Respondida
How to pass on a different sized matrix through GPU Arrayfun
Unfortunately, you cannot pass cell arrays to the GPU. What you might be able to do is instead use a nested function handle to p...

más de 12 años hace | 1

Respondida
Large broadcast variable in parfor loop
Unfortunately, because PARFOR supports operation across multiple machines and uses multiple MATLAB processes, I'm afraid there's...

más de 12 años hace | 0

| aceptada

Respondida
How can I modify this code to use parfor s=1:r?
You could try something like this r=20; n=2; m=3; D=unidrnd(20,8,2); upp=zeros(size(D,1),r,n); for j=1:n...

más de 12 años hace | 0

| aceptada

Respondida
Parfor Indexing -- Basic question
Here are two ways you could address this. Firstly, using concatenation: B1 = []; parfor idx = 1:1000 x = rand(); ...

más de 12 años hace | 2

Respondida
adapting pattersearch algorithm to use with distributed computing server.
Firstly, you need to set up a parallel configuration to allow Parallel Computing Toolbox to talk to your PBS cluster. You may ne...

más de 12 años hace | 1

| aceptada

Respondida
How can I modify this nested loop to work as a parfor without requiring a ridiculously large array?
Does it work to do something like this: prop = zeros(1, N); parfor ... ... tmp = zeros(1, N); tmp(h...

casi 13 años hace | 2

Respondida
Setting default priority for matlabpool processes
I assume you're running on windows - you could try using this file exchange submission: <http://www.mathworks.com/matlabcentral/...

casi 13 años hace | 0

Respondida
A Problem with matlabpool
That looks like somehow your installation has become corrupted. You probably need to reinstall.

casi 13 años hace | 2

Respondida
Why is parfor so slow?
Firstly, I assume you meant to put a PARFOR loop in your example code for the 1:N loop. The reason you are not seeing any speedu...

casi 13 años hace | 1

Respondida
How can I run two code blocks in parallel?
An alternative to BATCH might be SPMD. You could do something like this: spmd(2) if labindex == 1 % do first th...

casi 13 años hace | 0

Respondida
Can MATLAB work well and paralellize code with AMD Radeon HD 7670m graphics card ?
Currently, the gpuArray support in Parallel Computing Toolbox supports only NVIDIA GPU devices of compute capability 1.3 or grea...

casi 13 años hace | 2

Respondida
MEX memory leak - is this a bug?
It appears as though there's a problem with mxGPUCopyFromMxArray. Please could you try the following workaround: /** * ...

casi 13 años hace | 0

| aceptada

Respondida
MEX memory leak - is this a bug?
I think this is nothing to do with the MEX interface, and instead to do with the way MATLAB tries to recycle memory allocations ...

casi 13 años hace | 0

Respondida
parfor schedule not very smart?
The PARFOR scheduler divides loop iterations up in a fixed way to try and achieve a good balance for 'normal' workloads. In part...

casi 13 años hace | 0

Respondida
parfor for double iteration??
Unfortunately, PARFOR doesn't understand how you're accessing 'G' even though you are using it in an order-independent way. What...

casi 13 años hace | 0

| aceptada

Respondida
How does the client send data to the workes, when calling parfor?
A and B are sent once to each worker at the start of the PARFOR loop. There are certainly cases where the data transfer time dom...

casi 13 años hace | 2

| aceptada

Respondida
Assignin in parfor loop
When you run your code at the command-line, all of the FOR loop body is run in the base workspace - whereas the PARFOR body is n...

casi 13 años hace | 1

Respondida
multi-core CPU to DCS
The main difference that you might find when running your code on a remote MDCS cluster is that the workers must be able to acce...

casi 13 años hace | 1

Respondida
spmd inside parfor loop
All available parallelism is used up by the outermost PARFOR/SPMD, so there is no possible benefit to nesting these constructs. ...

casi 13 años hace | 0

Respondida
Parfor function for numerical simulations
You might need to extract the columns of E1 etc. before working on them. For example parfor colIdx = 1:numColumns ...

casi 13 años hace | 0

Respondida
Error using matlabpool _ Failed to open matlabpool
As the error message suggests, you need to set the NumWorkers property of the cluster to some finite value (i.e. the number of w...

casi 13 años hace | 0

Respondida
Can't find GPU in LAN
You need to install the CUDA driver on the worker machines. Once this is done, you should be able to use gpuArray and gpuDevice ...

casi 13 años hace | 0

Respondida
parfor question with 40 nodes
If you manually divide your problem and submit many independent tasks, you will probably see a slight improvement in the amount ...

alrededor de 13 años hace | 0

Respondida
How to use MDCS with a Torque based cluster
It seems that you are making reasonable progress towards getting things working. We are always happy to hear about suggestions f...

alrededor de 13 años hace | 1

| aceptada

Respondida
Definitive answer for hyperthreading and the Parallel Computing Toolbox (PCT)?
By default, MATLAB and Parallel Computing Toolbox consider only real cores, not hyperthreaded cores. You can override this ch...

alrededor de 13 años hace | 8

| aceptada

Respondida
How can i read data from a text file with parfor or spmd .i have to read as two workers and to combine the result lastly.please reply soon..
Something like this? spmd fh = fopen(sprintf('file_%d.txt', labindex), 'rt'); data = fscanf(fh, '%f'); fclos...

alrededor de 13 años hace | 0

Respondida
mvnrnd bug when run in parfor?
As Shashank points out, this is expected behaviour. Matlabpool workers have their random number generators set up carefully at t...

alrededor de 13 años hace | 0

Respondida
parfor with sliced and reduction variable
You could try something like this so that you're updating whole columns of newc_left and newc_right: numRows = size(oldc, 1...

alrededor de 13 años hace | 1

| aceptada

Respondida
I am having problem implementing parfor
Generally, it's best to have the PARFOR loop at the highest level possible because there's an overhead to running each PARFOR lo...

alrededor de 13 años hace | 0

Respondida
How to execute fft's with gpu,cuda in parallel (spmd)?
MATLAB's FFT function can operate along any single dimension. So you can simply do: data_device = fft(data_device, [], 3); ...

alrededor de 13 años hace | 1

| aceptada