearAttributes[Times, Orderless]; temp = b*a; Do[ Print[temp];, {i, 1} ] will print b*a However, the ...
1
vote
0answers
53 views

How can I launch GenerateDocument with a template file on multiple kernels in a batch fashion?

I am trying to do automated testing of my MMA package by launching test cases that are generated on-the-fly with GenerateDocument and a template document, and then evaluated with NotebookEvaluate. I ...
1
vote
0answers
131 views

Parallelizing NDSolve and Parareal method

I found this video on Youtube outlining a method for Parallelizing NDSolve https://www.youtube.com/watch?v=6TiO3nRWZ_U. Does anyone know what the current update is on this? I tried to implement in ...
1
vote
0answers
52 views

Why is this parallel notebook not maxing out the available memory and processors?

I've searched many questions about parallel processing here, and they are either specialized or over my head. I run the following parallel notebook on an 8 core EC2 instance. The average memory usage ...
1
vote
0answers
162 views

Memory use for large computation

I am running a "big" program on my 32G RAM laptop. When MMA is running, roughly there is about 28G RAM "available" to use. So I did a bit of a test. ...
1
vote
0answers
107 views

ParallelTable[ParallelTable] vs Table[ParallelTable]: inexplicable differences & nonlinear scaling in computation time

I have something that looks a lot like the following: ...
1
vote
0answers
89 views

How can I optimize this Parallel Map Monitor's code?

I want to know how many tasks each kernel has accomplished with the monitor. My Attemption: ...
1
vote
0answers
86 views

Parallel evaluation of MATLINK

I have to use MATLINK to connect to MATLAB to run some programs. Variables can be get using MGet and assigned to a variable using ...
1
vote
0answers
91 views

Parallel execution in $2 \times 4$ kernels

Let's say I have 8 CPUs available on a single node. I want to run two instances of the same script (from command line with wolframscript in args > out &) on that node in parallel. Is there a way ...
1
vote
0answers
61 views

Access to a specific subkernel

Say I want to distribute a task in the following way on the available subkernels: ...
1
vote
0answers
105 views

Parallel matrix inversion with gridMathematica

I'm trying to test parallel symbolic matrix inversion on cluster with gridMathematica 7.0 for Linux x86 (64-bit) (February 18, 2009). I use next commands: ...
1
vote
0answers
46 views

Trouble parallellising on HPC

I'm trying to carry out a parallel computation using Mathematica's inbuilt parallel functions, ParallelTable, etc. The problem is that the HPC doesn't seem to like ...
1
vote
0answers
154 views

Parallelization of Monte Carlo numerical integration

I'm trying to parallelize some integral. What I do: I define integrand: ...
1
vote
0answers
79 views

Finding the best way to try `Parallelize` a code

Consider a code like ...
1
vote
0answers
178 views

Keep kernels alive in parallel evaluations of several scripts

I have written a parallel script file that after initializing the kernels it puts the result of some computation in a file. I provide some external parameters to the script. I would like to run the ...
1
vote
0answers
65 views

Using NearestFunction in ParallelMap: why the slowdown?

Intro I am trying to do various calculations (call some Analyze[point, neighbourhood] function) over the large datasets of points in 2D space. The nature of the calculations is irrelevant, but basic ...
1
vote
0answers
67 views

ParallelSum faster… if I don't load my own Package

I have a big sum to compute. I remarked that if I load my package, the parallelisation is as slow as the "non" parallelisation. Whereas, when I don't load it, the parallelisation is faster. The ...
1
vote
0answers
111 views

Updating “Parallel Kernel Status” window during evaluation

I really like the "Parallel Kernel Status" window for monitoring my parallel kernels. However, as long as a cell is evaluating, it is almost not updated (only the red and green circles that show ...
1
vote
0answers
45 views

Parallel number systems don't scale well

I'm working on Residue Number System. This is basically a set of relatively coprime integers, let's say $\{3,4,5\}$ and we define its range to be the product of the moduli, i.e. $M=3\cdot4\cdot5=60$. ...
1
vote
0answers
93 views

Mathematica using all available cores, but not speeding up calculation as much as expected

This is a follow-up question to my previously posted question on how to get Mathematica to use all available cores to do a parallel calculation. I resolved this by rewriting the code in terms of a <...
1
vote
0answers
74 views

Wolfram cdf player does not support parallel computing?

I tested the following. ...
1
vote
0answers
140 views

How to make use of multi cores on a single node of supercomputer 'Stampede'

I am using Mathematica 10.4 in GUI mode on stampede supercomputer. I am using a single node on this machine and each node has two 8 core chips. Whenever I try to parallelize my code on 16 cores(using ...
1
vote
0answers
80 views

Functions, strings and ToExpression in ParallelDo

I have defined functions: ...
1
vote
0answers
61 views

Parrallelize unrelated expressions: how to solve transcendental equation by finding roots in parts of the interval simutaneously

The goal is to find all the roots of a transcendental equation. I copy a function from stackexchange: ...
1
vote
0answers
50 views

ParallelDo only output one file using $KernelID

I have some codes like this: ...
1
vote
0answers
41 views

How can I distribute redefinitions of system functions to parallel kernels?

I'm having some trouble getting my parallel kernels to get wind of user redefinitions of system packages, and I'm looking for the cleanest way to do this - preferably using DistributeDefinitions. To ...
1
vote
0answers
61 views

Launching specific remote kernels in parallel

For some reason I found that my numerical integration runs much faster on Mathematica 9 than on Mathematica 10. Since I sent my calculation to a cluster with 24 cores with the following command <...
1
vote
0answers
86 views

Can parallelization speed up FindClusters?

I have a clustering task that would take FindClusters 2-3 months1 to complete. Can this calculation be sped up with parallelization? (FWIW, the data to be ...
1
vote
0answers
33 views

Make an existing solution for monitoring parallel jobs robust against dying kernels

Is there any chance to make the solution by @David here https://mathematica.stackexchange.com/a/1562/21606 more robust in the following sense: In my case, some parallel kernels die regularly during ...
1
vote
0answers
99 views

ParallelTable gets slower when rerun in a module

Question: Why does the performance of ParallelTable within a Module drop so horribly when the module is RERUN several times? ...
1
vote
0answers
91 views

Distribute Definitions to different Evaluator

I would like to pass on a definition from one Kernel to the other. With that I mean manually configured Kernels. In this case, I do not want to use the inbuilt Parallelization options, in order to ...
1
vote
0answers
160 views

The module load only works for the first node, not all. Is there's a way to specify the full path to the math command when launching remote kernels

Running a Mathematica .m file in cluster for parallel computing. But get an error "bash: math: command not found". Is there's a way to specify the full path to the ...