Afficher la pageAnciennes révisionsHaut de page Cette page est en lecture seule. Vous pouvez afficher le texte source, mais ne pourrez pas le modifier. Contactez votre administrateur si vous pensez qu'il s'agit d'une erreur. ====== Using GPU in MATLAB ====== In this lab, we will use GPUs with MATLAB to run fftw calculations. First of all we use the parallel toolbox directly from matlab. Then we use the Matlab compiler to stop consuming tokens (only one token is available for the parallel toolbox). This simple example will be used: <file matlab fftgpu.m> function fftgpu() Nx=1024; Ny=1024; [x,y]=ndgrid(-Nx/2:Nx/2-1,-Ny/2:Ny/2-1); r=x+1i*y; ph=angle(r); r=abs(r); gpu=gpuDevice(); tic; % init m in GPU m=gpuArray(double(exp(-(r/64).^2))); % run FFT on GPU m=fftshift(fft(m)); % gather m from GPU to CPU toc; m=gather(m); % save matrix save('saveM.mat','m'); exit(); end </file> <note tip>Notice that the code is enclosed in function to be able to use the matlab compiler later</note> ===== Using Matlab directly ===== **prerequisites** * Matlab 2017b * Cuda 8 Here is the SGE script: <file bash fftmatlab1.sge> #!/bin/bash -l #$ -N fft_matlabGPU #$ -o $JOB_NAME.$JOB_ID.out #$ -q tesla.q ## request tesla #$ -l h_vmem=20G ## we request more because of Java module load gpu/cuda/8.0 module load matlab/r2017b matlab -nodisplay -r "fftgpu" </file> submit the job with: <code bash> $ qsub fftmatlab1.sge </code> ===== Using Matlab compiler ===== We use compiler to avoid using parallel tokens ( 1 token available!) MATLAB compiler will generate executable and scripts files in the same directory. here is the SGE script: <file bash fftmatlab2.sge> #!/bin/bash -l #$ -N fft_matlabGPUCompiler #$ -o $JOB_NAME.$JOB_ID.out #$ -q tesla.q ## request tesla #$ -l h_vmem=20G ## we request more because of Java module load gpu/cuda/8.0 module load matlab/r2017b mcc -m fftgpu.m ./run_fftgpu.sh $MATLAB_HOME </file> submit the job with: <code bash> $ qsub fftmatlab2.sge </code> perf/matlabgpu.txt Dernière modification : 2019/07/08 12:30de admin