Questions on parallel computing in Mathematica.

learn more… | top users | synonyms

7
votes
0answers
2k views

Threads vs Cores: How many kernels need to launch in parallel Mathematica?

I have a dual-core intel machine. I would like to test how many parallel local kernels should be launch to get the optimized performance. Knowing that the HyperThreading technology of Intel could run ...
5
votes
0answers
64 views

The change of precision doesn't work in ParallelDo. Is it a bug in Parallel?

Cross-post: http://zhidao.baidu.com/question/2075301703219376588.html Input: ...
5
votes
0answers
304 views

Mathematica + RasPi + Parallela = Kaboom?

Is it possible to use the Parallela computing platform to enhance Mathematica computing on a Raspberry Pi? It's not at all clear to me how to interface the two boards (here it says it's done via ...
5
votes
0answers
234 views

Discriminant of Characteristic Polynomial

I'm doing a calculation which finds the characteristic polynomial of a matrix with rather complex entries and then determines the discriminant of that polynomial. For smaller matrices up to around 7x7 ...
5
votes
0answers
323 views

Parallelizing is much slower than single kernel evaluation?

Starting with a vector of matrices, tVec, I would like to parallelize the multiplication of each element with the same matrix ...
5
votes
0answers
183 views

Raster with ColorFunction is blank when Dynamic Updating is disabled

UPDATE Today I was having these WaveletScalogram problems again. I think this is ultimately some kind of interaction issue with Dynamic. I have narrowed it down to ...
4
votes
0answers
59 views

Problem with Parallelization when using Packages

I tried to find a solution to my problem in several answers posted in MSE but due to lack of my knowledge on parallelization territory, I couldn't figure out solution to my problem. I have a big code ...
4
votes
0answers
39 views

Is there a clean way to parallelize multi-index tables?

The documentation of ParallelTable indicates that if you want to parallelize the evaluation of a table of more than one dimension, such as ...
4
votes
0answers
77 views

ParallelTable slow down, Region functions

I am experiencing speed issues with ParallelTable. There are a few related problems on SX posted here and here, but no resolution. The various respondents to those ...
4
votes
0answers
83 views

Improving the speed of an optimization algorithm via compilation and parallellization

I have written an implementation of eight variants of the PSO-algorithm and I want to test them over a set of test functions. I am using parallelization as it improves the speed a lot and I have also, ...
4
votes
0answers
80 views

Smart use of ParallelMap over Plus

I'm looking for ways to speed up calculation of a integral with a many-terms integrant. The obvious way is to go in parallel. I was surprised, but for some tests integration by ...
4
votes
0answers
331 views

OpenCL vs. CUDA with Mathematica

I am thinking about using GPU programming with Mathematica using a MacBook Pro with a NVIDIA GPU. At this page, the Mathematica documentation says "Programming OpenCL in the Wolfram Language is simple ...
4
votes
0answers
292 views

How to force the compilation language to be C++ (not C) in CreateExecutable or CreateLibrary

I'm trying to speed up a section of a Mathematica 9.0.1 notebook by performing some calculations in C++ with the Cilk Plus and Threading Building Blocks tools available for the Intel C++ 14.0 compiler ...
4
votes
0answers
117 views

LibraryLink parallel performance

I'm trying to use a LibraryLink function in parallel. It is an embarrassingly parallel problem, so that no dependency between those parallel tasks. However I can only get the parallel efficiency about ...
4
votes
0answers
400 views

To what extent can NonlinearModelFit be sped up?

Can NonlinearModelFit be parallelized or compiled to allow one to achieve a scalable speedup for a fitting procedure? Attempting to use this function to fit a ...
4
votes
0answers
132 views

How can you link Parallel Mapping and Error tracking

Following this question and the comments made, together with the information in this question, the following code allows error tracking and debugging very nicely. ...
3
votes
0answers
29 views

Where do DistributeDefinitions and ParallelNeeds put their definitions for newly-launched kernels to find

I'm sorry to keep banging on the definition distribution bell, but here is another (hopefully well-focused enough) question on that vein. If one is trying to distribute the definitions in a package ...
3
votes
0answers
57 views

Why is a LibraryLink function, which returns a list, not parallelizing with ParallelTable?

First example: librarylink function return a list of two element ...
3
votes
0answers
151 views

Parallel Kernels and Hyperthreading

I am using Eigenvalues a large number of times on a machine with 8 cores. When I run Eigenvalues one time without any parallel ...
3
votes
0answers
96 views

How to speed up summing a large number of vectors

First let me explain what I am trying to do in my code. Assume that I send a very short chirp (2,000 ms long) into a domain filled with 20,000 particles randomly scattered in the domain. The ...
3
votes
0answers
114 views

AppendTo or Part in a ParallelDo?

I have a question regarding how memory is managed in parallel. Specifically, I'd like to know what is the better practice when constructing an array within a ...
3
votes
0answers
325 views

ParallelTable kernels die - maybe Mathlink timeout?

I am new to parallel computing in Mathematica. I am using LaunchKernels[16] ParallelTable[] to parallelize calculations. The ParallelTable consists of approx ...
3
votes
0answers
83 views

k-means clustering in parallel

How can the k-means algorithm for some given distance function be implemented using ParallelMap or other parallel processing program constructs in Mathematica?
3
votes
0answers
334 views

Death of parallel sub-kernels

EDIT : Finally, the new Mathematica 10.0 seems to fix it. I have a little parallelization problem. I wrote a code to generate a quasicrystal by dynamical generation. Here the code: ...
3
votes
0answers
539 views

Remote kernel shuts down after several seconds

I have Mathematica 9 installed on two Windows Server 2008 R2 machines. Now i want to try using one of them as a frontend with local kernels and the other one for remote kernels. OpenSSH 6.5 for ...
3
votes
0answers
226 views

Launching Remote Kernels takes a lot of time

I recently played around with establishing a remote kernel setup without using mathematica grid. To do this I use the LaunchKernels[] command and ...
3
votes
0answers
241 views

Mathlink and multithreading

In order to make my computations faster I have developed a C/C++ application calling Mathematica kernel and performing many operations using Mathematica functions for equation solving. Now I want to ...
2
votes
0answers
62 views

`ParallelTable` pending the MathKernel after execution

I have done a ParallelTable computation in script mode. After execution, the output is fine and I've got all the data I needed. but the kernel seems pending, ...
2
votes
0answers
119 views

Can equation solving be done in parallel?

I'm solving a set of equations that look like: ...
2
votes
0answers
81 views

Is there a way to specify which kernel is used to import files (SOLVED)?

Following up on a previous question in which I encountered a memory leak in the JSON importer I have created a SandBox script that will run the Import and analysis on a separate kernel, which be ...
2
votes
0answers
114 views

Parallel evaluation of symbolic matrix eigenvalues

I'm trying to find eigenvalues of symbolic hermitian 40x40 block matrix. It is made from 20 2x2 matrices like this: ArrayFlatten[Table[M[m,n],{m,1,20},{n,1,20}]] ...
2
votes
0answers
85 views

Is it possible to automatically apply Parallelize when possible

Parallelize in Mathematica is pretty easy to use. Most of the time, applying Parallelize to an expression, it tries to evaluates ...
2
votes
0answers
81 views

How many kernels to set based on CPU?

Looks like 4 kernels are enough? My CPU is i7 4790K as given here. Does it also depend on the tasks and the codes? My understanding is that regardless what the benchmark says, I could always use ...
2
votes
0answers
55 views

ParallelSubmit and WaitNext: check if a job is done before calling WaitNext

Say I process something with ParallelSubmit: LaunchKernels[] job = ParallelSubmit[1 + 2] Parallel`Developer`QueueRun[] Then, I will use ...
2
votes
0answers
76 views

What was the thought behind the parallel versions of Table, Map, etc..?

There separately named versions of the parallel analogues of Map[] and friends: ...
2
votes
0answers
170 views

Bug in parallel computing

The following is a simplified example. We construct a library function f and another library function g, in which the library function f is called. ...
2
votes
0answers
168 views

Parallel Kernel Status

For parallel computing, the window Parallel Kernel Status shows some information on the subkernels. I can use two kernels, and which each of them I can do parallel computations. However, it seems that ...
2
votes
0answers
41 views

do successive parallel computations require distribute definitions at each intermediate step?

Suppose I am doing a parallel computation, say, using parallel table. I distribute necessary definitions to all kernels. After computation is done, I would like to use the first result in another ...
2
votes
0answers
361 views

ParallelSum in Mathematica 9 vs 10

Here's part of a package I'm working on: ...
2
votes
0answers
115 views

ParallelTable and expensive functions

I would like to build up a 2D-Table using ParallelTable as follows ...
2
votes
0answers
146 views

Whether NIntegrate evaluation is multithreaded or not?

About MultiThread evaluation I am talking about here, see this post I am NIntegrate the function grarm[e, 3, dimension, 1, 1, 0.005]. There is matrix operation in ...
2
votes
0answers
88 views

Setting Up Lightweight Grid On Multiple Clients Programmatically

I have a number of computers which all might need to use the same (client) configuration for the Wolfram Lightweight Grid at some point. I know that there are ways to programmatically set certain ...
2
votes
0answers
137 views

correct usage of ParallelTable

I am trying to parallelize my script. Here is a MWE of how I have done it: ...
1
vote
0answers
37 views

mathematica example for parallel run

I want to run a parallel mathematica example via a PBS script. I am not expert in this application, instead as a system administrator, I have to be sure that users are able to submit parallel jobs to ...
1
vote
0answers
48 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
31 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
99 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 ...
1
vote
0answers
43 views

Inconsistent font rendering when using a remote kernel on a different OS

I have a Mathematica 10.0 on Linux and one on OSX. I'm using the OSX as a remote kernel. During parallel computation, if I render some graphics, the fonts and axes are not rendered the same way ...
1
vote
0answers
97 views

ParallelMap not using all of the available kernels

Please note: I cannot provide the code here, since the project is far too big to post at any Internet forum. I have a computer with eight logical cores. I have Mathematica Version 10.0.2, and I am ...
1
vote
0answers
93 views

Avoid copying memory for each subkernel

Here is a simplified example illustrating my issue; ...